* If using NASM, 2.10 or later is required.
* If using NASM, 2.10 or later (except 2.11.08) is required for an x86-64 Mac
build (2.11.08 does not work properly with libjpeg-turbo's x86-64 SIMD code
- when building macho64 objects.) NASM or YASM can be obtained from
- [MacPorts](http://www.macports.org/) or [Homebrew](http://brew.sh/).
+ when building macho64 objects.)
* If using YASM, 1.2.0 or later is required.
+ * If building on macOS, NASM or YASM can be obtained from
+ [MacPorts](http://www.macports.org/) or [Homebrew](http://brew.sh/).
- NOTE: Currently, if it is desirable to hide the SIMD function symbols in
Mac executables or shared libraries that statically link with
- libjpeg-turbo, then YASM must be used when building libjpeg-turbo.
+ libjpeg-turbo, then NASM 2.14 or later or YASM must be used when
+ building libjpeg-turbo.
* If building on Windows, **nasm.exe**/**yasm.exe** should be in your `PATH`.
+ * NASM and YASM are located in the CRB (Code Ready Builder) repository on
+ Red Hat Enterprise Linux 8 and in the PowerTools repository on CentOS 8,
+ which is not enabled by default.
The binary RPMs released by the NASM project do not work on older Linux
systems, such as Red Hat Enterprise Linux 5. On such systems, you can easily
Building libjpeg-turbo for Android
----------------------------------
-Building libjpeg-turbo for Android platforms requires the
+Building libjpeg-turbo for Android platforms requires v13b or later of the
[Android NDK](https://developer.android.com/tools/sdk/ndk).
needs.
# Set these variables to suit your needs
- NDK_PATH={full path to the "ndk" directory-- for example, /opt/android/sdk/ndk-bundle}
- BUILD_PLATFORM={the platform name for the NDK package you installed--
- for example, "windows-x86" or "linux-x86_64" or "darwin-x86_64"}
- TOOLCHAIN_VERSION={"4.8", "4.9", "clang3.5", etc. This corresponds to a
- toolchain directory under ${NDK_PATH}/toolchains/.}
- ANDROID_VERSION={The minimum version of Android to support-- for example,
+ NDK_PATH={full path to the NDK directory-- for example,
+ /opt/android/android-ndk-r16b}
+ TOOLCHAIN={"gcc" or "clang"-- "gcc" must be used with NDK r16b and earlier,
+ and "clang" must be used with NDK r17c and later}
+ ANDROID_VERSION={the minimum version of Android to support-- for example,
"16", "19", etc.}
- # It should not be necessary to modify the rest
- HOST=arm-linux-androideabi
- SYSROOT=${NDK_PATH}/platforms/android-${ANDROID_VERSION}/arch-arm
- export CFLAGS="-march=armv7-a -mfloat-abi=softfp -fprefetch-loop-arrays \
- -D__ANDROID_API__=${ANDROID_VERSION} --sysroot=${SYSROOT} \
- -isystem ${NDK_PATH}/sysroot/usr/include \
- -isystem ${NDK_PATH}/sysroot/usr/include/${HOST}"
- export LDFLAGS=-pie
- TOOLCHAIN=${NDK_PATH}/toolchains/${HOST}-${TOOLCHAIN_VERSION}/prebuilt/${BUILD_PLATFORM}
-
cd {build_directory}
-
- cat <<EOF >toolchain.cmake
- set(CMAKE_SYSTEM_NAME Linux)
- set(CMAKE_SYSTEM_PROCESSOR arm)
- set(CMAKE_C_COMPILER ${TOOLCHAIN}/bin/${HOST}-gcc)
- set(CMAKE_FIND_ROOT_PATH ${TOOLCHAIN}/${HOST})
- EOF
-
- cmake -G"Unix Makefiles" -DCMAKE_TOOLCHAIN_FILE=toolchain.cmake \
- -DCMAKE_POSITION_INDEPENDENT_CODE=1 \
+ cmake -G"Unix Makefiles" \
+ -DANDROID_ABI=armeabi-v7a \
+ -DANDROID_ARM_MODE=arm \
+ -DANDROID_PLATFORM=android-${ANDROID_VERSION} \
+ -DANDROID_TOOLCHAIN=${TOOLCHAIN} \
+ -DCMAKE_ASM_FLAGS="--target=arm-linux-androideabi${ANDROID_VERSION}" \
+ -DCMAKE_TOOLCHAIN_FILE=${NDK_PATH}/build/cmake/android.toolchain.cmake \
[additional CMake flags] {source_directory}
make
needs.
# Set these variables to suit your needs
- NDK_PATH={full path to the "ndk" directory-- for example, /opt/android/sdk/ndk-bundle}
- BUILD_PLATFORM={the platform name for the NDK package you installed--
- for example, "windows-x86" or "linux-x86_64" or "darwin-x86_64"}
- TOOLCHAIN_VERSION={"4.8", "4.9", "clang3.5", etc. This corresponds to a
- toolchain directory under ${NDK_PATH}/toolchains/.}
- ANDROID_VERSION={The minimum version of Android to support. "21" or later
+ NDK_PATH={full path to the NDK directory-- for example,
+ /opt/android/android-ndk-r16b}
+ TOOLCHAIN={"gcc" or "clang"-- "gcc" must be used with NDK r14b and earlier,
+ and "clang" must be used with NDK r17c and later}
+ ANDROID_VERSION={the minimum version of Android to support. "21" or later
is required for a 64-bit build.}
- # It should not be necessary to modify the rest
- HOST=aarch64-linux-android
- SYSROOT=${NDK_PATH}/platforms/android-${ANDROID_VERSION}/arch-arm64
- export CFLAGS="-D__ANDROID_API__=${ANDROID_VERSION} --sysroot=${SYSROOT} \
- -isystem ${NDK_PATH}/sysroot/usr/include \
- -isystem ${NDK_PATH}/sysroot/usr/include/${HOST}"
- export LDFLAGS=-pie
- TOOLCHAIN=${NDK_PATH}/toolchains/${HOST}-${TOOLCHAIN_VERSION}/prebuilt/${BUILD_PLATFORM}
-
cd {build_directory}
-
- cat <<EOF >toolchain.cmake
- set(CMAKE_SYSTEM_NAME Linux)
- set(CMAKE_SYSTEM_PROCESSOR aarch64)
- set(CMAKE_C_COMPILER ${TOOLCHAIN}/bin/${HOST}-gcc)
- set(CMAKE_FIND_ROOT_PATH ${TOOLCHAIN}/${HOST})
- EOF
-
- cmake -G"Unix Makefiles" -DCMAKE_TOOLCHAIN_FILE=toolchain.cmake \
- -DCMAKE_POSITION_INDEPENDENT_CODE=1 \
+ cmake -G"Unix Makefiles" \
+ -DANDROID_ABI=arm64-v8a \
+ -DANDROID_ARM_MODE=arm \
+ -DANDROID_PLATFORM=android-${ANDROID_VERSION} \
+ -DANDROID_TOOLCHAIN=${TOOLCHAIN} \
+ -DCMAKE_ASM_FLAGS="--target=aarch64-linux-android${ANDROID_VERSION}" \
+ -DCMAKE_TOOLCHAIN_FILE=${NDK_PATH}/build/cmake/android.toolchain.cmake \
[additional CMake flags] {source_directory}
make
needs.
# Set these variables to suit your needs
- NDK_PATH={full path to the "ndk" directory-- for example, /opt/android/sdk/ndk-bundle}
- BUILD_PLATFORM={the platform name for the NDK package you installed--
- for example, "windows-x86" or "linux-x86_64" or "darwin-x86_64"}
- TOOLCHAIN_VERSION={"4.8", "4.9", "clang3.5", etc. This corresponds to a
- toolchain directory under ${NDK_PATH}/toolchains/.}
+ NDK_PATH={full path to the NDK directory-- for example,
+ /opt/android/android-ndk-r16b}
+ TOOLCHAIN={"gcc" or "clang"-- "gcc" must be used with NDK r14b and earlier,
+ and "clang" must be used with NDK r17c and later}
ANDROID_VERSION={The minimum version of Android to support-- for example,
"16", "19", etc.}
- # It should not be necessary to modify the rest
- HOST=i686-linux-android
- SYSROOT=${NDK_PATH}/platforms/android-${ANDROID_VERSION}/arch-x86
- export CFLAGS="-D__ANDROID_API__=${ANDROID_VERSION} --sysroot=${SYSROOT} \
- -isystem ${NDK_PATH}/sysroot/usr/include \
- -isystem ${NDK_PATH}/sysroot/usr/include/${HOST}"
- export LDFLAGS=-pie
- TOOLCHAIN=${NDK_PATH}/toolchains/x86-${TOOLCHAIN_VERSION}/prebuilt/${BUILD_PLATFORM}
-
cd {build_directory}
-
- cat <<EOF >toolchain.cmake
- set(CMAKE_SYSTEM_NAME Linux)
- set(CMAKE_SYSTEM_PROCESSOR i386)
- set(CMAKE_C_COMPILER ${TOOLCHAIN}/bin/${HOST}-gcc)
- set(CMAKE_FIND_ROOT_PATH ${TOOLCHAIN}/${HOST})
- EOF
-
- cmake -G"Unix Makefiles" -DCMAKE_TOOLCHAIN_FILE=toolchain.cmake \
- -DCMAKE_POSITION_INDEPENDENT_CODE=1 \
+ cmake -G"Unix Makefiles" \
+ -DANDROID_ABI=x86 \
+ -DANDROID_PLATFORM=android-${ANDROID_VERSION} \
+ -DANDROID_TOOLCHAIN=${TOOLCHAIN} \
+ -DCMAKE_TOOLCHAIN_FILE=${NDK_PATH}/build/cmake/android.toolchain.cmake \
[additional CMake flags] {source_directory}
make
needs.
# Set these variables to suit your needs
- NDK_PATH={full path to the "ndk" directory-- for example, /opt/android/sdk/ndk-bundle}
- BUILD_PLATFORM={the platform name for the NDK package you installed--
- for example, "windows-x86" or "linux-x86_64" or "darwin-x86_64"}
- TOOLCHAIN_VERSION={"4.8", "4.9", "clang3.5", etc. This corresponds to a
- toolchain directory under ${NDK_PATH}/toolchains/.}
- ANDROID_VERSION={The minimum version of Android to support. "21" or later
+ NDK_PATH={full path to the NDK directory-- for example,
+ /opt/android/android-ndk-r16b}
+ TOOLCHAIN={"gcc" or "clang"-- "gcc" must be used with NDK r14b and earlier,
+ and "clang" must be used with NDK r17c and later}
+ ANDROID_VERSION={the minimum version of Android to support. "21" or later
is required for a 64-bit build.}
- # It should not be necessary to modify the rest
- HOST=x86_64-linux-android
- SYSROOT=${NDK_PATH}/platforms/android-${ANDROID_VERSION}/arch-x86_64
- export CFLAGS="-D__ANDROID_API__=${ANDROID_VERSION} --sysroot=${SYSROOT} \
- -isystem ${NDK_PATH}/sysroot/usr/include \
- -isystem ${NDK_PATH}/sysroot/usr/include/${HOST}"
- export LDFLAGS=-pie
- TOOLCHAIN=${NDK_PATH}/toolchains/x86_64-${TOOLCHAIN_VERSION}/prebuilt/${BUILD_PLATFORM}
-
cd {build_directory}
-
- cat <<EOF >toolchain.cmake
- set(CMAKE_SYSTEM_NAME Linux)
- set(CMAKE_SYSTEM_PROCESSOR x86_64)
- set(CMAKE_C_COMPILER ${TOOLCHAIN}/bin/${HOST}-gcc)
- set(CMAKE_FIND_ROOT_PATH ${TOOLCHAIN}/${HOST})
- EOF
-
- cmake -G"Unix Makefiles" -DCMAKE_TOOLCHAIN_FILE=toolchain.cmake \
- -DCMAKE_POSITION_INDEPENDENT_CODE=1 \
+ cmake -G"Unix Makefiles" \
+ -DANDROID_ABI=x86_64 \
+ -DANDROID_PLATFORM=android-${ANDROID_VERSION} \
+ -DANDROID_TOOLCHAIN=${TOOLCHAIN} \
+ -DCMAKE_TOOLCHAIN_FILE=${NDK_PATH}/build/cmake/android.toolchain.cmake \
[additional CMake flags] {source_directory}
make
-If building for Android 4.0.x (API level < 16) or earlier, remove
-`-DCMAKE_POSITION_INDEPENDENT_CODE=1` from the CMake arguments and `-pie` from
-`LDFLAGS`.
