From d867f26c0ed7e82fb1381e0e295f3a4fb346f3d1 Mon Sep 17 00:00:00 2001
From: Moonchild
Date: Sun, 21 Feb 2021 10:32:47 +0000
Subject: [PATCH 1/9] [widget] Require user interaction when picking files or
folders v2
Now with extra sauce to make it work cross-platform and cross-versions and
for HTML input elements only.
---
dom/html/HTMLInputElement.cpp | 2 +-
dom/ipc/FilePickerParent.cpp | 3 ++-
widget/nsBaseFilePicker.cpp | 3 ++-
widget/nsBaseFilePicker.h | 3 ++-
widget/nsFilePickerProxy.cpp | 2 +-
widget/nsFilePickerProxy.h | 2 +-
widget/nsIFilePicker.idl | 5 ++++-
widget/windows/nsFilePicker.cpp | 19 ++++++++++++++++++-
widget/windows/nsFilePicker.h | 4 +++-
9 files changed, 34 insertions(+), 9 deletions(-)
diff --git a/dom/html/HTMLInputElement.cpp b/dom/html/HTMLInputElement.cpp
index 86d03d8f59..557e673e15 100644
--- a/dom/html/HTMLInputElement.cpp
+++ b/dom/html/HTMLInputElement.cpp
@@ -866,7 +866,7 @@ HTMLInputElement::InitFilePicker(FilePickerType aType)
mode = static_cast(nsIFilePicker::modeOpen);
}
- nsresult rv = filePicker->Init(win, title, mode);
+ nsresult rv = filePicker->Init(win, title, mode, /*aRequireInteraction = */ true);
NS_ENSURE_SUCCESS(rv, rv);
if (!okButtonLabel.IsEmpty()) {
diff --git a/dom/ipc/FilePickerParent.cpp b/dom/ipc/FilePickerParent.cpp
index 3e8301f246..1438e374fe 100644
--- a/dom/ipc/FilePickerParent.cpp
+++ b/dom/ipc/FilePickerParent.cpp
@@ -248,7 +248,8 @@ FilePickerParent::CreateFilePicker()
return false;
}
- return NS_SUCCEEDED(mFilePicker->Init(window, mTitle, mMode));
+ return NS_SUCCEEDED(mFilePicker->Init(window, mTitle, mMode,
+ element->IsNodeOfType(nsINode::eHTML_FORM_CONTROL)));
}
bool
diff --git a/widget/nsBaseFilePicker.cpp b/widget/nsBaseFilePicker.cpp
index d65ffb651a..1bcd78b462 100644
--- a/widget/nsBaseFilePicker.cpp
+++ b/widget/nsBaseFilePicker.cpp
@@ -166,7 +166,8 @@ nsBaseFilePicker::~nsBaseFilePicker()
NS_IMETHODIMP nsBaseFilePicker::Init(mozIDOMWindowProxy* aParent,
const nsAString& aTitle,
- int16_t aMode)
+ int16_t aMode,
+ bool aRequireInteraction)
{
NS_PRECONDITION(aParent, "Null parent passed to filepicker, no file "
"picker for you!");
diff --git a/widget/nsBaseFilePicker.h b/widget/nsBaseFilePicker.h
index 56ca5acc8d..c0a197e263 100644
--- a/widget/nsBaseFilePicker.h
+++ b/widget/nsBaseFilePicker.h
@@ -25,7 +25,8 @@ public:
NS_IMETHOD Init(mozIDOMWindowProxy* aParent,
const nsAString& aTitle,
- int16_t aMode);
+ int16_t aMode,
+ bool aRequireInteraction = false);
NS_IMETHOD Open(nsIFilePickerShownCallback *aCallback);
NS_IMETHOD AppendFilters(int32_t filterMask);
diff --git a/widget/nsFilePickerProxy.cpp b/widget/nsFilePickerProxy.cpp
index 8828c416e9..077168c455 100644
--- a/widget/nsFilePickerProxy.cpp
+++ b/widget/nsFilePickerProxy.cpp
@@ -27,7 +27,7 @@ nsFilePickerProxy::~nsFilePickerProxy()
NS_IMETHODIMP
nsFilePickerProxy::Init(mozIDOMWindowProxy* aParent, const nsAString& aTitle,
- int16_t aMode)
+ int16_t aMode, bool aRequireInteraction)
{
TabChild* tabChild = TabChild::GetFrom(aParent);
if (!tabChild) {
diff --git a/widget/nsFilePickerProxy.h b/widget/nsFilePickerProxy.h
index fbffb93dee..62d343d72f 100644
--- a/widget/nsFilePickerProxy.h
+++ b/widget/nsFilePickerProxy.h
@@ -34,7 +34,7 @@ public:
NS_DECL_ISUPPORTS
// nsIFilePicker (less what's in nsBaseFilePicker)
- NS_IMETHOD Init(mozIDOMWindowProxy* aParent, const nsAString& aTitle, int16_t aMode) override;
+ NS_IMETHOD Init(mozIDOMWindowProxy* aParent, const nsAString& aTitle, int16_t aMode, bool aRequireInteraction = false) override;
NS_IMETHOD AppendFilter(const nsAString& aTitle, const nsAString& aFilter) override;
NS_IMETHOD GetDefaultString(nsAString& aDefaultString) override;
NS_IMETHOD SetDefaultString(const nsAString& aDefaultString) override;
diff --git a/widget/nsIFilePicker.idl b/widget/nsIFilePicker.idl
index 62efe93ecf..8de69c56e9 100644
--- a/widget/nsIFilePicker.idl
+++ b/widget/nsIFilePicker.idl
@@ -66,9 +66,12 @@ interface nsIFilePicker : nsISupports
* on this parent. parent must be non-null.
* @param title The title for the file widget
* @param mode load, save, or get folder
+ * @param requireinteraction (optional)
+ * require interaction before confirmation is possible
*
*/
- void init(in mozIDOMWindowProxy parent, in AString title, in short mode);
+ void init(in mozIDOMWindowProxy parent, in AString title, in short mode,
+ [optional] in boolean requireinteraction);
/**
* Append to the filter list with things from the predefined list
diff --git a/widget/windows/nsFilePicker.cpp b/widget/windows/nsFilePicker.cpp
index 53857cf5e4..e2e0ab01f7 100644
--- a/widget/windows/nsFilePicker.cpp
+++ b/widget/windows/nsFilePicker.cpp
@@ -30,6 +30,7 @@
using mozilla::IsVistaOrLater;
using mozilla::IsWin8OrLater;
+using mozilla::IsWin10OrLater;
using mozilla::MakeUnique;
using mozilla::mscom::EnsureMTA;
using mozilla::UniquePtr;
@@ -194,11 +195,13 @@ nsFilePicker::~nsFilePicker()
NS_IMPL_ISUPPORTS(nsFilePicker, nsIFilePicker)
-NS_IMETHODIMP nsFilePicker::Init(mozIDOMWindowProxy *aParent, const nsAString& aTitle, int16_t aMode)
+NS_IMETHODIMP nsFilePicker::Init(mozIDOMWindowProxy *aParent, const nsAString& aTitle, int16_t aMode,
+ bool aRequireInteraction)
{
nsCOMPtr window = do_QueryInterface(aParent);
nsIDocShell* docShell = window ? window->GetDocShell() : nullptr;
mLoadContext = do_QueryInterface(docShell);
+ mRequireInteraction = aRequireInteraction;
return nsBaseFilePicker::Init(aParent, aTitle, aMode);
}
@@ -603,6 +606,13 @@ nsFilePicker::ShowFolderPicker(const nsString& aInitialDir, bool &aWasInitError)
// options
FILEOPENDIALOGOPTIONS fos = FOS_PICKFOLDERS;
+ // Require interaction if the folder picker is triggered by an element that
+ // is potentially unsafe to use the default value in.
+ // Win 10+ only, because this dialog flag is broken in earlier versions.
+ if (IsWin10OrLater() && mRequireInteraction) {
+ fos |= FOS_OKBUTTONNEEDSINTERACTION;
+ }
+
dialog->SetOptions(fos);
// initial strings
@@ -923,6 +933,13 @@ nsFilePicker::ShowFilePicker(const nsString& aInitialDir, bool &aWasInitError)
FILEOPENDIALOGOPTIONS fos = 0;
fos |= FOS_SHAREAWARE | FOS_OVERWRITEPROMPT |
FOS_FORCEFILESYSTEM;
+
+ // Require interaction if the file picker is triggered by an element that
+ // is potentially unsafe to use the default value in.
+ // Win 10+ only, because this dialog flag is broken in earlier versions.
+ if (IsWin10OrLater() && mRequireInteraction) {
+ fos |= FOS_OKBUTTONNEEDSINTERACTION;
+ }
// Handle add to recent docs settings
if (IsPrivacyModeEnabled() || !mAddToRecentDocs) {
diff --git a/widget/windows/nsFilePicker.h b/widget/windows/nsFilePicker.h
index 90d8c15bc1..0a2e01b90b 100644
--- a/widget/windows/nsFilePicker.h
+++ b/widget/windows/nsFilePicker.h
@@ -60,7 +60,8 @@ class nsFilePicker :
public:
nsFilePicker();
- NS_IMETHOD Init(mozIDOMWindowProxy *aParent, const nsAString& aTitle, int16_t aMode);
+ NS_IMETHOD Init(mozIDOMWindowProxy *aParent, const nsAString& aTitle, int16_t aMode,
+ bool aRequireInteraction = false);
NS_DECL_ISUPPORTS
@@ -125,6 +126,7 @@ protected:
nsString mUnicodeFile;
static char16_t *mLastUsedUnicodeDirectory;
HWND mDlgWnd;
+ bool mRequireInteraction;
class ComDlgFilterSpec
{
From 79d90233cdc3047cc8b3b5c8f46477acba1d8287 Mon Sep 17 00:00:00 2001
From: Moonchild
Date: Sun, 21 Feb 2021 19:20:31 +0000
Subject: [PATCH 2/9] Issue #1722 - Update about:license
Mostly making parts conditional and removing blocks that are no longer
applicable, and a few minor edits otherwise to update links and text.
Resolves #1722
---
toolkit/content/license.html | 520 +++++++++--------------------------
1 file changed, 127 insertions(+), 393 deletions(-)
diff --git a/toolkit/content/license.html b/toolkit/content/license.html
index 1041ec42f6..5e88440689 100644
--- a/toolkit/content/license.html
+++ b/toolkit/content/license.html
@@ -33,9 +33,7 @@
available under licenses which are both
free and
open source .
- A URL identifying the specific source code used to create this copy can be found
- on the build configuration page , and you can read
- instructions
+ You can read instructions
on how to download and build the code for yourself .
@@ -65,31 +63,34 @@
GNU General Public License 3.0
+#ifdef MOZ_WEBRTC
ACE License
+#endif
+#ifdef MOZ_DEVTOOLS_SERVER
acorn License
-#ifdef MOZ_INSTALL_TRACKING
- Adjust SDK License
#endif
Adobe CMap License
- Android Open Source License
+#ifdef MOZ_ANGLE_RENDERER
ANGLE License
+#endif
Apache License 2.0
Apple License
Apple/Mozilla NPRuntime License
ARM License
+#ifdef MOZ_UPDATER
bspatch License
+#endif
Cairo Component Licenses
Chromium License
- CodeMirror License
+#ifdef MOZ_DEVTOOLS CodeMirror License
cubic-bezier License
D3 License
Dagre-D3 License
+#endif
dtoa License
- Dutch Spellchecking Dictionary License
#if defined(XP_WIN) || defined(XP_LINUX)
Twemoji License
#endif
- Estonian Spellchecking Dictionary License
Expat License
Firebug License
gfxFontList License
@@ -98,11 +99,15 @@
Google Gears/iStumbler License
Google VP8 License
GSL License
+#ifdef MOZ_WEBRTC
gyp License
+#endif
halloc License
HarfBuzz License
ICU License
+#ifdef MOZ_DEVTOOLS
Immutable.js License
+#endif
Japan Network Information Center License
jQuery License
k_exp License
@@ -118,42 +123,56 @@
libnestegg License
libsoundtouch License
libyuv License
- Lithuanian Spellchecking Dictionary License
MIT license — microformat-shiv
MySpell License
+#ifdef MOZ_DEVTOOLS
naturalSort License
+#endif
+#ifdef MOZ_WEBRTC
nICEr License
+#endif
node-properties License
+#ifdef MOZ_WEBRTC
nrappkit License
+#endif
+#ifdef MOZ_EME
OpenAES License
+#endif
OpenVision License
- pbkdf2_sha256 License
praton License
qcms License
+#ifdef MOZ_DEVTOOLS_SERVER
QR Code Generator License
+#endif
React License
+#ifdef MOZ_DEVTOOLS
React-Redux License
React Virtualized License
+#endif
Red Hat xdg_user_dir_lookup License
+#ifdef MOZ_DEVTOOLS
Redux License
Reselect License
- Russian Spellchecking Dictionary License
+#endif
SCTP Licenses
+#ifdef MOZ_ENABLE_SKIA
Skia License
+#endif
Snappy License
+#ifdef MOZ_DEVTOOLS_SERVER
sprintf.js License
+#endif
SunSoft License
SuperFastHash License
Unicode License
University of California License
US English Spellchecking Dictionary Licenses
V8 License
-#if defined(XP_WIN) || defined(XP_MACOSX) || defined(XP_LINUX)
- Valve BSD License
-#endif
VTune License
+#ifdef MOZ_WEBRTC
WebRTC License
x264 License
+#endif
Xiph.org Foundation License
@@ -2053,7 +2072,7 @@ Public License instead of this License. But first, please read
<http://www.gnu.org/philosophy/why-not-lgpl.html >.
-
+#ifdef MOZ_WEBRTC
ACE License
This license applies to the file
@@ -2077,11 +2096,13 @@ executables of your software products.
-
+#endif
Adobe CMap License
- This license applies to files in the directory
- browser/extensions/pdfjs/content/web/cmaps/ .
+ This license applies to files in application directories for
+ applications including the pdf.js in-application PDF reader,
+ specifically
+ */pdfjs/content/web/cmaps/ .
Copyright 1990-2009 Adobe Systems Incorporated.
@@ -2122,41 +2143,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
- Android Open Source License
-
- This license applies to various files in the Mozilla codebase,
- including those in the directory gfx/skia/ .
-
-
-
- Copyright 2009, The Android Open Source Project
-
- Redistribution and use in source and binary forms, with or without
- modification, are permitted provided that the following conditions
- are met:
- * Redistributions of source code must retain the above copyright
- notice, this list of conditions and the following disclaimer.
- * Redistributions in binary form must reproduce the above copyright
- notice, this list of conditions and the following disclaimer in the
- documentation and/or other materials provided with the distribution.
-
- THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
- EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
- PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
- CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
- EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
- PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
- PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
- OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-
-
-
-
+#ifdef MOZ_ANGLE_RENDERER
ANGLE License
This license applies to files in the directory gfx/angle/ .
@@ -2198,7 +2185,8 @@ POSSIBILITY OF SUCH DAMAGE.
-
+#endif
+#ifdef MOZ_DEVTOOLS_SERVER
acorn License
This license applies to all files in
@@ -2232,6 +2220,7 @@ licences.
+#endif
#ifdef MOZ_INSTALL_TRACKING
Adjust SDK License
@@ -2559,6 +2548,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+#ifdef MOZ_UPDATER
bspatch License
This license applies to the files
@@ -2594,6 +2584,7 @@ POSSIBILITY OF SUCH DAMAGE.
+#endif
Cairo Component Licenses
@@ -2652,7 +2643,6 @@ WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
This license applies to parts of the code in:
editor/libeditor/EditorEventListener.cpp
- security/sandbox/
widget/cocoa/GfxInfo.mm
and also some files in these directories:
@@ -2700,7 +2690,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
+#ifdef MOZ_DEVTOOLS
CodeMirror License
This license applies to all files in
@@ -2777,7 +2767,7 @@ DEALINGS IN THE SOFTWARE.
D3 License
This license applies to the file
- devtools/client/shared/d3.js .
+ devtools/client/shared/vendor/d3.js .
Copyright (c) 2014, Michael Bostock
@@ -2840,6 +2830,7 @@ THE SOFTWARE.
+#endif
dtoa License
@@ -2866,47 +2857,6 @@ OF THIS SOFTWARE OR ITS FITNESS FOR ANY PARTICULAR PURPOSE.
- Dutch Spellchecking Dictionary License
-
- This license applies to the Dutch Spellchecking Dictionary. (This
- code only ships in some localized versions of this product.)
-
-
-Copyright (c) 2006, 2007 OpenTaal
-Copyright (c) 2001, 2002, 2003, 2005 Simon Brouwer e.a.
-Copyright (c) 1996 Nederlandstalige Tex Gebruikersgroep
-
-All rights reserved.
-
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are met:
-
-* Redistributions of source code must retain the above copyright notice, this
-list of conditions and the following disclaimer.
-* Redistributions in binary form must reproduce the above copyright notice,
-this list of conditions and the following disclaimer in the documentation
-and/or other materials provided with the distribution.
-* Neither the name of the OpenTaal, Simon Brouwer e.a., or Nederlandstalige Tex
-Gebruikersgroep nor the names of its contributors may be used to endorse or
-promote products derived from this software without specific prior written
-permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
-"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
-LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
-A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
-CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
-EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
-PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
-PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
-LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
-NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
-SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-
-
-
-
#if defined(XP_WIN) || defined(XP_LINUX)
Twemoji License
@@ -2951,56 +2901,6 @@ publicity, privacy, or moral rights may limit how you use the material.
#endif
- Estonian Spellchecking Dictionary License
-
- This license applies to precursor works to certain files which are
- part of the Estonian Spellchecking Dictionary. The
- shipped versions are under the GNU Lesser General Public License. (This
- code only ships in some localized versions of this product.)
-
-
-Copyright © Institute of the Estonian Language
-
-E-mail: litsents@eki.ee
-URL: http://www.eki.ee/tarkvara/
-
-The present Licence Agreement gives the user of this Software Product
-(hereinafter: Product) the right to use the Product for whatever purpose
-(incl. distribution, copying, altering, inclusion in other software, and
-selling) on the following conditions:
-
-1. The present Licence Agreement should belong unaltered to each copy ever
- made of this Product;
-2. Neither the Institute of the Estonian Language (hereinafter: IEL) nor the
- author(s) of the Product will take responsibility for any detriment, direct
- or indirect, possibly ensuing from the application of the Product;
-3. The IEL is ready to share the Product with other users as we wish to
- advance research on the Estonian language and to promote the use of
- Estonian in rapidly developing infotechnology, yet we refuse to bind
- ourselves to any further obligation, which means that the IEL is not
- obliged either to warrant the suitability of the Product for a specific
- purpose, to improve the software, or to provide a more detailed description
- of the underlying algorithms. (Which does not mean, though, that we may not
- do it.)
-
-Notification Request:
-
-As a courtesy, we would appreciate being informed whenever our linguistic
-products are used to create derivative works. If you modify our software or
-include it in other products, please inform us by sending e-mail to
-litsents@eki.ee or by letter to
-
-Institute of the Estonian Language
-Roosikrantsi 6
-10119 Tallinn
-ESTONIA
-
-Phone & Fax: +372 6411443
-
-
-
-
-
Expat License
@@ -3036,8 +2936,7 @@ SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
-
- Firebug License
+#ifdef MOZ_DEVTOOLS_SERVER Firebug License
This license applies to the code
devtools/shared/webconsole/network-helper.js .
@@ -3079,6 +2978,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+#endif
gfxFontList License
@@ -3122,7 +3022,6 @@ THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Google BSD License
This license applies to files in the directories
- toolkit/crashreporter/google-breakpad/ and
toolkit/components/protobuf/ .
@@ -3159,30 +3058,29 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- Google VP8 License
+ VPX License
- This license applies to certain files in the directory
+
This license applies to the files in the directory
media/libvpx .
-Copyright (c) 2010, Google, Inc.
-
-All rights reserved.
+Copyright (c) 2010, The WebM Project authors. All rights reserved.
Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions
-are met:
+modification, are permitted provided that the following conditions are
+met:
-- Redistributions of source code must retain the above copyright
- notice, this list of conditions and the following disclaimer.
+ * Redistributions of source code must retain the above copyright
+ notice, this list of conditions and the following disclaimer.
-- Redistributions in binary form must reproduce the above
- copyright notice, this list of conditions and the following
- disclaimer in the documentation and/or other materials provided
- with the distribution.
+ * Redistributions in binary form must reproduce the above copyright
+ notice, this list of conditions and the following disclaimer in
+ the documentation and/or other materials provided with the
+ distribution.
-- Neither the name of Google nor the names of its contributors may
- be used to endorse or promote products derived from this software
- without specific prior written permission.
+ * Neither the name of Google, nor the WebM Project, nor the names
+ of its contributors may be used to endorse or promote products
+ derived from this software without specific prior written
+ permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
@@ -3196,22 +3094,29 @@ THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-Subject to the terms and conditions of the above License, Google
-hereby grants to You a perpetual, worldwide, non-exclusive,
-no-charge, royalty-free, irrevocable (except as stated in this
-section) patent license to make, have made, use, offer to sell, sell,
-import, and otherwise transfer this implementation of VP8, where such
-license applies only to those patent claims, both currently owned by
-Google and acquired in the future, licensable by Google that are
-necessarily infringed by this implementation of VP8. If You or your
-agent or exclusive licensee institute or order or agree to the
-institution of patent litigation against any entity (including a
-cross-claim or counterclaim in a lawsuit) alleging that this
-implementation of VP8 or any code incorporated within this
-implementation of VP8 constitutes direct or contributory patent
-infringement, or inducement of patent infringement, then any rights
-granted to You under this License for this implementation of VP8
-shall terminate as of the date such litigation is filed.
+Additional IP Rights Grant (Patents)
+------------------------------------
+
+"These implementations" means the copyrightable works that implement the WebM
+codecs distributed by Google as part of the WebM Project.
+
+Google hereby grants to you a perpetual, worldwide, non-exclusive, no-charge,
+royalty-free, irrevocable (except as stated in this section) patent license to
+make, have made, use, offer to sell, sell, import, transfer, and otherwise
+run, modify and propagate the contents of these implementations of WebM, where
+such license applies only to those patent claims, both currently owned by
+Google and acquired in the future, licensable by Google that are necessarily
+infringed by these implementations of WebM. This grant does not include claims
+that would be infringed only as a consequence of further modification of these
+implementations. If you or your agent or exclusive licensee institute or order
+or agree to the institution of patent litigation or any other patent
+enforcement activity against any entity (including a cross-claim or
+counterclaim in a lawsuit) alleging that any of these implementations of WebM
+or any code incorporated within any of these implementations of WebM
+constitute direct or contributory patent infringement, or inducement of
+patent infringement, then any patent rights granted to you under this License
+for these implementations of WebM shall terminate as of the date such
+litigation is filed.
@@ -3290,6 +3195,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Copyright (c) 2015 Microsoft Corporation. All rights reserved.
+Copyright (c) 2020 Moonchild Productions. All rights reserved.
This code is licensed under the MIT License (MIT).
@@ -3314,7 +3220,7 @@ THE SOFTWARE.
-
+#ifdef MOZ_WEBRTC
gyp License
This license applies to certain files in the directory
@@ -3351,6 +3257,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+#endif
halloc License
@@ -3470,6 +3377,8 @@ All trademarks and registered trademarks mentioned herein are the property
of their respective owners.
+
+#ifdef MOZ_DEVTOOLS
Immutable.js License
@@ -3506,6 +3415,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+#endif
Japan Network Information Center License
This license applies to certain files in the
@@ -3624,8 +3534,8 @@ SUCH DAMAGE.
This license applies to the following files:
- openmax_dl/dl/api/omxtypes.h
- openmax_dl/dl/sp/api/omxSP.h
+ media/openmax_dl/dl/api/omxtypes.h
+ media/openmax_dl/dl/sp/api/omxSP.h
@@ -3663,6 +3573,7 @@ Khronos and OpenMAX are trademarks of the Khronos Group Inc.
Copyright (c) 2003-2010 Mark Borgerding
+Copyright (c) 2017 Mark Straver BASc
All rights reserved.
@@ -3945,43 +3856,6 @@ THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-
- Lithuanian Spellchecking Dictionary License
-
- This license applies to the Lithuanian Spellchecking Dictionary. (This
- code only ships in some localized versions of this product.)
-
-
-Copyright (c) 2000-2013, Albertas Agejevas and contributors.
-All rights reserved.
-
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions
-are met:
-1. Redistributions of source code must retain the above copyright
- notice, this list of conditions and the following disclaimer.
-2. Redistributions in binary form must reproduce the above copyright
- notice, this list of conditions and the following disclaimer in the
- documentation and/or other materials provided with the distribution.
-3. Neither the name of the copyright holders nor the names of its contributors
- may be used to endorse or promote products derived from this software
- without specific prior written permission.
-
-THIS SOFTWARE IS PROVIDED BY COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
-ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-ARE DISCLAIMED. IN NO EVENT SHALL ALBERTAS AGEJEVAS OR CONTRIBUTORS BE LIABLE
-FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
-OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
-HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
-LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
-OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
-SUCH DAMAGE.
-
-
-
MIT license — microformat-shiv
@@ -4056,7 +3930,7 @@ SUCH DAMAGE.
-
+#ifdef MOZ_DEVTOOLS
naturalSort License
This license applies to devtools/client/shared/natural-sort.js .
@@ -4086,7 +3960,8 @@ THE SOFTWARE.
-
+#endif
+#ifdef MOZ_WEBRTC
nICEr License
This license applies to certain files in the directory
@@ -4131,7 +4006,8 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
+#endif
+#ifdef MOZ_EME
OpenAES License
This license applies to certain files in the directory
@@ -4166,6 +4042,7 @@ POSSIBILITY OF SUCH DAMAGE.
+#endif
OpenVision License
@@ -4195,7 +4072,7 @@ PERFORMANCE OF THIS SOFTWARE.
-
+#ifdef MOZ_DEVTOOLS_SERVER
node-properties License
This license applies to
@@ -4226,7 +4103,8 @@ THE SOFTWARE.
-
+#endif
+#ifdef MOZ_WEBRTC
nrappkit License
This license applies to certain files in the directory
@@ -4373,6 +4251,7 @@ ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+#endif
praton License
@@ -4444,41 +4323,6 @@ OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
-
-
- pbkdf2_sha256 License
-
- This license applies to the code
- mozglue/android/pbkdf2_sha256.c and
- mozglue/android/pbkdf2_sha256.h .
-
-
-
-Copyright 2005,2007,2009 Colin Percival
-All rights reserved.
-
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions
-are met:
-1. Redistributions of source code must retain the above copyright
- notice, this list of conditions and the following disclaimer.
-2. Redistributions in binary form must reproduce the above copyright
- notice, this list of conditions and the following disclaimer in the
- documentation and/or other materials provided with the distribution.
-
-THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
-ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
-FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
-OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
-HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
-LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
-OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
-SUCH DAMAGE.
-
-
qcms License
@@ -4511,6 +4355,7 @@ CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+#ifdef MOZ_DEVTOOLS_SERVER
QR Code Generator License
This license applies to certain files in the directory
@@ -4539,6 +4384,7 @@ THE SOFTWARE.
+#endif
React License
@@ -4576,6 +4422,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+#ifdef MOZ_DEVTOOLS
React-Redux License
This license applies to the file
@@ -4631,6 +4478,7 @@ SOFTWARE.
+#endif
Red Hat xdg_user_dir_lookup License
@@ -4663,7 +4511,7 @@ SOFTWARE.
-
+#ifdef MOZ_DEVTOOLS
Redux License
This license applies to the file
@@ -4721,44 +4569,7 @@ SOFTWARE.
