wuggy/Dactyloidae
wuggy/Dactyloidae
1
0
Fork 0
mirror of https://repo.dactyloidae.xyz/Dactyloidae/UXP.git synced 2026-08-15 08:53:07 +09:00
Code Issues Projects Releases Packages Wiki Activity

Issue #1971 - Part 2: Update ICU source to 63.2.

Browse source
This commit is contained in:
Job Bautista 2022-07-24 21:03:27 +08:00 • committed by roytam1
commit 1e69214382
3160 changed files with 275815 additions and 234203 deletions
Download patch file Download diff file Expand all files Collapse all files

115
config/external/icu/common/sources.mozbuild vendored
View file

@ -4,26 +4,28 @@ SOURCES += [
'/intl/icu/source/common/bmpset.cpp',
'/intl/icu/source/common/brkeng.cpp',
'/intl/icu/source/common/brkiter.cpp',
'/intl/icu/source/common/bytesinkutil.cpp',
'/intl/icu/source/common/bytestream.cpp',
'/intl/icu/source/common/bytestrie.cpp',
'/intl/icu/source/common/bytestriebuilder.cpp',
'/intl/icu/source/common/bytestrieiterator.cpp',
'/intl/icu/source/common/caniter.cpp',
'/intl/icu/source/common/characterproperties.cpp',
'/intl/icu/source/common/chariter.cpp',
'/intl/icu/source/common/charstr.cpp',
'/intl/icu/source/common/cmemory.c',
'/intl/icu/source/common/cmemory.cpp',
'/intl/icu/source/common/cstr.cpp',
'/intl/icu/source/common/cstring.c',
'/intl/icu/source/common/cwchar.c',
'/intl/icu/source/common/cstring.cpp',
'/intl/icu/source/common/cwchar.cpp',
'/intl/icu/source/common/dictbe.cpp',
'/intl/icu/source/common/dictionarydata.cpp',
'/intl/icu/source/common/dtintrv.cpp',
'/intl/icu/source/common/edits.cpp',
'/intl/icu/source/common/errorcode.cpp',
'/intl/icu/source/common/filteredbrk.cpp',
'/intl/icu/source/common/filterednormalizer2.cpp',
'/intl/icu/source/common/icudataver.c',
'/intl/icu/source/common/icudataver.cpp',
'/intl/icu/source/common/icuplug.cpp',
'/intl/icu/source/common/listformatter.cpp',
'/intl/icu/source/common/loadednormalizer2impl.cpp',
'/intl/icu/source/common/locavailable.cpp',
'/intl/icu/source/common/locbased.cpp',
@ -31,7 +33,7 @@ SOURCES += [
'/intl/icu/source/common/locdspnm.cpp',
'/intl/icu/source/common/locid.cpp',
'/intl/icu/source/common/loclikely.cpp',
'/intl/icu/source/common/locmap.c',
'/intl/icu/source/common/locmap.cpp',
'/intl/icu/source/common/locresdata.cpp',
'/intl/icu/source/common/locutil.cpp',
'/intl/icu/source/common/messagepattern.cpp',
@ -42,10 +44,11 @@ SOURCES += [
'/intl/icu/source/common/patternprops.cpp',
'/intl/icu/source/common/pluralmap.cpp',
'/intl/icu/source/common/propname.cpp',
'/intl/icu/source/common/propsvec.c',
'/intl/icu/source/common/propsvec.cpp',
'/intl/icu/source/common/punycode.cpp',
'/intl/icu/source/common/putil.cpp',
'/intl/icu/source/common/rbbi.cpp',
'/intl/icu/source/common/rbbi_cache.cpp',
'/intl/icu/source/common/rbbidata.cpp',
'/intl/icu/source/common/rbbinode.cpp',
'/intl/icu/source/common/rbbirb.cpp',
@ -67,68 +70,70 @@ SOURCES += [
'/intl/icu/source/common/servslkf.cpp',
'/intl/icu/source/common/sharedobject.cpp',
'/intl/icu/source/common/simpleformatter.cpp',
'/intl/icu/source/common/static_unicode_sets.cpp',
'/intl/icu/source/common/stringpiece.cpp',
'/intl/icu/source/common/stringtriebuilder.cpp',
'/intl/icu/source/common/uarrsort.c',
'/intl/icu/source/common/ubidi.c',
'/intl/icu/source/common/ubidi_props.c',
'/intl/icu/source/common/ubidiln.c',
'/intl/icu/source/common/ubiditransform.c',
'/intl/icu/source/common/ubidiwrt.c',
'/intl/icu/source/common/uarrsort.cpp',
'/intl/icu/source/common/ubidi.cpp',
'/intl/icu/source/common/ubidi_props.cpp',
'/intl/icu/source/common/ubidiln.cpp',
'/intl/icu/source/common/ubiditransform.cpp',
'/intl/icu/source/common/ubidiwrt.cpp',
'/intl/icu/source/common/ubrk.cpp',
'/intl/icu/source/common/ucase.cpp',
'/intl/icu/source/common/ucasemap.cpp',
'/intl/icu/source/common/ucasemap_titlecase_brkiter.cpp',
'/intl/icu/source/common/ucat.c',
'/intl/icu/source/common/uchar.c',
'/intl/icu/source/common/ucat.cpp',
'/intl/icu/source/common/uchar.cpp',
'/intl/icu/source/common/ucharstrie.cpp',
'/intl/icu/source/common/ucharstriebuilder.cpp',
'/intl/icu/source/common/ucharstrieiterator.cpp',
'/intl/icu/source/common/uchriter.cpp',
'/intl/icu/source/common/ucln_cmn.cpp',
'/intl/icu/source/common/ucmndata.c',
'/intl/icu/source/common/ucnv.c',
'/intl/icu/source/common/ucmndata.cpp',
'/intl/icu/source/common/ucnv.cpp',
'/intl/icu/source/common/ucnv2022.cpp',
'/intl/icu/source/common/ucnv_bld.cpp',
'/intl/icu/source/common/ucnv_cb.c',
'/intl/icu/source/common/ucnv_cnv.c',
'/intl/icu/source/common/ucnv_ct.c',
'/intl/icu/source/common/ucnv_err.c',
'/intl/icu/source/common/ucnv_cb.cpp',
'/intl/icu/source/common/ucnv_cnv.cpp',
'/intl/icu/source/common/ucnv_ct.cpp',
'/intl/icu/source/common/ucnv_err.cpp',
'/intl/icu/source/common/ucnv_ext.cpp',
'/intl/icu/source/common/ucnv_io.cpp',
'/intl/icu/source/common/ucnv_lmb.c',
'/intl/icu/source/common/ucnv_set.c',
'/intl/icu/source/common/ucnv_u16.c',
'/intl/icu/source/common/ucnv_u32.c',
'/intl/icu/source/common/ucnv_u7.c',
'/intl/icu/source/common/ucnv_u8.c',
'/intl/icu/source/common/ucnv_lmb.cpp',
'/intl/icu/source/common/ucnv_set.cpp',
'/intl/icu/source/common/ucnv_u16.cpp',
'/intl/icu/source/common/ucnv_u32.cpp',
'/intl/icu/source/common/ucnv_u7.cpp',
'/intl/icu/source/common/ucnv_u8.cpp',
'/intl/icu/source/common/ucnvbocu.cpp',
'/intl/icu/source/common/ucnvdisp.c',
'/intl/icu/source/common/ucnvhz.c',
'/intl/icu/source/common/ucnvisci.c',
'/intl/icu/source/common/ucnvlat1.c',
'/intl/icu/source/common/ucnvdisp.cpp',
'/intl/icu/source/common/ucnvhz.cpp',
'/intl/icu/source/common/ucnvisci.cpp',
'/intl/icu/source/common/ucnvlat1.cpp',
'/intl/icu/source/common/ucnvmbcs.cpp',
'/intl/icu/source/common/ucnvscsu.c',
'/intl/icu/source/common/ucnvscsu.cpp',
'/intl/icu/source/common/ucnvsel.cpp',
'/intl/icu/source/common/ucol_swp.cpp',
'/intl/icu/source/common/ucptrie.cpp',
'/intl/icu/source/common/ucurr.cpp',
'/intl/icu/source/common/udata.cpp',
'/intl/icu/source/common/udatamem.c',
'/intl/icu/source/common/udataswp.c',
'/intl/icu/source/common/uenum.c',
'/intl/icu/source/common/uhash.c',
'/intl/icu/source/common/udatamem.cpp',
'/intl/icu/source/common/udataswp.cpp',
'/intl/icu/source/common/uenum.cpp',
'/intl/icu/source/common/uhash.cpp',
'/intl/icu/source/common/uhash_us.cpp',
'/intl/icu/source/common/uidna.cpp',
'/intl/icu/source/common/uinit.cpp',
'/intl/icu/source/common/uinvchar.c',
'/intl/icu/source/common/uinvchar.cpp',
'/intl/icu/source/common/uiter.cpp',
'/intl/icu/source/common/ulist.c',
'/intl/icu/source/common/ulistformatter.cpp',
'/intl/icu/source/common/ulist.cpp',
'/intl/icu/source/common/uloc.cpp',
'/intl/icu/source/common/uloc_keytype.cpp',
'/intl/icu/source/common/uloc_tag.c',
'/intl/icu/source/common/umapfile.c',
'/intl/icu/source/common/umath.c',
'/intl/icu/source/common/uloc_tag.cpp',
'/intl/icu/source/common/umapfile.cpp',
'/intl/icu/source/common/umath.cpp',
'/intl/icu/source/common/umutablecptrie.cpp',
'/intl/icu/source/common/umutex.cpp',
'/intl/icu/source/common/unames.cpp',
'/intl/icu/source/common/unifiedcache.cpp',
@ -148,11 +153,11 @@ SOURCES += [
'/intl/icu/source/common/unormcmp.cpp',
'/intl/icu/source/common/uobject.cpp',
'/intl/icu/source/common/uprops.cpp',
'/intl/icu/source/common/ures_cnv.c',
'/intl/icu/source/common/ures_cnv.cpp',
'/intl/icu/source/common/uresbund.cpp',
'/intl/icu/source/common/uresdata.cpp',
'/intl/icu/source/common/usc_impl.c',
'/intl/icu/source/common/uscript.c',
'/intl/icu/source/common/usc_impl.cpp',
'/intl/icu/source/common/uscript.cpp',
'/intl/icu/source/common/uscript_props.cpp',
'/intl/icu/source/common/uset.cpp',
'/intl/icu/source/common/uset_props.cpp',
@ -166,23 +171,24 @@ SOURCES += [
'/intl/icu/source/common/ustrcase.cpp',
'/intl/icu/source/common/ustrcase_locale.cpp',
'/intl/icu/source/common/ustrenum.cpp',
'/intl/icu/source/common/ustrfmt.c',
'/intl/icu/source/common/ustrfmt.cpp',
'/intl/icu/source/common/ustring.cpp',
'/intl/icu/source/common/ustrtrns.cpp',
'/intl/icu/source/common/utext.cpp',
'/intl/icu/source/common/utf_impl.c',
'/intl/icu/source/common/utf_impl.cpp',
'/intl/icu/source/common/util.cpp',
'/intl/icu/source/common/util_props.cpp',
'/intl/icu/source/common/utrace.c',
'/intl/icu/source/common/utrace.cpp',
'/intl/icu/source/common/utrie.cpp',
'/intl/icu/source/common/utrie2.cpp',
'/intl/icu/source/common/utrie2_builder.cpp',
'/intl/icu/source/common/utrie_swap.cpp',
'/intl/icu/source/common/uts46.cpp',
'/intl/icu/source/common/utypes.c',
'/intl/icu/source/common/utypes.cpp',
'/intl/icu/source/common/uvector.cpp',
'/intl/icu/source/common/uvectr32.cpp',
'/intl/icu/source/common/uvectr64.cpp',
'/intl/icu/source/common/wintz.c',
'/intl/icu/source/common/wintz.cpp',
]
EXPORTS.unicode += [
@ -192,17 +198,19 @@ EXPORTS.unicode += [
'/intl/icu/source/common/unicode/bytestrie.h',
'/intl/icu/source/common/unicode/bytestriebuilder.h',
'/intl/icu/source/common/unicode/caniter.h',
'/intl/icu/source/common/unicode/casemap.h',
'/intl/icu/source/common/unicode/char16ptr.h',
'/intl/icu/source/common/unicode/chariter.h',
'/intl/icu/source/common/unicode/dbbi.h',
'/intl/icu/source/common/unicode/docmain.h',
'/intl/icu/source/common/unicode/dtintrv.h',
'/intl/icu/source/common/unicode/edits.h',
'/intl/icu/source/common/unicode/enumset.h',
'/intl/icu/source/common/unicode/errorcode.h',
'/intl/icu/source/common/unicode/filteredbrk.h',
'/intl/icu/source/common/unicode/icudataver.h',
'/intl/icu/source/common/unicode/icuplug.h',
'/intl/icu/source/common/unicode/idna.h',
'/intl/icu/source/common/unicode/listformatter.h',
'/intl/icu/source/common/unicode/localpointer.h',
'/intl/icu/source/common/unicode/locdspnm.h',
'/intl/icu/source/common/unicode/locid.h',
@ -221,6 +229,7 @@ EXPORTS.unicode += [
'/intl/icu/source/common/unicode/simpleformatter.h',
'/intl/icu/source/common/unicode/std_string.h',
'/intl/icu/source/common/unicode/strenum.h',
'/intl/icu/source/common/unicode/stringoptions.h',
'/intl/icu/source/common/unicode/stringpiece.h',
'/intl/icu/source/common/unicode/stringtriebuilder.h',
'/intl/icu/source/common/unicode/symtable.h',
@ -239,6 +248,8 @@ EXPORTS.unicode += [
'/intl/icu/source/common/unicode/ucnv_err.h',
'/intl/icu/source/common/unicode/ucnvsel.h',
'/intl/icu/source/common/unicode/uconfig.h',
'/intl/icu/source/common/unicode/ucpmap.h',
'/intl/icu/source/common/unicode/ucptrie.h',
'/intl/icu/source/common/unicode/ucurr.h',
'/intl/icu/source/common/unicode/udata.h',
'/intl/icu/source/common/unicode/udisplaycontext.h',
@ -246,10 +257,10 @@ EXPORTS.unicode += [
'/intl/icu/source/common/unicode/uidna.h',
'/intl/icu/source/common/unicode/uiter.h',
'/intl/icu/source/common/unicode/uldnames.h',
'/intl/icu/source/common/unicode/ulistformatter.h',
'/intl/icu/source/common/unicode/uloc.h',
'/intl/icu/source/common/unicode/umachine.h',
'/intl/icu/source/common/unicode/umisc.h',
'/intl/icu/source/common/unicode/umutablecptrie.h',
'/intl/icu/source/common/unicode/unifilt.h',
'/intl/icu/source/common/unicode/unifunct.h',
'/intl/icu/source/common/unicode/unimatch.h',

BIN
config/external/icu/data/icudt58l.dat → config/external/icu/data/icudt63l.dat vendored
View file

Binary file not shown.

76
config/external/icu/i18n/sources.mozbuild vendored
View file

@ -1,6 +1,5 @@
# THIS FILE IS GENERATED BY /intl/icu_sources_data.py DO NOT EDIT
SOURCES += [
'/intl/icu/source/i18n/affixpatternparser.cpp',
'/intl/icu/source/i18n/alphaindex.cpp',
'/intl/icu/source/i18n/anytrans.cpp',
'/intl/icu/source/i18n/astro.cpp',
@ -53,23 +52,22 @@ SOURCES += [
'/intl/icu/source/i18n/datefmt.cpp',
'/intl/icu/source/i18n/dayperiodrules.cpp',
'/intl/icu/source/i18n/dcfmtsym.cpp',
'/intl/icu/source/i18n/decContext.c',
'/intl/icu/source/i18n/decfmtst.cpp',
'/intl/icu/source/i18n/decimalformatpattern.cpp',
'/intl/icu/source/i18n/decContext.cpp',
'/intl/icu/source/i18n/decimfmt.cpp',
'/intl/icu/source/i18n/decimfmtimpl.cpp',
'/intl/icu/source/i18n/decNumber.c',
'/intl/icu/source/i18n/digitaffix.cpp',
'/intl/icu/source/i18n/digitaffixesandpadding.cpp',
'/intl/icu/source/i18n/digitformatter.cpp',
'/intl/icu/source/i18n/digitgrouping.cpp',
'/intl/icu/source/i18n/digitinterval.cpp',
'/intl/icu/source/i18n/digitlst.cpp',
'/intl/icu/source/i18n/decNumber.cpp',
'/intl/icu/source/i18n/double-conversion-bignum-dtoa.cpp',
'/intl/icu/source/i18n/double-conversion-bignum.cpp',
'/intl/icu/source/i18n/double-conversion-cached-powers.cpp',
'/intl/icu/source/i18n/double-conversion-diy-fp.cpp',
'/intl/icu/source/i18n/double-conversion-fast-dtoa.cpp',
'/intl/icu/source/i18n/double-conversion-strtod.cpp',
'/intl/icu/source/i18n/double-conversion.cpp',
'/intl/icu/source/i18n/dtfmtsym.cpp',
'/intl/icu/source/i18n/dtitvfmt.cpp',
'/intl/icu/source/i18n/dtitvinf.cpp',
'/intl/icu/source/i18n/dtptngen.cpp',
'/intl/icu/source/i18n/dtrule.cpp',
'/intl/icu/source/i18n/erarules.cpp',
'/intl/icu/source/i18n/esctrn.cpp',
'/intl/icu/source/i18n/ethpccal.cpp',
'/intl/icu/source/i18n/fmtable.cpp',
@ -86,6 +84,7 @@ SOURCES += [
'/intl/icu/source/i18n/inputext.cpp',
'/intl/icu/source/i18n/islamcal.cpp',
'/intl/icu/source/i18n/japancal.cpp',
'/intl/icu/source/i18n/listformatter.cpp',
'/intl/icu/source/i18n/measfmt.cpp',
'/intl/icu/source/i18n/measunit.cpp',
'/intl/icu/source/i18n/measure.cpp',
@ -95,15 +94,50 @@ SOURCES += [
'/intl/icu/source/i18n/nfrule.cpp',
'/intl/icu/source/i18n/nfsubs.cpp',
'/intl/icu/source/i18n/nortrans.cpp',
'/intl/icu/source/i18n/nounit.cpp',
'/intl/icu/source/i18n/nultrans.cpp',
'/intl/icu/source/i18n/number_affixutils.cpp',
'/intl/icu/source/i18n/number_asformat.cpp',
'/intl/icu/source/i18n/number_capi.cpp',
'/intl/icu/source/i18n/number_compact.cpp',
'/intl/icu/source/i18n/number_currencysymbols.cpp',
'/intl/icu/source/i18n/number_decimalquantity.cpp',
'/intl/icu/source/i18n/number_decimfmtprops.cpp',
'/intl/icu/source/i18n/number_fluent.cpp',
'/intl/icu/source/i18n/number_formatimpl.cpp',
'/intl/icu/source/i18n/number_grouping.cpp',
'/intl/icu/source/i18n/number_integerwidth.cpp',
'/intl/icu/source/i18n/number_longnames.cpp',
'/intl/icu/source/i18n/number_mapper.cpp',
'/intl/icu/source/i18n/number_modifiers.cpp',
'/intl/icu/source/i18n/number_multiplier.cpp',
'/intl/icu/source/i18n/number_notation.cpp',
'/intl/icu/source/i18n/number_padding.cpp',
'/intl/icu/source/i18n/number_patternmodifier.cpp',
'/intl/icu/source/i18n/number_patternstring.cpp',
'/intl/icu/source/i18n/number_rounding.cpp',
'/intl/icu/source/i18n/number_scientific.cpp',
'/intl/icu/source/i18n/number_skeletons.cpp',
'/intl/icu/source/i18n/number_stringbuilder.cpp',
'/intl/icu/source/i18n/number_utils.cpp',
'/intl/icu/source/i18n/numfmt.cpp',
'/intl/icu/source/i18n/numparse_affixes.cpp',
'/intl/icu/source/i18n/numparse_compositions.cpp',
'/intl/icu/source/i18n/numparse_currency.cpp',
'/intl/icu/source/i18n/numparse_decimal.cpp',
'/intl/icu/source/i18n/numparse_impl.cpp',
'/intl/icu/source/i18n/numparse_parsednumber.cpp',
'/intl/icu/source/i18n/numparse_scientific.cpp',
'/intl/icu/source/i18n/numparse_stringsegment.cpp',
'/intl/icu/source/i18n/numparse_symbols.cpp',
'/intl/icu/source/i18n/numparse_validators.cpp',
'/intl/icu/source/i18n/numrange_fluent.cpp',
'/intl/icu/source/i18n/numrange_impl.cpp',
'/intl/icu/source/i18n/numsys.cpp',
'/intl/icu/source/i18n/olsontz.cpp',
'/intl/icu/source/i18n/persncal.cpp',
'/intl/icu/source/i18n/pluralaffix.cpp',
'/intl/icu/source/i18n/plurfmt.cpp',
'/intl/icu/source/i18n/plurrule.cpp',
'/intl/icu/source/i18n/precision.cpp',
'/intl/icu/source/i18n/quant.cpp',
'/intl/icu/source/i18n/quantityformatter.cpp',
'/intl/icu/source/i18n/rbnf.cpp',
@ -130,7 +164,6 @@ SOURCES += [
'/intl/icu/source/i18n/selfmt.cpp',
'/intl/icu/source/i18n/sharedbreakiterator.cpp',
'/intl/icu/source/i18n/simpletz.cpp',
'/intl/icu/source/i18n/smallintformatter.cpp',
'/intl/icu/source/i18n/smpdtfmt.cpp',
'/intl/icu/source/i18n/smpdtfst.cpp',
'/intl/icu/source/i18n/sortkey.cpp',
@ -167,7 +200,8 @@ SOURCES += [
'/intl/icu/source/i18n/udatpg.cpp',
'/intl/icu/source/i18n/ufieldpositer.cpp',
'/intl/icu/source/i18n/uitercollationiterator.cpp',
'/intl/icu/source/i18n/ulocdata.c',
'/intl/icu/source/i18n/ulistformatter.cpp',
'/intl/icu/source/i18n/ulocdata.cpp',
'/intl/icu/source/i18n/umsg.cpp',
'/intl/icu/source/i18n/unesctrn.cpp',
'/intl/icu/source/i18n/uni2name.cpp',
@ -184,10 +218,8 @@ SOURCES += [
'/intl/icu/source/i18n/uspoof_impl.cpp',
'/intl/icu/source/i18n/utf16collationiterator.cpp',
'/intl/icu/source/i18n/utf8collationiterator.cpp',
'/intl/icu/source/i18n/utmscale.c',
'/intl/icu/source/i18n/utmscale.cpp',
'/intl/icu/source/i18n/utrans.cpp',
'/intl/icu/source/i18n/valueformatter.cpp',
'/intl/icu/source/i18n/visibledigits.cpp',
'/intl/icu/source/i18n/vtzone.cpp',
'/intl/icu/source/i18n/vzone.cpp',
'/intl/icu/source/i18n/windtfmt.cpp',
@ -223,10 +255,14 @@ EXPORTS.unicode += [
'/intl/icu/source/i18n/unicode/fpositer.h',
'/intl/icu/source/i18n/unicode/gender.h',
'/intl/icu/source/i18n/unicode/gregocal.h',
'/intl/icu/source/i18n/unicode/listformatter.h',
'/intl/icu/source/i18n/unicode/measfmt.h',
'/intl/icu/source/i18n/unicode/measunit.h',
'/intl/icu/source/i18n/unicode/measure.h',
'/intl/icu/source/i18n/unicode/msgfmt.h',
'/intl/icu/source/i18n/unicode/nounit.h',
'/intl/icu/source/i18n/unicode/numberformatter.h',
'/intl/icu/source/i18n/unicode/numberrangeformatter.h',
'/intl/icu/source/i18n/unicode/numfmt.h',
'/intl/icu/source/i18n/unicode/numsys.h',
'/intl/icu/source/i18n/unicode/plurfmt.h',
@ -263,10 +299,12 @@ EXPORTS.unicode += [
'/intl/icu/source/i18n/unicode/ufieldpositer.h',
'/intl/icu/source/i18n/unicode/uformattable.h',
'/intl/icu/source/i18n/unicode/ugender.h',
'/intl/icu/source/i18n/unicode/ulistformatter.h',
'/intl/icu/source/i18n/unicode/ulocdata.h',
'/intl/icu/source/i18n/unicode/umsg.h',
'/intl/icu/source/i18n/unicode/unirepl.h',
'/intl/icu/source/i18n/unicode/unum.h',
'/intl/icu/source/i18n/unicode/unumberformatter.h',
'/intl/icu/source/i18n/unicode/unumsys.h',
'/intl/icu/source/i18n/unicode/upluralrules.h',
'/intl/icu/source/i18n/unicode/uregex.h',

2
config/external/icu/stubdata/moz.build vendored
View file

@ -9,4 +9,4 @@
Library('icustubdata')
SOURCES += ['/intl/icu/source/stubdata/stubdata.c']
SOURCES += ['/intl/icu/source/stubdata/stubdata.cpp']

8
intl/icu/GIT-INFO
View file

@ -1,5 +1,5 @@
commit 9248183bc6ab67503d03d4a6b4c842e77e3fd1b8
Author: yumaoka <y.umaoka@gmail.com>
Date: Wed Apr 10 00:49:25 2019 -0400
commit 4f715ae124c418a15a3fa4d8fb14f406576a7ee5
Author: Jeff Genovy <29107334+jefgen@users.noreply.github.com>
Date: Wed Apr 10 17:32:11 2019 -0700
ICU-20536 ICU 58.3 release tasks
ICU-20536 ICU 63.2 release tasks + tzdata2019a

2506
intl/icu/source/Doxyfile.in
View file

File diff suppressed because it is too large Load diff

27
intl/icu/source/Makefile.in
View file

@ -34,9 +34,11 @@ subdir = .
@LAYOUTEX_TRUE@LAYOUTEX = layoutex
@ICUIO_TRUE@ICUIO = io
@EXTRAS_TRUE@EXTRA = extra
@TESTS_TRUE@TEST = test
# need tools for tests
@TOOLS_TRUE@@TESTS_TRUE@TEST = test
@SAMPLES_TRUE@SAMPLE = samples
@TOOLS_TRUE@TOOLS = tools
@TOOLS_TRUE@DATASUBDIR = data
## pkgconfig setup. Always have uc and i18n. Others are optional.
ALL_PKGCONFIG_SUFFIX=uc i18n
@ -46,6 +48,8 @@ ALL_PKGCONFIG_SUFFIX=uc i18n
DOXYGEN = @DOXYGEN@
DOCZIP = icu-docs.zip
INSTALL_ICU_CONFIG = @INSTALL_ICU_CONFIG@
## Files to remove for 'make clean'
CLEANFILES = *~
@ -58,11 +62,13 @@ INSTALLED_BUILT_FILES = $(top_builddir)/config/Makefile.inc $(top_builddir)/conf
LOCAL_BUILT_FILES = icudefs.mk config/icucross.mk config/icucross.inc
DOCDIRS = common i18n
SUBDIRS = stubdata common i18n $(LAYOUTEX) $(ICUIO) $(TOOLS) data $(EXTRA) $(SAMPLE) $(TEST)
SUBDIRS = stubdata common i18n $(LAYOUTEX) $(ICUIO) $(TOOLS) $(DATASUBDIR) $(EXTRA) $(SAMPLE) $(TEST)
SECTION = 1
ifeq ($(INSTALL_ICU_CONFIG),true)
MANX_FILES = config/icu-config.$(SECTION)
endif
ALL_MAN_FILES = $(MANX_FILES)
@ -85,7 +91,7 @@ all: all-local all-recursive
install: install-recursive install-local
clean: clean-recursive-with-twist clean-local
distclean : distclean-recursive distclean-local
dist: dist-recursive dist-local
dist: dist-recursive
check: all check-recursive
check-recursive: all
xcheck: all xcheck-recursive
@ -144,6 +150,10 @@ $(LIBDIR) $(BINDIR):
## favor of RECURSIVE=YES when the submake in the subdirectory restarts itself
## after dependency files have been created.
all-recursive install-recursive clean-recursive distclean-recursive dist-recursive check-recursive check-exhaustive-recursive: $(LIBDIR) $(BINDIR)
ifneq ($(NEED_ESCAPING),)
@echo "building tools/escapesrc (Needed for this platform with NEED_ESCAPING)"
@(cd tools/escapesrc && $(MAKE) $(MAKEOVERRIDES) RECURSIVE=YES $$local_target) || exit
endif
@dot_seen=no; \
target=`echo $@ | sed s/-recursive//`; \
list='$(LOCAL_SUBDIRS)'; for subdir in $$list; do \
@ -185,13 +195,15 @@ install-icu: $(INSTALLED_BUILT_FILES)
@$(MKINSTALLDIRS) $(DESTDIR)$(libdir)/pkgconfig
$(INSTALL_DATA) $(ALL_PKGCONFIG_FILES) $(DESTDIR)$(libdir)/pkgconfig/
$(INSTALL_DATA) $(top_srcdir)/../LICENSE $(DESTDIR)$(pkgdatadir)/LICENSE
ifeq ($(INSTALL_ICU_CONFIG),true)
$(INSTALL_SCRIPT) $(top_builddir)/config/icu-config $(DESTDIR)$(bindir)/icu-config
endif
$(INSTALL_DATA) $(top_builddir)/config/Makefile.inc $(DESTDIR)$(pkglibdir)/Makefile.inc
$(INSTALL_DATA) $(top_builddir)/config/pkgdata.inc $(DESTDIR)$(pkglibdir)/pkgdata.inc
# @echo icuinfo.xml is built after make check.
# -$(INSTALL_DATA) $(top_builddir)/config/icuinfo.xml $(DESTDIR)$(pkglibdir)/icuinfo.xml
cd $(DESTDIR)$(pkglibdir)/..; \
$(RM) current && ln -s $(VERSION) current; \
$(RMV) current && ln -s $(VERSION) current; \
$(RM) Makefile.inc && ln -s current/Makefile.inc Makefile.inc; \
$(RM) pkgdata.inc && ln -s current/pkgdata.inc pkgdata.inc
@ -327,9 +339,10 @@ $(top_builddir)/config/icu-config: $(top_builddir)/Makefile $(top_srcdir)/config
-$(RMV) $@
$(INSTALL_SCRIPT) $(top_srcdir)/config/icu-config-top $@
chmod u+w $@
@echo "# Following from icu/icu4c/source/config/Makefile.inc" >> $@
LC_ALL=C $(SED) -f $(top_srcdir)/config/make2sh.sed < $(top_builddir)/config/Makefile.inc | grep -v '#M#' | uniq >> $@
@echo "# Following from @platform_make_fragment@" >> $@
LC_ALL=C sed -f $(top_srcdir)/config/make2sh.sed < $(top_builddir)/config/Makefile.inc | grep -v '#M#' | uniq >> $@
LC_ALL=C sed -f $(top_srcdir)/config/make2sh.sed < @platform_make_fragment@ | grep -v '#M#' | uniq >> $@
LC_ALL=C $(SED) -f $(top_srcdir)/config/make2sh.sed < @platform_make_fragment@ | grep -v '#M#' | uniq >> $@
cat $(top_srcdir)/config/icu-config-bottom >> $@
chmod u-w $@
@ -347,7 +360,9 @@ config.status: $(srcdir)/configure $(srcdir)/common/unicode/uvernum.h
install-manx: $(MANX_FILES)
$(MKINSTALLDIRS) $(DESTDIR)$(mandir)/man$(SECTION)
ifneq ($(MANX_FILES),)
$(INSTALL_DATA) $? $(DESTDIR)$(mandir)/man$(SECTION)
endif
config/%.$(SECTION): $(srcdir)/config/%.$(SECTION).in
cd $(top_builddir) \

6
intl/icu/source/acinclude.m4
View file

@ -464,12 +464,12 @@ AC_DEFUN([AC_CHECK_STRICT_COMPILE],
then
case "${host}" in
*-*-solaris*)
# Don't use -std=c99 on Solaris because of timezone check fails
# Don't use -std=c11 on Solaris because of timezone check fails
;;
*)
# Do not use -ansi. It limits us to C90, and it breaks some platforms.
# We use -std=c99 to disable the gnu99 defaults and its associated warnings
CFLAGS="$CFLAGS -std=c99"
# We use -std=c11 to disable the gnu99 defaults and its associated warnings
CFLAGS="$CFLAGS -std=c11"
;;
esac

20
intl/icu/source/allinone/Build.Windows.Library.ProjectConfiguration.props Normal file
View file

@ -0,0 +1,20 @@
<?xml version="1.0" encoding="utf-8"?>
<!-- Copyright (C) 2018 and later: Unicode, Inc. and others. License & terms of use: http://www.unicode.org/copyright.html -->
<Project DefaultTargets="Build" ToolsVersion="14.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<!-- This file is used to set configurations that are common to *all* ICU library code (common, i18n, and io). -->
<!-- Note: These options are for *all* configurations for *all* library projects. -->
<ItemDefinitionGroup>
<ClCompile>
<!-- ICU does not use exceptions in library code. -->
<PreprocessorDefinitions>
_HAS_EXCEPTIONS=0;
%(PreprocessorDefinitions)
</PreprocessorDefinitions>
</ClCompile>
</ItemDefinitionGroup>
<PropertyGroup>
<!-- Disable MSBuild warning about Linker OutputFile. -->
<!-- Ex: MSBuild complains that the common project creates "icuuc62.dll" rather than "common.dll". However, this is intentional. -->
<MSBuildWarningsAsMessages>MSB8012</MSBuildWarningsAsMessages>
</PropertyGroup>
</Project>

129
intl/icu/source/allinone/Build.Windows.ProjectConfiguration.props Normal file
View file

@ -0,0 +1,129 @@
<?xml version="1.0" encoding="utf-8"?>
<!-- Copyright (C) 2016 and later: Unicode, Inc. and others. License & terms of use: http://www.unicode.org/copyright.html -->
<Project DefaultTargets="Build" ToolsVersion="14.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<!-- This file is used to set default configuration options for all non-UWP Visual Studio projects. -->
<!-- These are the default project configurations for building. -->
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|Win32">
<Configuration>Debug</Configuration>
<Platform>Win32</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|Win32">
<Configuration>Release</Configuration>
<Platform>Win32</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup>
<!-- This is the version of the MSVC tool-set to use. -->
<!-- v140 is the Visual Studio 2015 toolset. -->
<!-- v141 is the Visual Studio 2017 toolset. -->
<PlatformToolset>v141</PlatformToolset>
</PropertyGroup>
<PropertyGroup>
<!-- This is the default SDK target. -->
<!-- Note that the Windows 8.1 SDK is backwards compatible down-level to Windows 7, so
setting this to 8.1 does not actually imply targeting Windows 8.1. -->
<WindowsTargetPlatformVersion>8.1</WindowsTargetPlatformVersion>
</PropertyGroup>
<PropertyGroup>
<!-- We need to explicitly set the target version to Windows 7. -->
<Win32_WinNTVersion>0x0601</Win32_WinNTVersion>
</PropertyGroup>
<!-- Options that are common to *all* configurations for *all* projects. -->
<ItemDefinitionGroup>
<Midl>
<MkTypLibCompatible>true</MkTypLibCompatible>
<SuppressStartupBanner>true</SuppressStartupBanner>
</Midl>
<ClCompile>
<!-- Note: These preprocessor defines are for *all* configurations for *all* projects. -->
<!-- Note: See ticket #5750 for the macro '_CRT_SECURE_NO_DEPRECATE'. -->
<PreprocessorDefinitions>
WINVER=$(Win32_WinNTVersion);
_WIN32_WINNT=$(Win32_WinNTVersion);
_CRT_SECURE_NO_DEPRECATE;
%(PreprocessorDefinitions)
</PreprocessorDefinitions>
<!-- We always want to treat wchar_t as a "real" C++ type, instead of a typedef. -->
<TreatWChar_tAsBuiltInType>true</TreatWChar_tAsBuiltInType>
<SuppressStartupBanner>true</SuppressStartupBanner>
<!-- Set the source encoding and runtime encoding to UTF-8 by default. -->
<AdditionalOptions>/utf-8 %(AdditionalOptions)</AdditionalOptions>
<!-- Enable parallel compilation for faster builds. -->
<MultiProcessorCompilation>true</MultiProcessorCompilation>
</ClCompile>
<ResourceCompile>
<Culture>0x0409</Culture>
</ResourceCompile>
<Link>
<SuppressStartupBanner>true</SuppressStartupBanner>
</Link>
</ItemDefinitionGroup>
<!-- Options that are common to all 'Release' configurations for *all* projects. -->
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<Midl>
<PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
</Midl>
<ClCompile>
<PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<StringPooling>true</StringPooling>
</ClCompile>
<ResourceCompile>
<PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
</ResourceCompile>
<Link>
<EnableCOMDATFolding>true</EnableCOMDATFolding>
</Link>
</ItemDefinitionGroup>
<!-- Options that are common to all 'Debug' configurations for *all* projects. -->
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<Midl>
<PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
</Midl>
<ClCompile>
<PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<Optimization>Disabled</Optimization>
<BasicRuntimeChecks>EnableFastChecks</BasicRuntimeChecks>
<BufferSecurityCheck>true</BufferSecurityCheck>
</ClCompile>
<ResourceCompile>
<PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
</ResourceCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<ImageHasSafeExceptionHandlers>false</ImageHasSafeExceptionHandlers>
</Link>
</ItemDefinitionGroup>
<!-- Options that are common to all 32-bit configurations for *all* projects. -->
<ItemDefinitionGroup Condition="'$(Platform)'=='Win32'">
<Midl>
<TargetEnvironment>Win32</TargetEnvironment>
</Midl>
<ClCompile>
<PreprocessorDefinitions>WIN32;%(PreprocessorDefinitions)</PreprocessorDefinitions>
</ClCompile>
<Link>
<TargetMachine>MachineX86</TargetMachine>
</Link>
</ItemDefinitionGroup>
<!-- Options that are common to all 64-bit configurations for *all* projects. -->
<ItemDefinitionGroup Condition="'$(Platform)'=='x64'">
<Midl>
<TargetEnvironment>X64</TargetEnvironment>
</Midl>
<ClCompile>
<PreprocessorDefinitions>WIN64;WIN32;%(PreprocessorDefinitions)</PreprocessorDefinitions>
</ClCompile>
<Link>
<TargetMachine>MachineX64</TargetMachine>
</Link>
</ItemDefinitionGroup>
</Project>

41
intl/icu/source/allinone/Build.Windows.UWP.ProjectConfiguration.props Normal file
View file

@ -0,0 +1,41 @@
<?xml version="1.0" encoding="utf-8"?>
<!-- Copyright (C) 2016 and later: Unicode, Inc. and others. License & terms of use: http://www.unicode.org/copyright.html -->
<Project DefaultTargets="Build" ToolsVersion="14.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<!-- This file is used to set common configuration options for all *_uwp projects. -->
<PropertyGroup>
<!-- If not already set, use this version of the Win10 SDK -->
<WindowsTargetPlatformVersion>10.0.16299.0</WindowsTargetPlatformVersion>
<!-- If not already set, set the minimum Win10 SDK version to TH1/RTM -->
<WindowsTargetPlatformMinVersion>10.0.10240.0</WindowsTargetPlatformMinVersion>
<MinimumVisualStudioVersion>14.0</MinimumVisualStudioVersion>
<AppContainerApplication>true</AppContainerApplication>
<ApplicationType>Windows Store</ApplicationType>
<ApplicationTypeRevision>10.0</ApplicationTypeRevision>
</PropertyGroup>
<PropertyGroup>
<!-- This is the version of the MSVC tool-set to use. -->
<!-- v141 is the Visual Studio 2017 toolset. -->
<PlatformToolset>v141</PlatformToolset>
</PropertyGroup>
<ItemDefinitionGroup>
<Midl>
<PreprocessorDefinitions>
%(PreprocessorDefinitions)
U_PLATFORM_HAS_WINUWP_API=1;
</PreprocessorDefinitions>
</Midl>
<ClCompile>
<PreprocessorDefinitions>
%(PreprocessorDefinitions);
U_PLATFORM_HAS_WINUWP_API=1;
</PreprocessorDefinitions>
</ClCompile>
<ResourceCompile>
<PreprocessorDefinitions>
%(PreprocessorDefinitions)
U_PLATFORM_HAS_WINUWP_API=1;
</PreprocessorDefinitions>
</ResourceCompile>
</ItemDefinitionGroup>
</Project>

27
intl/icu/source/allinone/Windows.CopyUnicodeHeaderFiles.targets Normal file
View file

@ -0,0 +1,27 @@
<?xml version="1.0" encoding="utf-8"?>
<!-- Copyright (C) 2016 and later: Unicode, Inc. and others. License & terms of use: http://www.unicode.org/copyright.html -->
<!--
This file is used to copy all of the header files (*.h) from a project's "unicode" folder to a common output folder.
-->
<Project ToolsVersion="14.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<!-- This is the location of the common output folder. -->
<CopyDestionationPath>$(SolutionDir)\..\..\include\unicode</CopyDestionationPath>
<BuildDependsOn>
$(BuildDependsOn);
CopyUnicodeHeaderFiles;
</BuildDependsOn>
</PropertyGroup>
<Target Name="CopyUnicodeHeaderFiles">
<ItemGroup>
<!-- Generate a list of all files that end in .h from the 'unicode' folder, relative to the current project. -->
<OutputFiles Include=".\unicode\**\*.h" />
</ItemGroup>
<!-- This message will be logged in the project's build output. -->
<Message Text="Copying @(OutputFiles->Count()) header files to $(CopyDestionationPath). Files copied: @(OutputFiles)" Importance="high"/>
<!-- Perform the copy. -->
<Copy SourceFiles="@(OutputFiles)"
DestinationFolder="$(CopyDestionationPath)\%(RecursiveDir)"
SkipUnchangedFiles="false"></Copy>
</Target>
</Project>