-
-If building on Windows, add `.exe` to the end of `CMAKE_C_COMPILER`.
-
-
Advanced CMake Options
----------------------
+++ /dev/null
-brew 'yasm'
-brew 'gcc@5'
-brew 'md5sha1sum'
-cask 'Caskroom/versions/java6'
endif()
project(libjpeg-turbo C)
-set(VERSION 2.0.1)
+set(VERSION 2.0.4)
string(REPLACE "." ";" VERSION_TRIPLET ${VERSION})
list(GET VERSION_TRIPLET 0 VERSION_MAJOR)
list(GET VERSION_TRIPLET 1 VERSION_MINOR)
include(cmakescripts/GNUInstallDirs.cmake)
-if(ENABLE_SHARED)
- set(CMAKE_INSTALL_RPATH ${CMAKE_INSTALL_FULL_LIBDIR})
-endif()
-
macro(report_directory var)
if(CMAKE_INSTALL_${var} STREQUAL CMAKE_INSTALL_FULL_${var})
message(STATUS "CMAKE_INSTALL_${var} = ${CMAKE_INSTALL_${var}}")
report_option(ENABLE_SHARED "Shared libraries")
report_option(ENABLE_STATIC "Static libraries")
+if(ENABLE_SHARED)
+ set(CMAKE_INSTALL_RPATH ${CMAKE_INSTALL_FULL_LIBDIR})
+endif()
+
if(WITH_12BIT)
set(WITH_ARITH_DEC 0)
set(WITH_ARITH_ENC 0)
# still work.
file(WRITE ${CMAKE_CURRENT_BINARY_DIR}/conftest.map
"VERS_1 { global: foo; local: *; }; VERS_2 { global: foo2; } VERS_1;")
- set(CMAKE_REQUIRED_FLAGS "-Wl,-M,${CMAKE_CURRENT_BINARY_DIR}/conftest.map")
- check_c_source_compiles("void foo() {} void foo2() {} int main(void) { return 0; }"
+ set(CMAKE_REQUIRED_FLAGS "-Wl,-M,${CMAKE_CURRENT_BINARY_DIR}/conftest.map -shared")
+ check_c_source_compiles("int foo() { return 0; } int foo2() { return 2; }"
HAVE_MAPFILE)
set(CMAKE_REQUIRED_FLAGS)
file(REMOVE ${CMAKE_CURRENT_BINARY_DIR}/conftest.map)
endif()
if(WITH_SIMD)
message(STATUS "SIMD extensions: ${CPU_TYPE} (WITH_SIMD = ${WITH_SIMD})")
- if(MSVC_IDE)
+ if(MSVC_IDE OR XCODE)
set_source_files_properties(${SIMD_OBJS} PROPERTIES GENERATED 1)
endif()
else()
add_subdirectory(md5)
-if(MSVC_IDE)
+if(MSVC_IDE OR XCODE)
set(OBJDIR "\${CTEST_CONFIGURATION_TYPE}/")
else()
set(OBJDIR "")
set(MD5_JPEG_422_IFAST_OPT 7322e3bd2f127f7de4b40d4480ce60e4)
set(MD5_PPM_422_IFAST 79807fa552899e66a04708f533e16950)
set(MD5_PPM_422M_IFAST 07737bfe8a7c1c87aaa393a0098d16b0)
- set(MD5_JPEG_420_IFAST_Q100_PROG a1da220b5604081863a504297ed59e55)
+ set(MD5_JPEG_420_IFAST_Q100_PROG 008ab68d6ddbba04a8f01deee4e0f9f8)
set(MD5_PPM_420_Q100_IFAST 1b3730122709f53d007255e8dfd3305e)
set(MD5_PPM_420M_Q100_IFAST 980a1a3c5bf9510022869d30b7d26566)
set(MD5_JPEG_GRAY_ISLOW 235c90707b16e2e069f37c888b2636d9)
set(MD5_PPM_422M_IFAST 8dbc65323d62cca7c91ba02dd1cfa81d)
set(MD5_BMP_422M_IFAST_565 3294bd4d9a1f2b3d08ea6020d0db7065)
set(MD5_BMP_422M_IFAST_565D da98c9c7b6039511be4a79a878a9abc1)
- set(MD5_JPEG_420_IFAST_Q100_PROG 990cbe0329c882420a2094da7e5adade)
+ set(MD5_JPEG_420_IFAST_Q100_PROG e59bb462016a8d9a748c330a3474bb55)
set(MD5_PPM_420_Q100_IFAST 5a732542015c278ff43635e473a8a294)
set(MD5_PPM_420M_Q100_IFAST ff692ee9323a3b424894862557c092f1)
set(MD5_JPEG_GRAY_ISLOW 72b51f894b8f4a10b3ee3066770aa38d)
add_test(djpeg-${libtype}-rgb-islow-icc-cmp
${MD5CMP} b06a39d730129122e85c1363ed1bbc9e testout_rgb_islow.icc)
+ set_tests_properties(djpeg-${libtype}-rgb-islow-icc-cmp PROPERTIES
+ DEPENDS djpeg-${libtype}-rgb-islow)
add_bittest(jpegtran icc "-copy;all;-icc;${TESTIMAGES}/test2.icc"
testout_rgb_islow2.jpg testout_rgb_islow.jpg ${MD5_JPEG_RGB_ISLOW2})
# CC: RGB->YCC SAMP: fullsize/h2v2 FDCT: ifast ENT: prog huff
add_bittest(cjpeg 420-q100-ifast-prog
- "-sample;2x2;-quality;100;-dct;fast;-prog"
+ "-sample;2x2;-quality;100;-dct;fast;-scans;${TESTIMAGES}/test.scan"
testout_420_q100_ifast_prog.jpg ${TESTIMAGES}/testorig.ppm
${MD5_JPEG_420_IFAST_Q100_PROG})
COMMAND ${BASH} ${CMAKE_CURRENT_BINARY_DIR}/tjbenchtest -yuv -alloc
COMMAND echo tjbenchtest -progressive
COMMAND ${BASH} ${CMAKE_CURRENT_BINARY_DIR}/tjbenchtest -progressive
+ COMMAND echo tjbenchtest -progressive -yuv
+ COMMAND ${BASH} ${CMAKE_CURRENT_BINARY_DIR}/tjbenchtest -progressive -yuv
COMMAND echo tjexampletest
COMMAND ${BASH} ${CMAKE_CURRENT_BINARY_DIR}/tjexampletest
COMMAND echo tjbenchtest.java
COMMAND ${BASH} ${CMAKE_CURRENT_BINARY_DIR}/tjbenchtest.java -yuv
COMMAND echo tjbenchtest.java -progressive
COMMAND ${BASH} ${CMAKE_CURRENT_BINARY_DIR}/tjbenchtest.java -progressive
+ COMMAND echo tjexampletest.java -progressive -yuv
+ COMMAND ${BASH} ${CMAKE_CURRENT_BINARY_DIR}/tjbenchtest.java
+ -progressive -yuv
COMMAND echo tjexampletest.java
COMMAND ${BASH} ${CMAKE_CURRENT_BINARY_DIR}/tjexampletest.java
DEPENDS ${CMAKE_CURRENT_BINARY_DIR}/tjbenchtest
COMMAND ${BASH} ${CMAKE_CURRENT_BINARY_DIR}/tjbenchtest -yuv
COMMAND echo tjbenchtest -yuv -alloc
COMMAND ${BASH} ${CMAKE_CURRENT_BINARY_DIR}/tjbenchtest -yuv -alloc
+ COMMAND echo tjbenchtest -progressive
+ COMMAND ${BASH} ${CMAKE_CURRENT_BINARY_DIR}/tjbenchtest -progressive
+ COMMAND echo tjbenchtest -progressive -yuv
+ COMMAND ${BASH} ${CMAKE_CURRENT_BINARY_DIR}/tjbenchtest -progressive -yuv
COMMAND echo tjexampletest
COMMAND ${BASH} ${CMAKE_CURRENT_BINARY_DIR}/tjexampletest
DEPENDS ${CMAKE_CURRENT_BINARY_DIR}/tjbenchtest)
ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
+ if(NOT CMAKE_VERSION VERSION_LESS "3.1" AND MSVC AND
+ CMAKE_C_LINKER_SUPPORTS_PDB)
+ install(FILES "$<TARGET_PDB_FILE:turbojpeg>"
+ DESTINATION ${CMAKE_INSTALL_BINDIR} OPTIONAL)
+ endif()
endif()
if(ENABLE_STATIC)
install(TARGETS turbojpeg-static ARCHIVE
DESTINATION ${CMAKE_INSTALL_LIBDIR})
if(NOT ENABLE_SHARED)
- install(PROGRAMS ${CMAKE_CURRENT_BINARY_DIR}/tjbench-static${EXE}
+ if(MSVC_IDE OR XCODE)
+ set(DIR "${CMAKE_CURRENT_BINARY_DIR}/\${CMAKE_INSTALL_CONFIG_NAME}")
+ else()
+ set(DIR ${CMAKE_CURRENT_BINARY_DIR})
+ endif()
+ install(PROGRAMS ${DIR}/tjbench-static${EXE}
DESTINATION ${CMAKE_INSTALL_BINDIR} RENAME tjbench${EXE})
endif()
endif()
if(ENABLE_STATIC)
install(TARGETS jpeg-static ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR})
if(NOT ENABLE_SHARED)
- install(PROGRAMS ${CMAKE_CURRENT_BINARY_DIR}/cjpeg-static${EXE}
+ if(MSVC_IDE OR XCODE)
+ set(DIR "${CMAKE_CURRENT_BINARY_DIR}/\${CMAKE_INSTALL_CONFIG_NAME}")
+ else()
+ set(DIR ${CMAKE_CURRENT_BINARY_DIR})
+ endif()
+ install(PROGRAMS ${DIR}/cjpeg-static${EXE}
DESTINATION ${CMAKE_INSTALL_BINDIR} RENAME cjpeg${EXE})
- install(PROGRAMS ${CMAKE_CURRENT_BINARY_DIR}/djpeg-static${EXE}
+ install(PROGRAMS ${DIR}/djpeg-static${EXE}
DESTINATION ${CMAKE_INSTALL_BINDIR} RENAME djpeg${EXE})
- install(PROGRAMS ${CMAKE_CURRENT_BINARY_DIR}/jpegtran-static${EXE}
+ install(PROGRAMS ${DIR}/jpegtran-static${EXE}
DESTINATION ${CMAKE_INSTALL_BINDIR} RENAME jpegtran${EXE})
endif()
endif()
+2.0.4
+=====
+
+### Significant changes relative to 2.0.3:
+
+1. Fixed a regression in the Windows packaging system (introduced by
+2.0 beta1[2]) whereby, if both the 64-bit libjpeg-turbo SDK for GCC and the
+64-bit libjpeg-turbo SDK for Visual C++ were installed on the same system, only
+one of them could be uninstalled.