-
- Russian Spellchecking Dictionary License
-
- This license applies to the Russian Spellchecking Dictionary. (This
- code only ships in some localized versions of this product.)
-
-
-* Copyright (c) 1997-2008, Alexander I. Lebedev
-
-All rights reserved.
-
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions
-are met:
-* Redistributions of source code must retain the above copyright
- notice, this list of conditions and the following disclaimer.
-* Redistributions in binary form must reproduce the above copyright
- notice, this list of conditions and the following disclaimer in the
- documentation and/or other materials provided with the distribution.
-* Modified versions must be clearly marked as such.
-* The name of Alexander I. Lebedev may not be used to endorse or promote
- products derived from this software without specific prior written
- permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
-AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
-LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
-CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
-SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
-INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
-CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
-ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGE.
-
-
-
+#endif
SCTP Licenses
@@ -4831,6 +4642,7 @@ THE POSSIBILITY OF SUCH DAMAGE.
+#ifdef MOZ_ENABLE_SKIA
Skia License
This license applies to certain files in the directory
@@ -4867,6 +4679,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+#endif
Snappy License
@@ -4905,7 +4718,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
+#ifdef MOZ_DEVTOOLS_SERVER
sprintf.js License
This license applies to
@@ -4939,6 +4752,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+#endif
SunSoft License
@@ -4978,42 +4792,6 @@ authorization from SunSoft Inc.
-
-
- SuperFastHash License
-
- This license applies to files in the directory
- security/sandbox/chromium/base/third_party/superfasthash/ .
-
-
-Copyright (c) 2010, Paul Hsieh
-All rights reserved.
-
-Redistribution and use in source and binary forms, with or without modification,
-are permitted provided that the following conditions are met:
-
-* Redistributions of source code must retain the above copyright notice, this
- list of conditions and the following disclaimer.
-* Redistributions in binary form must reproduce the above copyright notice, this
- list of conditions and the following disclaimer in the documentation and/or
- other materials provided with the distribution.
-* Neither my name, Paul Hsieh, nor the names of any other contributors to the
- code use may not be used to endorse or promote products derived from this
- software without specific prior written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
-ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
-ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
-(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
-LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
-ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
-(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
-SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-
-
Unicode License
@@ -5419,7 +5197,7 @@ Database section 7.
directories, certain files in those directories:
-Copyright (c) 2015, Valve Corporation
-All rights reserved.
-
-Redistribution and use in source and binary forms, with or without modification,
-are permitted provided that the following conditions are met:
-
-1. Redistributions of source code must retain the above copyright notice, this
-list of conditions and the following disclaimer.
-
-2. Redistributions in binary form must reproduce the above copyright notice,
-this list of conditions and the following disclaimer in the documentation and/or
-other materials provided with the distribution.
-
-3. Neither the name of the copyright holder nor the names of its contributors
-may be used to endorse or promote products derived from this software without
-specific prior written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
-ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR
-ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
-(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
-LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
-ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
-(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
-SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-
-#endif
-
-
-
VTune License
This license applies to certain files in the directory
@@ -5675,7 +5415,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
+#ifdef MOZ_WEBRTC
WebRTC License
This license applies to certain files in the directory
@@ -5743,6 +5483,7 @@ OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+#endif
Xiph.org Foundation License
@@ -5795,10 +5536,6 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
This software is based in part on the work of the Independent
JPEG Group.
- Portions of the OS/2 and Android versions
- of this software are copyright ©1996-2012
- The FreeType Project .
- All rights reserved.
@@ -5825,16 +5562,14 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-#ifdef XP_WIN
-
+#ifdef XP_WIN
Proprietary Operating System Components
Under some circumstances, under our
- binary components policy ,
- Mozilla may decide to include additional
+ Binary Component Policy ,
+ we may decide to include additional
operating system vendor code with the installer of our products designed
for that vendor's proprietary platform, to make our products work well on
that specific operating system. The following license statements
@@ -5846,7 +5581,8 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
they are referred to below as "Distributable Code":
d3d*.dll (Direct3D libraries)
- msvc*.dll (C and C++ runtime libraries)
+ msvc*.dll and vcruntime*.dll (C and C++ runtime libraries)
+ api-ms-win*.dll and ucrtbase.dll (Universal CRT runtime libraries)
@@ -5870,10 +5606,8 @@ following terms:
regulations that apply to the Distributable Code.
-#endif
-
-
+#endif
Return to top .
From d86d1256bc910d4e88e9d156f8d857f3656bde08 Mon Sep 17 00:00:00 2001
From: Moonchild
Date: Wed, 24 Feb 2021 09:05:30 +0000
Subject: [PATCH 3/9] [dom] Update noscript serialization to the changed spec.
Make escaping conditional on whether scripting is enabled.
---
dom/base/nsContentUtils.cpp | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/dom/base/nsContentUtils.cpp b/dom/base/nsContentUtils.cpp
index 107daaede6..7dc6ccb990 100644
--- a/dom/base/nsContentUtils.cpp
+++ b/dom/base/nsContentUtils.cpp
@@ -9140,10 +9140,6 @@ ShouldEscape(nsIContent* aParent)
nsGkAtoms::style, nsGkAtoms::script, nsGkAtoms::xmp,
nsGkAtoms::iframe, nsGkAtoms::noembed, nsGkAtoms::noframes,
nsGkAtoms::plaintext,
- // Per the current spec noscript should be escaped in case
- // scripts are disabled or if document doesn't have
- // browsing context. However the latter seems to be a spec bug
- // and Gecko hasn't traditionally done the former.
nsGkAtoms::noscript
};
static mozilla::BloomFilter<12, nsIAtom> sFilter;
@@ -9159,6 +9155,10 @@ ShouldEscape(nsIContent* aParent)
if (sFilter.mightContain(tag)) {
for (uint32_t i = 0; i < ArrayLength(nonEscapingElements); ++i) {
if (tag == nonEscapingElements[i]) {
+ if (MOZ_UNLIKELY(tag == nsGkAtoms::noscript) &&
+ MOZ_UNLIKELY(!aParent->OwnerDoc()->IsScriptEnabled())) {
+ return true;
+ }
return false;
}
}
From 5934c74a3fda58b4b72d9fc4e92ced28a57d0ef4 Mon Sep 17 00:00:00 2001
From: Moonchild
Date: Wed, 24 Feb 2021 09:57:24 +0000
Subject: [PATCH 4/9] [html parser] Check for integer overflow when computing
new buffer sizes.
---
.../nu/validator/htmlparser/impl/MetaScanner.java | 8 ++++----
.../nu/validator/htmlparser/impl/Portability.java | 15 ++++++++++++++-
.../nu/validator/htmlparser/impl/Tokenizer.java | 8 ++++----
parser/html/nsHtml5MetaScanner.cpp | 2 +-
parser/html/nsHtml5Portability.cpp | 9 +++++++++
parser/html/nsHtml5Portability.h | 3 ++-
parser/html/nsHtml5Tokenizer.cpp | 4 ++--
7 files changed, 36 insertions(+), 13 deletions(-)
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/MetaScanner.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/MetaScanner.java
index be7576ff0e..29c5138a41 100644
--- a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/MetaScanner.java
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/MetaScanner.java
@@ -1,7 +1,7 @@
/*
* Copyright (c) 2007 Henri Sivonen
* Copyright (c) 2008-2015 Mozilla Foundation
- * Copyright (c) 2018-2020 Moonchild Productions
+ * Copyright (c) 2018-2021 Moonchild Productions
* Copyright (c) 2020 Binary Outcast
*
* Permission is hereby granted, free of charge, to any person obtaining a
@@ -753,7 +753,7 @@ public abstract class MetaScanner {
stateSave = state;
}
- private void handleCharInAttributeValue(int c) {
+ private void handleCharInAttributeValue(int c) throws SAXException {
if (metaState == A) {
if (contentIndex == CONTENT.length || charsetIndex == CHARSET.length) {
addToBuffer(c);
@@ -778,9 +778,9 @@ public abstract class MetaScanner {
* Adds a character to the accumulation buffer.
* @param c the character to add
*/
- private void addToBuffer(int c) {
+ private void addToBuffer(int c) throws SAXException {
if (strBufLen == strBuf.length) {
- char[] newBuf = new char[strBuf.length + (strBuf.length << 1)];
+ char[] newBuf = new char[Portability.checkedAdd(strBuf.length, (strBuf.length << 1))];
System.arraycopy(strBuf, 0, newBuf, 0, strBuf.length);
strBuf = newBuf;
}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/Portability.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/Portability.java
index 8f941ce018..a83c3d519b 100644
--- a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/Portability.java
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/Portability.java
@@ -1,6 +1,6 @@
/*
* Copyright (c) 2008-2015 Mozilla Foundation
- * Copyright (c) 2018-2020 Moonchild Productions
+ * Copyright (c) 2018-2021 Moonchild Productions
* Copyright (c) 2020 Binary Outcast
*
* Permission is hereby granted, free of charge, to any person obtaining a
@@ -24,6 +24,8 @@
package nu.validator.htmlparser.impl;
+import org.xml.sax.SAXException;
+
import nu.validator.htmlparser.annotation.Literal;
import nu.validator.htmlparser.annotation.Local;
import nu.validator.htmlparser.annotation.NoLength;
@@ -31,6 +33,17 @@ import nu.validator.htmlparser.common.Interner;
public final class Portability {
+ public static int checkedAdd(int a, int b) throws SAXException {
+ // This can't be translated code, because in C++ signed integer overflow is UB, so the below code would be wrong.
+ assert a >= 0;
+ assert b >= 0;
+ int sum = a + b;
+ if (sum < a || sum < b) {
+ throw new SAXException("Integer overflow");
+ }
+ return sum;
+ }
+
// Allocating methods
/**
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/Tokenizer.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/Tokenizer.java
index 3d617fd01f..028b7a7d1e 100644
--- a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/Tokenizer.java
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/Tokenizer.java
@@ -1,7 +1,7 @@
/*
* Copyright (c) 2005-2007 Henri Sivonen
* Copyright (c) 2007-2015 Mozilla Foundation
- * Copyright (c) 2018-2020 Moonchild Productions
+ * Copyright (c) 2018-2021 Moonchild Productions
* Copyright (c) 2020 Binary Outcast
* Portions of comments Copyright 2004-2010 Apple Computer, Inc., Mozilla
* Foundation, and Opera Software ASA.
@@ -1009,8 +1009,8 @@ public class Tokenizer implements Locator {
// ]NOCPP]
}
- private void appendStrBuf(@NoLength char[] buffer, int offset, int length) {
- int newLen = strBufLen + length;
+ private void appendStrBuf(@NoLength char[] buffer, int offset, int length) throws SAXException {
+ int newLen = Portability.checkedAdd(strBufLen, length);
// CPPONLY: assert newLen <= strBuf.length: "Previous buffer length insufficient.";
// CPPONLY: if (strBuf.length < newLen) {
// CPPONLY: if (!EnsureBufferSpace(length)) {
@@ -1024,7 +1024,7 @@ public class Tokenizer implements Locator {
/**
* Append the contents of the char reference buffer to the main one.
*/
- @Inline private void appendCharRefBufToStrBuf() {
+ @Inline private void appendCharRefBufToStrBuf() throws SAXException {
appendStrBuf(charRefBuf, 0, charRefBufLen);
charRefBufLen = 0;
}
diff --git a/parser/html/nsHtml5MetaScanner.cpp b/parser/html/nsHtml5MetaScanner.cpp
index 9fa3d3a705..f7beddafd5 100644
--- a/parser/html/nsHtml5MetaScanner.cpp
+++ b/parser/html/nsHtml5MetaScanner.cpp
@@ -743,7 +743,7 @@ void
nsHtml5MetaScanner::addToBuffer(int32_t c)
{
if (strBufLen == strBuf.length) {
- jArray newBuf = jArray::newJArray(strBuf.length + (strBuf.length << 1));
+ jArray newBuf = jArray::newJArray(nsHtml5Portability::checkedAdd(strBuf.length, (strBuf.length << 1)));
nsHtml5ArrayCopy::arraycopy(strBuf, newBuf, strBuf.length);
strBuf = newBuf;
}
diff --git a/parser/html/nsHtml5Portability.cpp b/parser/html/nsHtml5Portability.cpp
index 400f062048..613f4e5305 100644
--- a/parser/html/nsHtml5Portability.cpp
+++ b/parser/html/nsHtml5Portability.cpp
@@ -7,6 +7,15 @@
#include "jArray.h"
#include "nsHtml5Portability.h"
#include "nsHtml5TreeBuilder.h"
+#include "mozilla/CheckedInt.h"
+
+int32_t nsHtml5Portability::checkedAdd(int32_t a, int32_t b) {
+ mozilla::CheckedInt sum(a);
+ sum += b;
+ MOZ_RELEASE_ASSERT(sum.isValid(),
+ "HTML input too large for signed 32-bit integer.");
+ return sum.value();
+}
nsIAtom*
nsHtml5Portability::newLocalNameFromBuffer(char16_t* buf, int32_t offset, int32_t length, nsHtml5AtomTable* interner)
diff --git a/parser/html/nsHtml5Portability.h b/parser/html/nsHtml5Portability.h
index 2a9d9422b5..3421b410cf 100644
--- a/parser/html/nsHtml5Portability.h
+++ b/parser/html/nsHtml5Portability.h
@@ -1,6 +1,6 @@
/*
* Copyright (c) 2008-2015 Mozilla Foundation
- * Copyright (c) 2018-2020 Moonchild Productions
+ * Copyright (c) 2018-2021 Moonchild Productions
* Copyright (c) 2020 Binary Outcast
*
* Permission is hereby granted, free of charge, to any person obtaining a
@@ -60,6 +60,7 @@ class nsHtml5StateSnapshot;
class nsHtml5Portability
{
public:
+ static int32_t checkedAdd(int32_t a, int32_t b);
static nsIAtom* newLocalNameFromBuffer(char16_t* buf, int32_t offset, int32_t length, nsHtml5AtomTable* interner);
static nsHtml5String newStringFromBuffer(char16_t* buf, int32_t offset, int32_t length, nsHtml5TreeBuilder* treeBuilder, bool maybeAtomize);
static nsHtml5String newEmptyString();
diff --git a/parser/html/nsHtml5Tokenizer.cpp b/parser/html/nsHtml5Tokenizer.cpp
index 60285ce8ee..4c6a32f731 100644
--- a/parser/html/nsHtml5Tokenizer.cpp
+++ b/parser/html/nsHtml5Tokenizer.cpp
@@ -1,7 +1,7 @@
/*
* Copyright (c) 2005-2007 Henri Sivonen
* Copyright (c) 2007-2015 Mozilla Foundation
- * Copyright (c) 2018-2020 Moonchild Productions
+ * Copyright (c) 2018-2021 Moonchild Productions
* Copyright (c) 2020 Binary Outcast
* Portions of comments Copyright 2004-2010 Apple Computer, Inc., Mozilla
* Foundation, and Opera Software ASA.
@@ -249,7 +249,7 @@ nsHtml5Tokenizer::emitStrBuf()
void
nsHtml5Tokenizer::appendStrBuf(char16_t* buffer, int32_t offset, int32_t length)
{
- int32_t newLen = strBufLen + length;
+ int32_t newLen = nsHtml5Portability::checkedAdd(strBufLen, length);
MOZ_ASSERT(newLen <= strBuf.length, "Previous buffer length insufficient.");
if (MOZ_UNLIKELY(strBuf.length < newLen)) {
if (MOZ_UNLIKELY(!EnsureBufferSpace(length))) {
From 8a55eab0f07dd4ef9f994089390eb8b1a912154b Mon Sep 17 00:00:00 2001
From: Moonchild
Date: Wed, 24 Feb 2021 10:13:37 +0000
Subject: [PATCH 5/9] [DOM] Don't reveal error details for CORS-cross-origin
decoding errors.
---
dom/html/HTMLMediaElement.cpp | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/dom/html/HTMLMediaElement.cpp b/dom/html/HTMLMediaElement.cpp
index 0828208f69..1ff1fd7a45 100644
--- a/dom/html/HTMLMediaElement.cpp
+++ b/dom/html/HTMLMediaElement.cpp
@@ -4614,8 +4614,12 @@ void HTMLMediaElement::DecodeError(const MediaResult& aError)
}
} else if (mReadyState == nsIDOMHTMLMediaElement::HAVE_NOTHING) {
NoSupportedMediaSourceError(aError.Description());
- } else {
+ } else if (IsCORSSameOrigin()) {
Error(MEDIA_ERR_DECODE, aError.Description());
+ } else {
+ nsAutoCString eMessage;
+ eMessage.AssignLiteral("Failed to decode media");
+ Error(MEDIA_ERR_DECODE, eMessage);
}
}
From ef29cca22466dfbf7f74a2812068b271df09f758 Mon Sep 17 00:00:00 2001
From: Moonchild
Date: Wed, 24 Feb 2021 10:48:34 +0000
Subject: [PATCH 6/9] [security] Hold mutex when accessing TSI fields.
---
security/manager/ssl/TransportSecurityInfo.cpp | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/security/manager/ssl/TransportSecurityInfo.cpp b/security/manager/ssl/TransportSecurityInfo.cpp
index 3f4bf4a904..6badceb880 100644
--- a/security/manager/ssl/TransportSecurityInfo.cpp
+++ b/security/manager/ssl/TransportSecurityInfo.cpp
@@ -74,6 +74,7 @@ NS_IMPL_ISUPPORTS(TransportSecurityInfo,
nsresult
TransportSecurityInfo::SetHostName(const char* host)
{
+ MutexAutoLock lock(mMutex);
mHostName.Adopt(host ? NS_strdup(host) : 0);
return NS_OK;
}
@@ -103,6 +104,7 @@ nsresult
TransportSecurityInfo::SetOriginAttributes(
const NeckoOriginAttributes& aOriginAttributes)
{
+ MutexAutoLock lock(mMutex);
mOriginAttributes = aOriginAttributes;
return NS_OK;
}
@@ -136,6 +138,7 @@ TransportSecurityInfo::GetSecurityState(uint32_t* state)
nsresult
TransportSecurityInfo::SetSecurityState(uint32_t aState)
{
+ MutexAutoLock lock(mMutex);
mSecurityState = aState;
return NS_OK;
}
@@ -152,6 +155,7 @@ NS_IMETHODIMP
TransportSecurityInfo::SetCountSubRequestsBrokenSecurity(
int32_t aSubRequestsBrokenSecurity)
{
+ MutexAutoLock lock(mMutex);
mSubRequestsBrokenSecurity = aSubRequestsBrokenSecurity;
return NS_OK;
}
@@ -168,6 +172,7 @@ NS_IMETHODIMP
TransportSecurityInfo::SetCountSubRequestsNoSecurity(
int32_t aSubRequestsNoSecurity)
{
+ MutexAutoLock lock(mMutex);
mSubRequestsNoSecurity = aSubRequestsNoSecurity;
return NS_OK;
}
@@ -515,6 +520,7 @@ TransportSecurityInfo::GetSSLStatus(nsISSLStatus** _result)
nsresult
TransportSecurityInfo::SetSSLStatus(nsSSLStatus *aSSLStatus)
{
+ MutexAutoLock lock(mMutex);
mSSLStatus = aSSLStatus;
return NS_OK;
From 9fd40b1c9328cd7459a1dd746a13e5f7f0ed7bb0 Mon Sep 17 00:00:00 2001
From: Moonchild
Date: Wed, 24 Feb 2021 11:09:47 +0000
Subject: [PATCH 7/9] Issue #457 - Remove duplicate PKCS11 definitions
---
security/manager/ssl/nsKeygenHandler.cpp | 4 ----
1 file changed, 4 deletions(-)
diff --git a/security/manager/ssl/nsKeygenHandler.cpp b/security/manager/ssl/nsKeygenHandler.cpp
index 0af761d7e4..8d8a98e73d 100644
--- a/security/manager/ssl/nsKeygenHandler.cpp
+++ b/security/manager/ssl/nsKeygenHandler.cpp
@@ -26,10 +26,6 @@
#include "secder.h"
#include "secdert.h"
-//These defines are taken from the PKCS#11 spec
-#define CKM_RSA_PKCS_KEY_PAIR_GEN 0x00000000
-#define CKM_DH_PKCS_KEY_PAIR_GEN 0x00000020
-
DERTemplate SECAlgorithmIDTemplate[] = {
{ DER_SEQUENCE,
0, nullptr, sizeof(SECAlgorithmID) },
From 63637d3f818415fa3907db0e9dce41d62f2cff13 Mon Sep 17 00:00:00 2001
From: Moonchild
Date: Wed, 24 Feb 2021 12:16:57 +0000
Subject: [PATCH 8/9] [MFBT] Update lz4 to 1.9.3
---
mfbt/lz4.c | 2379 +++++++++++++++++++++++++++++++++++++---------------
mfbt/lz4.h | 789 +++++++++++------
2 files changed, 2246 insertions(+), 922 deletions(-)
diff --git a/mfbt/lz4.c b/mfbt/lz4.c
index 5752b4d17b..9f5e9bfa08 100644
--- a/mfbt/lz4.c
+++ b/mfbt/lz4.c
@@ -1,6 +1,6 @@
/*
LZ4 - Fast LZ compression algorithm
- Copyright (C) 2011-2017, Yann Collet.
+ Copyright (C) 2011-present, Yann Collet.
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
@@ -32,7 +32,6 @@
- LZ4 source repository : https://github.com/lz4/lz4
*/
-
/*-************************************
* Tuning parameters
**************************************/
@@ -46,10 +45,16 @@
#endif
/*
- * ACCELERATION_DEFAULT :
+ * LZ4_ACCELERATION_DEFAULT :
* Select "acceleration" for LZ4_compress_fast() when parameter value <= 0
*/
-#define ACCELERATION_DEFAULT 1
+#define LZ4_ACCELERATION_DEFAULT 1
+/*
+ * LZ4_ACCELERATION_MAX :
+ * Any "acceleration" value higher than this threshold
+ * get treated as LZ4_ACCELERATION_MAX instead (fix #876)
+ */
+#define LZ4_ACCELERATION_MAX 65537
/*-************************************
@@ -69,9 +74,11 @@
* Prefer these methods in priority order (0 > 1 > 2)
*/
#ifndef LZ4_FORCE_MEMORY_ACCESS /* can be defined externally */
-# if defined(__GNUC__) && ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) )
+# if defined(__GNUC__) && \
+ ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) \
+ || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) )
# define LZ4_FORCE_MEMORY_ACCESS 2
-# elif defined(__INTEL_COMPILER) || defined(__GNUC__)
+# elif (defined(__INTEL_COMPILER) && !defined(_WIN32)) || defined(__GNUC__)
# define LZ4_FORCE_MEMORY_ACCESS 1
# endif
#endif
@@ -80,14 +87,33 @@
* LZ4_FORCE_SW_BITCOUNT
* Define this parameter if your target system or compiler does not support hardware bit count
*/
-#if defined(_MSC_VER) && defined(_WIN32_WCE) /* Visual Studio for Windows CE does not support Hardware bit count */
+#if defined(_MSC_VER) && defined(_WIN32_WCE) /* Visual Studio for WinCE doesn't support Hardware bit count */
+# undef LZ4_FORCE_SW_BITCOUNT /* avoid double def */
# define LZ4_FORCE_SW_BITCOUNT
#endif
+
/*-************************************
* Dependency
**************************************/
+/*
+ * LZ4_SRC_INCLUDED:
+ * Amalgamation flag, whether lz4.c is included
+ */
+#ifndef LZ4_SRC_INCLUDED
+# define LZ4_SRC_INCLUDED 1
+#endif
+
+#ifndef LZ4_STATIC_LINKING_ONLY
+#define LZ4_STATIC_LINKING_ONLY
+#endif
+
+#ifndef LZ4_DISABLE_DEPRECATE_WARNINGS
+#define LZ4_DISABLE_DEPRECATE_WARNINGS /* due to LZ4_decompress_safe_withPrefix64k */
+#endif
+
+#define LZ4_STATIC_LINKING_ONLY /* LZ4_DISTANCE_MAX */
#include "lz4.h"
/* see also "memory routines" below */
@@ -95,27 +121,48 @@
/*-************************************
* Compiler Options
**************************************/
-#ifdef _MSC_VER /* Visual Studio */
-# include
-# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */
-# pragma warning(disable : 4293) /* disable: C4293: too large shift (32-bits) */
+#if defined(_MSC_VER) && (_MSC_VER >= 1400) /* Visual Studio 2005+ */
+# include /* only present in VS2005+ */
+# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */
#endif /* _MSC_VER */
-#ifndef FORCE_INLINE
+#ifndef LZ4_FORCE_INLINE
# ifdef _MSC_VER /* Visual Studio */
-# define FORCE_INLINE static __forceinline
+# define LZ4_FORCE_INLINE static __forceinline
# else
# if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */
# ifdef __GNUC__
-# define FORCE_INLINE static inline __attribute__((always_inline))
+# define LZ4_FORCE_INLINE static inline __attribute__((always_inline))
# else
-# define FORCE_INLINE static inline
+# define LZ4_FORCE_INLINE static inline
# endif
# else
-# define FORCE_INLINE static
+# define LZ4_FORCE_INLINE static
# endif /* __STDC_VERSION__ */
# endif /* _MSC_VER */
-#endif /* FORCE_INLINE */
+#endif /* LZ4_FORCE_INLINE */
+
+/* LZ4_FORCE_O2 and LZ4_FORCE_INLINE
+ * gcc on ppc64le generates an unrolled SIMDized loop for LZ4_wildCopy8,
+ * together with a simple 8-byte copy loop as a fall-back path.
+ * However, this optimization hurts the decompression speed by >30%,
+ * because the execution does not go to the optimized loop
+ * for typical compressible data, and all of the preamble checks
+ * before going to the fall-back path become useless overhead.
+ * This optimization happens only with the -O3 flag, and -O2 generates
+ * a simple 8-byte copy loop.
+ * With gcc on ppc64le, all of the LZ4_decompress_* and LZ4_wildCopy8
+ * functions are annotated with __attribute__((optimize("O2"))),
+ * and also LZ4_wildCopy8 is forcibly inlined, so that the O2 attribute
+ * of LZ4_wildCopy8 does not affect the compression speed.
+ */
+#if defined(__PPC64__) && defined(__LITTLE_ENDIAN__) && defined(__GNUC__) && !defined(__clang__)
+# define LZ4_FORCE_O2 __attribute__((optimize("O2")))
+# undef LZ4_FORCE_INLINE
+# define LZ4_FORCE_INLINE static __inline __attribute__((optimize("O2"),always_inline))
+#else
+# define LZ4_FORCE_O2
+#endif
#if (defined(__GNUC__) && (__GNUC__ >= 3)) || (defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 800)) || defined(__clang__)
# define expect(expr,value) (__builtin_expect ((expr),(value)) )
@@ -123,23 +170,107 @@
# define expect(expr,value) (expr)
#endif
+#ifndef likely
#define likely(expr) expect((expr) != 0, 1)
+#endif
+#ifndef unlikely
#define unlikely(expr) expect((expr) != 0, 0)
+#endif
+
+/* Should the alignment test prove unreliable, for some reason,
+ * it can be disabled by setting LZ4_ALIGN_TEST to 0 */
+#ifndef LZ4_ALIGN_TEST /* can be externally provided */
+# define LZ4_ALIGN_TEST 1
+#endif
/*-************************************
* Memory routines
**************************************/
-#include /* malloc, calloc, free */
-#define ALLOCATOR(n,s) calloc(n,s)
-#define FREEMEM free
+#ifdef LZ4_USER_MEMORY_FUNCTIONS
+/* memory management functions can be customized by user project.