260
intl/icu/source/allinone/allinone.sln
View file

@ -1,328 +1,544 @@
Microsoft Visual Studio Solution File, Format Version 11.00
# Visual Studio 2010
Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio 15
VisualStudioVersion = 15.0.27130.2036
MinimumVisualStudioVersion = 10.0.40219.1
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "cal", "..\samples\cal\cal.vcxproj", "{F7659D77-09CF-4FE9-ACEE-927287AA9509}"
ProjectSection(ProjectDependencies) = postProject
{0178B127-6269-407D-B112-93877BB62776} = {0178B127-6269-407D-B112-93877BB62776}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "cintltst", "..\test\cintltst\cintltst.vcxproj", "{3D1246AE-1B32-479B-BECA-AEFA97BE2321}"
ProjectSection(ProjectDependencies) = postProject
{0178B127-6269-407D-B112-93877BB62776} = {0178B127-6269-407D-B112-93877BB62776}
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{ECA6B435-B4FA-4F9F-BF95-F451D078FC47} = {ECA6B435-B4FA-4F9F-BF95-F451D078FC47}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "common", "..\common\common.vcxproj", "{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}"
ProjectSection(ProjectDependencies) = postProject
{203EC78A-0531-43F0-A636-285439BDE025} = {203EC78A-0531-43F0-A636-285439BDE025}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "ctestfw", "..\tools\ctestfw\ctestfw.vcxproj", "{ECA6B435-B4FA-4F9F-BF95-F451D078FC47}"
ProjectSection(ProjectDependencies) = postProject
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "date", "..\samples\date\date.vcxproj", "{38B5751A-C6F9-4409-950C-F4F9DA17275F}"
ProjectSection(ProjectDependencies) = postProject
{0178B127-6269-407D-B112-93877BB62776} = {0178B127-6269-407D-B112-93877BB62776}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "derb", "..\tools\genrb\derb.vcxproj", "{D3065ADB-8820-4CC7-9B6C-9510833961A3}"
ProjectSection(ProjectDependencies) = postProject
{C2B04507-2521-4801-BF0D-5FD79D6D518C} = {C2B04507-2521-4801-BF0D-5FD79D6D518C}
{0178B127-6269-407D-B112-93877BB62776} = {0178B127-6269-407D-B112-93877BB62776}
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "genbrk", "..\tools\genbrk\genbrk.vcxproj", "{C2BE5000-7501-4E87-9724-B8D82494FAE6}"
ProjectSection(ProjectDependencies) = postProject
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "genccode", "..\tools\genccode\genccode.vcxproj", "{FDD3C4F2-9805-44EB-9A77-BC1C1C95B547}"
ProjectSection(ProjectDependencies) = postProject
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "gencmn", "..\tools\gencmn\gencmn.vcxproj", "{A8D36F8D-09E6-4174-91C3-7BEAA9C3F04F}"
ProjectSection(ProjectDependencies) = postProject
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "gencnval", "..\tools\gencnval\gencnval.vcxproj", "{8B41752B-5A52-41E4-B7E0-07921C0CC6BF}"
ProjectSection(ProjectDependencies) = postProject
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "genrb", "..\tools\genrb\genrb.vcxproj", "{97521D06-EC47-45D4-8BD0-9E16B3F93B2A}"
ProjectSection(ProjectDependencies) = postProject
{0178B127-6269-407D-B112-93877BB62776} = {0178B127-6269-407D-B112-93877BB62776}
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "gentest", "..\tools\gentest\gentest.vcxproj", "{77C78066-746F-4EA6-B3FE-B8C8A4A97891}"
ProjectSection(ProjectDependencies) = postProject
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{ECA6B435-B4FA-4F9F-BF95-F451D078FC47} = {ECA6B435-B4FA-4F9F-BF95-F451D078FC47}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "i18n", "..\i18n\i18n.vcxproj", "{0178B127-6269-407D-B112-93877BB62776}"
ProjectSection(ProjectDependencies) = postProject
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "intltest", "..\test\intltest\intltest.vcxproj", "{73632960-B3A6-464D-83A3-4B43365F19B8}"
ProjectSection(ProjectDependencies) = postProject
{0178B127-6269-407D-B112-93877BB62776} = {0178B127-6269-407D-B112-93877BB62776}
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{ECA6B435-B4FA-4F9F-BF95-F451D078FC47} = {ECA6B435-B4FA-4F9F-BF95-F451D078FC47}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "makeconv", "..\tools\makeconv\makeconv.vcxproj", "{F5AD9738-1A3D-4906-B9C4-A7D9CE33DC2C}"
ProjectSection(ProjectDependencies) = postProject
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "makedata", "..\data\makedata.vcxproj", "{D9DF7F2F-93B7-4810-B5CD-96F4F33C079B}"
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "pkgdata", "..\tools\pkgdata\pkgdata.vcxproj", "{4C8454FE-81D3-4CA3-9927-29BA96F03DAC}"
ProjectSection(ProjectDependencies) = postProject
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "stubdata", "..\stubdata\stubdata.vcxproj", "{203EC78A-0531-43F0-A636-285439BDE025}"
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "toolutil", "..\tools\toolutil\toolutil.vcxproj", "{6B231032-3CB5-4EED-9210-810D666A23A0}"
ProjectSection(ProjectDependencies) = postProject
{0178B127-6269-407D-B112-93877BB62776} = {0178B127-6269-407D-B112-93877BB62776}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "uconv", "..\extra\uconv\uconv.vcxproj", "{DBA4088D-F6F9-4F8F-8820-082A4765C16C}"
ProjectSection(ProjectDependencies) = postProject
{97521D06-EC47-45D4-8BD0-9E16B3F93B2A} = {97521D06-EC47-45D4-8BD0-9E16B3F93B2A}
{0178B127-6269-407D-B112-93877BB62776} = {0178B127-6269-407D-B112-93877BB62776}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
{4C8454FE-81D3-4CA3-9927-29BA96F03DAC} = {4C8454FE-81D3-4CA3-9927-29BA96F03DAC}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "io", "..\io\io.vcxproj", "{C2B04507-2521-4801-BF0D-5FD79D6D518C}"
ProjectSection(ProjectDependencies) = postProject
{0178B127-6269-407D-B112-93877BB62776} = {0178B127-6269-407D-B112-93877BB62776}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "gensprep", "..\tools\gensprep\gensprep.vcxproj", "{631C23CE-6C1D-4875-88F0-85E0A42B36EA}"
ProjectSection(ProjectDependencies) = postProject
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "iotest", "..\test\iotest\iotest.vcxproj", "{E4993E82-D68A-46CA-BAE0-9D35E172E46F}"
ProjectSection(ProjectDependencies) = postProject
{C2B04507-2521-4801-BF0D-5FD79D6D518C} = {C2B04507-2521-4801-BF0D-5FD79D6D518C}
{0178B127-6269-407D-B112-93877BB62776} = {0178B127-6269-407D-B112-93877BB62776}
{ECA6B435-B4FA-4F9F-BF95-F451D078FC47} = {ECA6B435-B4FA-4F9F-BF95-F451D078FC47}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "icupkg", "..\tools\icupkg\icupkg.vcxproj", "{62D4B15D-7A90-4ECB-BA19-5E021D6A21BC}"
ProjectSection(ProjectDependencies) = postProject
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "gendict", "..\tools\gendict\gendict.vcxproj", "{9D4211F7-2C77-439C-82F0-30A4E43BA569}"
ProjectSection(ProjectDependencies) = postProject
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "gencfu", "..\tools\gencfu\gencfu.vcxproj", "{691EE0C0-DC57-4A48-8AEE-8ED75EB3A057}"
ProjectSection(ProjectDependencies) = postProject
{0178B127-6269-407D-B112-93877BB62776} = {0178B127-6269-407D-B112-93877BB62776}
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "gennorm2", "..\tools\gennorm2\gennorm2.vcxproj", "{C7891A65-80AB-4245-912E-5F1E17B0E6C4}"
ProjectSection(ProjectDependencies) = postProject
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "icuinfo", "..\tools\icuinfo\icuinfo.vcxproj", "{E7611F49-F088-4175-9446-6111444E72C8}"
ProjectSection(ProjectDependencies) = postProject
{0178B127-6269-407D-B112-93877BB62776} = {0178B127-6269-407D-B112-93877BB62776}
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{ECA6B435-B4FA-4F9F-BF95-F451D078FC47} = {ECA6B435-B4FA-4F9F-BF95-F451D078FC47}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "testplug", "..\tools\icuinfo\testplug.vcxproj", "{659D0C08-D4ED-4BF3-B02B-2D8D4B5A7A7A}"
ProjectSection(ProjectDependencies) = postProject
{6B231032-3CB5-4EED-9210-810D666A23A0} = {6B231032-3CB5-4EED-9210-810D666A23A0}
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "makedata_uwp", "..\data\makedata_uwp.vcxproj", "{B1D53358-37BD-48BC-B27C-68BAF1E78508}"
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "i18n_uwp", "..\i18n\i18n_uwp.vcxproj", "{6786C051-383B-47E0-9E82-B8B994E06A25}"
ProjectSection(ProjectDependencies) = postProject
{0178B127-6269-407D-B112-93877BB62776} = {0178B127-6269-407D-B112-93877BB62776}
{C10CF34B-3F79-430E-AD38-5A32DC0589C2} = {C10CF34B-3F79-430E-AD38-5A32DC0589C2}
EndProjectSection
EndProject
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "common_uwp", "..\common\common_uwp.vcxproj", "{C10CF34B-3F79-430E-AD38-5A32DC0589C2}"
ProjectSection(ProjectDependencies) = postProject
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D} = {73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}
EndProjectSection
EndProject
Global
GlobalSection(SubversionScc) = preSolution
Svn-Managed = True
Manager = AnkhSVN - Subversion Support for Visual Studio
EndGlobalSection
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|ARM = Debug|ARM
Debug|Win32 = Debug|Win32
Debug|x64 = Debug|x64
Release|ARM = Release|ARM
Release|Win32 = Release|Win32
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{F7659D77-09CF-4FE9-ACEE-927287AA9509}.Debug|ARM.ActiveCfg = Debug|Win32
{F7659D77-09CF-4FE9-ACEE-927287AA9509}.Debug|Win32.ActiveCfg = Debug|Win32
{F7659D77-09CF-4FE9-ACEE-927287AA9509}.Debug|Win32.Build.0 = Debug|Win32
{F7659D77-09CF-4FE9-ACEE-927287AA9509}.Debug|x64.ActiveCfg = Debug|x64
{F7659D77-09CF-4FE9-ACEE-927287AA9509}.Debug|x64.Build.0 = Debug|x64
{F7659D77-09CF-4FE9-ACEE-927287AA9509}.Release|ARM.ActiveCfg = Release|Win32
{F7659D77-09CF-4FE9-ACEE-927287AA9509}.Release|Win32.ActiveCfg = Release|Win32
{F7659D77-09CF-4FE9-ACEE-927287AA9509}.Release|Win32.Build.0 = Release|Win32
{F7659D77-09CF-4FE9-ACEE-927287AA9509}.Release|x64.ActiveCfg = Release|x64
{F7659D77-09CF-4FE9-ACEE-927287AA9509}.Release|x64.Build.0 = Release|x64
{3D1246AE-1B32-479B-BECA-AEFA97BE2321}.Debug|ARM.ActiveCfg = Debug|Win32
{3D1246AE-1B32-479B-BECA-AEFA97BE2321}.Debug|Win32.ActiveCfg = Debug|Win32
{3D1246AE-1B32-479B-BECA-AEFA97BE2321}.Debug|Win32.Build.0 = Debug|Win32
{3D1246AE-1B32-479B-BECA-AEFA97BE2321}.Debug|x64.ActiveCfg = Debug|x64
{3D1246AE-1B32-479B-BECA-AEFA97BE2321}.Debug|x64.Build.0 = Debug|x64
{3D1246AE-1B32-479B-BECA-AEFA97BE2321}.Release|ARM.ActiveCfg = Release|Win32
{3D1246AE-1B32-479B-BECA-AEFA97BE2321}.Release|Win32.ActiveCfg = Release|Win32
{3D1246AE-1B32-479B-BECA-AEFA97BE2321}.Release|Win32.Build.0 = Release|Win32
{3D1246AE-1B32-479B-BECA-AEFA97BE2321}.Release|x64.ActiveCfg = Release|x64
{3D1246AE-1B32-479B-BECA-AEFA97BE2321}.Release|x64.Build.0 = Release|x64
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}.Debug|ARM.ActiveCfg = Debug|Win32
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}.Debug|Win32.ActiveCfg = Debug|Win32
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}.Debug|Win32.Build.0 = Debug|Win32
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}.Debug|x64.ActiveCfg = Debug|x64
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}.Debug|x64.Build.0 = Debug|x64
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}.Release|ARM.ActiveCfg = Release|Win32
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}.Release|Win32.ActiveCfg = Release|Win32
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}.Release|Win32.Build.0 = Release|Win32
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}.Release|x64.ActiveCfg = Release|x64
{73C0A65B-D1F2-4DE1-B3A6-15DAD2C23F3D}.Release|x64.Build.0 = Release|x64
{ECA6B435-B4FA-4F9F-BF95-F451D078FC47}.Debug|ARM.ActiveCfg = Debug|Win32
{ECA6B435-B4FA-4F9F-BF95-F451D078FC47}.Debug|Win32.ActiveCfg = Debug|Win32
{ECA6B435-B4FA-4F9F-BF95-F451D078FC47}.Debug|Win32.Build.0 = Debug|Win32
{ECA6B435-B4FA-4F9F-BF95-F451D078FC47}.Debug|x64.ActiveCfg = Debug|x64
{ECA6B435-B4FA-4F9F-BF95-F451D078FC47}.Debug|x64.Build.0 = Debug|x64
{ECA6B435-B4FA-4F9F-BF95-F451D078FC47}.Release|ARM.ActiveCfg = Release|Win32
{ECA6B435-B4FA-4F9F-BF95-F451D078FC47}.Release|Win32.ActiveCfg = Release|Win32
{ECA6B435-B4FA-4F9F-BF95-F451D078FC47}.Release|Win32.Build.0 = Release|Win32
{ECA6B435-B4FA-4F9F-BF95-F451D078FC47}.Release|x64.ActiveCfg = Release|x64
{ECA6B435-B4FA-4F9F-BF95-F451D078FC47}.Release|x64.Build.0 = Release|x64
{38B5751A-C6F9-4409-950C-F4F9DA17275F}.Debug|ARM.ActiveCfg = Debug|Win32
{38B5751A-C6F9-4409-950C-F4F9DA17275F}.Debug|Win32.ActiveCfg = Debug|Win32
{38B5751A-C6F9-4409-950C-F4F9DA17275F}.Debug|Win32.Build.0 = Debug|Win32
{38B5751A-C6F9-4409-950C-F4F9DA17275F}.Debug|x64.ActiveCfg = Debug|x64
{38B5751A-C6F9-4409-950C-F4F9DA17275F}.Debug|x64.Build.0 = Debug|x64
{38B5751A-C6F9-4409-950C-F4F9DA17275F}.Release|ARM.ActiveCfg = Release|Win32
{38B5751A-C6F9-4409-950C-F4F9DA17275F}.Release|Win32.ActiveCfg = Release|Win32
{38B5751A-C6F9-4409-950C-F4F9DA17275F}.Release|Win32.Build.0 = Release|Win32
{38B5751A-C6F9-4409-950C-F4F9DA17275F}.Release|x64.ActiveCfg = Release|x64
{38B5751A-C6F9-4409-950C-F4F9DA17275F}.Release|x64.Build.0 = Release|x64
{D3065ADB-8820-4CC7-9B6C-9510833961A3}.Debug|ARM.ActiveCfg = Debug|Win32
{D3065ADB-8820-4CC7-9B6C-9510833961A3}.Debug|Win32.ActiveCfg = Debug|Win32
{D3065ADB-8820-4CC7-9B6C-9510833961A3}.Debug|Win32.Build.0 = Debug|Win32
{D3065ADB-8820-4CC7-9B6C-9510833961A3}.Debug|x64.ActiveCfg = Debug|x64
{D3065ADB-8820-4CC7-9B6C-9510833961A3}.Debug|x64.Build.0 = Debug|x64
{D3065ADB-8820-4CC7-9B6C-9510833961A3}.Release|ARM.ActiveCfg = Release|Win32
{D3065ADB-8820-4CC7-9B6C-9510833961A3}.Release|Win32.ActiveCfg = Release|Win32
{D3065ADB-8820-4CC7-9B6C-9510833961A3}.Release|Win32.Build.0 = Release|Win32
{D3065ADB-8820-4CC7-9B6C-9510833961A3}.Release|x64.ActiveCfg = Release|x64
{D3065ADB-8820-4CC7-9B6C-9510833961A3}.Release|x64.Build.0 = Release|x64
{C2BE5000-7501-4E87-9724-B8D82494FAE6}.Debug|ARM.ActiveCfg = Debug|Win32
{C2BE5000-7501-4E87-9724-B8D82494FAE6}.Debug|Win32.ActiveCfg = Debug|Win32
{C2BE5000-7501-4E87-9724-B8D82494FAE6}.Debug|Win32.Build.0 = Debug|Win32
{C2BE5000-7501-4E87-9724-B8D82494FAE6}.Debug|x64.ActiveCfg = Debug|x64
{C2BE5000-7501-4E87-9724-B8D82494FAE6}.Debug|x64.Build.0 = Debug|x64
{C2BE5000-7501-4E87-9724-B8D82494FAE6}.Release|ARM.ActiveCfg = Release|Win32
{C2BE5000-7501-4E87-9724-B8D82494FAE6}.Release|Win32.ActiveCfg = Release|Win32
{C2BE5000-7501-4E87-9724-B8D82494FAE6}.Release|Win32.Build.0 = Release|Win32
{C2BE5000-7501-4E87-9724-B8D82494FAE6}.Release|x64.ActiveCfg = Release|x64
{C2BE5000-7501-4E87-9724-B8D82494FAE6}.Release|x64.Build.0 = Release|x64
{FDD3C4F2-9805-44EB-9A77-BC1C1C95B547}.Debug|ARM.ActiveCfg = Debug|Win32
{FDD3C4F2-9805-44EB-9A77-BC1C1C95B547}.Debug|Win32.ActiveCfg = Debug|Win32
{FDD3C4F2-9805-44EB-9A77-BC1C1C95B547}.Debug|Win32.Build.0 = Debug|Win32
{FDD3C4F2-9805-44EB-9A77-BC1C1C95B547}.Debug|x64.ActiveCfg = Debug|x64
{FDD3C4F2-9805-44EB-9A77-BC1C1C95B547}.Debug|x64.Build.0 = Debug|x64
{FDD3C4F2-9805-44EB-9A77-BC1C1C95B547}.Release|ARM.ActiveCfg = Release|Win32
{FDD3C4F2-9805-44EB-9A77-BC1C1C95B547}.Release|Win32.ActiveCfg = Release|Win32
{FDD3C4F2-9805-44EB-9A77-BC1C1C95B547}.Release|Win32.Build.0 = Release|Win32
{FDD3C4F2-9805-44EB-9A77-BC1C1C95B547}.Release|x64.ActiveCfg = Release|x64
{FDD3C4F2-9805-44EB-9A77-BC1C1C95B547}.Release|x64.Build.0 = Release|x64
{A8D36F8D-09E6-4174-91C3-7BEAA9C3F04F}.Debug|ARM.ActiveCfg = Debug|Win32
{A8D36F8D-09E6-4174-91C3-7BEAA9C3F04F}.Debug|Win32.ActiveCfg = Debug|Win32
{A8D36F8D-09E6-4174-91C3-7BEAA9C3F04F}.Debug|Win32.Build.0 = Debug|Win32
{A8D36F8D-09E6-4174-91C3-7BEAA9C3F04F}.Debug|x64.ActiveCfg = Debug|x64
{A8D36F8D-09E6-4174-91C3-7BEAA9C3F04F}.Debug|x64.Build.0 = Debug|x64
{A8D36F8D-09E6-4174-91C3-7BEAA9C3F04F}.Release|ARM.ActiveCfg = Release|Win32
{A8D36F8D-09E6-4174-91C3-7BEAA9C3F04F}.Release|Win32.ActiveCfg = Release|Win32
{A8D36F8D-09E6-4174-91C3-7BEAA9C3F04F}.Release|Win32.Build.0 = Release|Win32
{A8D36F8D-09E6-4174-91C3-7BEAA9C3F04F}.Release|x64.ActiveCfg = Release|x64
{A8D36F8D-09E6-4174-91C3-7BEAA9C3F04F}.Release|x64.Build.0 = Release|x64
{8B41752B-5A52-41E4-B7E0-07921C0CC6BF}.Debug|ARM.ActiveCfg = Debug|Win32
{8B41752B-5A52-41E4-B7E0-07921C0CC6BF}.Debug|Win32.ActiveCfg = Debug|Win32
{8B41752B-5A52-41E4-B7E0-07921C0CC6BF}.Debug|Win32.Build.0 = Debug|Win32
{8B41752B-5A52-41E4-B7E0-07921C0CC6BF}.Debug|x64.ActiveCfg = Debug|x64
{8B41752B-5A52-41E4-B7E0-07921C0CC6BF}.Debug|x64.Build.0 = Debug|x64
{8B41752B-5A52-41E4-B7E0-07921C0CC6BF}.Release|ARM.ActiveCfg = Release|Win32
{8B41752B-5A52-41E4-B7E0-07921C0CC6BF}.Release|Win32.ActiveCfg = Release|Win32
{8B41752B-5A52-41E4-B7E0-07921C0CC6BF}.Release|Win32.Build.0 = Release|Win32
{8B41752B-5A52-41E4-B7E0-07921C0CC6BF}.Release|x64.ActiveCfg = Release|x64
{8B41752B-5A52-41E4-B7E0-07921C0CC6BF}.Release|x64.Build.0 = Release|x64
{97521D06-EC47-45D4-8BD0-9E16B3F93B2A}.Debug|ARM.ActiveCfg = Debug|Win32
{97521D06-EC47-45D4-8BD0-9E16B3F93B2A}.Debug|Win32.ActiveCfg = Debug|Win32
{97521D06-EC47-45D4-8BD0-9E16B3F93B2A}.Debug|Win32.Build.0 = Debug|Win32
{97521D06-EC47-45D4-8BD0-9E16B3F93B2A}.Debug|x64.ActiveCfg = Debug|x64
{97521D06-EC47-45D4-8BD0-9E16B3F93B2A}.Debug|x64.Build.0 = Debug|x64
{97521D06-EC47-45D4-8BD0-9E16B3F93B2A}.Release|ARM.ActiveCfg = Release|Win32
{97521D06-EC47-45D4-8BD0-9E16B3F93B2A}.Release|Win32.ActiveCfg = Release|Win32
{97521D06-EC47-45D4-8BD0-9E16B3F93B2A}.Release|Win32.Build.0 = Release|Win32
{97521D06-EC47-45D4-8BD0-9E16B3F93B2A}.Release|x64.ActiveCfg = Release|x64
{97521D06-EC47-45D4-8BD0-9E16B3F93B2A}.Release|x64.Build.0 = Release|x64
{77C78066-746F-4EA6-B3FE-B8C8A4A97891}.Debug|ARM.ActiveCfg = Debug|Win32
{77C78066-746F-4EA6-B3FE-B8C8A4A97891}.Debug|Win32.ActiveCfg = Debug|Win32
{77C78066-746F-4EA6-B3FE-B8C8A4A97891}.Debug|Win32.Build.0 = Debug|Win32
{77C78066-746F-4EA6-B3FE-B8C8A4A97891}.Debug|x64.ActiveCfg = Debug|x64
{77C78066-746F-4EA6-B3FE-B8C8A4A97891}.Debug|x64.Build.0 = Debug|x64
{77C78066-746F-4EA6-B3FE-B8C8A4A97891}.Release|ARM.ActiveCfg = Release|Win32
{77C78066-746F-4EA6-B3FE-B8C8A4A97891}.Release|Win32.ActiveCfg = Release|Win32
{77C78066-746F-4EA6-B3FE-B8C8A4A97891}.Release|Win32.Build.0 = Release|Win32
{77C78066-746F-4EA6-B3FE-B8C8A4A97891}.Release|x64.ActiveCfg = Release|x64
{77C78066-746F-4EA6-B3FE-B8C8A4A97891}.Release|x64.Build.0 = Release|x64
{0178B127-6269-407D-B112-93877BB62776}.Debug|ARM.ActiveCfg = Debug|Win32
{0178B127-6269-407D-B112-93877BB62776}.Debug|Win32.ActiveCfg = Debug|Win32
{0178B127-6269-407D-B112-93877BB62776}.Debug|Win32.Build.0 = Debug|Win32
{0178B127-6269-407D-B112-93877BB62776}.Debug|x64.ActiveCfg = Debug|x64
{0178B127-6269-407D-B112-93877BB62776}.Debug|x64.Build.0 = Debug|x64
{0178B127-6269-407D-B112-93877BB62776}.Release|ARM.ActiveCfg = Release|Win32
{0178B127-6269-407D-B112-93877BB62776}.Release|Win32.ActiveCfg = Release|Win32
{0178B127-6269-407D-B112-93877BB62776}.Release|Win32.Build.0 = Release|Win32
{0178B127-6269-407D-B112-93877BB62776}.Release|x64.ActiveCfg = Release|x64
{0178B127-6269-407D-B112-93877BB62776}.Release|x64.Build.0 = Release|x64
{73632960-B3A6-464D-83A3-4B43365F19B8}.Debug|ARM.ActiveCfg = Debug|Win32
{73632960-B3A6-464D-83A3-4B43365F19B8}.Debug|Win32.ActiveCfg = Debug|Win32
{73632960-B3A6-464D-83A3-4B43365F19B8}.Debug|Win32.Build.0 = Debug|Win32
{73632960-B3A6-464D-83A3-4B43365F19B8}.Debug|x64.ActiveCfg = Debug|x64
{73632960-B3A6-464D-83A3-4B43365F19B8}.Debug|x64.Build.0 = Debug|x64
{73632960-B3A6-464D-83A3-4B43365F19B8}.Release|ARM.ActiveCfg = Release|Win32
{73632960-B3A6-464D-83A3-4B43365F19B8}.Release|Win32.ActiveCfg = Release|Win32
{73632960-B3A6-464D-83A3-4B43365F19B8}.Release|Win32.Build.0 = Release|Win32
{73632960-B3A6-464D-83A3-4B43365F19B8}.Release|x64.ActiveCfg = Release|x64
{73632960-B3A6-464D-83A3-4B43365F19B8}.Release|x64.Build.0 = Release|x64
{C920062A-0647-4553-A3B2-37C58065664B}.Debug|Win32.ActiveCfg = Debug|Win32
{C920062A-0647-4553-A3B2-37C58065664B}.Debug|Win32.Build.0 = Debug|Win32
{C920062A-0647-4553-A3B2-37C58065664B}.Debug|x64.ActiveCfg = Debug|x64
{C920062A-0647-4553-A3B2-37C58065664B}.Debug|x64.Build.0 = Debug|x64
{C920062A-0647-4553-A3B2-37C58065664B}.Release|Win32.ActiveCfg = Release|Win32
{C920062A-0647-4553-A3B2-37C58065664B}.Release|Win32.Build.0 = Release|Win32
{C920062A-0647-4553-A3B2-37C58065664B}.Release|x64.ActiveCfg = Release|x64
{C920062A-0647-4553-A3B2-37C58065664B}.Release|x64.Build.0 = Release|x64
{37FC2C7F-1904-4811-8955-2F478830EAD1}.Debug|Win32.ActiveCfg = Debug|Win32
{37FC2C7F-1904-4811-8955-2F478830EAD1}.Debug|Win32.Build.0 = Debug|Win32
{37FC2C7F-1904-4811-8955-2F478830EAD1}.Debug|x64.ActiveCfg = Debug|x64
{37FC2C7F-1904-4811-8955-2F478830EAD1}.Debug|x64.Build.0 = Debug|x64
{37FC2C7F-1904-4811-8955-2F478830EAD1}.Release|Win32.ActiveCfg = Release|Win32
{37FC2C7F-1904-4811-8955-2F478830EAD1}.Release|Win32.Build.0 = Release|Win32
{37FC2C7F-1904-4811-8955-2F478830EAD1}.Release|x64.ActiveCfg = Release|x64
{37FC2C7F-1904-4811-8955-2F478830EAD1}.Release|x64.Build.0 = Release|x64
{F5AD9738-1A3D-4906-B9C4-A7D9CE33DC2C}.Debug|ARM.ActiveCfg = Debug|Win32
{F5AD9738-1A3D-4906-B9C4-A7D9CE33DC2C}.Debug|Win32.ActiveCfg = Debug|Win32
{F5AD9738-1A3D-4906-B9C4-A7D9CE33DC2C}.Debug|Win32.Build.0 = Debug|Win32
{F5AD9738-1A3D-4906-B9C4-A7D9CE33DC2C}.Debug|x64.ActiveCfg = Debug|x64
{F5AD9738-1A3D-4906-B9C4-A7D9CE33DC2C}.Debug|x64.Build.0 = Debug|x64
{F5AD9738-1A3D-4906-B9C4-A7D9CE33DC2C}.Release|ARM.ActiveCfg = Release|Win32
{F5AD9738-1A3D-4906-B9C4-A7D9CE33DC2C}.Release|Win32.ActiveCfg = Release|Win32
{F5AD9738-1A3D-4906-B9C4-A7D9CE33DC2C}.Release|Win32.Build.0 = Release|Win32
{F5AD9738-1A3D-4906-B9C4-A7D9CE33DC2C}.Release|x64.ActiveCfg = Release|x64
{F5AD9738-1A3D-4906-B9C4-A7D9CE33DC2C}.Release|x64.Build.0 = Release|x64
{D9DF7F2F-93B7-4810-B5CD-96F4F33C079B}.Debug|ARM.ActiveCfg = Debug|Win32
{D9DF7F2F-93B7-4810-B5CD-96F4F33C079B}.Debug|Win32.ActiveCfg = Debug|Win32
{D9DF7F2F-93B7-4810-B5CD-96F4F33C079B}.Debug|Win32.Build.0 = Debug|Win32
{D9DF7F2F-93B7-4810-B5CD-96F4F33C079B}.Debug|x64.ActiveCfg = Debug|x64
{D9DF7F2F-93B7-4810-B5CD-96F4F33C079B}.Debug|x64.Build.0 = Debug|x64
{D9DF7F2F-93B7-4810-B5CD-96F4F33C079B}.Release|ARM.ActiveCfg = Release|Win32
{D9DF7F2F-93B7-4810-B5CD-96F4F33C079B}.Release|Win32.ActiveCfg = Release|Win32
{D9DF7F2F-93B7-4810-B5CD-96F4F33C079B}.Release|Win32.Build.0 = Release|Win32
{D9DF7F2F-93B7-4810-B5CD-96F4F33C079B}.Release|x64.ActiveCfg = Release|x64
{D9DF7F2F-93B7-4810-B5CD-96F4F33C079B}.Release|x64.Build.0 = Release|x64
{4C8454FE-81D3-4CA3-9927-29BA96F03DAC}.Debug|ARM.ActiveCfg = Debug|Win32
{4C8454FE-81D3-4CA3-9927-29BA96F03DAC}.Debug|Win32.ActiveCfg = Debug|Win32
{4C8454FE-81D3-4CA3-9927-29BA96F03DAC}.Debug|Win32.Build.0 = Debug|Win32
{4C8454FE-81D3-4CA3-9927-29BA96F03DAC}.Debug|x64.ActiveCfg = Debug|x64
{4C8454FE-81D3-4CA3-9927-29BA96F03DAC}.Debug|x64.Build.0 = Debug|x64
{4C8454FE-81D3-4CA3-9927-29BA96F03DAC}.Release|ARM.ActiveCfg = Release|Win32
{4C8454FE-81D3-4CA3-9927-29BA96F03DAC}.Release|Win32.ActiveCfg = Release|Win32
{4C8454FE-81D3-4CA3-9927-29BA96F03DAC}.Release|Win32.Build.0 = Release|Win32
{4C8454FE-81D3-4CA3-9927-29BA96F03DAC}.Release|x64.ActiveCfg = Release|x64
{4C8454FE-81D3-4CA3-9927-29BA96F03DAC}.Release|x64.Build.0 = Release|x64
{203EC78A-0531-43F0-A636-285439BDE025}.Debug|ARM.ActiveCfg = Debug|Win32
{203EC78A-0531-43F0-A636-285439BDE025}.Debug|Win32.ActiveCfg = Debug|Win32
{203EC78A-0531-43F0-A636-285439BDE025}.Debug|Win32.Build.0 = Debug|Win32
{203EC78A-0531-43F0-A636-285439BDE025}.Debug|x64.ActiveCfg = Debug|x64
{203EC78A-0531-43F0-A636-285439BDE025}.Debug|x64.Build.0 = Debug|x64
{203EC78A-0531-43F0-A636-285439BDE025}.Release|ARM.ActiveCfg = Release|Win32
{203EC78A-0531-43F0-A636-285439BDE025}.Release|Win32.ActiveCfg = Release|Win32
{203EC78A-0531-43F0-A636-285439BDE025}.Release|Win32.Build.0 = Release|Win32
{203EC78A-0531-43F0-A636-285439BDE025}.Release|x64.ActiveCfg = Release|x64
{203EC78A-0531-43F0-A636-285439BDE025}.Release|x64.Build.0 = Release|x64
{6B231032-3CB5-4EED-9210-810D666A23A0}.Debug|ARM.ActiveCfg = Debug|Win32
{6B231032-3CB5-4EED-9210-810D666A23A0}.Debug|Win32.ActiveCfg = Debug|Win32
{6B231032-3CB5-4EED-9210-810D666A23A0}.Debug|Win32.Build.0 = Debug|Win32
{6B231032-3CB5-4EED-9210-810D666A23A0}.Debug|x64.ActiveCfg = Debug|x64
{6B231032-3CB5-4EED-9210-810D666A23A0}.Debug|x64.Build.0 = Debug|x64
{6B231032-3CB5-4EED-9210-810D666A23A0}.Release|ARM.ActiveCfg = Release|Win32
{6B231032-3CB5-4EED-9210-810D666A23A0}.Release|Win32.ActiveCfg = Release|Win32
{6B231032-3CB5-4EED-9210-810D666A23A0}.Release|Win32.Build.0 = Release|Win32
{6B231032-3CB5-4EED-9210-810D666A23A0}.Release|x64.ActiveCfg = Release|x64
{6B231032-3CB5-4EED-9210-810D666A23A0}.Release|x64.Build.0 = Release|x64
{DBA4088D-F6F9-4F8F-8820-082A4765C16C}.Debug|ARM.ActiveCfg = Debug|Win32
{DBA4088D-F6F9-4F8F-8820-082A4765C16C}.Debug|Win32.ActiveCfg = Debug|Win32
{DBA4088D-F6F9-4F8F-8820-082A4765C16C}.Debug|Win32.Build.0 = Debug|Win32
{DBA4088D-F6F9-4F8F-8820-082A4765C16C}.Debug|x64.ActiveCfg = Debug|x64
{DBA4088D-F6F9-4F8F-8820-082A4765C16C}.Debug|x64.Build.0 = Debug|x64
{DBA4088D-F6F9-4F8F-8820-082A4765C16C}.Release|ARM.ActiveCfg = Release|Win32
{DBA4088D-F6F9-4F8F-8820-082A4765C16C}.Release|Win32.ActiveCfg = Release|Win32
{DBA4088D-F6F9-4F8F-8820-082A4765C16C}.Release|Win32.Build.0 = Release|Win32
{DBA4088D-F6F9-4F8F-8820-082A4765C16C}.Release|x64.ActiveCfg = Release|x64
{DBA4088D-F6F9-4F8F-8820-082A4765C16C}.Release|x64.Build.0 = Release|x64
{C2B04507-2521-4801-BF0D-5FD79D6D518C}.Debug|ARM.ActiveCfg = Debug|Win32
{C2B04507-2521-4801-BF0D-5FD79D6D518C}.Debug|Win32.ActiveCfg = Debug|Win32
{C2B04507-2521-4801-BF0D-5FD79D6D518C}.Debug|Win32.Build.0 = Debug|Win32
{C2B04507-2521-4801-BF0D-5FD79D6D518C}.Debug|x64.ActiveCfg = Debug|x64
{C2B04507-2521-4801-BF0D-5FD79D6D518C}.Debug|x64.Build.0 = Debug|x64
{C2B04507-2521-4801-BF0D-5FD79D6D518C}.Release|ARM.ActiveCfg = Release|Win32
{C2B04507-2521-4801-BF0D-5FD79D6D518C}.Release|Win32.ActiveCfg = Release|Win32
{C2B04507-2521-4801-BF0D-5FD79D6D518C}.Release|Win32.Build.0 = Release|Win32
{C2B04507-2521-4801-BF0D-5FD79D6D518C}.Release|x64.ActiveCfg = Release|x64
{C2B04507-2521-4801-BF0D-5FD79D6D518C}.Release|x64.Build.0 = Release|x64
{631C23CE-6C1D-4875-88F0-85E0A42B36EA}.Debug|ARM.ActiveCfg = Debug|Win32
{631C23CE-6C1D-4875-88F0-85E0A42B36EA}.Debug|Win32.ActiveCfg = Debug|Win32
{631C23CE-6C1D-4875-88F0-85E0A42B36EA}.Debug|Win32.Build.0 = Debug|Win32
{631C23CE-6C1D-4875-88F0-85E0A42B36EA}.Debug|x64.ActiveCfg = Debug|x64
{631C23CE-6C1D-4875-88F0-85E0A42B36EA}.Debug|x64.Build.0 = Debug|x64
{631C23CE-6C1D-4875-88F0-85E0A42B36EA}.Release|ARM.ActiveCfg = Release|Win32
{631C23CE-6C1D-4875-88F0-85E0A42B36EA}.Release|Win32.ActiveCfg = Release|Win32
{631C23CE-6C1D-4875-88F0-85E0A42B36EA}.Release|Win32.Build.0 = Release|Win32
{631C23CE-6C1D-4875-88F0-85E0A42B36EA}.Release|x64.ActiveCfg = Release|x64
{631C23CE-6C1D-4875-88F0-85E0A42B36EA}.Release|x64.Build.0 = Release|x64
{E4993E82-D68A-46CA-BAE0-9D35E172E46F}.Debug|ARM.ActiveCfg = Debug|Win32
{E4993E82-D68A-46CA-BAE0-9D35E172E46F}.Debug|Win32.ActiveCfg = Debug|Win32
{E4993E82-D68A-46CA-BAE0-9D35E172E46F}.Debug|Win32.Build.0 = Debug|Win32
{E4993E82-D68A-46CA-BAE0-9D35E172E46F}.Debug|x64.ActiveCfg = Debug|x64
{E4993E82-D68A-46CA-BAE0-9D35E172E46F}.Debug|x64.Build.0 = Debug|x64
{E4993E82-D68A-46CA-BAE0-9D35E172E46F}.Release|ARM.ActiveCfg = Release|Win32
{E4993E82-D68A-46CA-BAE0-9D35E172E46F}.Release|Win32.ActiveCfg = Release|Win32
{E4993E82-D68A-46CA-BAE0-9D35E172E46F}.Release|Win32.Build.0 = Release|Win32
{E4993E82-D68A-46CA-BAE0-9D35E172E46F}.Release|x64.ActiveCfg = Release|x64
{E4993E82-D68A-46CA-BAE0-9D35E172E46F}.Release|x64.Build.0 = Release|x64
{62D4B15D-7A90-4ECB-BA19-5E021D6A21BC}.Debug|ARM.ActiveCfg = Debug|Win32
{62D4B15D-7A90-4ECB-BA19-5E021D6A21BC}.Debug|Win32.ActiveCfg = Debug|Win32
{62D4B15D-7A90-4ECB-BA19-5E021D6A21BC}.Debug|Win32.Build.0 = Debug|Win32
{62D4B15D-7A90-4ECB-BA19-5E021D6A21BC}.Debug|x64.ActiveCfg = Debug|x64
{62D4B15D-7A90-4ECB-BA19-5E021D6A21BC}.Debug|x64.Build.0 = Debug|x64
{62D4B15D-7A90-4ECB-BA19-5E021D6A21BC}.Release|ARM.ActiveCfg = Release|Win32
{62D4B15D-7A90-4ECB-BA19-5E021D6A21BC}.Release|Win32.ActiveCfg = Release|Win32
{62D4B15D-7A90-4ECB-BA19-5E021D6A21BC}.Release|Win32.Build.0 = Release|Win32
{62D4B15D-7A90-4ECB-BA19-5E021D6A21BC}.Release|x64.ActiveCfg = Release|x64
{62D4B15D-7A90-4ECB-BA19-5E021D6A21BC}.Release|x64.Build.0 = Release|x64
{9D4211F7-2C77-439C-82F0-30A4E43BA569}.Debug|ARM.ActiveCfg = Debug|Win32
{9D4211F7-2C77-439C-82F0-30A4E43BA569}.Debug|Win32.ActiveCfg = Debug|Win32
{9D4211F7-2C77-439C-82F0-30A4E43BA569}.Debug|Win32.Build.0 = Debug|Win32
{9D4211F7-2C77-439C-82F0-30A4E43BA569}.Debug|x64.ActiveCfg = Debug|x64
{9D4211F7-2C77-439C-82F0-30A4E43BA569}.Debug|x64.Build.0 = Debug|x64
{9D4211F7-2C77-439C-82F0-30A4E43BA569}.Release|ARM.ActiveCfg = Release|Win32
{9D4211F7-2C77-439C-82F0-30A4E43BA569}.Release|Win32.ActiveCfg = Release|Win32
{9D4211F7-2C77-439C-82F0-30A4E43BA569}.Release|Win32.Build.0 = Release|Win32
{9D4211F7-2C77-439C-82F0-30A4E43BA569}.Release|x64.ActiveCfg = Release|x64
{9D4211F7-2C77-439C-82F0-30A4E43BA569}.Release|x64.Build.0 = Release|x64
{691EE0C0-DC57-4A48-8AEE-8ED75EB3A057}.Debug|ARM.ActiveCfg = Debug|Win32
{691EE0C0-DC57-4A48-8AEE-8ED75EB3A057}.Debug|Win32.ActiveCfg = Debug|Win32
{691EE0C0-DC57-4A48-8AEE-8ED75EB3A057}.Debug|Win32.Build.0 = Debug|Win32
{691EE0C0-DC57-4A48-8AEE-8ED75EB3A057}.Debug|x64.ActiveCfg = Debug|x64
{691EE0C0-DC57-4A48-8AEE-8ED75EB3A057}.Debug|x64.Build.0 = Debug|x64
{691EE0C0-DC57-4A48-8AEE-8ED75EB3A057}.Release|ARM.ActiveCfg = Release|Win32
{691EE0C0-DC57-4A48-8AEE-8ED75EB3A057}.Release|Win32.ActiveCfg = Release|Win32
{691EE0C0-DC57-4A48-8AEE-8ED75EB3A057}.Release|Win32.Build.0 = Release|Win32
{691EE0C0-DC57-4A48-8AEE-8ED75EB3A057}.Release|x64.ActiveCfg = Release|x64
{691EE0C0-DC57-4A48-8AEE-8ED75EB3A057}.Release|x64.Build.0 = Release|x64
{C7891A65-80AB-4245-912E-5F1E17B0E6C4}.Debug|ARM.ActiveCfg = Debug|Win32
{C7891A65-80AB-4245-912E-5F1E17B0E6C4}.Debug|Win32.ActiveCfg = Debug|Win32
{C7891A65-80AB-4245-912E-5F1E17B0E6C4}.Debug|Win32.Build.0 = Debug|Win32
{C7891A65-80AB-4245-912E-5F1E17B0E6C4}.Debug|x64.ActiveCfg = Debug|x64
{C7891A65-80AB-4245-912E-5F1E17B0E6C4}.Debug|x64.Build.0 = Debug|x64
{C7891A65-80AB-4245-912E-5F1E17B0E6C4}.Release|ARM.ActiveCfg = Release|Win32
{C7891A65-80AB-4245-912E-5F1E17B0E6C4}.Release|Win32.ActiveCfg = Release|Win32
{C7891A65-80AB-4245-912E-5F1E17B0E6C4}.Release|Win32.Build.0 = Release|Win32
{C7891A65-80AB-4245-912E-5F1E17B0E6C4}.Release|x64.ActiveCfg = Release|x64
{C7891A65-80AB-4245-912E-5F1E17B0E6C4}.Release|x64.Build.0 = Release|x64
{E7611F49-F088-4175-9446-6111444E72C8}.Debug|ARM.ActiveCfg = Debug|Win32
{E7611F49-F088-4175-9446-6111444E72C8}.Debug|Win32.ActiveCfg = Debug|Win32
{E7611F49-F088-4175-9446-6111444E72C8}.Debug|Win32.Build.0 = Debug|Win32
{E7611F49-F088-4175-9446-6111444E72C8}.Debug|x64.ActiveCfg = Debug|x64
{E7611F49-F088-4175-9446-6111444E72C8}.Debug|x64.Build.0 = Debug|x64
{E7611F49-F088-4175-9446-6111444E72C8}.Release|ARM.ActiveCfg = Release|Win32
{E7611F49-F088-4175-9446-6111444E72C8}.Release|Win32.ActiveCfg = Release|Win32
{E7611F49-F088-4175-9446-6111444E72C8}.Release|Win32.Build.0 = Release|Win32
{E7611F49-F088-4175-9446-6111444E72C8}.Release|x64.ActiveCfg = Release|x64
{E7611F49-F088-4175-9446-6111444E72C8}.Release|x64.Build.0 = Release|x64
{659D0C08-D4ED-4BF3-B02B-2D8D4B5A7A7A}.Debug|ARM.ActiveCfg = Debug|Win32
{659D0C08-D4ED-4BF3-B02B-2D8D4B5A7A7A}.Debug|Win32.ActiveCfg = Debug|Win32
{659D0C08-D4ED-4BF3-B02B-2D8D4B5A7A7A}.Debug|Win32.Build.0 = Debug|Win32
{659D0C08-D4ED-4BF3-B02B-2D8D4B5A7A7A}.Debug|x64.ActiveCfg = Debug|x64
{659D0C08-D4ED-4BF3-B02B-2D8D4B5A7A7A}.Debug|x64.Build.0 = Debug|x64
{659D0C08-D4ED-4BF3-B02B-2D8D4B5A7A7A}.Release|ARM.ActiveCfg = Release|Win32
{659D0C08-D4ED-4BF3-B02B-2D8D4B5A7A7A}.Release|Win32.ActiveCfg = Release|Win32
{659D0C08-D4ED-4BF3-B02B-2D8D4B5A7A7A}.Release|Win32.Build.0 = Release|Win32
{659D0C08-D4ED-4BF3-B02B-2D8D4B5A7A7A}.Release|x64.ActiveCfg = Release|x64
{659D0C08-D4ED-4BF3-B02B-2D8D4B5A7A7A}.Release|x64.Build.0 = Release|x64
{B1D53358-37BD-48BC-B27C-68BAF1E78508}.Debug|ARM.ActiveCfg = Debug|ARM
{B1D53358-37BD-48BC-B27C-68BAF1E78508}.Debug|ARM.Build.0 = Debug|ARM
{B1D53358-37BD-48BC-B27C-68BAF1E78508}.Debug|Win32.ActiveCfg = Debug|Win32
{B1D53358-37BD-48BC-B27C-68BAF1E78508}.Debug|Win32.Build.0 = Debug|Win32
{B1D53358-37BD-48BC-B27C-68BAF1E78508}.Debug|x64.ActiveCfg = Debug|x64
{B1D53358-37BD-48BC-B27C-68BAF1E78508}.Debug|x64.Build.0 = Debug|x64
{B1D53358-37BD-48BC-B27C-68BAF1E78508}.Release|ARM.ActiveCfg = Release|ARM
{B1D53358-37BD-48BC-B27C-68BAF1E78508}.Release|ARM.Build.0 = Release|ARM
{B1D53358-37BD-48BC-B27C-68BAF1E78508}.Release|Win32.ActiveCfg = Release|Win32
{B1D53358-37BD-48BC-B27C-68BAF1E78508}.Release|Win32.Build.0 = Release|Win32
{B1D53358-37BD-48BC-B27C-68BAF1E78508}.Release|x64.ActiveCfg = Release|x64
{B1D53358-37BD-48BC-B27C-68BAF1E78508}.Release|x64.Build.0 = Release|x64
{6786C051-383B-47E0-9E82-B8B994E06A25}.Debug|ARM.ActiveCfg = Debug|ARM
{6786C051-383B-47E0-9E82-B8B994E06A25}.Debug|ARM.Build.0 = Debug|ARM
{6786C051-383B-47E0-9E82-B8B994E06A25}.Debug|Win32.ActiveCfg = Debug|Win32
{6786C051-383B-47E0-9E82-B8B994E06A25}.Debug|Win32.Build.0 = Debug|Win32
{6786C051-383B-47E0-9E82-B8B994E06A25}.Debug|x64.ActiveCfg = Debug|x64
{6786C051-383B-47E0-9E82-B8B994E06A25}.Debug|x64.Build.0 = Debug|x64
{6786C051-383B-47E0-9E82-B8B994E06A25}.Release|ARM.ActiveCfg = Release|ARM
{6786C051-383B-47E0-9E82-B8B994E06A25}.Release|ARM.Build.0 = Release|ARM
{6786C051-383B-47E0-9E82-B8B994E06A25}.Release|Win32.ActiveCfg = Release|Win32
{6786C051-383B-47E0-9E82-B8B994E06A25}.Release|Win32.Build.0 = Release|Win32
{6786C051-383B-47E0-9E82-B8B994E06A25}.Release|x64.ActiveCfg = Release|x64
{6786C051-383B-47E0-9E82-B8B994E06A25}.Release|x64.Build.0 = Release|x64
{C10CF34B-3F79-430E-AD38-5A32DC0589C2}.Debug|ARM.ActiveCfg = Debug|ARM
{C10CF34B-3F79-430E-AD38-5A32DC0589C2}.Debug|ARM.Build.0 = Debug|ARM
{C10CF34B-3F79-430E-AD38-5A32DC0589C2}.Debug|Win32.ActiveCfg = Debug|Win32
{C10CF34B-3F79-430E-AD38-5A32DC0589C2}.Debug|Win32.Build.0 = Debug|Win32
{C10CF34B-3F79-430E-AD38-5A32DC0589C2}.Debug|x64.ActiveCfg = Debug|x64
{C10CF34B-3F79-430E-AD38-5A32DC0589C2}.Debug|x64.Build.0 = Debug|x64
{C10CF34B-3F79-430E-AD38-5A32DC0589C2}.Release|ARM.ActiveCfg = Release|ARM
{C10CF34B-3F79-430E-AD38-5A32DC0589C2}.Release|ARM.Build.0 = Release|ARM
{C10CF34B-3F79-430E-AD38-5A32DC0589C2}.Release|Win32.ActiveCfg = Release|Win32
{C10CF34B-3F79-430E-AD38-5A32DC0589C2}.Release|Win32.Build.0 = Release|Win32
{C10CF34B-3F79-430E-AD38-5A32DC0589C2}.Release|x64.ActiveCfg = Release|x64
{C10CF34B-3F79-430E-AD38-5A32DC0589C2}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
GlobalSection(ExtensibilityGlobals) = postSolution
SolutionGuid = {A714726C-FE2D-466C-95F3-06C5C4EAE54F}
EndGlobalSection
GlobalSection(SubversionScc) = preSolution
Svn-Managed = True
Manager = AnkhSVN - Subversion Support for Visual Studio
EndGlobalSection
EndGlobal

10
intl/icu/source/allinone/icucheck.bat
View file

@ -52,7 +52,7 @@ set ICUFAILCNT=0
@echo ==== %THT% =========================================================================
%ICUINFO_CMD% %ICUINFO_OPTS%
@IF NOT ERRORLEVEL 1 GOTO OK_%THT%
@IF %ERRORLEVEL% EQU 0 GOTO OK_%THT%
@set ICUFAILED=%ICUFAILED% %THT%
@set ICUFAILCNT=1
:OK_icuinfo
@ -63,7 +63,7 @@ set ICUFAILCNT=0
@cd %ICU_ICUDIR%\source\test\intltest
%INTLTEST_CMD% %INTLTEST_OPTS%
@IF NOT ERRORLEVEL 1 GOTO OK_%THT%
@IF %ERRORLEVEL% EQU 0 GOTO OK_%THT%
@set ICUFAILED=%ICUFAILED% %THT%
@set ICUFAILCNT=1
:OK_intltest
@ -74,7 +74,7 @@ set ICUFAILCNT=0
@cd %ICU_ICUDIR%\source\test\iotest
%IOTEST_CMD% %IOTEST_OPTS%
@IF NOT ERRORLEVEL 1 GOTO OK_%THT%
@IF %ERRORLEVEL% EQU 0 GOTO OK_%THT%
@set ICUFAILED=%ICUFAILED% %THT%
@set ICUFAILCNT=1
:OK_IOTEST
@ -85,7 +85,7 @@ set ICUFAILCNT=0
@cd %ICU_ICUDIR%\source\test\cintltst
%CINTLTST_CMD% %CINTLTST_OPTS%
@IF NOT ERRORLEVEL 1 GOTO OK_%THT%
@IF %ERRORLEVEL% EQU 0 GOTO OK_%THT%
@set ICUFAILED=%ICUFAILED% %THT%
@set ICUFAILCNT=1
:OK_cintltst
@ -97,7 +97,7 @@ set ICUFAILCNT=0
@REM @cd %ICU_ICUDIR%\source\test\letest
@REM %LETST_CMD% %LETEST_OPTS%
@REM @IF NOT ERRORLEVEL 1 GOTO OK_%THT%
@REM @IF %ERRORLEVEL% EQU 0 GOTO OK_%THT%
@REM @set ICUFAILED=%ICUFAILED% %THT%
@REM @set ICUFAILCNT=1
@REM :OK_letest

18
intl/icu/source/common/Makefile.in
View file

@ -81,7 +81,7 @@ LIBS = $(LIBICUDT) $(DEFAULT_LIBS)
OBJECTS = errorcode.o putil.o umath.o utypes.o uinvchar.o umutex.o ucln_cmn.o \
uinit.o uobject.o cmemory.o charstr.o cstr.o \
udata.o ucmndata.o udatamem.o umapfile.o udataswp.o ucol_swp.o utrace.o \
udata.o ucmndata.o udatamem.o umapfile.o udataswp.o utrie_swap.o ucol_swp.o utrace.o \
uhash.o uhash_us.o uenum.o ustrenum.o uvector.o ustack.o uvectr32.o uvectr64.o \
ucnv.o ucnv_bld.o ucnv_cnv.o ucnv_io.o ucnv_cb.o ucnv_err.o ucnvlat1.o \
ucnv_u7.o ucnv_u8.o ucnv_u16.o ucnv_u32.o ucnvscsu.o ucnvbocu.o \
@ -89,28 +89,32 @@ ucnv_ext.o ucnvmbcs.o ucnv2022.o ucnvhz.o ucnv_lmb.o ucnvisci.o ucnvdisp.o ucnv_
resource.o uresbund.o ures_cnv.o uresdata.o resbund.o resbund_cnv.o \
ucurr.o \
messagepattern.o ucat.o locmap.o uloc.o locid.o locutil.o locavailable.o locdispnames.o locdspnm.o loclikely.o locresdata.o \
bytestream.o stringpiece.o \
bytestream.o stringpiece.o bytesinkutil.o \
stringtriebuilder.o bytestriebuilder.o \
bytestrie.o bytestrieiterator.o \
ucharstrie.o ucharstriebuilder.o ucharstrieiterator.o \
dictionarydata.o \
edits.o \
appendable.o ustr_cnv.o unistr_cnv.o unistr.o unistr_case.o unistr_props.o \
utf_impl.o ustring.o ustrcase.o ucasemap.o ucasemap_titlecase_brkiter.o cstring.o ustrfmt.o ustrtrns.o ustr_wcs.o utext.o \
unistr_case_locale.o ustrcase_locale.o unistr_titlecase_brkiter.o ustr_titlecase_brkiter.o \
normalizer2impl.o normalizer2.o filterednormalizer2.o normlzr.o unorm.o unormcmp.o loadednormalizer2impl.o \
chariter.o schriter.o uchriter.o uiter.o \
patternprops.o uchar.o uprops.o ucase.o propname.o ubidi_props.o ubidi.o ubidiwrt.o ubidiln.o ushape.o \
patternprops.o uchar.o uprops.o ucase.o propname.o ubidi_props.o characterproperties.o \
ubidi.o ubidiwrt.o ubidiln.o ushape.o \
uscript.o uscript_props.o usc_impl.o unames.o \
utrie.o utrie2.o utrie2_builder.o bmpset.o unisetspan.o uset_props.o uniset_props.o uniset_closure.o uset.o uniset.o usetiter.o ruleiter.o caniter.o unifilt.o unifunct.o \
utrie.o utrie2.o utrie2_builder.o ucptrie.o umutablecptrie.o \
bmpset.o unisetspan.o uset_props.o uniset_props.o uniset_closure.o uset.o uniset.o usetiter.o ruleiter.o caniter.o unifilt.o unifunct.o \
uarrsort.o brkiter.o ubrk.o brkeng.o dictbe.o filteredbrk.o \
rbbi.o rbbidata.o rbbinode.o rbbirb.o rbbiscan.o rbbisetb.o rbbistbl.o rbbitblb.o \
rbbi.o rbbidata.o rbbinode.o rbbirb.o rbbiscan.o rbbisetb.o rbbistbl.o rbbitblb.o rbbi_cache.o \
serv.o servnotf.o servls.o servlk.o servlkf.o servrbf.o servslkf.o \
uidna.o usprep.o uts46.o punycode.o \
util.o util_props.o parsepos.o locbased.o cwchar.o wintz.o dtintrv.o ucnvsel.o propsvec.o \
ulist.o uloc_tag.o icudataver.o icuplug.o listformatter.o ulistformatter.o \
ulist.o uloc_tag.o icudataver.o icuplug.o \
sharedobject.o simpleformatter.o unifiedcache.o uloc_keytype.o \
ubiditransform.o \
pluralmap.o
pluralmap.o \
static_unicode_sets.o
## Header files to install
HEADERS = $(srcdir)/unicode/*.h

4
intl/icu/source/common/appendable.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -6,7 +6,7 @@
* Corporation and others. All Rights Reserved.
*******************************************************************************
* file name: appendable.cpp
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*

120
intl/icu/source/common/bmpset.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
@ -8,7 +8,7 @@
*
******************************************************************************
* file name: bmpset.cpp
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
@ -28,7 +28,7 @@ U_NAMESPACE_BEGIN
BMPSet::BMPSet(const int32_t *parentList, int32_t parentListLength) :
list(parentList), listLength(parentListLength) {
uprv_memset(asciiBytes, 0, sizeof(asciiBytes));
uprv_memset(latin1Contains, 0, sizeof(latin1Contains));
uprv_memset(table7FF, 0, sizeof(table7FF));
uprv_memset(bmpBlockBits, 0, sizeof(bmpBlockBits));
@ -45,14 +45,16 @@ BMPSet::BMPSet(const int32_t *parentList, int32_t parentListLength) :
list4kStarts[i]=findCodePoint(i<<12, list4kStarts[i-1], listLength-1);
}
list4kStarts[0x11]=listLength-1;
containsFFFD=containsSlow(0xfffd, list4kStarts[0xf], list4kStarts[0x10]);
initBits();
overrideIllegal();
}
BMPSet::BMPSet(const BMPSet &otherBMPSet, const int32_t *newParentList, int32_t newParentListLength) :
containsFFFD(otherBMPSet.containsFFFD),
list(newParentList), listLength(newParentListLength) {
uprv_memcpy(asciiBytes, otherBMPSet.asciiBytes, sizeof(asciiBytes));
uprv_memcpy(latin1Contains, otherBMPSet.latin1Contains, sizeof(latin1Contains));
uprv_memcpy(table7FF, otherBMPSet.table7FF, sizeof(table7FF));
uprv_memcpy(bmpBlockBits, otherBMPSet.bmpBlockBits, sizeof(bmpBlockBits));
uprv_memcpy(list4kStarts, otherBMPSet.list4kStarts, sizeof(list4kStarts));
@ -98,9 +100,9 @@ static void set32x64Bits(uint32_t table[64], int32_t start, int32_t limit) {
++lead;
}
if(lead<limitLead) {
bits=~((1<<lead)-1);
bits=~(((unsigned)1<<lead)-1);
if(limitLead<0x20) {
bits&=(1<<limitLead)-1;
bits&=((unsigned)1<<limitLead)-1;
}
for(trail=0; trail<64; ++trail) {
table[trail]|=bits;
@ -120,7 +122,7 @@ void BMPSet::initBits() {
UChar32 start, limit;
int32_t listIndex=0;
// Set asciiBytes[].
// Set latin1Contains[].
do {
start=list[listIndex++];
if(listIndex<listLength) {
@ -128,13 +130,30 @@ void BMPSet::initBits() {
} else {
limit=0x110000;
}
if(start>=0x80) {
if(start>=0x100) {
break;
}
do {
asciiBytes[start++]=1;
} while(start<limit && start<0x80);
} while(limit<=0x80);
latin1Contains[start++]=1;
} while(start<limit && start<0x100);
} while(limit<=0x100);
// Find the first range overlapping with (or after) 80..FF again,
// to include them in table7FF as well.
for(listIndex=0;;) {
start=list[listIndex++];
if(listIndex<listLength) {
limit=list[listIndex++];
} else {
limit=0x110000;
}
if(limit>0x80) {
if(start<0x80) {
start=0x80;
}
break;
}
}
// Set table7FF[].
while(start<0x800) {
@ -204,19 +223,14 @@ void BMPSet::initBits() {
* for faster validity checking at runtime.
* No need to set 0 values where they were reset to 0 in the constructor
* and not modified by initBits().
* (asciiBytes[] trail bytes, table7FF[] 0..7F, bmpBlockBits[] 0..7FF)
* (table7FF[] 0..7F, bmpBlockBits[] 0..7FF)
* Need to set 0 values for surrogates D800..DFFF.
*/
void BMPSet::overrideIllegal() {
uint32_t bits, mask;
int32_t i;
if(containsSlow(0xfffd, list4kStarts[0xf], list4kStarts[0x10])) {
// contains(FFFD)==TRUE
for(i=0x80; i<0xc0; ++i) {
asciiBytes[i]=1;
}
if(containsFFFD) {
bits=3; // Lead bytes 0xC0 and 0xC1.
for(i=0; i<64; ++i) {
table7FF[i]|=bits;
@ -227,14 +241,13 @@ void BMPSet::overrideIllegal() {
bmpBlockBits[i]|=bits;
}
mask=~(0x10001<<0xd); // Lead byte 0xED.
mask= static_cast<uint32_t>(~(0x10001<<0xd)); // Lead byte 0xED.
bits=1<<0xd;
for(i=32; i<64; ++i) { // Second half of 4k block.
bmpBlockBits[i]=(bmpBlockBits[i]&mask)|bits;
}
} else {
// contains(FFFD)==FALSE
mask=~(0x10001<<0xd); // Lead byte 0xED.
mask= static_cast<uint32_t>(~(0x10001<<0xd)); // Lead byte 0xED.
for(i=32; i<64; ++i) { // Second half of 4k block.
bmpBlockBits[i]&=mask;
}
@ -277,8 +290,8 @@ int32_t BMPSet::findCodePoint(UChar32 c, int32_t lo, int32_t hi) const {
UBool
BMPSet::contains(UChar32 c) const {
if((uint32_t)c<=0x7f) {
return (UBool)asciiBytes[c];
if((uint32_t)c<=0xff) {
return (UBool)latin1Contains[c];
} else if((uint32_t)c<=0x7ff) {
return (UBool)((table7FF[c&0x3f]&((uint32_t)1<<(c>>6)))!=0);
} else if((uint32_t)c<0xd800 || (c>=0xe000 && c<=0xffff)) {
@ -314,8 +327,8 @@ BMPSet::span(const UChar *s, const UChar *limit, USetSpanCondition spanCondition
// span
do {
c=*s;
if(c<=0x7f) {
if(!asciiBytes[c]) {
if(c<=0xff) {
if(!latin1Contains[c]) {
break;
}
} else if(c<=0x7ff) {
@ -354,8 +367,8 @@ BMPSet::span(const UChar *s, const UChar *limit, USetSpanCondition spanCondition
// span not
do {
c=*s;
if(c<=0x7f) {
if(asciiBytes[c]) {
if(c<=0xff) {
if(latin1Contains[c]) {
break;
}
} else if(c<=0x7ff) {
@ -403,8 +416,8 @@ BMPSet::spanBack(const UChar *s, const UChar *limit, USetSpanCondition spanCondi
// span
for(;;) {
c=*(--limit);
if(c<=0x7f) {
if(!asciiBytes[c]) {
if(c<=0xff) {
if(!latin1Contains[c]) {
break;
}
} else if(c<=0x7ff) {
@ -446,8 +459,8 @@ BMPSet::spanBack(const UChar *s, const UChar *limit, USetSpanCondition spanCondi
// span not
for(;;) {
c=*(--limit);
if(c<=0x7f) {
if(asciiBytes[c]) {
if(c<=0xff) {
if(latin1Contains[c]) {
break;
}
} else if(c<=0x7ff) {
@ -497,22 +510,22 @@ const uint8_t *
BMPSet::spanUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanCondition) const {
const uint8_t *limit=s+length;
uint8_t b=*s;
if((int8_t)b>=0) {
if(U8_IS_SINGLE(b)) {
// Initial all-ASCII span.
if(spanCondition) {
do {
if(!asciiBytes[b] || ++s==limit) {
if(!latin1Contains[b] || ++s==limit) {
return s;
}
b=*s;
} while((int8_t)b>=0);
} while(U8_IS_SINGLE(b));
} else {
do {
if(asciiBytes[b] || ++s==limit) {
if(latin1Contains[b] || ++s==limit) {
return s;
}
b=*s;
} while((int8_t)b>=0);
} while(U8_IS_SINGLE(b));
}
length=(int32_t)(limit-s);
}
@ -540,20 +553,20 @@ BMPSet::spanUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanConditi
// single trail byte, check for preceding 3- or 4-byte lead byte
if(length>=2 && (b=*(limit-2))>=0xe0) {
limit-=2;
if(asciiBytes[0x80]!=spanCondition) {
if(containsFFFD!=spanCondition) {
limit0=limit;
}
} else if(b<0xc0 && b>=0x80 && length>=3 && (b=*(limit-3))>=0xf0) {
// 4-byte lead byte with only two trail bytes
limit-=3;
if(asciiBytes[0x80]!=spanCondition) {
if(containsFFFD!=spanCondition) {
limit0=limit;
}
}
} else {
// lead byte with no trail bytes
--limit;
if(asciiBytes[0x80]!=spanCondition) {
if(containsFFFD!=spanCondition) {
limit0=limit;
}
}
@ -563,26 +576,26 @@ BMPSet::spanUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanConditi
while(s<limit) {
b=*s;
if(b<0xc0) {
// ASCII; or trail bytes with the result of contains(FFFD).
if(U8_IS_SINGLE(b)) {
// ASCII
if(spanCondition) {
do {
if(!asciiBytes[b]) {
if(!latin1Contains[b]) {
return s;
} else if(++s==limit) {
return limit0;
}
b=*s;
} while(b<0xc0);
} while(U8_IS_SINGLE(b));
} else {
do {
if(asciiBytes[b]) {
if(latin1Contains[b]) {
return s;
} else if(++s==limit) {
return limit0;
}
b=*s;
} while(b<0xc0);
} while(U8_IS_SINGLE(b));
}
}
++s; // Advance past the lead byte.
@ -619,7 +632,7 @@ BMPSet::spanUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanConditi
UChar32 c=((UChar32)(b-0xf0)<<18)|((UChar32)t1<<12)|(t2<<6)|t3;
if( ( (0x10000<=c && c<=0x10ffff) ?
containsSlow(c, list4kStarts[0x10], list4kStarts[0x11]) :
asciiBytes[0x80]
containsFFFD
) != spanCondition
) {
return s-1;
@ -627,8 +640,9 @@ BMPSet::spanUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanConditi
s+=3;
continue;
}
} else /* 0xc0<=b<0xe0 */ {
} else {
if( /* handle U+0000..U+07FF inline */
b>=0xc0 &&
(t1=(uint8_t)(*s-0x80)) <= 0x3f
) {
if((USetSpanCondition)((table7FF[t1]&((uint32_t)1<<(b&0x1f)))!=0) != spanCondition) {
@ -642,7 +656,7 @@ BMPSet::spanUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanConditi
// Give an illegal sequence the same value as the result of contains(FFFD).
// Handle each byte of an illegal sequence separately to simplify the code;
// no need to optimize error handling.
if(asciiBytes[0x80]!=spanCondition) {
if(containsFFFD!=spanCondition) {
return s-1;
}
}
@ -667,26 +681,26 @@ BMPSet::spanBackUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanCon
do {
b=s[--length];
if((int8_t)b>=0) {
if(U8_IS_SINGLE(b)) {
// ASCII sub-span
if(spanCondition) {
do {
if(!asciiBytes[b]) {
if(!latin1Contains[b]) {
return length+1;
} else if(length==0) {
return 0;
}
b=s[--length];
} while((int8_t)b>=0);
} while(U8_IS_SINGLE(b));
} else {
do {
if(asciiBytes[b]) {
if(latin1Contains[b]) {
return length+1;
} else if(length==0) {
return 0;
}
b=s[--length];
} while((int8_t)b>=0);
} while(U8_IS_SINGLE(b));
}
}

19
intl/icu/source/common/bmpset.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
@ -8,7 +8,7 @@
*
******************************************************************************
* file name: bmpset.h
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
@ -28,11 +28,12 @@ U_NAMESPACE_BEGIN
* Helper class for frozen UnicodeSets, implements contains() and span()
* optimized for BMP code points. Structured to be UTF-8-friendly.
*
* ASCII: Look up bytes.
* Latin-1: Look up bytes.
* 2-byte characters: Bits organized vertically.
* 3-byte characters: Use zero/one/mixed data per 64-block in U+0000..U+FFFF,
* with mixed for illegal ranges.
* Supplementary characters: Call contains() on the parent set.
* Supplementary characters: Binary search over
* the supplementary part of the parent set's inversion list.
*/
class BMPSet : public UMemory {
public:
@ -96,12 +97,12 @@ private:
inline UBool containsSlow(UChar32 c, int32_t lo, int32_t hi) const;
/*
* One byte per ASCII character, or trail byte in lead position.
* 0 or 1 for ASCII characters.
* The value for trail bytes is the result of contains(FFFD)
* for faster validity checking at runtime.
* One byte 0 or 1 per Latin-1 character.
*/
UBool asciiBytes[0xc0];
UBool latin1Contains[0x100];
/* TRUE if contains(U+FFFD). */
UBool containsFFFD;
/*
* One bit per code point from U+0000..U+07FF.