+
+2. Fixed a signed integer overflow and subsequent segfault that occurred when
+attempting to decompress images with more than 715827882 pixels using the
+64-bit C version of TJBench.
+
+3. Fixed out-of-bounds write in `tjDecompressToYUV2()` and
+`tjDecompressToYUVPlanes()` (sometimes manifesting as a double free) that
+occurred when attempting to decompress grayscale JPEG images that were
+compressed with a sampling factor other than 1 (for instance, with
+`cjpeg -grayscale -sample 2x2`).
+
+4. Fixed a regression introduced by 2.0.2[5] that caused the TurboJPEG API to
+incorrectly identify some JPEG images with unusual sampling factors as 4:4:4
+JPEG images. This was known to cause a buffer overflow when attempting to
+decompress some such images using `tjDecompressToYUV2()` or
+`tjDecompressToYUVPlanes()`.
+
+5. Fixed an issue, detected by ASan, whereby attempting to losslessly transform
+a specially-crafted malformed JPEG image containing an extremely-high-frequency
+coefficient block (junk image data that could never be generated by a
+legitimate JPEG compressor) could cause the Huffman encoder's local buffer to
+be overrun. (Refer to 1.4.0[9] and 1.4beta1[15].) Given that the buffer
+overrun was fully contained within the stack and did not cause a segfault or
+other user-visible errant behavior, and given that the lossless transformer
+(unlike the decompressor) is not generally exposed to arbitrary data exploits,
+this issue did not likely pose a security risk.
+
+6. The ARM 64-bit (ARMv8) NEON SIMD assembly code now stores constants in a
+separate read-only data section rather than in the text section, to support
+execute-only memory layouts.
+
+
+2.0.3
+=====
+
+### Significant changes relative to 2.0.2:
+
+1. Fixed "using JNI after critical get" errors that occurred on Android
+platforms when passing invalid arguments to certain methods in the TurboJPEG
+Java API.
+
+2. Fixed a regression in the SIMD feature detection code, introduced by
+the AVX2 SIMD extensions (2.0 beta1[1]), that was known to cause an illegal
+instruction exception, in rare cases, on CPUs that lack support for CPUID leaf
+07H (or on which the maximum CPUID leaf has been limited by way of a BIOS
+setting.)
+
+3. The 4:4:0 (h1v2) fancy (smooth) chroma upsampling algorithm in the
+decompressor now uses a similar bias pattern to that of the 4:2:2 (h2v1) fancy
+chroma upsampling algorithm, rounding up or down the upsampled result for
+alternate pixels rather than always rounding down. This ensures that,
+regardless of whether a 4:2:2 JPEG image is rotated or transposed prior to
+decompression (in the frequency domain) or after decompression (in the spatial
+domain), the final image will be similar.
+
+4. Fixed an integer overflow and subsequent segfault that occurred when
+attempting to compress or decompress images with more than 1 billion pixels
+using the TurboJPEG API.
+
+5. Fixed a regression introduced by 2.0 beta1[15] whereby attempting to
+generate a progressive JPEG image on an SSE2-capable CPU using a scan script
+containing one or more scans with lengths divisible by 16 would result in an
+error ("Missing Huffman code table entry") and an invalid JPEG image.
+
+6. Fixed an issue whereby `tjDecodeYUV()` and `tjDecodeYUVPlanes()` would throw
+an error ("Invalid progressive parameters") or a warning ("Inconsistent
+progression sequence") if passed a TurboJPEG instance that was previously used
+to decompress a progressive JPEG image.
+
+
+2.0.2
+=====
+
+### Significant changes relative to 2.0.1:
+
+1. Fixed a regression introduced by 2.0.1[5] that prevented a runtime search
+path (rpath) from being embedded in the libjpeg-turbo shared libraries and
+executables for macOS and iOS. This caused a fatal error of the form
+"dyld: Library not loaded" when attempting to use one of the executables,
+unless `DYLD_LIBRARY_PATH` was explicitly set to the location of the
+libjpeg-turbo shared libraries.
+
+2. Fixed an integer overflow and subsequent segfault (CVE-2018-20330) that
+occurred when attempting to load a BMP file with more than 1 billion pixels
+using the `tjLoadImage()` function.
+
+3. Fixed a buffer overrun (CVE-2018-19664) that occurred when attempting to
+decompress a specially-crafted malformed JPEG image to a 256-color BMP using
+djpeg.
+
+4. Fixed a floating point exception that occurred when attempting to
+decompress a specially-crafted malformed JPEG image with a specified image
+width or height of 0 using the C version of TJBench.
+
+5. The TurboJPEG API will now decompress 4:4:4 JPEG images with 2x1, 1x2, 3x1,
+or 1x3 luminance and chrominance sampling factors. This is a non-standard way
+of specifying 1x subsampling (normally 4:4:4 JPEGs have 1x1 luminance and
+chrominance sampling factors), but the JPEG format and the libjpeg API both
+allow it.
+
+6. Fixed a regression introduced by 2.0 beta1[7] that caused djpeg to generate
+incorrect PPM images when used with the `-colors` option.
+
+7. Fixed an issue whereby a static build of libjpeg-turbo (a build in which
+`ENABLE_SHARED` is `0`) could not be installed using the Visual Studio IDE.
+
+8. Fixed a severe performance issue in the Loongson MMI SIMD extensions that
+occurred when compressing RGB images whose image rows were not 64-bit-aligned.
+
+
2.0.1
=====
PPM readers/writers threw an error that was specific to the readers/writers
(as opposed to a general libjpeg API error.)
-4. Fixed an issue whereby a specially-crafted malformed BMP file, one in which
-the header specified an image width of 1073741824 pixels, would trigger a
-floating point exception (division by zero) in the `tjLoadImage()` function
-when attempting to load the BMP file into a 4-component image buffer.
+4. Fixed an issue (CVE-2018-1152) whereby a specially-crafted malformed BMP
+file, one in which the header specified an image width of 1073741824 pixels,
+would trigger a floating point exception (division by zero) in the
+`tjLoadImage()` function when attempting to load the BMP file into a
+4-component image buffer.
5. Fixed an issue whereby certain combinations of calls to
`jpeg_skip_scanlines()` and `jpeg_read_scanlines()` could trigger an infinite
7. The new CMake-based build system will now disable the MIPS DSPr2 SIMD
extensions if it detects that the compiler does not support DSPr2 instructions.
-8. Fixed out-of-bounds read in cjpeg that occurred when attempting to compress
-a specially-crafted malformed color-index (8-bit-per-sample) BMP file in which
-some of the samples (color indices) exceeded the bounds of the BMP file's color
-table.
+8. Fixed out-of-bounds read in cjpeg (CVE-2018-14498) that occurred when
+attempting to compress a specially-crafted malformed color-index
+(8-bit-per-sample) BMP file in which some of the samples (color indices)
+exceeded the bounds of the BMP file's color table.
9. Fixed a signed integer overflow in the progressive Huffman decoder, detected
by the Clang and GCC undefined behavior sanitizers, that could be triggered by
output format other than PPM/PGM, GIF, or Targa is selected along with the
`-crop` option.
-4. Fixed an issue whereby `jpeg_skip_scanlines()` would segfault if color
-quantization was enabled.
+4. Fixed an issue (CVE-2017-15232) whereby `jpeg_skip_scanlines()` would
+segfault if color quantization was enabled.
5. TJBench (both C and Java versions) will now display usage information if any
command-line argument is unrecognized. This prevents the program from silently
reasons (probably related to clang), this code cannot currently be compiled for
iOS.
-15. Fixed an extremely rare bug that could cause the Huffman encoder's local
-buffer to overrun when a very high-frequency MCU is compressed using quality
-100 and no subsampling, and when the JPEG output buffer is being dynamically
-resized by the destination manager. This issue was so rare that, even with a
-test program specifically designed to make the bug occur (by injecting random
-high-frequency YUV data into the compressor), it was reproducible only once in
-about every 25 million iterations.
+15. Fixed an extremely rare bug (CVE-2014-9092) that could cause the Huffman
+encoder's local buffer to overrun when a very high-frequency MCU is compressed
+using quality 100 and no subsampling, and when the JPEG output buffer is being
+dynamically resized by the destination manager. This issue was so rare that,
+even with a test program specifically designed to make the bug occur (by
+injecting random high-frequency YUV data into the compressor), it was
+reproducible only once in about every 25 million iterations.
16. Fixed an oversight in the TurboJPEG C wrapper: if any of the JPEG
compression functions was called repeatedly with the same
jpegtran, for instance) would result in an error, `Requested feature was
omitted at compile time`.
-4. Fixed a couple of issues whereby malformed JPEG images would cause
-libjpeg-turbo to use uninitialized memory during decompression.
+4. Fixed a couple of issues (CVE-2013-6629 and CVE-2013-6630) whereby malformed
+JPEG images would cause libjpeg-turbo to use uninitialized memory during
+decompression.
5. Fixed an error (`Buffer passed to JPEG library is too small`) that occurred
when calling the TurboJPEG YUV encoding function with a very small (< 5x5)
upper 64 bits of xmm6 and xmm7 on Win64 platforms, which violated the Win64
calling conventions.
-4. Fixed a regression caused by 1.2.0[6] whereby decompressing corrupt JPEG
-images (specifically, images in which the component count was erroneously set
-to a large value) would cause libjpeg-turbo to segfault.
+4. Fixed a regression (CVE-2012-2806) caused by 1.2.0[6] whereby decompressing
+corrupt JPEG images (specifically, images in which the component count was
+erroneously set to a large value) would cause libjpeg-turbo to segfault.
5. Worked around a severe performance issue with "Bobcat" (AMD Embedded APU)
processors. The `MASKMOVDQU` instruction, which was used by the libjpeg-turbo
This license covers the TurboJPEG API library and associated programs, as
well as the build system.
-- The zlib License, which is listed below
+- The [zlib License](https://opensource.org/licenses/Zlib)
This license is a subset of the other two, and it covers the libjpeg-turbo
SIMD extensions.
2. If your binary distribution includes or uses the TurboJPEG API, then
your product documentation must include the text of the Modified BSD
- License.
+ License (see below.)
**Origin**
- Clause 2 of the Modified BSD License
The Modified (3-clause) BSD License
===================================
-Copyright (C)\<YEAR\> \<AUTHOR\>. All Rights Reserved.
+Copyright (C)2009-2019 D. R. Commander. All Rights Reserved.
+Copyright (C)2015 Viktor Szathmáry. All Rights Reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
POSSIBILITY OF SUCH DAMAGE.
-The zlib License
-================
-
-Copyright (C) \<YEAR\>, \<AUTHOR\>.
-
-This software is provided 'as-is', without any express or implied
-warranty. In no event will the authors be held liable for any damages
-arising from the use of this software.