+ * Below functions must exist somewhere in the Project
+ * and be available at link time */
+void* LZ4_malloc(size_t s);
+void* LZ4_calloc(size_t n, size_t s);
+void LZ4_free(void* p);
+# define ALLOC(s) LZ4_malloc(s)
+# define ALLOC_AND_ZERO(s) LZ4_calloc(1,s)
+# define FREEMEM(p) LZ4_free(p)
+#else
+# include /* malloc, calloc, free */
+# define ALLOC(s) malloc(s)
+# define ALLOC_AND_ZERO(s) calloc(1,s)
+# define FREEMEM(p) free(p)
+#endif
+
#include /* memset, memcpy */
-#define MEM_INIT memset
+#define MEM_INIT(p,v,s) memset((p),(v),(s))
/*-************************************
-* Basic Types
+* Common Constants
**************************************/
+#define MINMATCH 4
+
+#define WILDCOPYLENGTH 8
+#define LASTLITERALS 5 /* see ../doc/lz4_Block_format.md#parsing-restrictions */
+#define MFLIMIT 12 /* see ../doc/lz4_Block_format.md#parsing-restrictions */
+#define MATCH_SAFEGUARD_DISTANCE ((2*WILDCOPYLENGTH) - MINMATCH) /* ensure it's possible to write 2 x wildcopyLength without overflowing output buffer */
+#define FASTLOOP_SAFE_DISTANCE 64
+static const int LZ4_minLength = (MFLIMIT+1);
+
+#define KB *(1 <<10)
+#define MB *(1 <<20)
+#define GB *(1U<<30)
+
+#define LZ4_DISTANCE_ABSOLUTE_MAX 65535
+#if (LZ4_DISTANCE_MAX > LZ4_DISTANCE_ABSOLUTE_MAX) /* max supported by LZ4 format */
+# error "LZ4_DISTANCE_MAX is too big : must be <= 65535"
+#endif
+
+#define ML_BITS 4
+#define ML_MASK ((1U<=1)
+# include
+#else
+# ifndef assert
+# define assert(condition) ((void)0)
+# endif
+#endif
+
+#define LZ4_STATIC_ASSERT(c) { enum { LZ4_static_assert = 1/(int)(!!(c)) }; } /* use after variable declarations */
+
+#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=2)
+# include
+ static int g_debuglog_enable = 1;
+# define DEBUGLOG(l, ...) { \
+ if ((g_debuglog_enable) && (l<=LZ4_DEBUG)) { \
+ fprintf(stderr, __FILE__ ": "); \
+ fprintf(stderr, __VA_ARGS__); \
+ fprintf(stderr, " \n"); \
+ } }
+#else
+# define DEBUGLOG(l, ...) {} /* disabled */
+#endif
+
+static int LZ4_isAligned(const void* ptr, size_t alignment)
+{
+ return ((size_t)ptr & (alignment -1)) == 0;
+}
+
+
+/*-************************************
+* Types
+**************************************/
+#include
#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
# include
typedef uint8_t BYTE;
@@ -149,6 +280,9 @@
typedef uint64_t U64;
typedef uintptr_t uptrval;
#else
+# if UINT_MAX != 4294967295UL
+# error "LZ4 code (when not C++ or C99) assumes that sizeof(int) == 4"
+# endif
typedef unsigned char BYTE;
typedef unsigned short U16;
typedef unsigned int U32;
@@ -163,9 +297,31 @@
typedef size_t reg_t; /* 32-bits in x32 mode */
#endif
+typedef enum {
+ notLimited = 0,
+ limitedOutput = 1,
+ fillOutput = 2
+} limitedOutput_directive;
+
+
/*-************************************
* Reading and writing into memory
**************************************/
+
+/**
+ * LZ4 relies on memcpy with a constant size being inlined. In freestanding
+ * environments, the compiler can't assume the implementation of memcpy() is
+ * standard compliant, so it can't apply its specialized memcpy() inlining
+ * logic. When possible, use __builtin_memcpy() to tell the compiler to analyze
+ * memcpy() as if it were standard compliant, so it can inline it in freestanding
+ * environments. This is needed when decompressing the Linux Kernel, for example.
+ */
+#if defined(__GNUC__) && (__GNUC__ >= 4)
+#define LZ4_memcpy(dst, src, size) __builtin_memcpy(dst, src, size)
+#else
+#define LZ4_memcpy(dst, src, size) memcpy(dst, src, size)
+#endif
+
static unsigned LZ4_isLittleEndian(void)
{
const union { U32 u; BYTE c[4]; } one = { 1 }; /* don't use static : performance detrimental */
@@ -196,31 +352,31 @@ static reg_t LZ4_read_ARCH(const void* ptr) { return ((const unalign*)ptr)->uArc
static void LZ4_write16(void* memPtr, U16 value) { ((unalign*)memPtr)->u16 = value; }
static void LZ4_write32(void* memPtr, U32 value) { ((unalign*)memPtr)->u32 = value; }
-#else /* safe and portable access through memcpy() */
+#else /* safe and portable access using memcpy() */
static U16 LZ4_read16(const void* memPtr)
{
- U16 val; memcpy(&val, memPtr, sizeof(val)); return val;
+ U16 val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val;
}
static U32 LZ4_read32(const void* memPtr)
{
- U32 val; memcpy(&val, memPtr, sizeof(val)); return val;
+ U32 val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val;
}
static reg_t LZ4_read_ARCH(const void* memPtr)
{
- reg_t val; memcpy(&val, memPtr, sizeof(val)); return val;
+ reg_t val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val;
}
static void LZ4_write16(void* memPtr, U16 value)
{
- memcpy(memPtr, &value, sizeof(value));
+ LZ4_memcpy(memPtr, &value, sizeof(value));
}
static void LZ4_write32(void* memPtr, U32 value)
{
- memcpy(memPtr, &value, sizeof(value));
+ LZ4_memcpy(memPtr, &value, sizeof(value));
}
#endif /* LZ4_FORCE_MEMORY_ACCESS */
@@ -247,130 +403,216 @@ static void LZ4_writeLE16(void* memPtr, U16 value)
}
}
-static void LZ4_copy8(void* dst, const void* src)
-{
- memcpy(dst,src,8);
-}
-
/* customized variant of memcpy, which can overwrite up to 8 bytes beyond dstEnd */
-static void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd)
+LZ4_FORCE_INLINE
+void LZ4_wildCopy8(void* dstPtr, const void* srcPtr, void* dstEnd)
{
BYTE* d = (BYTE*)dstPtr;
const BYTE* s = (const BYTE*)srcPtr;
BYTE* const e = (BYTE*)dstEnd;
- do { LZ4_copy8(d,s); d+=8; s+=8; } while (d=2)
-# include
-# define DEBUGLOG(l, ...) { \
- if (l<=LZ4_DEBUG) { \
- fprintf(stderr, __FILE__ ": "); \
- fprintf(stderr, __VA_ARGS__); \
- fprintf(stderr, " \n"); \
- } }
-#else
-# define DEBUGLOG(l, ...) {} /* disabled */
+#if LZ4_FAST_DEC_LOOP
+
+LZ4_FORCE_INLINE void
+LZ4_memcpy_using_offset_base(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const size_t offset)
+{
+ assert(srcPtr + offset == dstPtr);
+ if (offset < 8) {
+ LZ4_write32(dstPtr, 0); /* silence an msan warning when offset==0 */
+ dstPtr[0] = srcPtr[0];
+ dstPtr[1] = srcPtr[1];
+ dstPtr[2] = srcPtr[2];
+ dstPtr[3] = srcPtr[3];
+ srcPtr += inc32table[offset];
+ LZ4_memcpy(dstPtr+4, srcPtr, 4);
+ srcPtr -= dec64table[offset];
+ dstPtr += 8;
+ } else {
+ LZ4_memcpy(dstPtr, srcPtr, 8);
+ dstPtr += 8;
+ srcPtr += 8;
+ }
+
+ LZ4_wildCopy8(dstPtr, srcPtr, dstEnd);
+}
+
+/* customized variant of memcpy, which can overwrite up to 32 bytes beyond dstEnd
+ * this version copies two times 16 bytes (instead of one time 32 bytes)
+ * because it must be compatible with offsets >= 16. */
+LZ4_FORCE_INLINE void
+LZ4_wildCopy32(void* dstPtr, const void* srcPtr, void* dstEnd)
+{
+ BYTE* d = (BYTE*)dstPtr;
+ const BYTE* s = (const BYTE*)srcPtr;
+ BYTE* const e = (BYTE*)dstEnd;
+
+ do { LZ4_memcpy(d,s,16); LZ4_memcpy(d+16,s+16,16); d+=32; s+=32; } while (d= dstPtr + MINMATCH
+ * - there is at least 8 bytes available to write after dstEnd */
+LZ4_FORCE_INLINE void
+LZ4_memcpy_using_offset(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const size_t offset)
+{
+ BYTE v[8];
+
+ assert(dstEnd >= dstPtr + MINMATCH);
+
+ switch(offset) {
+ case 1:
+ MEM_INIT(v, *srcPtr, 8);
+ break;
+ case 2:
+ LZ4_memcpy(v, srcPtr, 2);
+ LZ4_memcpy(&v[2], srcPtr, 2);
+ LZ4_memcpy(&v[4], v, 4);
+ break;
+ case 4:
+ LZ4_memcpy(v, srcPtr, 4);
+ LZ4_memcpy(&v[4], srcPtr, 4);
+ break;
+ default:
+ LZ4_memcpy_using_offset_base(dstPtr, srcPtr, dstEnd, offset);
+ return;
+ }
+
+ LZ4_memcpy(dstPtr, v, 8);
+ dstPtr += 8;
+ while (dstPtr < dstEnd) {
+ LZ4_memcpy(dstPtr, v, 8);
+ dstPtr += 8;
+ }
+}
#endif
/*-************************************
* Common functions
**************************************/
-static unsigned LZ4_NbCommonBytes (register reg_t val)
+static unsigned LZ4_NbCommonBytes (reg_t val)
{
+ assert(val != 0);
if (LZ4_isLittleEndian()) {
- if (sizeof(val)==8) {
-# if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
+ if (sizeof(val) == 8) {
+# if defined(_MSC_VER) && (_MSC_VER >= 1800) && defined(_M_AMD64) && !defined(LZ4_FORCE_SW_BITCOUNT)
+ /* x64 CPUS without BMI support interpret `TZCNT` as `REP BSF` */
+ return (unsigned)_tzcnt_u64(val) >> 3;
+# elif defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
unsigned long r = 0;
- _BitScanForward64( &r, (U64)val );
- return (int)(r>>3);
-# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
- return (__builtin_ctzll((U64)val) >> 3);
+ _BitScanForward64(&r, (U64)val);
+ return (unsigned)r >> 3;
+# elif (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
+ ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
+ !defined(LZ4_FORCE_SW_BITCOUNT)
+ return (unsigned)__builtin_ctzll((U64)val) >> 3;
# else
- static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, 0, 3, 1, 3, 1, 4, 2, 7, 0, 2, 3, 6, 1, 5, 3, 5, 1, 3, 4, 4, 2, 5, 6, 7, 7, 0, 1, 2, 3, 3, 4, 6, 2, 6, 5, 5, 3, 4, 5, 6, 7, 1, 2, 4, 6, 4, 4, 5, 7, 2, 6, 5, 7, 6, 7, 7 };
- return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58];
+ const U64 m = 0x0101010101010101ULL;
+ val ^= val - 1;
+ return (unsigned)(((U64)((val & (m - 1)) * m)) >> 56);
# endif
} else /* 32 bits */ {
-# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
+# if defined(_MSC_VER) && (_MSC_VER >= 1400) && !defined(LZ4_FORCE_SW_BITCOUNT)
unsigned long r;
- _BitScanForward( &r, (U32)val );
- return (int)(r>>3);
-# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
- return (__builtin_ctz((U32)val) >> 3);
+ _BitScanForward(&r, (U32)val);
+ return (unsigned)r >> 3;
+# elif (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
+ ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
+ !defined(__TINYC__) && !defined(LZ4_FORCE_SW_BITCOUNT)
+ return (unsigned)__builtin_ctz((U32)val) >> 3;
# else
- static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, 3, 2, 2, 1, 3, 2, 0, 1, 3, 3, 1, 2, 2, 2, 2, 0, 3, 1, 2, 0, 1, 0, 1, 1 };
- return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27];
+ const U32 m = 0x01010101;
+ return (unsigned)((((val - 1) ^ val) & (m - 1)) * m) >> 24;
# endif
}
} else /* Big Endian CPU */ {
if (sizeof(val)==8) {
-# if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
- unsigned long r = 0;
- _BitScanReverse64( &r, val );
- return (unsigned)(r>>3);
-# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
- return (__builtin_clzll((U64)val) >> 3);
+# if (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
+ ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
+ !defined(__TINYC__) && !defined(LZ4_FORCE_SW_BITCOUNT)
+ return (unsigned)__builtin_clzll((U64)val) >> 3;
# else
+#if 1
+ /* this method is probably faster,
+ * but adds a 128 bytes lookup table */
+ static const unsigned char ctz7_tab[128] = {
+ 7, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+ 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+ 5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+ 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+ 6, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+ 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+ 5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+ 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+ };
+ U64 const mask = 0x0101010101010101ULL;
+ U64 const t = (((val >> 8) - mask) | val) & mask;
+ return ctz7_tab[(t * 0x0080402010080402ULL) >> 57];
+#else
+ /* this method doesn't consume memory space like the previous one,
+ * but it contains several branches,
+ * that may end up slowing execution */
+ static const U32 by32 = sizeof(val)*4; /* 32 on 64 bits (goal), 16 on 32 bits.
+ Just to avoid some static analyzer complaining about shift by 32 on 32-bits target.
+ Note that this code path is never triggered in 32-bits mode. */
unsigned r;
- if (!(val>>32)) { r=4; } else { r=0; val>>=32; }
+ if (!(val>>by32)) { r=4; } else { r=0; val>>=by32; }
if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; }
r += (!val);
return r;
+#endif
# endif
} else /* 32 bits */ {
-# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
- unsigned long r = 0;
- _BitScanReverse( &r, (unsigned long)val );
- return (unsigned)(r>>3);
-# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
- return (__builtin_clz((U32)val) >> 3);
+# if (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
+ ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
+ !defined(LZ4_FORCE_SW_BITCOUNT)
+ return (unsigned)__builtin_clz((U32)val) >> 3;
# else
- unsigned r;
- if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }
- r += (!val);
- return r;
+ val >>= 8;
+ val = ((((val + 0x00FFFF00) | 0x00FFFFFF) + val) |
+ (val + 0x00FF0000)) >> 24;
+ return (unsigned)val ^ 3;
# endif
}
}
}
+
#define STEPSIZE sizeof(reg_t)
-static unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit)
+LZ4_FORCE_INLINE
+unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit)
{
const BYTE* const pStart = pIn;
- while (likely(pIn compression ru
/*-************************************
* Local Structures and types
**************************************/
-typedef enum { notLimited = 0, limitedOutput = 1 } limitedOutput_directive;
-typedef enum { byPtr, byU32, byU16 } tableType_t;
+typedef enum { clearedTable = 0, byPtr, byU32, byU16 } tableType_t;
-typedef enum { noDict = 0, withPrefix64k, usingExtDict } dict_directive;
+/**
+ * This enum distinguishes several different modes of accessing previous
+ * content in the stream.
+ *
+ * - noDict : There is no preceding content.
+ * - withPrefix64k : Table entries up to ctx->dictSize before the current blob
+ * blob being compressed are valid and refer to the preceding
+ * content (of length ctx->dictSize), which is available
+ * contiguously preceding in memory the content currently
+ * being compressed.
+ * - usingExtDict : Like withPrefix64k, but the preceding content is somewhere
+ * else in memory, starting at ctx->dictionary with length
+ * ctx->dictSize.
+ * - usingDictCtx : Like usingExtDict, but everything concerning the preceding
+ * content is in a separate context, pointed to by
+ * ctx->dictCtx. ctx->dictionary, ctx->dictSize, and table
+ * entries in the current context that refer to positions
+ * preceding the beginning of the current compression are
+ * ignored. Instead, ctx->dictCtx->dictionary and ctx->dictCtx
+ * ->dictSize describe the location and size of the preceding
+ * content, and matches are found by looking in the ctx
+ * ->dictCtx->hashTable.
+ */
+typedef enum { noDict = 0, withPrefix64k, usingExtDict, usingDictCtx } dict_directive;
typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive;
-typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
-typedef enum { full = 0, partial = 1 } earlyEnd_directive;
-
/*-************************************
* Local Utils
@@ -411,13 +672,30 @@ typedef enum { full = 0, partial = 1 } earlyEnd_directive;
int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; }
const char* LZ4_versionString(void) { return LZ4_VERSION_STRING; }
int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); }
-int LZ4_sizeofState() { return LZ4_STREAMSIZE; }
+int LZ4_sizeofState(void) { return LZ4_STREAMSIZE; }
+/*-************************************
+* Internal Definitions used in Tests
+**************************************/
+#if defined (__cplusplus)
+extern "C" {
+#endif
+
+int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize);
+
+int LZ4_decompress_safe_forceExtDict(const char* source, char* dest,
+ int compressedSize, int maxOutputSize,
+ const void* dictStart, size_t dictSize);
+
+#if defined (__cplusplus)
+}
+#endif
+
/*-******************************
* Compression functions
********************************/
-static U32 LZ4_hash4(U32 sequence, tableType_t const tableType)
+LZ4_FORCE_INLINE U32 LZ4_hash4(U32 sequence, tableType_t const tableType)
{
if (tableType == byU16)
return ((sequence * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1)));
@@ -425,104 +703,222 @@ static U32 LZ4_hash4(U32 sequence, tableType_t const tableType)
return ((sequence * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG));
}
-static U32 LZ4_hash5(U64 sequence, tableType_t const tableType)
+LZ4_FORCE_INLINE U32 LZ4_hash5(U64 sequence, tableType_t const tableType)
{
- static const U64 prime5bytes = 889523592379ULL;
- static const U64 prime8bytes = 11400714785074694791ULL;
const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG;
- if (LZ4_isLittleEndian())
+ if (LZ4_isLittleEndian()) {
+ const U64 prime5bytes = 889523592379ULL;
return (U32)(((sequence << 24) * prime5bytes) >> (64 - hashLog));
- else
+ } else {
+ const U64 prime8bytes = 11400714785074694791ULL;
return (U32)(((sequence >> 24) * prime8bytes) >> (64 - hashLog));
+ }
}
-FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType)
+LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType)
{
if ((sizeof(reg_t)==8) && (tableType != byU16)) return LZ4_hash5(LZ4_read_ARCH(p), tableType);
return LZ4_hash4(LZ4_read32(p), tableType);
}
-static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t const tableType, const BYTE* srcBase)
+LZ4_FORCE_INLINE void LZ4_clearHash(U32 h, void* tableBase, tableType_t const tableType)
{
switch (tableType)
{
+ default: /* fallthrough */
+ case clearedTable: { /* illegal! */ assert(0); return; }
+ case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = NULL; return; }
+ case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = 0; return; }
+ case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = 0; return; }
+ }
+}
+
+LZ4_FORCE_INLINE void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t const tableType)
+{
+ switch (tableType)
+ {
+ default: /* fallthrough */
+ case clearedTable: /* fallthrough */
+ case byPtr: { /* illegal! */ assert(0); return; }
+ case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = idx; return; }
+ case byU16: { U16* hashTable = (U16*) tableBase; assert(idx < 65536); hashTable[h] = (U16)idx; return; }
+ }
+}
+
+LZ4_FORCE_INLINE void LZ4_putPositionOnHash(const BYTE* p, U32 h,
+ void* tableBase, tableType_t const tableType,
+ const BYTE* srcBase)
+{
+ switch (tableType)
+ {
+ case clearedTable: { /* illegal! */ assert(0); return; }
case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = p; return; }
case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); return; }
case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); return; }
}
}
-FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+LZ4_FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
{
U32 const h = LZ4_hashPosition(p, tableType);
LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase);
}
-static const BYTE* LZ4_getPositionOnHash(U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+/* LZ4_getIndexOnHash() :
+ * Index of match position registered in hash table.
+ * hash position must be calculated by using base+index, or dictBase+index.
+ * Assumption 1 : only valid if tableType == byU32 or byU16.
+ * Assumption 2 : h is presumed valid (within limits of hash table)
+ */
+LZ4_FORCE_INLINE U32 LZ4_getIndexOnHash(U32 h, const void* tableBase, tableType_t tableType)
{
- if (tableType == byPtr) { const BYTE** hashTable = (const BYTE**) tableBase; return hashTable[h]; }
- if (tableType == byU32) { const U32* const hashTable = (U32*) tableBase; return hashTable[h] + srcBase; }
- { const U16* const hashTable = (U16*) tableBase; return hashTable[h] + srcBase; } /* default, to ensure a return */
+ LZ4_STATIC_ASSERT(LZ4_MEMORY_USAGE > 2);
+ if (tableType == byU32) {
+ const U32* const hashTable = (const U32*) tableBase;
+ assert(h < (1U << (LZ4_MEMORY_USAGE-2)));
+ return hashTable[h];
+ }
+ if (tableType == byU16) {
+ const U16* const hashTable = (const U16*) tableBase;
+ assert(h < (1U << (LZ4_MEMORY_USAGE-1)));
+ return hashTable[h];
+ }
+ assert(0); return 0; /* forbidden case */
}
-FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+static const BYTE* LZ4_getPositionOnHash(U32 h, const void* tableBase, tableType_t tableType, const BYTE* srcBase)
+{
+ if (tableType == byPtr) { const BYTE* const* hashTable = (const BYTE* const*) tableBase; return hashTable[h]; }
+ if (tableType == byU32) { const U32* const hashTable = (const U32*) tableBase; return hashTable[h] + srcBase; }
+ { const U16* const hashTable = (const U16*) tableBase; return hashTable[h] + srcBase; } /* default, to ensure a return */
+}
+
+LZ4_FORCE_INLINE const BYTE*
+LZ4_getPosition(const BYTE* p,
+ const void* tableBase, tableType_t tableType,
+ const BYTE* srcBase)
{
U32 const h = LZ4_hashPosition(p, tableType);
return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase);
}
+LZ4_FORCE_INLINE void
+LZ4_prepareTable(LZ4_stream_t_internal* const cctx,
+ const int inputSize,
+ const tableType_t tableType) {
+ /* If the table hasn't been used, it's guaranteed to be zeroed out, and is
+ * therefore safe to use no matter what mode we're in. Otherwise, we figure
+ * out if it's safe to leave as is or whether it needs to be reset.
+ */
+ if ((tableType_t)cctx->tableType != clearedTable) {
+ assert(inputSize >= 0);
+ if ((tableType_t)cctx->tableType != tableType
+ || ((tableType == byU16) && cctx->currentOffset + (unsigned)inputSize >= 0xFFFFU)
+ || ((tableType == byU32) && cctx->currentOffset > 1 GB)
+ || tableType == byPtr
+ || inputSize >= 4 KB)
+ {
+ DEBUGLOG(4, "LZ4_prepareTable: Resetting table in %p", cctx);
+ MEM_INIT(cctx->hashTable, 0, LZ4_HASHTABLESIZE);
+ cctx->currentOffset = 0;
+ cctx->tableType = (U32)clearedTable;
+ } else {
+ DEBUGLOG(4, "LZ4_prepareTable: Re-use hash table (no reset)");
+ }
+ }
+
+ /* Adding a gap, so all previous entries are > LZ4_DISTANCE_MAX back, is faster
+ * than compressing without a gap. However, compressing with
+ * currentOffset == 0 is faster still, so we preserve that case.
+ */
+ if (cctx->currentOffset != 0 && tableType == byU32) {
+ DEBUGLOG(5, "LZ4_prepareTable: adding 64KB to currentOffset");
+ cctx->currentOffset += 64 KB;
+ }
+
+ /* Finally, clear history */
+ cctx->dictCtx = NULL;
+ cctx->dictionary = NULL;
+ cctx->dictSize = 0;
+}
/** LZ4_compress_generic() :
- inlined, to ensure branches are decided at compilation time */
-FORCE_INLINE int LZ4_compress_generic(
+ * inlined, to ensure branches are decided at compilation time.
+ * Presumed already validated at this stage:
+ * - source != NULL
+ * - inputSize > 0
+ */
+LZ4_FORCE_INLINE int LZ4_compress_generic_validated(
LZ4_stream_t_internal* const cctx,
const char* const source,
char* const dest,
const int inputSize,
+ int *inputConsumed, /* only written when outputDirective == fillOutput */
const int maxOutputSize,
- const limitedOutput_directive outputLimited,
+ const limitedOutput_directive outputDirective,
const tableType_t tableType,
- const dict_directive dict,
+ const dict_directive dictDirective,
const dictIssue_directive dictIssue,
- const U32 acceleration)
+ const int acceleration)
{
+ int result;
const BYTE* ip = (const BYTE*) source;
- const BYTE* base;
+
+ U32 const startIndex = cctx->currentOffset;
+ const BYTE* base = (const BYTE*) source - startIndex;
const BYTE* lowLimit;
- const BYTE* const lowRefLimit = ip - cctx->dictSize;
- const BYTE* const dictionary = cctx->dictionary;
- const BYTE* const dictEnd = dictionary + cctx->dictSize;
- const ptrdiff_t dictDelta = dictEnd - (const BYTE*)source;
+
+ const LZ4_stream_t_internal* dictCtx = (const LZ4_stream_t_internal*) cctx->dictCtx;
+ const BYTE* const dictionary =
+ dictDirective == usingDictCtx ? dictCtx->dictionary : cctx->dictionary;
+ const U32 dictSize =
+ dictDirective == usingDictCtx ? dictCtx->dictSize : cctx->dictSize;
+ const U32 dictDelta = (dictDirective == usingDictCtx) ? startIndex - dictCtx->currentOffset : 0; /* make indexes in dictCtx comparable with index in current context */
+
+ int const maybe_extMem = (dictDirective == usingExtDict) || (dictDirective == usingDictCtx);
+ U32 const prefixIdxLimit = startIndex - dictSize; /* used when dictDirective == dictSmall */
+ const BYTE* const dictEnd = dictionary ? dictionary + dictSize : dictionary;
const BYTE* anchor = (const BYTE*) source;
const BYTE* const iend = ip + inputSize;
- const BYTE* const mflimit = iend - MFLIMIT;
+ const BYTE* const mflimitPlusOne = iend - MFLIMIT + 1;
const BYTE* const matchlimit = iend - LASTLITERALS;
+ /* the dictCtx currentOffset is indexed on the start of the dictionary,
+ * while a dictionary in the current context precedes the currentOffset */
+ const BYTE* dictBase = !dictionary ? NULL : (dictDirective == usingDictCtx) ?