88
intl/icu/source/common/brkeng.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
************************************************************************************
@ -11,9 +11,6 @@
#if !UCONFIG_NO_BREAK_ITERATION
#include "brkeng.h"
#include "cmemory.h"
#include "dictbe.h"
#include "unicode/uchar.h"
#include "unicode/uniset.h"
#include "unicode/chariter.h"
@ -24,6 +21,10 @@
#include "unicode/uscript.h"
#include "unicode/ucharstrie.h"
#include "unicode/bytestrie.h"
#include "brkeng.h"
#include "cmemory.h"
#include "dictbe.h"
#include "charstr.h"
#include "dictionarydata.h"
#include "mutex.h"
@ -58,66 +59,47 @@ LanguageBreakFactory::~LanguageBreakFactory() {
******************************************************************
*/
UnhandledEngine::UnhandledEngine(UErrorCode &/*status*/) {
for (int32_t i = 0; i < UPRV_LENGTHOF(fHandled); ++i) {
fHandled[i] = 0;
}
UnhandledEngine::UnhandledEngine(UErrorCode &status) : fHandled(nullptr) {
(void)status;
}
UnhandledEngine::~UnhandledEngine() {
for (int32_t i = 0; i < UPRV_LENGTHOF(fHandled); ++i) {
if (fHandled[i] != 0) {
delete fHandled[i];
}
}
delete fHandled;
fHandled = nullptr;
}
UBool
UnhandledEngine::handles(UChar32 c, int32_t breakType) const {
return (breakType >= 0 && breakType < UPRV_LENGTHOF(fHandled)
&& fHandled[breakType] != 0 && fHandled[breakType]->contains(c));
UnhandledEngine::handles(UChar32 c) const {
return fHandled && fHandled->contains(c);
}
int32_t
UnhandledEngine::findBreaks( UText *text,
int32_t startPos,
int32_t endPos,
UBool reverse,
int32_t breakType,
UStack &/*foundBreaks*/ ) const {
if (breakType >= 0 && breakType < UPRV_LENGTHOF(fHandled)) {
UChar32 c = utext_current32(text);
if (reverse) {
while((int32_t)utext_getNativeIndex(text) > startPos && fHandled[breakType]->contains(c)) {
c = utext_previous32(text);
}
}
else {
while((int32_t)utext_getNativeIndex(text) < endPos && fHandled[breakType]->contains(c)) {
utext_next32(text); // TODO: recast loop to work with post-increment operations.
c = utext_current32(text);
}
}
int32_t /* startPos */,
int32_t endPos,
UVector32 &/*foundBreaks*/ ) const {
UChar32 c = utext_current32(text);
while((int32_t)utext_getNativeIndex(text) < endPos && fHandled->contains(c)) {
utext_next32(text); // TODO: recast loop to work with post-increment operations.
c = utext_current32(text);
}
return 0;
}
void
UnhandledEngine::handleCharacter(UChar32 c, int32_t breakType) {
if (breakType >= 0 && breakType < UPRV_LENGTHOF(fHandled)) {
if (fHandled[breakType] == 0) {
fHandled[breakType] = new UnicodeSet();
if (fHandled[breakType] == 0) {
return;
}
}
if (!fHandled[breakType]->contains(c)) {
UErrorCode status = U_ZERO_ERROR;
// Apply the entire script of the character.
int32_t script = u_getIntPropertyValue(c, UCHAR_SCRIPT);
fHandled[breakType]->applyIntPropertyValue(UCHAR_SCRIPT, script, status);
UnhandledEngine::handleCharacter(UChar32 c) {
if (fHandled == nullptr) {
fHandled = new UnicodeSet();
if (fHandled == nullptr) {
return;
}
}
if (!fHandled->contains(c)) {
UErrorCode status = U_ZERO_ERROR;
// Apply the entire script of the character.
int32_t script = u_getIntPropertyValue(c, UCHAR_SCRIPT);
fHandled->applyIntPropertyValue(UCHAR_SCRIPT, script, status);
}
}
/*
@ -145,7 +127,7 @@ U_NAMESPACE_BEGIN
static UMutex gBreakEngineMutex = U_MUTEX_INITIALIZER;
const LanguageBreakEngine *
ICULanguageBreakFactory::getEngineFor(UChar32 c, int32_t breakType) {
ICULanguageBreakFactory::getEngineFor(UChar32 c) {
const LanguageBreakEngine *lbe = NULL;
UErrorCode status = U_ZERO_ERROR;
@ -163,14 +145,14 @@ ICULanguageBreakFactory::getEngineFor(UChar32 c, int32_t breakType) {
int32_t i = fEngines->size();
while (--i >= 0) {
lbe = (const LanguageBreakEngine *)(fEngines->elementAt(i));
if (lbe != NULL && lbe->handles(c, breakType)) {
if (lbe != NULL && lbe->handles(c)) {
return lbe;
}
}
}
// We didn't find an engine. Create one.
lbe = loadEngineFor(c, breakType);
lbe = loadEngineFor(c);
if (lbe != NULL) {
fEngines->push((void *)lbe, status);
}
@ -178,11 +160,11 @@ ICULanguageBreakFactory::getEngineFor(UChar32 c, int32_t breakType) {
}
const LanguageBreakEngine *
ICULanguageBreakFactory::loadEngineFor(UChar32 c, int32_t breakType) {
ICULanguageBreakFactory::loadEngineFor(UChar32 c) {
UErrorCode status = U_ZERO_ERROR;
UScriptCode code = uscript_getScript(c, &status);
if (U_SUCCESS(status)) {
DictionaryMatcher *m = loadDictionaryMatcherFor(code, breakType);
DictionaryMatcher *m = loadDictionaryMatcherFor(code);
if (m != NULL) {
const LanguageBreakEngine *engine = NULL;
switch(code) {
@ -243,7 +225,7 @@ ICULanguageBreakFactory::loadEngineFor(UChar32 c, int32_t breakType) {
}
DictionaryMatcher *
ICULanguageBreakFactory::loadDictionaryMatcherFor(UScriptCode script, int32_t /* brkType */) {
ICULanguageBreakFactory::loadDictionaryMatcherFor(UScriptCode script) {
UErrorCode status = U_ZERO_ERROR;
// open root from brkitr tree.
UResourceBundle *b = ures_open(U_ICUDATA_BRKITR, "", &status);

48
intl/icu/source/common/brkeng.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/**
************************************************************************************
@ -19,6 +19,7 @@ U_NAMESPACE_BEGIN
class UnicodeSet;
class UStack;
class UVector32;
class DictionaryMatcher;
/*******************************************************************
@ -53,11 +54,10 @@ class LanguageBreakEngine : public UMemory {
* a particular kind of break.</p>
*
* @param c A character which begins a run that the engine might handle
* @param breakType The type of text break which the caller wants to determine
* @return TRUE if this engine handles the particular character and break
* type.
*/
virtual UBool handles(UChar32 c, int32_t breakType) const = 0;
virtual UBool handles(UChar32 c) const = 0;
/**
* <p>Find any breaks within a run in the supplied text.</p>
@ -67,18 +67,13 @@ class LanguageBreakEngine : public UMemory {
* is capable of handling.
* @param startPos The start of the run within the supplied text.
* @param endPos The end of the run within the supplied text.
* @param reverse Whether the caller is looking for breaks in a reverse
* direction.
* @param breakType The type of break desired, or -1.
* @param foundBreaks An allocated C array of the breaks found, if any
* @param foundBreaks A Vector of int32_t to receive the breaks.
* @return The number of breaks found.
*/
virtual int32_t findBreaks( UText *text,
int32_t startPos,
int32_t endPos,
UBool reverse,
int32_t breakType,
UStack &foundBreaks ) const = 0;
UVector32 &foundBreaks ) const = 0;
};
@ -127,11 +122,9 @@ class LanguageBreakFactory : public UMemory {
*
* @param c A character that begins a run for which a LanguageBreakEngine is
* sought.
* @param breakType The kind of text break for which a LanguageBreakEngine is
* sought.
* @return A LanguageBreakEngine with the desired characteristics, or 0.
*/
virtual const LanguageBreakEngine *getEngineFor(UChar32 c, int32_t breakType) = 0;
virtual const LanguageBreakEngine *getEngineFor(UChar32 c) = 0;
};
@ -154,11 +147,11 @@ class UnhandledEngine : public LanguageBreakEngine {
private:
/**
* The sets of characters handled, for each break type
* The sets of characters handled.
* @internal
*/
UnicodeSet *fHandled[4];
UnicodeSet *fHandled;
public:
@ -178,11 +171,10 @@ class UnhandledEngine : public LanguageBreakEngine {
* a particular kind of break.</p>
*
* @param c A character which begins a run that the engine might handle
* @param breakType The type of text break which the caller wants to determine
* @return TRUE if this engine handles the particular character and break
* type.
*/
virtual UBool handles(UChar32 c, int32_t breakType) const;
virtual UBool handles(UChar32 c) const;
/**
* <p>Find any breaks within a run in the supplied text.</p>
@ -192,26 +184,20 @@ class UnhandledEngine : public LanguageBreakEngine {
* is capable of handling.
* @param startPos The start of the run within the supplied text.
* @param endPos The end of the run within the supplied text.
* @param reverse Whether the caller is looking for breaks in a reverse
* direction.
* @param breakType The type of break desired, or -1.
* @param foundBreaks An allocated C array of the breaks found, if any
* @return The number of breaks found.
*/
virtual int32_t findBreaks( UText *text,
int32_t startPos,
int32_t endPos,
UBool reverse,
int32_t breakType,
UStack &foundBreaks ) const;
UVector32 &foundBreaks ) const;
/**
* <p>Tell the engine to handle a particular character and break type.</p>
*
* @param c A character which the engine should handle
* @param breakType The type of text break for which the engine should handle c
*/
virtual void handleCharacter(UChar32 c, int32_t breakType);
virtual void handleCharacter(UChar32 c);
};
@ -255,11 +241,9 @@ class ICULanguageBreakFactory : public LanguageBreakFactory {
*
* @param c A character that begins a run for which a LanguageBreakEngine is
* sought.
* @param breakType The kind of text break for which a LanguageBreakEngine is
* sought.
* @return A LanguageBreakEngine with the desired characteristics, or 0.
*/
virtual const LanguageBreakEngine *getEngineFor(UChar32 c, int32_t breakType);
virtual const LanguageBreakEngine *getEngineFor(UChar32 c);
protected:
/**
@ -268,21 +252,17 @@ protected:
*
* @param c A character that begins a run for which a LanguageBreakEngine is
* sought.
* @param breakType The kind of text break for which a LanguageBreakEngine is
* sought.
* @return A LanguageBreakEngine with the desired characteristics, or 0.
*/
virtual const LanguageBreakEngine *loadEngineFor(UChar32 c, int32_t breakType);
virtual const LanguageBreakEngine *loadEngineFor(UChar32 c);
/**
* <p>Create a DictionaryMatcher for the specified script and break type.</p>
* @param script An ISO 15924 script code that identifies the dictionary to be
* created.
* @param breakType The kind of text break for which a dictionary is
* sought.
* @return A DictionaryMatcher with the desired characteristics, or NULL.
*/
virtual DictionaryMatcher *loadDictionaryMatcherFor(UScriptCode script, int32_t breakType);
virtual DictionaryMatcher *loadDictionaryMatcherFor(UScriptCode script);
};
U_NAMESPACE_END

38
intl/icu/source/common/brkiter.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -52,7 +52,7 @@ U_NAMESPACE_BEGIN
// -------------------------------------
BreakIterator*
BreakIterator::buildInstance(const Locale& loc, const char *type, int32_t kind, UErrorCode &status)
BreakIterator::buildInstance(const Locale& loc, const char *type, UErrorCode &status)
{
char fnbuff[256];
char ext[4]={'\0'};
@ -121,7 +121,6 @@ BreakIterator::buildInstance(const Locale& loc, const char *type, int32_t kind,
U_LOCALE_BASED(locBased, *(BreakIterator*)result);
locBased.setLocaleIDs(ures_getLocaleByType(b, ULOC_VALID_LOCALE, &status),
actualLocale.data());
result->setBreakType(kind);
}
ures_close(b);
@ -195,7 +194,7 @@ BreakIterator::getAvailableLocales(int32_t& count)
// ------------------------------------------
//
// Default constructor and destructor
// Constructors, destructor and assignment operator
//
//-------------------------------------------
@ -204,6 +203,19 @@ BreakIterator::BreakIterator()
*validLocale = *actualLocale = 0;
}
BreakIterator::BreakIterator(const BreakIterator &other) : UObject(other) {
uprv_strncpy(actualLocale, other.actualLocale, sizeof(actualLocale));
uprv_strncpy(validLocale, other.validLocale, sizeof(validLocale));
}
BreakIterator &BreakIterator::operator =(const BreakIterator &other) {
if (this != &other) {
uprv_strncpy(actualLocale, other.actualLocale, sizeof(actualLocale));
uprv_strncpy(validLocale, other.validLocale, sizeof(validLocale));
}
return *this;
}
BreakIterator::~BreakIterator()
{
}
@ -265,7 +277,7 @@ ICUBreakIteratorService::~ICUBreakIteratorService() {}
// defined in ucln_cmn.h
U_NAMESPACE_END
static icu::UInitOnce gInitOnce;
static icu::UInitOnce gInitOnceBrkiter;
static icu::ICULocaleService* gService = NULL;
@ -280,7 +292,7 @@ static UBool U_CALLCONV breakiterator_cleanup(void) {
delete gService;
gService = NULL;
}
gInitOnce.reset();
gInitOnceBrkiter.reset();
#endif
return TRUE;
}
@ -296,7 +308,7 @@ initService(void) {
static ICULocaleService*
getService(void)
{
umtx_initOnce(gInitOnce, &initService);
umtx_initOnce(gInitOnceBrkiter, &initService);
return gService;
}
@ -306,7 +318,7 @@ getService(void)
static inline UBool
hasService(void)
{
return !gInitOnce.isReset() && getService() != NULL;
return !gInitOnceBrkiter.isReset() && getService() != NULL;
}
// -------------------------------------
@ -400,10 +412,10 @@ BreakIterator::makeInstance(const Locale& loc, int32_t kind, UErrorCode& status)
BreakIterator *result = NULL;
switch (kind) {
case UBRK_CHARACTER:
result = BreakIterator::buildInstance(loc, "grapheme", kind, status);
result = BreakIterator::buildInstance(loc, "grapheme", status);
break;
case UBRK_WORD:
result = BreakIterator::buildInstance(loc, "word", kind, status);
result = BreakIterator::buildInstance(loc, "word", status);
break;
case UBRK_LINE:
uprv_strcpy(lbType, "line");
@ -416,10 +428,10 @@ BreakIterator::makeInstance(const Locale& loc, int32_t kind, UErrorCode& status)
uprv_strcat(lbType, lbKeyValue);
}
}
result = BreakIterator::buildInstance(loc, lbType, kind, status);
result = BreakIterator::buildInstance(loc, lbType, status);
break;
case UBRK_SENTENCE:
result = BreakIterator::buildInstance(loc, "sentence", kind, status);
result = BreakIterator::buildInstance(loc, "sentence", status);
#if !UCONFIG_NO_FILTERED_BREAK_ITERATION
{
char ssKeyValue[kKeyValueLenMax] = {0};
@ -436,7 +448,7 @@ BreakIterator::makeInstance(const Locale& loc, int32_t kind, UErrorCode& status)
#endif
break;
case UBRK_TITLE:
result = BreakIterator::buildInstance(loc, "title", kind, status);
result = BreakIterator::buildInstance(loc, "title", status);
break;
default:
status = U_ILLEGAL_ARGUMENT_ERROR;

161
intl/icu/source/common/bytesinkutil.cpp Normal file
View file

@ -0,0 +1,161 @@
// © 2017 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// bytesinkutil.cpp
// created: 2017sep14 Markus W. Scherer
#include "unicode/utypes.h"
#include "unicode/bytestream.h"
#include "unicode/edits.h"
#include "unicode/stringoptions.h"
#include "unicode/utf8.h"
#include "unicode/utf16.h"
#include "bytesinkutil.h"
#include "charstr.h"
#include "cmemory.h"
#include "uassert.h"
U_NAMESPACE_BEGIN
UBool
ByteSinkUtil::appendChange(int32_t length, const char16_t *s16, int32_t s16Length,
ByteSink &sink, Edits *edits, UErrorCode &errorCode) {
if (U_FAILURE(errorCode)) { return FALSE; }
char scratch[200];
int32_t s8Length = 0;
for (int32_t i = 0; i < s16Length;) {
int32_t capacity;
int32_t desiredCapacity = s16Length - i;
if (desiredCapacity < (INT32_MAX / 3)) {
desiredCapacity *= 3; // max 3 UTF-8 bytes per UTF-16 code unit
} else if (desiredCapacity < (INT32_MAX / 2)) {
desiredCapacity *= 2;
} else {
desiredCapacity = INT32_MAX;
}
char *buffer = sink.GetAppendBuffer(U8_MAX_LENGTH, desiredCapacity,
scratch, UPRV_LENGTHOF(scratch), &capacity);
capacity -= U8_MAX_LENGTH - 1;
int32_t j = 0;
for (; i < s16Length && j < capacity;) {
UChar32 c;
U16_NEXT_UNSAFE(s16, i, c);
U8_APPEND_UNSAFE(buffer, j, c);
}
if (j > (INT32_MAX - s8Length)) {
errorCode = U_INDEX_OUTOFBOUNDS_ERROR;
return FALSE;
}
sink.Append(buffer, j);
s8Length += j;
}
if (edits != nullptr) {
edits->addReplace(length, s8Length);
}
return TRUE;
}
UBool
ByteSinkUtil::appendChange(const uint8_t *s, const uint8_t *limit,
const char16_t *s16, int32_t s16Length,
ByteSink &sink, Edits *edits, UErrorCode &errorCode) {
if (U_FAILURE(errorCode)) { return FALSE; }
if ((limit - s) > INT32_MAX) {
errorCode = U_INDEX_OUTOFBOUNDS_ERROR;
return FALSE;
}
return appendChange((int32_t)(limit - s), s16, s16Length, sink, edits, errorCode);
}
void
ByteSinkUtil::appendCodePoint(int32_t length, UChar32 c, ByteSink &sink, Edits *edits) {
char s8[U8_MAX_LENGTH];
int32_t s8Length = 0;
U8_APPEND_UNSAFE(s8, s8Length, c);
if (edits != nullptr) {
edits->addReplace(length, s8Length);
}
sink.Append(s8, s8Length);
}
namespace {
// See unicode/utf8.h U8_APPEND_UNSAFE().
inline uint8_t getTwoByteLead(UChar32 c) { return (uint8_t)((c >> 6) | 0xc0); }
inline uint8_t getTwoByteTrail(UChar32 c) { return (uint8_t)((c & 0x3f) | 0x80); }
} // namespace
void
ByteSinkUtil::appendTwoBytes(UChar32 c, ByteSink &sink) {
U_ASSERT(0x80 <= c && c <= 0x7ff); // 2-byte UTF-8
char s8[2] = { (char)getTwoByteLead(c), (char)getTwoByteTrail(c) };
sink.Append(s8, 2);
}
void
ByteSinkUtil::appendNonEmptyUnchanged(const uint8_t *s, int32_t length,
ByteSink &sink, uint32_t options, Edits *edits) {
U_ASSERT(length > 0);
if (edits != nullptr) {
edits->addUnchanged(length);
}
if ((options & U_OMIT_UNCHANGED_TEXT) == 0) {
sink.Append(reinterpret_cast<const char *>(s), length);
}
}
UBool
ByteSinkUtil::appendUnchanged(const uint8_t *s, const uint8_t *limit,
ByteSink &sink, uint32_t options, Edits *edits,
UErrorCode &errorCode) {
if (U_FAILURE(errorCode)) { return FALSE; }
if ((limit - s) > INT32_MAX) {
errorCode = U_INDEX_OUTOFBOUNDS_ERROR;
return FALSE;
}
int32_t length = (int32_t)(limit - s);
if (length > 0) {
appendNonEmptyUnchanged(s, length, sink, options, edits);
}
return TRUE;
}
CharStringByteSink::CharStringByteSink(CharString* dest) : dest_(*dest) {
}
CharStringByteSink::~CharStringByteSink() = default;
void
CharStringByteSink::Append(const char* bytes, int32_t n) {
UErrorCode status = U_ZERO_ERROR;
dest_.append(bytes, n, status);
// Any errors are silently ignored.
}
char*
CharStringByteSink::GetAppendBuffer(int32_t min_capacity,
int32_t desired_capacity_hint,
char* scratch,
int32_t scratch_capacity,
int32_t* result_capacity) {
if (min_capacity < 1 || scratch_capacity < min_capacity) {
*result_capacity = 0;
return nullptr;
}
UErrorCode status = U_ZERO_ERROR;
char* result = dest_.getAppendBuffer(
min_capacity,
desired_capacity_hint,
*result_capacity,
status);
if (U_SUCCESS(status)) {
return result;
}
*result_capacity = scratch_capacity;
return scratch;
}
U_NAMESPACE_END

83
intl/icu/source/common/bytesinkutil.h Normal file
View file

@ -0,0 +1,83 @@
// © 2017 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// bytesinkutil.h
// created: 2017sep14 Markus W. Scherer
#include "unicode/utypes.h"
#include "unicode/bytestream.h"
#include "unicode/edits.h"
#include "cmemory.h"
#include "uassert.h"
U_NAMESPACE_BEGIN
class ByteSink;
class CharString;
class Edits;
class U_COMMON_API ByteSinkUtil {
public:
ByteSinkUtil() = delete; // all static
/** (length) bytes were mapped to valid (s16, s16Length). */
static UBool appendChange(int32_t length,
const char16_t *s16, int32_t s16Length,
ByteSink &sink, Edits *edits, UErrorCode &errorCode);
/** The bytes at [s, limit[ were mapped to valid (s16, s16Length). */
static UBool appendChange(const uint8_t *s, const uint8_t *limit,
const char16_t *s16, int32_t s16Length,
ByteSink &sink, Edits *edits, UErrorCode &errorCode);
/** (length) bytes were mapped/changed to valid code point c. */
static void appendCodePoint(int32_t length, UChar32 c, ByteSink &sink, Edits *edits = nullptr);
/** The few bytes at [src, nextSrc[ were mapped/changed to valid code point c. */
static inline void appendCodePoint(const uint8_t *src, const uint8_t *nextSrc, UChar32 c,
ByteSink &sink, Edits *edits = nullptr) {
appendCodePoint((int32_t)(nextSrc - src), c, sink, edits);
}
/** Append the two-byte character (U+0080..U+07FF). */
static void appendTwoBytes(UChar32 c, ByteSink &sink);
static UBool appendUnchanged(const uint8_t *s, int32_t length,
ByteSink &sink, uint32_t options, Edits *edits,
UErrorCode &errorCode) {
if (U_FAILURE(errorCode)) { return FALSE; }
if (length > 0) { appendNonEmptyUnchanged(s, length, sink, options, edits); }
return TRUE;
}
static UBool appendUnchanged(const uint8_t *s, const uint8_t *limit,
ByteSink &sink, uint32_t options, Edits *edits,
UErrorCode &errorCode);
private:
static void appendNonEmptyUnchanged(const uint8_t *s, int32_t length,
ByteSink &sink, uint32_t options, Edits *edits);
};
class CharStringByteSink : public ByteSink {
public:
CharStringByteSink(CharString* dest);
~CharStringByteSink() override;
CharStringByteSink() = delete;
CharStringByteSink(const CharStringByteSink&) = delete;
CharStringByteSink& operator=(const CharStringByteSink&) = delete;
void Append(const char* bytes, int32_t n) override;
char* GetAppendBuffer(int32_t min_capacity,
int32_t desired_capacity_hint,
char* scratch,
int32_t scratch_capacity,
int32_t* result_capacity) override;
private:
CharString& dest_;
};
U_NAMESPACE_END

8
intl/icu/source/common/bytestream.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Copyright (C) 2009-2011, International Business Machines
// Corporation and others. All Rights Reserved.
@ -45,6 +45,12 @@ void CheckedArrayByteSink::Append(const char* bytes, int32_t n) {
if (n <= 0) {
return;
}
if (n > (INT32_MAX - appended_)) {
// TODO: Report as integer overflow, not merely buffer overflow.
appended_ = INT32_MAX;
overflowed_ = TRUE;
return;
}
appended_ += n;
int32_t available = capacity_ - size_;
if (n > available) {

4
intl/icu/source/common/bytestrie.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -6,7 +6,7 @@
* Corporation and others. All Rights Reserved.
*******************************************************************************
* file name: bytestrie.cpp
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*

7
intl/icu/source/common/bytestriebuilder.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -6,7 +6,7 @@
* Corporation and others. All Rights Reserved.
*******************************************************************************
* file name: bytestriebuilder.cpp
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
@ -339,7 +339,8 @@ BytesTrieBuilder::indexOfElementWithNextUnit(int32_t i, int32_t byteIndex, UChar
BytesTrieBuilder::BTLinearMatchNode::BTLinearMatchNode(const char *bytes, int32_t len, Node *nextNode)
: LinearMatchNode(len, nextNode), s(bytes) {
hash=hash*37+ustr_hashCharsN(bytes, len);
hash=static_cast<int32_t>(
static_cast<uint32_t>(hash)*37u + static_cast<uint32_t>(ustr_hashCharsN(bytes, len)));
}
UBool

4
intl/icu/source/common/bytestrieiterator.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -6,7 +6,7 @@
* Corporation and others. All Rights Reserved.
*******************************************************************************
* file name: bytestrieiterator.cpp
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*

8
intl/icu/source/common/caniter.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*****************************************************************************
@ -311,12 +311,12 @@ void U_EXPORT2 CanonicalIterator::permute(UnicodeString &source, UBool skipZeros
// see what the permutations of the characters before and after this one are
//Hashtable *subpermute = permute(source.substring(0,i) + source.substring(i + UTF16.getCharCount(cp)));
permute(subPermuteString.replace(i, U16_LENGTH(cp), NULL, 0), skipZeros, &subpermute, status);
permute(subPermuteString.remove(i, U16_LENGTH(cp)), skipZeros, &subpermute, status);
/* Test for buffer overflows */
if(U_FAILURE(status)) {
return;
}
// The upper replace is destructive. The question is do we have to make a copy, or we don't care about the contents
// The upper remove is destructive. The question is do we have to make a copy, or we don't care about the contents
// of source at this point.
// prefix this character to all of them
@ -405,7 +405,7 @@ UnicodeString* CanonicalIterator::getEquivalents(const UnicodeString &segment, i
//String[] finalResult = new String[result.size()];
UnicodeString *finalResult = NULL;
int32_t resultCount;
if((resultCount = result.count())) {
if((resultCount = result.count()) != 0) {
finalResult = new UnicodeString[resultCount];
if (finalResult == 0) {
status = U_MEMORY_ALLOCATION_ERROR;

381
intl/icu/source/common/characterproperties.cpp Normal file
View file

@ -0,0 +1,381 @@
// © 2018 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// characterproperties.cpp
// created: 2018sep03 Markus W. Scherer
#include "unicode/utypes.h"
#include "unicode/localpointer.h"
#include "unicode/uchar.h"
#include "unicode/ucpmap.h"
#include "unicode/ucptrie.h"
#include "unicode/umutablecptrie.h"
#include "unicode/uniset.h"
#include "unicode/uscript.h"
#include "unicode/uset.h"
#include "cmemory.h"
#include "mutex.h"
#include "normalizer2impl.h"
#include "uassert.h"
#include "ubidi_props.h"
#include "ucase.h"
#include "ucln_cmn.h"
#include "umutex.h"
#include "uprops.h"
using icu::LocalPointer;
using icu::Normalizer2Factory;
using icu::Normalizer2Impl;
using icu::UInitOnce;
using icu::UnicodeSet;
namespace {
UBool U_CALLCONV characterproperties_cleanup();
constexpr int32_t NUM_INCLUSIONS = UPROPS_SRC_COUNT + UCHAR_INT_LIMIT - UCHAR_INT_START;
struct Inclusion {
UnicodeSet *fSet;
UInitOnce fInitOnce;
};
Inclusion gInclusions[NUM_INCLUSIONS]; // cached getInclusions()
UnicodeSet *sets[UCHAR_BINARY_LIMIT] = {};
UCPMap *maps[UCHAR_INT_LIMIT - UCHAR_INT_START] = {};
UMutex cpMutex = U_MUTEX_INITIALIZER;
//----------------------------------------------------------------
// Inclusions list
//----------------------------------------------------------------
// USetAdder implementation
// Does not use uset.h to reduce code dependencies
void U_CALLCONV
_set_add(USet *set, UChar32 c) {
((UnicodeSet *)set)->add(c);
}
void U_CALLCONV
_set_addRange(USet *set, UChar32 start, UChar32 end) {
((UnicodeSet *)set)->add(start, end);
}
void U_CALLCONV
_set_addString(USet *set, const UChar *str, int32_t length) {
((UnicodeSet *)set)->add(icu::UnicodeString((UBool)(length<0), str, length));
}
UBool U_CALLCONV characterproperties_cleanup() {
for (Inclusion &in: gInclusions) {
delete in.fSet;
in.fSet = nullptr;
in.fInitOnce.reset();
}
for (int32_t i = 0; i < UPRV_LENGTHOF(sets); ++i) {
delete sets[i];
sets[i] = nullptr;
}
for (int32_t i = 0; i < UPRV_LENGTHOF(maps); ++i) {
ucptrie_close(reinterpret_cast<UCPTrie *>(maps[i]));
maps[i] = nullptr;
}
return TRUE;
}
void U_CALLCONV initInclusion(UPropertySource src, UErrorCode &errorCode) {
// This function is invoked only via umtx_initOnce().
U_ASSERT(0 <= src && src < UPROPS_SRC_COUNT);
if (src == UPROPS_SRC_NONE) {
errorCode = U_INTERNAL_PROGRAM_ERROR;
return;
}
U_ASSERT(gInclusions[src].fSet == nullptr);
LocalPointer<UnicodeSet> incl(new UnicodeSet());
if (incl.isNull()) {
errorCode = U_MEMORY_ALLOCATION_ERROR;
return;
}
USetAdder sa = {
(USet *)incl.getAlias(),
_set_add,
_set_addRange,
_set_addString,
nullptr, // don't need remove()
nullptr // don't need removeRange()
};
switch(src) {
case UPROPS_SRC_CHAR:
uchar_addPropertyStarts(&sa, &errorCode);
break;
case UPROPS_SRC_PROPSVEC:
upropsvec_addPropertyStarts(&sa, &errorCode);
break;
case UPROPS_SRC_CHAR_AND_PROPSVEC:
uchar_addPropertyStarts(&sa, &errorCode);
upropsvec_addPropertyStarts(&sa, &errorCode);
break;
#if !UCONFIG_NO_NORMALIZATION
case UPROPS_SRC_CASE_AND_NORM: {
const Normalizer2Impl *impl=Normalizer2Factory::getNFCImpl(errorCode);
if(U_SUCCESS(errorCode)) {
impl->addPropertyStarts(&sa, errorCode);
}
ucase_addPropertyStarts(&sa, &errorCode);
break;
}
case UPROPS_SRC_NFC: {
const Normalizer2Impl *impl=Normalizer2Factory::getNFCImpl(errorCode);
if(U_SUCCESS(errorCode)) {
impl->addPropertyStarts(&sa, errorCode);
}
break;
}
case UPROPS_SRC_NFKC: {
const Normalizer2Impl *impl=Normalizer2Factory::getNFKCImpl(errorCode);
if(U_SUCCESS(errorCode)) {
impl->addPropertyStarts(&sa, errorCode);
}
break;
}
case UPROPS_SRC_NFKC_CF: {
const Normalizer2Impl *impl=Normalizer2Factory::getNFKC_CFImpl(errorCode);
if(U_SUCCESS(errorCode)) {
impl->addPropertyStarts(&sa, errorCode);
}
break;
}
case UPROPS_SRC_NFC_CANON_ITER: {
const Normalizer2Impl *impl=Normalizer2Factory::getNFCImpl(errorCode);
if(U_SUCCESS(errorCode)) {
impl->addCanonIterPropertyStarts(&sa, errorCode);
}
break;
}
#endif
case UPROPS_SRC_CASE:
ucase_addPropertyStarts(&sa, &errorCode);
break;
case UPROPS_SRC_BIDI:
ubidi_addPropertyStarts(&sa, &errorCode);
break;
case UPROPS_SRC_INPC:
case UPROPS_SRC_INSC:
case UPROPS_SRC_VO:
uprops_addPropertyStarts((UPropertySource)src, &sa, &errorCode);
break;
default:
errorCode = U_INTERNAL_PROGRAM_ERROR;
break;
}
if (U_FAILURE(errorCode)) {
return;
}
if (incl->isBogus()) {
errorCode = U_MEMORY_ALLOCATION_ERROR;
return;
}
// Compact for caching.
incl->compact();
gInclusions[src].fSet = incl.orphan();
ucln_common_registerCleanup(UCLN_COMMON_CHARACTERPROPERTIES, characterproperties_cleanup);
}
const UnicodeSet *getInclusionsForSource(UPropertySource src, UErrorCode &errorCode) {
if (U_FAILURE(errorCode)) { return nullptr; }
if (src < 0 || UPROPS_SRC_COUNT <= src) {
errorCode = U_ILLEGAL_ARGUMENT_ERROR;
return nullptr;
}
Inclusion &i = gInclusions[src];
umtx_initOnce(i.fInitOnce, &initInclusion, src, errorCode);
return i.fSet;
}
void U_CALLCONV initIntPropInclusion(UProperty prop, UErrorCode &errorCode) {
// This function is invoked only via umtx_initOnce().
U_ASSERT(UCHAR_INT_START <= prop && prop < UCHAR_INT_LIMIT);
int32_t inclIndex = UPROPS_SRC_COUNT + prop - UCHAR_INT_START;
U_ASSERT(gInclusions[inclIndex].fSet == nullptr);
UPropertySource src = uprops_getSource(prop);
const UnicodeSet *incl = getInclusionsForSource(src, errorCode);
if (U_FAILURE(errorCode)) {
return;
}
LocalPointer<UnicodeSet> intPropIncl(new UnicodeSet(0, 0));
if (intPropIncl.isNull()) {
errorCode = U_MEMORY_ALLOCATION_ERROR;
return;
}
int32_t numRanges = incl->getRangeCount();
int32_t prevValue = 0;
for (int32_t i = 0; i < numRanges; ++i) {
UChar32 rangeEnd = incl->getRangeEnd(i);
for (UChar32 c = incl->getRangeStart(i); c <= rangeEnd; ++c) {
// TODO: Get a UCharacterProperty.IntProperty to avoid the property dispatch.
int32_t value = u_getIntPropertyValue(c, prop);
if (value != prevValue) {
intPropIncl->add(c);
prevValue = value;
}
}
}
if (intPropIncl->isBogus()) {
errorCode = U_MEMORY_ALLOCATION_ERROR;
return;
}
// Compact for caching.
intPropIncl->compact();
gInclusions[inclIndex].fSet = intPropIncl.orphan();
ucln_common_registerCleanup(UCLN_COMMON_CHARACTERPROPERTIES, characterproperties_cleanup);
}
} // namespace
U_NAMESPACE_BEGIN
const UnicodeSet *CharacterProperties::getInclusionsForProperty(
UProperty prop, UErrorCode &errorCode) {
if (U_FAILURE(errorCode)) { return nullptr; }
if (UCHAR_INT_START <= prop && prop < UCHAR_INT_LIMIT) {
int32_t inclIndex = UPROPS_SRC_COUNT + prop - UCHAR_INT_START;
Inclusion &i = gInclusions[inclIndex];
umtx_initOnce(i.fInitOnce, &initIntPropInclusion, prop, errorCode);
return i.fSet;
} else {
UPropertySource src = uprops_getSource(prop);
return getInclusionsForSource(src, errorCode);
}
}
U_NAMESPACE_END
namespace {
UnicodeSet *makeSet(UProperty property, UErrorCode &errorCode) {
if (U_FAILURE(errorCode)) { return nullptr; }
LocalPointer<UnicodeSet> set(new UnicodeSet());
if (set.isNull()) {
errorCode = U_MEMORY_ALLOCATION_ERROR;
return nullptr;
}
const UnicodeSet *inclusions =
icu::CharacterProperties::getInclusionsForProperty(property, errorCode);
if (U_FAILURE(errorCode)) { return nullptr; }
int32_t numRanges = inclusions->getRangeCount();
UChar32 startHasProperty = -1;
for (int32_t i = 0; i < numRanges; ++i) {
UChar32 rangeEnd = inclusions->getRangeEnd(i);
for (UChar32 c = inclusions->getRangeStart(i); c <= rangeEnd; ++c) {
// TODO: Get a UCharacterProperty.BinaryProperty to avoid the property dispatch.
if (u_hasBinaryProperty(c, property)) {
if (startHasProperty < 0) {
// Transition from false to true.
startHasProperty = c;
}
} else if (startHasProperty >= 0) {
// Transition from true to false.
set->add(startHasProperty, c - 1);
startHasProperty = -1;
}
}
}
if (startHasProperty >= 0) {
set->add(startHasProperty, 0x10FFFF);
}
set->freeze();
return set.orphan();
}
UCPMap *makeMap(UProperty property, UErrorCode &errorCode) {
if (U_FAILURE(errorCode)) { return nullptr; }
uint32_t nullValue = property == UCHAR_SCRIPT ? USCRIPT_UNKNOWN : 0;
icu::LocalUMutableCPTriePointer mutableTrie(
umutablecptrie_open(nullValue, nullValue, &errorCode));
const UnicodeSet *inclusions =
icu::CharacterProperties::getInclusionsForProperty(property, errorCode);
if (U_FAILURE(errorCode)) { return nullptr; }
int32_t numRanges = inclusions->getRangeCount();
UChar32 start = 0;
uint32_t value = nullValue;
for (int32_t i = 0; i < numRanges; ++i) {
UChar32 rangeEnd = inclusions->getRangeEnd(i);
for (UChar32 c = inclusions->getRangeStart(i); c <= rangeEnd; ++c) {
// TODO: Get a UCharacterProperty.IntProperty to avoid the property dispatch.
uint32_t nextValue = u_getIntPropertyValue(c, property);
if (value != nextValue) {
if (value != nullValue) {
umutablecptrie_setRange(mutableTrie.getAlias(), start, c - 1, value, &errorCode);
}
start = c;
value = nextValue;
}
}
}
if (value != 0) {
umutablecptrie_setRange(mutableTrie.getAlias(), start, 0x10FFFF, value, &errorCode);
}
UCPTrieType type;
if (property == UCHAR_BIDI_CLASS || property == UCHAR_GENERAL_CATEGORY) {
type = UCPTRIE_TYPE_FAST;
} else {
type = UCPTRIE_TYPE_SMALL;
}
UCPTrieValueWidth valueWidth;
// TODO: UCharacterProperty.IntProperty
int32_t max = u_getIntPropertyMaxValue(property);
if (max <= 0xff) {
valueWidth = UCPTRIE_VALUE_BITS_8;
} else if (max <= 0xffff) {
valueWidth = UCPTRIE_VALUE_BITS_16;
} else {
valueWidth = UCPTRIE_VALUE_BITS_32;
}
return reinterpret_cast<UCPMap *>(
umutablecptrie_buildImmutable(mutableTrie.getAlias(), type, valueWidth, &errorCode));
}
} // namespace
U_NAMESPACE_USE
U_CAPI const USet * U_EXPORT2
u_getBinaryPropertySet(UProperty property, UErrorCode *pErrorCode) {
if (U_FAILURE(*pErrorCode)) { return nullptr; }
if (property < 0 || UCHAR_BINARY_LIMIT <= property) {
*pErrorCode = U_ILLEGAL_ARGUMENT_ERROR;
return nullptr;
}
Mutex m(&cpMutex);
UnicodeSet *set = sets[property];
if (set == nullptr) {
sets[property] = set = makeSet(property, *pErrorCode);
}
if (U_FAILURE(*pErrorCode)) { return nullptr; }
return set->toUSet();
}
U_CAPI const UCPMap * U_EXPORT2
u_getIntPropertyMap(UProperty property, UErrorCode *pErrorCode) {
if (U_FAILURE(*pErrorCode)) { return nullptr; }
if (property < UCHAR_INT_START || UCHAR_INT_LIMIT <= property) {
*pErrorCode = U_ILLEGAL_ARGUMENT_ERROR;
return nullptr;
}
Mutex m(&cpMutex);
UCPMap *map = maps[property - UCHAR_INT_START];
if (map == nullptr) {
maps[property - UCHAR_INT_START] = map = makeMap(property, *pErrorCode);
}
return map;
}

2
intl/icu/source/common/chariter.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************

31
intl/icu/source/common/charstr.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -6,7 +6,7 @@
* Corporation and others. All Rights Reserved.
*******************************************************************************
* file name: charstr.cpp
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
@ -15,6 +15,7 @@
*/
#include "unicode/utypes.h"
#include "unicode/putil.h"
#include "charstr.h"
#include "cmemory.h"
#include "cstring.h"
@ -22,6 +23,18 @@
U_NAMESPACE_BEGIN
CharString::CharString(CharString&& src) U_NOEXCEPT
: buffer(std::move(src.buffer)), len(src.len) {
src.len = 0; // not strictly necessary because we make no guarantees on the source string
}
CharString& CharString::operator=(CharString&& src) U_NOEXCEPT {
buffer = std::move(src.buffer);
len = src.len;
src.len = 0; // not strictly necessary because we make no guarantees on the source string
return *this;
}
CharString &CharString::copyFrom(const CharString &s, UErrorCode &errorCode) {
if(U_SUCCESS(errorCode) && this!=&s && ensureCapacity(s.len+1, 0, errorCode)) {
len=s.len;
@ -66,7 +79,7 @@ CharString &CharString::append(const char *s, int32_t sLength, UErrorCode &error
return *this;
}
if(sLength<0) {
sLength=uprv_strlen(s);
sLength= static_cast<int32_t>(uprv_strlen(s));
}
if(sLength>0) {
if(s==(buffer.getAlias()+len)) {
@ -113,15 +126,21 @@ char *CharString::getAppendBuffer(int32_t minCapacity,
}
CharString &CharString::appendInvariantChars(const UnicodeString &s, UErrorCode &errorCode) {
return appendInvariantChars(s.getBuffer(), s.length(), errorCode);
}
CharString &CharString::appendInvariantChars(const UChar* uchars, int32_t ucharsLen, UErrorCode &errorCode) {
if(U_FAILURE(errorCode)) {
return *this;
}
if (!uprv_isInvariantUnicodeString(s)) {
if (!uprv_isInvariantUString(uchars, ucharsLen)) {
errorCode = U_INVARIANT_CONVERSION_ERROR;
return *this;
}
if(ensureCapacity(len+s.length()+1, 0, errorCode)) {
len+=s.extract(0, 0x7fffffff, buffer.getAlias()+len, buffer.getCapacity()-len, US_INV);
if(ensureCapacity(len+ucharsLen+1, 0, errorCode)) {
u_UCharsToChars(uchars, buffer.getAlias()+len, ucharsLen);
len += ucharsLen;
buffer[len] = 0;
}
return *this;
}

15
intl/icu/source/common/charstr.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
@ -55,6 +55,18 @@ public:
}
~CharString() {}
/**
* Move constructor; might leave src in an undefined state.
* This string will have the same contents and state that the source string had.
*/
CharString(CharString &&src) U_NOEXCEPT;
/**
* Move assignment operator; might leave src in an undefined state.
* This string will have the same contents and state that the source string had.
* The behavior is undefined if *this and src are the same object.
*/
CharString &operator=(CharString &&src) U_NOEXCEPT;
/**
* Replaces this string's contents with the other string's contents.
* CharString does not support the standard copy constructor nor
@ -111,6 +123,7 @@ public:
UErrorCode &errorCode);
CharString &appendInvariantChars(const UnicodeString &s, UErrorCode &errorCode);
CharString &appendInvariantChars(const UChar* uchars, int32_t ucharsLen, UErrorCode& errorCode);
/**
* Appends a filename/path part, e.g., a directory name.

26
intl/icu/source/common/cmemory.c → intl/icu/source/common/cmemory.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
@ -41,30 +41,6 @@ static int n=0;
static long b=0;
#endif
#if U_DEBUG
static char gValidMemorySink = 0;
U_CAPI void uprv_checkValidMemory(const void *p, size_t n) {
/*
* Access the memory to ensure that it's all valid.
* Load and save a computed value to try to ensure that the compiler
* does not throw away the whole loop.
* A thread analyzer might complain about un-mutexed access to gValidMemorySink
* which is true but harmless because no one ever uses the value in gValidMemorySink.
*/
const char *s = (const char *)p;
char c = gValidMemorySink;
size_t i;
U_ASSERT(p != NULL);
for(i = 0; i < n; ++i) {
c ^= s[i];
}
gValidMemorySink = c;
}
#endif /* U_DEBUG */
U_CAPI void * U_EXPORT2
uprv_malloc(size_t s) {
#if U_DEBUG && defined(UPRV_MALLOC_COUNT)

86
intl/icu/source/common/cmemory.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
@ -36,31 +36,10 @@
#include <stdio.h>
#endif
#if U_DEBUG
/*
* The C++ standard requires that the source pointer for memcpy() & memmove()
* is valid, not NULL, and not at the end of an allocated memory block.
* In debug mode, we read one byte from the source point to verify that it's
* a valid, readable pointer.
*/
U_CAPI void uprv_checkValidMemory(const void *p, size_t n);
#define uprv_memcpy(dst, src, size) ( \
uprv_checkValidMemory(src, 1), \
U_STANDARD_CPP_NAMESPACE memcpy(dst, src, size))
#define uprv_memmove(dst, src, size) ( \
uprv_checkValidMemory(src, 1), \
U_STANDARD_CPP_NAMESPACE memmove(dst, src, size))
#else
#define uprv_memcpy(dst, src, size) U_STANDARD_CPP_NAMESPACE memcpy(dst, src, size)
#define uprv_memmove(dst, src, size) U_STANDARD_CPP_NAMESPACE memmove(dst, src, size)
#endif /* U_DEBUG */
/**
* \def UPRV_LENGTHOF
* Convenience macro to determine the length of a fixed array at compile-time.
@ -162,7 +141,6 @@ public:
* @param p simple pointer to an array of T items that is adopted
*/
explicit LocalMemory(T *p=NULL) : LocalPointerBase<T>(p) {}
#if U_HAVE_RVALUE_REFERENCES
/**
* Move constructor, leaves src with isNull().
* @param src source smart pointer
@ -170,14 +148,12 @@ public:
LocalMemory(LocalMemory<T> &&src) U_NOEXCEPT : LocalPointerBase<T>(src.ptr) {
src.ptr=NULL;
}
#endif
/**
* Destructor deletes the memory it owns.
*/
~LocalMemory() {
uprv_free(LocalPointerBase<T>::ptr);
}
#if U_HAVE_RVALUE_REFERENCES
/**
* Move assignment operator, leaves src with isNull().
* The behavior is undefined if *this and src are the same object.
@ -187,7 +163,6 @@ public:
LocalMemory<T> &operator=(LocalMemory<T> &&src) U_NOEXCEPT {
return moveFrom(src);
}
#endif
/**
* Move assignment, leaves src with isNull().
* The behavior is undefined if *this and src are the same object.
@ -197,7 +172,7 @@ public:
* @return *this
*/
LocalMemory<T> &moveFrom(LocalMemory<T> &src) U_NOEXCEPT {
delete[] LocalPointerBase<T>::ptr;
uprv_free(LocalPointerBase<T>::ptr);
LocalPointerBase<T>::ptr=src.ptr;
src.ptr=NULL;
return *this;
@ -304,6 +279,10 @@ inline T *LocalMemory<T>::allocateInsteadAndCopy(int32_t newCapacity, int32_t le
*
* Unlike LocalMemory and LocalArray, this class never adopts
* (takes ownership of) another array.
*
* WARNING: MaybeStackArray only works with primitive (plain-old data) types.
* It does NOT know how to call a destructor! If you work with classes with
* destructors, consider LocalArray in localpointer.h.
*/
template<typename T, int32_t stackCapacity>
class MaybeStackArray {
@ -312,10 +291,26 @@ public:
* Default constructor initializes with internal T[stackCapacity] buffer.
*/
MaybeStackArray() : ptr(stackArray), capacity(stackCapacity), needToRelease(FALSE) {}
/**
* Automatically allocates the heap array if the argument is larger than the stack capacity.
* Intended for use when an approximate capacity is known at compile time but the true
* capacity is not known until runtime.
*/
MaybeStackArray(int32_t newCapacity) : MaybeStackArray() {
if (capacity < newCapacity) { resize(newCapacity); }
};
/**
* Destructor deletes the array (if owned).
*/
~MaybeStackArray() { releaseArray(); }
/**
* Move constructor: transfers ownership or copies the stack array.
*/
MaybeStackArray(MaybeStackArray<T, stackCapacity> &&src) U_NOEXCEPT;
/**
* Move assignment: transfers ownership or copies the stack array.
*/
MaybeStackArray<T, stackCapacity> &operator=(MaybeStackArray<T, stackCapacity> &&src) U_NOEXCEPT;
/**
* Returns the array capacity (number of T items).
* @return array capacity
@ -393,6 +388,11 @@ private:
uprv_free(ptr);
}
}
void resetToStackArray() {
ptr=stackArray;
capacity=stackCapacity;
needToRelease=FALSE;
}
/* No comparison operators with other MaybeStackArray's. */
bool operator==(const MaybeStackArray & /*other*/) {return FALSE;}
bool operator!=(const MaybeStackArray & /*other*/) {return TRUE;}
@ -415,6 +415,34 @@ private:
#endif
};
template<typename T, int32_t stackCapacity>
icu::MaybeStackArray<T, stackCapacity>::MaybeStackArray(
MaybeStackArray <T, stackCapacity>&& src) U_NOEXCEPT
: ptr(src.ptr), capacity(src.capacity), needToRelease(src.needToRelease) {
if (src.ptr == src.stackArray) {
ptr = stackArray;
uprv_memcpy(stackArray, src.stackArray, sizeof(T) * src.capacity);
} else {
src.resetToStackArray(); // take ownership away from src
}
}
template<typename T, int32_t stackCapacity>
inline MaybeStackArray <T, stackCapacity>&
MaybeStackArray<T, stackCapacity>::operator=(MaybeStackArray <T, stackCapacity>&& src) U_NOEXCEPT {
releaseArray(); // in case this instance had its own memory allocated
capacity = src.capacity;
needToRelease = src.needToRelease;
if (src.ptr == src.stackArray) {
ptr = stackArray;
uprv_memcpy(stackArray, src.stackArray, sizeof(T) * src.capacity);
} else {
ptr = src.ptr;
src.resetToStackArray(); // take ownership away from src
}
return *this;
}
template<typename T, int32_t stackCapacity>
inline T *MaybeStackArray<T, stackCapacity>::resize(int32_t newCapacity, int32_t length) {
if(newCapacity>0) {
@ -464,9 +492,7 @@ inline T *MaybeStackArray<T, stackCapacity>::orphanOrClone(int32_t length, int32
uprv_memcpy(p, ptr, (size_t)length*sizeof(T));
}
resultCapacity=length;
ptr=stackArray;
capacity=stackCapacity;
needToRelease=FALSE;
resetToStackArray();
return p;
}