-
-Permission is granted to anyone to use this software for any purpose,
-including commercial applications, and to alter it and redistribute it
-freely, subject to the following restrictions:
-
-1. The origin of this software must not be misrepresented; you must not
- claim that you wrote the original software. If you use this software
- in a product, an acknowledgment in the product documentation would be
- appreciated but is not required.
-2. Altered source versions must be plainly marked as such, and must not be
- misrepresented as being the original software.
-3. This notice may not be removed or altered from any source distribution.
-
-
Why Three Licenses?
===================
Background
==========
-libjpeg-turbo is a JPEG image codec that uses SIMD instructions (MMX, SSE2,
-AVX2, NEON, AltiVec) to accelerate baseline JPEG compression and decompression
-on x86, x86-64, ARM, and PowerPC systems, as well as progressive JPEG
-compression on x86 and x86-64 systems. On such systems, libjpeg-turbo is
-generally 2-6x as fast as libjpeg, all else being equal. On other types of
-systems, libjpeg-turbo can still outperform libjpeg by a significant amount, by
-virtue of its highly-optimized Huffman coding routines. In many cases, the
-performance of libjpeg-turbo rivals that of proprietary high-speed JPEG codecs.
+libjpeg-turbo is a JPEG image codec that uses SIMD instructions to accelerate
+baseline JPEG compression and decompression on x86, x86-64, ARM, PowerPC, and
+MIPS systems, as well as progressive JPEG compression on x86 and x86-64
+systems. On such systems, libjpeg-turbo is generally 2-6x as fast as libjpeg,
+all else being equal. On other types of systems, libjpeg-turbo can still
+outperform libjpeg by a significant amount, by virtue of its highly-optimized
+Huffman coding routines. In many cases, the performance of libjpeg-turbo
+rivals that of proprietary high-speed JPEG codecs.
libjpeg-turbo implements both the traditional libjpeg API as well as the less
powerful but more straightforward TurboJPEG API. libjpeg-turbo also features
libjpeg v7+ features, nor to produce identical output to libjpeg v7+ in all
cases (see below.)
-By passing an argument of `--with-jpeg7` or `--with-jpeg8` to `configure`, or
-an argument of `-DWITH_JPEG7=1` or `-DWITH_JPEG8=1` to `cmake`, you can build a
-version of libjpeg-turbo that emulates the libjpeg v7 or v8 ABI, so that
-programs that are built against libjpeg v7 or v8 can be run with libjpeg-turbo.
-The following section describes which libjpeg v7+ features are supported and
-which aren't.
+By passing an argument of `-DWITH_JPEG7=1` or `-DWITH_JPEG8=1` to `cmake`, you
+can build a version of libjpeg-turbo that emulates the libjpeg v7 or v8 ABI, so
+that programs that are built against libjpeg v7 or v8 can be run with
+libjpeg-turbo. The following section describes which libjpeg v7+ features are
+supported and which aren't.
### Support for libjpeg v7 and v8 Features
#### Fully supported
-- **libjpeg: IDCT scaling extensions in decompressor**<br>
+- **libjpeg API: IDCT scaling extensions in decompressor**<br>
libjpeg-turbo supports IDCT scaling with scaling factors of 1/8, 1/4, 3/8,
1/2, 5/8, 3/4, 7/8, 9/8, 5/4, 11/8, 3/2, 13/8, 7/4, 15/8, and 2/1 (only 1/4
and 1/2 are SIMD-accelerated.)
-- **libjpeg: Arithmetic coding**
+- **libjpeg API: Arithmetic coding**
-- **libjpeg: In-memory source and destination managers**<br>
+- **libjpeg API: In-memory source and destination managers**<br>
See notes below.
- **cjpeg: Separate quality settings for luminance and chrominance**<br>
but it is the general belief of our project that these features have not
demonstrated sufficient usefulness to justify inclusion in libjpeg-turbo.
-- **libjpeg: DCT scaling in compressor**<br>
+- **libjpeg API: DCT scaling in compressor**<br>
`cinfo.scale_num` and `cinfo.scale_denom` are silently ignored.
There is no technical reason why DCT scaling could not be supported when
emulating the libjpeg v7+ API/ABI, but without the SmartScale extension (see
below), only scaling factors of 1/2, 8/15, 4/7, 8/13, 2/3, 8/11, 4/5, and
8/9 would be available, which is of limited usefulness.
-- **libjpeg: SmartScale**<br>
+- **libjpeg API: SmartScale**<br>
`cinfo.block_size` is silently ignored.
SmartScale is an extension to the JPEG format that allows for DCT block
sizes other than 8x8. Providing support for this new format would be
interest in providing this feature would be as a means of supporting
additional DCT scaling factors.
-- **libjpeg: Fancy downsampling in compressor**<br>
+- **libjpeg API: Fancy downsampling in compressor**<br>
`cinfo.do_fancy_downsampling` is silently ignored.
This requires the DCT scaling feature, which is not supported.
libjpeg-turbo binaries.
Those who are concerned about maintaining strict conformance with the libjpeg
-v6b or v7 API can pass an argument of `--without-mem-srcdst` to `configure` or
-an argument of `-DWITH_MEM_SRCDST=0` to `cmake` prior to building
-libjpeg-turbo. This will restore the pre-1.3 behavior, in which
+v6b or v7 API can pass an argument of `-DWITH_MEM_SRCDST=0` to `cmake` prior to
+building libjpeg-turbo. This will restore the pre-1.3 behavior, in which
`jpeg_mem_src()` and `jpeg_mem_dest()` are only included when emulating the
libjpeg v8 API/ABI.
On Un*x systems, including the in-memory source/destination managers changes
-the dynamic library version from 62.1.0 to 62.2.0 if using libjpeg v6b API/ABI
-emulation and from 7.1.0 to 7.2.0 if using libjpeg v7 API/ABI emulation.
+the dynamic library version from 62.2.0 to 62.3.0 if using libjpeg v6b API/ABI
+emulation and from 7.2.0 to 7.3.0 if using libjpeg v7 API/ABI emulation.
Note that, on most Un*x systems, the dynamic linker will not look for a
function in a library until that function is actually used. Thus, if a program
necessary to use the slow Huffman decoder when decompressing a JPEG image that
has restart markers. This can cause the decompression performance to drop by
as much as 20%, but the performance will still be much greater than that of
-libjpeg. Many consumer packages, such as PhotoShop, use restart markers when
+libjpeg. Many consumer packages, such as Photoshop, use restart markers when
generating JPEG images, so images generated by those programs will experience
this issue.
function in those cases. This causes performance to drop by as much as 40%.
It is therefore strongly advised that you use the slow integer forward DCT
whenever encoding images with a JPEG quality of 98 or higher.
+
+
+Memory Debugger Pitfalls
+========================
+
+Valgrind and Memory Sanitizer (MSan) can generate false positives
+(specifically, incorrect reports of uninitialized memory accesses) when used
+with libjpeg-turbo's SIMD extensions. It is generally recommended that the
+SIMD extensions be disabled, either by passing an argument of `-DWITH_SIMD=0`
+to `cmake` when configuring the build or by setting the environment variable
+`JSIMD_FORCENONE` to `1` at run time, when testing libjpeg-turbo with Valgrind,
+MSan, or other memory debuggers.
if(BITS EQUAL 64)
set(INST_PLATFORM "${INST_PLATFORM} 64-bit")
set(INST_NAME ${INST_NAME}64)
- set(INST_REG_NAME ${INST_DIR}64)
+ set(INST_REG_NAME ${INST_REG_NAME}64)
set(INST_DEFS ${INST_DEFS} -DWIN64)
endif()
set(IOS_ARMV8_BUILD ${DEFAULT_IOS_ARMV8_BUILD} CACHE PATH
"Directory containing ARMv8 iOS build to include in universal binaries (default: ${DEFAULT_IOS_ARMV8_BUILD})")
+set(OSX_APP_CERT_NAME "" CACHE STRING
+ "Name of the Developer ID Application certificate (in the macOS keychain) that should be used to sign the libjpeg-turbo DMG. Leave this blank to generate an unsigned DMG.")
+set(OSX_INST_CERT_NAME "" CACHE STRING
+ "Name of the Developer ID Installer certificate (in the macOS keychain) that should be used to sign the libjpeg-turbo installer package. Leave this blank to generate an unsigned package.")
+
configure_file(release/makemacpkg.in pkgscripts/makemacpkg)
configure_file(release/Distribution.xml.in pkgscripts/Distribution.xml)
configure_file(release/uninstall.in pkgscripts/uninstall)
# absolute paths where necessary, using the same logic.
#=============================================================================
-# Copyright 2016 D. R. Commander
+# Copyright 2016, 2019 D. R. Commander
# Copyright 2016 Dmitry Marakasov
# Copyright 2016 Roger Leigh
# Copyright 2015 Alex Turbov
"${docstring} (Default: ${CMAKE_INSTALL_DEFAULT_${var}})"
${_GNUInstallDirs_CMAKE_INSTALL_FORCE_${var}})
- if(NOT "${CMAKE_INSTALL_${var}}" STREQUAL "${CMAKE_INSTALL_DEFAULT_${var}}")
+ if(NOT CMAKE_INSTALL_${var} STREQUAL CMAKE_INSTALL_DEFAULT_${var})
unset(_GNUInstallDirs_CMAKE_INSTALL_DEFAULT_${var} CACHE)
endif()
FILE *input_file;
FILE *output_file;
unsigned char *inbuffer = NULL;
+#if JPEG_LIB_VERSION >= 80 || defined(MEM_SRCDST_SUPPORTED)
unsigned long insize = 0;
+#endif
JDIMENSION num_scanlines;
/* On Mac, fetch a command line. */
}
+METHODDEF(int) do_read_JPEG_file(struct jpeg_decompress_struct *cinfo,
+ char *filename);
+
/*
* Sample routine for JPEG decompression. We assume that the source file name
* is passed in. We want to return 1 on success, 0 on error.
*/
-
GLOBAL(int)
read_JPEG_file(char *filename)
{
* working space (which is allocated as needed by the JPEG library).
*/
struct jpeg_decompress_struct cinfo;
+
+ return do_read_JPEG_file(&cinfo, filename);
+}
+
+/*
+ * We call the libjpeg API from within a separate function, because modifying
+ * the local non-volatile jpeg_decompress_struct instance below the setjmp()
+ * return point and then accessing the instance after setjmp() returns would
+ * return in undefined behavior that may potentially overwrite all or part of
+ * the structure.
+ */
+
+METHODDEF(int)
+do_read_JPEG_file(struct jpeg_decompress_struct *cinfo, char *filename)
+{
/* We use our private extension JPEG error handler.
* Note that this struct must live as long as the main JPEG parameter
* struct, to avoid dangling-pointer problems.
/* Step 1: allocate and initialize JPEG decompression object */
/* We set up the normal JPEG error routines, then override error_exit. */
- cinfo.err = jpeg_std_error(&jerr.pub);
+ cinfo->err = jpeg_std_error(&jerr.pub);
jerr.pub.error_exit = my_error_exit;
/* Establish the setjmp return context for my_error_exit to use. */
if (setjmp(jerr.setjmp_buffer)) {
/* If we get here, the JPEG code has signaled an error.
* We need to clean up the JPEG object, close the input file, and return.