+ dictionary + dictSize - dictCtx->currentOffset :
+ dictionary + dictSize - startIndex;
+
BYTE* op = (BYTE*) dest;
BYTE* const olimit = op + maxOutputSize;
+ U32 offset = 0;
U32 forwardH;
- /* Init conditions */
- if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported inputSize, too large (or negative) */
- switch(dict)
- {
- case noDict:
- default:
- base = (const BYTE*)source;
- lowLimit = (const BYTE*)source;
- break;
- case withPrefix64k:
- base = (const BYTE*)source - cctx->currentOffset;
- lowLimit = (const BYTE*)source - cctx->dictSize;
- break;
- case usingExtDict:
- base = (const BYTE*)source - cctx->currentOffset;
- lowLimit = (const BYTE*)source;
- break;
+ DEBUGLOG(5, "LZ4_compress_generic_validated: srcSize=%i, tableType=%u", inputSize, tableType);
+ assert(ip != NULL);
+ /* If init conditions are not met, we don't have to mark stream
+ * as having dirty context, since no action was taken yet */
+ if (outputDirective == fillOutput && maxOutputSize < 1) { return 0; } /* Impossible to store anything */
+ if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) { return 0; } /* Size too large (not within 64K limit) */
+ if (tableType==byPtr) assert(dictDirective==noDict); /* only supported use case with byPtr */
+ assert(acceleration >= 1);
+
+ lowLimit = (const BYTE*)source - (dictDirective == withPrefix64k ? dictSize : 0);
+
+ /* Update context state */
+ if (dictDirective == usingDictCtx) {
+ /* Subsequent linked blocks can't use the dictionary. */
+ /* Instead, they use the block we just compressed. */
+ cctx->dictCtx = NULL;
+ cctx->dictSize = (U32)inputSize;
+ } else {
+ cctx->dictSize += (U32)inputSize;
}
- if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) return 0; /* Size too large (not within 64K limit) */
- if (inputSizecurrentOffset += (U32)inputSize;
+ cctx->tableType = (U32)tableType;
+
+ if (inputSizehashTable, tableType, base);
@@ -530,50 +926,112 @@ FORCE_INLINE int LZ4_compress_generic(
/* Main Loop */
for ( ; ; ) {
- ptrdiff_t refDelta = 0;
const BYTE* match;
BYTE* token;
+ const BYTE* filledIp;
/* Find a match */
- { const BYTE* forwardIp = ip;
- unsigned step = 1;
- unsigned searchMatchNb = acceleration << LZ4_skipTrigger;
+ if (tableType == byPtr) {
+ const BYTE* forwardIp = ip;
+ int step = 1;
+ int searchMatchNb = acceleration << LZ4_skipTrigger;
do {
U32 const h = forwardH;
ip = forwardIp;
forwardIp += step;
step = (searchMatchNb++ >> LZ4_skipTrigger);
- if (unlikely(forwardIp > mflimit)) goto _last_literals;
+ if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals;
+ assert(ip < mflimitPlusOne);
match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType, base);
- if (dict==usingExtDict) {
- if (match < (const BYTE*)source) {
- refDelta = dictDelta;
- lowLimit = dictionary;
- } else {
- refDelta = 0;
- lowLimit = (const BYTE*)source;
- } }
forwardH = LZ4_hashPosition(forwardIp, tableType);
LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base);
- } while ( ((dictIssue==dictSmall) ? (match < lowRefLimit) : 0)
- || ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip))
- || (LZ4_read32(match+refDelta) != LZ4_read32(ip)) );
+ } while ( (match+LZ4_DISTANCE_MAX < ip)
+ || (LZ4_read32(match) != LZ4_read32(ip)) );
+
+ } else { /* byU32, byU16 */
+
+ const BYTE* forwardIp = ip;
+ int step = 1;
+ int searchMatchNb = acceleration << LZ4_skipTrigger;
+ do {
+ U32 const h = forwardH;
+ U32 const current = (U32)(forwardIp - base);
+ U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType);
+ assert(matchIndex <= current);
+ assert(forwardIp - base < (ptrdiff_t)(2 GB - 1));
+ ip = forwardIp;
+ forwardIp += step;
+ step = (searchMatchNb++ >> LZ4_skipTrigger);
+
+ if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals;
+ assert(ip < mflimitPlusOne);
+
+ if (dictDirective == usingDictCtx) {
+ if (matchIndex < startIndex) {
+ /* there was no match, try the dictionary */
+ assert(tableType == byU32);
+ matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32);
+ match = dictBase + matchIndex;
+ matchIndex += dictDelta; /* make dictCtx index comparable with current context */
+ lowLimit = dictionary;
+ } else {
+ match = base + matchIndex;
+ lowLimit = (const BYTE*)source;
+ }
+ } else if (dictDirective==usingExtDict) {
+ if (matchIndex < startIndex) {
+ DEBUGLOG(7, "extDict candidate: matchIndex=%5u < startIndex=%5u", matchIndex, startIndex);
+ assert(startIndex - matchIndex >= MINMATCH);
+ match = dictBase + matchIndex;
+ lowLimit = dictionary;
+ } else {
+ match = base + matchIndex;
+ lowLimit = (const BYTE*)source;
+ }
+ } else { /* single continuous memory segment */
+ match = base + matchIndex;
+ }
+ forwardH = LZ4_hashPosition(forwardIp, tableType);
+ LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);
+
+ DEBUGLOG(7, "candidate at pos=%u (offset=%u \n", matchIndex, current - matchIndex);
+ if ((dictIssue == dictSmall) && (matchIndex < prefixIdxLimit)) { continue; } /* match outside of valid area */
+ assert(matchIndex < current);
+ if ( ((tableType != byU16) || (LZ4_DISTANCE_MAX < LZ4_DISTANCE_ABSOLUTE_MAX))
+ && (matchIndex+LZ4_DISTANCE_MAX < current)) {
+ continue;
+ } /* too far */
+ assert((current - matchIndex) <= LZ4_DISTANCE_MAX); /* match now expected within distance */
+
+ if (LZ4_read32(match) == LZ4_read32(ip)) {
+ if (maybe_extMem) offset = current - matchIndex;
+ break; /* match found */
+ }
+
+ } while(1);
}
/* Catch up */
- while (((ip>anchor) & (match+refDelta > lowLimit)) && (unlikely(ip[-1]==match[refDelta-1]))) { ip--; match--; }
+ filledIp = ip;
+ while (((ip>anchor) & (match > lowLimit)) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; }
/* Encode Literals */
{ unsigned const litLength = (unsigned)(ip - anchor);
token = op++;
- if ((outputLimited) && /* Check output buffer overflow */
- (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)))
- return 0;
+ if ((outputDirective == limitedOutput) && /* Check output buffer overflow */
+ (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)) ) {
+ return 0; /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */
+ }
+ if ((outputDirective == fillOutput) &&
+ (unlikely(op + (litLength+240)/255 /* litlen */ + litLength /* literals */ + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit))) {
+ op--;
+ goto _last_literals;
+ }
if (litLength >= RUN_MASK) {
- int len = (int)litLength-RUN_MASK;
+ int len = (int)(litLength - RUN_MASK);
*token = (RUN_MASK<= 255 ; len-=255) *op++ = 255;
*op++ = (BYTE)len;
@@ -581,37 +1039,87 @@ FORCE_INLINE int LZ4_compress_generic(
else *token = (BYTE)(litLength< olimit)) {
+ /* the match was too close to the end, rewind and go to last literals */
+ op = token;
+ goto _last_literals;
+ }
+
/* Encode Offset */
- LZ4_writeLE16(op, (U16)(ip-match)); op+=2;
+ if (maybe_extMem) { /* static test */
+ DEBUGLOG(6, " with offset=%u (ext if > %i)", offset, (int)(ip - (const BYTE*)source));
+ assert(offset <= LZ4_DISTANCE_MAX && offset > 0);
+ LZ4_writeLE16(op, (U16)offset); op+=2;
+ } else {
+ DEBUGLOG(6, " with offset=%u (same segment)", (U32)(ip - match));
+ assert(ip-match <= LZ4_DISTANCE_MAX);
+ LZ4_writeLE16(op, (U16)(ip - match)); op+=2;
+ }
/* Encode MatchLength */
{ unsigned matchCode;
- if ((dict==usingExtDict) && (lowLimit==dictionary)) {
- const BYTE* limit;
- match += refDelta;
- limit = ip + (dictEnd-match);
+ if ( (dictDirective==usingExtDict || dictDirective==usingDictCtx)
+ && (lowLimit==dictionary) /* match within extDict */ ) {
+ const BYTE* limit = ip + (dictEnd-match);
+ assert(dictEnd > match);
if (limit > matchlimit) limit = matchlimit;
matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit);
- ip += MINMATCH + matchCode;
+ ip += (size_t)matchCode + MINMATCH;
if (ip==limit) {
- unsigned const more = LZ4_count(ip, (const BYTE*)source, matchlimit);
+ unsigned const more = LZ4_count(limit, (const BYTE*)source, matchlimit);
matchCode += more;
ip += more;
}
+ DEBUGLOG(6, " with matchLength=%u starting in extDict", matchCode+MINMATCH);
} else {
matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);
- ip += MINMATCH + matchCode;
+ ip += (size_t)matchCode + MINMATCH;
+ DEBUGLOG(6, " with matchLength=%u", matchCode+MINMATCH);
}
- if ( outputLimited && /* Check output buffer overflow */
- (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) )
- return 0;
+ if ((outputDirective) && /* Check output buffer overflow */
+ (unlikely(op + (1 + LASTLITERALS) + (matchCode+240)/255 > olimit)) ) {
+ if (outputDirective == fillOutput) {
+ /* Match description too long : reduce it */
+ U32 newMatchCode = 15 /* in token */ - 1 /* to avoid needing a zero byte */ + ((U32)(olimit - op) - 1 - LASTLITERALS) * 255;
+ ip -= matchCode - newMatchCode;
+ assert(newMatchCode < matchCode);
+ matchCode = newMatchCode;
+ if (unlikely(ip <= filledIp)) {
+ /* We have already filled up to filledIp so if ip ends up less than filledIp
+ * we have positions in the hash table beyond the current position. This is
+ * a problem if we reuse the hash table. So we have to remove these positions
+ * from the hash table.
+ */
+ const BYTE* ptr;
+ DEBUGLOG(5, "Clearing %u positions", (U32)(filledIp - ip));
+ for (ptr = ip; ptr <= filledIp; ++ptr) {
+ U32 const h = LZ4_hashPosition(ptr, tableType);
+ LZ4_clearHash(h, cctx->hashTable, tableType);
+ }
+ }
+ } else {
+ assert(outputDirective == limitedOutput);
+ return 0; /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */
+ }
+ }
if (matchCode >= ML_MASK) {
*token += ML_MASK;
matchCode -= ML_MASK;
@@ -626,41 +1134,89 @@ _next_match:
} else
*token += (BYTE)(matchCode);
}
+ /* Ensure we have enough space for the last literals. */
+ assert(!(outputDirective == fillOutput && op + 1 + LASTLITERALS > olimit));
anchor = ip;
/* Test end of chunk */
- if (ip > mflimit) break;
+ if (ip >= mflimitPlusOne) break;
/* Fill table */
LZ4_putPosition(ip-2, cctx->hashTable, tableType, base);
/* Test next position */
- match = LZ4_getPosition(ip, cctx->hashTable, tableType, base);
- if (dict==usingExtDict) {
- if (match < (const BYTE*)source) {
- refDelta = dictDelta;
- lowLimit = dictionary;
- } else {
- refDelta = 0;
- lowLimit = (const BYTE*)source;
- } }
- LZ4_putPosition(ip, cctx->hashTable, tableType, base);
- if ( ((dictIssue==dictSmall) ? (match>=lowRefLimit) : 1)
- && (match+MAX_DISTANCE>=ip)
- && (LZ4_read32(match+refDelta)==LZ4_read32(ip)) )
- { token=op++; *token=0; goto _next_match; }
+ if (tableType == byPtr) {
+
+ match = LZ4_getPosition(ip, cctx->hashTable, tableType, base);
+ LZ4_putPosition(ip, cctx->hashTable, tableType, base);
+ if ( (match+LZ4_DISTANCE_MAX >= ip)
+ && (LZ4_read32(match) == LZ4_read32(ip)) )
+ { token=op++; *token=0; goto _next_match; }
+
+ } else { /* byU32, byU16 */
+
+ U32 const h = LZ4_hashPosition(ip, tableType);
+ U32 const current = (U32)(ip-base);
+ U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType);
+ assert(matchIndex < current);
+ if (dictDirective == usingDictCtx) {
+ if (matchIndex < startIndex) {
+ /* there was no match, try the dictionary */
+ matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32);
+ match = dictBase + matchIndex;
+ lowLimit = dictionary; /* required for match length counter */
+ matchIndex += dictDelta;
+ } else {
+ match = base + matchIndex;
+ lowLimit = (const BYTE*)source; /* required for match length counter */
+ }
+ } else if (dictDirective==usingExtDict) {
+ if (matchIndex < startIndex) {
+ match = dictBase + matchIndex;
+ lowLimit = dictionary; /* required for match length counter */
+ } else {
+ match = base + matchIndex;
+ lowLimit = (const BYTE*)source; /* required for match length counter */
+ }
+ } else { /* single memory segment */
+ match = base + matchIndex;
+ }
+ LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);
+ assert(matchIndex < current);
+ if ( ((dictIssue==dictSmall) ? (matchIndex >= prefixIdxLimit) : 1)
+ && (((tableType==byU16) && (LZ4_DISTANCE_MAX == LZ4_DISTANCE_ABSOLUTE_MAX)) ? 1 : (matchIndex+LZ4_DISTANCE_MAX >= current))
+ && (LZ4_read32(match) == LZ4_read32(ip)) ) {
+ token=op++;
+ *token=0;
+ if (maybe_extMem) offset = current - matchIndex;
+ DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i",
+ (int)(anchor-(const BYTE*)source), 0, (int)(ip-(const BYTE*)source));
+ goto _next_match;
+ }
+ }
/* Prepare next loop */
forwardH = LZ4_hashPosition(++ip, tableType);
+
}
_last_literals:
/* Encode Last Literals */
- { size_t const lastRun = (size_t)(iend - anchor);
- if ( (outputLimited) && /* Check output buffer overflow */
- ((op - (BYTE*)dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize) )
- return 0;
+ { size_t lastRun = (size_t)(iend - anchor);
+ if ( (outputDirective) && /* Check output buffer overflow */
+ (op + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > olimit)) {
+ if (outputDirective == fillOutput) {
+ /* adapt lastRun to fill 'dst' */
+ assert(olimit >= op);
+ lastRun = (size_t)(olimit-op) - 1/*token*/;
+ lastRun -= (lastRun + 256 - RUN_MASK) / 256; /*additional length tokens*/
+ } else {
+ assert(outputDirective == limitedOutput);
+ return 0; /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */
+ }
+ }
+ DEBUGLOG(6, "Final literal run : %i literals", (int)lastRun);
if (lastRun >= RUN_MASK) {
size_t accumulator = lastRun - RUN_MASK;
*op++ = RUN_MASK << ML_BITS;
@@ -669,45 +1225,143 @@ _last_literals:
} else {
*op++ = (BYTE)(lastRun< 0);
+ DEBUGLOG(5, "LZ4_compress_generic: compressed %i bytes into %i bytes", inputSize, result);
+ return result;
+}
+
+/** LZ4_compress_generic() :
+ * inlined, to ensure branches are decided at compilation time;
+ * takes care of src == (NULL, 0)
+ * and forward the rest to LZ4_compress_generic_validated */
+LZ4_FORCE_INLINE int LZ4_compress_generic(
+ LZ4_stream_t_internal* const cctx,
+ const char* const src,
+ char* const dst,
+ const int srcSize,
+ int *inputConsumed, /* only written when outputDirective == fillOutput */
+ const int dstCapacity,
+ const limitedOutput_directive outputDirective,
+ const tableType_t tableType,
+ const dict_directive dictDirective,
+ const dictIssue_directive dictIssue,
+ const int acceleration)
+{
+ DEBUGLOG(5, "LZ4_compress_generic: srcSize=%i, dstCapacity=%i",
+ srcSize, dstCapacity);
+
+ if ((U32)srcSize > (U32)LZ4_MAX_INPUT_SIZE) { return 0; } /* Unsupported srcSize, too large (or negative) */
+ if (srcSize == 0) { /* src == NULL supported if srcSize == 0 */
+ if (outputDirective != notLimited && dstCapacity <= 0) return 0; /* no output, can't write anything */
+ DEBUGLOG(5, "Generating an empty block");
+ assert(outputDirective == notLimited || dstCapacity >= 1);
+ assert(dst != NULL);
+ dst[0] = 0;
+ if (outputDirective == fillOutput) {
+ assert (inputConsumed != NULL);
+ *inputConsumed = 0;
+ }
+ return 1;
+ }
+ assert(src != NULL);
+
+ return LZ4_compress_generic_validated(cctx, src, dst, srcSize,
+ inputConsumed, /* only written into if outputDirective == fillOutput */
+ dstCapacity, outputDirective,
+ tableType, dictDirective, dictIssue, acceleration);
}
int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
{
- LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)state)->internal_donotuse;
- LZ4_resetStream((LZ4_stream_t*)state);
- if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
-
+ LZ4_stream_t_internal* const ctx = & LZ4_initStream(state, sizeof(LZ4_stream_t)) -> internal_donotuse;
+ assert(ctx != NULL);
+ if (acceleration < 1) acceleration = LZ4_ACCELERATION_DEFAULT;
+ if (acceleration > LZ4_ACCELERATION_MAX) acceleration = LZ4_ACCELERATION_MAX;
if (maxOutputSize >= LZ4_compressBound(inputSize)) {
- if (inputSize < LZ4_64Klimit)
- return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue, acceleration);
- else
- return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration);
+ if (inputSize < LZ4_64Klimit) {
+ return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, byU16, noDict, noDictIssue, acceleration);
+ } else {
+ const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
+ return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
+ }
} else {
- if (inputSize < LZ4_64Klimit)
- return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration);
- else
- return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration);
+ if (inputSize < LZ4_64Klimit) {
+ return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration);
+ } else {
+ const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
+ return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, noDict, noDictIssue, acceleration);
+ }
+ }
+}
+
+/**
+ * LZ4_compress_fast_extState_fastReset() :
+ * A variant of LZ4_compress_fast_extState().
+ *
+ * Using this variant avoids an expensive initialization step. It is only safe
+ * to call if the state buffer is known to be correctly initialized already
+ * (see comment in lz4.h on LZ4_resetStream_fast() for a definition of
+ * "correctly initialized").
+ */
+int LZ4_compress_fast_extState_fastReset(void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration)
+{
+ LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)state)->internal_donotuse;
+ if (acceleration < 1) acceleration = LZ4_ACCELERATION_DEFAULT;
+ if (acceleration > LZ4_ACCELERATION_MAX) acceleration = LZ4_ACCELERATION_MAX;
+
+ if (dstCapacity >= LZ4_compressBound(srcSize)) {
+ if (srcSize < LZ4_64Klimit) {
+ const tableType_t tableType = byU16;
+ LZ4_prepareTable(ctx, srcSize, tableType);
+ if (ctx->currentOffset) {
+ return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, dictSmall, acceleration);
+ } else {
+ return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
+ }
+ } else {
+ const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
+ LZ4_prepareTable(ctx, srcSize, tableType);
+ return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
+ }
+ } else {
+ if (srcSize < LZ4_64Klimit) {
+ const tableType_t tableType = byU16;
+ LZ4_prepareTable(ctx, srcSize, tableType);
+ if (ctx->currentOffset) {
+ return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, dictSmall, acceleration);
+ } else {
+ return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration);
+ }
+ } else {
+ const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
+ LZ4_prepareTable(ctx, srcSize, tableType);
+ return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration);
+ }
}
}
int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
{
+ int result;
#if (LZ4_HEAPMODE)
- void* ctxPtr = ALLOCATOR(1, sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */
+ LZ4_stream_t* ctxPtr = ALLOC(sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */
+ if (ctxPtr == NULL) return 0;
#else
LZ4_stream_t ctx;
- void* const ctxPtr = &ctx;
+ LZ4_stream_t* const ctxPtr = &ctx;
#endif
-
- int const result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration);
+ result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration);
#if (LZ4_HEAPMODE)
FREEMEM(ctxPtr);
@@ -716,205 +1370,37 @@ int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutp
}
-int LZ4_compress_default(const char* source, char* dest, int inputSize, int maxOutputSize)
+int LZ4_compress_default(const char* src, char* dst, int srcSize, int maxOutputSize)
{
- return LZ4_compress_fast(source, dest, inputSize, maxOutputSize, 1);
-}
-
-
-/* hidden debug function */
-/* strangely enough, gcc generates faster code when this function is uncommented, even if unused */
-int LZ4_compress_fast_force(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
-{
- LZ4_stream_t ctx;
- LZ4_resetStream(&ctx);
-
- if (inputSize < LZ4_64Klimit)
- return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration);
- else
- return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, maxOutputSize, limitedOutput, sizeof(void*)==8 ? byU32 : byPtr, noDict, noDictIssue, acceleration);
-}
-
-
-/*-******************************
-* *_destSize() variant
-********************************/
-
-static int LZ4_compress_destSize_generic(
- LZ4_stream_t_internal* const ctx,
- const char* const src,
- char* const dst,
- int* const srcSizePtr,
- const int targetDstSize,
- const tableType_t tableType)
-{
- const BYTE* ip = (const BYTE*) src;
- const BYTE* base = (const BYTE*) src;
- const BYTE* lowLimit = (const BYTE*) src;
- const BYTE* anchor = ip;
- const BYTE* const iend = ip + *srcSizePtr;
- const BYTE* const mflimit = iend - MFLIMIT;
- const BYTE* const matchlimit = iend - LASTLITERALS;
-
- BYTE* op = (BYTE*) dst;
- BYTE* const oend = op + targetDstSize;
- BYTE* const oMaxLit = op + targetDstSize - 2 /* offset */ - 8 /* because 8+MINMATCH==MFLIMIT */ - 1 /* token */;
- BYTE* const oMaxMatch = op + targetDstSize - (LASTLITERALS + 1 /* token */);
- BYTE* const oMaxSeq = oMaxLit - 1 /* token */;
-
- U32 forwardH;
-
-
- /* Init conditions */
- if (targetDstSize < 1) return 0; /* Impossible to store anything */
- if ((U32)*srcSizePtr > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported input size, too large (or negative) */
- if ((tableType == byU16) && (*srcSizePtr>=LZ4_64Klimit)) return 0; /* Size too large (not within 64K limit) */
- if (*srcSizePtrhashTable, tableType, base);
- ip++; forwardH = LZ4_hashPosition(ip, tableType);
-
- /* Main Loop */
- for ( ; ; ) {
- const BYTE* match;
- BYTE* token;
-
- /* Find a match */
- { const BYTE* forwardIp = ip;
- unsigned step = 1;
- unsigned searchMatchNb = 1 << LZ4_skipTrigger;
-
- do {
- U32 h = forwardH;
- ip = forwardIp;
- forwardIp += step;
- step = (searchMatchNb++ >> LZ4_skipTrigger);
-
- if (unlikely(forwardIp > mflimit)) goto _last_literals;
-
- match = LZ4_getPositionOnHash(h, ctx->hashTable, tableType, base);
- forwardH = LZ4_hashPosition(forwardIp, tableType);
- LZ4_putPositionOnHash(ip, h, ctx->hashTable, tableType, base);
-
- } while ( ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip))
- || (LZ4_read32(match) != LZ4_read32(ip)) );
- }
-
- /* Catch up */
- while ((ip>anchor) && (match > lowLimit) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; }
-
- /* Encode Literal length */
- { unsigned litLength = (unsigned)(ip - anchor);
- token = op++;
- if (op + ((litLength+240)/255) + litLength > oMaxLit) {
- /* Not enough space for a last match */
- op--;
- goto _last_literals;
- }
- if (litLength>=RUN_MASK) {
- unsigned len = litLength - RUN_MASK;
- *token=(RUN_MASK<= 255 ; len-=255) *op++ = 255;
- *op++ = (BYTE)len;
- }
- else *token = (BYTE)(litLength< oMaxMatch) {
- /* Match description too long : reduce it */
- matchLength = (15-1) + (oMaxMatch-op) * 255;
- }
- ip += MINMATCH + matchLength;
-
- if (matchLength>=ML_MASK) {
- *token += ML_MASK;
- matchLength -= ML_MASK;
- while (matchLength >= 255) { matchLength-=255; *op++ = 255; }
- *op++ = (BYTE)matchLength;
- }
- else *token += (BYTE)(matchLength);
- }
-
- anchor = ip;
-
- /* Test end of block */
- if (ip > mflimit) break;
- if (op > oMaxSeq) break;
-
- /* Fill table */
- LZ4_putPosition(ip-2, ctx->hashTable, tableType, base);
-
- /* Test next position */
- match = LZ4_getPosition(ip, ctx->hashTable, tableType, base);
- LZ4_putPosition(ip, ctx->hashTable, tableType, base);
- if ( (match+MAX_DISTANCE>=ip)
- && (LZ4_read32(match)==LZ4_read32(ip)) )
- { token=op++; *token=0; goto _next_match; }
-
- /* Prepare next loop */
- forwardH = LZ4_hashPosition(++ip, tableType);
- }
-
-_last_literals:
- /* Encode Last Literals */
- { size_t lastRunSize = (size_t)(iend - anchor);
- if (op + 1 /* token */ + ((lastRunSize+240)/255) /* litLength */ + lastRunSize /* literals */ > oend) {
- /* adapt lastRunSize to fill 'dst' */
- lastRunSize = (oend-op) - 1;
- lastRunSize -= (lastRunSize+240)/255;
- }
- ip = anchor + lastRunSize;
-
- if (lastRunSize >= RUN_MASK) {
- size_t accumulator = lastRunSize - RUN_MASK;
- *op++ = RUN_MASK << ML_BITS;
- for(; accumulator >= 255 ; accumulator-=255) *op++ = 255;
- *op++ = (BYTE) accumulator;
- } else {
- *op++ = (BYTE)(lastRunSize<= LZ4_compressBound(*srcSizePtr)) { /* compression success is guaranteed */
return LZ4_compress_fast_extState(state, src, dst, *srcSizePtr, targetDstSize, 1);
} else {
- if (*srcSizePtr < LZ4_64Klimit)
- return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, byU16);
- else
- return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, sizeof(void*)==8 ? byU32 : byPtr);
- }
+ if (*srcSizePtr < LZ4_64Klimit) {
+ return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, byU16, noDict, noDictIssue, 1);
+ } else {
+ tableType_t const addrMode = ((sizeof(void*)==4) && ((uptrval)src > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
+ return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, addrMode, noDict, noDictIssue, 1);
+ } }
}
int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize)
{
#if (LZ4_HEAPMODE)
- LZ4_stream_t* ctx = (LZ4_stream_t*)ALLOCATOR(1, sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */
+ LZ4_stream_t* ctx = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */
+ if (ctx == NULL) return 0;
#else
LZ4_stream_t ctxBody;
LZ4_stream_t* ctx = &ctxBody;
@@ -936,20 +1422,50 @@ int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targe
LZ4_stream_t* LZ4_createStream(void)
{
- LZ4_stream_t* lz4s = (LZ4_stream_t*)ALLOCATOR(8, LZ4_STREAMSIZE_U64);
+ LZ4_stream_t* const lz4s = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t));
LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_stream_t_internal)); /* A compilation error here means LZ4_STREAMSIZE is not large enough */
- LZ4_resetStream(lz4s);
+ DEBUGLOG(4, "LZ4_createStream %p", lz4s);
+ if (lz4s == NULL) return NULL;
+ LZ4_initStream(lz4s, sizeof(*lz4s));
return lz4s;
}
+static size_t LZ4_stream_t_alignment(void)
+{
+#if LZ4_ALIGN_TEST
+ typedef struct { char c; LZ4_stream_t t; } t_a;
+ return sizeof(t_a) - sizeof(LZ4_stream_t);
+#else
+ return 1; /* effectively disabled */
+#endif
+}
+
+LZ4_stream_t* LZ4_initStream (void* buffer, size_t size)
+{
+ DEBUGLOG(5, "LZ4_initStream");
+ if (buffer == NULL) { return NULL; }
+ if (size < sizeof(LZ4_stream_t)) { return NULL; }
+ if (!LZ4_isAligned(buffer, LZ4_stream_t_alignment())) return NULL;
+ MEM_INIT(buffer, 0, sizeof(LZ4_stream_t_internal));
+ return (LZ4_stream_t*)buffer;
+}
+
+/* resetStream is now deprecated,
+ * prefer initStream() which is more general */
void LZ4_resetStream (LZ4_stream_t* LZ4_stream)
{
- MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t));
+ DEBUGLOG(5, "LZ4_resetStream (ctx:%p)", LZ4_stream);
+ MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t_internal));
+}
+
+void LZ4_resetStream_fast(LZ4_stream_t* ctx) {
+ LZ4_prepareTable(&(ctx->internal_donotuse), 0, byU32);
}
int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
{
if (!LZ4_stream) return 0; /* support free on NULL */
+ DEBUGLOG(5, "LZ4_freeStream %p", LZ4_stream);
FREEMEM(LZ4_stream);
return (0);
}
@@ -959,43 +1475,82 @@ int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
{
LZ4_stream_t_internal* dict = &LZ4_dict->internal_donotuse;
+ const tableType_t tableType = byU32;
const BYTE* p = (const BYTE*)dictionary;
const BYTE* const dictEnd = p + dictSize;
const BYTE* base;
- if ((dict->initCheck) || (dict->currentOffset > 1 GB)) /* Uninitialized structure, or reuse overflow */
- LZ4_resetStream(LZ4_dict);
+ DEBUGLOG(4, "LZ4_loadDict (%i bytes from %p into %p)", dictSize, dictionary, LZ4_dict);
+
+ /* It's necessary to reset the context,
+ * and not just continue it with prepareTable()
+ * to avoid any risk of generating overflowing matchIndex
+ * when compressing using this dictionary */
+ LZ4_resetStream(LZ4_dict);
+
+ /* We always increment the offset by 64 KB, since, if the dict is longer,
+ * we truncate it to the last 64k, and if it's shorter, we still want to
+ * advance by a whole window length so we can provide the guarantee that
+ * there are only valid offsets in the window, which allows an optimization
+ * in LZ4_compress_fast_continue() where it uses noDictIssue even when the
+ * dictionary isn't a full 64k. */
+ dict->currentOffset += 64 KB;
if (dictSize < (int)HASH_UNIT) {
- dict->dictionary = NULL;
- dict->dictSize = 0;
return 0;
}
if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB;
- dict->currentOffset += 64 KB;
- base = p - dict->currentOffset;
+ base = dictEnd - dict->currentOffset;
dict->dictionary = p;
dict->dictSize = (U32)(dictEnd - p);
- dict->currentOffset += dict->dictSize;
+ dict->tableType = (U32)tableType;
while (p <= dictEnd-HASH_UNIT) {
- LZ4_putPosition(p, dict->hashTable, byU32, base);
+ LZ4_putPosition(p, dict->hashTable, tableType, base);
p+=3;
}
- return dict->dictSize;
+ return (int)dict->dictSize;
+}
+
+void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream) {
+ const LZ4_stream_t_internal* dictCtx = dictionaryStream == NULL ? NULL :
+ &(dictionaryStream->internal_donotuse);
+
+ DEBUGLOG(4, "LZ4_attach_dictionary (%p, %p, size %u)",
+ workingStream, dictionaryStream,
+ dictCtx != NULL ? dictCtx->dictSize : 0);
+
+ if (dictCtx != NULL) {
+ /* If the current offset is zero, we will never look in the
+ * external dictionary context, since there is no value a table
+ * entry can take that indicate a miss. In that case, we need
+ * to bump the offset to something non-zero.