1673
intl/icu/source/common/common.vcxproj
View file

File diff suppressed because it is too large Load diff

166
intl/icu/source/common/common.vcxproj.filters
View file

@ -1,4 +1,4 @@
<?xml version="1.0" encoding="utf-8"?>
<?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<ItemGroup>
<Filter Include="bidi">
@ -49,16 +49,16 @@
</Filter>
</ItemGroup>
<ItemGroup>
<ClCompile Include="ubidi.c">
<ClCompile Include="ubidi.cpp">
<Filter>bidi</Filter>
</ClCompile>
<ClCompile Include="ubidi_props.c">
<ClCompile Include="ubidi_props.cpp">
<Filter>bidi</Filter>
</ClCompile>
<ClCompile Include="ubidiln.c">
<ClCompile Include="ubidiln.cpp">
<Filter>bidi</Filter>
</ClCompile>
<ClCompile Include="ubidiwrt.c">
<ClCompile Include="ubidiwrt.cpp">
<Filter>bidi</Filter>
</ClCompile>
<ClCompile Include="ushape.cpp">
@ -97,6 +97,9 @@
<ClCompile Include="rbbitblb.cpp">
<Filter>break iteration</Filter>
</ClCompile>
<ClCompile Include="rbbi_cache.cpp">
<Filter>break iteration</Filter>
</ClCompile>
<ClCompile Include="ubrk.cpp">
<Filter>break iteration</Filter>
</ClCompile>
@ -106,22 +109,22 @@
<ClCompile Include="pluralmap.cpp">
<Filter>collections</Filter>
</ClCompile>
<ClCompile Include="propsvec.c">
<ClCompile Include="propsvec.cpp">
<Filter>collections</Filter>
</ClCompile>
<ClCompile Include="uarrsort.c">
<ClCompile Include="uarrsort.cpp">
<Filter>collections</Filter>
</ClCompile>
<ClCompile Include="uenum.c">
<ClCompile Include="uenum.cpp">
<Filter>collections</Filter>
</ClCompile>
<ClCompile Include="uhash.c">
<ClCompile Include="uhash.cpp">
<Filter>collections</Filter>
</ClCompile>
<ClCompile Include="uhash_us.cpp">
<Filter>collections</Filter>
</ClCompile>
<ClCompile Include="ulist.c">
<ClCompile Include="ulist.cpp">
<Filter>collections</Filter>
</ClCompile>
<ClCompile Include="unifiedcache.cpp">
@ -136,6 +139,9 @@
<ClCompile Include="utrie.cpp">
<Filter>collections</Filter>
</ClCompile>
<ClCompile Include="utrie_swap.cpp">
<Filter>collections</Filter>
</ClCompile>
<ClCompile Include="utrie2.cpp">
<Filter>collections</Filter>
</ClCompile>
@ -154,31 +160,31 @@
<ClCompile Include="errorcode.cpp">
<Filter>configuration</Filter>
</ClCompile>
<ClCompile Include="icudataver.c">
<ClCompile Include="icudataver.cpp">
<Filter>configuration</Filter>
</ClCompile>
<ClCompile Include="locmap.c">
<ClCompile Include="locmap.cpp">
<Filter>configuration</Filter>
</ClCompile>
<ClCompile Include="putil.cpp">
<Filter>configuration</Filter>
</ClCompile>
<ClCompile Include="umath.c">
<ClCompile Include="umath.cpp">
<Filter>configuration</Filter>
</ClCompile>
<ClCompile Include="umutex.cpp">
<Filter>configuration</Filter>
</ClCompile>
<ClCompile Include="utrace.c">
<ClCompile Include="utrace.cpp">
<Filter>configuration</Filter>
</ClCompile>
<ClCompile Include="utypes.c">
<ClCompile Include="utypes.cpp">
<Filter>configuration</Filter>
</ClCompile>
<ClCompile Include="wintz.c">
<ClCompile Include="wintz.cpp">
<Filter>configuration</Filter>
</ClCompile>
<ClCompile Include="ucnv.c">
<ClCompile Include="ucnv.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnv2022.cpp">
@ -187,13 +193,13 @@
<ClCompile Include="ucnv_bld.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnv_cb.c">
<ClCompile Include="ucnv_cb.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnv_cnv.c">
<ClCompile Include="ucnv_cnv.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnv_err.c">
<ClCompile Include="ucnv_err.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnv_ext.cpp">
@ -202,49 +208,49 @@
<ClCompile Include="ucnv_io.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnv_lmb.c">
<ClCompile Include="ucnv_lmb.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnv_set.c">
<ClCompile Include="ucnv_set.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnv_u16.c">
<ClCompile Include="ucnv_u16.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnv_u32.c">
<ClCompile Include="ucnv_u32.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnv_u7.c">
<ClCompile Include="ucnv_u7.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnv_u8.c">
<ClCompile Include="ucnv_u8.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnvbocu.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnvdisp.c">
<ClCompile Include="ucnvdisp.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnvhz.c">
<ClCompile Include="ucnvhz.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnvisci.c">
<ClCompile Include="ucnvisci.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnvlat1.c">
<ClCompile Include="ucnvlat1.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnvmbcs.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnvscsu.c">
<ClCompile Include="ucnvscsu.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucnvsel.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="cmemory.c">
<ClCompile Include="cmemory.cpp">
<Filter>data &amp; memory</Filter>
</ClCompile>
<ClCompile Include="sharedobject.cpp">
@ -253,22 +259,22 @@
<ClCompile Include="ucln_cmn.cpp">
<Filter>data &amp; memory</Filter>
</ClCompile>
<ClCompile Include="ucmndata.c">
<ClCompile Include="ucmndata.cpp">
<Filter>data &amp; memory</Filter>
</ClCompile>
<ClCompile Include="udata.cpp">
<Filter>data &amp; memory</Filter>
</ClCompile>
<ClCompile Include="udatamem.c">
<ClCompile Include="udatamem.cpp">
<Filter>data &amp; memory</Filter>
</ClCompile>
<ClCompile Include="udataswp.c">
<ClCompile Include="udataswp.cpp">
<Filter>data &amp; memory</Filter>
</ClCompile>
<ClCompile Include="uinit.cpp">
<Filter>data &amp; memory</Filter>
</ClCompile>
<ClCompile Include="umapfile.c">
<ClCompile Include="umapfile.cpp">
<Filter>data &amp; memory</Filter>
</ClCompile>
<ClCompile Include="uobject.cpp">
@ -289,7 +295,7 @@
<ClCompile Include="ucurr.cpp">
<Filter>formatting</Filter>
</ClCompile>
<ClCompile Include="ustrfmt.c">
<ClCompile Include="ustrfmt.cpp">
<Filter>formatting</Filter>
</ClCompile>
<ClCompile Include="util.cpp">
@ -334,16 +340,16 @@
<ClCompile Include="resbund_cnv.cpp">
<Filter>locales &amp; resources</Filter>
</ClCompile>
<ClCompile Include="ucat.c">
<ClCompile Include="ucat.cpp">
<Filter>locales &amp; resources</Filter>
</ClCompile>
<ClCompile Include="uloc.cpp">
<Filter>locales &amp; resources</Filter>
</ClCompile>
<ClCompile Include="uloc_tag.c">
<ClCompile Include="uloc_tag.cpp">
<Filter>locales &amp; resources</Filter>
</ClCompile>
<ClCompile Include="ures_cnv.c">
<ClCompile Include="ures_cnv.cpp">
<Filter>locales &amp; resources</Filter>
</ClCompile>
<ClCompile Include="uresbund.cpp">
@ -382,6 +388,9 @@
<ClCompile Include="bmpset.cpp">
<Filter>properties &amp; sets</Filter>
</ClCompile>
<ClCompile Include="characterproperties.cpp">
<Filter>properties &amp; sets</Filter>
</ClCompile>
<ClCompile Include="propname.cpp">
<Filter>properties &amp; sets</Filter>
</ClCompile>
@ -391,7 +400,7 @@
<ClCompile Include="ucase.cpp">
<Filter>properties &amp; sets</Filter>
</ClCompile>
<ClCompile Include="uchar.c">
<ClCompile Include="uchar.cpp">
<Filter>properties &amp; sets</Filter>
</ClCompile>
<ClCompile Include="unames.cpp">
@ -418,10 +427,10 @@
<ClCompile Include="uprops.cpp">
<Filter>properties &amp; sets</Filter>
</ClCompile>
<ClCompile Include="usc_impl.c">
<ClCompile Include="usc_impl.cpp">
<Filter>properties &amp; sets</Filter>
</ClCompile>
<ClCompile Include="uscript.c">
<ClCompile Include="uscript.cpp">
<Filter>properties &amp; sets</Filter>
</ClCompile>
<ClCompile Include="uscript_props.cpp">
@ -460,6 +469,9 @@
<ClCompile Include="usprep.cpp">
<Filter>sprep</Filter>
</ClCompile>
<ClCompile Include="bytesinkutil.cpp">
<Filter>strings</Filter>
</ClCompile>
<ClCompile Include="bytestream.cpp">
<Filter>strings</Filter>
</ClCompile>
@ -469,13 +481,16 @@
<ClCompile Include="charstr.cpp">
<Filter>strings</Filter>
</ClCompile>
<ClCompile Include="cstring.c">
<ClCompile Include="cstring.cpp">
<Filter>strings</Filter>
</ClCompile>
<ClCompile Include="cstr.cpp">
<Filter>strings</Filter>
</ClCompile>
<ClCompile Include="cwchar.c">
<ClCompile Include="cwchar.cpp">
<Filter>strings</Filter>
</ClCompile>
<ClCompile Include="edits.cpp">
<Filter>strings</Filter>
</ClCompile>
<ClCompile Include="schriter.cpp">
@ -493,7 +508,7 @@
<ClCompile Include="uchriter.cpp">
<Filter>strings</Filter>
</ClCompile>
<ClCompile Include="uinvchar.c">
<ClCompile Include="uinvchar.cpp">
<Filter>strings</Filter>
</ClCompile>
<ClCompile Include="uiter.cpp">
@ -541,7 +556,7 @@
<ClCompile Include="utext.cpp">
<Filter>strings</Filter>
</ClCompile>
<ClCompile Include="utf_impl.c">
<ClCompile Include="utf_impl.cpp">
<Filter>strings</Filter>
</ClCompile>
<ClCompile Include="bytestrie.cpp">
@ -553,12 +568,6 @@
<ClCompile Include="bytestriebuilder.cpp">
<Filter>collections</Filter>
</ClCompile>
<ClCompile Include="listformatter.cpp">
<Filter>formatting</Filter>
</ClCompile>
<ClCompile Include="ulistformatter.cpp">
<Filter>formatting</Filter>
</ClCompile>
<ClCompile Include="messagepattern.cpp">
<Filter>formatting</Filter>
</ClCompile>
@ -568,7 +577,7 @@
<ClCompile Include="dictionarydata.cpp">
<Filter>break iteration</Filter>
</ClCompile>
<ClCompile Include="ucnv_ct.c">
<ClCompile Include="ucnv_ct.cpp">
<Filter>conversion</Filter>
</ClCompile>
<ClCompile Include="ucharstrie.cpp">
@ -580,6 +589,12 @@
<ClCompile Include="ucharstrieiterator.cpp">
<Filter>collections</Filter>
</ClCompile>
<ClCompile Include="ucptrie.cpp">
<Filter>collections</Filter>
</ClCompile>
<ClCompile Include="umutablecptrie.cpp">
<Filter>collections</Filter>
</ClCompile>
<ClCompile Include="patternprops.cpp">
<Filter>properties &amp; sets</Filter>
</ClCompile>
@ -595,9 +610,12 @@
<ClCompile Include="icuplug.cpp">
<Filter>registration</Filter>
</ClCompile>
<ClCompile Include="ubiditransform.c">
<ClCompile Include="ubiditransform.cpp">
<Filter>bidi</Filter>
</ClCompile>
<ClCompile Include="static_unicode_sets.cpp">
<Filter>formatting</Filter>
</ClCompile>
</ItemGroup>
<ItemGroup>
<ClInclude Include="ubidi_props.h">
@ -633,6 +651,9 @@
<ClInclude Include="rbbitblb.h">
<Filter>break iteration</Filter>
</ClInclude>
<ClInclude Include="rbbi_cache.h">
<Filter>break iteration</Filter>
</ClInclude>
<ClInclude Include="ubrkimpl.h">
<Filter>break iteration</Filter>
</ClInclude>
@ -858,6 +879,9 @@
<ClInclude Include="sprpimpl.h">
<Filter>sprep</Filter>
</ClInclude>
<ClInclude Include="bytesinkutil.h">
<Filter>strings</Filter>
</ClInclude>
<ClInclude Include="charstr.h">
<Filter>strings</Filter>
</ClInclude>
@ -870,6 +894,9 @@
<ClInclude Include="cwchar.h">
<Filter>strings</Filter>
</ClInclude>
<ClInclude Include="ucasemap_imp.h">
<Filter>strings</Filter>
</ClInclude>
<ClInclude Include="uinvchar.h">
<Filter>strings</Filter>
</ClInclude>
@ -918,6 +945,9 @@
<ClInclude Include="unicode\ubiditransform.h">
<Filter>bidi</Filter>
</ClInclude>
<ClInclude Include="static_unicode_sets.h">
<Filter>formatting</Filter>
</ClInclude>
</ItemGroup>
<ItemGroup>
<ResourceCompile Include="common.rc">
@ -1096,9 +1126,18 @@
<CustomBuild Include="unicode\bytestream.h">
<Filter>strings</Filter>
</CustomBuild>
<CustomBuild Include="unicode\casemap.h">
<Filter>strings</Filter>
</CustomBuild>
<CustomBuild Include="unicode\char16ptr.h">
<Filter>strings</Filter>
</CustomBuild>
<CustomBuild Include="unicode\chariter.h">
<Filter>strings</Filter>
</CustomBuild>
<CustomBuild Include="unicode\edits.h">
<Filter>strings</Filter>
</CustomBuild>
<CustomBuild Include="unicode\rep.h">
<Filter>strings</Filter>
</CustomBuild>
@ -1153,12 +1192,6 @@
<CustomBuild Include="unicode\messagepattern.h">
<Filter>formatting</Filter>
</CustomBuild>
<CustomBuild Include="unicode\listformatter.h">
<Filter>formatting</Filter>
</CustomBuild>
<CustomBuild Include="unicode\ulistformatter.h">
<Filter>formatting</Filter>
</CustomBuild>
<CustomBuild Include="unicode\appendable.h">
<Filter>strings</Filter>
</CustomBuild>
@ -1171,6 +1204,12 @@
<CustomBuild Include="unicode\ucharstriebuilder.h">
<Filter>collections</Filter>
</CustomBuild>
<CustomBuild Include="unicode\ucptrie.h">
<Filter>collections</Filter>
</CustomBuild>
<CustomBuild Include="unicode\umutablecptrie.h">
<Filter>collections</Filter>
</CustomBuild>
<CustomBuild Include="unicode\enumset.h">
<Filter>data &amp; memory</Filter>
</CustomBuild>
@ -1180,5 +1219,8 @@
<CustomBuild Include="unicode\stringtriebuilder.h">
<Filter>collections</Filter>
</CustomBuild>
<CustomBuild Include="unicode\stringoptions.h">
<Filter>strings</Filter>
</CustomBuild>
</ItemGroup>
</Project>
</Project>

580
intl/icu/source/common/common_uwp.vcxproj Normal file
View file

@ -0,0 +1,580 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="14.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<!-- The following import will include the UWP configuration options for VS projects. -->
<Import Project="..\allinone\Build.Windows.UWP.ProjectConfiguration.props" />
<!-- The following import will include the library configuration options for VS projects. -->
<Import Project="..\allinone\Build.Windows.Library.ProjectConfiguration.props" />
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|Win32">
<Configuration>Debug</Configuration>
<Platform>Win32</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Debug|ARM">
<Configuration>Debug</Configuration>
<Platform>ARM</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|Win32">
<Configuration>Release</Configuration>
<Platform>Win32</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|ARM">
<Configuration>Release</Configuration>
<Platform>ARM</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{C10CF34B-3F79-430E-AD38-5A32DC0589C2}</ProjectGuid>
<Keyword>DynamicLibrary</Keyword>
<DefaultLanguage>en-US</DefaultLanguage>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup Label="Configuration">
<ConfigurationType>DynamicLibrary</ConfigurationType>
<UseOfMfc>false</UseOfMfc>
<CharacterSet>MultiByte</CharacterSet>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
<Import Project="$(VCTargetsPath)Microsoft.CPP.UpgradeFromVC71.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<_ProjectFileVersion>10.0.30319.1</_ProjectFileVersion>
<OutDir Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">.\x86\ReleaseUWP\</OutDir>
<IntDir Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">.\x86\ReleaseUWP\</IntDir>
<OutDir Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">.\x86\DebugUWP\</OutDir>
<IntDir Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">.\x86\DebugUWP\</IntDir>
<OutDir Condition="'$(Configuration)|$(Platform)'=='Release|x64'">.\x64\ReleaseUWP\</OutDir>
<IntDir Condition="'$(Configuration)|$(Platform)'=='Release|x64'">.\x64\ReleaseUWP\</IntDir>
<OutDir Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">.\x64\DebugUWP\</OutDir>
<IntDir Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">.\x64\DebugUWP\</IntDir>
<OutDir Condition="'$(Configuration)|$(Platform)'=='Release|ARM'">.\arm\ReleaseUWP\</OutDir>
<IntDir Condition="'$(Configuration)|$(Platform)'=='Release|ARM'">.\arm\ReleaseUWP\</IntDir>
<OutDir Condition="'$(Configuration)|$(Platform)'=='Debug|ARM'">.\arm\DebugUWP\</OutDir>
<IntDir Condition="'$(Configuration)|$(Platform)'=='Debug|ARM'">.\arm\DebugUWP\</IntDir>
<LinkIncremental Condition="'$(Configuration)'=='Release'">false</LinkIncremental>
<LinkIncremental Condition="'$(Configuration)'=='Debug'">true</LinkIncremental>
</PropertyGroup>
<ItemDefinitionGroup>
<!-- Options that are common to *all* configurations -->
<Midl>
<MkTypLibCompatible>true</MkTypLibCompatible>
<SuppressStartupBanner>true</SuppressStartupBanner>
</Midl>
<ClCompile>
<AdditionalIncludeDirectories>..\..\include;..\common;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
<!-- U_DISABLE_RENAMING -->
<!-- U_HIDE_DRAFT_API & U_HIDE_DEPRECATED_API -->
<PreprocessorDefinitions>U_ATTRIBUTE_DEPRECATED=;_CRT_SECURE_NO_DEPRECATE;U_COMMON_IMPLEMENTATION;U_PLATFORM_USES_ONLY_WIN32_API=1;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<StringPooling>true</StringPooling>
<ExceptionHandling>
</ExceptionHandling>
<FunctionLevelLinking>true</FunctionLevelLinking>
<DisableLanguageExtensions>false</DisableLanguageExtensions>
<TreatWChar_tAsBuiltInType>true</TreatWChar_tAsBuiltInType>
<WarningLevel>Level3</WarningLevel>
<SuppressStartupBanner>true</SuppressStartupBanner>
<CompileAs>Default</CompileAs>
<PrecompiledHeader>NotUsing</PrecompiledHeader>
<CompileAsWinRT>false</CompileAsWinRT>
<AdditionalOptions>/utf-8 %(AdditionalOptions)</AdditionalOptions>
</ClCompile>
<ResourceCompile>
<Culture>0x0409</Culture>
<AdditionalIncludeDirectories>../common;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
</ResourceCompile>
<Link>
<SuppressStartupBanner>true</SuppressStartupBanner>
<GenerateWindowsMetadata>false</GenerateWindowsMetadata>
<RandomizedBaseAddress>true</RandomizedBaseAddress>
<DataExecutionPrevention>
</DataExecutionPrevention>
<TurnOffAssemblyGeneration>true</TurnOffAssemblyGeneration>
<IgnoreSpecificDefaultLibraries>vccorlib.lib;msvcrt.lib</IgnoreSpecificDefaultLibraries>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<!-- Options that are common to all 'Release' configurations -->
<Midl>
<PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
</Midl>
<ClCompile>
<PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<RuntimeLibrary>MultiThreadedDLL</RuntimeLibrary>
</ClCompile>
<ResourceCompile>
<PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
</ResourceCompile>
<Link>
<EnableCOMDATFolding>true</EnableCOMDATFolding>
<AdditionalDependencies>vccorlib.lib;WindowsApp.lib;msvcrt.lib;%(AdditionalDependencies)</AdditionalDependencies>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<!-- Options that are common to all 'Debug' configurations -->
<Midl>
<PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
</Midl>
<ClCompile>
<PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<RuntimeLibrary>MultiThreadedDebugDLL</RuntimeLibrary>
<Optimization>Disabled</Optimization>
<BasicRuntimeChecks>EnableFastChecks</BasicRuntimeChecks>
<BufferSecurityCheck>true</BufferSecurityCheck>
<DebugInformationFormat>EditAndContinue</DebugInformationFormat>
</ClCompile>
<ResourceCompile>
<PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
</ResourceCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<AdditionalDependencies>vccorlibd.lib;WindowsApp.lib;msvcrtd.lib;%(AdditionalDependencies)</AdditionalDependencies>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Platform)'=='Win32'">
<!-- Options that are common to all 32-bit configurations -->
<Midl>
<TargetEnvironment>Win32</TargetEnvironment>
</Midl>
<ClCompile>
<PreprocessorDefinitions>WIN32;%(PreprocessorDefinitions)</PreprocessorDefinitions>
</ClCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Platform)'=='x64'">
<!-- Options that are common to all 64-bit configurations -->
<Midl>
<TargetEnvironment>X64</TargetEnvironment>
</Midl>
<ClCompile>
<PreprocessorDefinitions>WIN64;WIN32;%(PreprocessorDefinitions)</PreprocessorDefinitions>
</ClCompile>
<Link>
<TargetMachine>MachineX64</TargetMachine>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Platform)'=='ARM'">
<!-- Options that are common to all ARM configurations -->
<Midl>
<TargetEnvironment>ARM</TargetEnvironment>
</Midl>
<ClCompile>
<PreprocessorDefinitions>ARM;WIN32;%(PreprocessorDefinitions)</PreprocessorDefinitions>
</ClCompile>
<Link>
<TargetMachine>MachineARM</TargetMachine>
</Link>
</ItemDefinitionGroup>
<!-- Options that are specific to a particular configuration -->
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
<Midl>
<TypeLibraryName>.\..\..\lib32uwp\icuuc.tlb</TypeLibraryName>
</Midl>
<ClCompile>
<PrecompiledHeaderOutputFile>.\x86\ReleaseUWP/common.pch</PrecompiledHeaderOutputFile>
<AssemblerListingLocation>.\x86\ReleaseUWP/</AssemblerListingLocation>
<ObjectFileName>.\x86\ReleaseUWP/</ObjectFileName>
<ProgramDataBaseFileName>.\x86\ReleaseUWP/</ProgramDataBaseFileName>
</ClCompile>
<Link>
<OutputFile>..\..\bin32uwp\icuuc63.dll</OutputFile>
<ProgramDatabaseFile>.\..\..\lib32uwp\icuuc.pdb</ProgramDatabaseFile>
<ImportLibrary>..\..\lib32uwp\icuuc.lib</ImportLibrary>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
<Midl>
<TypeLibraryName>.\..\..\lib32uwp\icuucd.tlb</TypeLibraryName>
</Midl>
<ClCompile>
<PrecompiledHeaderOutputFile>.\x86\DebugUWP/common.pch</PrecompiledHeaderOutputFile>
<AssemblerListingLocation>.\x86\DebugUWP/</AssemblerListingLocation>
<ObjectFileName>.\x86\DebugUWP/</ObjectFileName>
<ProgramDataBaseFileName>.\x86\DebugUWP/</ProgramDataBaseFileName>
</ClCompile>
<Link>
<OutputFile>..\..\bin32uwp\icuuc63d.dll</OutputFile>
<ProgramDatabaseFile>.\..\..\lib32uwp\icuucd.pdb</ProgramDatabaseFile>
<ImportLibrary>..\..\lib32uwp\icuucd.lib</ImportLibrary>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
<Midl>
<TypeLibraryName>.\..\..\lib64uwp\icuuc.tlb</TypeLibraryName>
</Midl>
<ClCompile>
<PrecompiledHeaderOutputFile>.\x64\ReleaseUWP/common.pch</PrecompiledHeaderOutputFile>
<AssemblerListingLocation>.\x64\ReleaseUWP/</AssemblerListingLocation>
<ObjectFileName>.\x64\ReleaseUWP/</ObjectFileName>
<ProgramDataBaseFileName>.\x64\ReleaseUWP/</ProgramDataBaseFileName>
</ClCompile>
<Link>
<OutputFile>..\..\bin64uwp\icuuc63.dll</OutputFile>
<ProgramDatabaseFile>.\..\..\lib64uwp\icuuc.pdb</ProgramDatabaseFile>
<ImportLibrary>..\..\lib64uwp\icuuc.lib</ImportLibrary>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
<Midl>
<TypeLibraryName>.\..\..\lib64uwp\icuucd.tlb</TypeLibraryName>
</Midl>
<ClCompile>
<PrecompiledHeaderOutputFile>.\x64\DebugUWP/common.pch</PrecompiledHeaderOutputFile>
<AssemblerListingLocation>.\x64\DebugUWP/</AssemblerListingLocation>
<ObjectFileName>.\x64\DebugUWP/</ObjectFileName>
<ProgramDataBaseFileName>.\x64\DebugUWP/</ProgramDataBaseFileName>
</ClCompile>
<Link>
<OutputFile>..\..\bin64uwp\icuuc63d.dll</OutputFile>
<ProgramDatabaseFile>.\..\..\lib64uwp\icuucd.pdb</ProgramDatabaseFile>
<ImportLibrary>..\..\lib64uwp\icuucd.lib</ImportLibrary>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|ARM'">
<Midl>
<TypeLibraryName>.\..\..\libARMuwp\icuuc.tlb</TypeLibraryName>
</Midl>
<ClCompile>
<PrecompiledHeaderOutputFile>.\ARM\ReleaseUWP/common.pch</PrecompiledHeaderOutputFile>
<AssemblerListingLocation>.\ARM\ReleaseUWP/</AssemblerListingLocation>
<ObjectFileName>.\ARM\ReleaseUWP/</ObjectFileName>
<ProgramDataBaseFileName>.\ARM\ReleaseUWP/</ProgramDataBaseFileName>
</ClCompile>
<Link>
<OutputFile>..\..\binARMuwp\icuuc63.dll</OutputFile>
<ProgramDatabaseFile>.\..\..\libARMuwp\icuuc.pdb</ProgramDatabaseFile>
<ImportLibrary>..\..\libARMuwp\icuuc.lib</ImportLibrary>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|ARM'">
<Midl>
<TypeLibraryName>.\..\..\libARMuwp\icuucd.tlb</TypeLibraryName>
</Midl>
<ClCompile>
<PrecompiledHeaderOutputFile>.\ARM\DebugUWP/common.pch</PrecompiledHeaderOutputFile>
<AssemblerListingLocation>.\ARM\DebugUWP/</AssemblerListingLocation>
<ObjectFileName>.\ARM\DebugUWP/</ObjectFileName>
<ProgramDataBaseFileName>.\ARM\DebugUWP/</ProgramDataBaseFileName>
</ClCompile>
<Link>
<OutputFile>..\..\binARMuwp\icuuc63d.dll</OutputFile>
<ProgramDatabaseFile>.\..\..\libARMuwp\icuucd.pdb</ProgramDatabaseFile>
<ImportLibrary>..\..\libARMuwp\icuucd.lib</ImportLibrary>
</Link>
</ItemDefinitionGroup>
<ItemGroup>
<ClCompile Include="edits.cpp" />
<ClCompile Include="filteredbrk.cpp" />
<ClCompile Include="ubidi.cpp" />
<ClCompile Include="ubidi_props.cpp" />
<ClCompile Include="ubiditransform.cpp" />
<ClCompile Include="ubidiln.cpp" />
<ClCompile Include="ubidiwrt.cpp" />
<ClCompile Include="uloc_keytype.cpp" />
<ClCompile Include="ushape.cpp" />
<ClCompile Include="brkeng.cpp" />
<ClCompile Include="brkiter.cpp" />
<ClCompile Include="dictbe.cpp" />
<ClCompile Include="pluralmap.cpp" />
<ClCompile Include="rbbi.cpp" />
<ClCompile Include="rbbidata.cpp" />
<ClCompile Include="rbbinode.cpp" />
<ClCompile Include="rbbirb.cpp" />
<ClCompile Include="rbbiscan.cpp" />
<ClCompile Include="rbbisetb.cpp" />
<ClCompile Include="rbbistbl.cpp" />
<ClCompile Include="rbbitblb.cpp" />
<ClCompile Include="rbbi_cache.cpp" />
<ClCompile Include="dictionarydata.cpp" />
<ClCompile Include="ubrk.cpp" />
<ClCompile Include="ucol_swp.cpp" />
<ClCompile Include="propsvec.cpp" />
<ClCompile Include="uarrsort.cpp" />
<ClCompile Include="uenum.cpp" />
<ClCompile Include="uhash.cpp" />
<ClCompile Include="uhash_us.cpp" />
<ClCompile Include="ulist.cpp" />
<ClCompile Include="ustack.cpp" />
<ClCompile Include="ustrenum.cpp" />
<ClCompile Include="utrie.cpp" />
<ClCompile Include="utrie_swap.cpp" />
<ClCompile Include="utrie2.cpp" />
<ClCompile Include="utrie2_builder.cpp" />
<ClCompile Include="uvector.cpp" />
<ClCompile Include="uvectr32.cpp" />
<ClCompile Include="uvectr64.cpp" />
<ClCompile Include="errorcode.cpp" />
<ClCompile Include="icudataver.cpp" />
<ClCompile Include="locmap.cpp" />
<ClCompile Include="putil.cpp">
<CompileAsWinRT>true</CompileAsWinRT>
</ClCompile>
<ClCompile Include="umath.cpp" />
<ClCompile Include="umutex.cpp" />
<ClCompile Include="utrace.cpp" />
<ClCompile Include="utypes.cpp" />
<ClCompile Include="wintz.cpp" />
<ClCompile Include="ucnv.cpp" />
<ClCompile Include="ucnv2022.cpp" />
<ClCompile Include="ucnv_bld.cpp" />
<ClCompile Include="ucnv_cb.cpp" />
<ClCompile Include="ucnv_cnv.cpp" />
<ClCompile Include="ucnv_ct.cpp" />
<ClCompile Include="ucnv_err.cpp" />
<ClCompile Include="ucnv_ext.cpp" />
<ClCompile Include="ucnv_io.cpp" />
<ClCompile Include="ucnv_lmb.cpp" />
<ClCompile Include="ucnv_set.cpp" />
<ClCompile Include="ucnv_u16.cpp" />
<ClCompile Include="ucnv_u32.cpp" />
<ClCompile Include="ucnv_u7.cpp" />
<ClCompile Include="ucnv_u8.cpp" />
<ClCompile Include="ucnvbocu.cpp" />
<ClCompile Include="ucnvdisp.cpp" />
<ClCompile Include="ucnvhz.cpp" />
<ClCompile Include="ucnvisci.cpp" />
<ClCompile Include="ucnvlat1.cpp" />
<ClCompile Include="ucnvmbcs.cpp" />
<ClCompile Include="ucnvscsu.cpp" />
<ClCompile Include="ucnvsel.cpp" />
<ClCompile Include="cmemory.cpp" />
<ClCompile Include="ucln_cmn.cpp" />
<ClCompile Include="ucmndata.cpp" />
<ClCompile Include="udata.cpp" />
<ClCompile Include="udatamem.cpp" />
<ClCompile Include="udataswp.cpp" />
<ClCompile Include="uinit.cpp" />
<ClCompile Include="umapfile.cpp" />
<ClCompile Include="uobject.cpp" />
<ClCompile Include="dtintrv.cpp" />
<ClCompile Include="parsepos.cpp" />
<ClCompile Include="ustrfmt.cpp" />
<ClCompile Include="util.cpp" />
<ClCompile Include="util_props.cpp" />
<ClCompile Include="punycode.cpp" />
<ClCompile Include="uidna.cpp" />
<ClCompile Include="uts46.cpp" />
<ClCompile Include="locavailable.cpp" />
<ClCompile Include="locbased.cpp" />
<ClCompile Include="locdispnames.cpp" />
<ClCompile Include="locdspnm.cpp" />
<ClCompile Include="locid.cpp" />
<ClCompile Include="loclikely.cpp" />
<ClCompile Include="locresdata.cpp" />
<ClCompile Include="locutil.cpp" />
<ClCompile Include="resbund.cpp" />
<ClCompile Include="resbund_cnv.cpp" />
<ClCompile Include="ucat.cpp" />
<ClCompile Include="uloc.cpp" />
<ClCompile Include="uloc_tag.cpp" />
<ClCompile Include="ures_cnv.cpp" />
<ClCompile Include="uresbund.cpp" />
<ClCompile Include="uresdata.cpp" />
<ClCompile Include="resource.cpp" />
<ClCompile Include="ucurr.cpp" />
<ClCompile Include="caniter.cpp" />
<ClCompile Include="filterednormalizer2.cpp" />
<ClCompile Include="loadednormalizer2impl.cpp" />
<ClCompile Include="normalizer2.cpp" />
<ClCompile Include="normalizer2impl.cpp" />
<ClCompile Include="normlzr.cpp" />
<ClCompile Include="unorm.cpp" />
<ClCompile Include="unormcmp.cpp" />
<ClCompile Include="bmpset.cpp" />
<ClCompile Include="patternprops.cpp" />
<ClCompile Include="propname.cpp" />
<ClCompile Include="ruleiter.cpp" />
<ClCompile Include="ucase.cpp" />
<ClCompile Include="uchar.cpp" />
<ClCompile Include="characterproperties.cpp" />
<ClCompile Include="unames.cpp" />
<ClCompile Include="unifiedcache.cpp" />
<ClCompile Include="unifilt.cpp" />
<ClCompile Include="unifunct.cpp" />
<ClCompile Include="uniset.cpp" />
<ClCompile Include="uniset_closure.cpp" />
<ClCompile Include="uniset_props.cpp" />
<ClCompile Include="unisetspan.cpp" />
<ClCompile Include="uprops.cpp" />
<ClCompile Include="usc_impl.cpp" />
<ClCompile Include="uscript.cpp" />
<ClCompile Include="uscript_props.cpp" />
<ClCompile Include="uset.cpp" />
<ClCompile Include="uset_props.cpp" />
<ClCompile Include="usetiter.cpp" />
<ClCompile Include="icuplug.cpp" />
<ClCompile Include="serv.cpp" />
<ClCompile Include="servlk.cpp" />
<ClCompile Include="servlkf.cpp" />
<ClCompile Include="servls.cpp" />
<ClCompile Include="servnotf.cpp" />
<ClCompile Include="servrbf.cpp" />
<ClCompile Include="servslkf.cpp" />
<ClCompile Include="usprep.cpp" />
<ClCompile Include="appendable.cpp" />
<ClCompile Include="bytesinkutil.cpp" />
<ClCompile Include="bytestream.cpp" />
<ClCompile Include="bytestrie.cpp" />
<ClCompile Include="bytestriebuilder.cpp" />
<ClCompile Include="bytestrieiterator.cpp" />
<ClCompile Include="chariter.cpp" />
<ClCompile Include="charstr.cpp" />
<ClCompile Include="cstring.cpp" />
<ClCompile Include="cstr.cpp" />
<ClCompile Include="cwchar.cpp" />
<ClCompile Include="messagepattern.cpp" />
<ClCompile Include="schriter.cpp" />
<ClCompile Include="stringpiece.cpp" />
<ClCompile Include="stringtriebuilder.cpp" />
<ClCompile Include="simpleformatter.cpp" />
<ClCompile Include="ucasemap.cpp" />
<ClCompile Include="ucasemap_titlecase_brkiter.cpp" />
<ClCompile Include="ucharstrie.cpp" />
<ClCompile Include="ucharstriebuilder.cpp" />
<ClCompile Include="ucharstrieiterator.cpp" />
<ClCompile Include="ucptrie.cpp" />
<ClCompile Include="uchriter.cpp" />
<ClCompile Include="uinvchar.cpp" />
<ClCompile Include="uiter.cpp" />
<ClCompile Include="umutablecptrie.cpp" />
<ClCompile Include="unistr.cpp" />
<ClCompile Include="unistr_case.cpp" />
<ClCompile Include="unistr_case_locale.cpp" />
<ClCompile Include="unistr_cnv.cpp" />
<ClCompile Include="unistr_props.cpp" />
<ClCompile Include="unistr_titlecase_brkiter.cpp" />
<ClCompile Include="ustr_cnv.cpp" />
<ClCompile Include="ustr_titlecase_brkiter.cpp" />
<ClCompile Include="ustr_wcs.cpp" />
<ClCompile Include="ustrcase.cpp" />
<ClCompile Include="ustrcase_locale.cpp" />
<ClCompile Include="ustring.cpp" />
<ClCompile Include="ustrtrns.cpp" />
<ClCompile Include="utext.cpp" />
<ClCompile Include="utf_impl.cpp" />
<ClCompile Include="static_unicode_sets.cpp" />
</ItemGroup>
<ItemGroup>
<ClInclude Include="localsvc.h" />
<ClInclude Include="msvcres.h" />
<ClInclude Include="pluralmap.h" />
<ClInclude Include="propname_data.h" />
<ClInclude Include="ubidi_props.h" />
<ClInclude Include="ubidiimp.h" />
<ClInclude Include="brkeng.h" />
<ClInclude Include="dictbe.h" />
<ClInclude Include="rbbidata.h" />
<ClInclude Include="rbbinode.h" />
<ClInclude Include="rbbirb.h" />
<ClInclude Include="rbbirpt.h" />
<ClInclude Include="rbbiscan.h" />
<ClInclude Include="rbbisetb.h" />
<ClInclude Include="rbbitblb.h" />
<ClInclude Include="rbbi_cache.h" />
<ClInclude Include="dictionarydata.h" />
<ClInclude Include="ubidi_props_data.h" />
<ClInclude Include="ubrkimpl.h" />
<ClInclude Include="ucase_props_data.h" />
<ClInclude Include="uchar_props_data.h" />
<ClInclude Include="ucol_data.h" />
<ClInclude Include="ucol_swp.h" />
<ClInclude Include="unicode\ubiditransform.h" />
<ClInclude Include="unistrappender.h" />
<ClInclude Include="hash.h" />
<ClInclude Include="propsvec.h" />
<ClInclude Include="uarrsort.h" />
<ClInclude Include="uelement.h" />
<ClInclude Include="uenumimp.h" />
<ClInclude Include="uhash.h" />
<ClInclude Include="ulist.h" />
<ClInclude Include="unicode\filteredbrk.h" />
<ClInclude Include="ustrenum.h" />
<ClInclude Include="utrie.h" />
<ClInclude Include="utrie2.h" />
<ClInclude Include="utrie2_impl.h" />
<ClInclude Include="utypeinfo.h" />
<ClInclude Include="uvector.h" />
<ClInclude Include="uvectr32.h" />
<ClInclude Include="uvectr64.h" />
<ClInclude Include="cpputils.h" />
<ClInclude Include="locmap.h" />
<ClInclude Include="mutex.h" />
<ClInclude Include="putilimp.h" />
<ClInclude Include="uassert.h" />
<ClInclude Include="umutex.h" />
<ClInclude Include="uposixdefs.h" />
<ClInclude Include="utracimp.h" />
<ClInclude Include="wintz.h" />
<ClInclude Include="ucnv_bld.h" />
<ClInclude Include="ucnv_cnv.h" />
<ClInclude Include="ucnv_ext.h" />
<ClInclude Include="ucnv_imp.h" />
<ClInclude Include="ucnv_io.h" />
<ClInclude Include="ucnvmbcs.h" />
<ClInclude Include="cmemory.h" />
<ClInclude Include="ucln.h" />
<ClInclude Include="ucln_cmn.h" />
<ClInclude Include="ucln_imp.h" />
<ClInclude Include="ucmndata.h" />
<ClInclude Include="udatamem.h" />
<ClInclude Include="udataswp.h" />
<ClInclude Include="umapfile.h" />
<ClInclude Include="ustrfmt.h" />
<ClInclude Include="util.h" />
<ClInclude Include="punycode.h" />
<ClInclude Include="locbased.h" />
<ClInclude Include="locutil.h" />
<ClInclude Include="sharedobject.h" />
<ClCompile Include="sharedobject.cpp" />
<ClInclude Include="ulocimp.h" />
<ClInclude Include="unifiedcache.h" />
<ClInclude Include="uresdata.h" />
<ClInclude Include="uresimp.h" />
<ClInclude Include="ureslocs.h" />
<ClInclude Include="resource.h" />
<ClInclude Include="ucurrimp.h" />
<ClInclude Include="norm2allmodes.h" />
<ClInclude Include="normalizer2impl.h" />
<ClInclude Include="unormimp.h" />
<ClInclude Include="bmpset.h" />
<ClInclude Include="messageimpl.h" />
<ClInclude Include="patternprops.h" />
<ClInclude Include="propname.h" />
<ClInclude Include="ruleiter.h" />
<ClInclude Include="ucase.h" />
<ClInclude Include="unisetspan.h" />
<ClInclude Include="uprops.h" />
<ClInclude Include="usc_impl.h" />
<ClInclude Include="uset_imp.h" />
<ClInclude Include="icuplugimp.h" />
<ClInclude Include="serv.h" />
<ClInclude Include="servloc.h" />
<ClInclude Include="servnotf.h" />
<ClInclude Include="sprpimpl.h" />
<ClInclude Include="bytesinkutil.h" />
<ClInclude Include="charstr.h" />
<ClInclude Include="cstring.h" />
<ClInclude Include="cstr.h" />
<ClInclude Include="cwchar.h" />
<ClInclude Include="uinvchar.h" />
<ClInclude Include="ustr_cnv.h" />
<ClInclude Include="ustr_imp.h" />
<ClInclude Include="static_unicode_sets.h" />
</ItemGroup>
<ItemGroup>
<ResourceCompile Include="common.rc" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
</ImportGroup>
</Project>

4
intl/icu/source/common/cpputils.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
@ -8,7 +8,7 @@
*
******************************************************************************
* file name: cpputils.h
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*/

2
intl/icu/source/common/cstr.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************

2
intl/icu/source/common/cstr.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************

2
intl/icu/source/common/cstring.c → intl/icu/source/common/cstring.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************

20
intl/icu/source/common/cstring.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
@ -40,28 +40,10 @@
#define uprv_strchr(s, c) U_STANDARD_CPP_NAMESPACE strchr(s, c)
#define uprv_strstr(s, c) U_STANDARD_CPP_NAMESPACE strstr(s, c)
#define uprv_strrchr(s, c) U_STANDARD_CPP_NAMESPACE strrchr(s, c)
#if U_DEBUG
#define uprv_strncpy(dst, src, size) ( \
uprv_checkValidMemory(src, 1), \
U_STANDARD_CPP_NAMESPACE strncpy(dst, src, size))
#define uprv_strncmp(s1, s2, n) ( \
uprv_checkValidMemory(s1, 1), \
uprv_checkValidMemory(s2, 1), \
U_STANDARD_CPP_NAMESPACE strncmp(s1, s2, n))
#define uprv_strncat(dst, src, n) ( \
uprv_checkValidMemory(src, 1), \
U_STANDARD_CPP_NAMESPACE strncat(dst, src, n))
#else
#define uprv_strncpy(dst, src, size) U_STANDARD_CPP_NAMESPACE strncpy(dst, src, size)
#define uprv_strncmp(s1, s2, n) U_STANDARD_CPP_NAMESPACE strncmp(s1, s2, n)
#define uprv_strncat(dst, src, n) U_STANDARD_CPP_NAMESPACE strncat(dst, src, n)
#endif /* U_DEBUG */
/**
* Is c an ASCII-repertoire letter a-z or A-Z?
* Note: The implementation is specific to whether ICU is compiled for

4
intl/icu/source/common/cwchar.c → intl/icu/source/common/cwchar.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
@ -8,7 +8,7 @@
*
******************************************************************************
* file name: cwchar.c
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*

4
intl/icu/source/common/cwchar.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
@ -8,7 +8,7 @@
*
******************************************************************************
* file name: cwchar.h
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*

121
intl/icu/source/common/dictbe.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/**
*******************************************************************************
@ -29,26 +29,23 @@ U_NAMESPACE_BEGIN
******************************************************************
*/
DictionaryBreakEngine::DictionaryBreakEngine(uint32_t breakTypes) {
fTypes = breakTypes;
DictionaryBreakEngine::DictionaryBreakEngine() {
}
DictionaryBreakEngine::~DictionaryBreakEngine() {
}
UBool
DictionaryBreakEngine::handles(UChar32 c, int32_t breakType) const {
return (breakType >= 0 && breakType < 32 && (((uint32_t)1 << breakType) & fTypes)
&& fSet.contains(c));
DictionaryBreakEngine::handles(UChar32 c) const {
return fSet.contains(c);
}
int32_t
DictionaryBreakEngine::findBreaks( UText *text,
int32_t startPos,
int32_t endPos,
UBool reverse,
int32_t breakType,
UStack &foundBreaks ) const {
UVector32 &foundBreaks ) const {
(void)startPos; // TODO: remove this param?
int32_t result = 0;
// Find the span of characters included in the set.
@ -60,38 +57,14 @@ DictionaryBreakEngine::findBreaks( UText *text,
int32_t rangeStart;
int32_t rangeEnd;
UChar32 c = utext_current32(text);
if (reverse) {
UBool isDict = fSet.contains(c);
while((current = (int32_t)utext_getNativeIndex(text)) > startPos && isDict) {
c = utext_previous32(text);
isDict = fSet.contains(c);
}
if (current < startPos) {
rangeStart = startPos;
} else {
rangeStart = current;
if (!isDict) {
utext_next32(text);
rangeStart = (int32_t)utext_getNativeIndex(text);
}
}
// rangeEnd = start + 1;
utext_setNativeIndex(text, start);
utext_next32(text);
rangeEnd = (int32_t)utext_getNativeIndex(text);
}
else {
while((current = (int32_t)utext_getNativeIndex(text)) < endPos && fSet.contains(c)) {
utext_next32(text); // TODO: recast loop for postincrement
c = utext_current32(text);
}
rangeStart = start;
rangeEnd = current;
}
if (breakType >= 0 && breakType < 32 && (((uint32_t)1 << breakType) & fTypes)) {
result = divideUpDictionaryRange(text, rangeStart, rangeEnd, foundBreaks);
utext_setNativeIndex(text, current);
while((current = (int32_t)utext_getNativeIndex(text)) < endPos && fSet.contains(c)) {
utext_next32(text); // TODO: recast loop for postincrement
c = utext_current32(text);
}
rangeStart = start;
rangeEnd = current;
result = divideUpDictionaryRange(text, rangeStart, rangeEnd, foundBreaks);
utext_setNativeIndex(text, current);
return result;
}
@ -216,7 +189,7 @@ static const int32_t THAI_MIN_WORD = 2;
static const int32_t THAI_MIN_WORD_SPAN = THAI_MIN_WORD * 2;
ThaiBreakEngine::ThaiBreakEngine(DictionaryMatcher *adoptDictionary, UErrorCode &status)
: DictionaryBreakEngine((1<<UBRK_WORD) | (1<<UBRK_LINE)),
: DictionaryBreakEngine(),
fDictionary(adoptDictionary)
{
fThaiWordSet.applyPattern(UNICODE_STRING_SIMPLE("[[:Thai:]&[:LineBreak=SA:]]"), status);
@ -248,7 +221,7 @@ int32_t
ThaiBreakEngine::divideUpDictionaryRange( UText *text,
int32_t rangeStart,
int32_t rangeEnd,
UStack &foundBreaks ) const {
UVector32 &foundBreaks ) const {
utext_setNativeIndex(text, rangeStart);
utext_moveIndex32(text, THAI_MIN_WORD_SPAN);
if (utext_getNativeIndex(text) >= rangeEnd) {
@ -352,9 +325,9 @@ foundBest:
// two characters after uc were not 0x0E4C THANTHAKHAT before
// checking the dictionary. That is just a performance filter,
// but it's not clear it's faster than checking the trie.
int32_t candidates = words[(wordsFound + 1) % THAI_LOOKAHEAD].candidates(text, fDictionary, rangeEnd);
int32_t num_candidates = words[(wordsFound + 1) % THAI_LOOKAHEAD].candidates(text, fDictionary, rangeEnd);
utext_setNativeIndex(text, current + cuWordLength + chars);
if (candidates > 0) {
if (num_candidates > 0) {
break;
}
}
@ -458,7 +431,7 @@ static const int32_t LAO_MIN_WORD = 2;
static const int32_t LAO_MIN_WORD_SPAN = LAO_MIN_WORD * 2;
LaoBreakEngine::LaoBreakEngine(DictionaryMatcher *adoptDictionary, UErrorCode &status)
: DictionaryBreakEngine((1<<UBRK_WORD) | (1<<UBRK_LINE)),
: DictionaryBreakEngine(),
fDictionary(adoptDictionary)
{
fLaoWordSet.applyPattern(UNICODE_STRING_SIMPLE("[[:Laoo:]&[:LineBreak=SA:]]"), status);
@ -487,7 +460,7 @@ int32_t
LaoBreakEngine::divideUpDictionaryRange( UText *text,
int32_t rangeStart,
int32_t rangeEnd,
UStack &foundBreaks ) const {
UVector32 &foundBreaks ) const {
if ((rangeEnd - rangeStart) < LAO_MIN_WORD_SPAN) {
return 0; // Not enough characters for two words
}
@ -582,9 +555,9 @@ foundBest:
if (fEndWordSet.contains(pc) && fBeginWordSet.contains(uc)) {
// Maybe. See if it's in the dictionary.
// TODO: this looks iffy; compare with old code.
int32_t candidates = words[(wordsFound + 1) % LAO_LOOKAHEAD].candidates(text, fDictionary, rangeEnd);
int32_t num_candidates = words[(wordsFound + 1) % LAO_LOOKAHEAD].candidates(text, fDictionary, rangeEnd);
utext_setNativeIndex(text, current + cuWordLength + chars);
if (candidates > 0) {
if (num_candidates > 0) {
break;
}
}
@ -654,7 +627,7 @@ static const int32_t BURMESE_MIN_WORD = 2;
static const int32_t BURMESE_MIN_WORD_SPAN = BURMESE_MIN_WORD * 2;
BurmeseBreakEngine::BurmeseBreakEngine(DictionaryMatcher *adoptDictionary, UErrorCode &status)
: DictionaryBreakEngine((1<<UBRK_WORD) | (1<<UBRK_LINE)),
: DictionaryBreakEngine(),
fDictionary(adoptDictionary)
{
fBurmeseWordSet.applyPattern(UNICODE_STRING_SIMPLE("[[:Mymr:]&[:LineBreak=SA:]]"), status);
@ -680,7 +653,7 @@ int32_t
BurmeseBreakEngine::divideUpDictionaryRange( UText *text,
int32_t rangeStart,
int32_t rangeEnd,
UStack &foundBreaks ) const {
UVector32 &foundBreaks ) const {
if ((rangeEnd - rangeStart) < BURMESE_MIN_WORD_SPAN) {
return 0; // Not enough characters for two words
}
@ -775,9 +748,9 @@ foundBest:
if (fEndWordSet.contains(pc) && fBeginWordSet.contains(uc)) {
// Maybe. See if it's in the dictionary.
// TODO: this looks iffy; compare with old code.
int32_t candidates = words[(wordsFound + 1) % BURMESE_LOOKAHEAD].candidates(text, fDictionary, rangeEnd);
int32_t num_candidates = words[(wordsFound + 1) % BURMESE_LOOKAHEAD].candidates(text, fDictionary, rangeEnd);
utext_setNativeIndex(text, current + cuWordLength + chars);
if (candidates > 0) {
if (num_candidates > 0) {
break;
}
}
@ -847,7 +820,7 @@ static const int32_t KHMER_MIN_WORD = 2;
static const int32_t KHMER_MIN_WORD_SPAN = KHMER_MIN_WORD * 2;
KhmerBreakEngine::KhmerBreakEngine(DictionaryMatcher *adoptDictionary, UErrorCode &status)
: DictionaryBreakEngine((1 << UBRK_WORD) | (1 << UBRK_LINE)),
: DictionaryBreakEngine(),
fDictionary(adoptDictionary)
{
fKhmerWordSet.applyPattern(UNICODE_STRING_SIMPLE("[[:Khmr:]&[:LineBreak=SA:]]"), status);
@ -885,7 +858,7 @@ int32_t
KhmerBreakEngine::divideUpDictionaryRange( UText *text,
int32_t rangeStart,
int32_t rangeEnd,
UStack &foundBreaks ) const {
UVector32 &foundBreaks ) const {
if ((rangeEnd - rangeStart) < KHMER_MIN_WORD_SPAN) {
return 0; // Not enough characters for two words
}
@ -980,9 +953,9 @@ foundBest:
uc = utext_current32(text);
if (fEndWordSet.contains(pc) && fBeginWordSet.contains(uc)) {
// Maybe. See if it's in the dictionary.
int32_t candidates = words[(wordsFound + 1) % KHMER_LOOKAHEAD].candidates(text, fDictionary, rangeEnd);
int32_t num_candidates = words[(wordsFound + 1) % KHMER_LOOKAHEAD].candidates(text, fDictionary, rangeEnd);
utext_setNativeIndex(text, current+cuWordLength+chars);
if (candidates > 0) {
if (num_candidates > 0) {
break;
}
}
@ -1069,7 +1042,7 @@ foundBest:
*/
static const uint32_t kuint32max = 0xFFFFFFFF;
CjkBreakEngine::CjkBreakEngine(DictionaryMatcher *adoptDictionary, LanguageType type, UErrorCode &status)
: DictionaryBreakEngine(1 << UBRK_WORD), fDictionary(adoptDictionary) {
: DictionaryBreakEngine(), fDictionary(adoptDictionary) {
// Korean dictionary only includes Hangul syllables
fHangulWordSet.applyPattern(UNICODE_STRING_SIMPLE("[\\uac00-\\ud7a3]"), status);
fHanWordSet.applyPattern(UNICODE_STRING_SIMPLE("[:Han:]"), status);
@ -1110,9 +1083,9 @@ static inline uint32_t getKatakanaCost(int32_t wordLength){
return (wordLength > kMaxKatakanaLength) ? 8192 : katakanaCost[wordLength];
}
static inline bool isKatakana(uint16_t value) {
return (value >= 0x30A1u && value <= 0x30FEu && value != 0x30FBu) ||
(value >= 0xFF66u && value <= 0xFF9fu);
static inline bool isKatakana(UChar32 value) {
return (value >= 0x30A1 && value <= 0x30FE && value != 0x30FB) ||
(value >= 0xFF66 && value <= 0xFF9f);
}
@ -1128,14 +1101,14 @@ static inline int32_t utext_i32_flag(int32_t bitIndex) {
* @param text A UText representing the text
* @param rangeStart The start of the range of dictionary characters
* @param rangeEnd The end of the range of dictionary characters
* @param foundBreaks Output of C array of int32_t break positions, or 0
* @param foundBreaks vector<int32> to receive the break positions
* @return The number of breaks found
*/
int32_t
CjkBreakEngine::divideUpDictionaryRange( UText *inText,
int32_t rangeStart,
int32_t rangeEnd,
UStack &foundBreaks ) const {
UVector32 &foundBreaks ) const {
if (rangeStart >= rangeEnd) {
return 0;
}
@ -1346,8 +1319,8 @@ CjkBreakEngine::divideUpDictionaryRange( UText *inText,
}
if (katakanaRunLength < kMaxKatakanaGroupLength) {
uint32_t newSnlp = bestSnlp.elementAti(i) + getKatakanaCost(katakanaRunLength);
if (newSnlp < (uint32_t)bestSnlp.elementAti(j)) {
bestSnlp.setElementAt(newSnlp, j);
if (newSnlp < (uint32_t)bestSnlp.elementAti(i+katakanaRunLength)) {
bestSnlp.setElementAt(newSnlp, i+katakanaRunLength);
prev.setElementAt(i, i+katakanaRunLength); // prev[j] = i;
}
}
@ -1385,13 +1358,27 @@ CjkBreakEngine::divideUpDictionaryRange( UText *inText,
// Now that we're done, convert positions in t_boundary[] (indices in
// the normalized input string) back to indices in the original input UText
// while reversing t_boundary and pushing values to foundBreaks.
int32_t prevCPPos = -1;
int32_t prevUTextPos = -1;
for (int32_t i = numBreaks-1; i >= 0; i--) {
int32_t cpPos = t_boundary.elementAti(i);
U_ASSERT(cpPos > prevCPPos);
int32_t utextPos = inputMap.isValid() ? inputMap->elementAti(cpPos) : cpPos + rangeStart;
// Boundaries are added to foundBreaks output in ascending order.
U_ASSERT(foundBreaks.size() == 0 ||foundBreaks.peeki() < utextPos);
foundBreaks.push(utextPos, status);
U_ASSERT(utextPos >= prevUTextPos);
if (utextPos > prevUTextPos) {
// Boundaries are added to foundBreaks output in ascending order.
U_ASSERT(foundBreaks.size() == 0 || foundBreaks.peeki() < utextPos);
foundBreaks.push(utextPos, status);
} else {
// Normalization expanded the input text, the dictionary found a boundary
// within the expansion, giving two boundaries with the same index in the
// original text. Ignore the second. See ticket #12918.
--numBreaks;
}
prevCPPos = cpPos;
prevUTextPos = utextPos;
}
(void)prevCPPos; // suppress compiler warnings about unused variable
// inString goes out of scope
// inputMap goes out of scope

55
intl/icu/source/common/dictbe.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/**
*******************************************************************************
@ -15,6 +15,7 @@
#include "unicode/utext.h"
#include "brkeng.h"
#include "uvectr32.h"
U_NAMESPACE_BEGIN
@ -41,27 +42,12 @@ class DictionaryBreakEngine : public LanguageBreakEngine {
UnicodeSet fSet;
/**
* The set of break types handled by this engine
* @internal
*/
uint32_t fTypes;
/**
* <p>Default constructor.</p>
*
*/
DictionaryBreakEngine();
public:
/**
* <p>Constructor setting the break types handled.</p>
*
* @param breakTypes A bitmap of types handled by the engine.
* <p>Constructor </p>
*/
DictionaryBreakEngine( uint32_t breakTypes );
DictionaryBreakEngine();
/**
* <p>Virtual destructor.</p>
@ -73,32 +59,26 @@ class DictionaryBreakEngine : public LanguageBreakEngine {
* a particular kind of break.</p>
*
* @param c A character which begins a run that the engine might handle
* @param breakType The type of text break which the caller wants to determine
* @return TRUE if this engine handles the particular character and break
* type.
*/
virtual UBool handles( UChar32 c, int32_t breakType ) const;
virtual UBool handles(UChar32 c) const;
/**
* <p>Find any breaks within a run in the supplied text.</p>
*
* @param text A UText representing the text. The iterator is left at
* the end of the run of characters which the engine is capable of handling
* that starts from the first (or last) character in the range.
* that starts from the first character in the range.
* @param startPos The start of the run within the supplied text.
* @param endPos The end of the run within the supplied text.
* @param reverse Whether the caller is looking for breaks in a reverse
* direction.
* @param breakType The type of break desired, or -1.
* @param foundBreaks An allocated C array of the breaks found, if any
* @param foundBreaks vector of int32_t to receive the break positions
* @return The number of breaks found.
*/
virtual int32_t findBreaks( UText *text,
int32_t startPos,
int32_t endPos,
UBool reverse,
int32_t breakType,
UStack &foundBreaks ) const;
UVector32 &foundBreaks ) const;
protected:
@ -109,13 +89,6 @@ class DictionaryBreakEngine : public LanguageBreakEngine {
*/
virtual void setCharacters( const UnicodeSet &set );
/**
* <p>Set the break types handled by this engine.</p>
*
* @param breakTypes A bitmap of types handled by the engine.
*/
// virtual void setBreakTypes( uint32_t breakTypes );
/**
* <p>Divide up a range of known dictionary characters handled by this break engine.</p>
*
@ -128,7 +101,7 @@ class DictionaryBreakEngine : public LanguageBreakEngine {
virtual int32_t divideUpDictionaryRange( UText *text,
int32_t rangeStart,
int32_t rangeEnd,
UStack &foundBreaks ) const = 0;
UVector32 &foundBreaks ) const = 0;
};
@ -185,7 +158,7 @@ class ThaiBreakEngine : public DictionaryBreakEngine {
virtual int32_t divideUpDictionaryRange( UText *text,
int32_t rangeStart,
int32_t rangeEnd,
UStack &foundBreaks ) const;
UVector32 &foundBreaks ) const;
};
@ -241,7 +214,7 @@ class LaoBreakEngine : public DictionaryBreakEngine {
virtual int32_t divideUpDictionaryRange( UText *text,
int32_t rangeStart,
int32_t rangeEnd,
UStack &foundBreaks ) const;
UVector32 &foundBreaks ) const;
};
@ -297,7 +270,7 @@ class BurmeseBreakEngine : public DictionaryBreakEngine {
virtual int32_t divideUpDictionaryRange( UText *text,
int32_t rangeStart,
int32_t rangeEnd,
UStack &foundBreaks ) const;
UVector32 &foundBreaks ) const;
};
@ -353,7 +326,7 @@ class KhmerBreakEngine : public DictionaryBreakEngine {
virtual int32_t divideUpDictionaryRange( UText *text,
int32_t rangeStart,
int32_t rangeEnd,
UStack &foundBreaks ) const;
UVector32 &foundBreaks ) const;
};
@ -417,7 +390,7 @@ class CjkBreakEngine : public DictionaryBreakEngine {
virtual int32_t divideUpDictionaryRange( UText *text,
int32_t rangeStart,
int32_t rangeEnd,
UStack &foundBreaks ) const;
UVector32 &foundBreaks ) const;
};