*/
- jpeg_destroy_decompress(&cinfo);
+ jpeg_destroy_decompress(cinfo);
fclose(infile);
return 0;
}
/* Now we can initialize the JPEG decompression object. */
- jpeg_create_decompress(&cinfo);
+ jpeg_create_decompress(cinfo);
/* Step 2: specify data source (eg, a file) */
- jpeg_stdio_src(&cinfo, infile);
+ jpeg_stdio_src(cinfo, infile);
/* Step 3: read file parameters with jpeg_read_header() */
- (void)jpeg_read_header(&cinfo, TRUE);
+ (void)jpeg_read_header(cinfo, TRUE);
/* We can ignore the return value from jpeg_read_header since
* (a) suspension is not possible with the stdio data source, and
* (b) we passed TRUE to reject a tables-only JPEG file as an error.
/* Step 5: Start decompressor */
- (void)jpeg_start_decompress(&cinfo);
+ (void)jpeg_start_decompress(cinfo);
/* We can ignore the return value since suspension is not possible
* with the stdio data source.
*/
* In this example, we need to make an output work buffer of the right size.
*/
/* JSAMPLEs per row in output buffer */
- row_stride = cinfo.output_width * cinfo.output_components;
+ row_stride = cinfo->output_width * cinfo->output_components;
/* Make a one-row-high sample array that will go away when done with image */
- buffer = (*cinfo.mem->alloc_sarray)
- ((j_common_ptr)&cinfo, JPOOL_IMAGE, row_stride, 1);
+ buffer = (*cinfo->mem->alloc_sarray)
+ ((j_common_ptr)cinfo, JPOOL_IMAGE, row_stride, 1);
/* Step 6: while (scan lines remain to be read) */
/* jpeg_read_scanlines(...); */
- /* Here we use the library's state variable cinfo.output_scanline as the
+ /* Here we use the library's state variable cinfo->output_scanline as the
* loop counter, so that we don't have to keep track ourselves.
*/
- while (cinfo.output_scanline < cinfo.output_height) {
+ while (cinfo->output_scanline < cinfo->output_height) {
/* jpeg_read_scanlines expects an array of pointers to scanlines.
* Here the array is only one element long, but you could ask for
* more than one scanline at a time if that's more convenient.
*/
- (void)jpeg_read_scanlines(&cinfo, buffer, 1);
+ (void)jpeg_read_scanlines(cinfo, buffer, 1);
/* Assume put_scanline_someplace wants a pointer and sample count. */
put_scanline_someplace(buffer[0], row_stride);
}
/* Step 7: Finish decompression */
- (void)jpeg_finish_decompress(&cinfo);
+ (void)jpeg_finish_decompress(cinfo);
/* We can ignore the return value since suspension is not possible
* with the stdio data source.
*/
/* Step 8: Release JPEG decompression object */
/* This is an important step since it will release a good deal of memory. */
- jpeg_destroy_decompress(&cinfo);
+ jpeg_destroy_decompress(cinfo);
/* After finish_decompress, we can close the input file.
* Here we postpone it until after no more JPEG errors are possible,
/*
- * Copyright (C)2009-2014, 2016-2018 D. R. Commander. All Rights Reserved.
+ * Copyright (C)2009-2014, 2016-2019 D. R. Commander. All Rights Reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
int rindex = TJ.getRedOffset(pixelFormat);
int gindex = TJ.getGreenOffset(pixelFormat);
int bindex = TJ.getBlueOffset(pixelFormat);
+ if ((long)w[0] * (long)h[0] * (long)ps > (long)Integer.MAX_VALUE)
+ throw new Exception("Image is too large");
byte[] dstBuf = new byte[w[0] * h[0] * ps];
int pixels = w[0] * h[0], dstPtr = 0, rgbPtr = 0;
tjd = new TJDecompressor();
- if (dstBuf == null)
+ if (dstBuf == null) {
+ if ((long)pitch * (long)scaledh > (long)Integer.MAX_VALUE)
+ throw new Exception("Image is too large");
dstBuf = new byte[pitch * scaledh];
+ }
/* Set the destination buffer to gray so we know whether the decompressor
attempted to write to it */
int width = doTile ? Math.min(tilew, w - x) : scaledw;
int height = doTile ? Math.min(tileh, h - y) : scaledh;
- tjd.setSourceImage(jpegBuf[tile], jpegSize[tile]);
+ try {
+ tjd.setSourceImage(jpegBuf[tile], jpegSize[tile]);
+ } catch (TJException e) { handleTJException(e); }
if (doYUV) {
yuvImage.setBuf(yuvImage.getBuf(), width, yuvPad, height, subsamp);
try {
String pfStr = PIXFORMATSTR[pf];
YUVImage yuvImage = null;
+ if ((long)pitch * (long)h > (long)Integer.MAX_VALUE)
+ throw new Exception("Image is too large");
tmpBuf = new byte[pitch * h];
if (quiet == 0)
if (!compOnly)
decomp(srcBuf, jpegBuf, jpegSize, tmpBuf, w, h, subsamp, jpegQual,
fileName, tilew, tileh);
+ else if (quiet == 1)
+ System.out.println("N/A");
if (tilew == w && tileh == h) break;
}
int tw, th, ttilew, ttileh, tntilesw, tntilesh, tsubsamp;
FileInputStream fis = new FileInputStream(fileName);
+ if (fis.getChannel().size() > (long)Integer.MAX_VALUE)
+ throw new Exception("Image is too large");
int srcSize = (int)fis.getChannel().size();
srcBuf = new byte[srcSize];
fis.read(srcBuf, 0, srcSize);
tjt = new TJTransformer();
- tjt.setSourceImage(srcBuf, srcSize);
+ try {
+ tjt.setSourceImage(srcBuf, srcSize);
+ } catch (TJException e) { handleTJException(e); }
w = tjt.getWidth();
h = tjt.getHeight();
subsamp = tjt.getSubsamp();
elapsed = 0.;
while (true) {
start = getTime();
- tjt.transform(jpegBuf, t, flags);
+ try {
+ tjt.transform(jpegBuf, t, flags);
+ } catch (TJException e) { handleTJException(e); }
jpegSize = tjt.getTransformedSizes();
elapsed += getTime() - start;
if (iter >= 0) {
System.out.println(" bytes to which each row of each plane in the intermediate YUV image is");
System.out.println(" padded (default = 1)");
System.out.println("-scale M/N = Scale down the width/height of the decompressed JPEG image by a");
- System.out.print (" factor of M/N (M/N = ");
+ System.out.print(" factor of M/N (M/N = ");
for (i = 0; i < nsf; i++) {
System.out.format("%d/%d", scalingFactors[i].getNum(),
scalingFactors[i].getDenom());
* This file was part of the Independent JPEG Group's software:
* Copyright (C) 1991-1997, Thomas G. Lane.
* libjpeg-turbo Modifications:
- * Copyright (C) 2009-2011, 2014-2016, 2018, D. R. Commander.
+ * Copyright (C) 2009-2011, 2014-2016, 2018-2019, D. R. Commander.
* Copyright (C) 2015, Matthieu Darbois.
* For conditions of distribution and use, see the accompanying README.ijg
* file.
*/
/* NOTE: Both GCC and Clang define __GNUC__ */
-#if defined __GNUC__ && (defined __arm__ || defined __aarch64__)
-#if !defined __thumb__ || defined __thumb2__
+#if defined(__GNUC__) && (defined(__arm__) || defined(__aarch64__))
+#if !defined(__thumb__) || defined(__thumb2__)
#define USE_CLZ_INTRINSIC
#endif
#endif
put_buffer = (put_buffer << size) | code; \
}
+#if SIZEOF_SIZE_T != 8 && !defined(_WIN64)
+
#define CHECKBUF15() { \
if (put_bits > 15) { \
EMIT_BYTE() \
} \
}
+#endif
+
#define CHECKBUF31() { \
if (put_bits > 31) { \
EMIT_BYTE() \
* scanning order-- 1, 8, 16, etc.), then this will produce an encoded block
* larger than 200 bytes.
*/
-#define BUFSIZE (DCTSIZE2 * 4)
+#define BUFSIZE (DCTSIZE2 * 8)
#define LOAD_BUFFER() { \
if (state->free_in_buffer < BUFSIZE) { \
*/
master->pass_type = output_pass;
master->pass_number++;
- /*FALLTHROUGH*/
#endif
+ /*FALLTHROUGH*/
case output_pass:
/* Do a data-output pass. */
/* We need not repeat per-scan setup if prior optimization pass did it. */
*/
/* NOTE: Both GCC and Clang define __GNUC__ */
-#if defined __GNUC__ && (defined __arm__ || defined __aarch64__)
-#if !defined __thumb__ || defined __thumb2__
+#if defined(__GNUC__) && (defined(__arm__) || defined(__aarch64__))
+#if !defined(__thumb__) || defined(__thumb2__)
#define USE_CLZ_INTRINSIC
#endif
#endif
* Copyright (C) 1994-1996, Thomas G. Lane.
* Modified 2009-2012 by Guido Vollbeding.
* libjpeg-turbo Modifications:
- * Copyright (C) 2011, 2014, 2016, D. R. Commander.
+ * Copyright (C) 2011, 2014, 2016, 2019, D. R. Commander.
* For conditions of distribution and use, see the accompanying README.ijg
* file.
*
extern void *malloc(size_t size);
extern void free(void *ptr);
#endif
+void jpeg_mem_dest_tj(j_compress_ptr cinfo, unsigned char **outbuffer,
+ unsigned long *outsize, boolean alloc);
#define OUTPUT_BUF_SIZE 4096 /* choose an efficiently fwrite'able size */
* Copyright (C) 1994-1996, Thomas G. Lane.
* Modified 2009-2011 by Guido Vollbeding.
* libjpeg-turbo Modifications:
- * Copyright (C) 2011, 2016, D. R. Commander.
+ * Copyright (C) 2011, 2016, 2019, D. R. Commander.
* For conditions of distribution and use, see the accompanying README.ijg
* file.
*
#include "jpeglib.h"
#include "jerror.h"
+void jpeg_mem_src_tj(j_decompress_ptr cinfo, const unsigned char *inbuffer,
+ unsigned long insize);
+
/*
* Initialize source --- called by jpeg_read_header
* This file was part of the Independent JPEG Group's software:
* Copyright (C) 1991-1997, Thomas G. Lane.
* libjpeg-turbo Modifications:
- * Copyright (C) 2009-2011, 2016, 2018, D. R. Commander.
+ * Copyright (C) 2009-2011, 2016, 2018-2019, D. R. Commander.
* For conditions of distribution and use, see the accompanying README.ijg
* file.
*
if (entropy->dc_needed[blkn]) {
/* Convert DC difference to actual value, update last_dc_val */
int ci = cinfo->MCU_membership[blkn];
- s += state.last_dc_val[ci];
+ /* This is really just
+ * s += state.last_dc_val[ci];
+ * It is written this way in order to shut up UBSan.
+ */
+ s = (int)((unsigned int)s + (unsigned int)state.last_dc_val[ci]);
state.last_dc_val[ci] = s;
if (block) {
/* Output the DC coefficient (assumes jpeg_natural_order[0] = 0) */
if (entropy->dc_needed[blkn]) {
int ci = cinfo->MCU_membership[blkn];
- s += state.last_dc_val[ci];
+ s = (int)((unsigned int)s + (unsigned int)state.last_dc_val[ci]);
state.last_dc_val[ci] = s;
if (block)
(*block)[0] = (JCOEF)s;
#define PACK_TWO_PIXELS_LE(l, r) ((r << 16) | l)
#define PACK_TWO_PIXELS_BE(l, r) ((l << 16) | r)
-#define PACK_NEED_ALIGNMENT(ptr) (((size_t)(ptr)) & 3)
-
#define WRITE_TWO_PIXELS_LE(addr, pixels) { \
((INT16 *)(addr))[0] = (INT16)(pixels); \
((INT16 *)(addr))[1] = (INT16)((pixels) >> 16); \
* Copyright (C) 2010, 2015-2016, D. R. Commander.