+ */
+ if (workingStream->internal_donotuse.currentOffset == 0) {
+ workingStream->internal_donotuse.currentOffset = 64 KB;
+ }
+
+ /* Don't actually attach an empty dictionary.
+ */
+ if (dictCtx->dictSize == 0) {
+ dictCtx = NULL;
+ }
+ }
+ workingStream->internal_donotuse.dictCtx = dictCtx;
}
-static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src)
+static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, int nextSize)
{
- if ((LZ4_dict->currentOffset > 0x80000000) ||
- ((uptrval)LZ4_dict->currentOffset > (uptrval)src)) { /* address space overflow */
+ assert(nextSize >= 0);
+ if (LZ4_dict->currentOffset + (unsigned)nextSize > 0x80000000) { /* potential ptrdiff_t overflow (32-bits mode) */
/* rescale hash table */
U32 const delta = LZ4_dict->currentOffset - 64 KB;
const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize;
int i;
+ DEBUGLOG(4, "LZ4_renormDictT");
for (i=0; ihashTable[i] < delta) LZ4_dict->hashTable[i]=0;
else LZ4_dict->hashTable[i] -= delta;
@@ -1007,16 +1562,29 @@ static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src)
}
-int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
+int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream,
+ const char* source, char* dest,
+ int inputSize, int maxOutputSize,
+ int acceleration)
{
+ const tableType_t tableType = byU32;
LZ4_stream_t_internal* streamPtr = &LZ4_stream->internal_donotuse;
- const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize;
+ const BYTE* dictEnd = streamPtr->dictionary + streamPtr->dictSize;
- const BYTE* smallest = (const BYTE*) source;
- if (streamPtr->initCheck) return 0; /* Uninitialized structure detected */
- if ((streamPtr->dictSize>0) && (smallest>dictEnd)) smallest = dictEnd;
- LZ4_renormDictT(streamPtr, smallest);
- if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
+ DEBUGLOG(5, "LZ4_compress_fast_continue (inputSize=%i)", inputSize);
+
+ LZ4_renormDictT(streamPtr, inputSize); /* avoid index overflow */
+ if (acceleration < 1) acceleration = LZ4_ACCELERATION_DEFAULT;
+ if (acceleration > LZ4_ACCELERATION_MAX) acceleration = LZ4_ACCELERATION_MAX;
+
+ /* invalidate tiny dictionaries */
+ if ( (streamPtr->dictSize-1 < 4-1) /* intentional underflow */
+ && (dictEnd != (const BYTE*)source) ) {
+ DEBUGLOG(5, "LZ4_compress_fast_continue: dictSize(%u) at addr:%p is too small", streamPtr->dictSize, streamPtr->dictionary);
+ streamPtr->dictSize = 0;
+ streamPtr->dictionary = (const BYTE*)source;
+ dictEnd = (const BYTE*)source;
+ }
/* Check overlapping input/dictionary space */
{ const BYTE* sourceEnd = (const BYTE*) source + inputSize;
@@ -1030,46 +1598,61 @@ int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, ch
/* prefix mode : source data follows dictionary */
if (dictEnd == (const BYTE*)source) {
- int result;
if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
- result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, dictSmall, acceleration);
+ return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, dictSmall, acceleration);
else
- result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, noDictIssue, acceleration);
- streamPtr->dictSize += (U32)inputSize;
- streamPtr->currentOffset += (U32)inputSize;
- return result;
+ return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, noDictIssue, acceleration);
}
/* external dictionary mode */
{ int result;
- if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
- result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, dictSmall, acceleration);
- else
- result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, noDictIssue, acceleration);
+ if (streamPtr->dictCtx) {
+ /* We depend here on the fact that dictCtx'es (produced by
+ * LZ4_loadDict) guarantee that their tables contain no references
+ * to offsets between dictCtx->currentOffset - 64 KB and
+ * dictCtx->currentOffset - dictCtx->dictSize. This makes it safe
+ * to use noDictIssue even when the dict isn't a full 64 KB.
+ */
+ if (inputSize > 4 KB) {
+ /* For compressing large blobs, it is faster to pay the setup
+ * cost to copy the dictionary's tables into the active context,
+ * so that the compression loop is only looking into one table.
+ */
+ LZ4_memcpy(streamPtr, streamPtr->dictCtx, sizeof(*streamPtr));
+ result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration);
+ } else {
+ result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingDictCtx, noDictIssue, acceleration);
+ }
+ } else {
+ if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) {
+ result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, dictSmall, acceleration);
+ } else {
+ result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration);
+ }
+ }
streamPtr->dictionary = (const BYTE*)source;
streamPtr->dictSize = (U32)inputSize;
- streamPtr->currentOffset += (U32)inputSize;
return result;
}
}
-/* Hidden debug function, to force external dictionary mode */
-int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int inputSize)
+/* Hidden debug function, to force-test external dictionary mode */
+int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize)
{
LZ4_stream_t_internal* streamPtr = &LZ4_dict->internal_donotuse;
int result;
- const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize;
- const BYTE* smallest = dictEnd;
- if (smallest > (const BYTE*) source) smallest = (const BYTE*) source;
- LZ4_renormDictT(streamPtr, smallest);
+ LZ4_renormDictT(streamPtr, srcSize);
- result = LZ4_compress_generic(streamPtr, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1);
+ if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) {
+ result = LZ4_compress_generic(streamPtr, source, dest, srcSize, NULL, 0, notLimited, byU32, usingExtDict, dictSmall, 1);
+ } else {
+ result = LZ4_compress_generic(streamPtr, source, dest, srcSize, NULL, 0, notLimited, byU32, usingExtDict, noDictIssue, 1);
+ }
streamPtr->dictionary = (const BYTE*)source;
- streamPtr->dictSize = (U32)inputSize;
- streamPtr->currentOffset += (U32)inputSize;
+ streamPtr->dictSize = (U32)srcSize;
return result;
}
@@ -1087,10 +1670,12 @@ int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize)
LZ4_stream_t_internal* const dict = &LZ4_dict->internal_donotuse;
const BYTE* const previousDictEnd = dict->dictionary + dict->dictSize;
- if ((U32)dictSize > 64 KB) dictSize = 64 KB; /* useless to define a dictionary > 64 KB */
- if ((U32)dictSize > dict->dictSize) dictSize = dict->dictSize;
+ if ((U32)dictSize > 64 KB) { dictSize = 64 KB; } /* useless to define a dictionary > 64 KB */
+ if ((U32)dictSize > dict->dictSize) { dictSize = (int)dict->dictSize; }
- memmove(safeBuffer, previousDictEnd - dictSize, dictSize);
+ if (safeBuffer == NULL) assert(dictSize == 0);
+ if (dictSize > 0)
+ memmove(safeBuffer, previousDictEnd - dictSize, dictSize);
dict->dictionary = (const BYTE*)safeBuffer;
dict->dictSize = (U32)dictSize;
@@ -1100,214 +1685,602 @@ int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize)
-/*-*****************************
-* Decompression functions
-*******************************/
+/*-*******************************
+ * Decompression functions
+ ********************************/
+
+typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
+typedef enum { decode_full_block = 0, partial_decode = 1 } earlyEnd_directive;
+
+#undef MIN
+#define MIN(a,b) ( (a) < (b) ? (a) : (b) )
+
+/* Read the variable-length literal or match length.
+ *
+ * ip - pointer to use as input.
+ * lencheck - end ip. Return an error if ip advances >= lencheck.
+ * loop_check - check ip >= lencheck in body of loop. Returns loop_error if so.
+ * initial_check - check ip >= lencheck before start of loop. Returns initial_error if so.
+ * error (output) - error code. Should be set to 0 before call.
+ */
+typedef enum { loop_error = -2, initial_error = -1, ok = 0 } variable_length_error;
+LZ4_FORCE_INLINE unsigned
+read_variable_length(const BYTE**ip, const BYTE* lencheck,
+ int loop_check, int initial_check,
+ variable_length_error* error)
+{
+ U32 length = 0;
+ U32 s;
+ if (initial_check && unlikely((*ip) >= lencheck)) { /* overflow detection */
+ *error = initial_error;
+ return length;
+ }
+ do {
+ s = **ip;
+ (*ip)++;
+ length += s;
+ if (loop_check && unlikely((*ip) >= lencheck)) { /* overflow detection */
+ *error = loop_error;
+ return length;
+ }
+ } while (s==255);
+
+ return length;
+}
+
/*! LZ4_decompress_generic() :
- * This generic decompression function cover all use cases.
- * It shall be instantiated several times, using different sets of directives
- * Note that it is important this generic function is really inlined,
+ * This generic decompression function covers all use cases.
+ * It shall be instantiated several times, using different sets of directives.
+ * Note that it is important for performance that this function really get inlined,
* in order to remove useless branches during compilation optimization.
*/
-FORCE_INLINE int LZ4_decompress_generic(
- const char* const source,
- char* const dest,
- int inputSize,
- int outputSize, /* If endOnInput==endOnInputSize, this value is the max size of Output Buffer. */
+LZ4_FORCE_INLINE int
+LZ4_decompress_generic(
+ const char* const src,
+ char* const dst,
+ int srcSize,
+ int outputSize, /* If endOnInput==endOnInputSize, this value is `dstCapacity` */
- int endOnInput, /* endOnOutputSize, endOnInputSize */
- int partialDecoding, /* full, partial */
- int targetOutputSize, /* only used if partialDecoding==partial */
- int dict, /* noDict, withPrefix64k, usingExtDict */
- const BYTE* const lowPrefix, /* == dest when no prefix */
+ endCondition_directive endOnInput, /* endOnOutputSize, endOnInputSize */
+ earlyEnd_directive partialDecoding, /* full, partial */
+ dict_directive dict, /* noDict, withPrefix64k, usingExtDict */
+ const BYTE* const lowPrefix, /* always <= dst, == dst when no prefix */
const BYTE* const dictStart, /* only if dict==usingExtDict */
const size_t dictSize /* note : = 0 if noDict */
)
{
- /* Local Variables */
- const BYTE* ip = (const BYTE*) source;
- const BYTE* const iend = ip + inputSize;
+ if (src == NULL) { return -1; }
- BYTE* op = (BYTE*) dest;
- BYTE* const oend = op + outputSize;
- BYTE* cpy;
- BYTE* oexit = op + targetOutputSize;
- const BYTE* const lowLimit = lowPrefix - dictSize;
+ { const BYTE* ip = (const BYTE*) src;
+ const BYTE* const iend = ip + srcSize;
- const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize;
- const unsigned dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4};
- const int dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3};
+ BYTE* op = (BYTE*) dst;
+ BYTE* const oend = op + outputSize;
+ BYTE* cpy;
- const int safeDecode = (endOnInput==endOnInputSize);
- const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB)));
+ const BYTE* const dictEnd = (dictStart == NULL) ? NULL : dictStart + dictSize;
+
+ const int safeDecode = (endOnInput==endOnInputSize);
+ const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB)));
- /* Special cases */
- if ((partialDecoding) && (oexit > oend-MFLIMIT)) oexit = oend-MFLIMIT; /* targetOutputSize too high => decode everything */
- if ((endOnInput) && (unlikely(outputSize==0))) return ((inputSize==1) && (*ip==0)) ? 0 : -1; /* Empty output buffer */
- if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1);
+ /* Set up the "end" pointers for the shortcut. */
+ const BYTE* const shortiend = iend - (endOnInput ? 14 : 8) /*maxLL*/ - 2 /*offset*/;
+ const BYTE* const shortoend = oend - (endOnInput ? 14 : 8) /*maxLL*/ - 18 /*maxML*/;
- /* Main Loop : decode sequences */
- while (1) {
- size_t length;
const BYTE* match;
size_t offset;
+ unsigned token;
+ size_t length;
- /* get literal length */
- unsigned const token = *ip++;
- if ((length=(token>>ML_BITS)) == RUN_MASK) {
- unsigned s;
- do {
- s = *ip++;
- length += s;
- } while ( likely(endOnInput ? ip(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) )
- || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) )
- {
- if (partialDecoding) {
- if (cpy > oend) goto _output_error; /* Error : write attempt beyond end of output buffer */
- if ((endOnInput) && (ip+length > iend)) goto _output_error; /* Error : read attempt beyond end of input buffer */
+ /* Fast loop : decode sequences as long as output < iend-FASTLOOP_SAFE_DISTANCE */
+ while (1) {
+ /* Main fastloop assertion: We can always wildcopy FASTLOOP_SAFE_DISTANCE */
+ assert(oend - op >= FASTLOOP_SAFE_DISTANCE);
+ if (endOnInput) { assert(ip < iend); }
+ token = *ip++;
+ length = token >> ML_BITS; /* literal length */
+
+ assert(!endOnInput || ip <= iend); /* ip < iend before the increment */
+
+ /* decode literal length */
+ if (length == RUN_MASK) {
+ variable_length_error error = ok;
+ length += read_variable_length(&ip, iend-RUN_MASK, (int)endOnInput, (int)endOnInput, &error);
+ if (error == initial_error) { goto _output_error; }
+ if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */
+ if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */
+
+ /* copy literals */
+ cpy = op+length;
+ LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH);
+ if (endOnInput) { /* LZ4_decompress_safe() */
+ if ((cpy>oend-32) || (ip+length>iend-32)) { goto safe_literal_copy; }
+ LZ4_wildCopy32(op, ip, cpy);
+ } else { /* LZ4_decompress_fast() */
+ if (cpy>oend-8) { goto safe_literal_copy; }
+ LZ4_wildCopy8(op, ip, cpy); /* LZ4_decompress_fast() cannot copy more than 8 bytes at a time :
+ * it doesn't know input length, and only relies on end-of-block properties */
+ }
+ ip += length; op = cpy;
} else {
- if ((!endOnInput) && (cpy != oend)) goto _output_error; /* Error : block decoding must stop exactly there */
- if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) goto _output_error; /* Error : input must be consumed */
+ cpy = op+length;
+ if (endOnInput) { /* LZ4_decompress_safe() */
+ DEBUGLOG(7, "copy %u bytes in a 16-bytes stripe", (unsigned)length);
+ /* We don't need to check oend, since we check it once for each loop below */
+ if (ip > iend-(16 + 1/*max lit + offset + nextToken*/)) { goto safe_literal_copy; }
+ /* Literals can only be 14, but hope compilers optimize if we copy by a register size */
+ LZ4_memcpy(op, ip, 16);
+ } else { /* LZ4_decompress_fast() */
+ /* LZ4_decompress_fast() cannot copy more than 8 bytes at a time :
+ * it doesn't know input length, and relies on end-of-block properties */
+ LZ4_memcpy(op, ip, 8);
+ if (length > 8) { LZ4_memcpy(op+8, ip+8, 8); }
+ }
+ ip += length; op = cpy;
}
- memcpy(op, ip, length);
- ip += length;
- op += length;
- break; /* Necessarily EOF, due to parsing restrictions */
- }
- LZ4_wildCopy(op, ip, cpy);
- ip += length; op = cpy;
- /* get offset */
- offset = LZ4_readLE16(ip); ip+=2;
- match = op - offset;
- if ((checkOffset) && (unlikely(match < lowLimit))) goto _output_error; /* Error : offset outside buffers */
- LZ4_write32(op, (U32)offset); /* costs ~1%; silence an msan warning when offset==0 */
+ /* get offset */
+ offset = LZ4_readLE16(ip); ip+=2;
+ match = op - offset;
+ assert(match <= op);
- /* get matchlength */
- length = token & ML_MASK;
- if (length == ML_MASK) {
- unsigned s;
- do {
- s = *ip++;
- if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error;
- length += s;
- } while (s==255);
- if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error; /* overflow detection */
- }
- length += MINMATCH;
+ /* get matchlength */
+ length = token & ML_MASK;
- /* check external dictionary */
- if ((dict==usingExtDict) && (match < lowPrefix)) {
- if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error; /* doesn't respect parsing restriction */
-
- if (length <= (size_t)(lowPrefix-match)) {
- /* match can be copied as a single segment from external dictionary */
- memmove(op, dictEnd - (lowPrefix-match), length);
- op += length;
+ if (length == ML_MASK) {
+ variable_length_error error = ok;
+ if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */
+ length += read_variable_length(&ip, iend - LASTLITERALS + 1, (int)endOnInput, 0, &error);
+ if (error != ok) { goto _output_error; }
+ if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) { goto _output_error; } /* overflow detection */
+ length += MINMATCH;
+ if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) {
+ goto safe_match_copy;
+ }
} else {
- /* match encompass external dictionary and current block */
- size_t const copySize = (size_t)(lowPrefix-match);
- size_t const restSize = length - copySize;
- memcpy(op, dictEnd - copySize, copySize);
- op += copySize;
- if (restSize > (size_t)(op-lowPrefix)) { /* overlap copy */
- BYTE* const endOfMatch = op + restSize;
- const BYTE* copyFrom = lowPrefix;
- while (op < endOfMatch) *op++ = *copyFrom++;
+ length += MINMATCH;
+ if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) {
+ goto safe_match_copy;
+ }
+
+ /* Fastpath check: Avoids a branch in LZ4_wildCopy32 if true */
+ if ((dict == withPrefix64k) || (match >= lowPrefix)) {
+ if (offset >= 8) {
+ assert(match >= lowPrefix);
+ assert(match <= op);
+ assert(op + 18 <= oend);
+
+ LZ4_memcpy(op, match, 8);
+ LZ4_memcpy(op+8, match+8, 8);
+ LZ4_memcpy(op+16, match+16, 2);
+ op += length;
+ continue;
+ } } }
+
+ if (checkOffset && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */
+ /* match starting within external dictionary */
+ if ((dict==usingExtDict) && (match < lowPrefix)) {
+ if (unlikely(op+length > oend-LASTLITERALS)) {
+ if (partialDecoding) {
+ DEBUGLOG(7, "partialDecoding: dictionary match, close to dstEnd");
+ length = MIN(length, (size_t)(oend-op));
+ } else {
+ goto _output_error; /* end-of-block condition violated */
+ } }
+
+ if (length <= (size_t)(lowPrefix-match)) {
+ /* match fits entirely within external dictionary : just copy */
+ memmove(op, dictEnd - (lowPrefix-match), length);
+ op += length;
} else {
- memcpy(op, lowPrefix, restSize);
- op += restSize;
- } }
- continue;
- }
-
- /* copy match within block */
- cpy = op + length;
- if (unlikely(offset<8)) {
- const int dec64 = dec64table[offset];
- op[0] = match[0];
- op[1] = match[1];
- op[2] = match[2];
- op[3] = match[3];
- match += dec32table[offset];
- memcpy(op+4, match, 4);
- match -= dec64;
- } else { LZ4_copy8(op, match); match+=8; }
- op += 8;
-
- if (unlikely(cpy>oend-12)) {
- BYTE* const oCopyLimit = oend-(WILDCOPYLENGTH-1);
- if (cpy > oend-LASTLITERALS) goto _output_error; /* Error : last LASTLITERALS bytes must be literals (uncompressed) */
- if (op < oCopyLimit) {
- LZ4_wildCopy(op, match, oCopyLimit);
- match += oCopyLimit - op;
- op = oCopyLimit;
+ /* match stretches into both external dictionary and current block */
+ size_t const copySize = (size_t)(lowPrefix - match);
+ size_t const restSize = length - copySize;
+ LZ4_memcpy(op, dictEnd - copySize, copySize);
+ op += copySize;
+ if (restSize > (size_t)(op - lowPrefix)) { /* overlap copy */
+ BYTE* const endOfMatch = op + restSize;
+ const BYTE* copyFrom = lowPrefix;
+ while (op < endOfMatch) { *op++ = *copyFrom++; }
+ } else {
+ LZ4_memcpy(op, lowPrefix, restSize);
+ op += restSize;
+ } }
+ continue;
}
- while (op16) LZ4_wildCopy(op+8, match+8, cpy);
+
+ /* copy match within block */
+ cpy = op + length;
+
+ assert((op <= oend) && (oend-op >= 32));
+ if (unlikely(offset<16)) {
+ LZ4_memcpy_using_offset(op, match, cpy, offset);
+ } else {
+ LZ4_wildCopy32(op, match, cpy);
+ }
+
+ op = cpy; /* wildcopy correction */
}
- op=cpy; /* correction */
+ safe_decode:
+#endif
+
+ /* Main Loop : decode remaining sequences where output < FASTLOOP_SAFE_DISTANCE */
+ while (1) {
+ token = *ip++;
+ length = token >> ML_BITS; /* literal length */
+
+ assert(!endOnInput || ip <= iend); /* ip < iend before the increment */
+
+ /* A two-stage shortcut for the most common case:
+ * 1) If the literal length is 0..14, and there is enough space,
+ * enter the shortcut and copy 16 bytes on behalf of the literals
+ * (in the fast mode, only 8 bytes can be safely copied this way).
+ * 2) Further if the match length is 4..18, copy 18 bytes in a similar
+ * manner; but we ensure that there's enough space in the output for
+ * those 18 bytes earlier, upon entering the shortcut (in other words,
+ * there is a combined check for both stages).
+ */
+ if ( (endOnInput ? length != RUN_MASK : length <= 8)
+ /* strictly "less than" on input, to re-enter the loop with at least one byte */
+ && likely((endOnInput ? ip < shortiend : 1) & (op <= shortoend)) ) {
+ /* Copy the literals */
+ LZ4_memcpy(op, ip, endOnInput ? 16 : 8);
+ op += length; ip += length;
+
+ /* The second stage: prepare for match copying, decode full info.
+ * If it doesn't work out, the info won't be wasted. */
+ length = token & ML_MASK; /* match length */
+ offset = LZ4_readLE16(ip); ip += 2;
+ match = op - offset;
+ assert(match <= op); /* check overflow */
+
+ /* Do not deal with overlapping matches. */
+ if ( (length != ML_MASK)
+ && (offset >= 8)
+ && (dict==withPrefix64k || match >= lowPrefix) ) {
+ /* Copy the match. */
+ LZ4_memcpy(op + 0, match + 0, 8);
+ LZ4_memcpy(op + 8, match + 8, 8);
+ LZ4_memcpy(op +16, match +16, 2);
+ op += length + MINMATCH;
+ /* Both stages worked, load the next token. */
+ continue;
+ }
+
+ /* The second stage didn't work out, but the info is ready.
+ * Propel it right to the point of match copying. */
+ goto _copy_match;
+ }
+
+ /* decode literal length */
+ if (length == RUN_MASK) {
+ variable_length_error error = ok;
+ length += read_variable_length(&ip, iend-RUN_MASK, (int)endOnInput, (int)endOnInput, &error);
+ if (error == initial_error) { goto _output_error; }
+ if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */
+ if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */
+ }
+
+ /* copy literals */
+ cpy = op+length;
+#if LZ4_FAST_DEC_LOOP
+ safe_literal_copy:
+#endif
+ LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH);
+ if ( ((endOnInput) && ((cpy>oend-MFLIMIT) || (ip+length>iend-(2+1+LASTLITERALS))) )
+ || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) )
+ {
+ /* We've either hit the input parsing restriction or the output parsing restriction.
+ * In the normal scenario, decoding a full block, it must be the last sequence,
+ * otherwise it's an error (invalid input or dimensions).
+ * In partialDecoding scenario, it's necessary to ensure there is no buffer overflow.
+ */
+ if (partialDecoding) {
+ /* Since we are partial decoding we may be in this block because of the output parsing
+ * restriction, which is not valid since the output buffer is allowed to be undersized.
+ */
+ assert(endOnInput);
+ DEBUGLOG(7, "partialDecoding: copying literals, close to input or output end")
+ DEBUGLOG(7, "partialDecoding: literal length = %u", (unsigned)length);
+ DEBUGLOG(7, "partialDecoding: remaining space in dstBuffer : %i", (int)(oend - op));
+ DEBUGLOG(7, "partialDecoding: remaining space in srcBuffer : %i", (int)(iend - ip));
+ /* Finishing in the middle of a literals segment,
+ * due to lack of input.
+ */
+ if (ip+length > iend) {
+ length = (size_t)(iend-ip);
+ cpy = op + length;
+ }
+ /* Finishing in the middle of a literals segment,
+ * due to lack of output space.
+ */
+ if (cpy > oend) {
+ cpy = oend;
+ assert(op<=oend);
+ length = (size_t)(oend-op);
+ }
+ } else {
+ /* We must be on the last sequence because of the parsing limitations so check
+ * that we exactly regenerate the original size (must be exact when !endOnInput).
+ */
+ if ((!endOnInput) && (cpy != oend)) { goto _output_error; }
+ /* We must be on the last sequence (or invalid) because of the parsing limitations
+ * so check that we exactly consume the input and don't overrun the output buffer.