2
intl/icu/source/common/dictionarydata.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************

2
intl/icu/source/common/dictionarydata.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************

2
intl/icu/source/common/dtintrv.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*******************************************************************************
* Copyright (C) 2008, International Business Machines Corporation and

803
intl/icu/source/common/edits.cpp Normal file
View file

@ -0,0 +1,803 @@
// © 2017 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// edits.cpp
// created: 2017feb08 Markus W. Scherer
#include "unicode/edits.h"
#include "unicode/unistr.h"
#include "unicode/utypes.h"
#include "cmemory.h"
#include "uassert.h"
#include "util.h"
U_NAMESPACE_BEGIN
namespace {
// 0000uuuuuuuuuuuu records u+1 unchanged text units.
const int32_t MAX_UNCHANGED_LENGTH = 0x1000;
const int32_t MAX_UNCHANGED = MAX_UNCHANGED_LENGTH - 1;
// 0mmmnnnccccccccc with m=1..6 records ccc+1 replacements of m:n text units.
const int32_t MAX_SHORT_CHANGE_OLD_LENGTH = 6;
const int32_t MAX_SHORT_CHANGE_NEW_LENGTH = 7;
const int32_t SHORT_CHANGE_NUM_MASK = 0x1ff;
const int32_t MAX_SHORT_CHANGE = 0x6fff;
// 0111mmmmmmnnnnnn records a replacement of m text units with n.
// m or n = 61: actual length follows in the next edits array unit.
// m or n = 62..63: actual length follows in the next two edits array units.
// Bit 30 of the actual length is in the head unit.
// Trailing units have bit 15 set.
const int32_t LENGTH_IN_1TRAIL = 61;
const int32_t LENGTH_IN_2TRAIL = 62;
} // namespace
void Edits::releaseArray() U_NOEXCEPT {
if (array != stackArray) {
uprv_free(array);
}
}
Edits &Edits::copyArray(const Edits &other) {
if (U_FAILURE(errorCode_)) {
length = delta = numChanges = 0;
return *this;
}
if (length > capacity) {
uint16_t *newArray = (uint16_t *)uprv_malloc((size_t)length * 2);
if (newArray == nullptr) {
length = delta = numChanges = 0;
errorCode_ = U_MEMORY_ALLOCATION_ERROR;
return *this;
}
releaseArray();
array = newArray;
capacity = length;
}
if (length > 0) {
uprv_memcpy(array, other.array, (size_t)length * 2);
}
return *this;
}
Edits &Edits::moveArray(Edits &src) U_NOEXCEPT {
if (U_FAILURE(errorCode_)) {
length = delta = numChanges = 0;
return *this;
}
releaseArray();
if (length > STACK_CAPACITY) {
array = src.array;
capacity = src.capacity;
src.array = src.stackArray;
src.capacity = STACK_CAPACITY;
src.reset();
return *this;
}
array = stackArray;
capacity = STACK_CAPACITY;
if (length > 0) {
uprv_memcpy(array, src.array, (size_t)length * 2);
}
return *this;
}
Edits &Edits::operator=(const Edits &other) {
length = other.length;
delta = other.delta;
numChanges = other.numChanges;
errorCode_ = other.errorCode_;
return copyArray(other);
}
Edits &Edits::operator=(Edits &&src) U_NOEXCEPT {
length = src.length;
delta = src.delta;
numChanges = src.numChanges;
errorCode_ = src.errorCode_;
return moveArray(src);
}
Edits::~Edits() {
releaseArray();
}
void Edits::reset() U_NOEXCEPT {
length = delta = numChanges = 0;
errorCode_ = U_ZERO_ERROR;
}
void Edits::addUnchanged(int32_t unchangedLength) {
if(U_FAILURE(errorCode_) || unchangedLength == 0) { return; }
if(unchangedLength < 0) {
errorCode_ = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
// Merge into previous unchanged-text record, if any.
int32_t last = lastUnit();
if(last < MAX_UNCHANGED) {
int32_t remaining = MAX_UNCHANGED - last;
if (remaining >= unchangedLength) {
setLastUnit(last + unchangedLength);
return;
}
setLastUnit(MAX_UNCHANGED);
unchangedLength -= remaining;
}
// Split large lengths into multiple units.
while(unchangedLength >= MAX_UNCHANGED_LENGTH) {
append(MAX_UNCHANGED);
unchangedLength -= MAX_UNCHANGED_LENGTH;
}
// Write a small (remaining) length.
if(unchangedLength > 0) {
append(unchangedLength - 1);
}
}
void Edits::addReplace(int32_t oldLength, int32_t newLength) {
if(U_FAILURE(errorCode_)) { return; }
if(oldLength < 0 || newLength < 0) {
errorCode_ = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
if (oldLength == 0 && newLength == 0) {
return;
}
++numChanges;
int32_t newDelta = newLength - oldLength;
if (newDelta != 0) {
if ((newDelta > 0 && delta >= 0 && newDelta > (INT32_MAX - delta)) ||
(newDelta < 0 && delta < 0 && newDelta < (INT32_MIN - delta))) {
// Integer overflow or underflow.
errorCode_ = U_INDEX_OUTOFBOUNDS_ERROR;
return;
}
delta += newDelta;
}
if(0 < oldLength && oldLength <= MAX_SHORT_CHANGE_OLD_LENGTH &&
newLength <= MAX_SHORT_CHANGE_NEW_LENGTH) {
// Merge into previous same-lengths short-replacement record, if any.
int32_t u = (oldLength << 12) | (newLength << 9);
int32_t last = lastUnit();
if(MAX_UNCHANGED < last && last < MAX_SHORT_CHANGE &&
(last & ~SHORT_CHANGE_NUM_MASK) == u &&
(last & SHORT_CHANGE_NUM_MASK) < SHORT_CHANGE_NUM_MASK) {
setLastUnit(last + 1);
return;
}
append(u);
return;
}
int32_t head = 0x7000;
if (oldLength < LENGTH_IN_1TRAIL && newLength < LENGTH_IN_1TRAIL) {
head |= oldLength << 6;
head |= newLength;
append(head);
} else if ((capacity - length) >= 5 || growArray()) {
int32_t limit = length + 1;
if(oldLength < LENGTH_IN_1TRAIL) {
head |= oldLength << 6;
} else if(oldLength <= 0x7fff) {
head |= LENGTH_IN_1TRAIL << 6;
array[limit++] = (uint16_t)(0x8000 | oldLength);
} else {
head |= (LENGTH_IN_2TRAIL + (oldLength >> 30)) << 6;
array[limit++] = (uint16_t)(0x8000 | (oldLength >> 15));
array[limit++] = (uint16_t)(0x8000 | oldLength);
}
if(newLength < LENGTH_IN_1TRAIL) {
head |= newLength;
} else if(newLength <= 0x7fff) {
head |= LENGTH_IN_1TRAIL;
array[limit++] = (uint16_t)(0x8000 | newLength);
} else {
head |= LENGTH_IN_2TRAIL + (newLength >> 30);
array[limit++] = (uint16_t)(0x8000 | (newLength >> 15));
array[limit++] = (uint16_t)(0x8000 | newLength);
}
array[length] = (uint16_t)head;
length = limit;
}
}
void Edits::append(int32_t r) {
if(length < capacity || growArray()) {
array[length++] = (uint16_t)r;
}
}
UBool Edits::growArray() {
int32_t newCapacity;
if (array == stackArray) {
newCapacity = 2000;
} else if (capacity == INT32_MAX) {
// Not U_BUFFER_OVERFLOW_ERROR because that could be confused on a string transform API
// with a result-string-buffer overflow.
errorCode_ = U_INDEX_OUTOFBOUNDS_ERROR;
return FALSE;
} else if (capacity >= (INT32_MAX / 2)) {
newCapacity = INT32_MAX;
} else {
newCapacity = 2 * capacity;
}
// Grow by at least 5 units so that a maximal change record will fit.
if ((newCapacity - capacity) < 5) {
errorCode_ = U_INDEX_OUTOFBOUNDS_ERROR;
return FALSE;
}
uint16_t *newArray = (uint16_t *)uprv_malloc((size_t)newCapacity * 2);
if (newArray == NULL) {
errorCode_ = U_MEMORY_ALLOCATION_ERROR;
return FALSE;
}
uprv_memcpy(newArray, array, (size_t)length * 2);
releaseArray();
array = newArray;
capacity = newCapacity;
return TRUE;
}
UBool Edits::copyErrorTo(UErrorCode &outErrorCode) {
if (U_FAILURE(outErrorCode)) { return TRUE; }
if (U_SUCCESS(errorCode_)) { return FALSE; }
outErrorCode = errorCode_;
return TRUE;
}
Edits &Edits::mergeAndAppend(const Edits &ab, const Edits &bc, UErrorCode &errorCode) {
if (copyErrorTo(errorCode)) { return *this; }
// Picture string a --(Edits ab)--> string b --(Edits bc)--> string c.
// Parallel iteration over both Edits.
Iterator abIter = ab.getFineIterator();
Iterator bcIter = bc.getFineIterator();
UBool abHasNext = TRUE, bcHasNext = TRUE;
// Copy iterator state into local variables, so that we can modify and subdivide spans.
// ab old & new length, bc old & new length
int32_t aLength = 0, ab_bLength = 0, bc_bLength = 0, cLength = 0;
// When we have different-intermediate-length changes, we accumulate a larger change.
int32_t pending_aLength = 0, pending_cLength = 0;
for (;;) {
// At this point, for each of the two iterators:
// Either we are done with the locally cached current edit,
// and its intermediate-string length has been reset,
// or we will continue to work with a truncated remainder of this edit.
//
// If the current edit is done, and the iterator has not yet reached the end,
// then we fetch the next edit. This is true for at least one of the iterators.
//
// Normally it does not matter whether we fetch from ab and then bc or vice versa.
// However, the result is observably different when
// ab deletions meet bc insertions at the same intermediate-string index.
// Some users expect the bc insertions to come first, so we fetch from bc first.
if (bc_bLength == 0) {
if (bcHasNext && (bcHasNext = bcIter.next(errorCode)) != 0) {
bc_bLength = bcIter.oldLength();
cLength = bcIter.newLength();
if (bc_bLength == 0) {
// insertion
if (ab_bLength == 0 || !abIter.hasChange()) {
addReplace(pending_aLength, pending_cLength + cLength);
pending_aLength = pending_cLength = 0;
} else {
pending_cLength += cLength;
}
continue;
}
}
// else see if the other iterator is done, too.
}
if (ab_bLength == 0) {
if (abHasNext && (abHasNext = abIter.next(errorCode)) != 0) {
aLength = abIter.oldLength();
ab_bLength = abIter.newLength();
if (ab_bLength == 0) {
// deletion
if (bc_bLength == bcIter.oldLength() || !bcIter.hasChange()) {
addReplace(pending_aLength + aLength, pending_cLength);
pending_aLength = pending_cLength = 0;
} else {
pending_aLength += aLength;
}
continue;
}
} else if (bc_bLength == 0) {
// Both iterators are done at the same time:
// The intermediate-string lengths match.
break;
} else {
// The ab output string is shorter than the bc input string.
if (!copyErrorTo(errorCode)) {
errorCode = U_ILLEGAL_ARGUMENT_ERROR;
}
return *this;
}
}
if (bc_bLength == 0) {
// The bc input string is shorter than the ab output string.
if (!copyErrorTo(errorCode)) {
errorCode = U_ILLEGAL_ARGUMENT_ERROR;
}
return *this;
}
// Done fetching: ab_bLength > 0 && bc_bLength > 0
// The current state has two parts:
// - Past: We accumulate a longer ac edit in the "pending" variables.
// - Current: We have copies of the current ab/bc edits in local variables.
// At least one side is newly fetched.
// One side might be a truncated remainder of an edit we fetched earlier.
if (!abIter.hasChange() && !bcIter.hasChange()) {
// An unchanged span all the way from string a to string c.
if (pending_aLength != 0 || pending_cLength != 0) {
addReplace(pending_aLength, pending_cLength);
pending_aLength = pending_cLength = 0;
}
int32_t unchangedLength = aLength <= cLength ? aLength : cLength;
addUnchanged(unchangedLength);
ab_bLength = aLength -= unchangedLength;
bc_bLength = cLength -= unchangedLength;
// At least one of the unchanged spans is now empty.
continue;
}
if (!abIter.hasChange() && bcIter.hasChange()) {
// Unchanged a->b but changed b->c.
if (ab_bLength >= bc_bLength) {
// Split the longer unchanged span into change + remainder.
addReplace(pending_aLength + bc_bLength, pending_cLength + cLength);
pending_aLength = pending_cLength = 0;
aLength = ab_bLength -= bc_bLength;
bc_bLength = 0;
continue;
}
// Handle the shorter unchanged span below like a change.
} else if (abIter.hasChange() && !bcIter.hasChange()) {
// Changed a->b and then unchanged b->c.
if (ab_bLength <= bc_bLength) {
// Split the longer unchanged span into change + remainder.
addReplace(pending_aLength + aLength, pending_cLength + ab_bLength);
pending_aLength = pending_cLength = 0;
cLength = bc_bLength -= ab_bLength;
ab_bLength = 0;
continue;
}
// Handle the shorter unchanged span below like a change.
} else { // both abIter.hasChange() && bcIter.hasChange()
if (ab_bLength == bc_bLength) {
// Changes on both sides up to the same position. Emit & reset.
addReplace(pending_aLength + aLength, pending_cLength + cLength);
pending_aLength = pending_cLength = 0;
ab_bLength = bc_bLength = 0;
continue;
}
}
// Accumulate the a->c change, reset the shorter side,
// keep a remainder of the longer one.
pending_aLength += aLength;
pending_cLength += cLength;
if (ab_bLength < bc_bLength) {
bc_bLength -= ab_bLength;
cLength = ab_bLength = 0;
} else { // ab_bLength > bc_bLength
ab_bLength -= bc_bLength;
aLength = bc_bLength = 0;
}
}
if (pending_aLength != 0 || pending_cLength != 0) {
addReplace(pending_aLength, pending_cLength);
}
copyErrorTo(errorCode);
return *this;
}
Edits::Iterator::Iterator(const uint16_t *a, int32_t len, UBool oc, UBool crs) :
array(a), index(0), length(len), remaining(0),
onlyChanges_(oc), coarse(crs),
dir(0), changed(FALSE), oldLength_(0), newLength_(0),
srcIndex(0), replIndex(0), destIndex(0) {}
int32_t Edits::Iterator::readLength(int32_t head) {
if (head < LENGTH_IN_1TRAIL) {
return head;
} else if (head < LENGTH_IN_2TRAIL) {
U_ASSERT(index < length);
U_ASSERT(array[index] >= 0x8000);
return array[index++] & 0x7fff;
} else {
U_ASSERT((index + 2) <= length);
U_ASSERT(array[index] >= 0x8000);
U_ASSERT(array[index + 1] >= 0x8000);
int32_t len = ((head & 1) << 30) |
((int32_t)(array[index] & 0x7fff) << 15) |
(array[index + 1] & 0x7fff);
index += 2;
return len;
}
}
void Edits::Iterator::updateNextIndexes() {
srcIndex += oldLength_;
if (changed) {
replIndex += newLength_;
}
destIndex += newLength_;
}
void Edits::Iterator::updatePreviousIndexes() {
srcIndex -= oldLength_;
if (changed) {
replIndex -= newLength_;
}
destIndex -= newLength_;
}
UBool Edits::Iterator::noNext() {
// No change before or beyond the string.
dir = 0;
changed = FALSE;
oldLength_ = newLength_ = 0;
return FALSE;
}
UBool Edits::Iterator::next(UBool onlyChanges, UErrorCode &errorCode) {
// Forward iteration: Update the string indexes to the limit of the current span,
// and post-increment-read array units to assemble a new span.
// Leaves the array index one after the last unit of that span.
if (U_FAILURE(errorCode)) { return FALSE; }
// We have an errorCode in case we need to start guarding against integer overflows.
// It is also convenient for caller loops if we bail out when an error was set elsewhere.
if (dir > 0) {
updateNextIndexes();
} else {
if (dir < 0) {
// Turn around from previous() to next().
// Post-increment-read the same span again.
if (remaining > 0) {
// Fine-grained iterator:
// Stay on the current one of a sequence of compressed changes.
++index; // next() rests on the index after the sequence unit.
dir = 1;
return TRUE;
}
}
dir = 1;
}
if (remaining >= 1) {
// Fine-grained iterator: Continue a sequence of compressed changes.
if (remaining > 1) {
--remaining;
return TRUE;
}
remaining = 0;
}
if (index >= length) {
return noNext();
}
int32_t u = array[index++];
if (u <= MAX_UNCHANGED) {
// Combine adjacent unchanged ranges.
changed = FALSE;
oldLength_ = u + 1;
while (index < length && (u = array[index]) <= MAX_UNCHANGED) {
++index;
oldLength_ += u + 1;
}
newLength_ = oldLength_;
if (onlyChanges) {
updateNextIndexes();
if (index >= length) {
return noNext();
}
// already fetched u > MAX_UNCHANGED at index
++index;
} else {
return TRUE;
}
}
changed = TRUE;
if (u <= MAX_SHORT_CHANGE) {
int32_t oldLen = u >> 12;
int32_t newLen = (u >> 9) & MAX_SHORT_CHANGE_NEW_LENGTH;
int32_t num = (u & SHORT_CHANGE_NUM_MASK) + 1;
if (coarse) {
oldLength_ = num * oldLen;
newLength_ = num * newLen;
} else {
// Split a sequence of changes that was compressed into one unit.
oldLength_ = oldLen;
newLength_ = newLen;
if (num > 1) {
remaining = num; // This is the first of two or more changes.
}
return TRUE;
}
} else {
U_ASSERT(u <= 0x7fff);
oldLength_ = readLength((u >> 6) & 0x3f);
newLength_ = readLength(u & 0x3f);
if (!coarse) {
return TRUE;
}
}
// Combine adjacent changes.
while (index < length && (u = array[index]) > MAX_UNCHANGED) {
++index;
if (u <= MAX_SHORT_CHANGE) {
int32_t num = (u & SHORT_CHANGE_NUM_MASK) + 1;
oldLength_ += (u >> 12) * num;
newLength_ += ((u >> 9) & MAX_SHORT_CHANGE_NEW_LENGTH) * num;
} else {
U_ASSERT(u <= 0x7fff);
oldLength_ += readLength((u >> 6) & 0x3f);
newLength_ += readLength(u & 0x3f);
}
}
return TRUE;
}
UBool Edits::Iterator::previous(UErrorCode &errorCode) {
// Backward iteration: Pre-decrement-read array units to assemble a new span,
// then update the string indexes to the start of that span.
// Leaves the array index on the head unit of that span.
if (U_FAILURE(errorCode)) { return FALSE; }
// We have an errorCode in case we need to start guarding against integer overflows.
// It is also convenient for caller loops if we bail out when an error was set elsewhere.
if (dir >= 0) {
if (dir > 0) {
// Turn around from next() to previous().
// Set the string indexes to the span limit and
// pre-decrement-read the same span again.
if (remaining > 0) {
// Fine-grained iterator:
// Stay on the current one of a sequence of compressed changes.
--index; // previous() rests on the sequence unit.
dir = -1;
return TRUE;
}
updateNextIndexes();
}
dir = -1;
}
if (remaining > 0) {
// Fine-grained iterator: Continue a sequence of compressed changes.
int32_t u = array[index];
U_ASSERT(MAX_UNCHANGED < u && u <= MAX_SHORT_CHANGE);
if (remaining <= (u & SHORT_CHANGE_NUM_MASK)) {
++remaining;
updatePreviousIndexes();
return TRUE;
}
remaining = 0;
}
if (index <= 0) {
return noNext();
}
int32_t u = array[--index];
if (u <= MAX_UNCHANGED) {
// Combine adjacent unchanged ranges.
changed = FALSE;
oldLength_ = u + 1;
while (index > 0 && (u = array[index - 1]) <= MAX_UNCHANGED) {
--index;
oldLength_ += u + 1;
}
newLength_ = oldLength_;
// No need to handle onlyChanges as long as previous() is called only from findIndex().
updatePreviousIndexes();
return TRUE;
}
changed = TRUE;
if (u <= MAX_SHORT_CHANGE) {
int32_t oldLen = u >> 12;
int32_t newLen = (u >> 9) & MAX_SHORT_CHANGE_NEW_LENGTH;
int32_t num = (u & SHORT_CHANGE_NUM_MASK) + 1;
if (coarse) {
oldLength_ = num * oldLen;
newLength_ = num * newLen;
} else {
// Split a sequence of changes that was compressed into one unit.
oldLength_ = oldLen;
newLength_ = newLen;
if (num > 1) {
remaining = 1; // This is the last of two or more changes.
}
updatePreviousIndexes();
return TRUE;
}
} else {
if (u <= 0x7fff) {
// The change is encoded in u alone.
oldLength_ = readLength((u >> 6) & 0x3f);
newLength_ = readLength(u & 0x3f);
} else {
// Back up to the head of the change, read the lengths,
// and reset the index to the head again.
U_ASSERT(index > 0);
while ((u = array[--index]) > 0x7fff) {}
U_ASSERT(u > MAX_SHORT_CHANGE);
int32_t headIndex = index++;
oldLength_ = readLength((u >> 6) & 0x3f);
newLength_ = readLength(u & 0x3f);
index = headIndex;
}
if (!coarse) {
updatePreviousIndexes();
return TRUE;
}
}
// Combine adjacent changes.
while (index > 0 && (u = array[index - 1]) > MAX_UNCHANGED) {
--index;
if (u <= MAX_SHORT_CHANGE) {
int32_t num = (u & SHORT_CHANGE_NUM_MASK) + 1;
oldLength_ += (u >> 12) * num;
newLength_ += ((u >> 9) & MAX_SHORT_CHANGE_NEW_LENGTH) * num;
} else if (u <= 0x7fff) {
// Read the lengths, and reset the index to the head again.
int32_t headIndex = index++;
oldLength_ += readLength((u >> 6) & 0x3f);
newLength_ += readLength(u & 0x3f);
index = headIndex;
}
}
updatePreviousIndexes();
return TRUE;
}
int32_t Edits::Iterator::findIndex(int32_t i, UBool findSource, UErrorCode &errorCode) {
if (U_FAILURE(errorCode) || i < 0) { return -1; }
int32_t spanStart, spanLength;
if (findSource) { // find source index
spanStart = srcIndex;
spanLength = oldLength_;
} else { // find destination index
spanStart = destIndex;
spanLength = newLength_;
}
if (i < spanStart) {
if (i >= (spanStart / 2)) {
// Search backwards.
for (;;) {
UBool hasPrevious = previous(errorCode);
U_ASSERT(hasPrevious); // because i>=0 and the first span starts at 0
(void)hasPrevious; // avoid unused-variable warning
spanStart = findSource ? srcIndex : destIndex;
if (i >= spanStart) {
// The index is in the current span.
return 0;
}
if (remaining > 0) {
// Is the index in one of the remaining compressed edits?
// spanStart is the start of the current span, first of the remaining ones.
spanLength = findSource ? oldLength_ : newLength_;
int32_t u = array[index];
U_ASSERT(MAX_UNCHANGED < u && u <= MAX_SHORT_CHANGE);
int32_t num = (u & SHORT_CHANGE_NUM_MASK) + 1 - remaining;
int32_t len = num * spanLength;
if (i >= (spanStart - len)) {
int32_t n = ((spanStart - i - 1) / spanLength) + 1;
// 1 <= n <= num
srcIndex -= n * oldLength_;
replIndex -= n * newLength_;
destIndex -= n * newLength_;
remaining += n;
return 0;
}
// Skip all of these edits at once.
srcIndex -= num * oldLength_;
replIndex -= num * newLength_;
destIndex -= num * newLength_;
remaining = 0;
}
}
}
// Reset the iterator to the start.
dir = 0;
index = remaining = oldLength_ = newLength_ = srcIndex = replIndex = destIndex = 0;
} else if (i < (spanStart + spanLength)) {
// The index is in the current span.
return 0;
}
while (next(FALSE, errorCode)) {
if (findSource) {
spanStart = srcIndex;
spanLength = oldLength_;
} else {
spanStart = destIndex;
spanLength = newLength_;
}
if (i < (spanStart + spanLength)) {
// The index is in the current span.
return 0;
}
if (remaining > 1) {
// Is the index in one of the remaining compressed edits?
// spanStart is the start of the current span, first of the remaining ones.
int32_t len = remaining * spanLength;
if (i < (spanStart + len)) {
int32_t n = (i - spanStart) / spanLength; // 1 <= n <= remaining - 1
srcIndex += n * oldLength_;
replIndex += n * newLength_;
destIndex += n * newLength_;
remaining -= n;
return 0;
}
// Make next() skip all of these edits at once.
oldLength_ *= remaining;
newLength_ *= remaining;
remaining = 0;
}
}
return 1;
}
int32_t Edits::Iterator::destinationIndexFromSourceIndex(int32_t i, UErrorCode &errorCode) {
int32_t where = findIndex(i, TRUE, errorCode);
if (where < 0) {
// Error or before the string.
return 0;
}
if (where > 0 || i == srcIndex) {
// At or after string length, or at start of the found span.
return destIndex;
}
if (changed) {
// In a change span, map to its end.
return destIndex + newLength_;
} else {
// In an unchanged span, offset 1:1 within it.
return destIndex + (i - srcIndex);
}
}
int32_t Edits::Iterator::sourceIndexFromDestinationIndex(int32_t i, UErrorCode &errorCode) {
int32_t where = findIndex(i, FALSE, errorCode);
if (where < 0) {
// Error or before the string.
return 0;
}
if (where > 0 || i == destIndex) {
// At or after string length, or at start of the found span.
return srcIndex;
}
if (changed) {
// In a change span, map to its end.
return srcIndex + oldLength_;
} else {
// In an unchanged span, offset within it.
return srcIndex + (i - destIndex);
}
}
UnicodeString& Edits::Iterator::toString(UnicodeString& sb) const {
sb.append(u"{ src[", -1);
ICU_Utility::appendNumber(sb, srcIndex);
sb.append(u"..", -1);
ICU_Utility::appendNumber(sb, srcIndex + oldLength_);
if (changed) {
sb.append(u"] ⇝ dest[", -1);
} else {
sb.append(u"] ≡ dest[", -1);
}
ICU_Utility::appendNumber(sb, destIndex);
sb.append(u"..", -1);
ICU_Utility::appendNumber(sb, destIndex + newLength_);
if (changed) {
sb.append(u"], repl[", -1);
ICU_Utility::appendNumber(sb, replIndex);
sb.append(u"..", -1);
ICU_Utility::appendNumber(sb, replIndex + newLength_);
sb.append(u"] }", -1);
} else {
sb.append(u"] (no-change) }", -1);
}
return sb;
}
U_NAMESPACE_END

4
intl/icu/source/common/errorcode.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -8,7 +8,7 @@
*
*******************************************************************************
* file name: errorcode.cpp
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*

11
intl/icu/source/common/filteredbrk.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -694,7 +694,12 @@ FilteredBreakIteratorBuilder::createInstance(const Locale& where, UErrorCode& st
}
FilteredBreakIteratorBuilder *
FilteredBreakIteratorBuilder::createInstance(UErrorCode& status) {
FilteredBreakIteratorBuilder::createInstance(UErrorCode &status) {
return createEmptyInstance(status);
}
FilteredBreakIteratorBuilder *
FilteredBreakIteratorBuilder::createEmptyInstance(UErrorCode& status) {
if(U_FAILURE(status)) return NULL;
LocalPointer<FilteredBreakIteratorBuilder> ret(new SimpleFilteredBreakIteratorBuilder(status), status);
return (U_SUCCESS(status))? ret.orphan(): NULL;
@ -702,4 +707,4 @@ FilteredBreakIteratorBuilder::createInstance(UErrorCode& status) {
U_NAMESPACE_END
#endif //#if !UCONFIG_NO_BREAK_ITERATION && U_HAVE_STD_STRING && !UCONFIG_NO_FILTERED_BREAK_ITERATION
#endif //#if !UCONFIG_NO_BREAK_ITERATION && !UCONFIG_NO_FILTERED_BREAK_ITERATION

77
intl/icu/source/common/filterednormalizer2.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -8,7 +8,7 @@
*
*******************************************************************************
* file name: filterednormalizer2.cpp
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
@ -20,7 +20,9 @@
#if !UCONFIG_NO_NORMALIZATION
#include "unicode/edits.h"
#include "unicode/normalizer2.h"
#include "unicode/stringoptions.h"
#include "unicode/uniset.h"
#include "unicode/unistr.h"
#include "unicode/unorm.h"
@ -85,6 +87,52 @@ FilteredNormalizer2::normalize(const UnicodeString &src,
return dest;
}
void
FilteredNormalizer2::normalizeUTF8(uint32_t options, StringPiece src, ByteSink &sink,
Edits *edits, UErrorCode &errorCode) const {
if (U_FAILURE(errorCode)) {
return;
}
if (edits != nullptr && (options & U_EDITS_NO_RESET) == 0) {
edits->reset();
}
options |= U_EDITS_NO_RESET; // Do not reset for each span.
normalizeUTF8(options, src.data(), src.length(), sink, edits, USET_SPAN_SIMPLE, errorCode);
}
void
FilteredNormalizer2::normalizeUTF8(uint32_t options, const char *src, int32_t length,
ByteSink &sink, Edits *edits,
USetSpanCondition spanCondition,
UErrorCode &errorCode) const {
while (length > 0) {
int32_t spanLength = set.spanUTF8(src, length, spanCondition);
if (spanCondition == USET_SPAN_NOT_CONTAINED) {
if (spanLength != 0) {
if (edits != nullptr) {
edits->addUnchanged(spanLength);
}
if ((options & U_OMIT_UNCHANGED_TEXT) == 0) {
sink.Append(src, spanLength);
}
}
spanCondition = USET_SPAN_SIMPLE;
} else {
if (spanLength != 0) {
// Not norm2.normalizeSecondAndAppend() because we do not want
// to modify the non-filter part of dest.
norm2.normalizeUTF8(options, StringPiece(src, spanLength), sink, edits, errorCode);
if (U_FAILURE(errorCode)) {
break;
}
}
spanCondition = USET_SPAN_NOT_CONTAINED;
}
src += spanLength;
length -= spanLength;
}
}
UnicodeString &
FilteredNormalizer2::normalizeSecondAndAppend(UnicodeString &first,
const UnicodeString &second,
@ -196,6 +244,31 @@ FilteredNormalizer2::isNormalized(const UnicodeString &s, UErrorCode &errorCode)
return TRUE;
}
UBool
FilteredNormalizer2::isNormalizedUTF8(StringPiece sp, UErrorCode &errorCode) const {
if(U_FAILURE(errorCode)) {
return FALSE;
}
const char *s = sp.data();
int32_t length = sp.length();
USetSpanCondition spanCondition = USET_SPAN_SIMPLE;
while (length > 0) {
int32_t spanLength = set.spanUTF8(s, length, spanCondition);
if (spanCondition == USET_SPAN_NOT_CONTAINED) {
spanCondition = USET_SPAN_SIMPLE;
} else {
if (!norm2.isNormalizedUTF8(StringPiece(s, spanLength), errorCode) ||
U_FAILURE(errorCode)) {
return FALSE;
}
spanCondition = USET_SPAN_NOT_CONTAINED;
}
s += spanLength;
length -= spanLength;
}
return TRUE;
}
UNormalizationCheckResult
FilteredNormalizer2::quickCheck(const UnicodeString &s, UErrorCode &errorCode) const {
uprv_checkCanGetBuffer(s, errorCode);

50
intl/icu/source/common/hash.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
@ -33,6 +33,8 @@ class U_COMMON_API Hashtable : public UMemory {
inline void init(UHashFunction *keyHash, UKeyComparator *keyComp, UValueComparator *valueComp, UErrorCode& status);
inline void initSize(UHashFunction *keyHash, UKeyComparator *keyComp, UValueComparator *valueComp, int32_t size, UErrorCode& status);
public:
/**
* Construct a hashtable
@ -41,6 +43,14 @@ public:
*/
Hashtable(UBool ignoreKeyCase, UErrorCode& status);
/**
* Construct a hashtable
* @param ignoreKeyCase If true, keys are case insensitive.
* @param size initial size allocation
* @param status Error code
*/
Hashtable(UBool ignoreKeyCase, int32_t size, UErrorCode& status);
/**
* Construct a hashtable
* @param keyComp Comparator for comparing the keys
@ -76,9 +86,9 @@ public:
int32_t puti(const UnicodeString& key, int32_t value, UErrorCode& status);
void* get(const UnicodeString& key) const;
int32_t geti(const UnicodeString& key) const;
void* remove(const UnicodeString& key);
int32_t removei(const UnicodeString& key);
@ -92,9 +102,9 @@ public:
* @see uhash_nextElement
*/
const UHashElement* nextElement(int32_t& pos) const;
UKeyComparator* setKeyComparator(UKeyComparator*keyComp);
UValueComparator* setValueComparator(UValueComparator* valueComp);
UBool equals(const Hashtable& that) const;
@ -107,7 +117,7 @@ private:
* Implementation
********************************************************************/
inline void Hashtable::init(UHashFunction *keyHash, UKeyComparator *keyComp,
inline void Hashtable::init(UHashFunction *keyHash, UKeyComparator *keyComp,
UValueComparator *valueComp, UErrorCode& status) {
if (U_FAILURE(status)) {
return;
@ -119,10 +129,23 @@ inline void Hashtable::init(UHashFunction *keyHash, UKeyComparator *keyComp,
}
}
inline Hashtable::Hashtable(UKeyComparator *keyComp, UValueComparator *valueComp,
inline void Hashtable::initSize(UHashFunction *keyHash, UKeyComparator *keyComp,
UValueComparator *valueComp, int32_t size, UErrorCode& status) {
if (U_FAILURE(status)) {
return;
}
uhash_initSize(&hashObj, keyHash, keyComp, valueComp, size, &status);
if (U_SUCCESS(status)) {
hash = &hashObj;
uhash_setKeyDeleter(hash, uprv_deleteUObject);
}
}
inline Hashtable::Hashtable(UKeyComparator *keyComp, UValueComparator *valueComp,
UErrorCode& status) : hash(0) {
init( uhash_hashUnicodeString, keyComp, valueComp, status);
}
inline Hashtable::Hashtable(UBool ignoreKeyCase, UErrorCode& status)
: hash(0)
{
@ -134,6 +157,17 @@ inline Hashtable::Hashtable(UBool ignoreKeyCase, UErrorCode& status)
status);
}
inline Hashtable::Hashtable(UBool ignoreKeyCase, int32_t size, UErrorCode& status)
: hash(0)
{
initSize(ignoreKeyCase ? uhash_hashCaselessUnicodeString
: uhash_hashUnicodeString,
ignoreKeyCase ? uhash_compareCaselessUnicodeString
: uhash_compareUnicodeString,
NULL, size,
status);
}
inline Hashtable::Hashtable(UErrorCode& status)
: hash(0)
{
@ -200,7 +234,7 @@ inline void Hashtable::removeAll(void) {
inline UKeyComparator* Hashtable::setKeyComparator(UKeyComparator*keyComp){
return uhash_setKeyComparator(hash, keyComp);
}
inline UValueComparator* Hashtable::setValueComparator(UValueComparator* valueComp){
return uhash_setValueComparator(hash, valueComp);
}

2
intl/icu/source/common/icudataver.c → intl/icu/source/common/icudataver.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************

2
intl/icu/source/common/icuplug.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************

2
intl/icu/source/common/icuplugimp.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************

88
intl/icu/source/common/loadednormalizer2impl.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -18,6 +18,7 @@
#include "unicode/udata.h"
#include "unicode/localpointer.h"
#include "unicode/normalizer2.h"
#include "unicode/ucptrie.h"
#include "unicode/unistr.h"
#include "unicode/unorm.h"
#include "cstring.h"
@ -42,12 +43,12 @@ private:
isAcceptable(void *context, const char *type, const char *name, const UDataInfo *pInfo);
UDataMemory *memory;
UTrie2 *ownedTrie;
UCPTrie *ownedTrie;
};
LoadedNormalizer2Impl::~LoadedNormalizer2Impl() {
udata_close(memory);
utrie2_close(ownedTrie);
ucptrie_close(ownedTrie);
}
UBool U_CALLCONV
@ -62,7 +63,7 @@ LoadedNormalizer2Impl::isAcceptable(void * /*context*/,
pInfo->dataFormat[1]==0x72 &&
pInfo->dataFormat[2]==0x6d &&
pInfo->dataFormat[3]==0x32 &&
pInfo->formatVersion[0]==2
pInfo->formatVersion[0]==4
) {
// Normalizer2Impl *me=(Normalizer2Impl *)context;
// uprv_memcpy(me->dataVersion, pInfo->dataVersion, 4);
@ -84,16 +85,16 @@ LoadedNormalizer2Impl::load(const char *packageName, const char *name, UErrorCod
const uint8_t *inBytes=(const uint8_t *)udata_getMemory(memory);
const int32_t *inIndexes=(const int32_t *)inBytes;
int32_t indexesLength=inIndexes[IX_NORM_TRIE_OFFSET]/4;
if(indexesLength<=IX_MIN_MAYBE_YES) {
if(indexesLength<=IX_MIN_LCCC_CP) {
errorCode=U_INVALID_FORMAT_ERROR; // Not enough indexes.
return;
}
int32_t offset=inIndexes[IX_NORM_TRIE_OFFSET];
int32_t nextOffset=inIndexes[IX_EXTRA_DATA_OFFSET];
ownedTrie=utrie2_openFromSerialized(UTRIE2_16_VALUE_BITS,
inBytes+offset, nextOffset-offset, NULL,
&errorCode);
ownedTrie=ucptrie_openFromBinary(UCPTRIE_TYPE_FAST, UCPTRIE_VALUE_BITS_16,
inBytes+offset, nextOffset-offset, NULL,
&errorCode);
if(U_FAILURE(errorCode)) {
return;
}
@ -131,15 +132,26 @@ U_CDECL_BEGIN
static UBool U_CALLCONV uprv_loaded_normalizer2_cleanup();
U_CDECL_END
static Norm2AllModes *nfkcSingleton;
static Norm2AllModes *nfkc_cfSingleton;
static UHashtable *cache=NULL;
#if !NORM2_HARDCODE_NFC_DATA
static Norm2AllModes *nfcSingleton;
static icu::UInitOnce nfcInitOnce = U_INITONCE_INITIALIZER;
#endif
static Norm2AllModes *nfkcSingleton;
static icu::UInitOnce nfkcInitOnce = U_INITONCE_INITIALIZER;
static Norm2AllModes *nfkc_cfSingleton;
static icu::UInitOnce nfkc_cfInitOnce = U_INITONCE_INITIALIZER;
static UHashtable *cache=NULL;
// UInitOnce singleton initialization function
static void U_CALLCONV initSingletons(const char *what, UErrorCode &errorCode) {
#if !NORM2_HARDCODE_NFC_DATA
if (uprv_strcmp(what, "nfc") == 0) {
nfcSingleton = Norm2AllModes::createInstance(NULL, "nfc", errorCode);
} else
#endif
if (uprv_strcmp(what, "nfkc") == 0) {
nfkcSingleton = Norm2AllModes::createInstance(NULL, "nfkc", errorCode);
} else if (uprv_strcmp(what, "nfkc_cf") == 0) {
@ -157,19 +169,36 @@ static void U_CALLCONV deleteNorm2AllModes(void *allModes) {
}
static UBool U_CALLCONV uprv_loaded_normalizer2_cleanup() {
#if !NORM2_HARDCODE_NFC_DATA
delete nfcSingleton;
nfcSingleton = NULL;
nfcInitOnce.reset();
#endif
delete nfkcSingleton;
nfkcSingleton = NULL;
nfkcInitOnce.reset();
delete nfkc_cfSingleton;
nfkc_cfSingleton = NULL;
nfkc_cfInitOnce.reset();
uhash_close(cache);
cache=NULL;
nfkcInitOnce.reset();
nfkc_cfInitOnce.reset();
return TRUE;
}
U_CDECL_END
#if !NORM2_HARDCODE_NFC_DATA
const Norm2AllModes *
Norm2AllModes::getNFCInstance(UErrorCode &errorCode) {
if(U_FAILURE(errorCode)) { return NULL; }
umtx_initOnce(nfcInitOnce, &initSingletons, "nfc", errorCode);
return nfcSingleton;
}
#endif
const Norm2AllModes *
Norm2AllModes::getNFKCInstance(UErrorCode &errorCode) {
if(U_FAILURE(errorCode)) { return NULL; }
@ -184,6 +213,36 @@ Norm2AllModes::getNFKC_CFInstance(UErrorCode &errorCode) {
return nfkc_cfSingleton;
}
#if !NORM2_HARDCODE_NFC_DATA
const Normalizer2 *
Normalizer2::getNFCInstance(UErrorCode &errorCode) {
const Norm2AllModes *allModes=Norm2AllModes::getNFCInstance(errorCode);
return allModes!=NULL ? &allModes->comp : NULL;
}
const Normalizer2 *
Normalizer2::getNFDInstance(UErrorCode &errorCode) {
const Norm2AllModes *allModes=Norm2AllModes::getNFCInstance(errorCode);
return allModes!=NULL ? &allModes->decomp : NULL;
}
const Normalizer2 *Normalizer2Factory::getFCDInstance(UErrorCode &errorCode) {
const Norm2AllModes *allModes=Norm2AllModes::getNFCInstance(errorCode);
return allModes!=NULL ? &allModes->fcd : NULL;
}
const Normalizer2 *Normalizer2Factory::getFCCInstance(UErrorCode &errorCode) {
const Norm2AllModes *allModes=Norm2AllModes::getNFCInstance(errorCode);
return allModes!=NULL ? &allModes->fcc : NULL;
}
const Normalizer2Impl *
Normalizer2Factory::getNFCImpl(UErrorCode &errorCode) {
const Norm2AllModes *allModes=Norm2AllModes::getNFCInstance(errorCode);
return allModes!=NULL ? allModes->impl : NULL;
}
#endif
const Normalizer2 *
Normalizer2::getNFKCInstance(UErrorCode &errorCode) {
const Norm2AllModes *allModes=Norm2AllModes::getNFKCInstance(errorCode);
@ -232,6 +291,7 @@ Normalizer2::getInstance(const char *packageName,
}
}
if(allModes==NULL) {
ucln_common_registerCleanup(UCLN_COMMON_LOADED_NORMALIZER2, uprv_loaded_normalizer2_cleanup);
LocalPointer<Norm2AllModes> localAllModes(
Norm2AllModes::createInstance(packageName, name, errorCode));
if(U_SUCCESS(errorCode)) {
@ -246,7 +306,7 @@ Normalizer2::getInstance(const char *packageName,
}
void *temp=uhash_get(cache, name);
if(temp==NULL) {
int32_t keyLength=uprv_strlen(name)+1;
int32_t keyLength= static_cast<int32_t>(uprv_strlen(name)+1);
char *nameCopy=(char *)uprv_malloc(keyLength);
if(nameCopy==NULL) {
errorCode=U_MEMORY_ALLOCATION_ERROR;

2
intl/icu/source/common/localsvc.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
***************************************************************************

10
intl/icu/source/common/locavailable.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -8,7 +8,7 @@
*
*******************************************************************************
* file name: locavailable.cpp
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
@ -35,7 +35,7 @@ U_NAMESPACE_BEGIN
static icu::Locale* availableLocaleList = NULL;
static int32_t availableLocaleListCount;
static icu::UInitOnce gInitOnce = U_INITONCE_INITIALIZER;
static icu::UInitOnce gInitOnceLocale = U_INITONCE_INITIALIZER;
U_NAMESPACE_END
@ -50,7 +50,7 @@ static UBool U_CALLCONV locale_available_cleanup(void)
availableLocaleList = NULL;
}
availableLocaleListCount = 0;
gInitOnce.reset();
gInitOnceLocale.reset();
return TRUE;
}
@ -81,7 +81,7 @@ void U_CALLCONV locale_available_init() {
const Locale* U_EXPORT2
Locale::getAvailableLocales(int32_t& count)
{
umtx_initOnce(gInitOnce, &locale_available_init);
umtx_initOnce(gInitOnceLocale, &locale_available_init);
count = availableLocaleListCount;
return availableLocaleList;
}

2
intl/icu/source/common/locbased.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************

2
intl/icu/source/common/locbased.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************

12
intl/icu/source/common/locdispnames.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -8,7 +8,7 @@
*
*******************************************************************************
* file name: locdispnames.cpp
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
@ -542,7 +542,7 @@ uloc_getDisplayName(const char *locale,
return 0;
}
separator = (const UChar *)p0 + subLen;
sepLen = p1 - separator;
sepLen = static_cast<int32_t>(p1 - separator);
}
if(patLen==0 || (patLen==defaultPatLen && !u_strncmp(pattern, defaultPattern, patLen))) {
@ -558,8 +558,8 @@ uloc_getDisplayName(const char *locale,
*pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
return 0;
}
sub0Pos=p0-pattern;
sub1Pos=p1-pattern;
sub0Pos = static_cast<int32_t>(p0-pattern);
sub1Pos = static_cast<int32_t>(p1-pattern);
if (sub1Pos < sub0Pos) { /* a very odd pattern */
int32_t t=sub0Pos; sub0Pos=sub1Pos; sub1Pos=t;
langi=1;
@ -821,6 +821,8 @@ uloc_getDisplayKeywordValue( const char* locale,
/* get the keyword value */
keywordValue[0]=0;
keywordValueLen = uloc_getKeywordValue(locale, keyword, keywordValue, capacity, status);
if (*status == U_STRING_NOT_TERMINATED_WARNING)
*status = U_BUFFER_OVERFLOW_ERROR;
/*
* if the keyword is equal to currency .. then to get the display name

30
intl/icu/source/common/locdspnm.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -13,6 +13,7 @@
#include "unicode/locdspnm.h"
#include "unicode/simpleformatter.h"
#include "unicode/ucasemap.h"
#include "unicode/ures.h"
#include "unicode/udisplaycontext.h"
#include "unicode/brkiter.h"
@ -44,16 +45,16 @@ static int32_t ncat(char *buffer, uint32_t buflen, ...) {
}
va_start(args, buflen);
while ((str = va_arg(args, char *))) {
while ((str = va_arg(args, char *)) != 0) {
char c;
while (p != e && (c = *str++)) {
while (p != e && (c = *str++) != 0) {
*p++ = c;
}
}
*p = 0;
va_end(args);
return p - buffer;
return static_cast<int32_t>(p - buffer);
}
U_NAMESPACE_BEGIN
@ -97,7 +98,7 @@ ICUDataTable::ICUDataTable(const char* path, const Locale& locale)
: path(NULL), locale(Locale::getRoot())
{
if (path) {
int32_t len = uprv_strlen(path);
int32_t len = static_cast<int32_t>(uprv_strlen(path));
this->path = (const char*) uprv_malloc(len + 1);
if (this->path) {
uprv_strcpy((char *)this->path, path);
@ -559,21 +560,21 @@ LocaleDisplayNamesImpl::adjustForUsageAndContext(CapContextUsage usage,
}
UnicodeString&
LocaleDisplayNamesImpl::localeDisplayName(const Locale& locale,
LocaleDisplayNamesImpl::localeDisplayName(const Locale& loc,
UnicodeString& result) const {
if (locale.isBogus()) {
if (loc.isBogus()) {
result.setToBogus();
return result;
}
UnicodeString resultName;
const char* lang = locale.getLanguage();
const char* lang = loc.getLanguage();
if (uprv_strlen(lang) == 0) {
lang = "root";
}
const char* script = locale.getScript();
const char* country = locale.getCountry();
const char* variant = locale.getVariant();
const char* script = loc.getScript();
const char* country = loc.getCountry();
const char* variant = loc.getVariant();
UBool hasScript = uprv_strlen(script) > 0;
UBool hasCountry = uprv_strlen(country) > 0;
@ -629,14 +630,15 @@ LocaleDisplayNamesImpl::localeDisplayName(const Locale& locale,
resultRemainder.findAndReplace(formatOpenParen, formatReplaceOpenParen);
resultRemainder.findAndReplace(formatCloseParen, formatReplaceCloseParen);
LocalPointer<StringEnumeration> e(locale.createKeywords(status));
LocalPointer<StringEnumeration> e(loc.createKeywords(status));
if (e.isValid() && U_SUCCESS(status)) {
UnicodeString temp2;
char value[ULOC_KEYWORD_AND_VALUES_CAPACITY]; // sigh, no ULOC_VALUE_CAPACITY
const char* key;
while ((key = e->next((int32_t *)0, status)) != NULL) {
locale.getKeywordValue(key, value, ULOC_KEYWORD_AND_VALUES_CAPACITY, status);
if (U_FAILURE(status)) {
value[0] = 0;
loc.getKeywordValue(key, value, ULOC_KEYWORD_AND_VALUES_CAPACITY, status);
if (U_FAILURE(status) || status == U_STRING_NOT_TERMINATED_WARNING) {
return result;
}
keyDisplayName(key, temp, TRUE);