* Copyright (C) 2014, MIPS Technologies, Inc., California.
* Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2019, Arm Limited.
* For conditions of distribution and use, see the accompanying README.ijg
* file.
*
JSAMPARRAY output_data = *output_data_ptr;
JSAMPROW inptr0, inptr1, outptr;
#if BITS_IN_JSAMPLE == 8
- int thiscolsum;
+ int thiscolsum, bias;
#else
- JLONG thiscolsum;
+ JLONG thiscolsum, bias;
#endif
JDIMENSION colctr;
int inrow, outrow, v;
for (v = 0; v < 2; v++) {
/* inptr0 points to nearest input row, inptr1 points to next nearest */
inptr0 = input_data[inrow];
- if (v == 0) /* next nearest is row above */
+ if (v == 0) { /* next nearest is row above */
inptr1 = input_data[inrow - 1];
- else /* next nearest is row below */
+ bias = 1;
+ } else { /* next nearest is row below */
inptr1 = input_data[inrow + 1];
+ bias = 2;
+ }
outptr = output_data[outrow++];
for (colctr = 0; colctr < compptr->downsampled_width; colctr++) {
thiscolsum = GETJSAMPLE(*inptr0++) * 3 + GETJSAMPLE(*inptr1++);
- *outptr++ = (JSAMPLE)((thiscolsum + 1) >> 2);
+ *outptr++ = (JSAMPLE)((thiscolsum + bias) >> 2);
}
}
inrow++;
/*
* jfdctint.c
*
- * This file was part of the Independent JPEG Group's software.
+ * This file was part of the Independent JPEG Group's software:
* Copyright (C) 1991-1996, Thomas G. Lane.
* libjpeg-turbo Modifications:
* Copyright (C) 2015, D. R. Commander.
/*
* jidctint.c
*
- * This file was part of the Independent JPEG Group's software.
+ * This file was part of the Independent JPEG Group's software:
* Copyright (C) 1991-1998, Thomas G. Lane.
* Modification developed 2002-2009 by Guido Vollbeding.
* libjpeg-turbo Modifications:
/*
* jidctred.c
*
- * This file was part of the Independent JPEG Group's software.
+ * This file was part of the Independent JPEG Group's software:
* Copyright (C) 1994-1998, Thomas G. Lane.
* libjpeg-turbo Modifications:
* Copyright (C) 2015, D. R. Commander.
* This file was part of the Independent JPEG Group's software:
* Copyright (C) 1991-2012, Thomas G. Lane, Guido Vollbeding.
* libjpeg-turbo Modifications:
- * Copyright (C) 2010, 2012-2018, D. R. Commander.
+ * Copyright (C) 2010, 2012-2019, D. R. Commander.
* For conditions of distribution and use, see the accompanying README.ijg
* file.
*
*/
#define JCOPYRIGHT \
- "Copyright (C) 2009-2018 D. R. Commander\n" \
+ "Copyright (C) 2009-2019 D. R. Commander\n" \
"Copyright (C) 2011-2016 Siarhei Siamashka\n" \
"Copyright (C) 2015-2016, 2018 Matthieu Darbois\n" \
"Copyright (C) 2015 Intel Corporation\n" \
"Copyright (C) 1991-2016 Thomas G. Lane, Guido Vollbeding"
#define JCOPYRIGHT_SHORT \
- "Copyright (C) 1991-2018 The libjpeg-turbo Project and many others"
+ "Copyright (C) 1991-2019 The libjpeg-turbo Project and many others"
* this stuff is worth it, you can buy me a beer in return. Poul-Henning Kamp
* ----------------------------------------------------------------------------
* libjpeg-turbo Modifications:
- * Copyright (C)2016, 2018 D. R. Commander. All Rights Reserved.
+ * Copyright (C)2016, 2018-2019 D. R. Commander. All Rights Reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
#include "./md5.h"
-char *MD5End(MD5_CTX *ctx, char *buf)
+static char *MD5End(MD5_CTX *ctx, char *buf)
{
int i;
unsigned char digest[LENGTH];
off_t n;
MD5Init(&ctx);
-#if _WIN32
+#ifdef _WIN32
f = _open(filename, O_RDONLY | O_BINARY);
#else
f = open(filename, O_RDONLY);
return 0;
return (MD5End(&ctx, buf));
}
-
-char *MD5Data(const void *data, unsigned int len, char *buf)
-{
- MD5_CTX ctx;
-
- MD5Init(&ctx);
- MD5Update(&ctx, (unsigned char *)data, len);
- return (MD5End(&ctx, buf));
-}
#define M_SOI 0xD8 /* Start Of Image (beginning of datastream) */
#define M_EOI 0xD9 /* End Of Image (end of datastream) */
#define M_SOS 0xDA /* Start Of Scan (begins compressed data) */
-#define M_APP0 0xE0 /* Application-specific marker, type N */
#define M_APP12 0xEC /* (we don't bother to list all 16 APPn's) */
#define M_COM 0xFE /* COMment */
-libjpeg-turbo is a JPEG image codec that uses SIMD instructions (MMX, SSE2, AVX2, NEON, AltiVec) to accelerate baseline JPEG compression and decompression on x86, x86-64, ARM, and PowerPC systems, as well as progressive JPEG compression on x86 and x86-64 systems. On such systems, libjpeg-turbo is generally 2-6x as fast as libjpeg, all else being equal. On other types of systems, libjpeg-turbo can still outperform libjpeg by a significant amount, by virtue of its highly-optimized Huffman coding routines. In many cases, the performance of libjpeg-turbo rivals that of proprietary high-speed JPEG codecs.
+libjpeg-turbo is a JPEG image codec that uses SIMD instructions to accelerate baseline JPEG compression and decompression on x86, x86-64, ARM, PowerPC, and MIPS systems, as well as progressive JPEG compression on x86 and x86-64 systems. On such systems, libjpeg-turbo is generally 2-6x as fast as libjpeg, all else being equal. On other types of systems, libjpeg-turbo can still outperform libjpeg by a significant amount, by virtue of its highly-optimized Huffman coding routines. In many cases, the performance of libjpeg-turbo rivals that of proprietary high-speed JPEG codecs.
libjpeg-turbo implements both the traditional libjpeg API as well as the less powerful but more straightforward TurboJPEG API. libjpeg-turbo also features colorspace extensions that allow it to compress from/decompress to 32-bit and big-endian pixel buffers (RGBX, XBGR, etc.), as well as a full-featured Java interface.
Homepage: @PKGURL@
Installed-Size: {__SIZE}
Description: A SIMD-accelerated JPEG codec that provides both the libjpeg and TurboJPEG APIs
- libjpeg-turbo is a JPEG image codec that uses SIMD instructions (MMX, SSE2,
- AVX2, NEON, AltiVec) to accelerate baseline JPEG compression and decompression
- on x86, x86-64, ARM, and PowerPC systems, as well as progressive JPEG
- compression on x86 and x86-64 systems. On such systems, libjpeg-turbo is
- generally 2-6x as fast as libjpeg, all else being equal. On other types of
- systems, libjpeg-turbo can still outperform libjpeg by a significant amount,
- by virtue of its highly-optimized Huffman coding routines. In many cases, the
- performance of libjpeg-turbo rivals that of proprietary high-speed JPEG
- codecs.
+ libjpeg-turbo is a JPEG image codec that uses SIMD instructions to accelerate
+ baseline JPEG compression and decompression on x86, x86-64, ARM, PowerPC, and
+ MIPS systems, as well as progressive JPEG compression on x86 and x86-64
+ systems. On such systems, libjpeg-turbo is generally 2-6x as fast as libjpeg,
+ all else being equal. On other types of systems, libjpeg-turbo can still
+ outperform libjpeg by a significant amount, by virtue of its highly-optimized
+ Huffman coding routines. In many cases, the performance of libjpeg-turbo
+ rivals that of proprietary high-speed JPEG codecs.
.
libjpeg-turbo implements both the traditional libjpeg API as well as the less
powerful but more straightforward TurboJPEG API. libjpeg-turbo also features
BUILDDIRARMV7S=@IOS_ARMV7S_BUILD@
BUILDDIRARMV8=@IOS_ARMV8_BUILD@
WITH_JAVA=@WITH_JAVA@
+OSX_APP_CERT_NAME="@OSX_APP_CERT_NAME@"
+OSX_INST_CERT_NAME="@OSX_INST_CERT_NAME@"
LIPO=lipo
PREFIX=@CMAKE_INSTALL_PREFIX@
mkdir $TMPDIR/dmg
pkgbuild --root $PKGROOT --version $VERSION.$BUILD --identifier @PKGID@ \
$TMPDIR/pkg/$PKGNAME.pkg
+SUFFIX=
+if [ "$OSX_INST_CERT_NAME" != "" ]; then
+ SUFFIX=-unsigned
+fi
productbuild --distribution pkgscripts/Distribution.xml \
--package-path $TMPDIR/pkg/ --resources $TMPDIR/pkg/ \
- $TMPDIR/dmg/$PKGNAME.pkg
+ $TMPDIR/dmg/$PKGNAME$SUFFIX.pkg
+if [ "$OSX_INST_CERT_NAME" != "" ]; then
+ productsign --sign "$OSX_INST_CERT_NAME" --timestamp \
+ $TMPDIR/dmg/$PKGNAME$SUFFIX.pkg $TMPDIR/dmg/$PKGNAME.pkg
+ rm -r $TMPDIR/dmg/$PKGNAME$SUFFIX.pkg
+ pkgutil --check-signature $TMPDIR/dmg/$PKGNAME.pkg
+fi
hdiutil create -fs HFS+ -volname $PKGNAME-$VERSION \
-srcfolder "$TMPDIR/dmg" $TMPDIR/$PKGNAME-$VERSION.dmg
+if [ "$OSX_APP_CERT_NAME" != "" ]; then
+ codesign -s "$OSX_APP_CERT_NAME" --timestamp $TMPDIR/$PKGNAME-$VERSION.dmg
+ codesign -vv $TMPDIR/$PKGNAME-$VERSION.dmg
+fi
cp $TMPDIR/$PKGNAME-$VERSION.dmg .
exit
+%global _docdir %{_defaultdocdir}/%{name}-%{version}
%define _prefix @CMAKE_INSTALL_PREFIX@
%define _bindir @CMAKE_INSTALL_FULL_BINDIR@
%define _datarootdir @CMAKE_INSTALL_FULL_DATAROOTDIR@
-%define _docdir %{_defaultdocdir}/%{name}-%{version}
%define _includedir @CMAKE_INSTALL_FULL_INCLUDEDIR@
%define _javadir @CMAKE_INSTALL_FULL_JAVADIR@
%define _mandir @CMAKE_INSTALL_FULL_MANDIR@
Release: @BUILD@
License: BSD-style
BuildRoot: %{_blddir}/%{name}-buildroot-%{version}-%{release}
-Prereq: /sbin/ldconfig
+Requires: /sbin/ldconfig
%if "%{_bits}" == "64"
Provides: %{name} = %{version}-%{release}, @CMAKE_PROJECT_NAME@ = %{version}-%{release}, libturbojpeg.so()(64bit)
%else
%endif
%description
-libjpeg-turbo is a JPEG image codec that uses SIMD instructions (MMX, SSE2,
-AVX2, NEON, AltiVec) to accelerate baseline JPEG compression and decompression
-on x86, x86-64, ARM, and PowerPC systems, as well as progressive JPEG
-compression on x86 and x86-64 systems. On such systems, libjpeg-turbo is
-generally 2-6x as fast as libjpeg, all else being equal. On other types of
-systems, libjpeg-turbo can still outperform libjpeg by a significant amount, by
-virtue of its highly-optimized Huffman coding routines. In many cases, the
-performance of libjpeg-turbo rivals that of proprietary high-speed JPEG codecs.