+ */
+ if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) {
+ DEBUGLOG(6, "should have been last run of literals")
+ DEBUGLOG(6, "ip(%p) + length(%i) = %p != iend (%p)", ip, (int)length, ip+length, iend);
+ DEBUGLOG(6, "or cpy(%p) > oend(%p)", cpy, oend);
+ goto _output_error;
+ }
+ }
+ memmove(op, ip, length); /* supports overlapping memory regions; only matters for in-place decompression scenarios */
+ ip += length;
+ op += length;
+ /* Necessarily EOF when !partialDecoding.
+ * When partialDecoding, it is EOF if we've either
+ * filled the output buffer or
+ * can't proceed with reading an offset for following match.
+ */
+ if (!partialDecoding || (cpy == oend) || (ip >= (iend-2))) {
+ break;
+ }
+ } else {
+ LZ4_wildCopy8(op, ip, cpy); /* may overwrite up to WILDCOPYLENGTH beyond cpy */
+ ip += length; op = cpy;
+ }
+
+ /* get offset */
+ offset = LZ4_readLE16(ip); ip+=2;
+ match = op - offset;
+
+ /* get matchlength */
+ length = token & ML_MASK;
+
+ _copy_match:
+ if (length == ML_MASK) {
+ variable_length_error error = ok;
+ length += read_variable_length(&ip, iend - LASTLITERALS + 1, (int)endOnInput, 0, &error);
+ if (error != ok) goto _output_error;
+ if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error; /* overflow detection */
+ }
+ length += MINMATCH;
+
+#if LZ4_FAST_DEC_LOOP
+ safe_match_copy:
+#endif
+ if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error; /* Error : offset outside buffers */
+ /* match starting within external dictionary */
+ if ((dict==usingExtDict) && (match < lowPrefix)) {
+ if (unlikely(op+length > oend-LASTLITERALS)) {
+ if (partialDecoding) length = MIN(length, (size_t)(oend-op));
+ else goto _output_error; /* doesn't respect parsing restriction */
+ }
+
+ if (length <= (size_t)(lowPrefix-match)) {
+ /* match fits entirely within external dictionary : just copy */
+ memmove(op, dictEnd - (lowPrefix-match), length);
+ op += length;
+ } else {
+ /* match stretches into both external dictionary and current block */
+ size_t const copySize = (size_t)(lowPrefix - match);
+ size_t const restSize = length - copySize;
+ LZ4_memcpy(op, dictEnd - copySize, copySize);
+ op += copySize;
+ if (restSize > (size_t)(op - lowPrefix)) { /* overlap copy */
+ BYTE* const endOfMatch = op + restSize;
+ const BYTE* copyFrom = lowPrefix;
+ while (op < endOfMatch) *op++ = *copyFrom++;
+ } else {
+ LZ4_memcpy(op, lowPrefix, restSize);
+ op += restSize;
+ } }
+ continue;
+ }
+ assert(match >= lowPrefix);
+
+ /* copy match within block */
+ cpy = op + length;
+
+ /* partialDecoding : may end anywhere within the block */
+ assert(op<=oend);
+ if (partialDecoding && (cpy > oend-MATCH_SAFEGUARD_DISTANCE)) {
+ size_t const mlen = MIN(length, (size_t)(oend-op));
+ const BYTE* const matchEnd = match + mlen;
+ BYTE* const copyEnd = op + mlen;
+ if (matchEnd > op) { /* overlap copy */
+ while (op < copyEnd) { *op++ = *match++; }
+ } else {
+ LZ4_memcpy(op, match, mlen);
+ }
+ op = copyEnd;
+ if (op == oend) { break; }
+ continue;
+ }
+
+ if (unlikely(offset<8)) {
+ LZ4_write32(op, 0); /* silence msan warning when offset==0 */
+ op[0] = match[0];
+ op[1] = match[1];
+ op[2] = match[2];
+ op[3] = match[3];
+ match += inc32table[offset];
+ LZ4_memcpy(op+4, match, 4);
+ match -= dec64table[offset];
+ } else {
+ LZ4_memcpy(op, match, 8);
+ match += 8;
+ }
+ op += 8;
+
+ if (unlikely(cpy > oend-MATCH_SAFEGUARD_DISTANCE)) {
+ BYTE* const oCopyLimit = oend - (WILDCOPYLENGTH-1);
+ if (cpy > oend-LASTLITERALS) { goto _output_error; } /* Error : last LASTLITERALS bytes must be literals (uncompressed) */
+ if (op < oCopyLimit) {
+ LZ4_wildCopy8(op, match, oCopyLimit);
+ match += oCopyLimit - op;
+ op = oCopyLimit;
+ }
+ while (op < cpy) { *op++ = *match++; }
+ } else {
+ LZ4_memcpy(op, match, 8);
+ if (length > 16) { LZ4_wildCopy8(op+8, match+8, cpy); }
+ }
+ op = cpy; /* wildcopy correction */
+ }
+
+ /* end of decoding */
+ if (endOnInput) {
+ DEBUGLOG(5, "decoded %i bytes", (int) (((char*)op)-dst));
+ return (int) (((char*)op)-dst); /* Nb of output bytes decoded */
+ } else {
+ return (int) (((const char*)ip)-src); /* Nb of input bytes read */
+ }
+
+ /* Overflow error detected */
+ _output_error:
+ return (int) (-(((const char*)ip)-src))-1;
}
-
- /* end of decoding */
- if (endOnInput)
- return (int) (((char*)op)-dest); /* Nb of output bytes decoded */
- else
- return (int) (((const char*)ip)-source); /* Nb of input bytes read */
-
- /* Overflow error detected */
-_output_error:
- return (int) (-(((const char*)ip)-source))-1;
}
+/*===== Instantiate the API decoding functions. =====*/
+
+LZ4_FORCE_O2
int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize)
{
- return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, full, 0, noDict, (BYTE*)dest, NULL, 0);
+ return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize,
+ endOnInputSize, decode_full_block, noDict,
+ (BYTE*)dest, NULL, 0);
}
-int LZ4_decompress_safe_partial(const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize)
+LZ4_FORCE_O2
+int LZ4_decompress_safe_partial(const char* src, char* dst, int compressedSize, int targetOutputSize, int dstCapacity)
{
- return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, partial, targetOutputSize, noDict, (BYTE*)dest, NULL, 0);
+ dstCapacity = MIN(targetOutputSize, dstCapacity);
+ return LZ4_decompress_generic(src, dst, compressedSize, dstCapacity,
+ endOnInputSize, partial_decode,
+ noDict, (BYTE*)dst, NULL, 0);
}
+LZ4_FORCE_O2
int LZ4_decompress_fast(const char* source, char* dest, int originalSize)
{
- return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)(dest - 64 KB), NULL, 64 KB);
+ return LZ4_decompress_generic(source, dest, 0, originalSize,
+ endOnOutputSize, decode_full_block, withPrefix64k,
+ (BYTE*)dest - 64 KB, NULL, 0);
}
+/*===== Instantiate a few more decoding cases, used more than once. =====*/
+
+LZ4_FORCE_O2 /* Exported, an obsolete API function. */
+int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize)
+{
+ return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+ endOnInputSize, decode_full_block, withPrefix64k,
+ (BYTE*)dest - 64 KB, NULL, 0);
+}
+
+/* Another obsolete API function, paired with the previous one. */
+int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize)
+{
+ /* LZ4_decompress_fast doesn't validate match offsets,
+ * and thus serves well with any prefixed dictionary. */
+ return LZ4_decompress_fast(source, dest, originalSize);
+}
+
+LZ4_FORCE_O2
+static int LZ4_decompress_safe_withSmallPrefix(const char* source, char* dest, int compressedSize, int maxOutputSize,
+ size_t prefixSize)
+{
+ return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+ endOnInputSize, decode_full_block, noDict,
+ (BYTE*)dest-prefixSize, NULL, 0);
+}
+
+LZ4_FORCE_O2
+int LZ4_decompress_safe_forceExtDict(const char* source, char* dest,
+ int compressedSize, int maxOutputSize,
+ const void* dictStart, size_t dictSize)
+{
+ return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+ endOnInputSize, decode_full_block, usingExtDict,
+ (BYTE*)dest, (const BYTE*)dictStart, dictSize);
+}
+
+LZ4_FORCE_O2
+static int LZ4_decompress_fast_extDict(const char* source, char* dest, int originalSize,
+ const void* dictStart, size_t dictSize)
+{
+ return LZ4_decompress_generic(source, dest, 0, originalSize,
+ endOnOutputSize, decode_full_block, usingExtDict,
+ (BYTE*)dest, (const BYTE*)dictStart, dictSize);
+}
+
+/* The "double dictionary" mode, for use with e.g. ring buffers: the first part
+ * of the dictionary is passed as prefix, and the second via dictStart + dictSize.
+ * These routines are used only once, in LZ4_decompress_*_continue().
+ */
+LZ4_FORCE_INLINE
+int LZ4_decompress_safe_doubleDict(const char* source, char* dest, int compressedSize, int maxOutputSize,
+ size_t prefixSize, const void* dictStart, size_t dictSize)
+{
+ return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+ endOnInputSize, decode_full_block, usingExtDict,
+ (BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize);
+}
+
+LZ4_FORCE_INLINE
+int LZ4_decompress_fast_doubleDict(const char* source, char* dest, int originalSize,
+ size_t prefixSize, const void* dictStart, size_t dictSize)
+{
+ return LZ4_decompress_generic(source, dest, 0, originalSize,
+ endOnOutputSize, decode_full_block, usingExtDict,
+ (BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize);
+}
/*===== streaming decompression functions =====*/
LZ4_streamDecode_t* LZ4_createStreamDecode(void)
{
- LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOCATOR(1, sizeof(LZ4_streamDecode_t));
+ LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOC_AND_ZERO(sizeof(LZ4_streamDecode_t));
+ LZ4_STATIC_ASSERT(LZ4_STREAMDECODESIZE >= sizeof(LZ4_streamDecode_t_internal)); /* A compilation error here means LZ4_STREAMDECODESIZE is not large enough */
return lz4s;
}
int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream)
{
- if (!LZ4_stream) return 0; /* support free on NULL */
+ if (LZ4_stream == NULL) { return 0; } /* support free on NULL */
FREEMEM(LZ4_stream);
return 0;
}
-/*!
- * LZ4_setStreamDecode() :
- * Use this function to instruct where to find the dictionary.
- * This function is not necessary if previous data is still available where it was decoded.
- * Loading a size of 0 is allowed (same effect as no dictionary).
- * Return : 1 if OK, 0 if error
+/*! LZ4_setStreamDecode() :
+ * Use this function to instruct where to find the dictionary.
+ * This function is not necessary if previous data is still available where it was decoded.
+ * Loading a size of 0 is allowed (same effect as no dictionary).
+ * @return : 1 if OK, 0 if error
*/
int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize)
{
@@ -1319,6 +2292,25 @@ int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dicti
return 1;
}
+/*! LZ4_decoderRingBufferSize() :
+ * when setting a ring buffer for streaming decompression (optional scenario),
+ * provides the minimum size of this ring buffer
+ * to be compatible with any source respecting maxBlockSize condition.
+ * Note : in a ring buffer scenario,
+ * blocks are presumed decompressed next to each other.
+ * When not enough space remains for next block (remainingSize < maxBlockSize),
+ * decoding resumes from beginning of ring buffer.
+ * @return : minimum ring buffer size,
+ * or 0 if there is an error (invalid maxBlockSize).
+ */
+int LZ4_decoderRingBufferSize(int maxBlockSize)
+{
+ if (maxBlockSize < 0) return 0;
+ if (maxBlockSize > LZ4_MAX_INPUT_SIZE) return 0;
+ if (maxBlockSize < 16) maxBlockSize = 16;
+ return LZ4_DECODER_RING_BUFFER_SIZE(maxBlockSize);
+}
+
/*
*_continue() :
These decoding functions allow decompression of multiple blocks in "streaming" mode.
@@ -1326,52 +2318,75 @@ int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dicti
If it's not possible, save the relevant part of decoded data into a safe buffer,
and indicate where it stands using LZ4_setStreamDecode()
*/
+LZ4_FORCE_O2
int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxOutputSize)
{
LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
int result;
- if (lz4sd->prefixEnd == (BYTE*)dest) {
- result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
- endOnInputSize, full, 0,
- usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
+ if (lz4sd->prefixSize == 0) {
+ /* The first call, no dictionary yet. */
+ assert(lz4sd->extDictSize == 0);
+ result = LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize);
if (result <= 0) return result;
- lz4sd->prefixSize += result;
+ lz4sd->prefixSize = (size_t)result;
+ lz4sd->prefixEnd = (BYTE*)dest + result;
+ } else if (lz4sd->prefixEnd == (BYTE*)dest) {
+ /* They're rolling the current segment. */
+ if (lz4sd->prefixSize >= 64 KB - 1)
+ result = LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize);
+ else if (lz4sd->extDictSize == 0)
+ result = LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize,
+ lz4sd->prefixSize);
+ else
+ result = LZ4_decompress_safe_doubleDict(source, dest, compressedSize, maxOutputSize,
+ lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
+ if (result <= 0) return result;
+ lz4sd->prefixSize += (size_t)result;
lz4sd->prefixEnd += result;
} else {
+ /* The buffer wraps around, or they're switching to another buffer. */
lz4sd->extDictSize = lz4sd->prefixSize;
lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
- result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
- endOnInputSize, full, 0,
- usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize);
+ result = LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize,
+ lz4sd->externalDict, lz4sd->extDictSize);
if (result <= 0) return result;
- lz4sd->prefixSize = result;
+ lz4sd->prefixSize = (size_t)result;
lz4sd->prefixEnd = (BYTE*)dest + result;
}
return result;
}
+LZ4_FORCE_O2
int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize)
{
LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
int result;
+ assert(originalSize >= 0);
- if (lz4sd->prefixEnd == (BYTE*)dest) {
- result = LZ4_decompress_generic(source, dest, 0, originalSize,
- endOnOutputSize, full, 0,
- usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
+ if (lz4sd->prefixSize == 0) {
+ assert(lz4sd->extDictSize == 0);
+ result = LZ4_decompress_fast(source, dest, originalSize);
if (result <= 0) return result;
- lz4sd->prefixSize += originalSize;
+ lz4sd->prefixSize = (size_t)originalSize;
+ lz4sd->prefixEnd = (BYTE*)dest + originalSize;
+ } else if (lz4sd->prefixEnd == (BYTE*)dest) {
+ if (lz4sd->prefixSize >= 64 KB - 1 || lz4sd->extDictSize == 0)
+ result = LZ4_decompress_fast(source, dest, originalSize);
+ else
+ result = LZ4_decompress_fast_doubleDict(source, dest, originalSize,
+ lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
+ if (result <= 0) return result;
+ lz4sd->prefixSize += (size_t)originalSize;
lz4sd->prefixEnd += originalSize;
} else {
lz4sd->extDictSize = lz4sd->prefixSize;
lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
- result = LZ4_decompress_generic(source, dest, 0, originalSize,
- endOnOutputSize, full, 0,
- usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize);
+ result = LZ4_decompress_fast_extDict(source, dest, originalSize,
+ lz4sd->externalDict, lz4sd->extDictSize);
if (result <= 0) return result;
- lz4sd->prefixSize = originalSize;
+ lz4sd->prefixSize = (size_t)originalSize;
lz4sd->prefixEnd = (BYTE*)dest + originalSize;
}
@@ -1386,32 +2401,27 @@ Advanced decoding functions :
the dictionary must be explicitly provided within parameters
*/
-FORCE_INLINE int LZ4_decompress_usingDict_generic(const char* source, char* dest, int compressedSize, int maxOutputSize, int safe, const char* dictStart, int dictSize)
-{
- if (dictSize==0)
- return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest, NULL, 0);
- if (dictStart+dictSize == dest) {
- if (dictSize >= (int)(64 KB - 1))
- return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, withPrefix64k, (BYTE*)dest-64 KB, NULL, 0);
- return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest-dictSize, NULL, 0);
- }
- return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize);
-}
-
int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
{
- return LZ4_decompress_usingDict_generic(source, dest, compressedSize, maxOutputSize, 1, dictStart, dictSize);
+ if (dictSize==0)
+ return LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize);
+ if (dictStart+dictSize == dest) {
+ if (dictSize >= 64 KB - 1) {
+ return LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize);
+ }
+ assert(dictSize >= 0);
+ return LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, (size_t)dictSize);
+ }
+ assert(dictSize >= 0);
+ return LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, dictStart, (size_t)dictSize);
}
int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize)
{
- return LZ4_decompress_usingDict_generic(source, dest, 0, originalSize, 0, dictStart, dictSize);
-}
-
-/* debug function */
-int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
-{
- return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize);
+ if (dictSize==0 || dictStart+dictSize == dest)
+ return LZ4_decompress_fast(source, dest, originalSize);
+ assert(dictSize >= 0);
+ return LZ4_decompress_fast_extDict(source, dest, originalSize, dictStart, (size_t)dictSize);
}
@@ -1419,64 +2429,67 @@ int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compres
* Obsolete Functions
***************************************************/
/* obsolete compression functions */
-int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize) { return LZ4_compress_default(source, dest, inputSize, maxOutputSize); }
-int LZ4_compress(const char* source, char* dest, int inputSize) { return LZ4_compress_default(source, dest, inputSize, LZ4_compressBound(inputSize)); }
-int LZ4_compress_limitedOutput_withState (void* state, const char* src, char* dst, int srcSize, int dstSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, dstSize, 1); }
-int LZ4_compress_withState (void* state, const char* src, char* dst, int srcSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, LZ4_compressBound(srcSize), 1); }
-int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* src, char* dst, int srcSize, int maxDstSize) { return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, maxDstSize, 1); }
-int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize) { return LZ4_compress_fast_continue(LZ4_stream, source, dest, inputSize, LZ4_compressBound(inputSize), 1); }
+int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize)
+{
+ return LZ4_compress_default(source, dest, inputSize, maxOutputSize);
+}
+int LZ4_compress(const char* src, char* dest, int srcSize)
+{
+ return LZ4_compress_default(src, dest, srcSize, LZ4_compressBound(srcSize));
+}
+int LZ4_compress_limitedOutput_withState (void* state, const char* src, char* dst, int srcSize, int dstSize)
+{
+ return LZ4_compress_fast_extState(state, src, dst, srcSize, dstSize, 1);
+}
+int LZ4_compress_withState (void* state, const char* src, char* dst, int srcSize)
+{
+ return LZ4_compress_fast_extState(state, src, dst, srcSize, LZ4_compressBound(srcSize), 1);
+}
+int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* src, char* dst, int srcSize, int dstCapacity)
+{
+ return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, dstCapacity, 1);
+}
+int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize)
+{
+ return LZ4_compress_fast_continue(LZ4_stream, source, dest, inputSize, LZ4_compressBound(inputSize), 1);
+}
/*
-These function names are deprecated and should no longer be used.
+These decompression functions are deprecated and should no longer be used.
They are only provided here for compatibility with older user programs.
- LZ4_uncompress is totally equivalent to LZ4_decompress_fast
- LZ4_uncompress_unknownOutputSize is totally equivalent to LZ4_decompress_safe
*/
-int LZ4_uncompress (const char* source, char* dest, int outputSize) { return LZ4_decompress_fast(source, dest, outputSize); }
-int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize) { return LZ4_decompress_safe(source, dest, isize, maxOutputSize); }
-
+int LZ4_uncompress (const char* source, char* dest, int outputSize)
+{
+ return LZ4_decompress_fast(source, dest, outputSize);
+}
+int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize)
+{
+ return LZ4_decompress_safe(source, dest, isize, maxOutputSize);
+}
/* Obsolete Streaming functions */
-int LZ4_sizeofStreamState() { return LZ4_STREAMSIZE; }
-
-static void LZ4_init(LZ4_stream_t* lz4ds, BYTE* base)
-{
- MEM_INIT(lz4ds, 0, sizeof(LZ4_stream_t));
- lz4ds->internal_donotuse.bufferStart = base;
-}
+int LZ4_sizeofStreamState(void) { return LZ4_STREAMSIZE; }
int LZ4_resetStreamState(void* state, char* inputBuffer)
{
- if ((((uptrval)state) & 3) != 0) return 1; /* Error : pointer is not aligned on 4-bytes boundary */
- LZ4_init((LZ4_stream_t*)state, (BYTE*)inputBuffer);
+ (void)inputBuffer;
+ LZ4_resetStream((LZ4_stream_t*)state);
return 0;
}
void* LZ4_create (char* inputBuffer)
{
- LZ4_stream_t* lz4ds = (LZ4_stream_t*)ALLOCATOR(8, sizeof(LZ4_stream_t));
- LZ4_init (lz4ds, (BYTE*)inputBuffer);
- return lz4ds;
+ (void)inputBuffer;
+ return LZ4_createStream();
}
-char* LZ4_slideInputBuffer (void* LZ4_Data)
+char* LZ4_slideInputBuffer (void* state)
{
- LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)LZ4_Data)->internal_donotuse;
- int dictSize = LZ4_saveDict((LZ4_stream_t*)LZ4_Data, (char*)ctx->bufferStart, 64 KB);
- return (char*)(ctx->bufferStart + dictSize);
-}
-
-/* Obsolete streaming decompression functions */
-
-int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize)
-{
- return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB);
-}
-
-int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize)
-{
- return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB);
+ /* avoid const char * -> char * conversion warning */
+ return (char *)(uptrval)((LZ4_stream_t*)state)->internal_donotuse.dictionary;
}
#endif /* LZ4_COMMONDEFS_ONLY */
diff --git a/mfbt/lz4.h b/mfbt/lz4.h
index 86ca0d59c1..7ab1e483a9 100644
--- a/mfbt/lz4.h
+++ b/mfbt/lz4.h
@@ -1,7 +1,7 @@
/*
* LZ4 - Fast LZ compression algorithm
* Header File
- * Copyright (C) 2011-2017, Yann Collet.
+ * Copyright (C) 2011-present, Yann Collet.
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
@@ -46,24 +46,31 @@ extern "C" {
/**
Introduction
- LZ4 is lossless compression algorithm, providing compression speed at 400 MB/s per core,
+ LZ4 is lossless compression algorithm, providing compression speed >500 MB/s per core,
scalable with multi-cores CPU. It features an extremely fast decoder, with speed in
multiple GB/s per core, typically reaching RAM speed limits on multi-core systems.
The LZ4 compression library provides in-memory compression and decompression functions.
+ It gives full buffer control to user.
Compression can be done in:
- a single step (described as Simple Functions)
- a single step, reusing a context (described in Advanced Functions)
- unbounded multiple steps (described as Streaming compression)
- lz4.h provides block compression functions. It gives full buffer control to user.
- Decompressing an lz4-compressed block also requires metadata (such as compressed size).
- Each application is free to encode such metadata in whichever way it wants.
+ lz4.h generates and decodes LZ4-compressed blocks (doc/lz4_Block_format.md).
+ Decompressing such a compressed block requires additional metadata.
+ Exact metadata depends on exact decompression function.
+ For the typical case of LZ4_decompress_safe(),
+ metadata includes block's compressed size, and maximum bound of decompressed size.
+ Each application is free to encode and pass such metadata in whichever way it wants.
- An additional format, called LZ4 frame specification (doc/lz4_Frame_format.md),
- take care of encoding standard metadata alongside LZ4-compressed blocks.
- If your application requires interoperability, it's recommended to use it.
- A library is provided to take care of it, see lz4frame.h.
+ lz4.h only handle blocks, it can not generate Frames.
+
+ Blocks are different from Frames (doc/lz4_Frame_format.md).
+ Frames bundle both blocks and metadata in a specified manner.
+ Embedding metadata is required for compressed data to be self-contained and portable.
+ Frame format is delivered through a companion API, declared in lz4frame.h.
+ The `lz4` CLI can only manage frames.
*/
/*^***************************************************************
@@ -72,24 +79,28 @@ extern "C" {
/*
* LZ4_DLL_EXPORT :
* Enable exporting of functions when building a Windows DLL
-* LZ4LIB_API :
+* LZ4LIB_VISIBILITY :
* Control library symbols visibility.
*/
-#if defined(LZ4_DLL_EXPORT) && (LZ4_DLL_EXPORT==1)
-# define LZ4LIB_API __declspec(dllexport)
-#elif defined(LZ4_DLL_IMPORT) && (LZ4_DLL_IMPORT==1)
-# define LZ4LIB_API __declspec(dllimport) /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/
-#elif defined(__GNUC__) && (__GNUC__ >= 4)
-# define LZ4LIB_API __attribute__ ((__visibility__ ("default")))
-#else
-# define LZ4LIB_API
+#ifndef LZ4LIB_VISIBILITY
+# if defined(__GNUC__) && (__GNUC__ >= 4)
+# define LZ4LIB_VISIBILITY __attribute__ ((visibility ("default")))
+# else
+# define LZ4LIB_VISIBILITY
+# endif
+#endif
+#if defined(LZ4_DLL_EXPORT) && (LZ4_DLL_EXPORT==1)
+# define LZ4LIB_API __declspec(dllexport) LZ4LIB_VISIBILITY
+#elif defined(LZ4_DLL_IMPORT) && (LZ4_DLL_IMPORT==1)
+# define LZ4LIB_API __declspec(dllimport) LZ4LIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/
+#else
+# define LZ4LIB_API LZ4LIB_VISIBILITY
#endif
-
/*------ Version ------*/
#define LZ4_VERSION_MAJOR 1 /* for breaking interface changes */
-#define LZ4_VERSION_MINOR 8 /* for new (non-breaking) interface capabilities */
-#define LZ4_VERSION_RELEASE 0 /* for tweaks, bug-fixes, or development */
+#define LZ4_VERSION_MINOR 9 /* for new (non-breaking) interface capabilities */
+#define LZ4_VERSION_RELEASE 3 /* for tweaks, bug-fixes, or development */
#define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE)
@@ -98,8 +109,8 @@ extern "C" {
#define LZ4_EXPAND_AND_QUOTE(str) LZ4_QUOTE(str)
#define LZ4_VERSION_STRING LZ4_EXPAND_AND_QUOTE(LZ4_LIB_VERSION)
-LZ4LIB_API int LZ4_versionNumber (void); /**< library version number; to be used when checking dll version */
-LZ4LIB_API const char* LZ4_versionString (void); /**< library version string; to be used when checking dll version */
+LZ4LIB_API int LZ4_versionNumber (void); /**< library version number; useful to check dll version */
+LZ4LIB_API const char* LZ4_versionString (void); /**< library version string; useful to check dll version */
/*-************************************
@@ -108,42 +119,49 @@ LZ4LIB_API const char* LZ4_versionString (void); /**< library version string;
/*!
* LZ4_MEMORY_USAGE :
* Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.)
- * Increasing memory usage improves compression ratio
- * Reduced memory usage can improve speed, due to cache effect
+ * Increasing memory usage improves compression ratio.
+ * Reduced memory usage may improve speed, thanks to better cache locality.
* Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache
*/
#ifndef LZ4_MEMORY_USAGE
# define LZ4_MEMORY_USAGE 14
#endif
+
/*-************************************
* Simple Functions
**************************************/
/*! LZ4_compress_default() :
- Compresses 'sourceSize' bytes from buffer 'source'
- into already allocated 'dest' buffer of size 'maxDestSize'.
- Compression is guaranteed to succeed if 'maxDestSize' >= LZ4_compressBound(sourceSize).
- It also runs faster, so it's a recommended setting.
- If the function cannot compress 'source' into a more limited 'dest' budget,
- compression stops *immediately*, and the function result is zero.
- As a consequence, 'dest' content is not valid.
- This function never writes outside 'dest' buffer, nor read outside 'source' buffer.