564
intl/icu/source/common/locid.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
@ -31,8 +31,12 @@
******************************************************************************
*/
#include <utility>
#include "unicode/bytestream.h"
#include "unicode/locid.h"
#include "unicode/strenum.h"
#include "unicode/stringpiece.h"
#include "unicode/uloc.h"
#include "putilimp.h"
#include "mutex.h"
@ -42,9 +46,11 @@
#include "cstring.h"
#include "uassert.h"
#include "uhash.h"
#include "ulocimp.h"
#include "ucln_cmn.h"
#include "ustr_imp.h"
#include "charstr.h"
#include "bytesinkutil.h"
U_CDECL_BEGIN
static UBool U_CALLCONV locale_cleanup(void);
@ -423,49 +429,70 @@ Locale::Locale(const Locale &other)
*this = other;
}
Locale &Locale::operator=(const Locale &other)
{
Locale::Locale(Locale&& other) U_NOEXCEPT
: UObject(other), fullName(fullNameBuffer), baseName(fullName) {
*this = std::move(other);
}
Locale& Locale::operator=(const Locale& other) {
if (this == &other) {
return *this;
}
/* Free our current storage */
if (baseName != fullName) {
uprv_free(baseName);
}
baseName = NULL;
if(fullName != fullNameBuffer) {
uprv_free(fullName);
fullName = fullNameBuffer;
setToBogus();
if (other.fullName == other.fullNameBuffer) {
uprv_strcpy(fullNameBuffer, other.fullNameBuffer);
} else if (other.fullName == nullptr) {
fullName = nullptr;
} else {
fullName = uprv_strdup(other.fullName);
if (fullName == nullptr) return *this;
}
/* Allocate the full name if necessary */
if(other.fullName != other.fullNameBuffer) {
fullName = (char *)uprv_malloc(sizeof(char)*(uprv_strlen(other.fullName)+1));
if (fullName == NULL) {
return *this;
}
}
/* Copy the full name */
uprv_strcpy(fullName, other.fullName);
/* Copy the baseName if it differs from fullName. */
if (other.baseName == other.fullName) {
baseName = fullName;
} else {
if (other.baseName) {
baseName = uprv_strdup(other.baseName);
}
} else if (other.baseName != nullptr) {
baseName = uprv_strdup(other.baseName);
if (baseName == nullptr) return *this;
}
/* Copy the language and country fields */
uprv_strcpy(language, other.language);
uprv_strcpy(script, other.script);
uprv_strcpy(country, other.country);
/* The variantBegin is an offset, just copy it */
variantBegin = other.variantBegin;
fIsBogus = other.fIsBogus;
return *this;
}
Locale& Locale::operator=(Locale&& other) U_NOEXCEPT {
if (baseName != fullName) uprv_free(baseName);
if (fullName != fullNameBuffer) uprv_free(fullName);
if (other.fullName == other.fullNameBuffer) {
uprv_strcpy(fullNameBuffer, other.fullNameBuffer);
fullName = fullNameBuffer;
} else {
fullName = other.fullName;
}
if (other.baseName == other.fullName) {
baseName = fullName;
} else {
baseName = other.baseName;
}
uprv_strcpy(language, other.language);
uprv_strcpy(script, other.script);
uprv_strcpy(country, other.country);
variantBegin = other.variantBegin;
fIsBogus = other.fIsBogus;
other.baseName = other.fullName = other.fullNameBuffer;
return *this;
}
@ -544,7 +571,7 @@ Locale& Locale::init(const char* localeID, UBool canonicalize)
/* after uloc_getName/canonicalize() we know that only '_' are separators */
separator = field[0] = fullName;
fieldIdx = 1;
while ((separator = uprv_strchr(field[fieldIdx-1], SEP_CHAR)) && fieldIdx < UPRV_LENGTHOF(field)-1) {
while ((separator = uprv_strchr(field[fieldIdx-1], SEP_CHAR)) != 0 && fieldIdx < UPRV_LENGTHOF(field)-1) {
field[fieldIdx] = separator + 1;
fieldLen[fieldIdx-1] = (int32_t)(separator - field[fieldIdx-1]);
fieldIdx++;
@ -651,7 +678,7 @@ Locale::initBaseName(UErrorCode &status) {
int32_t
Locale::hashCode() const
{
return ustr_hashCharsN(fullName, uprv_strlen(fullName));
return ustr_hashCharsN(fullName, static_cast<int32_t>(uprv_strlen(fullName)));
}
void
@ -703,6 +730,276 @@ Locale::setDefault( const Locale& newLocale,
locale_set_default_internal(localeID, status);
}
void
Locale::addLikelySubtags(UErrorCode& status) {
if (U_FAILURE(status)) {
return;
}
// The maximized locale ID string is often longer, but there is no good
// heuristic to estimate just how much longer. Leave that to CharString.
CharString maximizedLocaleID;
int32_t maximizedLocaleIDCapacity = static_cast<int32_t>(uprv_strlen(fullName));
char* buffer;
int32_t reslen;
for (;;) {
buffer = maximizedLocaleID.getAppendBuffer(
/*minCapacity=*/maximizedLocaleIDCapacity,
/*desiredCapacityHint=*/maximizedLocaleIDCapacity,
maximizedLocaleIDCapacity,
status);
if (U_FAILURE(status)) {
return;
}
reslen = uloc_addLikelySubtags(
fullName,
buffer,
maximizedLocaleIDCapacity,
&status);
if (status != U_BUFFER_OVERFLOW_ERROR) {
break;
}
maximizedLocaleIDCapacity = reslen;
status = U_ZERO_ERROR;
}
if (U_FAILURE(status)) {
return;
}
maximizedLocaleID.append(buffer, reslen, status);
if (status == U_STRING_NOT_TERMINATED_WARNING) {
status = U_ZERO_ERROR; // Terminators provided by CharString.
}
if (U_FAILURE(status)) {
return;
}
init(maximizedLocaleID.data(), /*canonicalize=*/FALSE);
if (isBogus()) {
status = U_ILLEGAL_ARGUMENT_ERROR;
}
}
void
Locale::minimizeSubtags(UErrorCode& status) {
if (U_FAILURE(status)) {
return;
}
// Except for a few edge cases (like the empty string, that is minimized to
// "en__POSIX"), minimized locale ID strings will be either the same length
// or shorter than their input.
CharString minimizedLocaleID;
int32_t minimizedLocaleIDCapacity = static_cast<int32_t>(uprv_strlen(fullName));
char* buffer;
int32_t reslen;
for (;;) {
buffer = minimizedLocaleID.getAppendBuffer(
/*minCapacity=*/minimizedLocaleIDCapacity,
/*desiredCapacityHint=*/minimizedLocaleIDCapacity,
minimizedLocaleIDCapacity,
status);
if (U_FAILURE(status)) {
return;
}
reslen = uloc_minimizeSubtags(
fullName,
buffer,
minimizedLocaleIDCapacity,
&status);
if (status != U_BUFFER_OVERFLOW_ERROR) {
break;
}
// Because of the internal minimal buffer size of CharString, I can't
// think of any input data for which this could possibly ever happen.
// Maybe it would be better replaced with an assertion instead?
minimizedLocaleIDCapacity = reslen;
status = U_ZERO_ERROR;
}
if (U_FAILURE(status)) {
return;
}
minimizedLocaleID.append(buffer, reslen, status);
if (status == U_STRING_NOT_TERMINATED_WARNING) {
status = U_ZERO_ERROR; // Terminators provided by CharString.
}
if (U_FAILURE(status)) {
return;
}
init(minimizedLocaleID.data(), /*canonicalize=*/FALSE);
if (isBogus()) {
status = U_ILLEGAL_ARGUMENT_ERROR;
}
}
Locale U_EXPORT2
Locale::forLanguageTag(StringPiece tag, UErrorCode& status)
{
Locale result(Locale::eBOGUS);
if (U_FAILURE(status)) {
return result;
}
// If a BCP-47 language tag is passed as the language parameter to the
// normal Locale constructor, it will actually fall back to invoking
// uloc_forLanguageTag() to parse it if it somehow is able to detect that
// the string actually is BCP-47. This works well for things like strings
// using BCP-47 extensions, but it does not at all work for things like
// BCP-47 grandfathered tags (eg. "en-GB-oed") which are possible to also
// interpret as ICU locale IDs and because of that won't trigger the BCP-47
// parsing. Therefore the code here explicitly calls uloc_forLanguageTag()
// and then Locale::init(), instead of just calling the normal constructor.
// All simple language tags will have the exact same length as ICU locale
// ID strings as they have as BCP-47 strings (like "en_US" for "en-US").
CharString localeID;
int32_t resultCapacity = tag.size();
char* buffer;
int32_t parsedLength, reslen;
for (;;) {
buffer = localeID.getAppendBuffer(
/*minCapacity=*/resultCapacity,
/*desiredCapacityHint=*/resultCapacity,
resultCapacity,
status);
if (U_FAILURE(status)) {
return result;
}
reslen = ulocimp_forLanguageTag(
tag.data(),
tag.length(),
buffer,
resultCapacity,
&parsedLength,
&status);
if (status != U_BUFFER_OVERFLOW_ERROR) {
break;
}
// For all BCP-47 language tags that use extensions, the corresponding
// ICU locale ID will be longer but uloc_forLanguageTag() does compute
// the exact length needed so this memory reallocation will be done at
// most once.
resultCapacity = reslen;
status = U_ZERO_ERROR;
}
if (U_FAILURE(status)) {
return result;
}
if (parsedLength != tag.size()) {
status = U_ILLEGAL_ARGUMENT_ERROR;
return result;
}
localeID.append(buffer, reslen, status);
if (status == U_STRING_NOT_TERMINATED_WARNING) {
status = U_ZERO_ERROR; // Terminators provided by CharString.
}
if (U_FAILURE(status)) {
return result;
}
result.init(localeID.data(), /*canonicalize=*/FALSE);
if (result.isBogus()) {
status = U_ILLEGAL_ARGUMENT_ERROR;
}
return result;
}
void
Locale::toLanguageTag(ByteSink& sink, UErrorCode& status) const
{
if (U_FAILURE(status)) {
return;
}
if (fIsBogus) {
status = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
// All simple language tags will have the exact same length as BCP-47
// strings as they have as ICU locale IDs (like "en-US" for "en_US").
LocalMemory<char> scratch;
int32_t scratch_capacity = static_cast<int32_t>(uprv_strlen(fullName));
if (scratch_capacity == 0) {
scratch_capacity = 3; // "und"
}
char* buffer;
int32_t result_capacity, reslen;
for (;;) {
if (scratch.allocateInsteadAndReset(scratch_capacity) == nullptr) {
status = U_MEMORY_ALLOCATION_ERROR;
return;
}
buffer = sink.GetAppendBuffer(
/*min_capacity=*/scratch_capacity,
/*desired_capacity_hint=*/scratch_capacity,
scratch.getAlias(),
scratch_capacity,
&result_capacity);
reslen = uloc_toLanguageTag(
fullName,
buffer,
result_capacity,
/*strict=*/FALSE,
&status);
if (status != U_BUFFER_OVERFLOW_ERROR) {
break;
}
// For some very few edge cases a language tag will be longer as a
// BCP-47 string than it is as an ICU locale ID. Most notoriously "C"
// expands to the BCP-47 tag "en-US-u-va-posix", 16 times longer, and
// it'll take several calls to uloc_toLanguageTag() to figure that out.
// https://unicode-org.atlassian.net/browse/ICU-20132
scratch_capacity = reslen;
status = U_ZERO_ERROR;
}
if (U_FAILURE(status)) {
return;
}
sink.Append(buffer, reslen);
if (status == U_STRING_NOT_TERMINATED_WARNING) {
status = U_ZERO_ERROR; // Terminators not used.
}
}
Locale U_EXPORT2
Locale::createFromName (const char *name)
{
@ -1009,20 +1306,84 @@ KeywordEnumeration::~KeywordEnumeration() {
uprv_free(keywords);
}
// A wrapper around KeywordEnumeration that calls uloc_toUnicodeLocaleKey() in
// the next() method for each keyword before returning it.
class UnicodeKeywordEnumeration : public KeywordEnumeration {
public:
using KeywordEnumeration::KeywordEnumeration;
virtual ~UnicodeKeywordEnumeration();
virtual const char* next(int32_t* resultLength, UErrorCode& status) {
const char* legacy_key = KeywordEnumeration::next(nullptr, status);
if (U_SUCCESS(status) && legacy_key != nullptr) {
const char* key = uloc_toUnicodeLocaleKey(legacy_key);
if (key == nullptr) {
status = U_ILLEGAL_ARGUMENT_ERROR;
} else {
if (resultLength != nullptr) {
*resultLength = static_cast<int32_t>(uprv_strlen(key));
}
return key;
}
}
if (resultLength != nullptr) *resultLength = 0;
return nullptr;
}
};
// Out-of-line virtual destructor to serve as the "key function".
UnicodeKeywordEnumeration::~UnicodeKeywordEnumeration() = default;
StringEnumeration *
Locale::createKeywords(UErrorCode &status) const
{
char keywords[256];
int32_t keywordCapacity = 256;
int32_t keywordCapacity = sizeof keywords;
StringEnumeration *result = NULL;
if (U_FAILURE(status)) {
return result;
}
const char* variantStart = uprv_strchr(fullName, '@');
const char* assignment = uprv_strchr(fullName, '=');
if(variantStart) {
if(assignment > variantStart) {
int32_t keyLen = locale_getKeywords(variantStart+1, '@', keywords, keywordCapacity, NULL, 0, NULL, FALSE, &status);
if(keyLen) {
if(U_SUCCESS(status) && keyLen) {
result = new KeywordEnumeration(keywords, keyLen, 0, status);
if (!result) {
status = U_MEMORY_ALLOCATION_ERROR;
}
}
} else {
status = U_INVALID_FORMAT_ERROR;
}
}
return result;
}
StringEnumeration *
Locale::createUnicodeKeywords(UErrorCode &status) const
{
char keywords[256];
int32_t keywordCapacity = sizeof keywords;
StringEnumeration *result = NULL;
if (U_FAILURE(status)) {
return result;
}
const char* variantStart = uprv_strchr(fullName, '@');
const char* assignment = uprv_strchr(fullName, '=');
if(variantStart) {
if(assignment > variantStart) {
int32_t keyLen = locale_getKeywords(variantStart+1, '@', keywords, keywordCapacity, NULL, 0, NULL, FALSE, &status);
if(U_SUCCESS(status) && keyLen) {
result = new UnicodeKeywordEnumeration(keywords, keyLen, 0, status);
if (!result) {
status = U_MEMORY_ALLOCATION_ERROR;
}
}
} else {
status = U_INVALID_FORMAT_ERROR;
@ -1037,6 +1398,105 @@ Locale::getKeywordValue(const char* keywordName, char *buffer, int32_t bufLen, U
return uloc_getKeywordValue(fullName, keywordName, buffer, bufLen, &status);
}
void
Locale::getKeywordValue(StringPiece keywordName, ByteSink& sink, UErrorCode& status) const {
if (U_FAILURE(status)) {
return;
}
if (fIsBogus) {
status = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
// TODO: Remove the need for a const char* to a NUL terminated buffer.
const CharString keywordName_nul(keywordName, status);
if (U_FAILURE(status)) {
return;
}
LocalMemory<char> scratch;
int32_t scratch_capacity = 16; // Arbitrarily chosen default size.
char* buffer;
int32_t result_capacity, reslen;
for (;;) {
if (scratch.allocateInsteadAndReset(scratch_capacity) == nullptr) {
status = U_MEMORY_ALLOCATION_ERROR;
return;
}
buffer = sink.GetAppendBuffer(
/*min_capacity=*/scratch_capacity,
/*desired_capacity_hint=*/scratch_capacity,
scratch.getAlias(),
scratch_capacity,
&result_capacity);
reslen = uloc_getKeywordValue(
fullName,
keywordName_nul.data(),
buffer,
result_capacity,
&status);
if (status != U_BUFFER_OVERFLOW_ERROR) {
break;
}
scratch_capacity = reslen;
status = U_ZERO_ERROR;
}
if (U_FAILURE(status)) {
return;
}
sink.Append(buffer, reslen);
if (status == U_STRING_NOT_TERMINATED_WARNING) {
status = U_ZERO_ERROR; // Terminators not used.
}
}
void
Locale::getUnicodeKeywordValue(StringPiece keywordName,
ByteSink& sink,
UErrorCode& status) const {
// TODO: Remove the need for a const char* to a NUL terminated buffer.
const CharString keywordName_nul(keywordName, status);
if (U_FAILURE(status)) {
return;
}
const char* legacy_key = uloc_toLegacyKey(keywordName_nul.data());
if (legacy_key == nullptr) {
status = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
CharString legacy_value;
{
CharStringByteSink sink(&legacy_value);
getKeywordValue(legacy_key, sink, status);
}
if (U_FAILURE(status)) {
return;
}
const char* unicode_value = uloc_toUnicodeLocaleType(
keywordName_nul.data(), legacy_value.data());
if (unicode_value == nullptr) {
status = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
sink.Append(unicode_value, static_cast<int32_t>(uprv_strlen(unicode_value)));
}
void
Locale::setKeywordValue(const char* keywordName, const char* keywordValue, UErrorCode &status)
{
@ -1047,6 +1507,46 @@ Locale::setKeywordValue(const char* keywordName, const char* keywordValue, UErro
}
}
void
Locale::setKeywordValue(StringPiece keywordName,
StringPiece keywordValue,
UErrorCode& status) {
// TODO: Remove the need for a const char* to a NUL terminated buffer.
const CharString keywordName_nul(keywordName, status);
const CharString keywordValue_nul(keywordValue, status);
setKeywordValue(keywordName_nul.data(), keywordValue_nul.data(), status);
}
void
Locale::setUnicodeKeywordValue(StringPiece keywordName,
StringPiece keywordValue,
UErrorCode& status) {
// TODO: Remove the need for a const char* to a NUL terminated buffer.
const CharString keywordName_nul(keywordName, status);
const CharString keywordValue_nul(keywordValue, status);
if (U_FAILURE(status)) {
return;
}
const char* legacy_key = uloc_toLegacyKey(keywordName_nul.data());
if (legacy_key == nullptr) {
status = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
const char* legacy_value =
uloc_toLegacyType(keywordName_nul.data(), keywordValue_nul.data());
if (legacy_value == nullptr) {
status = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
setKeywordValue(legacy_key, legacy_value, status);
}
const char *
Locale::getBaseName() const {
return baseName;

9
intl/icu/source/common/loclikely.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -8,7 +8,7 @@
*
*******************************************************************************
* file name: loclikely.cpp
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
@ -22,6 +22,7 @@
#include "unicode/utypes.h"
#include "unicode/locid.h"
#include "unicode/putil.h"
#include "unicode/uchar.h"
#include "unicode/uloc.h"
#include "unicode/ures.h"
#include "unicode/uscript.h"
@ -510,7 +511,7 @@ parseTagString(
unknownLanguage);
*langLength = (int32_t)uprv_strlen(lang);
}
else if (_isIDSeparator(*position)) {
if (_isIDSeparator(*position)) {
++position;
}
@ -1280,7 +1281,7 @@ uloc_minimizeSubtags(const char* localeID,
// Pairs of (language subtag, + or -) for finding out fast if common languages
// are LTR (minus) or RTL (plus).
static const char* LANG_DIR_STRING =
static const char LANG_DIR_STRING[] =
"root-en-es-pt-zh-ja-ko-de-fr-it-ar+he+fa+ru-nl-pl-th-tr-";
// Implemented here because this calls uloc_addLikelySubtags().

267
intl/icu/source/common/locmap.c → intl/icu/source/common/locmap.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
@ -30,6 +30,7 @@
#include "locmap.h"
#include "cstring.h"
#include "cmemory.h"
#include "unicode/uloc.h"
#if U_PLATFORM == U_PF_WINDOWS && defined(_MSC_VER) && (_MSC_VER >= 1500)
/*
@ -40,10 +41,7 @@
* We might need to #include some Windows header and test for some version macro from there.
* Or call some Windows function and see what it returns.
*/
#define USE_WINDOWS_LOCALE_API
#endif
#ifdef USE_WINDOWS_LOCALE_API
#define USE_WINDOWS_LCID_MAPPING_API
#include <windows.h>
#include <winnls.h>
#endif
@ -53,8 +51,8 @@
* The mapping from Win32 locale ID numbers to POSIX locale strings should
* be the faster one.
*
* Many LCID values come from winnt.h
* Some also come from http://www.microsoft.com/globaldev/reference/lcid-all.mspx
* Windows LCIDs are defined at https://msdn.microsoft.com/en-us/library/cc233965.aspx
* [MS-LCID] Windows Language Code Identifier (LCID) Reference
*/
/*
@ -126,7 +124,9 @@ static const ILcidPosixElement locmap_ ## id [] =
// Keep static locale variables inside the function so that
// it can be created properly during static init.
//
// Note: This table should be updated periodically. Check the National Lanaguage Support API Reference Website.
// Note: This table should be updated periodically. Check the [MS-LCID] Windows Language Code Identifier
// (LCID) Reference defined at https://msdn.microsoft.com/en-us/library/cc233965.aspx
//
// Microsoft is moving away from LCID in favor of locale name as of Vista. This table needs to be
// maintained for support of older Windows version.
// Update: Windows 7 (091130)
@ -138,6 +138,9 @@ static const ILcidPosixElement locmap_ ## id [] =
////////////////////////////////////////////
*/
// TODO: For Windows ideally this table would be a list of exceptions rather than a complete list as
// LocaleNameToLCID and LCIDToLocaleName provide 90% of these.
ILCID_POSIX_ELEMENT_ARRAY(0x0436, af, af_ZA)
ILCID_POSIX_SUBTABLE(ar) {
@ -187,7 +190,10 @@ ILCID_POSIX_ELEMENT_ARRAY(0x0423, be, be_BY)
ILCID_POSIX_ELEMENT_ARRAY(0x0402, bg, bg_BG)
ILCID_POSIX_ELEMENT_ARRAY(0x0466, bin, bin_NG)
ILCID_POSIX_SUBTABLE(bin) {
{0x66, "bin"},
{0x0466, "bin_NG"}
};
ILCID_POSIX_SUBTABLE(bn) {
{0x45, "bn"},
@ -211,8 +217,15 @@ ILCID_POSIX_SUBTABLE(ca) {
};
ILCID_POSIX_ELEMENT_ARRAY(0x0483, co, co_FR)
ILCID_POSIX_ELEMENT_ARRAY(0x045c, chr,chr_US)
ILCID_POSIX_SUBTABLE(chr) {
{0x05c, "chr"},
{0x7c5c, "chr_Cher"},
{0x045c, "chr_Cher_US"},
{0x045c, "chr_US"}
};
// ICU has chosen different names for these.
ILCID_POSIX_SUBTABLE(ckb) {
{0x92, "ckb"},
{0x7c92, "ckb_Arab"},
@ -225,6 +238,7 @@ ILCID_POSIX_ELEMENT_ARRAY(0x0405, cs, cs_CZ)
ILCID_POSIX_ELEMENT_ARRAY(0x0452, cy, cy_GB)
ILCID_POSIX_ELEMENT_ARRAY(0x0406, da, da_DK)
// Windows doesn't know POSIX or BCP47 Unicode phonebook sort names
ILCID_POSIX_SUBTABLE(de) {
{0x07, "de"},
{0x0c07, "de_AT"},
@ -239,6 +253,7 @@ ILCID_POSIX_SUBTABLE(de) {
ILCID_POSIX_ELEMENT_ARRAY(0x0465, dv, dv_MV)
ILCID_POSIX_ELEMENT_ARRAY(0x0408, el, el_GR)
// Windows uses an empty string for 'invariant'
ILCID_POSIX_SUBTABLE(en) {
{0x09, "en"},
{0x0c09, "en_AU"},
@ -256,22 +271,23 @@ ILCID_POSIX_SUBTABLE(en) {
{0x4809, "en_SG"},
{0x2C09, "en_TT"},
{0x0409, "en_US"},
{0x007f, "en_US_POSIX"}, /* duplicate for roundtripping */
{0x2409, "en_VI"}, /* Virgin Islands AKA Caribbean Islands (en_CB). */
{0x007f, "en_US_POSIX"}, /* duplicate for round-tripping */
{0x2409, "en_029"},
{0x1c09, "en_ZA"},
{0x3009, "en_ZW"},
{0x2409, "en_029"},
{0x0409, "en_AS"}, /* Alias for en_US. Leave last. */
{0x0409, "en_GU"}, /* Alias for en_US. Leave last. */
{0x0409, "en_MH"}, /* Alias for en_US. Leave last. */
{0x0409, "en_MP"}, /* Alias for en_US. Leave last. */
{0x0409, "en_UM"} /* Alias for en_US. Leave last. */
{0x2409, "en_VI"}, /* Virgin Islands AKA Caribbean Islands (en_CB). On Windows8+ This is 0x1000 or dynamically assigned */
{0x0409, "en_AS"}, /* Alias for en_US. Leave last. On Windows8+ This is 0x1000 or dynamically assigned */
{0x0409, "en_GU"}, /* Alias for en_US. Leave last. On Windows8+ This is 0x1000 or dynamically assigned */
{0x0409, "en_MH"}, /* Alias for en_US. Leave last. On Windows8+ This is 0x1000 or dynamically assigned */
{0x0409, "en_MP"}, /* Alias for en_US. Leave last. On Windows8+ This is 0x1000 or dynamically assigned */
{0x0409, "en_UM"} /* Alias for en_US. Leave last. On Windows8+ This is 0x1000 or dynamically assigned */
};
ILCID_POSIX_SUBTABLE(en_US_POSIX) {
{0x007f, "en_US_POSIX"} /* duplicate for roundtripping */
};
// Windows doesn't know POSIX or BCP47 Unicode traditional sort names
ILCID_POSIX_SUBTABLE(es) {
{0x0a, "es"},
{0x2c0a, "es_AR"},
@ -297,7 +313,7 @@ ILCID_POSIX_SUBTABLE(es) {
{0x200a, "es_VE"},
{0x580a, "es_419"},
{0x040a, "es_ES@collation=traditional"},
{0x040a, "es@collation=traditional"}
{0x040a, "es@collation=traditional"} // Windows will treat this as es-ES@collation=traditional
};
ILCID_POSIX_ELEMENT_ARRAY(0x0425, et, et_EE)
@ -310,6 +326,7 @@ ILCID_POSIX_SUBTABLE(fa) {
{0x048c, "fa_AF"} /* Persian/Dari (Afghanistan) */
};
/* duplicate for roundtripping */
ILCID_POSIX_SUBTABLE(fa_AF) {
{0x8c, "fa_AF"}, /* Persian/Dari (Afghanistan) */
@ -411,7 +428,12 @@ ILCID_POSIX_SUBTABLE(hsb) {
ILCID_POSIX_ELEMENT_ARRAY(0x040e, hu, hu_HU)
ILCID_POSIX_ELEMENT_ARRAY(0x042b, hy, hy_AM)
ILCID_POSIX_ELEMENT_ARRAY(0x0469, ibb, ibb_NG)
ILCID_POSIX_SUBTABLE(ibb) {
{0x69, "ibb"},
{0x0469, "ibb_NG"}
};
ILCID_POSIX_ELEMENT_ARRAY(0x0421, id, id_ID)
ILCID_POSIX_ELEMENT_ARRAY(0x0470, ig, ig_NG)
ILCID_POSIX_ELEMENT_ARRAY(0x0478, ii, ii_CN)
@ -450,13 +472,18 @@ ILCID_POSIX_ELEMENT_ARRAY(0x0471, kr, kr_NG)
ILCID_POSIX_SUBTABLE(ks) { /* We could add PK and CN too */
{0x60, "ks"},
{0x0860, "ks_IN"}, /* Documentation doesn't mention script */
{0x0460, "ks_Arab_IN"},
{0x0860, "ks_Deva_IN"}
};
ILCID_POSIX_ELEMENT_ARRAY(0x0440, ky, ky_KG) /* Kyrgyz is spoken in Kyrgyzstan */
ILCID_POSIX_ELEMENT_ARRAY(0x0476, la, la_IT) /* TODO: Verify the country */
ILCID_POSIX_SUBTABLE(la) {
{0x76, "la"},
{0x0476, "la_001"},
{0x0476, "la_IT"} /*Left in for compatibility*/
};
ILCID_POSIX_ELEMENT_ARRAY(0x046e, lb, lb_LU)
ILCID_POSIX_ELEMENT_ARRAY(0x0454, lo, lo_LA)
ILCID_POSIX_ELEMENT_ARRAY(0x0427, lt, lt_LT)
@ -501,8 +528,9 @@ ILCID_POSIX_SUBTABLE(nl) {
};
/* The "no" locale split into nb and nn. By default in ICU, "no" is nb.*/
// TODO: Not all of these are needed on Windows, but I don't know how ICU treats preferred ones here.
ILCID_POSIX_SUBTABLE(no) {
{0x14, "no"}, /* really nb_NO */
{0x14, "no"}, /* really nb_NO - actually Windows differentiates between neutral (no region) and specific (with region) */
{0x7c14, "nb"}, /* really nb */
{0x0414, "nb_NO"}, /* really nb_NO. Keep first in the 414 list. */
{0x0414, "no_NO"}, /* really nb_NO */
@ -526,15 +554,19 @@ ILCID_POSIX_SUBTABLE(or_IN) {
{0x0448, "or_IN"},
};
ILCID_POSIX_SUBTABLE(pa) {
{0x46, "pa"},
{0x0446, "pa_IN"},
{0x0846, "pa_PK"},
{0x0846, "pa_Arab_PK"}
{0x0846, "pa_Arab_PK"},
{0x0846, "pa_PK"}
};
ILCID_POSIX_SUBTABLE(pap) {
{0x79, "pap"},
{0x0479, "pap_029"},
{0x0479, "pap_AN"} /*Left in for compatibility*/
};
ILCID_POSIX_ELEMENT_ARRAY(0x0479, pap, pap_AN)
ILCID_POSIX_ELEMENT_ARRAY(0x0415, pl, pl_PL)
ILCID_POSIX_ELEMENT_ARRAY(0x0463, ps, ps_AF)
@ -591,6 +623,9 @@ ILCID_POSIX_SUBTABLE(ro) {
{0x0818, "ro_MD"}
};
// TODO: This is almost certainly 'wrong'. 0 in Windows is a synonym for LOCALE_USER_DEFAULT.
// More likely this is a similar concept to the Windows 0x7f Invariant locale ""
// (Except that it's not invariant in ICU)
ILCID_POSIX_SUBTABLE(root) {
{0x00, "root"}
};
@ -607,9 +642,11 @@ ILCID_POSIX_ELEMENT_ARRAY(0x0485, sah,sah_RU)
ILCID_POSIX_SUBTABLE(sd) {
{0x59, "sd"},
{0x0459, "sd_IN"},
{0x0459, "sd_Deva_IN"},
{0x0859, "sd_PK"}
{0x0459, "sd_IN"},
{0x0859, "sd_Arab_PK"},
{0x0859, "sd_PK"},
{0x7c59, "sd_Arab"}
};
ILCID_POSIX_SUBTABLE(se) {
@ -633,9 +670,8 @@ ILCID_POSIX_ELEMENT_ARRAY(0x045b, si, si_LK)
ILCID_POSIX_ELEMENT_ARRAY(0x041b, sk, sk_SK)
ILCID_POSIX_ELEMENT_ARRAY(0x0424, sl, sl_SI)
ILCID_POSIX_SUBTABLE(so) { /* TODO: Verify the country */
ILCID_POSIX_SUBTABLE(so) {
{0x77, "so"},
{0x0477, "so_ET"},
{0x0477, "so_SO"}
};
@ -727,9 +763,16 @@ ILCID_POSIX_SUBTABLE(ve) { /* TODO: Verify the country */
ILCID_POSIX_ELEMENT_ARRAY(0x042a, vi, vi_VN)
ILCID_POSIX_ELEMENT_ARRAY(0x0488, wo, wo_SN)
ILCID_POSIX_ELEMENT_ARRAY(0x0434, xh, xh_ZA)
ILCID_POSIX_ELEMENT_ARRAY(0x043d, yi, yi)
ILCID_POSIX_SUBTABLE(yi) {
{0x003d, "yi"},
{0x043d, "yi_001"}
};
ILCID_POSIX_ELEMENT_ARRAY(0x046a, yo, yo_NG)
// Windows & ICU tend to different names for some of these
// TODO: Windows probably does not need all of these entries, but I don't know how the precedence works.
ILCID_POSIX_SUBTABLE(zh) {
{0x0004, "zh_Hans"},
{0x7804, "zh"},
@ -753,6 +796,7 @@ ILCID_POSIX_SUBTABLE(zh) {
{0x20804,"zh_Hans@collation=stroke"},
{0x20804,"zh_Hans_CN@collation=stroke"},
{0x20804,"zh_CN@collation=stroke"}
// TODO: Alternate collations for other LCIDs are missing, eg: 0x50804
};
ILCID_POSIX_ELEMENT_ARRAY(0x0435, zu, zu_ZA)
@ -971,7 +1015,7 @@ static const char*
getPosixID(const ILcidPosixMap *this_0, uint32_t hostID)
{
uint32_t i;
for (i = 0; i <= this_0->numRegions; i++)
for (i = 0; i < this_0->numRegions; i++)
{
if (this_0->regionMaps[i].hostID == hostID)
{
@ -991,7 +1035,7 @@ getPosixID(const ILcidPosixMap *this_0, uint32_t hostID)
//
/////////////////////////////////////
*/
#ifdef USE_WINDOWS_LOCALE_API
#ifdef USE_WINDOWS_LCID_MAPPING_API
/*
* Various language tags needs to be changed:
* quz -> qu
@ -1017,43 +1061,57 @@ uprv_convertToPosix(uint32_t hostid, char *posixID, int32_t posixIDCapacity, UEr
UBool bLookup = TRUE;
const char *pPosixID = NULL;
#ifdef USE_WINDOWS_LOCALE_API
#ifdef USE_WINDOWS_LCID_MAPPING_API
char locName[LOCALE_NAME_MAX_LENGTH] = {}; // ICU name can't be longer than Windows name
// Note: Windows primary lang ID 0x92 in LCID is used for Central Kurdish and
// GetLocaleInfo() maps such LCID to "ku". However, CLDR uses "ku" for
// Northern Kurdish and "ckb" for Central Kurdish. For this reason, we cannot
// use the Windows API to resolve locale ID for this specific case.
if ((hostid & 0x3FF) != 0x92) {
int32_t tmpLen = 0;
char locName[157]; /* ULOC_FULLNAME_CAPACITY */
UChar windowsLocaleName[LOCALE_NAME_MAX_LENGTH]; // ULOC_FULLNAME_CAPACITY > LOCALE_NAME_MAX_LENGTH
tmpLen = GetLocaleInfoA(hostid, LOCALE_SNAME, (LPSTR)locName, UPRV_LENGTHOF(locName));
// Note: LOCALE_ALLOW_NEUTRAL_NAMES was enabled in Windows7+, prior versions did not handle neutral (no-region) locale names.
tmpLen = LCIDToLocaleName(hostid, (PWSTR)windowsLocaleName, UPRV_LENGTHOF(windowsLocaleName), LOCALE_ALLOW_NEUTRAL_NAMES);
if (tmpLen > 1) {
/* Windows locale name may contain sorting variant, such as "es-ES_tradnl".
In such case, we need special mapping data found in the hardcoded table
in this source file. */
char *p = uprv_strchr(locName, '_');
if (p) {
/* Keep the base locale, without variant */
*p = 0;
tmpLen = uprv_strlen(locName);
}
else {
/* No hardcoded table lookup necessary */
bLookup = FALSE;
}
/* Change the tag separator from '-' to '_' */
p = locName;
while (*p) {
if (*p == '-') {
*p = '_';
int32_t i = 0;
// Only need to look up in table if have _, eg for de-de_phoneb type alternate sort.
bLookup = FALSE;
for (i = 0; i < UPRV_LENGTHOF(locName); i++)
{
locName[i] = (char)(windowsLocaleName[i]);
// Windows locale name may contain sorting variant, such as "es-ES_tradnl".
// In such cases, we need special mapping data found in the hardcoded table
// in this source file.
if (windowsLocaleName[i] == L'_')
{
// Keep the base locale, without variant
// TODO: Should these be mapped from _phoneb to @collation=phonebook, etc.?
locName[i] = '\0';
tmpLen = i;
bLookup = TRUE;
break;
}
else if (windowsLocaleName[i] == L'-')
{
// Windows names use -, ICU uses _
locName[i] = '_';
}
else if (windowsLocaleName[i] == L'\0')
{
// No point in doing more work than necessary
break;
}
p++;
}
// TODO: Need to understand this better, why isn't it an alias?
FIX_LANGUAGE_ID_TAG(locName, tmpLen);
pPosixID = locName;
}
}
#endif
#endif // USE_WINDOWS_LCID_MAPPING_API
if (bLookup) {
const char *pCandidate = NULL;
langID = LANGUAGE_LCID(hostid);
@ -1074,7 +1132,7 @@ uprv_convertToPosix(uint32_t hostid, char *posixID, int32_t posixIDCapacity, UEr
}
if (pPosixID) {
int32_t resLen = uprv_strlen(pPosixID);
int32_t resLen = static_cast<int32_t>(uprv_strlen(pPosixID));
int32_t copyLen = resLen <= posixIDCapacity ? resLen : posixIDCapacity;
uprv_memcpy(posixID, pPosixID, copyLen);
if (resLen < posixIDCapacity) {
@ -1101,15 +1159,103 @@ uprv_convertToPosix(uint32_t hostid, char *posixID, int32_t posixIDCapacity, UEr
// POSIX --> LCID
// This should only be called from uloc_getLCID.
// The locale ID must be in canonical form.
// langID is separate so that this file doesn't depend on the uloc_* API.
//
/////////////////////////////////////
*/
U_CAPI uint32_t
uprv_convertToLCIDPlatform(const char* localeID)
{
// The purpose of this function is to leverage native platform name->lcid
// conversion functionality when available.
#ifdef USE_WINDOWS_LCID_MAPPING_API
DWORD nameLCIDFlags = 0;
UErrorCode myStatus = U_ZERO_ERROR;
// First check for a Windows name->LCID match, fall through to catch
// ICU special cases, but Windows may know it already.
#if LOCALE_ALLOW_NEUTRAL_NAMES
nameLCIDFlags = LOCALE_ALLOW_NEUTRAL_NAMES;
#endif /* LOCALE_ALLOW_NEUTRAL_NAMES */
int32_t len;
char collVal[ULOC_KEYWORDS_CAPACITY] = {};
char baseName[ULOC_FULLNAME_CAPACITY] = {};
const char * mylocaleID = localeID;
// Check any for keywords.
if (uprv_strchr(localeID, '@'))
{
len = uloc_getKeywordValue(localeID, "collation", collVal, UPRV_LENGTHOF(collVal) - 1, &myStatus);
if (U_SUCCESS(myStatus) && len > 0)
{
// If it contains the keyword collation, return 0 so that the LCID lookup table will be used.
return 0;
}
else
{
// If the locale ID contains keywords other than collation, just use the base name.
len = uloc_getBaseName(localeID, baseName, UPRV_LENGTHOF(baseName) - 1, &myStatus);
if (U_SUCCESS(myStatus) && len > 0)
{
baseName[len] = 0;
mylocaleID = baseName;
}
}
}
char asciiBCP47Tag[LOCALE_NAME_MAX_LENGTH] = {};
// this will change it from de_DE@collation=phonebook to de-DE-u-co-phonebk form
(void)uloc_toLanguageTag(mylocaleID, asciiBCP47Tag, UPRV_LENGTHOF(asciiBCP47Tag), FALSE, &myStatus);
if (U_SUCCESS(myStatus))
{
// Need it to be UTF-16, not 8-bit
wchar_t bcp47Tag[LOCALE_NAME_MAX_LENGTH] = {};
int32_t i;
for (i = 0; i < UPRV_LENGTHOF(bcp47Tag); i++)
{
if (asciiBCP47Tag[i] == '\0')
{
break;
}
else
{
// Copy the character
bcp47Tag[i] = static_cast<wchar_t>(asciiBCP47Tag[i]);
}
}
if (i < (UPRV_LENGTHOF(bcp47Tag) - 1))
{
// Ensure it's null terminated
bcp47Tag[i] = L'\0';
LCID lcid = LocaleNameToLCID(bcp47Tag, nameLCIDFlags);
if (lcid > 0)
{
// Found LCID from windows, return that one, unless its completely ambiguous
// LOCALE_USER_DEFAULT and transients are OK because they will round trip
// for this process.
if (lcid != LOCALE_CUSTOM_UNSPECIFIED)
{
return lcid;
}
}
}
}
#else
(void)localeID; // Suppress unused variable warning.
#endif /* USE_WINDOWS_LCID_MAPPING_API */
// No found, or not implemented on platforms without native name->lcid conversion
return 0;
}
U_CAPI uint32_t
uprv_convertToLCID(const char *langID, const char* posixID, UErrorCode* status)
{
// This function does the table lookup when native platform name->lcid conversion isn't available,
// or for locales that don't follow patterns the platform expects.
uint32_t low = 0;
uint32_t high = gLocaleCount;
uint32_t mid;
@ -1172,4 +1318,3 @@ uprv_convertToLCID(const char *langID, const char* posixID, UErrorCode* status)
*status = U_ILLEGAL_ARGUMENT_ERROR;
return 0; /* return international (root) */
}

5
intl/icu/source/common/locmap.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
@ -32,7 +32,8 @@
U_CAPI int32_t uprv_convertToPosix(uint32_t hostid, char* posixID, int32_t posixIDCapacity, UErrorCode* status);
/* Don't call this function directly. Use uloc_getLCID instead. */
/* Don't call these functions directly. Use uloc_getLCID instead. */
U_CAPI uint32_t uprv_convertToLCIDPlatform(const char *localeID); // Leverage platform conversion if possible
U_CAPI uint32_t uprv_convertToLCID(const char *langID, const char* posixID, UErrorCode* status);
#endif /* LOCMAP_H */

4
intl/icu/source/common/locresdata.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -8,7 +8,7 @@
*
*******************************************************************************
* file name: loclikely.cpp
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*

2
intl/icu/source/common/locutil.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************

2
intl/icu/source/common/locutil.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/**
*******************************************************************************

4
intl/icu/source/common/messageimpl.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -6,7 +6,7 @@
* Corporation and others. All Rights Reserved.
*******************************************************************************
* file name: messageimpl.h
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*

4
intl/icu/source/common/messagepattern.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -6,7 +6,7 @@
* Corporation and others. All Rights Reserved.
*******************************************************************************
* file name: messagepattern.cpp
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*

2
intl/icu/source/common/msvcres.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
//{{NO_DEPENDENCIES}}
// Copyright (c) 2003-2010 International Business Machines

8
intl/icu/source/common/mutex.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
@ -34,9 +34,9 @@ U_NAMESPACE_BEGIN
// private mutex where possible.
// For example:
//
// UMutex myMutex;
//
//
// UMutex myMutex = U_MUTEX_INITIALIZER;
//
// void Function(int arg1, int arg2)
// {
// static Object* foo; // Shared read-write object

2053
intl/icu/source/common/norm2_nfc_data.h
View file

File diff suppressed because it is too large Load diff

56
intl/icu/source/common/norm2allmodes.h
View file

@ -1,11 +1,11 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 2014, International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
* loadednormalizer2impl.h
* norm2allmodes.h
*
* created on: 2014sep07
* created by: Markus W. Scherer
@ -18,7 +18,9 @@
#if !UCONFIG_NO_NORMALIZATION
#include "unicode/edits.h"
#include "unicode/normalizer2.h"
#include "unicode/stringoptions.h"
#include "unicode/unistr.h"
#include "cpputils.h"
#include "normalizer2impl.h"
@ -210,8 +212,8 @@ private:
virtual UNormalizationCheckResult getQuickCheck(UChar32 c) const {
return impl.isDecompYes(impl.getNorm16(c)) ? UNORM_YES : UNORM_NO;
}
virtual UBool hasBoundaryBefore(UChar32 c) const { return impl.hasDecompBoundary(c, TRUE); }
virtual UBool hasBoundaryAfter(UChar32 c) const { return impl.hasDecompBoundary(c, FALSE); }
virtual UBool hasBoundaryBefore(UChar32 c) const { return impl.hasDecompBoundaryBefore(c); }
virtual UBool hasBoundaryAfter(UChar32 c) const { return impl.hasDecompBoundaryAfter(c); }
virtual UBool isInert(UChar32 c) const { return impl.isDecompInert(c); }
};
@ -224,19 +226,35 @@ public:
private:
virtual void
normalize(const UChar *src, const UChar *limit,
ReorderingBuffer &buffer, UErrorCode &errorCode) const {
ReorderingBuffer &buffer, UErrorCode &errorCode) const U_OVERRIDE {
impl.compose(src, limit, onlyContiguous, TRUE, buffer, errorCode);
}
using Normalizer2WithImpl::normalize; // Avoid warning about hiding base class function.
void
normalizeUTF8(uint32_t options, StringPiece src, ByteSink &sink,
Edits *edits, UErrorCode &errorCode) const U_OVERRIDE {
if (U_FAILURE(errorCode)) {
return;
}
if (edits != nullptr && (options & U_EDITS_NO_RESET) == 0) {
edits->reset();
}
const uint8_t *s = reinterpret_cast<const uint8_t *>(src.data());
impl.composeUTF8(options, onlyContiguous, s, s + src.length(),
&sink, edits, errorCode);
sink.Flush();
}
virtual void
normalizeAndAppend(const UChar *src, const UChar *limit, UBool doNormalize,
UnicodeString &safeMiddle,
ReorderingBuffer &buffer, UErrorCode &errorCode) const {
ReorderingBuffer &buffer, UErrorCode &errorCode) const U_OVERRIDE {
impl.composeAndAppend(src, limit, doNormalize, onlyContiguous, safeMiddle, buffer, errorCode);
}
virtual UBool
isNormalized(const UnicodeString &s, UErrorCode &errorCode) const {
isNormalized(const UnicodeString &s, UErrorCode &errorCode) const U_OVERRIDE {
if(U_FAILURE(errorCode)) {
return FALSE;
}
@ -252,8 +270,16 @@ private:
}
return impl.compose(sArray, sArray+s.length(), onlyContiguous, FALSE, buffer, errorCode);
}
virtual UBool
isNormalizedUTF8(StringPiece sp, UErrorCode &errorCode) const U_OVERRIDE {
if(U_FAILURE(errorCode)) {
return FALSE;
}
const uint8_t *s = reinterpret_cast<const uint8_t *>(sp.data());
return impl.composeUTF8(0, onlyContiguous, s, s + sp.length(), nullptr, nullptr, errorCode);
}
virtual UNormalizationCheckResult
quickCheck(const UnicodeString &s, UErrorCode &errorCode) const {
quickCheck(const UnicodeString &s, UErrorCode &errorCode) const U_OVERRIDE {
if(U_FAILURE(errorCode)) {
return UNORM_MAYBE;
}
@ -267,21 +293,21 @@ private:
return qcResult;
}
virtual const UChar *
spanQuickCheckYes(const UChar *src, const UChar *limit, UErrorCode &) const {
spanQuickCheckYes(const UChar *src, const UChar *limit, UErrorCode &) const U_OVERRIDE {
return impl.composeQuickCheck(src, limit, onlyContiguous, NULL);
}
using Normalizer2WithImpl::spanQuickCheckYes; // Avoid warning about hiding base class function.
virtual UNormalizationCheckResult getQuickCheck(UChar32 c) const {
virtual UNormalizationCheckResult getQuickCheck(UChar32 c) const U_OVERRIDE {
return impl.getCompQuickCheck(impl.getNorm16(c));
}
virtual UBool hasBoundaryBefore(UChar32 c) const {
virtual UBool hasBoundaryBefore(UChar32 c) const U_OVERRIDE {
return impl.hasCompBoundaryBefore(c);
}
virtual UBool hasBoundaryAfter(UChar32 c) const {
return impl.hasCompBoundaryAfter(c, onlyContiguous, FALSE);
virtual UBool hasBoundaryAfter(UChar32 c) const U_OVERRIDE {
return impl.hasCompBoundaryAfter(c, onlyContiguous);
}
virtual UBool isInert(UChar32 c) const {
return impl.hasCompBoundaryAfter(c, onlyContiguous, TRUE);
virtual UBool isInert(UChar32 c) const U_OVERRIDE {
return impl.isCompInert(c, onlyContiguous);
}
const UBool onlyContiguous;

160
intl/icu/source/common/normalizer2.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -8,7 +8,7 @@
*
*******************************************************************************
* file name: normalizer2.cpp
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
@ -20,7 +20,9 @@
#if !UCONFIG_NO_NORMALIZATION
#include "unicode/edits.h"
#include "unicode/normalizer2.h"
#include "unicode/stringoptions.h"
#include "unicode/unistr.h"
#include "unicode/unorm.h"
#include "cstring.h"
@ -32,9 +34,11 @@
using icu::Normalizer2Impl;
#if NORM2_HARDCODE_NFC_DATA
// NFC/NFD data machine-generated by gennorm2 --csource
#define INCLUDED_FROM_NORMALIZER2_CPP
#include "norm2_nfc_data.h"
#endif
U_NAMESPACE_BEGIN
@ -42,6 +46,20 @@ U_NAMESPACE_BEGIN
Normalizer2::~Normalizer2() {}
void
Normalizer2::normalizeUTF8(uint32_t /*options*/, StringPiece src, ByteSink &sink,
Edits *edits, UErrorCode &errorCode) const {
if (U_FAILURE(errorCode)) {
return;
}
if (edits != nullptr) {
errorCode = U_UNSUPPORTED_ERROR;
return;
}
UnicodeString src16 = UnicodeString::fromUTF8(src);
normalize(src16, errorCode).toUTF8(sink);
}
UBool
Normalizer2::getRawDecomposition(UChar32, UnicodeString &) const {
return FALSE;
@ -57,6 +75,11 @@ Normalizer2::getCombiningClass(UChar32 /*c*/) const {
return 0;
}
UBool
Normalizer2::isNormalizedUTF8(StringPiece s, UErrorCode &errorCode) const {
return U_SUCCESS(errorCode) && isNormalized(UnicodeString::fromUTF8(s), errorCode);
}
// Normalizer2 implementation for the old UNORM_NONE.
class NoopNormalizer2 : public Normalizer2 {
virtual ~NoopNormalizer2();
@ -64,7 +87,7 @@ class NoopNormalizer2 : public Normalizer2 {
virtual UnicodeString &
normalize(const UnicodeString &src,
UnicodeString &dest,
UErrorCode &errorCode) const {
UErrorCode &errorCode) const U_OVERRIDE {
if(U_SUCCESS(errorCode)) {
if(&dest!=&src) {
dest=src;
@ -74,10 +97,27 @@ class NoopNormalizer2 : public Normalizer2 {
}
return dest;
}
virtual void
normalizeUTF8(uint32_t options, StringPiece src, ByteSink &sink,
Edits *edits, UErrorCode &errorCode) const U_OVERRIDE {
if(U_SUCCESS(errorCode)) {
if (edits != nullptr) {
if ((options & U_EDITS_NO_RESET) == 0) {
edits->reset();
}
edits->addUnchanged(src.length());
}
if ((options & U_OMIT_UNCHANGED_TEXT) == 0) {
sink.Append(src.data(), src.length());
}
sink.Flush();
}
}
virtual UnicodeString &
normalizeSecondAndAppend(UnicodeString &first,
const UnicodeString &second,
UErrorCode &errorCode) const {
UErrorCode &errorCode) const U_OVERRIDE {
if(U_SUCCESS(errorCode)) {
if(&first!=&second) {
first.append(second);
@ -90,7 +130,7 @@ class NoopNormalizer2 : public Normalizer2 {
virtual UnicodeString &
append(UnicodeString &first,
const UnicodeString &second,
UErrorCode &errorCode) const {
UErrorCode &errorCode) const U_OVERRIDE {
if(U_SUCCESS(errorCode)) {
if(&first!=&second) {
first.append(second);
@ -101,25 +141,29 @@ class NoopNormalizer2 : public Normalizer2 {
return first;
}
virtual UBool
getDecomposition(UChar32, UnicodeString &) const {
getDecomposition(UChar32, UnicodeString &) const U_OVERRIDE {
return FALSE;
}
// No need to override the default getRawDecomposition().
// No need to U_OVERRIDE the default getRawDecomposition().
virtual UBool
isNormalized(const UnicodeString &, UErrorCode &) const {
return TRUE;
isNormalized(const UnicodeString &, UErrorCode &errorCode) const U_OVERRIDE {
return U_SUCCESS(errorCode);
}
virtual UBool
isNormalizedUTF8(StringPiece, UErrorCode &errorCode) const U_OVERRIDE {
return U_SUCCESS(errorCode);
}
virtual UNormalizationCheckResult
quickCheck(const UnicodeString &, UErrorCode &) const {
quickCheck(const UnicodeString &, UErrorCode &) const U_OVERRIDE {
return UNORM_YES;
}
virtual int32_t
spanQuickCheckYes(const UnicodeString &s, UErrorCode &) const {
spanQuickCheckYes(const UnicodeString &s, UErrorCode &) const U_OVERRIDE {
return s.length();
}
virtual UBool hasBoundaryBefore(UChar32) const { return TRUE; }
virtual UBool hasBoundaryAfter(UChar32) const { return TRUE; }
virtual UBool isInert(UChar32) const { return TRUE; }
virtual UBool hasBoundaryBefore(UChar32) const U_OVERRIDE { return TRUE; }
virtual UBool hasBoundaryAfter(UChar32) const U_OVERRIDE { return TRUE; }
virtual UBool isInert(UChar32) const U_OVERRIDE { return TRUE; }
};
NoopNormalizer2::~NoopNormalizer2() {}
@ -134,6 +178,36 @@ FCDNormalizer2::~FCDNormalizer2() {}
// instance cache ---------------------------------------------------------- ***
U_CDECL_BEGIN
static UBool U_CALLCONV uprv_normalizer2_cleanup();
U_CDECL_END
static Normalizer2 *noopSingleton;
static icu::UInitOnce noopInitOnce = U_INITONCE_INITIALIZER;
static void U_CALLCONV initNoopSingleton(UErrorCode &errorCode) {
if(U_FAILURE(errorCode)) {
return;
}
noopSingleton=new NoopNormalizer2;
if(noopSingleton==NULL) {
errorCode=U_MEMORY_ALLOCATION_ERROR;
return;
}
ucln_common_registerCleanup(UCLN_COMMON_NORMALIZER2, uprv_normalizer2_cleanup);
}
const Normalizer2 *Normalizer2Factory::getNoopInstance(UErrorCode &errorCode) {
if(U_FAILURE(errorCode)) { return NULL; }
umtx_initOnce(noopInitOnce, &initNoopSingleton, errorCode);
return noopSingleton;
}
const Normalizer2Impl *
Normalizer2Factory::getImpl(const Normalizer2 *norm2) {
return &((Normalizer2WithImpl *)norm2)->impl;
}
Norm2AllModes::~Norm2AllModes() {
delete impl;
}
@ -153,6 +227,7 @@ Norm2AllModes::createInstance(Normalizer2Impl *impl, UErrorCode &errorCode) {
return allModes;
}
#if NORM2_HARDCODE_NFC_DATA
Norm2AllModes *
Norm2AllModes::createNFCInstance(UErrorCode &errorCode) {
if(U_FAILURE(errorCode)) {
@ -168,48 +243,15 @@ Norm2AllModes::createNFCInstance(UErrorCode &errorCode) {
return createInstance(impl, errorCode);
}
U_CDECL_BEGIN
static UBool U_CALLCONV uprv_normalizer2_cleanup();
U_CDECL_END
static Norm2AllModes *nfcSingleton;
static Normalizer2 *noopSingleton;
static icu::UInitOnce nfcInitOnce = U_INITONCE_INITIALIZER;
static icu::UInitOnce noopInitOnce = U_INITONCE_INITIALIZER;
// UInitOnce singleton initialization functions
static void U_CALLCONV initNFCSingleton(UErrorCode &errorCode) {
nfcSingleton=Norm2AllModes::createNFCInstance(errorCode);
ucln_common_registerCleanup(UCLN_COMMON_NORMALIZER2, uprv_normalizer2_cleanup);
}
static void U_CALLCONV initNoopSingleton(UErrorCode &errorCode) {
if(U_FAILURE(errorCode)) {
return;
}
noopSingleton=new NoopNormalizer2;
if(noopSingleton==NULL) {
errorCode=U_MEMORY_ALLOCATION_ERROR;
return;
}
ucln_common_registerCleanup(UCLN_COMMON_NORMALIZER2, uprv_normalizer2_cleanup);
}
U_CDECL_BEGIN
static UBool U_CALLCONV uprv_normalizer2_cleanup() {
delete nfcSingleton;
nfcSingleton = NULL;
delete noopSingleton;
noopSingleton = NULL;
nfcInitOnce.reset();
noopInitOnce.reset();
return TRUE;
}
U_CDECL_END
const Norm2AllModes *
Norm2AllModes::getNFCInstance(UErrorCode &errorCode) {
if(U_FAILURE(errorCode)) { return NULL; }
@ -239,23 +281,29 @@ const Normalizer2 *Normalizer2Factory::getFCCInstance(UErrorCode &errorCode) {
return allModes!=NULL ? &allModes->fcc : NULL;
}
const Normalizer2 *Normalizer2Factory::getNoopInstance(UErrorCode &errorCode) {
if(U_FAILURE(errorCode)) { return NULL; }
umtx_initOnce(noopInitOnce, &initNoopSingleton, errorCode);
return noopSingleton;
}
const Normalizer2Impl *
Normalizer2Factory::getNFCImpl(UErrorCode &errorCode) {
const Norm2AllModes *allModes=Norm2AllModes::getNFCInstance(errorCode);
return allModes!=NULL ? allModes->impl : NULL;
}
#endif // NORM2_HARDCODE_NFC_DATA
const Normalizer2Impl *
Normalizer2Factory::getImpl(const Normalizer2 *norm2) {
return &((Normalizer2WithImpl *)norm2)->impl;
U_CDECL_BEGIN
static UBool U_CALLCONV uprv_normalizer2_cleanup() {
delete noopSingleton;
noopSingleton = NULL;
noopInitOnce.reset();
#if NORM2_HARDCODE_NFC_DATA
delete nfcSingleton;
nfcSingleton = NULL;
nfcInitOnce.reset();
#endif
return TRUE;
}
U_CDECL_END
U_NAMESPACE_END
// C API ------------------------------------------------------------------- ***