+libjpeg-turbo is a JPEG image codec that uses SIMD instructions to accelerate
+baseline JPEG compression and decompression on x86, x86-64, ARM, PowerPC, and
+MIPS systems, as well as progressive JPEG compression on x86 and x86-64
+systems. On such systems, libjpeg-turbo is generally 2-6x as fast as libjpeg,
+all else being equal. On other types of systems, libjpeg-turbo can still
+outperform libjpeg by a significant amount, by virtue of its highly-optimized
+Huffman coding routines. In many cases, the performance of libjpeg-turbo
+rivals that of proprietary high-speed JPEG codecs.
libjpeg-turbo implements both the traditional libjpeg API as well as the less
powerful but more straightforward TurboJPEG API. libjpeg-turbo also features
%if "%{_enable_static}" == "1"
%{_libdir}/libjpeg.a
%endif
-%{_libdir}/pkgconfig
+%dir %{_libdir}/pkgconfig
%{_libdir}/pkgconfig/libjpeg.pc
%if "%{_with_turbojpeg}" == "1"
%if "%{_enable_shared}" == "1" || "%{_with_java}" == "1"
set(JPEG_SRCS ${JPEG_SRCS} ../${src})
endforeach()
-if(WITH_SIMD AND MSVC_IDE)
+if(WITH_SIMD AND (MSVC_IDE OR XCODE))
# This tells CMake that the "source" files haven't been generated yet
set_source_files_properties(${SIMD_OBJS} PROPERTIES GENERATED 1)
endif()
LINK_FLAGS "${MAPFLAG}${CMAKE_CURRENT_BINARY_DIR}/../libjpeg.map")
endif()
if(MSVC)
- set_target_properties(jpeg PROPERTIES SUFFIX ${SO_MAJOR_VERSION}.dll)
+ set_target_properties(jpeg PROPERTIES
+ RUNTIME_OUTPUT_NAME jpeg${SO_MAJOR_VERSION})
# The jsimd_*.c file is built using /MT, so this prevents a linker warning.
set_target_properties(jpeg PROPERTIES LINK_FLAGS "/NODEFAULTLIB:LIBCMT /NODEFAULTLIB:LIBCMTD")
elseif(MINGW)
ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
+if(NOT CMAKE_VERSION VERSION_LESS "3.1" AND MSVC AND
+ CMAKE_C_LINKER_SUPPORTS_PDB)
+ install(FILES "$<TARGET_PDB_FILE:jpeg>"
+ DESTINATION ${CMAKE_INSTALL_BINDIR} OPTIONAL)
+endif()
endif()
endif()
+if(NOT REQUIRE_SIMD)
+ include(CheckLanguage)
+ check_language(ASM_NASM)
+ if(NOT CMAKE_ASM_NASM_COMPILER)
+ simd_fail("SIMD extensions disabled: could not find NASM compiler")
+ return()
+ endif()
+endif()
enable_language(ASM_NASM)
message(STATUS "CMAKE_ASM_NASM_COMPILER = ${CMAKE_ASM_NASM_COMPILER}")
if(MSVC_IDE)
set(OBJDIR "${CMAKE_CURRENT_BINARY_DIR}/${CMAKE_CFG_INTDIR}")
string(REGEX REPLACE " " ";" CMAKE_ASM_NASM_FLAGS "${CMAKE_ASM_NASM_FLAGS}")
+elseif(XCODE)
+ set(OBJDIR "${CMAKE_CURRENT_BINARY_DIR}")
+ string(REGEX REPLACE " " ";" CMAKE_ASM_NASM_FLAGS "${CMAKE_ASM_NASM_FLAGS}")
endif()
file(GLOB INC_FILES nasm/*.inc)
${CMAKE_CURRENT_SOURCE_DIR}/${DEPFILE})
endif()
set(OBJECT_DEPENDS ${OBJECT_DEPENDS} ${INC_FILES})
- if(MSVC_IDE)
+ if(MSVC_IDE OR XCODE)
# The CMake Visual Studio generators do not work properly with the ASM_NASM
# language, so we have to go rogue here and use a custom command like we
# did in prior versions of libjpeg-turbo. (This is why we can't have nice
# things.)
string(REGEX REPLACE "${CPU_TYPE}/" "" filename ${file})
- set(SIMD_OBJ ${OBJDIR}/${filename}.obj)
+ set(SIMD_OBJ ${OBJDIR}/${filename}${CMAKE_C_OUTPUT_EXTENSION})
add_custom_command(OUTPUT ${SIMD_OBJ} DEPENDS ${file} ${OBJECT_DEPENDS}
COMMAND ${CMAKE_ASM_NASM_COMPILER} -f${CMAKE_ASM_NASM_OBJECT_FORMAT}
${CMAKE_ASM_NASM_FLAGS} ${CMAKE_CURRENT_SOURCE_DIR}/${file}
endif()
endforeach()
-if(MSVC_IDE)
+if(MSVC_IDE OR XCODE)
set(SIMD_OBJS ${SIMD_OBJS} PARENT_SCOPE)
add_library(simd OBJECT ${CPU_TYPE}/jsimd.c)
add_custom_target(simd-objs DEPENDS ${SIMD_OBJS})
* Copyright (C) 2011, Nokia Corporation and/or its subsidiary(-ies).
* Copyright (C) 2009-2011, 2013-2014, 2016, 2018, D. R. Commander.
* Copyright (C) 2015-2016, 2018, Matthieu Darbois.
+ * Copyright (C) 2019, Google LLC.
*
* Based on the x86 SIMD extension for IJG JPEG library,
* Copyright (C) 1999-2006, MIYASAKA Masaru.
static unsigned int simd_support = ~0;
static unsigned int simd_huffman = 1;
-#if defined(__linux__) || defined(ANDROID) || defined(__ANDROID__)
+#if !defined(__ARM_NEON__) && (defined(__linux__) || defined(ANDROID) || defined(__ANDROID__))
#define SOMEWHAT_SANE_PROC_CPUINFO_SIZE_LIMIT (1024 * 1024)
#ifndef NO_GETENV
char *env = NULL;
#endif
-#if !defined(__ARM_NEON__) && defined(__linux__) || defined(ANDROID) || defined(__ANDROID__)
+#if !defined(__ARM_NEON__) && (defined(__linux__) || defined(ANDROID) || defined(__ANDROID__))
int bufsize = 1024; /* an initial guess for the line buffer size limit */
#endif
.section .note.GNU-stack, "", %progbits /* mark stack as non-executable */
#endif
+#if defined(__APPLE__)
+.section __DATA, __const
+#else
+.section .rodata, "a", %progbits
+#endif
+
+/* Constants for jsimd_idct_islow_neon() */
+
+#define F_0_298 2446 /* FIX(0.298631336) */
+#define F_0_390 3196 /* FIX(0.390180644) */
+#define F_0_541 4433 /* FIX(0.541196100) */
+#define F_0_765 6270 /* FIX(0.765366865) */
+#define F_0_899 7373 /* FIX(0.899976223) */
+#define F_1_175 9633 /* FIX(1.175875602) */
+#define F_1_501 12299 /* FIX(1.501321110) */
+#define F_1_847 15137 /* FIX(1.847759065) */
+#define F_1_961 16069 /* FIX(1.961570560) */
+#define F_2_053 16819 /* FIX(2.053119869) */
+#define F_2_562 20995 /* FIX(2.562915447) */
+#define F_3_072 25172 /* FIX(3.072711026) */
+
+.balign 16
+Ljsimd_idct_islow_neon_consts:
+ .short F_0_298
+ .short -F_0_390
+ .short F_0_541
+ .short F_0_765
+ .short - F_0_899
+ .short F_1_175
+ .short F_1_501
+ .short - F_1_847
+ .short - F_1_961
+ .short F_2_053
+ .short - F_2_562
+ .short F_3_072
+ .short 0 /* padding */
+ .short 0
+ .short 0
+ .short 0
+
+#undef F_0_298
+#undef F_0_390
+#undef F_0_541
+#undef F_0_765
+#undef F_0_899
+#undef F_1_175
+#undef F_1_501
+#undef F_1_847
+#undef F_1_961
+#undef F_2_053
+#undef F_2_562
+#undef F_3_072
+
+/* Constants for jsimd_idct_ifast_neon() */
+
+.balign 16
+Ljsimd_idct_ifast_neon_consts:
+ .short (277 * 128 - 256 * 128) /* XFIX_1_082392200 */
+ .short (362 * 128 - 256 * 128) /* XFIX_1_414213562 */
+ .short (473 * 128 - 256 * 128) /* XFIX_1_847759065 */
+ .short (669 * 128 - 512 * 128) /* XFIX_2_613125930 */
+
+/* Constants for jsimd_idct_4x4_neon() and jsimd_idct_2x2_neon() */
+
+#define CONST_BITS 13
+
+#define FIX_0_211164243 (1730) /* FIX(0.211164243) */
+#define FIX_0_509795579 (4176) /* FIX(0.509795579) */
+#define FIX_0_601344887 (4926) /* FIX(0.601344887) */
+#define FIX_0_720959822 (5906) /* FIX(0.720959822) */
+#define FIX_0_765366865 (6270) /* FIX(0.765366865) */
+#define FIX_0_850430095 (6967) /* FIX(0.850430095) */
+#define FIX_0_899976223 (7373) /* FIX(0.899976223) */
+#define FIX_1_061594337 (8697) /* FIX(1.061594337) */
+#define FIX_1_272758580 (10426) /* FIX(1.272758580) */
+#define FIX_1_451774981 (11893) /* FIX(1.451774981) */
+#define FIX_1_847759065 (15137) /* FIX(1.847759065) */
+#define FIX_2_172734803 (17799) /* FIX(2.172734803) */
+#define FIX_2_562915447 (20995) /* FIX(2.562915447) */
+#define FIX_3_624509785 (29692) /* FIX(3.624509785) */
+
+.balign 16
+Ljsimd_idct_4x4_neon_consts:
+ .short FIX_1_847759065 /* v0.h[0] */
+ .short -FIX_0_765366865 /* v0.h[1] */
+ .short -FIX_0_211164243 /* v0.h[2] */
+ .short FIX_1_451774981 /* v0.h[3] */
+ .short -FIX_2_172734803 /* d1[0] */
+ .short FIX_1_061594337 /* d1[1] */
+ .short -FIX_0_509795579 /* d1[2] */
+ .short -FIX_0_601344887 /* d1[3] */
+ .short FIX_0_899976223 /* v2.h[0] */
+ .short FIX_2_562915447 /* v2.h[1] */
+ .short 1 << (CONST_BITS + 1) /* v2.h[2] */
+ .short 0 /* v2.h[3] */
+
+.balign 8
+Ljsimd_idct_2x2_neon_consts:
+ .short -FIX_0_720959822 /* v14[0] */
+ .short FIX_0_850430095 /* v14[1] */
+ .short -FIX_1_272758580 /* v14[2] */
+ .short FIX_3_624509785 /* v14[3] */
+
+/* Constants for jsimd_ycc_*_neon() */
+
+.balign 16
+Ljsimd_ycc_rgb_neon_consts:
+ .short 0, 0, 0, 0
+ .short 22971, -11277, -23401, 29033
+ .short -128, -128, -128, -128
+ .short -128, -128, -128, -128
+
+/* Constants for jsimd_*_ycc_neon() */
+
+.balign 16
+Ljsimd_rgb_ycc_neon_consts:
+ .short 19595, 38470, 7471, 11059
+ .short 21709, 32768, 27439, 5329
+ .short 32767, 128, 32767, 128
+ .short 32767, 128, 32767, 128
+