- sourceSize : Max supported value is LZ4_MAX_INPUT_VALUE
- maxDestSize : full or partial size of buffer 'dest' (which must be already allocated)
- return : the number of bytes written into buffer 'dest' (necessarily <= maxOutputSize)
- or 0 if compression fails */
-LZ4LIB_API int LZ4_compress_default(const char* source, char* dest, int sourceSize, int maxDestSize);
+ * Compresses 'srcSize' bytes from buffer 'src'
+ * into already allocated 'dst' buffer of size 'dstCapacity'.
+ * Compression is guaranteed to succeed if 'dstCapacity' >= LZ4_compressBound(srcSize).
+ * It also runs faster, so it's a recommended setting.
+ * If the function cannot compress 'src' into a more limited 'dst' budget,
+ * compression stops *immediately*, and the function result is zero.
+ * In which case, 'dst' content is undefined (invalid).
+ * srcSize : max supported value is LZ4_MAX_INPUT_SIZE.
+ * dstCapacity : size of buffer 'dst' (which must be already allocated)
+ * @return : the number of bytes written into buffer 'dst' (necessarily <= dstCapacity)
+ * or 0 if compression fails
+ * Note : This function is protected against buffer overflow scenarios (never writes outside 'dst' buffer, nor read outside 'source' buffer).
+ */
+LZ4LIB_API int LZ4_compress_default(const char* src, char* dst, int srcSize, int dstCapacity);
/*! LZ4_decompress_safe() :
- compressedSize : is the precise full size of the compressed block.
- maxDecompressedSize : is the size of destination buffer, which must be already allocated.
- return : the number of bytes decompressed into destination buffer (necessarily <= maxDecompressedSize)
- If destination buffer is not large enough, decoding will stop and output an error code (<0).
- If the source stream is detected malformed, the function will stop decoding and return a negative result.
- This function is protected against buffer overflow exploits, including malicious data packets.
- It never writes outside output buffer, nor reads outside input buffer.
-*/
-LZ4LIB_API int LZ4_decompress_safe (const char* source, char* dest, int compressedSize, int maxDecompressedSize);
+ * compressedSize : is the exact complete size of the compressed block.
+ * dstCapacity : is the size of destination buffer (which must be already allocated), presumed an upper bound of decompressed size.
+ * @return : the number of bytes decompressed into destination buffer (necessarily <= dstCapacity)
+ * If destination buffer is not large enough, decoding will stop and output an error code (negative value).
+ * If the source stream is detected malformed, the function will stop decoding and return a negative result.
+ * Note 1 : This function is protected against malicious data packets :
+ * it will never writes outside 'dst' buffer, nor read outside 'source' buffer,
+ * even if the compressed block is maliciously modified to order the decoder to do these actions.
+ * In such case, the decoder stops immediately, and considers the compressed block malformed.
+ * Note 2 : compressedSize and dstCapacity must be provided to the function, the compressed block does not contain them.
+ * The implementation is free to send / store / derive this information in whichever way is most beneficial.
+ * If there is a need for a different format which bundles together both compressed data and its metadata, consider looking at lz4frame.h instead.
+ */
+LZ4LIB_API int LZ4_decompress_safe (const char* src, char* dst, int compressedSize, int dstCapacity);
/*-************************************
@@ -152,252 +170,489 @@ LZ4LIB_API int LZ4_decompress_safe (const char* source, char* dest, int compress
#define LZ4_MAX_INPUT_SIZE 0x7E000000 /* 2 113 929 216 bytes */
#define LZ4_COMPRESSBOUND(isize) ((unsigned)(isize) > (unsigned)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16)
-/*!
-LZ4_compressBound() :
+/*! LZ4_compressBound() :
Provides the maximum size that LZ4 compression may output in a "worst case" scenario (input data not compressible)
This function is primarily useful for memory allocation purposes (destination buffer size).
Macro LZ4_COMPRESSBOUND() is also provided for compilation-time evaluation (stack memory allocation for example).
- Note that LZ4_compress_default() compress faster when dest buffer size is >= LZ4_compressBound(srcSize)
+ Note that LZ4_compress_default() compresses faster when dstCapacity is >= LZ4_compressBound(srcSize)
inputSize : max supported value is LZ4_MAX_INPUT_SIZE
return : maximum output size in a "worst case" scenario
- or 0, if input size is too large ( > LZ4_MAX_INPUT_SIZE)
+ or 0, if input size is incorrect (too large or negative)
*/
LZ4LIB_API int LZ4_compressBound(int inputSize);
-/*!
-LZ4_compress_fast() :
- Same as LZ4_compress_default(), but allows to select an "acceleration" factor.
+/*! LZ4_compress_fast() :
+ Same as LZ4_compress_default(), but allows selection of "acceleration" factor.
The larger the acceleration value, the faster the algorithm, but also the lesser the compression.
It's a trade-off. It can be fine tuned, with each successive value providing roughly +~3% to speed.
An acceleration value of "1" is the same as regular LZ4_compress_default()
- Values <= 0 will be replaced by ACCELERATION_DEFAULT (see lz4.c), which is 1.
+ Values <= 0 will be replaced by LZ4_ACCELERATION_DEFAULT (currently == 1, see lz4.c).
+ Values > LZ4_ACCELERATION_MAX will be replaced by LZ4_ACCELERATION_MAX (currently == 65537, see lz4.c).
*/
-LZ4LIB_API int LZ4_compress_fast (const char* source, char* dest, int sourceSize, int maxDestSize, int acceleration);
+LZ4LIB_API int LZ4_compress_fast (const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
-/*!
-LZ4_compress_fast_extState() :
- Same compression function, just using an externally allocated memory space to store compression state.
- Use LZ4_sizeofState() to know how much memory must be allocated,
- and allocate it on 8-bytes boundaries (using malloc() typically).
- Then, provide it as 'void* state' to compression function.
-*/
+/*! LZ4_compress_fast_extState() :
+ * Same as LZ4_compress_fast(), using an externally allocated memory space for its state.
+ * Use LZ4_sizeofState() to know how much memory must be allocated,
+ * and allocate it on 8-bytes boundaries (using `malloc()` typically).
+ * Then, provide this buffer as `void* state` to compression function.
+ */
LZ4LIB_API int LZ4_sizeofState(void);
-LZ4LIB_API int LZ4_compress_fast_extState (void* state, const char* source, char* dest, int inputSize, int maxDestSize, int acceleration);
+LZ4LIB_API int LZ4_compress_fast_extState (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
-/*!
-LZ4_compress_destSize() :
- Reverse the logic, by compressing as much data as possible from 'source' buffer
- into already allocated buffer 'dest' of size 'targetDestSize'.
- This function either compresses the entire 'source' content into 'dest' if it's large enough,
- or fill 'dest' buffer completely with as much data as possible from 'source'.
- *sourceSizePtr : will be modified to indicate how many bytes where read from 'source' to fill 'dest'.
- New value is necessarily <= old value.
- return : Nb bytes written into 'dest' (necessarily <= targetDestSize)
- or 0 if compression fails
-*/
-LZ4LIB_API int LZ4_compress_destSize (const char* source, char* dest, int* sourceSizePtr, int targetDestSize);
+/*! LZ4_compress_destSize() :
+ * Reverse the logic : compresses as much data as possible from 'src' buffer
+ * into already allocated buffer 'dst', of size >= 'targetDestSize'.
+ * This function either compresses the entire 'src' content into 'dst' if it's large enough,
+ * or fill 'dst' buffer completely with as much data as possible from 'src'.
+ * note: acceleration parameter is fixed to "default".
+ *
+ * *srcSizePtr : will be modified to indicate how many bytes where read from 'src' to fill 'dst'.
+ * New value is necessarily <= input value.
+ * @return : Nb bytes written into 'dst' (necessarily <= targetDestSize)
+ * or 0 if compression fails.
+ *
+ * Note : from v1.8.2 to v1.9.1, this function had a bug (fixed un v1.9.2+):
+ * the produced compressed content could, in specific circumstances,
+ * require to be decompressed into a destination buffer larger
+ * by at least 1 byte than the content to decompress.
+ * If an application uses `LZ4_compress_destSize()`,
+ * it's highly recommended to update liblz4 to v1.9.2 or better.
+ * If this can't be done or ensured,
+ * the receiving decompression function should provide
+ * a dstCapacity which is > decompressedSize, by at least 1 byte.
+ * See https://github.com/lz4/lz4/issues/859 for details
+ */
+LZ4LIB_API int LZ4_compress_destSize (const char* src, char* dst, int* srcSizePtr, int targetDstSize);
-/*!
-LZ4_decompress_fast() :
- originalSize : is the original and therefore uncompressed size
- return : the number of bytes read from the source buffer (in other words, the compressed size)
- If the source stream is detected malformed, the function will stop decoding and return a negative result.
- Destination buffer must be already allocated. Its size must be a minimum of 'originalSize' bytes.
- note : This function fully respect memory boundaries for properly formed compressed data.
- It is a bit faster than LZ4_decompress_safe().
- However, it does not provide any protection against intentionally modified data stream (malicious input).
- Use this function in trusted environment only (data to decode comes from a trusted source).
-*/
-LZ4LIB_API int LZ4_decompress_fast (const char* source, char* dest, int originalSize);
-
-/*!
-LZ4_decompress_safe_partial() :
- This function decompress a compressed block of size 'compressedSize' at position 'source'
- into destination buffer 'dest' of size 'maxDecompressedSize'.
- The function tries to stop decompressing operation as soon as 'targetOutputSize' has been reached,
- reducing decompression time.
- return : the number of bytes decoded in the destination buffer (necessarily <= maxDecompressedSize)
- Note : this number can be < 'targetOutputSize' should the compressed block to decode be smaller.
- Always control how many bytes were decoded.
- If the source stream is detected malformed, the function will stop decoding and return a negative result.
- This function never writes outside of output buffer, and never reads outside of input buffer. It is therefore protected against malicious data packets
-*/
-LZ4LIB_API int LZ4_decompress_safe_partial (const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize);
+/*! LZ4_decompress_safe_partial() :
+ * Decompress an LZ4 compressed block, of size 'srcSize' at position 'src',
+ * into destination buffer 'dst' of size 'dstCapacity'.
+ * Up to 'targetOutputSize' bytes will be decoded.
+ * The function stops decoding on reaching this objective.
+ * This can be useful to boost performance
+ * whenever only the beginning of a block is required.
+ *
+ * @return : the number of bytes decoded in `dst` (necessarily <= targetOutputSize)
+ * If source stream is detected malformed, function returns a negative result.
+ *
+ * Note 1 : @return can be < targetOutputSize, if compressed block contains less data.
+ *
+ * Note 2 : targetOutputSize must be <= dstCapacity
+ *
+ * Note 3 : this function effectively stops decoding on reaching targetOutputSize,
+ * so dstCapacity is kind of redundant.
+ * This is because in older versions of this function,
+ * decoding operation would still write complete sequences.
+ * Therefore, there was no guarantee that it would stop writing at exactly targetOutputSize,
+ * it could write more bytes, though only up to dstCapacity.
+ * Some "margin" used to be required for this operation to work properly.
+ * Thankfully, this is no longer necessary.
+ * The function nonetheless keeps the same signature, in an effort to preserve API compatibility.
+ *
+ * Note 4 : If srcSize is the exact size of the block,
+ * then targetOutputSize can be any value,
+ * including larger than the block's decompressed size.
+ * The function will, at most, generate block's decompressed size.
+ *
+ * Note 5 : If srcSize is _larger_ than block's compressed size,
+ * then targetOutputSize **MUST** be <= block's decompressed size.
+ * Otherwise, *silent corruption will occur*.
+ */
+LZ4LIB_API int LZ4_decompress_safe_partial (const char* src, char* dst, int srcSize, int targetOutputSize, int dstCapacity);
/*-*********************************************
* Streaming Compression Functions
***********************************************/
-typedef union LZ4_stream_u LZ4_stream_t; /* incomplete type (defined later) */
+typedef union LZ4_stream_u LZ4_stream_t; /* incomplete type (defined later) */
-/*! LZ4_createStream() and LZ4_freeStream() :
- * LZ4_createStream() will allocate and initialize an `LZ4_stream_t` structure.
- * LZ4_freeStream() releases its memory.
- */
LZ4LIB_API LZ4_stream_t* LZ4_createStream(void);
LZ4LIB_API int LZ4_freeStream (LZ4_stream_t* streamPtr);
-/*! LZ4_resetStream() :
- * An LZ4_stream_t structure can be allocated once and re-used multiple times.
- * Use this function to init an allocated `LZ4_stream_t` structure and start a new compression.
+/*! LZ4_resetStream_fast() : v1.9.0+
+ * Use this to prepare an LZ4_stream_t for a new chain of dependent blocks
+ * (e.g., LZ4_compress_fast_continue()).
+ *
+ * An LZ4_stream_t must be initialized once before usage.
+ * This is automatically done when created by LZ4_createStream().
+ * However, should the LZ4_stream_t be simply declared on stack (for example),
+ * it's necessary to initialize it first, using LZ4_initStream().
+ *
+ * After init, start any new stream with LZ4_resetStream_fast().
+ * A same LZ4_stream_t can be re-used multiple times consecutively
+ * and compress multiple streams,
+ * provided that it starts each new stream with LZ4_resetStream_fast().
+ *
+ * LZ4_resetStream_fast() is much faster than LZ4_initStream(),
+ * but is not compatible with memory regions containing garbage data.
+ *
+ * Note: it's only useful to call LZ4_resetStream_fast()
+ * in the context of streaming compression.
+ * The *extState* functions perform their own resets.
+ * Invoking LZ4_resetStream_fast() before is redundant, and even counterproductive.
*/
-LZ4LIB_API void LZ4_resetStream (LZ4_stream_t* streamPtr);
+LZ4LIB_API void LZ4_resetStream_fast (LZ4_stream_t* streamPtr);
/*! LZ4_loadDict() :
- * Use this function to load a static dictionary into LZ4_stream.
- * Any previous data will be forgotten, only 'dictionary' will remain in memory.
- * Loading a size of 0 is allowed.
- * Return : dictionary size, in bytes (necessarily <= 64 KB)
+ * Use this function to reference a static dictionary into LZ4_stream_t.
+ * The dictionary must remain available during compression.
+ * LZ4_loadDict() triggers a reset, so any previous data will be forgotten.
+ * The same dictionary will have to be loaded on decompression side for successful decoding.
+ * Dictionary are useful for better compression of small data (KB range).
+ * While LZ4 accept any input as dictionary,
+ * results are generally better when using Zstandard's Dictionary Builder.
+ * Loading a size of 0 is allowed, and is the same as reset.
+ * @return : loaded dictionary size, in bytes (necessarily <= 64 KB)
*/
LZ4LIB_API int LZ4_loadDict (LZ4_stream_t* streamPtr, const char* dictionary, int dictSize);
/*! LZ4_compress_fast_continue() :
- * Compress buffer content 'src', using data from previously compressed blocks as dictionary to improve compression ratio.
- * Important : Previous data blocks are assumed to remain present and unmodified !
- * 'dst' buffer must be already allocated.
+ * Compress 'src' content using data from previously compressed blocks, for better compression ratio.
+ * 'dst' buffer must be already allocated.
* If dstCapacity >= LZ4_compressBound(srcSize), compression is guaranteed to succeed, and runs faster.
- * If not, and if compressed data cannot fit into 'dst' buffer size, compression stops, and function @return==0.
- * After an error, the stream status is invalid, it can only be reset or freed.
+ *
+ * @return : size of compressed block
+ * or 0 if there is an error (typically, cannot fit into 'dst').
+ *
+ * Note 1 : Each invocation to LZ4_compress_fast_continue() generates a new block.
+ * Each block has precise boundaries.
+ * Each block must be decompressed separately, calling LZ4_decompress_*() with relevant metadata.
+ * It's not possible to append blocks together and expect a single invocation of LZ4_decompress_*() to decompress them together.
+ *
+ * Note 2 : The previous 64KB of source data is __assumed__ to remain present, unmodified, at same address in memory !
+ *
+ * Note 3 : When input is structured as a double-buffer, each buffer can have any size, including < 64 KB.
+ * Make sure that buffers are separated, by at least one byte.
+ * This construction ensures that each block only depends on previous block.
+ *
+ * Note 4 : If input buffer is a ring-buffer, it can have any size, including < 64 KB.
+ *
+ * Note 5 : After an error, the stream status is undefined (invalid), it can only be reset or freed.
*/
LZ4LIB_API int LZ4_compress_fast_continue (LZ4_stream_t* streamPtr, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
/*! LZ4_saveDict() :
- * If previously compressed data block is not guaranteed to remain available at its current memory location,
+ * If last 64KB data cannot be guaranteed to remain available at its current memory location,
* save it into a safer place (char* safeBuffer).
- * Note : it's not necessary to call LZ4_loadDict() after LZ4_saveDict(), dictionary is immediately usable.
- * @return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error.
+ * This is schematically equivalent to a memcpy() followed by LZ4_loadDict(),
+ * but is much faster, because LZ4_saveDict() doesn't need to rebuild tables.
+ * @return : saved dictionary size in bytes (necessarily <= maxDictSize), or 0 if error.
*/
-LZ4LIB_API int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int dictSize);
+LZ4LIB_API int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int maxDictSize);
/*-**********************************************
* Streaming Decompression Functions
* Bufferless synchronous API
************************************************/
-typedef union LZ4_streamDecode_u LZ4_streamDecode_t; /* incomplete type (defined later) */
+typedef union LZ4_streamDecode_u LZ4_streamDecode_t; /* tracking context */
/*! LZ4_createStreamDecode() and LZ4_freeStreamDecode() :
- * creation / destruction of streaming decompression tracking structure */
+ * creation / destruction of streaming decompression tracking context.
+ * A tracking context can be re-used multiple times.
+ */
LZ4LIB_API LZ4_streamDecode_t* LZ4_createStreamDecode(void);
LZ4LIB_API int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream);
/*! LZ4_setStreamDecode() :
- * Use this function to instruct where to find the dictionary.
- * Setting a size of 0 is allowed (same effect as reset).
- * @return : 1 if OK, 0 if error
+ * An LZ4_streamDecode_t context can be allocated once and re-used multiple times.
+ * Use this function to start decompression of a new stream of blocks.
+ * A dictionary can optionally be set. Use NULL or size 0 for a reset order.
+ * Dictionary is presumed stable : it must remain accessible and unmodified during next decompression.
+ * @return : 1 if OK, 0 if error
*/
LZ4LIB_API int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize);
+/*! LZ4_decoderRingBufferSize() : v1.8.2+
+ * Note : in a ring buffer scenario (optional),
+ * blocks are presumed decompressed next to each other
+ * up to the moment there is not enough remaining space for next block (remainingSize < maxBlockSize),
+ * at which stage it resumes from beginning of ring buffer.
+ * When setting such a ring buffer for streaming decompression,
+ * provides the minimum size of this ring buffer
+ * to be compatible with any source respecting maxBlockSize condition.
+ * @return : minimum ring buffer size,
+ * or 0 if there is an error (invalid maxBlockSize).
+ */
+LZ4LIB_API int LZ4_decoderRingBufferSize(int maxBlockSize);
+#define LZ4_DECODER_RING_BUFFER_SIZE(maxBlockSize) (65536 + 14 + (maxBlockSize)) /* for static allocation; maxBlockSize presumed valid */
+
/*! LZ4_decompress_*_continue() :
- * These decoding functions allow decompression of multiple blocks in "streaming" mode.
- * Previously decoded blocks *must* remain available at the memory position where they were decoded (up to 64 KB)
- * In the case of a ring buffers, decoding buffer must be either :
- * - Exactly same size as encoding buffer, with same update rule (block boundaries at same positions)
- * In which case, the decoding & encoding ring buffer can have any size, including very small ones ( < 64 KB).
- * - Larger than encoding buffer, by a minimum of maxBlockSize more bytes.
- * maxBlockSize is implementation dependent. It's the maximum size you intend to compress into a single block.
+ * These decoding functions allow decompression of consecutive blocks in "streaming" mode.
+ * A block is an unsplittable entity, it must be presented entirely to a decompression function.
+ * Decompression functions only accepts one block at a time.
+ * The last 64KB of previously decoded data *must* remain available and unmodified at the memory position where they were decoded.
+ * If less than 64KB of data has been decoded, all the data must be present.
+ *
+ * Special : if decompression side sets a ring buffer, it must respect one of the following conditions :
+ * - Decompression buffer size is _at least_ LZ4_decoderRingBufferSize(maxBlockSize).
+ * maxBlockSize is the maximum size of any single block. It can have any value > 16 bytes.
+ * In which case, encoding and decoding buffers do not need to be synchronized.
+ * Actually, data can be produced by any source compliant with LZ4 format specification, and respecting maxBlockSize.
+ * - Synchronized mode :
+ * Decompression buffer size is _exactly_ the same as compression buffer size,
+ * and follows exactly same update rule (block boundaries at same positions),
+ * and decoding function is provided with exact decompressed size of each block (exception for last block of the stream),
+ * _then_ decoding & encoding ring buffer can have any size, including small ones ( < 64 KB).
+ * - Decompression buffer is larger than encoding buffer, by a minimum of maxBlockSize more bytes.
* In which case, encoding and decoding buffers do not need to be synchronized,
* and encoding ring buffer can have any size, including small ones ( < 64 KB).
- * - _At least_ 64 KB + 8 bytes + maxBlockSize.
- * In which case, encoding and decoding buffers do not need to be synchronized,
- * and encoding ring buffer can have any size, including larger than decoding buffer.
- * Whenever these conditions are not possible, save the last 64KB of decoded data into a safe buffer,
- * and indicate where it is saved using LZ4_setStreamDecode()
+ *
+ * Whenever these conditions are not possible,
+ * save the last 64KB of decoded data into a safe buffer where it can't be modified during decompression,
+ * then indicate where this data is saved using LZ4_setStreamDecode(), before decompressing next block.
*/
-LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxDecompressedSize);
-LZ4LIB_API int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize);
+LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int srcSize, int dstCapacity);
/*! LZ4_decompress_*_usingDict() :
* These decoding functions work the same as
* a combination of LZ4_setStreamDecode() followed by LZ4_decompress_*_continue()
* They are stand-alone, and don't need an LZ4_streamDecode_t structure.
+ * Dictionary is presumed stable : it must remain accessible and unmodified during decompression.
+ * Performance tip : Decompression speed can be substantially increased
+ * when dst == dictStart + dictSize.
*/
-LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* source, char* dest, int compressedSize, int maxDecompressedSize, const char* dictStart, int dictSize);
-LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* source, char* dest, int originalSize, const char* dictStart, int dictSize);
+LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* src, char* dst, int srcSize, int dstCapcity, const char* dictStart, int dictSize);
+
+#endif /* LZ4_H_2983827168210 */
-/*^**********************************************
+/*^*************************************
* !!!!!! STATIC LINKING ONLY !!!!!!
- ***********************************************/
-/*-************************************
- * Private definitions
- **************************************
- * Do not use these definitions.
- * They are exposed to allow static allocation of `LZ4_stream_t` and `LZ4_streamDecode_t`.
- * Using these definitions will expose code to API and/or ABI break in future versions of the library.
- **************************************/
+ ***************************************/
+
+/*-****************************************************************************
+ * Experimental section
+ *
+ * Symbols declared in this section must be considered unstable. Their
+ * signatures or semantics may change, or they may be removed altogether in the
+ * future. They are therefore only safe to depend on when the caller is
+ * statically linked against the library.
+ *
+ * To protect against unsafe usage, not only are the declarations guarded,
+ * the definitions are hidden by default
+ * when building LZ4 as a shared/dynamic library.
+ *
+ * In order to access these declarations,
+ * define LZ4_STATIC_LINKING_ONLY in your application
+ * before including LZ4's headers.
+ *
+ * In order to make their implementations accessible dynamically, you must
+ * define LZ4_PUBLISH_STATIC_FUNCTIONS when building the LZ4 library.
+ ******************************************************************************/
+
+#ifdef LZ4_STATIC_LINKING_ONLY
+
+#ifndef LZ4_STATIC_3504398509
+#define LZ4_STATIC_3504398509
+
+#ifdef LZ4_PUBLISH_STATIC_FUNCTIONS
+#define LZ4LIB_STATIC_API LZ4LIB_API
+#else
+#define LZ4LIB_STATIC_API
+#endif
+
+
+/*! LZ4_compress_fast_extState_fastReset() :
+ * A variant of LZ4_compress_fast_extState().
+ *
+ * Using this variant avoids an expensive initialization step.
+ * It is only safe to call if the state buffer is known to be correctly initialized already
+ * (see above comment on LZ4_resetStream_fast() for a definition of "correctly initialized").
+ * From a high level, the difference is that
+ * this function initializes the provided state with a call to something like LZ4_resetStream_fast()
+ * while LZ4_compress_fast_extState() starts with a call to LZ4_resetStream().
+ */
+LZ4LIB_STATIC_API int LZ4_compress_fast_extState_fastReset (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
+
+/*! LZ4_attach_dictionary() :
+ * This is an experimental API that allows
+ * efficient use of a static dictionary many times.
+ *
+ * Rather than re-loading the dictionary buffer into a working context before
+ * each compression, or copying a pre-loaded dictionary's LZ4_stream_t into a
+ * working LZ4_stream_t, this function introduces a no-copy setup mechanism,
+ * in which the working stream references the dictionary stream in-place.
+ *
+ * Several assumptions are made about the state of the dictionary stream.
+ * Currently, only streams which have been prepared by LZ4_loadDict() should
+ * be expected to work.
+ *
+ * Alternatively, the provided dictionaryStream may be NULL,
+ * in which case any existing dictionary stream is unset.
+ *
+ * If a dictionary is provided, it replaces any pre-existing stream history.
+ * The dictionary contents are the only history that can be referenced and
+ * logically immediately precede the data compressed in the first subsequent
+ * compression call.
+ *
+ * The dictionary will only remain attached to the working stream through the
+ * first compression call, at the end of which it is cleared. The dictionary
+ * stream (and source buffer) must remain in-place / accessible / unchanged
+ * through the completion of the first compression call on the stream.
+ */
+LZ4LIB_STATIC_API void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream);
+
+
+/*! In-place compression and decompression
+ *
+ * It's possible to have input and output sharing the same buffer,
+ * for highly contrained memory environments.
+ * In both cases, it requires input to lay at the end of the buffer,
+ * and decompression to start at beginning of the buffer.
+ * Buffer size must feature some margin, hence be larger than final size.
+ *
+ * |<------------------------buffer--------------------------------->|
+ * |<-----------compressed data--------->|
+ * |<-----------decompressed size------------------>|
+ * |<----margin---->|
+ *
+ * This technique is more useful for decompression,
+ * since decompressed size is typically larger,
+ * and margin is short.
+ *
+ * In-place decompression will work inside any buffer
+ * which size is >= LZ4_DECOMPRESS_INPLACE_BUFFER_SIZE(decompressedSize).
+ * This presumes that decompressedSize > compressedSize.
+ * Otherwise, it means compression actually expanded data,
+ * and it would be more efficient to store such data with a flag indicating it's not compressed.
+ * This can happen when data is not compressible (already compressed, or encrypted).
+ *
+ * For in-place compression, margin is larger, as it must be able to cope with both
+ * history preservation, requiring input data to remain unmodified up to LZ4_DISTANCE_MAX,
+ * and data expansion, which can happen when input is not compressible.
+ * As a consequence, buffer size requirements are much higher,
+ * and memory savings offered by in-place compression are more limited.
+ *
+ * There are ways to limit this cost for compression :
+ * - Reduce history size, by modifying LZ4_DISTANCE_MAX.
+ * Note that it is a compile-time constant, so all compressions will apply this limit.
+ * Lower values will reduce compression ratio, except when input_size < LZ4_DISTANCE_MAX,
+ * so it's a reasonable trick when inputs are known to be small.