1964
intl/icu/source/common/normalizer2impl.cpp
View file

File diff suppressed because it is too large Load diff

350
intl/icu/source/common/normalizer2impl.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -8,7 +8,7 @@
*
*******************************************************************************
* file name: normalizer2impl.h
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
@ -24,17 +24,30 @@
#if !UCONFIG_NO_NORMALIZATION
#include "unicode/normalizer2.h"
#include "unicode/ucptrie.h"
#include "unicode/unistr.h"
#include "unicode/unorm.h"
#include "unicode/utf.h"
#include "unicode/utf16.h"
#include "mutex.h"
#include "udataswp.h"
#include "uset_imp.h"
#include "utrie2.h"
// When the nfc.nrm data is *not* hardcoded into the common library
// (with this constant set to 0),
// then it needs to be built into the data package:
// Add nfc.nrm to icu4c/source/data/Makefile.in DAT_FILES_SHORT
#define NORM2_HARDCODE_NFC_DATA 1
U_NAMESPACE_BEGIN
struct CanonIterData;
class ByteSink;
class Edits;
class InitCanonIterData;
class LcccContext;
class U_COMMON_API Hangul {
public:
/* Korean Hangul and Jamo constants */
@ -63,9 +76,9 @@ public:
return HANGUL_BASE<=c && c<HANGUL_LIMIT;
}
static inline UBool
isHangulWithoutJamoT(UChar c) {
isHangulLV(UChar32 c) {
c-=HANGUL_BASE;
return c<HANGUL_COUNT && c%JAMO_T_COUNT==0;
return 0<=c && c<HANGUL_COUNT && c%JAMO_T_COUNT==0;
}
static inline UBool isJamoL(UChar32 c) {
return (uint32_t)(c-JAMO_L_BASE)<JAMO_L_COUNT;
@ -73,6 +86,14 @@ public:
static inline UBool isJamoV(UChar32 c) {
return (uint32_t)(c-JAMO_V_BASE)<JAMO_V_COUNT;
}
static inline UBool isJamoT(UChar32 c) {
int32_t t=c-JAMO_T_BASE;
return 0<t && t<JAMO_T_COUNT; // not JAMO_T_BASE itself
}
static UBool isJamo(UChar32 c) {
return JAMO_L_BASE<=c && c<=JAMO_T_END &&
(c<=JAMO_L_END || (JAMO_V_BASE<=c && c<=JAMO_V_END) || JAMO_T_BASE<c);
}
/**
* Decomposes c, which must be a Hangul syllable, into buffer
@ -105,7 +126,7 @@ public:
buffer[0]=(UChar)(JAMO_L_BASE+c/JAMO_V_COUNT);
buffer[1]=(UChar)(JAMO_V_BASE+c%JAMO_V_COUNT);
} else {
buffer[0]=orig-c2; // LV syllable
buffer[0]=(UChar)(orig-c2); // LV syllable
buffer[1]=(UChar)(JAMO_T_BASE+c2);
}
}
@ -117,10 +138,13 @@ class Normalizer2Impl;
class U_COMMON_API ReorderingBuffer : public UMemory {
public:
/** Constructs only; init() should be called. */
ReorderingBuffer(const Normalizer2Impl &ni, UnicodeString &dest) :
impl(ni), str(dest),
start(NULL), reorderStart(NULL), limit(NULL),
remainingCapacity(0), lastCC(0) {}
/** Constructs, removes the string contents, and initializes for a small initial capacity. */
ReorderingBuffer(const Normalizer2Impl &ni, UnicodeString &dest, UErrorCode &errorCode);
~ReorderingBuffer() {
if(start!=NULL) {
str.releaseBuffer((int32_t)(limit-start));
@ -135,19 +159,14 @@ public:
uint8_t getLastCC() const { return lastCC; }
UBool equals(const UChar *start, const UChar *limit) const;
// For Hangul composition, replacing the Leading consonant Jamo with the syllable.
void setLastChar(UChar c) {
*(limit-1)=c;
}
UBool equals(const uint8_t *otherStart, const uint8_t *otherLimit) const;
UBool append(UChar32 c, uint8_t cc, UErrorCode &errorCode) {
return (c<=0xffff) ?
appendBMP((UChar)c, cc, errorCode) :
appendSupplementary(c, cc, errorCode);
}
// s must be in NFD, otherwise change the implementation.
UBool append(const UChar *s, int32_t length,
UBool append(const UChar *s, int32_t length, UBool isNFD,
uint8_t leadCC, uint8_t trailCC,
UErrorCode &errorCode);
UBool appendBMP(UChar c, uint8_t cc, UErrorCode &errorCode) {
@ -176,7 +195,7 @@ public:
lastCC=0;
}
void copyReorderableSuffixTo(UnicodeString &s) const {
s.setTo(reorderStart, (int32_t)(limit-reorderStart));
s.setTo(ConstChar16Ptr(reorderStart), (int32_t)(limit-reorderStart));
}
private:
/*
@ -218,6 +237,12 @@ private:
UChar *codePointStart, *codePointLimit;
};
/**
* Low-level implementation of the Unicode Normalization Algorithm.
* For the data structure and details see the documentation at the end of
* this normalizer2impl.h and in the design doc at
* http://site.icu-project.org/design/normalization/custom
*/
class U_COMMON_API Normalizer2Impl : public UObject {
public:
Normalizer2Impl() : normTrie(NULL), fCanonIterData(NULL) {
@ -225,7 +250,7 @@ public:
}
virtual ~Normalizer2Impl();
void init(const int32_t *inIndexes, const UTrie2 *inTrie,
void init(const int32_t *inIndexes, const UCPTrie *inTrie,
const uint16_t *inExtraData, const uint8_t *inSmallFCD);
void addLcccChars(UnicodeSet &set) const;
@ -234,11 +259,14 @@ public:
// low-level properties ------------------------------------------------ ***
const UTrie2 *getNormTrie() const { return normTrie; }
UBool ensureCanonIterData(UErrorCode &errorCode) const;
uint16_t getNorm16(UChar32 c) const { return UTRIE2_GET16(normTrie, c); }
// The trie stores values for lead surrogate code *units*.
// Surrogate code *points* are inert.
uint16_t getNorm16(UChar32 c) const {
return U_IS_LEAD(c) ? INERT : UCPTRIE_FAST_GET(normTrie, UCPTRIE_16, c);
}
uint16_t getRawNorm16(UChar32 c) const { return UCPTRIE_FAST_GET(normTrie, UCPTRIE_16, c); }
UNormalizationCheckResult getCompQuickCheck(uint16_t norm16) const {
if(norm16<minNoNo || MIN_YES_YES_WITH_CC<=norm16) {
@ -255,15 +283,22 @@ public:
uint8_t getCC(uint16_t norm16) const {
if(norm16>=MIN_NORMAL_MAYBE_YES) {
return (uint8_t)norm16;
return getCCFromNormalYesOrMaybe(norm16);
}
if(norm16<minNoNo || limitNoNo<=norm16) {
return 0;
}
return getCCFromNoNo(norm16);
}
static uint8_t getCCFromNormalYesOrMaybe(uint16_t norm16) {
return (uint8_t)(norm16 >> OFFSET_SHIFT);
}
static uint8_t getCCFromYesOrMaybe(uint16_t norm16) {
return norm16>=MIN_NORMAL_MAYBE_YES ? (uint8_t)norm16 : 0;
return norm16>=MIN_NORMAL_MAYBE_YES ? getCCFromNormalYesOrMaybe(norm16) : 0;
}
uint8_t getCCFromYesOrMaybeCP(UChar32 c) const {
if (c < minCompNoMaybeCP) { return 0; }
return getCCFromYesOrMaybe(getNorm16(c));
}
/**
@ -272,10 +307,8 @@ public:
* @return The lccc(c) in bits 15..8 and tccc(c) in bits 7..0.
*/
uint16_t getFCD16(UChar32 c) const {
if(c<0) {
if(c<minDecompNoCP) {
return 0;
} else if(c<0x180) {
return tccc180[c];
} else if(c<=0xffff) {
if(!singleLeadMightHaveNonZeroFCD16(c)) { return 0; }
}
@ -291,9 +324,7 @@ public:
*/
uint16_t nextFCD16(const UChar *&s, const UChar *limit) const {
UChar32 c=*s++;
if(c<0x180) {
return tccc180[c];
} else if(!singleLeadMightHaveNonZeroFCD16(c)) {
if(c<minDecompNoCP || !singleLeadMightHaveNonZeroFCD16(c)) {
return 0;
}
UChar c2;
@ -311,8 +342,8 @@ public:
*/
uint16_t previousFCD16(const UChar *start, const UChar *&s) const {
UChar32 c=*--s;
if(c<0x180) {
return tccc180[c];
if(c<minDecompNoCP) {
return 0;
}
if(!U16_IS_TRAIL(c)) {
if(!singleLeadMightHaveNonZeroFCD16(c)) {
@ -328,8 +359,6 @@ public:
return getFCD16FromNormData(c);
}
/** Returns the FCD data for U+0000<=c<U+0180. */
uint16_t getFCD16FromBelow180(UChar32 c) const { return tccc180[c]; }
/** Returns TRUE if the single-or-lead code unit c might have non-zero FCD data. */
UBool singleLeadMightHaveNonZeroFCD16(UChar32 lead) const {
// 0<=lead<=0xffff
@ -340,9 +369,6 @@ public:
/** Returns the FCD value from the regular normalization data. */
uint16_t getFCD16FromNormData(UChar32 c) const;
void makeCanonIterDataFromNorm16(UChar32 start, UChar32 end, uint16_t norm16,
CanonIterData &newData, UErrorCode &errorCode) const;
/**
* Gets the decomposition for one code point.
* @param c code point
@ -367,14 +393,25 @@ public:
UBool getCanonStartSet(UChar32 c, UnicodeSet &set) const;
enum {
MIN_CCC_LCCC_CP=0x300
};
// Fixed norm16 values.
MIN_YES_YES_WITH_CC=0xfe02,
JAMO_VT=0xfe00,
MIN_NORMAL_MAYBE_YES=0xfc00,
JAMO_L=2, // offset=1 hasCompBoundaryAfter=FALSE
INERT=1, // offset=0 hasCompBoundaryAfter=TRUE
// norm16 bit 0 is comp-boundary-after.
HAS_COMP_BOUNDARY_AFTER=1,
OFFSET_SHIFT=1,
// For algorithmic one-way mappings, norm16 bits 2..1 indicate the
// tccc (0, 1, >1) for quick FCC boundary-after tests.
DELTA_TCCC_0=0,
DELTA_TCCC_1=2,
DELTA_TCCC_GT_1=4,
DELTA_TCCC_MASK=6,
DELTA_SHIFT=3,
enum {
MIN_YES_YES_WITH_CC=0xff01,
JAMO_VT=0xff00,
MIN_NORMAL_MAYBE_YES=0xfe00,
JAMO_L=1,
MAX_DELTA=0x40
};
@ -394,21 +431,32 @@ public:
IX_MIN_COMP_NO_MAYBE_CP,
// Norm16 value thresholds for quick check combinations and types of extra data.
IX_MIN_YES_NO, // Mappings & compositions in [minYesNo..minYesNoMappingsOnly[.
/** Mappings & compositions in [minYesNo..minYesNoMappingsOnly[. */
IX_MIN_YES_NO,
/** Mappings are comp-normalized. */
IX_MIN_NO_NO,
IX_LIMIT_NO_NO,
IX_MIN_MAYBE_YES,
IX_MIN_YES_NO_MAPPINGS_ONLY, // Mappings only in [minYesNoMappingsOnly..minNoNo[.
/** Mappings only in [minYesNoMappingsOnly..minNoNo[. */
IX_MIN_YES_NO_MAPPINGS_ONLY,
/** Mappings are not comp-normalized but have a comp boundary before. */
IX_MIN_NO_NO_COMP_BOUNDARY_BEFORE,
/** Mappings do not have a comp boundary before. */
IX_MIN_NO_NO_COMP_NO_MAYBE_CC,
/** Mappings to the empty string. */
IX_MIN_NO_NO_EMPTY,
IX_RESERVED15,
IX_MIN_LCCC_CP,
IX_RESERVED19,
IX_COUNT
};
enum {
MAPPING_HAS_CCC_LCCC_WORD=0x80,
MAPPING_HAS_RAW_MAPPING=0x40,
MAPPING_NO_COMP_BOUNDARY_AFTER=0x20,
// unused bit 0x20,
MAPPING_LENGTH_MASK=0x1f
};
@ -457,6 +505,12 @@ public:
UnicodeString &safeMiddle,
ReorderingBuffer &buffer,
UErrorCode &errorCode) const;
/** sink==nullptr: isNormalized() */
UBool composeUTF8(uint32_t options, UBool onlyContiguous,
const uint8_t *src, const uint8_t *limit,
ByteSink *sink, icu::Edits *edits, UErrorCode &errorCode) const;
const UChar *makeFCD(const UChar *src, const UChar *limit,
ReorderingBuffer *buffer, UErrorCode &errorCode) const;
void makeFCDAndAppend(const UChar *src, const UChar *limit,
@ -465,27 +519,42 @@ public:
ReorderingBuffer &buffer,
UErrorCode &errorCode) const;
UBool hasDecompBoundary(UChar32 c, UBool before) const;
UBool hasDecompBoundaryBefore(UChar32 c) const;
UBool norm16HasDecompBoundaryBefore(uint16_t norm16) const;
UBool hasDecompBoundaryAfter(UChar32 c) const;
UBool norm16HasDecompBoundaryAfter(uint16_t norm16) const;
UBool isDecompInert(UChar32 c) const { return isDecompYesAndZeroCC(getNorm16(c)); }
UBool hasCompBoundaryBefore(UChar32 c) const {
return c<minCompNoMaybeCP || hasCompBoundaryBefore(c, getNorm16(c));
return c<minCompNoMaybeCP || norm16HasCompBoundaryBefore(getNorm16(c));
}
UBool hasCompBoundaryAfter(UChar32 c, UBool onlyContiguous) const {
return norm16HasCompBoundaryAfter(getNorm16(c), onlyContiguous);
}
UBool isCompInert(UChar32 c, UBool onlyContiguous) const {
uint16_t norm16=getNorm16(c);
return isCompYesAndZeroCC(norm16) &&
(norm16 & HAS_COMP_BOUNDARY_AFTER) != 0 &&
(!onlyContiguous || isInert(norm16) || *getMapping(norm16) <= 0x1ff);
}
UBool hasCompBoundaryAfter(UChar32 c, UBool onlyContiguous, UBool testInert) const;
UBool hasFCDBoundaryBefore(UChar32 c) const { return c<MIN_CCC_LCCC_CP || getFCD16(c)<=0xff; }
UBool hasFCDBoundaryAfter(UChar32 c) const {
uint16_t fcd16=getFCD16(c);
return fcd16<=1 || (fcd16&0xff)==0;
}
UBool hasFCDBoundaryBefore(UChar32 c) const { return hasDecompBoundaryBefore(c); }
UBool hasFCDBoundaryAfter(UChar32 c) const { return hasDecompBoundaryAfter(c); }
UBool isFCDInert(UChar32 c) const { return getFCD16(c)<=1; }
private:
friend class InitCanonIterData;
friend class LcccContext;
UBool isMaybe(uint16_t norm16) const { return minMaybeYes<=norm16 && norm16<=JAMO_VT; }
UBool isMaybeOrNonZeroCC(uint16_t norm16) const { return norm16>=minMaybeYes; }
static UBool isInert(uint16_t norm16) { return norm16==0; }
static UBool isJamoL(uint16_t norm16) { return norm16==1; }
static UBool isInert(uint16_t norm16) { return norm16==INERT; }
static UBool isJamoL(uint16_t norm16) { return norm16==JAMO_L; }
static UBool isJamoVT(uint16_t norm16) { return norm16==JAMO_VT; }
UBool isHangul(uint16_t norm16) const { return norm16==minYesNo; }
uint16_t hangulLVT() const { return minYesNoMappingsOnly|HAS_COMP_BOUNDARY_AFTER; }
UBool isHangulLV(uint16_t norm16) const { return norm16==minYesNo; }
UBool isHangulLVT(uint16_t norm16) const {
return norm16==hangulLVT();
}
UBool isCompYesAndZeroCC(uint16_t norm16) const { return norm16<minNoNo; }
// UBool isCompYes(uint16_t norm16) const {
// return norm16>=MIN_YES_YES_WITH_CC || norm16<minNoNo;
@ -504,7 +573,7 @@ private:
/**
* A little faster and simpler than isDecompYesAndZeroCC() but does not include
* the MaybeYes which combine-forward and have ccc=0.
* (Standard Unicode 5.2 normalization does not have such characters.)
* (Standard Unicode 10 normalization does not have such characters.)
*/
UBool isMostDecompYesAndZeroCC(uint16_t norm16) const {
return norm16<minYesNo || norm16==MIN_NORMAL_MAYBE_YES || norm16==JAMO_VT;
@ -514,7 +583,7 @@ private:
// For use with isCompYes().
// Perhaps the compiler can combine the two tests for MIN_YES_YES_WITH_CC.
// static uint8_t getCCFromYes(uint16_t norm16) {
// return norm16>=MIN_YES_YES_WITH_CC ? (uint8_t)norm16 : 0;
// return norm16>=MIN_YES_YES_WITH_CC ? getCCFromNormalYesOrMaybe(norm16) : 0;
// }
uint8_t getCCFromNoNo(uint16_t norm16) const {
const uint16_t *mapping=getMapping(norm16);
@ -525,30 +594,47 @@ private:
}
}
// requires that the [cpStart..cpLimit[ character passes isCompYesAndZeroCC()
uint8_t getTrailCCFromCompYesAndZeroCC(const UChar *cpStart, const UChar *cpLimit) const;
uint8_t getTrailCCFromCompYesAndZeroCC(uint16_t norm16) const {
if(norm16<=minYesNo) {
return 0; // yesYes and Hangul LV have ccc=tccc=0
} else {
// For Hangul LVT we harmlessly fetch a firstUnit with tccc=0 here.
return (uint8_t)(*getMapping(norm16)>>8); // tccc from yesNo
}
}
uint8_t getPreviousTrailCC(const UChar *start, const UChar *p) const;
uint8_t getPreviousTrailCC(const uint8_t *start, const uint8_t *p) const;
// Requires algorithmic-NoNo.
UChar32 mapAlgorithmic(UChar32 c, uint16_t norm16) const {
return c+norm16-(minMaybeYes-MAX_DELTA-1);
return c+(norm16>>DELTA_SHIFT)-centerNoNoDelta;
}
UChar32 getAlgorithmicDelta(uint16_t norm16) const {
return (norm16>>DELTA_SHIFT)-centerNoNoDelta;
}
// Requires minYesNo<norm16<limitNoNo.
const uint16_t *getMapping(uint16_t norm16) const { return extraData+norm16; }
const uint16_t *getMapping(uint16_t norm16) const { return extraData+(norm16>>OFFSET_SHIFT); }
const uint16_t *getCompositionsListForDecompYes(uint16_t norm16) const {
if(norm16==0 || MIN_NORMAL_MAYBE_YES<=norm16) {
if(norm16<JAMO_L || MIN_NORMAL_MAYBE_YES<=norm16) {
return NULL;
} else if(norm16<minMaybeYes) {
return extraData+norm16; // for yesYes; if Jamo L: harmless empty list
return getMapping(norm16); // for yesYes; if Jamo L: harmless empty list
} else {
return maybeYesCompositions+norm16-minMaybeYes;
}
}
const uint16_t *getCompositionsListForComposite(uint16_t norm16) const {
const uint16_t *list=extraData+norm16; // composite has both mapping & compositions list
// A composite has both mapping & compositions list.
const uint16_t *list=getMapping(norm16);
return list+ // mapping pointer
1+ // +1 to skip the first unit with the mapping lenth
1+ // +1 to skip the first unit with the mapping length
(*list&MAPPING_LENGTH_MASK); // + mapping length
}
const uint16_t *getCompositionsListForMaybe(uint16_t norm16) const {
// minMaybeYes<=norm16<MIN_NORMAL_MAYBE_YES
return maybeYesCompositions+((norm16-minMaybeYes)>>OFFSET_SHIFT);
}
/**
* @param c code point must have compositions
* @return compositions list pointer
@ -563,46 +649,78 @@ private:
UChar32 minNeedDataCP,
ReorderingBuffer *buffer,
UErrorCode &errorCode) const;
UBool decomposeShort(const UChar *src, const UChar *limit,
ReorderingBuffer &buffer, UErrorCode &errorCode) const;
const UChar *decomposeShort(const UChar *src, const UChar *limit,
UBool stopAtCompBoundary, UBool onlyContiguous,
ReorderingBuffer &buffer, UErrorCode &errorCode) const;
UBool decompose(UChar32 c, uint16_t norm16,
ReorderingBuffer &buffer, UErrorCode &errorCode) const;
const uint8_t *decomposeShort(const uint8_t *src, const uint8_t *limit,
UBool stopAtCompBoundary, UBool onlyContiguous,
ReorderingBuffer &buffer, UErrorCode &errorCode) const;
static int32_t combine(const uint16_t *list, UChar32 trail);
void addComposites(const uint16_t *list, UnicodeSet &set) const;
void recompose(ReorderingBuffer &buffer, int32_t recomposeStartIndex,
UBool onlyContiguous) const;
UBool hasCompBoundaryBefore(UChar32 c, uint16_t norm16) const;
const UChar *findPreviousCompBoundary(const UChar *start, const UChar *p) const;
const UChar *findNextCompBoundary(const UChar *p, const UChar *limit) const;
UBool hasCompBoundaryBefore(UChar32 c, uint16_t norm16) const {
return c<minCompNoMaybeCP || norm16HasCompBoundaryBefore(norm16);
}
UBool norm16HasCompBoundaryBefore(uint16_t norm16) const {
return norm16 < minNoNoCompNoMaybeCC || isAlgorithmicNoNo(norm16);
}
UBool hasCompBoundaryBefore(const UChar *src, const UChar *limit) const;
UBool hasCompBoundaryBefore(const uint8_t *src, const uint8_t *limit) const;
UBool hasCompBoundaryAfter(const UChar *start, const UChar *p,
UBool onlyContiguous) const;
UBool hasCompBoundaryAfter(const uint8_t *start, const uint8_t *p,
UBool onlyContiguous) const;
UBool norm16HasCompBoundaryAfter(uint16_t norm16, UBool onlyContiguous) const {
return (norm16 & HAS_COMP_BOUNDARY_AFTER) != 0 &&
(!onlyContiguous || isTrailCC01ForCompBoundaryAfter(norm16));
}
/** For FCC: Given norm16 HAS_COMP_BOUNDARY_AFTER, does it have tccc<=1? */
UBool isTrailCC01ForCompBoundaryAfter(uint16_t norm16) const {
return isInert(norm16) || (isDecompNoAlgorithmic(norm16) ?
(norm16 & DELTA_TCCC_MASK) <= DELTA_TCCC_1 : *getMapping(norm16) <= 0x1ff);
}
const UChar *findPreviousCompBoundary(const UChar *start, const UChar *p, UBool onlyContiguous) const;
const UChar *findNextCompBoundary(const UChar *p, const UChar *limit, UBool onlyContiguous) const;
const UChar *findPreviousFCDBoundary(const UChar *start, const UChar *p) const;
const UChar *findNextFCDBoundary(const UChar *p, const UChar *limit) const;
void makeCanonIterDataFromNorm16(UChar32 start, UChar32 end, const uint16_t norm16,
CanonIterData &newData, UErrorCode &errorCode) const;
int32_t getCanonValue(UChar32 c) const;
const UnicodeSet &getCanonStartSet(int32_t n) const;
// UVersionInfo dataVersion;
// Code point thresholds for quick check codes.
UChar32 minDecompNoCP;
UChar32 minCompNoMaybeCP;
// BMP code point thresholds for quick check loops looking at single UTF-16 code units.
UChar minDecompNoCP;
UChar minCompNoMaybeCP;
UChar minLcccCP;
// Norm16 value thresholds for quick check combinations and types of extra data.
uint16_t minYesNo;
uint16_t minYesNoMappingsOnly;
uint16_t minNoNo;
uint16_t minNoNoCompBoundaryBefore;
uint16_t minNoNoCompNoMaybeCC;
uint16_t minNoNoEmpty;
uint16_t limitNoNo;
uint16_t centerNoNoDelta;
uint16_t minMaybeYes;
const UTrie2 *normTrie;
const UCPTrie *normTrie;
const uint16_t *maybeYesCompositions;
const uint16_t *extraData; // mappings and/or compositions for yesYes, yesNo & noNo characters
const uint8_t *smallFCD; // [0x100] one bit per 32 BMP code points, set if any FCD!=0
uint8_t tccc180[0x180]; // tccc values for U+0000..U+017F
public: // CanonIterData is public to allow access from C callback functions.
UInitOnce fCanonIterDataInitOnce;
CanonIterData *fCanonIterData;
};
@ -658,13 +776,14 @@ unorm_getFCD16(UChar32 c);
/**
* Format of Normalizer2 .nrm data files.
* Format version 2.0.
* Format version 4.0.
*
* Normalizer2 .nrm data files provide data for the Unicode Normalization algorithms.
* ICU ships with data files for standard Unicode Normalization Forms
* NFC and NFD (nfc.nrm), NFKC and NFKD (nfkc.nrm) and NFKC_Casefold (nfkc_cf.nrm).
* Custom (application-specific) data can be built into additional .nrm files
* with the gennorm2 build tool.
* ICU ships with one such file, uts46.nrm, for the implementation of UTS #46.
*
* Normalizer2.getInstance() causes a .nrm file to be loaded, unless it has been
* cached already. Internally, Normalizer2Impl.load() reads the .nrm file.
@ -695,27 +814,35 @@ unorm_getFCD16(UChar32 c);
* with a decomposition mapping, that is, with NF*D_QC=No.
* minCompNoMaybeCP=indexes[IX_MIN_COMP_NO_MAYBE_CP] is the lowest code point
* with NF*C_QC=No (has a one-way mapping) or Maybe (combines backward).
* minLcccCP=indexes[IX_MIN_LCCC_CP] (index 18, new in formatVersion 3)
* is the lowest code point with lccc!=0.
*
* The next five indexes are thresholds of 16-bit trie values for ranges of
* The next eight indexes are thresholds of 16-bit trie values for ranges of
* values indicating multiple normalization properties.
* They are listed here in threshold order, not in the order they are stored in the indexes.
* minYesNo=indexes[IX_MIN_YES_NO];
* minYesNoMappingsOnly=indexes[IX_MIN_YES_NO_MAPPINGS_ONLY];
* minNoNo=indexes[IX_MIN_NO_NO];
* minNoNoCompBoundaryBefore=indexes[IX_MIN_NO_NO_COMP_BOUNDARY_BEFORE];
* minNoNoCompNoMaybeCC=indexes[IX_MIN_NO_NO_COMP_NO_MAYBE_CC];
* minNoNoEmpty=indexes[IX_MIN_NO_NO_EMPTY];
* limitNoNo=indexes[IX_LIMIT_NO_NO];
* minMaybeYes=indexes[IX_MIN_MAYBE_YES];
* minYesNoMappingsOnly=indexes[IX_MIN_YES_NO_MAPPINGS_ONLY];
* See the normTrie description below and the design doc for details.
*
* UTrie2 normTrie; -- see utrie2_impl.h and utrie2.h
* UCPTrie normTrie; -- see ucptrie_impl.h and ucptrie.h, same as Java CodePointTrie
*
* The trie holds the main normalization data. Each code point is mapped to a 16-bit value.
* Rather than using independent bits in the value (which would require more than 16 bits),
* information is extracted primarily via range checks.
* Except, format version 3 uses bit 0 for hasCompBoundaryAfter().
* For example, a 16-bit value norm16 in the range minYesNo<=norm16<minNoNo
* means that the character has NF*C_QC=Yes and NF*D_QC=No properties,
* which means it has a two-way (round-trip) decomposition mapping.
* Values in the range 2<=norm16<limitNoNo are also directly indexes into the extraData
* pointing to mappings, compositions lists, or both.
* Value norm16==0 means that the character is normalization-inert, that is,
* Value norm16==INERT (0 in versions 1 & 2, 1 in version 3)
* means that the character is normalization-inert, that is,
* it does not have a mapping, does not participate in composition, has a zero
* canonical combining class, and forms a boundary where text before it and after it
* can be normalized independently.
@ -729,7 +856,7 @@ unorm_getFCD16(UChar32 c);
* The trie has a value for each lead surrogate code unit representing the "worst case"
* properties of the 1024 supplementary characters whose UTF-16 form starts with
* the lead surrogate. If all of the 1024 supplementary characters are normalization-inert,
* then their lead surrogate code unit has the trie value 0.
* then their lead surrogate code unit has the trie value INERT.
* When the lead surrogate unit's value exceeds the quick check minimum during processing,
* the properties for the full supplementary code point need to be looked up.
*
@ -738,6 +865,7 @@ unorm_getFCD16(UChar32 c);
*
* There is only one byte offset for the end of these two arrays.
* The split between them is given by the constant and variable mentioned above.
* In version 3, the difference must be shifted right by OFFSET_SHIFT.
*
* The maybeYesCompositions array contains compositions lists for characters that
* combine both forward (as starters in composition pairs)
@ -754,6 +882,8 @@ unorm_getFCD16(UChar32 c);
* followed by only mappings for "NoNo" characters.
* (Referring to pairs of NFC/NFD quick check values.)
* The norm16 values of those characters are directly indexes into the extraData array.
* In version 3, the norm16 values must be shifted right by OFFSET_SHIFT
* for accessing extraData.
*
* The data structures for compositions lists and mappings are described in the design doc.
*
@ -784,6 +914,64 @@ unorm_getFCD16(UChar32 c);
* This is fully equivalent with formatVersion 1's MAPPING_PLUS_COMPOSITION_LIST flag.
* It is needed for the new (in ICU 49) composePair(), not for other normalization.
* - Addition of the smallFCD[] bit set.
*
* Changes from format version 2 to format version 3 (ICU 60) ------------------
*
* - norm16 bit 0 indicates hasCompBoundaryAfter(),
* except that for contiguous composition (FCC) the tccc must be checked as well.
* Data indexes and ccc values are shifted left by one (OFFSET_SHIFT).
* Thresholds like minNoNo are tested before shifting.
*
* - Algorithmic mapping deltas are shifted left by two more bits (total DELTA_SHIFT),
* to make room for two bits (three values) indicating whether the tccc is 0, 1, or greater.
* See DELTA_TCCC_MASK etc.
* This helps with fetching tccc/FCD values and FCC hasCompBoundaryAfter().
* minMaybeYes is 8-aligned so that the DELTA_TCCC_MASK bits can be tested directly.
*
* - Algorithmic mappings are only used for mapping to "comp yes and ccc=0" characters,
* and ASCII characters are mapped algorithmically only to other ASCII characters.
* This helps with hasCompBoundaryBefore() and compose() fast paths.
* It is never necessary any more to loop for algorithmic mappings.
*
* - Addition of indexes[IX_MIN_NO_NO_COMP_BOUNDARY_BEFORE],
* indexes[IX_MIN_NO_NO_COMP_NO_MAYBE_CC], and indexes[IX_MIN_NO_NO_EMPTY],
* and separation of the noNo extraData into distinct ranges.
* With this, the noNo norm16 value indicates whether the mapping is
* compose-normalized, not normalized but hasCompBoundaryBefore(),
* not even that, or maps to an empty string.
* hasCompBoundaryBefore() can be determined solely from the norm16 value.
*
* - The norm16 value for Hangul LVT is now different from that for Hangul LV,
* so that hasCompBoundaryAfter() need not check for the syllable type.
* For Hangul LV, minYesNo continues to be used (no comp-boundary-after).
* For Hangul LVT, minYesNoMappingsOnly|HAS_COMP_BOUNDARY_AFTER is used.
* The extraData units at these indexes are set to firstUnit=2 and firstUnit=3, respectively,
* to simplify some code.
*
* - The extraData firstUnit bit 5 is no longer necessary
* (norm16 bit 0 used instead of firstUnit MAPPING_NO_COMP_BOUNDARY_AFTER),
* is reserved again, and always set to 0.
*
* - Addition of indexes[IX_MIN_LCCC_CP], the first code point where lccc!=0.
* This used to be hardcoded to U+0300, but in data like NFKC_Casefold it is lower:
* U+00AD Soft Hyphen maps to an empty string,
* which is artificially assigned "worst case" values lccc=1 and tccc=255.
*
* - A mapping to an empty string has explicit lccc=1 and tccc=255 values.
*
* Changes from format version 3 to format version 4 (ICU 63) ------------------
*
* Switched from UTrie2 to UCPTrie/CodePointTrie.
*
* The new trie no longer stores different values for surrogate code *units* vs.
* surrogate code *points*.
* Lead surrogates still have values for optimized UTF-16 string processing.
* When looking up code point properties, the code now checks for lead surrogates and
* treats them as inert.
*
* gennorm2 now has to reject mappings for surrogate code points.
* UTS #46 maps unpaired surrogates to U+FFFD in code rather than via its
* custom normalization data file.
*/
#endif /* !UCONFIG_NO_NORMALIZATION */

12
intl/icu/source/common/normlzr.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*************************************************************************
@ -23,6 +23,12 @@
#include "normalizer2impl.h"
#include "uprops.h" // for uniset_getUnicode32Instance()
#if defined(_ARM64_) && defined(move32)
// System can define move32 intrinsics, but the char iters define move32 method
// using same undef trick in headers, so undef here to re-enable the method.
#undef move32
#endif
U_NAMESPACE_BEGIN
UOBJECT_DEFINE_RTTI_IMPLEMENTATION(Normalizer)
@ -40,7 +46,7 @@ Normalizer::Normalizer(const UnicodeString& str, UNormalizationMode mode) :
init();
}
Normalizer::Normalizer(const UChar *str, int32_t length, UNormalizationMode mode) :
Normalizer::Normalizer(ConstChar16Ptr str, int32_t length, UNormalizationMode mode) :
UObject(), fFilteredNorm2(NULL), fNorm2(NULL), fUMode(mode), fOptions(0),
text(new UCharCharacterIterator(str, length)),
currentIndex(0), nextIndex(0),
@ -435,7 +441,7 @@ Normalizer::setText(const CharacterIterator& newText,
}
void
Normalizer::setText(const UChar* newText,
Normalizer::setText(ConstChar16Ptr newText,
int32_t length,
UErrorCode &status)
{

2
intl/icu/source/common/parsepos.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************

4
intl/icu/source/common/patternprops.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -6,7 +6,7 @@
* Corporation and others. All Rights Reserved.
*******************************************************************************
* file name: patternprops.cpp
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*

4
intl/icu/source/common/patternprops.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -6,7 +6,7 @@
* Corporation and others. All Rights Reserved.
*******************************************************************************
* file name: patternprops.h
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*

2
intl/icu/source/common/pluralmap.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
* Copyright (C) 2015, International Business Machines Corporation and

2
intl/icu/source/common/pluralmap.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************

2
intl/icu/source/common/propname.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************

2
intl/icu/source/common/propname.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************

1992
intl/icu/source/common/propname_data.h
View file

File diff suppressed because it is too large Load diff

6
intl/icu/source/common/propsvec.c → intl/icu/source/common/propsvec.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -8,7 +8,7 @@
*
*******************************************************************************
* file name: propsvec.c
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
@ -499,6 +499,8 @@ upvec_compactToUTrie2Handler(void *context,
UChar32 start, UChar32 end,
int32_t rowIndex, uint32_t *row, int32_t columns,
UErrorCode *pErrorCode) {
(void)row;
(void)columns;
UPVecToUTrie2Context *toUTrie2=(UPVecToUTrie2Context *)context;
if(start<UPVEC_FIRST_SPECIAL_CP) {
utrie2_setRange32(toUTrie2->trie, start, end, (uint32_t)rowIndex, TRUE, pErrorCode);

4
intl/icu/source/common/propsvec.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -8,7 +8,7 @@
*
*******************************************************************************
* file name: propsvec.h
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*

4
intl/icu/source/common/punycode.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -8,7 +8,7 @@
*
*******************************************************************************
* file name: punycode.cpp
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*

4
intl/icu/source/common/punycode.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -8,7 +8,7 @@
*
*******************************************************************************
* file name: punycode.h
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*

392
intl/icu/source/common/putil.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
@ -43,8 +43,24 @@
// Must be before any other #includes.
#include "uposixdefs.h"
/* include ICU headers */
#include "unicode/utypes.h"
// First, the platform type. Need this for U_PLATFORM.
#include "unicode/platform.h"
#if U_PLATFORM == U_PF_MINGW && defined __STRICT_ANSI__
/* tzset isn't defined in strict ANSI on MinGW. */
#undef __STRICT_ANSI__
#endif
/*
* Cygwin with GCC requires inclusion of time.h after the above disabling strict asci mode statement.
*/
#include <time.h>
#if !U_PLATFORM_USES_ONLY_WIN32_API
#include <sys/time.h>
#endif
/* include the rest of the ICU headers */
#include "unicode/putil.h"
#include "unicode/ustring.h"
#include "putilimp.h"
@ -76,14 +92,28 @@
* Should Cygwin be included as well (U_PLATFORM_HAS_WIN32_API)
* to use native APIs as much as possible?
*/
#ifndef WIN32_LEAN_AND_MEAN
# define WIN32_LEAN_AND_MEAN
#endif
# define VC_EXTRALEAN
# define NOUSER
# define NOSERVICE
# define NOIME
# define NOMCX
# include <windows.h>
# include "unicode/uloc.h"
# include "wintz.h"
#if U_PLATFORM_HAS_WINUWP_API
typedef PVOID LPMSG; // TODO: figure out how to get rid of this typedef
#include <Windows.Globalization.h>
#include <windows.system.userprofile.h>
#include <wrl/wrappers/corewrappers.h>
#include <wrl/client.h>
using namespace ABI::Windows::Foundation;
using namespace Microsoft::WRL;
using namespace Microsoft::WRL::Wrappers;
#endif
#elif U_PLATFORM == U_PF_OS400
# include <float.h>
# include <qusec.h> /* error code structure */
@ -104,20 +134,6 @@
# include <sys/neutrino.h>
#endif
#if (U_PF_MINGW <= U_PLATFORM && U_PLATFORM <= U_PF_CYGWIN) && defined(__STRICT_ANSI__)
/* tzset isn't defined in strict ANSI on Cygwin and MinGW. */
#undef __STRICT_ANSI__
#endif
/*
* Cygwin with GCC requires inclusion of time.h after the above disabling strict asci mode statement.
*/
#include <time.h>
#if !U_PLATFORM_USES_ONLY_WIN32_API
#include <sys/time.h>
#endif
/*
* Only include langinfo.h if we have a way to get the codeset. If we later
* depend on more feature, we can test on U_HAVE_NL_LANGINFO.
@ -516,6 +532,28 @@ uprv_fmin(double x, double y)
return (x > y ? y : x);
}
U_CAPI UBool U_EXPORT2
uprv_add32_overflow(int32_t a, int32_t b, int32_t* res) {
// NOTE: Some compilers (GCC, Clang) have primitives available, like __builtin_add_overflow.
// This function could be optimized by calling one of those primitives.
auto a64 = static_cast<int64_t>(a);
auto b64 = static_cast<int64_t>(b);
int64_t res64 = a64 + b64;
*res = static_cast<int32_t>(res64);
return res64 != *res;
}
U_CAPI UBool U_EXPORT2
uprv_mul32_overflow(int32_t a, int32_t b, int32_t* res) {
// NOTE: Some compilers (GCC, Clang) have primitives available, like __builtin_mul_overflow.
// This function could be optimized by calling one of those primitives.
auto a64 = static_cast<int64_t>(a);
auto b64 = static_cast<int64_t>(b);
int64_t res64 = a64 * b64;
*res = static_cast<int32_t>(res64);
return res64 != *res;
}
/**
* Truncates the given double.
* trunc(3.3) = 3.0, trunc (-3.3) = -3.0
@ -651,13 +689,23 @@ uprv_timezone()
/* Note that U_TZNAME does *not* have to be tzname, but if it is,
some platforms need to have it declared here. */
#if defined(U_TZNAME) && (U_PLATFORM == U_PF_IRIX || U_PLATFORM_IS_DARWIN_BASED || (U_PLATFORM == U_PF_CYGWIN && !U_PLATFORM_USES_ONLY_WIN32_API))
#if defined(U_TZNAME) && (U_PLATFORM == U_PF_IRIX || U_PLATFORM_IS_DARWIN_BASED)
/* RS6000 and others reject char **tzname. */
extern U_IMPORT char *U_TZNAME[];
#endif
#if !UCONFIG_NO_FILE_IO && ((U_PLATFORM_IS_DARWIN_BASED && (U_PLATFORM != U_PF_IPHONE || defined(U_TIMEZONE))) || U_PLATFORM_IS_LINUX_BASED || U_PLATFORM == U_PF_BSD || U_PLATFORM == U_PF_SOLARIS)
/* These platforms are likely to use Olson timezone IDs. */
/* common targets of the symbolic link at TZDEFAULT are:
* "/usr/share/zoneinfo/<olsonID>" default, older Linux distros, macOS to 10.12
* "../usr/share/zoneinfo/<olsonID>" newer Linux distros: Red Hat Enterprise Linux 7, Ubuntu 16, SuSe Linux 12
* "/usr/share/lib/zoneinfo/<olsonID>" Solaris
* "../usr/share/lib/zoneinfo/<olsonID>" Solaris
* "/var/db/timezone/zoneinfo/<olsonID>" macOS 10.13
* To avoid checking lots of paths, just check that the target path
* before the <olsonID> ends with "/zoneinfo/", and the <olsonID> is valid.
*/
#define CHECK_LOCALTIME_LINK 1
#if U_PLATFORM_IS_DARWIN_BASED
#include <tzfile.h>
@ -665,12 +713,12 @@ extern U_IMPORT char *U_TZNAME[];
#elif U_PLATFORM == U_PF_SOLARIS
#define TZDEFAULT "/etc/localtime"
#define TZZONEINFO "/usr/share/lib/zoneinfo/"
#define TZZONEINFO2 "../usr/share/lib/zoneinfo/"
#define TZ_ENV_CHECK "localtime"
#else
#define TZDEFAULT "/etc/localtime"
#define TZZONEINFO "/usr/share/zoneinfo/"
#endif
#define TZZONEINFOTAIL "/zoneinfo/"
#if U_HAVE_DIRENT_H
#define TZFILE_SKIP "posixrules" /* tz file to skip when searching. */
/* Some Linux distributions have 'localtime' in /usr/share/zoneinfo
@ -922,30 +970,30 @@ static CharString *gSearchTZFileResult = NULL;
* This function is not thread safe - it uses a global, gSearchTZFileResult, to hold its results.
*/
static char* searchForTZFile(const char* path, DefaultTZInfo* tzInfo) {
DIR* dirp = opendir(path);
DIR* subDirp = NULL;
DIR* dirp = NULL;
struct dirent* dirEntry = NULL;
char* result = NULL;
UErrorCode status = U_ZERO_ERROR;
/* Save the current path */
CharString curpath(path, -1, status);
if (U_FAILURE(status)) {
goto cleanupAndReturn;
}
dirp = opendir(path);
if (dirp == NULL) {
return result;
goto cleanupAndReturn;
}
if (gSearchTZFileResult == NULL) {
gSearchTZFileResult = new CharString;
if (gSearchTZFileResult == NULL) {
return NULL;
goto cleanupAndReturn;
}
ucln_common_registerCleanup(UCLN_COMMON_PUTIL, putil_cleanup);
}
/* Save the current path */
UErrorCode status = U_ZERO_ERROR;
CharString curpath(path, -1, status);
if (U_FAILURE(status)) {
return NULL;
}
/* Check each entry in the directory. */
while((dirEntry = readdir(dirp)) != NULL) {
const char* dirName = dirEntry->d_name;
@ -954,15 +1002,16 @@ static char* searchForTZFile(const char* path, DefaultTZInfo* tzInfo) {
CharString newpath(curpath, status);
newpath.append(dirName, -1, status);
if (U_FAILURE(status)) {
return NULL;
break;
}
DIR* subDirp = NULL;
if ((subDirp = opendir(newpath.data())) != NULL) {
/* If this new path is a directory, make a recursive call with the newpath. */
closedir(subDirp);
newpath.append('/', status);
if (U_FAILURE(status)) {
return NULL;
break;
}
result = searchForTZFile(newpath.data(), tzInfo);
/*
@ -986,7 +1035,7 @@ static char* searchForTZFile(const char* path, DefaultTZInfo* tzInfo) {
gSearchTZFileResult->clear();
gSearchTZFileResult->append(zoneid, -1, status);
if (U_FAILURE(status)) {
return NULL;
break;
}
result = gSearchTZFileResult->data();
/* Get out after the first one found. */
@ -995,7 +1044,11 @@ static char* searchForTZFile(const char* path, DefaultTZInfo* tzInfo) {
}
}
}
closedir(dirp);
cleanupAndReturn:
if (dirp) {
closedir(dirp);
}
return result;
}
#endif
@ -1011,6 +1064,7 @@ uprv_tzname_clear_cache()
U_CAPI const char* U_EXPORT2
uprv_tzname(int n)
{
(void)n; // Avoid unreferenced parameter warning.
const char *tzid = NULL;
#if U_PLATFORM_USES_ONLY_WIN32_API
tzid = uprv_detectWindowsTimeZone();
@ -1018,6 +1072,15 @@ uprv_tzname(int n)
if (tzid != NULL) {
return tzid;
}
#ifndef U_TZNAME
// The return value is free'd in timezone.cpp on Windows because
// the other code path returns a pointer to a heap location.
// If we don't have a name already, then tzname wouldn't be any
// better, so just fall back.
return uprv_strdup("Etc/UTC");
#endif // !U_TZNAME
#else
/*#if U_PLATFORM_IS_DARWIN_BASED
@ -1059,24 +1122,15 @@ uprv_tzname(int n)
*/
int32_t ret = (int32_t)readlink(TZDEFAULT, gTimeZoneBuffer, sizeof(gTimeZoneBuffer)-1);
if (0 < ret) {
int32_t tzZoneInfoLen = uprv_strlen(TZZONEINFO);
int32_t tzZoneInfoTailLen = uprv_strlen(TZZONEINFOTAIL);
gTimeZoneBuffer[ret] = 0;
if (uprv_strncmp(gTimeZoneBuffer, TZZONEINFO, tzZoneInfoLen) == 0
&& isValidOlsonID(gTimeZoneBuffer + tzZoneInfoLen))
char * tzZoneInfoTailPtr = uprv_strstr(gTimeZoneBuffer, TZZONEINFOTAIL);
if (tzZoneInfoTailPtr != NULL
&& isValidOlsonID(tzZoneInfoTailPtr + tzZoneInfoTailLen))
{
return (gTimeZoneBufferPtr = gTimeZoneBuffer + tzZoneInfoLen);
return (gTimeZoneBufferPtr = tzZoneInfoTailPtr + tzZoneInfoTailLen);
}
#if U_PLATFORM == U_PF_SOLARIS
else
{
tzZoneInfoLen = uprv_strlen(TZZONEINFO2);
if (uprv_strncmp(gTimeZoneBuffer, TZZONEINFO2, tzZoneInfoLen) == 0
&& isValidOlsonID(gTimeZoneBuffer + tzZoneInfoLen))
{
return (gTimeZoneBufferPtr = gTimeZoneBuffer + tzZoneInfoLen);
}
}
#endif
} else {
#if defined(SEARCH_TZFILE)
DefaultTZInfo* tzInfo = (DefaultTZInfo*)uprv_malloc(sizeof(DefaultTZInfo));
@ -1162,7 +1216,8 @@ UInitOnce gTimeZoneFilesInitOnce = U_INITONCE_INITIALIZER;
static CharString *gTimeZoneFilesDirectory = NULL;
#if U_POSIX_LOCALE || U_PLATFORM_USES_ONLY_WIN32_API
static char *gCorrectedPOSIXLocale = NULL; /* Heap allocated */
static const char *gCorrectedPOSIXLocale = NULL; /* Sometimes heap allocated */
static bool gCorrectedPOSIXLocaleHeapAllocated = false;
#endif
static UBool U_CALLCONV putil_cleanup(void)
@ -1183,9 +1238,10 @@ static UBool U_CALLCONV putil_cleanup(void)
#endif
#if U_POSIX_LOCALE || U_PLATFORM_USES_ONLY_WIN32_API
if (gCorrectedPOSIXLocale) {
uprv_free(gCorrectedPOSIXLocale);
if (gCorrectedPOSIXLocale && gCorrectedPOSIXLocaleHeapAllocated) {
uprv_free(const_cast<char *>(gCorrectedPOSIXLocale));
gCorrectedPOSIXLocale = NULL;
gCorrectedPOSIXLocaleHeapAllocated = false;
}
#endif
return TRUE;
@ -1219,7 +1275,7 @@ u_setDataDirectory(const char *directory) {
#if (U_FILE_SEP_CHAR != U_FILE_ALT_SEP_CHAR)
{
char *p;
while(p = uprv_strchr(newDataDir, U_FILE_ALT_SEP_CHAR)) {
while((p = uprv_strchr(newDataDir, U_FILE_ALT_SEP_CHAR)) != NULL) {
*p = U_FILE_SEP_CHAR;
}
}
@ -1269,6 +1325,43 @@ uprv_pathIsAbsolute(const char *path)
# endif
#endif
#if U_PLATFORM_HAS_WINUWP_API != 0
// Helper function to get the ICU Data Directory under the Windows directory location.
static BOOL U_CALLCONV getIcuDataDirectoryUnderWindowsDirectory(char* directoryBuffer, UINT bufferLength)
{
#if defined(ICU_DATA_DIR_WINDOWS)
wchar_t windowsPath[MAX_PATH];
char windowsPathUtf8[MAX_PATH];
UINT length = GetSystemWindowsDirectoryW(windowsPath, UPRV_LENGTHOF(windowsPath));
if ((length > 0) && (length < (UPRV_LENGTHOF(windowsPath) - 1))) {
// Convert UTF-16 to a UTF-8 string.
UErrorCode status = U_ZERO_ERROR;
int32_t windowsPathUtf8Len = 0;
u_strToUTF8(windowsPathUtf8, static_cast<int32_t>(UPRV_LENGTHOF(windowsPathUtf8)),
&windowsPathUtf8Len, reinterpret_cast<const UChar*>(windowsPath), -1, &status);
if (U_SUCCESS(status) && (status != U_STRING_NOT_TERMINATED_WARNING) &&
(windowsPathUtf8Len < (UPRV_LENGTHOF(windowsPathUtf8) - 1))) {
// Ensure it always has a separator, so we can append the ICU data path.
if (windowsPathUtf8[windowsPathUtf8Len - 1] != U_FILE_SEP_CHAR) {
windowsPathUtf8[windowsPathUtf8Len++] = U_FILE_SEP_CHAR;
windowsPathUtf8[windowsPathUtf8Len] = '\0';
}
// Check if the concatenated string will fit.
if ((windowsPathUtf8Len + UPRV_LENGTHOF(ICU_DATA_DIR_WINDOWS)) < bufferLength) {
uprv_strcpy(directoryBuffer, windowsPathUtf8);
uprv_strcat(directoryBuffer, ICU_DATA_DIR_WINDOWS);
return TRUE;
}
}
}
#endif
return FALSE;
}
#endif
static void U_CALLCONV dataDirectoryInitFn() {
/* If we already have the directory, then return immediately. Will happen if user called
* u_setDataDirectory().
@ -1297,7 +1390,9 @@ static void U_CALLCONV dataDirectoryInitFn() {
*/
# if !defined(ICU_NO_USER_DATA_OVERRIDE) && !UCONFIG_NO_FILE_IO
/* First try to get the environment variable */
path=getenv("ICU_DATA");
# if U_PLATFORM_HAS_WINUWP_API == 0 // Windows UWP does not support getenv
path=getenv("ICU_DATA");
# endif
# endif
/* ICU_DATA_DIR may be set as a compile option.
@ -1326,9 +1421,21 @@ static void U_CALLCONV dataDirectoryInitFn() {
}
#endif
#if U_PLATFORM_HAS_WINUWP_API != 0 && defined(ICU_DATA_DIR_WINDOWS)
char datadir_path_buffer[MAX_PATH];
if (getIcuDataDirectoryUnderWindowsDirectory(datadir_path_buffer, UPRV_LENGTHOF(datadir_path_buffer))) {
path = datadir_path_buffer;
}
#endif
if(path==NULL) {
/* It looks really bad, set it to something. */
#if U_PLATFORM_HAS_WIN32_API
// Windows UWP will require icudtl.dat file in same directory as icuuc.dll
path = ".\\";
#else
path = "";
#endif
}
u_setDataDirectory(path);
@ -1349,7 +1456,7 @@ static void setTimeZoneFilesDir(const char *path, UErrorCode &status) {
gTimeZoneFilesDirectory->append(path, status);
#if (U_FILE_SEP_CHAR != U_FILE_ALT_SEP_CHAR)
char *p = gTimeZoneFilesDirectory->data();
while (p = uprv_strchr(p, U_FILE_ALT_SEP_CHAR)) {
while ((p = uprv_strchr(p, U_FILE_ALT_SEP_CHAR)) != NULL) {
*p = U_FILE_SEP_CHAR;
}
#endif
@ -1366,15 +1473,30 @@ static void U_CALLCONV TimeZoneDataDirInitFn(UErrorCode &status) {
status = U_MEMORY_ALLOCATION_ERROR;
return;
}
const char *dir = getenv("ICU_TIMEZONE_FILES_DIR");
const char *dir = "";
#if U_PLATFORM_HAS_WINUWP_API != 0
// The UWP version does not support the environment variable setting, but can possibly pick them up from the Windows directory.
char datadir_path_buffer[MAX_PATH];
if (getIcuDataDirectoryUnderWindowsDirectory(datadir_path_buffer, UPRV_LENGTHOF(datadir_path_buffer))) {
dir = datadir_path_buffer;
}
#else
dir = getenv("ICU_TIMEZONE_FILES_DIR");
#endif // U_PLATFORM_HAS_WINUWP_API
#if defined(U_TIMEZONE_FILES_DIR)
if (dir == NULL) {
// Build time configuration setting.
dir = TO_STRING(U_TIMEZONE_FILES_DIR);
}
#endif
if (dir == NULL) {
dir = "";
}
setTimeZoneFilesDir(dir, status);
}
@ -1546,7 +1668,8 @@ The leftmost codepage (.xxx) wins.
/* Note that we scan the *uncorrected* ID. */
if ((p = uprv_strrchr(posixID, '@')) != NULL) {
if (correctedPOSIXLocale == NULL) {
correctedPOSIXLocale = static_cast<char *>(uprv_malloc(uprv_strlen(posixID)+1));
/* new locale can be 1 char longer than old one if @ -> __ */
correctedPOSIXLocale = static_cast<char *>(uprv_malloc(uprv_strlen(posixID)+2));
/* Exit on memory allocation error. */
if (correctedPOSIXLocale == NULL) {
return NULL;
@ -1563,7 +1686,7 @@ The leftmost codepage (.xxx) wins.
}
if (uprv_strchr(correctedPOSIXLocale,'_') == NULL) {
uprv_strcat(correctedPOSIXLocale, "__"); /* aa@b -> aa__b */
uprv_strcat(correctedPOSIXLocale, "__"); /* aa@b -> aa__b (note this can make the new locale 1 char longer) */
}
else {
uprv_strcat(correctedPOSIXLocale, "_"); /* aa_CC@b -> aa_CC_b */
@ -1603,6 +1726,7 @@ The leftmost codepage (.xxx) wins.
if (gCorrectedPOSIXLocale == NULL) {
gCorrectedPOSIXLocale = correctedPOSIXLocale;
gCorrectedPOSIXLocaleHeapAllocated = true;
ucln_common_registerCleanup(UCLN_COMMON_PUTIL, putil_cleanup);
correctedPOSIXLocale = NULL;
}
@ -1616,27 +1740,71 @@ The leftmost codepage (.xxx) wins.
#elif U_PLATFORM_USES_ONLY_WIN32_API
#define POSIX_LOCALE_CAPACITY 64
UErrorCode status = U_ZERO_ERROR;
char *correctedPOSIXLocale = 0;
char *correctedPOSIXLocale = nullptr;
if (gCorrectedPOSIXLocale != NULL) {
// If we have already figured this out just use the cached value
if (gCorrectedPOSIXLocale != nullptr) {
return gCorrectedPOSIXLocale;
}
LCID id = GetThreadLocale();
correctedPOSIXLocale = static_cast<char *>(uprv_malloc(POSIX_LOCALE_CAPACITY + 1));
if (correctedPOSIXLocale) {
int32_t posixLen = uprv_convertToPosix(id, correctedPOSIXLocale, POSIX_LOCALE_CAPACITY, &status);
if (U_SUCCESS(status)) {
*(correctedPOSIXLocale + posixLen) = 0;
gCorrectedPOSIXLocale = correctedPOSIXLocale;
ucln_common_registerCleanup(UCLN_COMMON_PUTIL, putil_cleanup);
} else {
uprv_free(correctedPOSIXLocale);
// No cached value, need to determine the current value
static WCHAR windowsLocale[LOCALE_NAME_MAX_LENGTH] = {};
int length = GetLocaleInfoEx(LOCALE_NAME_USER_DEFAULT, LOCALE_SNAME, windowsLocale, LOCALE_NAME_MAX_LENGTH);
// Now we should have a Windows locale name that needs converted to the POSIX style.
if (length > 0) // If length is 0, then the GetLocaleInfoEx failed.
{
// First we need to go from UTF-16 to char (and also convert from _ to - while we're at it.)
char modifiedWindowsLocale[LOCALE_NAME_MAX_LENGTH] = {};
int32_t i;
for (i = 0; i < UPRV_LENGTHOF(modifiedWindowsLocale); i++)
{
if (windowsLocale[i] == '_')
{
modifiedWindowsLocale[i] = '-';
}
else
{
modifiedWindowsLocale[i] = static_cast<char>(windowsLocale[i]);
}
if (modifiedWindowsLocale[i] == '\0')
{
break;
}
}
if (i >= UPRV_LENGTHOF(modifiedWindowsLocale))
{
// Ran out of room, can't really happen, maybe we'll be lucky about a matching
// locale when tags are dropped
modifiedWindowsLocale[UPRV_LENGTHOF(modifiedWindowsLocale) - 1] = '\0';
}
// Now normalize the resulting name
correctedPOSIXLocale = static_cast<char *>(uprv_malloc(POSIX_LOCALE_CAPACITY + 1));
/* TODO: Should we just exit on memory allocation failure? */
if (correctedPOSIXLocale)
{
int32_t posixLen = uloc_canonicalize(modifiedWindowsLocale, correctedPOSIXLocale, POSIX_LOCALE_CAPACITY, &status);
if (U_SUCCESS(status))
{
*(correctedPOSIXLocale + posixLen) = 0;
gCorrectedPOSIXLocale = correctedPOSIXLocale;
gCorrectedPOSIXLocaleHeapAllocated = true;
ucln_common_registerCleanup(UCLN_COMMON_PUTIL, putil_cleanup);
}
else
{
uprv_free(correctedPOSIXLocale);
}
}
}
if (gCorrectedPOSIXLocale == NULL) {
return "en_US";
// If unable to find a locale we can agree upon, use en-US by default
if (gCorrectedPOSIXLocale == nullptr) {
gCorrectedPOSIXLocale = "en_US";
}
return gCorrectedPOSIXLocale;
@ -1923,8 +2091,34 @@ int_getDefaultCodepage()
#elif U_PLATFORM_USES_ONLY_WIN32_API
static char codepage[64];
sprintf(codepage, "windows-%d", GetACP());
return codepage;
DWORD codepageNumber = 0;
#if U_PLATFORM_HAS_WINUWP_API > 0
// UWP doesn't have a direct API to get the default ACP as Microsoft would rather
// have folks use Unicode than a "system" code page, however this is the same
// codepage as the system default locale codepage. (FWIW, the system locale is
// ONLY used for codepage, it should never be used for anything else)
GetLocaleInfoEx(LOCALE_NAME_SYSTEM_DEFAULT, LOCALE_IDEFAULTANSICODEPAGE | LOCALE_RETURN_NUMBER,
(LPWSTR)&codepageNumber, sizeof(codepageNumber) / sizeof(WCHAR));
#else
// Win32 apps can call GetACP
codepageNumber = GetACP();
#endif
// Special case for UTF-8
if (codepageNumber == 65001)
{
return "UTF-8";
}
// Windows codepages can look like windows-1252, so format the found number
// the numbers are eclectic, however all valid system code pages, besides UTF-8
// are between 3 and 19999
if (codepageNumber > 0 && codepageNumber < 20000)
{
sprintf(codepage, "windows-%ld", codepageNumber);
return codepage;
}
// If the codepage number call failed then return UTF-8
return "UTF-8";
#elif U_POSIX_LOCALE
static char codesetName[100];
@ -2108,19 +2302,16 @@ u_getVersion(UVersionInfo versionArray) {
* icucfg.h dependent code
*/
#if U_ENABLE_DYLOAD
#if HAVE_DLOPEN && !U_PLATFORM_USES_ONLY_WIN32_API
#if U_ENABLE_DYLOAD && HAVE_DLOPEN && !U_PLATFORM_USES_ONLY_WIN32_API
#if HAVE_DLFCN_H
#ifdef __MVS__
#ifndef __SUSV3
#define __SUSV3 1
#endif
#endif
#include <dlfcn.h>
#endif
#endif /* HAVE_DLFCN_H */
U_INTERNAL void * U_EXPORT2
uprv_dl_open(const char *libName, UErrorCode *status) {
@ -2160,38 +2351,10 @@ uprv_dlsym_func(void *lib, const char* sym, UErrorCode *status) {
return uret.fp;
}
#else
#elif U_ENABLE_DYLOAD && U_PLATFORM_USES_ONLY_WIN32_API && !U_PLATFORM_HAS_WINUWP_API
/* null (nonexistent) implementation. */
U_INTERNAL void * U_EXPORT2
uprv_dl_open(const char *libName, UErrorCode *status) {
if(U_FAILURE(*status)) return NULL;
*status = U_UNSUPPORTED_ERROR;
return NULL;
}
U_INTERNAL void U_EXPORT2
uprv_dl_close(void *lib, UErrorCode *status) {
if(U_FAILURE(*status)) return;
*status = U_UNSUPPORTED_ERROR;
return;
}
U_INTERNAL UVoidFunction* U_EXPORT2
uprv_dlsym_func(void *lib, const char* sym, UErrorCode *status) {
if(U_SUCCESS(*status)) {
*status = U_UNSUPPORTED_ERROR;
}
return (UVoidFunction*)NULL;
}
#endif
#elif U_PLATFORM_USES_ONLY_WIN32_API
/* Windows API implementation. */
// Note: UWP does not expose/allow these APIs, so the UWP version gets the null implementation. */
U_INTERNAL void * U_EXPORT2
uprv_dl_open(const char *libName, UErrorCode *status) {
@ -2218,7 +2381,6 @@ uprv_dl_close(void *lib, UErrorCode *status) {
return;
}
U_INTERNAL UVoidFunction* U_EXPORT2
uprv_dlsym_func(void *lib, const char* sym, UErrorCode *status) {
HMODULE handle = (HMODULE)lib;
@ -2240,10 +2402,9 @@ uprv_dlsym_func(void *lib, const char* sym, UErrorCode *status) {
return addr;
}
#else
/* No dynamic loading set. */
/* No dynamic loading, null (nonexistent) implementation. */
U_INTERNAL void * U_EXPORT2
uprv_dl_open(const char *libName, UErrorCode *status) {
@ -2261,7 +2422,6 @@ uprv_dl_close(void *lib, UErrorCode *status) {
return;
}
U_INTERNAL UVoidFunction* U_EXPORT2
uprv_dlsym_func(void *lib, const char* sym, UErrorCode *status) {
(void)lib;
@ -2272,7 +2432,7 @@ uprv_dlsym_func(void *lib, const char* sym, UErrorCode *status) {
return (UVoidFunction*)NULL;
}
#endif /* U_ENABLE_DYLOAD */
#endif
/*
* Hey, Emacs, please set the following:

138
intl/icu/source/common/putilimp.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
@ -72,22 +72,13 @@
typedef size_t uintptr_t;
#endif
/**
* \def U_HAVE_MSVC_2003_OR_EARLIER
* Flag for workaround of MSVC 2003 optimization bugs
* @internal
*/
#if !defined(U_HAVE_MSVC_2003_OR_EARLIER) && defined(_MSC_VER) && (_MSC_VER < 1400)
#define U_HAVE_MSVC_2003_OR_EARLIER
#endif
/*===========================================================================*/
/** @{ Information about POSIX support */
/*===========================================================================*/
#ifdef U_HAVE_NL_LANGINFO_CODESET
/* Use the predefined value. */
#elif U_PLATFORM_HAS_WIN32_API || U_PLATFORM == U_PF_ANDROID || U_PLATFORM == U_PF_QNX
#elif U_PLATFORM_USES_ONLY_WIN32_API || U_PLATFORM == U_PF_ANDROID || U_PLATFORM == U_PF_QNX
# define U_HAVE_NL_LANGINFO_CODESET 0
#else
# define U_HAVE_NL_LANGINFO_CODESET 1
@ -103,10 +94,13 @@ typedef size_t uintptr_t;
# define U_NL_LANGINFO_CODESET CODESET
#endif
#ifdef U_TZSET
#if defined(U_TZSET) || defined(U_HAVE_TZSET)
/* Use the predefined value. */
#elif U_PLATFORM_USES_ONLY_WIN32_API
// UWP doesn't support tzset or environment variables for tz
#if U_PLATFORM_HAS_WINUWP_API == 0
# define U_TZSET _tzset
#endif
#elif U_PLATFORM == U_PF_OS400
/* not defined */
#else
@ -117,15 +111,15 @@ typedef size_t uintptr_t;
/* Use the predefined value. */
#elif U_PLATFORM == U_PF_ANDROID
# define U_TIMEZONE timezone
#elif defined(__UCLIBC__)
// uClibc does not have __timezone or _timezone.
#elif defined(_NEWLIB_VERSION)
# define U_TIMEZONE _timezone
#elif defined(__GLIBC__)
// glibc
# define U_TIMEZONE __timezone
#elif U_PLATFORM_IS_LINUX_BASED
# if defined(__UCLIBC__)
/* uClibc does not have __timezone or _timezone. */
# elif defined(_NEWLIB_VERSION)
# define U_TIMEZONE _timezone
# elif defined(__GLIBC__)
/* glibc */
# define U_TIMEZONE __timezone
# endif
// not defined
#elif U_PLATFORM_USES_ONLY_WIN32_API
# define U_TIMEZONE _timezone
#elif U_PLATFORM == U_PF_BSD && !defined(__NetBSD__)
@ -138,10 +132,13 @@ typedef size_t uintptr_t;
# define U_TIMEZONE timezone
#endif
#ifdef U_TZNAME
#if defined(U_TZNAME) || defined(U_HAVE_TZNAME)
/* Use the predefined value. */
#elif U_PLATFORM_USES_ONLY_WIN32_API
/* not usable on all windows platforms */
#if U_PLATFORM_HAS_WINUWP_API == 0
# define U_TZNAME _tzname
#endif
#elif U_PLATFORM == U_PF_OS400
/* not defined */
#else
@ -207,33 +204,21 @@ typedef size_t uintptr_t;
/**
* \def U_HAVE_STD_ATOMICS
* Defines whether the standard C++11 <atomic> is available.
* ICU will use this when avialable,
* otherwise will fall back to compiler or platform specific alternatives.
* Defines whether to use the standard C++11 <atomic> functions
* If false, ICU will fall back to compiler or platform specific alternatives.
* Note: support for these fall back options for atomics will be removed in a future version
* of ICU, and the use of C++ 11 atomics will be required.
* @internal
*/
#ifdef U_HAVE_STD_ATOMICS
/* Use the predefined value. */
#elif U_CPLUSPLUS_VERSION < 11
/* Not C++11, disable use of atomics */
# define U_HAVE_STD_ATOMICS 0
#elif __clang__ && __clang_major__==3 && __clang_minor__<=1
/* Clang 3.1, has atomic variable initializer bug. */
# define U_HAVE_STD_ATOMICS 0
#else
/* U_HAVE_ATOMIC is typically set by an autoconf test of #include <atomic> */
/* Can be set manually, or left undefined, on platforms without autoconf. */
# if defined(U_HAVE_ATOMIC) && U_HAVE_ATOMIC
# define U_HAVE_STD_ATOMICS 1
# else
# define U_HAVE_STD_ATOMICS 0
# endif
#else
# define U_HAVE_STD_ATOMICS 1
#endif
/**
* \def U_HAVE_CLANG_ATOMICS
* Defines whether Clang c11 style built-in atomics are avaialable.
* Defines whether Clang c11 style built-in atomics are available.
* These are used in preference to gcc atomics when both are available.
*/
#ifdef U_HAVE_CLANG_ATOMICS
@ -271,7 +256,7 @@ typedef size_t uintptr_t;
/**
* Platform utilities isolates the platform dependencies of the
* libarary. For each platform which this code is ported to, these
* library. For each platform which this code is ported to, these
* functions may have to be re-implemented.
*/
@ -394,6 +379,32 @@ U_INTERNAL double U_EXPORT2 uprv_log(double d);
*/
U_INTERNAL double U_EXPORT2 uprv_round(double x);
/**
* Adds the signed integers a and b, storing the result in res.
* Checks for signed integer overflow.
* Similar to the GCC/Clang extension __builtin_add_overflow
*
* @param a The first operand.
* @param b The second operand.
* @param res a + b
* @return true if overflow occurred; false if no overflow occurred.
* @internal
*/
U_INTERNAL UBool U_EXPORT2 uprv_add32_overflow(int32_t a, int32_t b, int32_t* res);
/**
* Multiplies the signed integers a and b, storing the result in res.
* Checks for signed integer overflow.
* Similar to the GCC/Clang extension __builtin_mul_overflow
*
* @param a The first multiplicand.
* @param b The second multiplicand.
* @param res a * b
* @return true if overflow occurred; false if no overflow occurred.
* @internal
*/
U_INTERNAL UBool U_EXPORT2 uprv_mul32_overflow(int32_t a, int32_t b, int32_t* res);
#if 0
/**
* Returns the number of digits after the decimal point in a double number x.
@ -419,7 +430,7 @@ U_INTERNAL const char* U_EXPORT2 uprv_getDefaultCodepage(void);
/**
* Please use uloc_getDefault() instead.
* Return the default locale ID string by querying ths system, or
* Return the default locale ID string by querying the system, or
* zero if one cannot be found.
* This function can call setlocale() on Unix platforms. Please read the
* platform documentation on setlocale() before calling this function.
@ -563,6 +574,49 @@ U_INTERNAL void * U_EXPORT2 uprv_maximumPtr(void *base);
# endif
#endif
#ifdef __cplusplus
/**
* Pin a buffer capacity such that doing pointer arithmetic
* on the destination pointer and capacity cannot overflow.
*
* The pinned capacity must fulfill the following conditions (for positive capacities):
* - dest + capacity is a valid pointer according to the machine arcitecture (AS/400, 64-bit, etc.)
* - (dest + capacity) >= dest
* - The size (in bytes) of T[capacity] does not exceed 0x7fffffff
*
* @param dest the destination buffer pointer.
* @param capacity the requested buffer capacity, in units of type T.
* @return the pinned capacity.
* @internal
*/
template <typename T>
inline int32_t pinCapacity(T *dest, int32_t capacity) {
if (capacity <= 0) { return capacity; }
uintptr_t destInt = (uintptr_t)dest;
uintptr_t maxInt;
# if U_PLATFORM == U_PF_OS390 && !defined(_LP64)
// We have 31-bit pointers.
maxInt = 0x7fffffff;
# elif U_PLATFORM == U_PF_OS400
maxInt = (uintptr_t)uprv_maximumPtr((void *)dest);
# else
maxInt = destInt + 0x7fffffffu;
if (maxInt < destInt) {
// Less than 2GB to the end of the address space.
// Pin to that to prevent address overflow.
maxInt = (uintptr_t)-1;
}
# endif
uintptr_t maxBytes = maxInt - destInt; // max. 2GB
int32_t maxCapacity = (int32_t)(maxBytes / sizeof(T));
return capacity <= maxCapacity ? capacity : maxCapacity;
}
#endif // __cplusplus
/* Dynamic Library Functions */
typedef void (UVoidFunction)(void);

1249
intl/icu/source/common/rbbi.cpp
View file

File diff suppressed because it is too large Load diff

658
intl/icu/source/common/rbbi_cache.cpp Normal file
View file

@ -0,0 +1,658 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// file: rbbi_cache.cpp
#include "unicode/utypes.h"
#if !UCONFIG_NO_BREAK_ITERATION
#include "unicode/ubrk.h"
#include "unicode/rbbi.h"
#include "rbbi_cache.h"
#include "brkeng.h"
#include "cmemory.h"
#include "rbbidata.h"
#include "rbbirb.h"
#include "uassert.h"
#include "uvectr32.h"
U_NAMESPACE_BEGIN
/*
* DictionaryCache implementation
*/
RuleBasedBreakIterator::DictionaryCache::DictionaryCache(RuleBasedBreakIterator *bi, UErrorCode &status) :
fBI(bi), fBreaks(status), fPositionInCache(-1),
fStart(0), fLimit(0), fFirstRuleStatusIndex(0), fOtherRuleStatusIndex(0) {
}
RuleBasedBreakIterator::DictionaryCache::~DictionaryCache() {
}
void RuleBasedBreakIterator::DictionaryCache::reset() {
fPositionInCache = -1;
fStart = 0;
fLimit = 0;
fFirstRuleStatusIndex = 0;
fOtherRuleStatusIndex = 0;
fBreaks.removeAllElements();
}
UBool RuleBasedBreakIterator::DictionaryCache::following(int32_t fromPos, int32_t *result, int32_t *statusIndex) {
if (fromPos >= fLimit || fromPos < fStart) {
fPositionInCache = -1;
return FALSE;
}
// Sequential iteration, move from previous boundary to the following
int32_t r = 0;
if (fPositionInCache >= 0 && fPositionInCache < fBreaks.size() && fBreaks.elementAti(fPositionInCache) == fromPos) {
++fPositionInCache;
if (fPositionInCache >= fBreaks.size()) {
fPositionInCache = -1;
return FALSE;
}
r = fBreaks.elementAti(fPositionInCache);
U_ASSERT(r > fromPos);
*result = r;
*statusIndex = fOtherRuleStatusIndex;
return TRUE;
}
// Random indexing. Linear search for the boundary following the given position.
for (fPositionInCache = 0; fPositionInCache < fBreaks.size(); ++fPositionInCache) {
r= fBreaks.elementAti(fPositionInCache);
if (r > fromPos) {
*result = r;
*statusIndex = fOtherRuleStatusIndex;
return TRUE;
}
}
U_ASSERT(FALSE);
fPositionInCache = -1;
return FALSE;
}
UBool RuleBasedBreakIterator::DictionaryCache::preceding(int32_t fromPos, int32_t *result, int32_t *statusIndex) {
if (fromPos <= fStart || fromPos > fLimit) {
fPositionInCache = -1;
return FALSE;
}
if (fromPos == fLimit) {
fPositionInCache = fBreaks.size() - 1;
if (fPositionInCache >= 0) {
U_ASSERT(fBreaks.elementAti(fPositionInCache) == fromPos);
}
}
int32_t r;
if (fPositionInCache > 0 && fPositionInCache < fBreaks.size() && fBreaks.elementAti(fPositionInCache) == fromPos) {
--fPositionInCache;
r = fBreaks.elementAti(fPositionInCache);
U_ASSERT(r < fromPos);
*result = r;
*statusIndex = ( r== fStart) ? fFirstRuleStatusIndex : fOtherRuleStatusIndex;
return TRUE;
}
if (fPositionInCache == 0) {
fPositionInCache = -1;
return FALSE;
}
for (fPositionInCache = fBreaks.size()-1; fPositionInCache >= 0; --fPositionInCache) {
r = fBreaks.elementAti(fPositionInCache);
if (r < fromPos) {
*result = r;
*statusIndex = ( r == fStart) ? fFirstRuleStatusIndex : fOtherRuleStatusIndex;
return TRUE;
}
}
U_ASSERT(FALSE);
fPositionInCache = -1;
return FALSE;
}
void RuleBasedBreakIterator::DictionaryCache::populateDictionary(int32_t startPos, int32_t endPos,
int32_t firstRuleStatus, int32_t otherRuleStatus) {
if ((endPos - startPos) <= 1) {
return;
}
reset();
fFirstRuleStatusIndex = firstRuleStatus;
fOtherRuleStatusIndex = otherRuleStatus;
int32_t rangeStart = startPos;
int32_t rangeEnd = endPos;
uint16_t category;
int32_t current;
UErrorCode status = U_ZERO_ERROR;
int32_t foundBreakCount = 0;
UText *text = &fBI->fText;
// Loop through the text, looking for ranges of dictionary characters.
// For each span, find the appropriate break engine, and ask it to find
// any breaks within the span.
utext_setNativeIndex(text, rangeStart);
UChar32 c = utext_current32(text);
category = UTRIE2_GET16(fBI->fData->fTrie, c);
while(U_SUCCESS(status)) {
while((current = (int32_t)UTEXT_GETNATIVEINDEX(text)) < rangeEnd && (category & 0x4000) == 0) {
utext_next32(text); // TODO: cleaner loop structure.
c = utext_current32(text);
category = UTRIE2_GET16(fBI->fData->fTrie, c);
}
if (current >= rangeEnd) {
break;
}
// We now have a dictionary character. Get the appropriate language object
// to deal with it.
const LanguageBreakEngine *lbe = fBI->getLanguageBreakEngine(c);
// Ask the language object if there are any breaks. It will add them to the cache and
// leave the text pointer on the other side of its range, ready to search for the next one.
if (lbe != NULL) {
foundBreakCount += lbe->findBreaks(text, rangeStart, rangeEnd, fBreaks);
}
// Reload the loop variables for the next go-round
c = utext_current32(text);
category = UTRIE2_GET16(fBI->fData->fTrie, c);
}
// If we found breaks, ensure that the first and last entries are
// the original starting and ending position. And initialize the
// cache iteration position to the first entry.
// printf("foundBreakCount = %d\n", foundBreakCount);
if (foundBreakCount > 0) {
U_ASSERT(foundBreakCount == fBreaks.size());
if (startPos < fBreaks.elementAti(0)) {
// The dictionary did not place a boundary at the start of the segment of text.
// Add one now. This should not commonly happen, but it would be easy for interactions
// of the rules for dictionary segments and the break engine implementations to
// inadvertently cause it. Cover it here, just in case.
fBreaks.insertElementAt(startPos, 0, status);
}
if (endPos > fBreaks.peeki()) {
fBreaks.push(endPos, status);
}
fPositionInCache = 0;
// Note: Dictionary matching may extend beyond the original limit.
fStart = fBreaks.elementAti(0);
fLimit = fBreaks.peeki();
} else {
// there were no language-based breaks, even though the segment contained
// dictionary characters. Subsequent attempts to fetch boundaries from the dictionary cache
// for this range will fail, and the calling code will fall back to the rule based boundaries.
}
}
/*
* BreakCache implemetation
*/
RuleBasedBreakIterator::BreakCache::BreakCache(RuleBasedBreakIterator *bi, UErrorCode &status) :
fBI(bi), fSideBuffer(status) {
reset();
}
RuleBasedBreakIterator::BreakCache::~BreakCache() {
}
void RuleBasedBreakIterator::BreakCache::reset(int32_t pos, int32_t ruleStatus) {
fStartBufIdx = 0;
fEndBufIdx = 0;
fTextIdx = pos;
fBufIdx = 0;
fBoundaries[0] = pos;
fStatuses[0] = (uint16_t)ruleStatus;
}
int32_t RuleBasedBreakIterator::BreakCache::current() {
fBI->fPosition = fTextIdx;
fBI->fRuleStatusIndex = fStatuses[fBufIdx];
fBI->fDone = FALSE;
return fTextIdx;
}
void RuleBasedBreakIterator::BreakCache::following(int32_t startPos, UErrorCode &status) {
if (U_FAILURE(status)) {
return;
}
if (startPos == fTextIdx || seek(startPos) || populateNear(startPos, status)) {
// startPos is in the cache. Do a next() from that position.
// TODO: an awkward set of interactions with bi->fDone
// seek() does not clear it; it can't because of interactions with populateNear().
// next() does not clear it in the fast-path case, where everything matters. Maybe it should.
// So clear it here, for the case where seek() succeeded on an iterator that had previously run off the end.
fBI->fDone = false;
next();
}
return;
}
void RuleBasedBreakIterator::BreakCache::preceding(int32_t startPos, UErrorCode &status) {
if (U_FAILURE(status)) {
return;
}
if (startPos == fTextIdx || seek(startPos) || populateNear(startPos, status)) {
if (startPos == fTextIdx) {
previous(status);
} else {
// seek() leaves the BreakCache positioned at the preceding boundary
// if the requested position is between two bounaries.
// current() pushes the BreakCache position out to the BreakIterator itself.
U_ASSERT(startPos > fTextIdx);
current();
}
}
return;
}
/*
* Out-of-line code for BreakCache::next().
* Cache does not already contain the boundary
*/
void RuleBasedBreakIterator::BreakCache::nextOL() {
fBI->fDone = !populateFollowing();
fBI->fPosition = fTextIdx;
fBI->fRuleStatusIndex = fStatuses[fBufIdx];
return;
}
void RuleBasedBreakIterator::BreakCache::previous(UErrorCode &status) {
if (U_FAILURE(status)) {
return;
}
int32_t initialBufIdx = fBufIdx;
if (fBufIdx == fStartBufIdx) {
// At start of cache. Prepend to it.
populatePreceding(status);
} else {
// Cache already holds the next boundary
fBufIdx = modChunkSize(fBufIdx - 1);
fTextIdx = fBoundaries[fBufIdx];
}
fBI->fDone = (fBufIdx == initialBufIdx);
fBI->fPosition = fTextIdx;
fBI->fRuleStatusIndex = fStatuses[fBufIdx];
return;
}
UBool RuleBasedBreakIterator::BreakCache::seek(int32_t pos) {
if (pos < fBoundaries[fStartBufIdx] || pos > fBoundaries[fEndBufIdx]) {
return FALSE;
}
if (pos == fBoundaries[fStartBufIdx]) {
// Common case: seek(0), from BreakIterator::first()
fBufIdx = fStartBufIdx;
fTextIdx = fBoundaries[fBufIdx];
return TRUE;
}
if (pos == fBoundaries[fEndBufIdx]) {
fBufIdx = fEndBufIdx;
fTextIdx = fBoundaries[fBufIdx];
return TRUE;
}
int32_t min = fStartBufIdx;
int32_t max = fEndBufIdx;
while (min != max) {
int32_t probe = (min + max + (min>max ? CACHE_SIZE : 0)) / 2;
probe = modChunkSize(probe);
if (fBoundaries[probe] > pos) {
max = probe;
} else {
min = modChunkSize(probe + 1);
}
}
U_ASSERT(fBoundaries[max] > pos);
fBufIdx = modChunkSize(max - 1);
fTextIdx = fBoundaries[fBufIdx];
U_ASSERT(fTextIdx <= pos);
return TRUE;
}
UBool RuleBasedBreakIterator::BreakCache::populateNear(int32_t position, UErrorCode &status) {
if (U_FAILURE(status)) {
return FALSE;
}
U_ASSERT(position < fBoundaries[fStartBufIdx] || position > fBoundaries[fEndBufIdx]);
// Find a boundary somewhere in the vicinity of the requested position.
// Depending on the safe rules and the text data, it could be either before, at, or after
// the requested position.
// If the requested position is not near already cached positions, clear the existing cache,
// find a near-by boundary and begin new cache contents there.
if ((position < fBoundaries[fStartBufIdx] - 15) || position > (fBoundaries[fEndBufIdx] + 15)) {
int32_t aBoundary = 0;
int32_t ruleStatusIndex = 0;
if (position > 20) {
int32_t backupPos = fBI->handleSafePrevious(position);
if (backupPos > 0) {
// Advance to the boundary following the backup position.
// There is a complication: the safe reverse rules identify pairs of code points
// that are safe. If advancing from the safe point moves forwards by less than
// two code points, we need to advance one more time to ensure that the boundary
// is good, including a correct rules status value.
//
fBI->fPosition = backupPos;
aBoundary = fBI->handleNext();
if (aBoundary <= backupPos + 4) {
// +4 is a quick test for possibly having advanced only one codepoint.
// Four being the length of the longest potential code point, a supplementary in UTF-8
utext_setNativeIndex(&fBI->fText, aBoundary);
if (backupPos == utext_getPreviousNativeIndex(&fBI->fText)) {
// The initial handleNext() only advanced by a single code point. Go again.
aBoundary = fBI->handleNext(); // Safe rules identify safe pairs.
}
}
ruleStatusIndex = fBI->fRuleStatusIndex;
}
}
reset(aBoundary, ruleStatusIndex); // Reset cache to hold aBoundary as a single starting point.
}
// Fill in boundaries between existing cache content and the new requested position.
if (fBoundaries[fEndBufIdx] < position) {
// The last position in the cache precedes the requested position.
// Add following position(s) to the cache.
while (fBoundaries[fEndBufIdx] < position) {
if (!populateFollowing()) {
U_ASSERT(false);
return false;
}
}
fBufIdx = fEndBufIdx; // Set iterator position to the end of the buffer.
fTextIdx = fBoundaries[fBufIdx]; // Required because populateFollowing may add extra boundaries.
while (fTextIdx > position) { // Move backwards to a position at or preceding the requested pos.
previous(status);
}
return true;
}
if (fBoundaries[fStartBufIdx] > position) {
// The first position in the cache is beyond the requested position.
// back up more until we get a boundary <= the requested position.
while (fBoundaries[fStartBufIdx] > position) {
populatePreceding(status);
}
fBufIdx = fStartBufIdx; // Set iterator position to the start of the buffer.
fTextIdx = fBoundaries[fBufIdx]; // Required because populatePreceding may add extra boundaries.
while (fTextIdx < position) { // Move forwards to a position at or following the requested pos.
next();
}
if (fTextIdx > position) {
// If position is not itself a boundary, the next() loop above will overshoot.
// Back up one, leaving cache position at the boundary preceding the requested position.
previous(status);
}
return true;
}
U_ASSERT(fTextIdx == position);
return true;
}
UBool RuleBasedBreakIterator::BreakCache::populateFollowing() {
int32_t fromPosition = fBoundaries[fEndBufIdx];
int32_t fromRuleStatusIdx = fStatuses[fEndBufIdx];
int32_t pos = 0;
int32_t ruleStatusIdx = 0;
if (fBI->fDictionaryCache->following(fromPosition, &pos, &ruleStatusIdx)) {
addFollowing(pos, ruleStatusIdx, UpdateCachePosition);
return TRUE;
}
fBI->fPosition = fromPosition;
pos = fBI->handleNext();
if (pos == UBRK_DONE) {
return FALSE;
}
ruleStatusIdx = fBI->fRuleStatusIndex;
if (fBI->fDictionaryCharCount > 0) {
// The text segment obtained from the rules includes dictionary characters.
// Subdivide it, with subdivided results going into the dictionary cache.
fBI->fDictionaryCache->populateDictionary(fromPosition, pos, fromRuleStatusIdx, ruleStatusIdx);
if (fBI->fDictionaryCache->following(fromPosition, &pos, &ruleStatusIdx)) {
addFollowing(pos, ruleStatusIdx, UpdateCachePosition);
return TRUE;
// TODO: may want to move a sizable chunk of dictionary cache to break cache at this point.
// But be careful with interactions with populateNear().
}
}
// Rule based segment did not include dictionary characters.
// Or, it did contain dictionary chars, but the dictionary segmenter didn't handle them,
// meaning that we didn't take the return, above.
// Add its end point to the cache.
addFollowing(pos, ruleStatusIdx, UpdateCachePosition);
// Add several non-dictionary boundaries at this point, to optimize straight forward iteration.
// (subsequent calls to BreakIterator::next() will take the fast path, getting cached results.
//
for (int count=0; count<6; ++count) {
pos = fBI->handleNext();
if (pos == UBRK_DONE || fBI->fDictionaryCharCount > 0) {
break;
}
addFollowing(pos, fBI->fRuleStatusIndex, RetainCachePosition);
}
return TRUE;
}
UBool RuleBasedBreakIterator::BreakCache::populatePreceding(UErrorCode &status) {
if (U_FAILURE(status)) {
return FALSE;
}
int32_t fromPosition = fBoundaries[fStartBufIdx];
if (fromPosition == 0) {
return FALSE;
}
int32_t position = 0;
int32_t positionStatusIdx = 0;
if (fBI->fDictionaryCache->preceding(fromPosition, &position, &positionStatusIdx)) {
addPreceding(position, positionStatusIdx, UpdateCachePosition);
return TRUE;
}
int32_t backupPosition = fromPosition;
// Find a boundary somewhere preceding the first already-cached boundary
do {
backupPosition = backupPosition - 30;
if (backupPosition <= 0) {
backupPosition = 0;
} else {
backupPosition = fBI->handleSafePrevious(backupPosition);
}
if (backupPosition == UBRK_DONE || backupPosition == 0) {
position = 0;
positionStatusIdx = 0;
} else {
// Advance to the boundary following the backup position.
// There is a complication: the safe reverse rules identify pairs of code points
// that are safe. If advancing from the safe point moves forwards by less than
// two code points, we need to advance one more time to ensure that the boundary
// is good, including a correct rules status value.
//
fBI->fPosition = backupPosition;
position = fBI->handleNext();
if (position <= backupPosition + 4) {
// +4 is a quick test for possibly having advanced only one codepoint.
// Four being the length of the longest potential code point, a supplementary in UTF-8
utext_setNativeIndex(&fBI->fText, position);
if (backupPosition == utext_getPreviousNativeIndex(&fBI->fText)) {
// The initial handleNext() only advanced by a single code point. Go again.
position = fBI->handleNext(); // Safe rules identify safe pairs.
}
};
positionStatusIdx = fBI->fRuleStatusIndex;
}
} while (position >= fromPosition);
// Find boundaries between the one we just located and the first already-cached boundary
// Put them in a side buffer, because we don't yet know where they will fall in the circular cache buffer..
fSideBuffer.removeAllElements();
fSideBuffer.addElement(position, status);
fSideBuffer.addElement(positionStatusIdx, status);
do {
int32_t prevPosition = fBI->fPosition = position;
int32_t prevStatusIdx = positionStatusIdx;
position = fBI->handleNext();
positionStatusIdx = fBI->fRuleStatusIndex;
if (position == UBRK_DONE) {
break;
}
UBool segmentHandledByDictionary = FALSE;
if (fBI->fDictionaryCharCount != 0) {
// Segment from the rules includes dictionary characters.
// Subdivide it, with subdivided results going into the dictionary cache.
int32_t dictSegEndPosition = position;
fBI->fDictionaryCache->populateDictionary(prevPosition, dictSegEndPosition, prevStatusIdx, positionStatusIdx);
while (fBI->fDictionaryCache->following(prevPosition, &position, &positionStatusIdx)) {
segmentHandledByDictionary = true;
U_ASSERT(position > prevPosition);
if (position >= fromPosition) {
break;
}
U_ASSERT(position <= dictSegEndPosition);
fSideBuffer.addElement(position, status);
fSideBuffer.addElement(positionStatusIdx, status);
prevPosition = position;
}
U_ASSERT(position==dictSegEndPosition || position>=fromPosition);
}
if (!segmentHandledByDictionary && position < fromPosition) {
fSideBuffer.addElement(position, status);
fSideBuffer.addElement(positionStatusIdx, status);
}
} while (position < fromPosition);
// Move boundaries from the side buffer to the main circular buffer.
UBool success = FALSE;
if (!fSideBuffer.isEmpty()) {
positionStatusIdx = fSideBuffer.popi();
position = fSideBuffer.popi();
addPreceding(position, positionStatusIdx, UpdateCachePosition);
success = TRUE;
}
while (!fSideBuffer.isEmpty()) {
positionStatusIdx = fSideBuffer.popi();
position = fSideBuffer.popi();
if (!addPreceding(position, positionStatusIdx, RetainCachePosition)) {
// No space in circular buffer to hold a new preceding result while
// also retaining the current cache (iteration) position.
// Bailing out is safe; the cache will refill again if needed.
break;
}
}
return success;
}
void RuleBasedBreakIterator::BreakCache::addFollowing(int32_t position, int32_t ruleStatusIdx, UpdatePositionValues update) {
U_ASSERT(position > fBoundaries[fEndBufIdx]);
U_ASSERT(ruleStatusIdx <= UINT16_MAX);
int32_t nextIdx = modChunkSize(fEndBufIdx + 1);
if (nextIdx == fStartBufIdx) {
fStartBufIdx = modChunkSize(fStartBufIdx + 6); // TODO: experiment. Probably revert to 1.
}
fBoundaries[nextIdx] = position;
fStatuses[nextIdx] = static_cast<uint16_t>(ruleStatusIdx);
fEndBufIdx = nextIdx;
if (update == UpdateCachePosition) {
// Set current position to the newly added boundary.
fBufIdx = nextIdx;
fTextIdx = position;
} else {
// Retaining the original cache position.
// Check if the added boundary wraps around the buffer, and would over-write the original position.
// It's the responsibility of callers of this function to not add too many.
U_ASSERT(nextIdx != fBufIdx);
}
}
bool RuleBasedBreakIterator::BreakCache::addPreceding(int32_t position, int32_t ruleStatusIdx, UpdatePositionValues update) {
U_ASSERT(position < fBoundaries[fStartBufIdx]);
U_ASSERT(ruleStatusIdx <= UINT16_MAX);
int32_t nextIdx = modChunkSize(fStartBufIdx - 1);
if (nextIdx == fEndBufIdx) {
if (fBufIdx == fEndBufIdx && update == RetainCachePosition) {
// Failure. The insertion of the new boundary would claim the buffer position that is the
// current iteration position. And we also want to retain the current iteration position.
// (The buffer is already completely full of entries that precede the iteration position.)
return false;
}
fEndBufIdx = modChunkSize(fEndBufIdx - 1);
}
fBoundaries[nextIdx] = position;
fStatuses[nextIdx] = static_cast<uint16_t>(ruleStatusIdx);
fStartBufIdx = nextIdx;
if (update == UpdateCachePosition) {
fBufIdx = nextIdx;
fTextIdx = position;
}
return true;
}
void RuleBasedBreakIterator::BreakCache::dumpCache() {
#ifdef RBBI_DEBUG
RBBIDebugPrintf("fTextIdx:%d fBufIdx:%d\n", fTextIdx, fBufIdx);
for (int32_t i=fStartBufIdx; ; i=modChunkSize(i+1)) {
RBBIDebugPrintf("%d %d\n", i, fBoundaries[i]);
if (i == fEndBufIdx) {
break;
}
}
#endif
}
U_NAMESPACE_END
#endif // #if !UCONFIG_NO_BREAK_ITERATION

203
intl/icu/source/common/rbbi_cache.h Normal file
View file

@ -0,0 +1,203 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// file: rbbi_cache.h
//
#ifndef RBBI_CACHE_H
#define RBBI_CACHE_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_BREAK_ITERATION
#include "unicode/rbbi.h"
#include "unicode/uobject.h"
#include "uvectr32.h"
U_NAMESPACE_BEGIN
/* DictionaryCache stores the boundaries obtained from a run of dictionary characters.
* Dictionary boundaries are moved first to this cache, then from here
* to the main BreakCache, where they may inter-leave with non-dictionary
* boundaries. The public BreakIterator API always fetches directly
* from the main BreakCache, not from here.
*
* In common situations, the number of boundaries in a single dictionary run
* should be quite small, it will be terminated by punctuation, spaces,
* or any other non-dictionary characters. The main BreakCache may end
* up with boundaries from multiple dictionary based runs.
*
* The boundaries are stored in a simple ArrayList (vector), with the
* assumption that they will be accessed sequentially.
*/
class RuleBasedBreakIterator::DictionaryCache: public UMemory {
public:
DictionaryCache(RuleBasedBreakIterator *bi, UErrorCode &status);
~DictionaryCache();
void reset();
UBool following(int32_t fromPos, int32_t *pos, int32_t *statusIndex);
UBool preceding(int32_t fromPos, int32_t *pos, int32_t *statusIndex);
/**
* Populate the cache with the dictionary based boundaries within a region of text.
* @param startPos The start position of a range of text
* @param endPos The end position of a range of text
* @param firstRuleStatus The rule status index that applies to the break at startPos
* @param otherRuleStatus The rule status index that applies to boundaries other than startPos
* @internal
*/
void populateDictionary(int32_t startPos, int32_t endPos,
int32_t firstRuleStatus, int32_t otherRuleStatus);
RuleBasedBreakIterator *fBI;
UVector32 fBreaks; // A vector containing the boundaries.
int32_t fPositionInCache; // Index in fBreaks of last boundary returned by following()
// or preceding(). Optimizes sequential access.
int32_t fStart; // Text position of first boundary in cache.
int32_t fLimit; // Last boundary in cache. Which is the limit of the
// text segment being handled by the dictionary.
int32_t fFirstRuleStatusIndex; // Rule status info for first boundary.
int32_t fOtherRuleStatusIndex; // Rule status info for 2nd through last boundaries.
};
/*
* class BreakCache
*
* Cache of break boundary positions and rule status values.
* Break iterator API functions, next(), previous(), etc., will use cached results
* when possible, and otherwise cache new results as they are obtained.
*
* Uniformly caches both dictionary and rule based (non-dictionary) boundaries.
*
* The cache is implemented as a single circular buffer.
*/
/*
* size of the circular cache buffer.
*/
class RuleBasedBreakIterator::BreakCache: public UMemory {
public:
BreakCache(RuleBasedBreakIterator *bi, UErrorCode &status);
virtual ~BreakCache();
void reset(int32_t pos = 0, int32_t ruleStatus = 0);
void next() { if (fBufIdx == fEndBufIdx) {
nextOL();
} else {
fBufIdx = modChunkSize(fBufIdx + 1);
fTextIdx = fBI->fPosition = fBoundaries[fBufIdx];
fBI->fRuleStatusIndex = fStatuses[fBufIdx];
}
};
void nextOL();
void previous(UErrorCode &status);
// Move the iteration state to the position following the startPosition.
// Input position must be pinned to the input length.
void following(int32_t startPosition, UErrorCode &status);
void preceding(int32_t startPosition, UErrorCode &status);
/*
* Update the state of the public BreakIterator (fBI) to reflect the
* current state of the break iterator cache (this).
*/
int32_t current();
/**
* Add boundaries to the cache near the specified position.
* The given position need not be a boundary itself.
* The input position must be within the range of the text, and
* on a code point boundary.
* If the requested position is a break boundary, leave the iteration
* position on it.
* If the requested position is not a boundary, leave the iteration
* position on the preceding boundary and include both the
* preceding and following boundaries in the cache.
* Additional boundaries, either preceding or following, may be added
* to the cache as a side effect.
*
* Return FALSE if the operation failed.
*/
UBool populateNear(int32_t position, UErrorCode &status);
/**
* Add boundary(s) to the cache following the current last boundary.
* Return FALSE if at the end of the text, and no more boundaries can be added.
* Leave iteration position at the first newly added boundary, or unchanged if no boundary was added.
*/
UBool populateFollowing();
/**
* Add one or more boundaries to the cache preceding the first currently cached boundary.
* Leave the iteration position on the first added boundary.
* Return false if no boundaries could be added (if at the start of the text.)
*/
UBool populatePreceding(UErrorCode &status);
enum UpdatePositionValues {
RetainCachePosition = 0,
UpdateCachePosition = 1
};
/*
* Add the boundary following the current position.
* The current position can be left as it was, or changed to the newly added boundary,
* as specified by the update parameter.
*/
void addFollowing(int32_t position, int32_t ruleStatusIdx, UpdatePositionValues update);
/*
* Add the boundary preceding the current position.
* The current position can be left as it was, or changed to the newly added boundary,
* as specified by the update parameter.
*/
bool addPreceding(int32_t position, int32_t ruleStatusIdx, UpdatePositionValues update);
/**
* Set the cache position to the specified position, or, if the position
* falls between to cached boundaries, to the preceding boundary.
* Fails if the requested position is outside of the range of boundaries currently held by the cache.
* The startPosition must be on a code point boundary.
*
* Return TRUE if successful, FALSE if the specified position is after
* the last cached boundary or before the first.
*/
UBool seek(int32_t startPosition);
void dumpCache();
private:
static inline int32_t modChunkSize(int index) { return index & (CACHE_SIZE - 1); };
static constexpr int32_t CACHE_SIZE = 128;
static_assert((CACHE_SIZE & (CACHE_SIZE-1)) == 0, "CACHE_SIZE must be power of two.");
RuleBasedBreakIterator *fBI;
int32_t fStartBufIdx;
int32_t fEndBufIdx; // inclusive
int32_t fTextIdx;
int32_t fBufIdx;
int32_t fBoundaries[CACHE_SIZE];
uint16_t fStatuses[CACHE_SIZE];
UVector32 fSideBuffer;
};
U_NAMESPACE_END
#endif // #if !UCONFIG_NO_BREAK_ITERATION
#endif // RBBI_CACHE_H

107
intl/icu/source/common/rbbidata.cpp
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
***************************************************************************
@ -14,7 +14,7 @@
#include "unicode/utypes.h"
#include "rbbidata.h"
#include "rbbirb.h"
#include "utrie.h"
#include "utrie2.h"
#include "udatamem.h"
#include "cmemory.h"
#include "cstring.h"
@ -23,23 +23,6 @@
#include "uassert.h"
//-----------------------------------------------------------------------------------
//
// Trie access folding function. Copied as-is from properties code in uchar.c
//
//-----------------------------------------------------------------------------------
U_CDECL_BEGIN
static int32_t U_CALLCONV
getFoldingOffset(uint32_t data) {
/* if bit 15 is set, then the folding offset is in bits 14..0 of the 16-bit trie result */
if(data&0x8000) {
return (int32_t)(data&0x7fff);
} else {
return 0;
}
}
U_CDECL_END
U_NAMESPACE_BEGIN
//-----------------------------------------------------------------------------
@ -71,9 +54,8 @@ RBBIDataWrapper::RBBIDataWrapper(UDataMemory* udm, UErrorCode &status) {
dh->info.dataFormat[0] == 0x42 && // dataFormat="Brk "
dh->info.dataFormat[1] == 0x72 &&
dh->info.dataFormat[2] == 0x6b &&
dh->info.dataFormat[3] == 0x20)
// Note: info.fFormatVersion is duplicated in the RBBIDataHeader, and is
// validated when checking that.
dh->info.dataFormat[3] == 0x20 &&
isDataVersionAcceptable(dh->info.formatVersion))
) {
status = U_INVALID_FORMAT_ERROR;
return;
@ -84,6 +66,11 @@ RBBIDataWrapper::RBBIDataWrapper(UDataMemory* udm, UErrorCode &status) {
fUDataMem = udm;
}
UBool RBBIDataWrapper::isDataVersionAcceptable(const UVersionInfo version) {
return RBBI_DATA_FORMAT_VERSION[0] == version[0];
}
//-----------------------------------------------------------------------------
//
// init(). Does most of the work of construction, shared between the
@ -94,12 +81,11 @@ void RBBIDataWrapper::init0() {
fHeader = NULL;
fForwardTable = NULL;
fReverseTable = NULL;
fSafeFwdTable = NULL;
fSafeRevTable = NULL;
fRuleSource = NULL;
fRuleSource = NULL;
fRuleStatusTable = NULL;
fUDataMem = NULL;
fRefCount = 0;
fTrie = NULL;
fUDataMem = NULL;
fRefCount = 0;
fDontFreeData = TRUE;
}
@ -108,8 +94,7 @@ void RBBIDataWrapper::init(const RBBIDataHeader *data, UErrorCode &status) {
return;
}
fHeader = data;
if (fHeader->fMagic != 0xb1a0 || fHeader->fFormatVersion[0] != 3)
{
if (fHeader->fMagic != 0xb1a0 || !isDataVersionAcceptable(fHeader->fFormatVersion)) {
status = U_INVALID_FORMAT_ERROR;
return;
}
@ -124,23 +109,15 @@ void RBBIDataWrapper::init(const RBBIDataHeader *data, UErrorCode &status) {
if (data->fRTableLen != 0) {
fReverseTable = (RBBIStateTable *)((char *)data + fHeader->fRTable);
}
if (data->fSFTableLen != 0) {
fSafeFwdTable = (RBBIStateTable *)((char *)data + fHeader->fSFTable);
}
if (data->fSRTableLen != 0) {
fSafeRevTable = (RBBIStateTable *)((char *)data + fHeader->fSRTable);
}
utrie_unserialize(&fTrie,
(uint8_t *)data + fHeader->fTrie,
fHeader->fTrieLen,
&status);
fTrie = utrie2_openFromSerialized(UTRIE2_16_VALUE_BITS,
(uint8_t *)data + fHeader->fTrie,
fHeader->fTrieLen,
NULL, // *actual length
&status);
if (U_FAILURE(status)) {
return;
}
fTrie.getFoldingOffset=getFoldingOffset;
fRuleSource = (UChar *)((char *)data + fHeader->fRuleSource);
fRuleString.setTo(TRUE, fRuleSource, -1);
@ -165,6 +142,8 @@ void RBBIDataWrapper::init(const RBBIDataHeader *data, UErrorCode &status) {
//-----------------------------------------------------------------------------
RBBIDataWrapper::~RBBIDataWrapper() {
U_ASSERT(fRefCount == 0);
utrie2_close(fTrie);
fTrie = NULL;
if (fUDataMem) {
udata_close(fUDataMem);
} else if (!fDontFreeData) {
@ -271,8 +250,8 @@ void RBBIDataWrapper::printTable(const char *heading, const RBBIStateTable *tab
#endif
#ifdef RBBI_DEBUG
void RBBIDataWrapper::printData() {
#ifdef RBBI_DEBUG
RBBIDebugPrintf("RBBI Data at %p\n", (void *)fHeader);
RBBIDebugPrintf(" Version = {%d %d %d %d}\n", fHeader->fFormatVersion[0], fHeader->fFormatVersion[1],
fHeader->fFormatVersion[2], fHeader->fFormatVersion[3]);
@ -281,16 +260,14 @@ void RBBIDataWrapper::printData() {
printTable("Forward State Transition Table", fForwardTable);
printTable("Reverse State Transition Table", fReverseTable);
printTable("Safe Forward State Transition Table", fSafeFwdTable);
printTable("Safe Reverse State Transition Table", fSafeRevTable);
RBBIDebugPrintf("\nOrignal Rules source:\n");
for (int32_t c=0; fRuleSource[c] != 0; c++) {
RBBIDebugPrintf("%c", fRuleSource[c]);
}
RBBIDebugPrintf("\n\n");
}
#endif
}
U_NAMESPACE_END
@ -323,7 +300,7 @@ ubrk_swap(const UDataSwapper *ds, const void *inData, int32_t length, void *outD
pInfo->dataFormat[1]==0x72 &&
pInfo->dataFormat[2]==0x6b &&
pInfo->dataFormat[3]==0x20 &&
pInfo->formatVersion[0]==3 )) {
RBBIDataWrapper::isDataVersionAcceptable(pInfo->formatVersion) )) {
udata_printError(ds, "ubrk_swap(): data format %02x.%02x.%02x.%02x (format version %02x) is not recognized\n",
pInfo->dataFormat[0], pInfo->dataFormat[1],
pInfo->dataFormat[2], pInfo->dataFormat[3],
@ -344,17 +321,11 @@ ubrk_swap(const UDataSwapper *ds, const void *inData, int32_t length, void *outD
//
// Get the RRBI Data Header, and check that it appears to be OK.
//
// Note: ICU 3.2 and earlier, RBBIDataHeader::fDataFormat was actually
// an int32_t with a value of 1. Starting with ICU 3.4,
// RBBI's fDataFormat matches the dataFormat field from the
// UDataInfo header, four int8_t bytes. The value is {3,1,0,0}
//
const uint8_t *inBytes =(const uint8_t *)inData+headerSize;
RBBIDataHeader *rbbiDH = (RBBIDataHeader *)inBytes;
if (ds->readUInt32(rbbiDH->fMagic) != 0xb1a0 ||
rbbiDH->fFormatVersion[0] != 3 ||
ds->readUInt32(rbbiDH->fLength) < sizeof(RBBIDataHeader))
{
!RBBIDataWrapper::isDataVersionAcceptable(rbbiDH->fFormatVersion) ||
ds->readUInt32(rbbiDH->fLength) < sizeof(RBBIDataHeader)) {
udata_printError(ds, "ubrk_swap(): RBBI Data header is invalid.\n");
*status=U_UNSUPPORTED_ERROR;
return 0;
@ -428,31 +399,9 @@ ubrk_swap(const UDataSwapper *ds, const void *inData, int32_t length, void *outD
outBytes+tableStartOffset+topSize, status);
}
// Safe Forward state table. Same layout as forward table, above.
tableStartOffset = ds->readUInt32(rbbiDH->fSFTable);
tableLength = ds->readUInt32(rbbiDH->fSFTableLen);
if (tableLength > 0) {
ds->swapArray32(ds, inBytes+tableStartOffset, topSize,
outBytes+tableStartOffset, status);
ds->swapArray16(ds, inBytes+tableStartOffset+topSize, tableLength-topSize,
outBytes+tableStartOffset+topSize, status);
}
// Safe Reverse state table. Same layout as forward table, above.
tableStartOffset = ds->readUInt32(rbbiDH->fSRTable);
tableLength = ds->readUInt32(rbbiDH->fSRTableLen);
if (tableLength > 0) {
ds->swapArray32(ds, inBytes+tableStartOffset, topSize,
outBytes+tableStartOffset, status);
ds->swapArray16(ds, inBytes+tableStartOffset+topSize, tableLength-topSize,
outBytes+tableStartOffset+topSize, status);
}
// Trie table for character categories
utrie_swap(ds, inBytes+ds->readUInt32(rbbiDH->fTrie), ds->readUInt32(rbbiDH->fTrieLen),
outBytes+ds->readUInt32(rbbiDH->fTrie), status);
utrie2_swap(ds, inBytes+ds->readUInt32(rbbiDH->fTrie), ds->readUInt32(rbbiDH->fTrieLen),
outBytes+ds->readUInt32(rbbiDH->fTrie), status);
// Source Rules Text. It's UChar data
ds->swapArray16(ds, inBytes+ds->readUInt32(rbbiDH->fRuleSource), ds->readUInt32(rbbiDH->fRuleSourceLen),

43
intl/icu/source/common/rbbidata.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -8,7 +8,7 @@
*
*******************************************************************************
* file name: rbbidata.h
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
@ -51,22 +51,23 @@ ubrk_swap(const UDataSwapper *ds,
#include "unicode/uobject.h"
#include "unicode/unistr.h"
#include "unicode/uversion.h"
#include "umutex.h"
#include "utrie.h"
#include "utrie2.h"
U_NAMESPACE_BEGIN
// The current RBBI data format version.
static const uint8_t RBBI_DATA_FORMAT_VERSION[] = {5, 0, 0, 0};
/*
* The following structs map exactly onto the raw data from ICU common data file.
*/
struct RBBIDataHeader {
uint32_t fMagic; /* == 0xbla0 */
uint8_t fFormatVersion[4]; /* Data Format. Same as the value in struct UDataInfo */
UVersionInfo fFormatVersion; /* Data Format. Same as the value in struct UDataInfo */
/* if there is one associated with this data. */
/* (version originates in rbbi, is copied to UDataInfo) */
/* For ICU 3.2 and earlier, this field was */
/* uint32_t fVersion */
/* with a value of 1. */
uint32_t fLength; /* Total length in bytes of this RBBI Data, */
/* including all sections, not just the header. */
uint32_t fCatCount; /* Number of character categories. */
@ -80,10 +81,6 @@ struct RBBIDataHeader {
uint32_t fFTableLen;
uint32_t fRTable; /* Offset to the reverse state transition table. */
uint32_t fRTableLen;
uint32_t fSFTable; /* safe point forward transition table */
uint32_t fSFTableLen;
uint32_t fSRTable; /* safe point reverse transition table */
uint32_t fSRTableLen;
uint32_t fTrie; /* Offset to Trie data for character categories */
uint32_t fTrieLen;
uint32_t fRuleSource; /* Offset to the source for for the break */
@ -115,9 +112,10 @@ struct RBBIStateTableRow {
/* StatusTable of the set of matching */
/* tags (rule status values) */
int16_t fReserved;
uint16_t fNextState[2]; /* Next State, indexed by char category. */
/* This array does not have two elements */
/* Array Size is actually fData->fHeader->fCatCount */
uint16_t fNextState[1]; /* Next State, indexed by char category. */
/* Variable-length array declared with length 1 */
/* to disable bounds checkers. */
/* Array Size is actually fData->fHeader->fCatCount*/
/* CAUTION: see RBBITableBuilder::getTableSize() */
/* before changing anything here. */
};
@ -128,7 +126,9 @@ struct RBBIStateTable {
uint32_t fRowLen; /* Length of a state table row, in bytes. */
uint32_t fFlags; /* Option Flags for this state table */
uint32_t fReserved; /* reserved */
char fTableData[4]; /* First RBBIStateTableRow begins here. */
char fTableData[1]; /* First RBBIStateTableRow begins here. */
/* Variable-length array declared with length 1 */
/* to disable bounds checkers. */
/* (making it char[] simplifies ugly address */
/* arithmetic for indexing variable length rows.) */
};
@ -152,6 +152,8 @@ public:
RBBIDataWrapper(UDataMemory* udm, UErrorCode &status);
~RBBIDataWrapper();
static UBool isDataVersionAcceptable(const UVersionInfo version);
void init0();
void init(const RBBIDataHeader *data, UErrorCode &status);
RBBIDataWrapper *addReference();
@ -159,13 +161,8 @@ public:
UBool operator ==(const RBBIDataWrapper &other) const;
int32_t hashCode();
const UnicodeString &getRuleSourceString() const;
#ifdef RBBI_DEBUG
void printData();
void printTable(const char *heading, const RBBIStateTable *table);
#else
#define printData()
#define printTable(heading, table)
#endif
/* */
/* Pointers to items within the data */
@ -173,19 +170,17 @@ public:
const RBBIDataHeader *fHeader;
const RBBIStateTable *fForwardTable;
const RBBIStateTable *fReverseTable;
const RBBIStateTable *fSafeFwdTable;
const RBBIStateTable *fSafeRevTable;
const UChar *fRuleSource;
const int32_t *fRuleStatusTable;
/* number of int32_t values in the rule status table. Used to sanity check indexing */
int32_t fStatusMaxIdx;
UTrie fTrie;
UTrie2 *fTrie;
private:
u_atomic_int32_t fRefCount;
UDataMemory *fUDataMem;
UDataMemory *fUDataMem;
UnicodeString fRuleString;
UBool fDontFreeData;

Some files were not shown because too many files have changed in this diff Show more