+ * - Require the compressor to deliver a "maximum compressed size".
+ * This is the `dstCapacity` parameter in `LZ4_compress*()`.
+ * When this size is < LZ4_COMPRESSBOUND(inputSize), then compression can fail,
+ * in which case, the return code will be 0 (zero).
+ * The caller must be ready for these cases to happen,
+ * and typically design a backup scheme to send data uncompressed.
+ * The combination of both techniques can significantly reduce
+ * the amount of margin required for in-place compression.
+ *
+ * In-place compression can work in any buffer
+ * which size is >= (maxCompressedSize)
+ * with maxCompressedSize == LZ4_COMPRESSBOUND(srcSize) for guaranteed compression success.
+ * LZ4_COMPRESS_INPLACE_BUFFER_SIZE() depends on both maxCompressedSize and LZ4_DISTANCE_MAX,
+ * so it's possible to reduce memory requirements by playing with them.
+ */
+
+#define LZ4_DECOMPRESS_INPLACE_MARGIN(compressedSize) (((compressedSize) >> 8) + 32)
+#define LZ4_DECOMPRESS_INPLACE_BUFFER_SIZE(decompressedSize) ((decompressedSize) + LZ4_DECOMPRESS_INPLACE_MARGIN(decompressedSize)) /**< note: presumes that compressedSize < decompressedSize. note2: margin is overestimated a bit, since it could use compressedSize instead */
+
+#ifndef LZ4_DISTANCE_MAX /* history window size; can be user-defined at compile time */
+# define LZ4_DISTANCE_MAX 65535 /* set to maximum value by default */
+#endif
+
+#define LZ4_COMPRESS_INPLACE_MARGIN (LZ4_DISTANCE_MAX + 32) /* LZ4_DISTANCE_MAX can be safely replaced by srcSize when it's smaller */
+#define LZ4_COMPRESS_INPLACE_BUFFER_SIZE(maxCompressedSize) ((maxCompressedSize) + LZ4_COMPRESS_INPLACE_MARGIN) /**< maxCompressedSize is generally LZ4_COMPRESSBOUND(inputSize), but can be set to any lower value, with the risk that compression can fail (return code 0(zero)) */
+
+#endif /* LZ4_STATIC_3504398509 */
+#endif /* LZ4_STATIC_LINKING_ONLY */
+
+
+
+#ifndef LZ4_H_98237428734687
+#define LZ4_H_98237428734687
+
+/*-************************************************************
+ * Private Definitions
+ **************************************************************
+ * Do not use these definitions directly.
+ * They are only exposed to allow static allocation of `LZ4_stream_t` and `LZ4_streamDecode_t`.
+ * Accessing members will expose user code to API and/or ABI break in future versions of the library.
+ **************************************************************/
#define LZ4_HASHLOG (LZ4_MEMORY_USAGE-2)
#define LZ4_HASHTABLESIZE (1 << LZ4_MEMORY_USAGE)
#define LZ4_HASH_SIZE_U32 (1 << LZ4_HASHLOG) /* required as macro for static allocation */
#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
-#include
-
-typedef struct {
- uint32_t hashTable[LZ4_HASH_SIZE_U32];
- uint32_t currentOffset;
- uint32_t initCheck;
- const uint8_t* dictionary;
- uint8_t* bufferStart; /* obsolete, used for slideInputBuffer */
- uint32_t dictSize;
-} LZ4_stream_t_internal;
-
-typedef struct {
- const uint8_t* externalDict;
- size_t extDictSize;
- const uint8_t* prefixEnd;
- size_t prefixSize;
-} LZ4_streamDecode_t_internal;
-
+# include
+ typedef int8_t LZ4_i8;
+ typedef uint8_t LZ4_byte;
+ typedef uint16_t LZ4_u16;
+ typedef uint32_t LZ4_u32;
#else
-
-typedef struct {
- unsigned int hashTable[LZ4_HASH_SIZE_U32];
- unsigned int currentOffset;
- unsigned int initCheck;
- const unsigned char* dictionary;
- unsigned char* bufferStart; /* obsolete, used for slideInputBuffer */
- unsigned int dictSize;
-} LZ4_stream_t_internal;
-
-typedef struct {
- const unsigned char* externalDict;
- size_t extDictSize;
- const unsigned char* prefixEnd;
- size_t prefixSize;
-} LZ4_streamDecode_t_internal;
-
+ typedef signed char LZ4_i8;
+ typedef unsigned char LZ4_byte;
+ typedef unsigned short LZ4_u16;
+ typedef unsigned int LZ4_u32;
#endif
-/*!
- * LZ4_stream_t :
- * information structure to track an LZ4 stream.
- * init this structure before first use.
- * note : only use in association with static linking !
- * this definition is not API/ABI safe,
- * it may change in a future version !
+typedef struct LZ4_stream_t_internal LZ4_stream_t_internal;
+struct LZ4_stream_t_internal {
+ LZ4_u32 hashTable[LZ4_HASH_SIZE_U32];
+ LZ4_u32 currentOffset;
+ LZ4_u32 tableType;
+ const LZ4_byte* dictionary;
+ const LZ4_stream_t_internal* dictCtx;
+ LZ4_u32 dictSize;
+};
+
+typedef struct {
+ const LZ4_byte* externalDict;
+ size_t extDictSize;
+ const LZ4_byte* prefixEnd;
+ size_t prefixSize;
+} LZ4_streamDecode_t_internal;
+
+
+/*! LZ4_stream_t :
+ * Do not use below internal definitions directly !
+ * Declare or allocate an LZ4_stream_t instead.
+ * LZ4_stream_t can also be created using LZ4_createStream(), which is recommended.
+ * The structure definition can be convenient for static allocation
+ * (on stack, or as part of larger structure).
+ * Init this structure with LZ4_initStream() before first use.
+ * note : only use this definition in association with static linking !
+ * this definition is not API/ABI safe, and may change in future versions.
*/
-#define LZ4_STREAMSIZE_U64 ((1 << (LZ4_MEMORY_USAGE-3)) + 4)
-#define LZ4_STREAMSIZE (LZ4_STREAMSIZE_U64 * sizeof(unsigned long long))
+#define LZ4_STREAMSIZE 16416 /* static size, for inter-version compatibility */
+#define LZ4_STREAMSIZE_VOIDP (LZ4_STREAMSIZE / sizeof(void*))
union LZ4_stream_u {
- unsigned long long table[LZ4_STREAMSIZE_U64];
+ void* table[LZ4_STREAMSIZE_VOIDP];
LZ4_stream_t_internal internal_donotuse;
-} ; /* previously typedef'd to LZ4_stream_t */
+}; /* previously typedef'd to LZ4_stream_t */
-/*!
- * LZ4_streamDecode_t :
- * information structure to track an LZ4 stream during decompression.
- * init this structure using LZ4_setStreamDecode (or memset()) before first use
- * note : only use in association with static linking !
- * this definition is not API/ABI safe,
- * and may change in a future version !
+/*! LZ4_initStream() : v1.9.0+
+ * An LZ4_stream_t structure must be initialized at least once.
+ * This is automatically done when invoking LZ4_createStream(),
+ * but it's not when the structure is simply declared on stack (for example).
+ *
+ * Use LZ4_initStream() to properly initialize a newly declared LZ4_stream_t.
+ * It can also initialize any arbitrary buffer of sufficient size,
+ * and will @return a pointer of proper type upon initialization.
+ *
+ * Note : initialization fails if size and alignment conditions are not respected.
+ * In which case, the function will @return NULL.
+ * Note2: An LZ4_stream_t structure guarantees correct alignment and size.
+ * Note3: Before v1.9.0, use LZ4_resetStream() instead
*/
-#define LZ4_STREAMDECODESIZE_U64 4
+LZ4LIB_API LZ4_stream_t* LZ4_initStream (void* buffer, size_t size);
+
+
+/*! LZ4_streamDecode_t :
+ * information structure to track an LZ4 stream during decompression.
+ * init this structure using LZ4_setStreamDecode() before first use.
+ * note : only use in association with static linking !
+ * this definition is not API/ABI safe,
+ * and may change in a future version !
+ */
+#define LZ4_STREAMDECODESIZE_U64 (4 + ((sizeof(void*)==16) ? 2 : 0) /*AS-400*/ )
#define LZ4_STREAMDECODESIZE (LZ4_STREAMDECODESIZE_U64 * sizeof(unsigned long long))
union LZ4_streamDecode_u {
unsigned long long table[LZ4_STREAMDECODESIZE_U64];
@@ -405,57 +660,113 @@ union LZ4_streamDecode_u {
} ; /* previously typedef'd to LZ4_streamDecode_t */
+
/*-************************************
* Obsolete Functions
**************************************/
/*! Deprecation warnings
- Should deprecation warnings be a problem,
- it is generally possible to disable them,
- typically with -Wno-deprecated-declarations for gcc
- or _CRT_SECURE_NO_WARNINGS in Visual.
- Otherwise, it's also possible to define LZ4_DISABLE_DEPRECATE_WARNINGS */
+ *
+ * Deprecated functions make the compiler generate a warning when invoked.
+ * This is meant to invite users to update their source code.
+ * Should deprecation warnings be a problem, it is generally possible to disable them,
+ * typically with -Wno-deprecated-declarations for gcc
+ * or _CRT_SECURE_NO_WARNINGS in Visual.
+ *
+ * Another method is to define LZ4_DISABLE_DEPRECATE_WARNINGS
+ * before including the header file.
+ */
#ifdef LZ4_DISABLE_DEPRECATE_WARNINGS
# define LZ4_DEPRECATED(message) /* disable deprecation warnings */
#else
-# define LZ4_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)
# if defined (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */
# define LZ4_DEPRECATED(message) [[deprecated(message)]]
-# elif (LZ4_GCC_VERSION >= 405) || defined(__clang__)
-# define LZ4_DEPRECATED(message) __attribute__((deprecated(message)))
-# elif (LZ4_GCC_VERSION >= 301)
-# define LZ4_DEPRECATED(message) __attribute__((deprecated))
# elif defined(_MSC_VER)
# define LZ4_DEPRECATED(message) __declspec(deprecated(message))
+# elif defined(__clang__) || (defined(__GNUC__) && (__GNUC__ * 10 + __GNUC_MINOR__ >= 45))
+# define LZ4_DEPRECATED(message) __attribute__((deprecated(message)))
+# elif defined(__GNUC__) && (__GNUC__ * 10 + __GNUC_MINOR__ >= 31)
+# define LZ4_DEPRECATED(message) __attribute__((deprecated))
# else
-# pragma message("WARNING: You need to implement LZ4_DEPRECATED for this compiler")
-# define LZ4_DEPRECATED(message)
+# pragma message("WARNING: LZ4_DEPRECATED needs custom implementation for this compiler")
+# define LZ4_DEPRECATED(message) /* disabled */
# endif
#endif /* LZ4_DISABLE_DEPRECATE_WARNINGS */
-/* Obsolete compression functions */
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_default() instead") int LZ4_compress (const char* source, char* dest, int sourceSize);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_default() instead") int LZ4_compress_limitedOutput (const char* source, char* dest, int sourceSize, int maxOutputSize);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") int LZ4_compress_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize);
+/*! Obsolete compression functions (since v1.7.3) */
+LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress (const char* src, char* dest, int srcSize);
+LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress_limitedOutput (const char* src, char* dest, int srcSize, int maxOutputSize);
+LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize);
+LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize);
+LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize);
+LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize);
-/* Obsolete decompression functions */
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_decompress_fast() instead") int LZ4_uncompress (const char* source, char* dest, int outputSize);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_decompress_safe() instead") int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize);
+/*! Obsolete decompression functions (since v1.8.0) */
+LZ4_DEPRECATED("use LZ4_decompress_fast() instead") LZ4LIB_API int LZ4_uncompress (const char* source, char* dest, int outputSize);
+LZ4_DEPRECATED("use LZ4_decompress_safe() instead") LZ4LIB_API int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize);
-/* Obsolete streaming functions; use new streaming interface whenever possible */
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_createStream() instead") void* LZ4_create (char* inputBuffer);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_createStream() instead") int LZ4_sizeofStreamState(void);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_resetStream() instead") int LZ4_resetStreamState(void* state, char* inputBuffer);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_saveDict() instead") char* LZ4_slideInputBuffer (void* state);
+/* Obsolete streaming functions (since v1.7.0)
+ * degraded functionality; do not use!
+ *
+ * In order to perform streaming compression, these functions depended on data
+ * that is no longer tracked in the state. They have been preserved as well as
+ * possible: using them will still produce a correct output. However, they don't
+ * actually retain any history between compression calls. The compression ratio
+ * achieved will therefore be no better than compressing each chunk
+ * independently.
+ */
+LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API void* LZ4_create (char* inputBuffer);
+LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API int LZ4_sizeofStreamState(void);
+LZ4_DEPRECATED("Use LZ4_resetStream() instead") LZ4LIB_API int LZ4_resetStreamState(void* state, char* inputBuffer);
+LZ4_DEPRECATED("Use LZ4_saveDict() instead") LZ4LIB_API char* LZ4_slideInputBuffer (void* state);
-/* Obsolete streaming decoding functions */
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_decompress_safe_usingDict() instead") int LZ4_decompress_safe_withPrefix64k (const char* src, char* dst, int compressedSize, int maxDstSize);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") int LZ4_decompress_fast_withPrefix64k (const char* src, char* dst, int originalSize);
+/*! Obsolete streaming decoding functions (since v1.7.0) */
+LZ4_DEPRECATED("use LZ4_decompress_safe_usingDict() instead") LZ4LIB_API int LZ4_decompress_safe_withPrefix64k (const char* src, char* dst, int compressedSize, int maxDstSize);
+LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") LZ4LIB_API int LZ4_decompress_fast_withPrefix64k (const char* src, char* dst, int originalSize);
-#endif /* LZ4_H_2983827168210 */
+/*! Obsolete LZ4_decompress_fast variants (since v1.9.0) :
+ * These functions used to be faster than LZ4_decompress_safe(),
+ * but this is no longer the case. They are now slower.
+ * This is because LZ4_decompress_fast() doesn't know the input size,
+ * and therefore must progress more cautiously into the input buffer to not read beyond the end of block.
+ * On top of that `LZ4_decompress_fast()` is not protected vs malformed or malicious inputs, making it a security liability.
+ * As a consequence, LZ4_decompress_fast() is strongly discouraged, and deprecated.
+ *
+ * The last remaining LZ4_decompress_fast() specificity is that
+ * it can decompress a block without knowing its compressed size.
+ * Such functionality can be achieved in a more secure manner
+ * by employing LZ4_decompress_safe_partial().
+ *
+ * Parameters:
+ * originalSize : is the uncompressed size to regenerate.
+ * `dst` must be already allocated, its size must be >= 'originalSize' bytes.
+ * @return : number of bytes read from source buffer (== compressed size).
+ * The function expects to finish at block's end exactly.
+ * If the source stream is detected malformed, the function stops decoding and returns a negative result.
+ * note : LZ4_decompress_fast*() requires originalSize. Thanks to this information, it never writes past the output buffer.
+ * However, since it doesn't know its 'src' size, it may read an unknown amount of input, past input buffer bounds.
+ * Also, since match offsets are not validated, match reads from 'src' may underflow too.
+ * These issues never happen if input (compressed) data is correct.
+ * But they may happen if input data is invalid (error or intentional tampering).
+ * As a consequence, use these functions in trusted environments with trusted data **only**.
+ */
+LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe() instead")
+LZ4LIB_API int LZ4_decompress_fast (const char* src, char* dst, int originalSize);
+LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe_continue() instead")
+LZ4LIB_API int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int originalSize);
+LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe_usingDict() instead")
+LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* src, char* dst, int originalSize, const char* dictStart, int dictSize);
+
+/*! LZ4_resetStream() :
+ * An LZ4_stream_t structure must be initialized at least once.
+ * This is done with LZ4_initStream(), or LZ4_resetStream().
+ * Consider switching to LZ4_initStream(),
+ * invoking LZ4_resetStream() will trigger deprecation warnings in the future.
+ */
+LZ4LIB_API void LZ4_resetStream (LZ4_stream_t* streamPtr);
+
+
+#endif /* LZ4_H_98237428734687 */
#if defined (__cplusplus)
From 88a254136576c924307dd7fc54fd69bf483200cf Mon Sep 17 00:00:00 2001
From: Moonchild
Date: Wed, 24 Feb 2021 14:24:24 +0000
Subject: [PATCH 9/9] [OTS] Backport some upstream OTS commits.
---
gfx/ots/src/glyf.cc | 203 +++++++++++++++++++++++++++++++++++++++-----
gfx/ots/src/glyf.h | 28 +++++-
2 files changed, 209 insertions(+), 22 deletions(-)
diff --git a/gfx/ots/src/glyf.cc b/gfx/ots/src/glyf.cc
index 0c19d6d7bc..322fd52fe5 100644
--- a/gfx/ots/src/glyf.cc
+++ b/gfx/ots/src/glyf.cc
@@ -99,6 +99,12 @@ bool OpenTypeGLYF::ParseSimpleGlyph(Buffer &glyph,
num_flags = tmp_index + 1;
}
+ if (this->maxp->version_1 &&
+ num_flags > this->maxp->max_points) {
+ Warning("Number of contour points exceeds maxp maxPoints, adjusting limit.");
+ this->maxp->max_points = num_flags;
+ }
+
uint16_t bytecode_length = 0;
if (!glyph.ReadU16(&bytecode_length)) {
return Error("Can't read bytecode length");
@@ -144,7 +150,9 @@ bool OpenTypeGLYF::ParseSimpleGlyph(Buffer &glyph,
#define WE_HAVE_A_TWO_BY_TWO (1u << 7)
#define WE_HAVE_INSTRUCTIONS (1u << 8)
-bool OpenTypeGLYF::ParseCompositeGlyph(Buffer &glyph) {
+bool OpenTypeGLYF::ParseCompositeGlyph(
+ Buffer &glyph,
+ ComponentPointCount* component_point_count) {
uint16_t flags = 0;
uint16_t gid = 0;
do {
@@ -193,6 +201,10 @@ bool OpenTypeGLYF::ParseCompositeGlyph(Buffer &glyph) {
return Error("Can't read transform");
}
}
+
+ // Push inital components on stack at level 1
+ // to traverse them in parent function.
+ component_point_count->gid_stack.push_back({gid, 1});
} while (flags & MORE_COMPONENTS);
if (flags & WE_HAVE_INSTRUCTIONS) {
@@ -243,29 +255,14 @@ bool OpenTypeGLYF::Parse(const uint8_t *data, size_t length) {
uint32_t current_offset = 0;
for (unsigned i = 0; i < num_glyphs; ++i) {
- const unsigned gly_offset = offsets[i];
- // The LOCA parser checks that these values are monotonic
- const unsigned gly_length = offsets[i + 1] - offsets[i];
- if (!gly_length) {
- // this glyph has no outline (e.g. the space charactor)
+ Buffer glyph(GetGlyphBufferSection(data, length, offsets, i));
+ if (!glyph.buffer())
+ return false;
+ if (!glyph.length()) {
resulting_offsets[i] = current_offset;
continue;
}
- if (gly_offset >= length) {
- return Error("Glyph %d offset %d too high %ld", i, gly_offset, length);
- }
- // Since these are unsigned types, the compiler is not allowed to assume
- // that they never overflow.
- if (gly_offset + gly_length < gly_offset) {
- return Error("Glyph %d length (%d < 0)!", i, gly_length);
- }
- if (gly_offset + gly_length > length) {
- return Error("Glyph %d length %d too high", i, gly_length);
- }
-
- Buffer glyph(data + gly_offset, gly_length);
-
int16_t num_contours, xmin, ymin, xmax, ymax;
if (!glyph.ReadS16(&num_contours) ||
!glyph.ReadS16(&xmin) ||
@@ -302,9 +299,56 @@ bool OpenTypeGLYF::Parse(const uint8_t *data, size_t length) {
return Error("Failed to parse glyph %d", i);
}
} else {
- if (!ParseCompositeGlyph(glyph)) {
+ ComponentPointCount component_point_count;
+ if (!ParseCompositeGlyph(glyph, &component_point_count)) {
return Error("Failed to parse glyph %d", i);
}
+
+ // Check maxComponentDepth and validate maxComponentPoints.
+ // ParseCompositeGlyph placed the first set of component glyphs on the
+ // component_point_count.gid_stack, which we start to process below. If a
+ // nested glyph is in turn a component glyph, additional glyphs are placed
+ // on the stack.
+ while (component_point_count.gid_stack.size()) {
+ GidAtLevel stack_top_gid = component_point_count.gid_stack.back();
+ component_point_count.gid_stack.pop_back();
+
+ Buffer points_count_glyph(GetGlyphBufferSection(
+ data,
+ length,
+ offsets,
+ stack_top_gid.gid));
+
+ if (!points_count_glyph.buffer())
+ return false;
+
+ if (!points_count_glyph.length())
+ continue;
+
+ if (!TraverseComponentsCountingPoints(points_count_glyph,
+ i,
+ stack_top_gid.level,
+ &component_point_count)) {
+ return Error("Error validating component points and depth.");
+ }
+
+ if (component_point_count.accumulated_component_points >
+ std::numeric_limits::max()) {
+ return Error("Illegal composite points value "
+ "exceeding 0xFFFF for base glyph %d.", i);
+ } else if (this->maxp->version_1 &&
+ component_point_count.accumulated_component_points >
+ this->maxp->max_c_points) {
+ Warning("Number of composite points in glyph %d exceeds "
+ "maxp maxCompositePoints: %d vs %d, adjusting limit.",
+ i,
+ component_point_count.accumulated_component_points,
+ this->maxp->max_c_points
+ );
+ this->maxp->max_c_points =
+ component_point_count.accumulated_component_points;
+ }
+ }
}
size_t new_size = glyph.offset();
@@ -344,6 +388,123 @@ bool OpenTypeGLYF::Parse(const uint8_t *data, size_t length) {
return true;
}
+bool OpenTypeGLYF::TraverseComponentsCountingPoints(
+ Buffer &glyph,
+ uint16_t base_glyph_id,
+ uint32_t level,
+ ComponentPointCount* component_point_count) {
+
+ int16_t num_contours;
+ if (!glyph.ReadS16(&num_contours) ||
+ !glyph.Skip(8)) {
+ return Error("Can't read glyph header.");
+ }
+
+ if (num_contours <= -2) {
+ return Error("Bad number of contours %d in glyph.", num_contours);
+ }
+
+ if (num_contours == 0)
+ return true;
+
+ // FontTools counts a component level for each traversed recursion. We start
+ // counting at level 0. If we reach a level that's deeper than
+ // maxComponentDepth, we expand maxComponentDepth unless it's larger than
+ // the maximum possible depth.
+ if (level > std::numeric_limits::max()) {
+ return Error("Illegal component depth exceeding 0xFFFF in base glyph id %d.",
+ base_glyph_id);
+ } else if (this->maxp->version_1 &&
+ level > this->maxp->max_c_depth) {
+ this->maxp->max_c_depth = level;
+ Warning("Component depth exceeds maxp maxComponentDepth "
+ "in glyph %d, adjust limit to %d.",
+ base_glyph_id, level);
+ }
+
+ if (num_contours > 0) {
+ uint16_t num_points = 0;
+ for (int i = 0; i < num_contours; ++i) {
+ // Simple glyph, add contour points.
+ uint16_t tmp_index = 0;
+ if (!glyph.ReadU16(&tmp_index)) {
+ return Error("Can't read contour index %d", i);
+ }
+ num_points = tmp_index + 1;
+ }
+
+ component_point_count->accumulated_component_points += num_points;
+ return true;
+ } else {
+ assert(num_contours == -1);
+
+ // Composite glyph, add gid's to stack.
+ uint16_t flags = 0;
+ uint16_t gid = 0;
+ do {
+ if (!glyph.ReadU16(&flags) || !glyph.ReadU16(&gid)) {
+ return Error("Can't read composite glyph flags or glyphIndex");
+ }
+
+ size_t skip_bytes = 0;
+ skip_bytes += flags & ARG_1_AND_2_ARE_WORDS ? 4 : 2;
+
+ if (flags & WE_HAVE_A_SCALE) {
+ skip_bytes += 2;
+ } else if (flags & WE_HAVE_AN_X_AND_Y_SCALE) {
+ skip_bytes += 4;
+ } else if (flags & WE_HAVE_A_TWO_BY_TWO) {
+ skip_bytes += 8;
+ }
+
+ if (!glyph.Skip(skip_bytes)) {
+ return Error("Failed to parse component glyph.");
+ }
+
+ if (gid >= this->maxp->num_glyphs) {
+ return Error("Invalid glyph id used in composite glyph: %d", gid);
+ }
+
+ component_point_count->gid_stack.push_back({gid, level + 1u});
+ } while (flags & MORE_COMPONENTS);
+ return true;
+ }
+}
+
+Buffer OpenTypeGLYF::GetGlyphBufferSection(
+ const uint8_t *data,
+ size_t length,
+ const std::vector& loca_offsets,
+ unsigned glyph_id) {
+
+ Buffer null_buffer(nullptr, 0);
+
+ const unsigned gly_offset = loca_offsets[glyph_id];
+ // The LOCA parser checks that these values are monotonic
+ const unsigned gly_length = loca_offsets[glyph_id + 1] - loca_offsets[glyph_id];
+ if (!gly_length) {
+ // this glyph has no outline (e.g. the space character)
+ return Buffer(data + gly_offset, 0);
+ }
+
+ if (gly_offset >= length) {
+ Error("Glyph %d offset %d too high %ld", glyph_id, gly_offset, length);
+ return null_buffer;
+ }
+ // Since these are unsigned types, the compiler is not allowed to assume
+ // that they never overflow.
+ if (gly_offset + gly_length < gly_offset) {
+ Error("Glyph %d length (%d < 0)!", glyph_id, gly_length);
+ return null_buffer;
+ }
+ if (gly_offset + gly_length > length) {
+ Error("Glyph %d length %d too high", glyph_id, gly_length);
+ return null_buffer;
+ }
+
+ return Buffer(data + gly_offset, gly_length);
+}
+
bool OpenTypeGLYF::Serialize(OTSStream *out) {
for (unsigned i = 0; i < this->iov.size(); ++i) {
if (!out->Write(this->iov[i].first, this->iov[i].second)) {
diff --git a/gfx/ots/src/glyf.h b/gfx/ots/src/glyf.h
index 1da94e4b94..08c585df34 100644
--- a/gfx/ots/src/glyf.h
+++ b/gfx/ots/src/glyf.h
@@ -23,12 +23,38 @@ class OpenTypeGLYF : public Table {
bool Serialize(OTSStream *out);
private:
+ struct GidAtLevel {
+ uint16_t gid;
+ uint32_t level;
+ };
+
+ struct ComponentPointCount {
+ ComponentPointCount() : accumulated_component_points(0) {};
+ uint32_t accumulated_component_points;
+ std::vector gid_stack;
+ };
+
bool ParseFlagsForSimpleGlyph(Buffer &glyph,
uint32_t num_flags,
uint32_t *flag_index,
uint32_t *coordinates_length);
bool ParseSimpleGlyph(Buffer &glyph, int16_t num_contours);
- bool ParseCompositeGlyph(Buffer &glyph);
+ bool ParseCompositeGlyph(
+ Buffer &glyph,
+ ComponentPointCount* component_point_count);
+
+
+ bool TraverseComponentsCountingPoints(
+ Buffer& glyph,
+ uint16_t base_glyph_id,
+ uint32_t level,
+ ComponentPointCount* component_point_count);
+
+ Buffer GetGlyphBufferSection(
+ const uint8_t *data,
+ size_t length,
+ const std::vector& loca_offsets,
+ unsigned glyph_id);
OpenTypeMAXP* maxp;