+/* Constants for jsimd_fdct_islow_neon() */
+
+#define F_0_298 2446 /* FIX(0.298631336) */
+#define F_0_390 3196 /* FIX(0.390180644) */
+#define F_0_541 4433 /* FIX(0.541196100) */
+#define F_0_765 6270 /* FIX(0.765366865) */
+#define F_0_899 7373 /* FIX(0.899976223) */
+#define F_1_175 9633 /* FIX(1.175875602) */
+#define F_1_501 12299 /* FIX(1.501321110) */
+#define F_1_847 15137 /* FIX(1.847759065) */
+#define F_1_961 16069 /* FIX(1.961570560) */
+#define F_2_053 16819 /* FIX(2.053119869) */
+#define F_2_562 20995 /* FIX(2.562915447) */
+#define F_3_072 25172 /* FIX(3.072711026) */
+
+.balign 16
+Ljsimd_fdct_islow_neon_consts:
+ .short F_0_298
+ .short -F_0_390
+ .short F_0_541
+ .short F_0_765
+ .short - F_0_899
+ .short F_1_175
+ .short F_1_501
+ .short - F_1_847
+ .short - F_1_961
+ .short F_2_053
+ .short - F_2_562
+ .short F_3_072
+ .short 0 /* padding */
+ .short 0
+ .short 0
+ .short 0
+
+#undef F_0_298
+#undef F_0_390
+#undef F_0_541
+#undef F_0_765
+#undef F_0_899
+#undef F_1_175
+#undef F_1_501
+#undef F_1_847
+#undef F_1_961
+#undef F_2_053
+#undef F_2_562
+#undef F_3_072
+
+/* Constants for jsimd_fdct_ifast_neon() */
+
+.balign 16
+Ljsimd_fdct_ifast_neon_consts:
+ .short (98 * 128) /* XFIX_0_382683433 */
+ .short (139 * 128) /* XFIX_0_541196100 */
+ .short (181 * 128) /* XFIX_0_707106781 */
+ .short (334 * 128 - 256 * 128) /* XFIX_1_306562965 */
+
+/* Constants for jsimd_h2*_downsample_neon() */
+
+.balign 16
+Ljsimd_h2_downsample_neon_consts:
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F /* diff 0 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0E /* diff 1 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0D, 0x0D /* diff 2 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0C, 0x0C, 0x0C /* diff 3 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x08, 0x09, 0x0A, 0x0B, 0x0B, 0x0B, 0x0B, 0x0B /* diff 4 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x08, 0x09, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A /* diff 5 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x08, 0x09, 0x09, 0x09, 0x09, 0x09, 0x09, 0x09 /* diff 6 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08 /* diff 7 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
+ 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07 /* diff 8 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x06, \
+ 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06 /* diff 9 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x05, 0x05, \
+ 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05 /* diff 10 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x04, 0x04, 0x04, \
+ 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04 /* diff 11 */
+ .byte 0x00, 0x01, 0x02, 0x03, 0x03, 0x03, 0x03, 0x03, \
+ 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03 /* diff 12 */
+ .byte 0x00, 0x01, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, \
+ 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02 /* diff 13 */
+ .byte 0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, \
+ 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01 /* diff 14 */
+ .byte 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 /* diff 15 */
+
+/* Constants for jsimd_huff_encode_one_block_neon() */
+
+.balign 16
+Ljsimd_huff_encode_one_block_neon_consts:
+ .byte 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, \
+ 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80
+ .byte 0, 1, 2, 3, 16, 17, 32, 33, \
+ 18, 19, 4, 5, 6, 7, 20, 21 /* L0 => L3 : 4 lines OK */
+ .byte 34, 35, 48, 49, 255, 255, 50, 51, \
+ 36, 37, 22, 23, 8, 9, 10, 11 /* L0 => L3 : 4 lines OK */
+ .byte 8, 9, 22, 23, 36, 37, 50, 51, \
+ 255, 255, 255, 255, 255, 255, 52, 53 /* L1 => L4 : 4 lines OK */
+ .byte 54, 55, 40, 41, 26, 27, 12, 13, \
+ 14, 15, 28, 29, 42, 43, 56, 57 /* L0 => L3 : 4 lines OK */
+ .byte 6, 7, 20, 21, 34, 35, 48, 49, \
+ 50, 51, 36, 37, 22, 23, 8, 9 /* L4 => L7 : 4 lines OK */
+ .byte 42, 43, 28, 29, 14, 15, 30, 31, \
+ 44, 45, 58, 59, 255, 255, 255, 255 /* L1 => L4 : 4 lines OK */
+ .byte 255, 255, 255, 255, 56, 57, 42, 43, \
+ 28, 29, 14, 15, 30, 31, 44, 45 /* L3 => L6 : 4 lines OK */
+ .byte 26, 27, 40, 41, 42, 43, 28, 29, \
+ 14, 15, 30, 31, 44, 45, 46, 47 /* L5 => L7 : 3 lines OK */
+ .byte 255, 255, 255, 255, 0, 1, 255, 255, \
+ 255, 255, 255, 255, 255, 255, 255, 255 /* L4 : 1 lines OK */
+ .byte 255, 255, 255, 255, 255, 255, 255, 255, \
+ 0, 1, 16, 17, 2, 3, 255, 255 /* L5 => L6 : 2 lines OK */
+ .byte 255, 255, 255, 255, 255, 255, 255, 255, \
+ 255, 255, 255, 255, 8, 9, 22, 23 /* L5 => L6 : 2 lines OK */
+ .byte 4, 5, 6, 7, 255, 255, 255, 255, \
+ 255, 255, 255, 255, 255, 255, 255, 255 /* L7 : 1 line OK */
+
.text
#endif
.endm
+/* Get symbol location */
+.macro get_symbol_loc reg, symbol
+#ifdef __APPLE__
+ adrp \reg, \symbol@PAGE
+ add \reg, \reg, \symbol@PAGEOFF
+#else
+ adrp \reg, \symbol
+ add \reg, \reg, :lo12:\symbol
+#endif
+.endm
+
/* Transpose elements of single 128 bit registers */
.macro transpose_single x0, x1, xi, xilen, literal
ins \xi\xilen[0], \x0\xilen[0]
#define CONST_BITS 13
#define PASS1_BITS 2
-#define F_0_298 2446 /* FIX(0.298631336) */
-#define F_0_390 3196 /* FIX(0.390180644) */
-#define F_0_541 4433 /* FIX(0.541196100) */
-#define F_0_765 6270 /* FIX(0.765366865) */
-#define F_0_899 7373 /* FIX(0.899976223) */
-#define F_1_175 9633 /* FIX(1.175875602) */
-#define F_1_501 12299 /* FIX(1.501321110) */
-#define F_1_847 15137 /* FIX(1.847759065) */
-#define F_1_961 16069 /* FIX(1.961570560) */
-#define F_2_053 16819 /* FIX(2.053119869) */
-#define F_2_562 20995 /* FIX(2.562915447) */
-#define F_3_072 25172 /* FIX(3.072711026) */
-
-.balign 16
-Ljsimd_idct_islow_neon_consts:
- .short F_0_298
- .short -F_0_390
- .short F_0_541
- .short F_0_765
- .short - F_0_899
- .short F_1_175
- .short F_1_501
- .short - F_1_847
- .short - F_1_961
- .short F_2_053
- .short - F_2_562
- .short F_3_072
- .short 0 /* padding */
- .short 0
- .short 0
- .short 0
-
-#undef F_0_298
-#undef F_0_390
-#undef F_0_541
-#undef F_0_765
-#undef F_0_899
-#undef F_1_175
-#undef F_1_501
-#undef F_1_847
-#undef F_1_961
-#undef F_2_053
-#undef F_2_562
-#undef F_3_072
-
#define XFIX_P_0_298 v0.h[0]
#define XFIX_N_0_390 v0.h[1]
#define XFIX_P_0_541 v0.h[2]
uxtw x3, w3
sub sp, sp, #64
- adr x15, Ljsimd_idct_islow_neon_consts
+ get_symbol_loc x15, Ljsimd_idct_islow_neon_consts
mov x10, sp
st1 {v8.8b, v9.8b, v10.8b, v11.8b}, [x10], #32
st1 {v12.8b, v13.8b, v14.8b, v15.8b}, [x10], #32
#define XFIX_1_847759065 v0.h[2]
#define XFIX_2_613125930 v0.h[3]
-.balign 16
-Ljsimd_idct_ifast_neon_consts:
- .short (277 * 128 - 256 * 128) /* XFIX_1_082392200 */
- .short (362 * 128 - 256 * 128) /* XFIX_1_414213562 */
- .short (473 * 128 - 256 * 128) /* XFIX_1_847759065 */
- .short (669 * 128 - 512 * 128) /* XFIX_2_613125930 */
-
asm_function jsimd_idct_ifast_neon
DCT_TABLE .req x0
* 7 | d30 | d31 ( v23.8h )
*/
/* Save NEON registers used in fast IDCT */
- adr TMP5, Ljsimd_idct_ifast_neon_consts
+ get_symbol_loc TMP5, Ljsimd_idct_ifast_neon_consts
ld1 {v16.8h, v17.8h}, [COEF_BLOCK], 32
ld1 {v0.8h, v1.8h}, [DCT_TABLE], 32
ld1 {v18.8h, v19.8h}, [COEF_BLOCK], 32
* but readability will suffer somewhat.
*/
-#define CONST_BITS 13
-
-#define FIX_0_211164243 (1730) /* FIX(0.211164243) */
-#define FIX_0_509795579 (4176) /* FIX(0.509795579) */
-#define FIX_0_601344887 (4926) /* FIX(0.601344887) */
-#define FIX_0_720959822 (5906) /* FIX(0.720959822) */
-#define FIX_0_765366865 (6270) /* FIX(0.765366865) */
-#define FIX_0_850430095 (6967) /* FIX(0.850430095) */
-#define FIX_0_899976223 (7373) /* FIX(0.899976223) */
-#define FIX_1_061594337 (8697) /* FIX(1.061594337) */
-#define FIX_1_272758580 (10426) /* FIX(1.272758580) */
-#define FIX_1_451774981 (11893) /* FIX(1.451774981) */
-#define FIX_1_847759065 (15137) /* FIX(1.847759065) */
-#define FIX_2_172734803 (17799) /* FIX(2.172734803) */
-#define FIX_2_562915447 (20995) /* FIX(2.562915447) */
-#define FIX_3_624509785 (29692) /* FIX(3.624509785) */
-
-.balign 16
-Ljsimd_idct_4x4_neon_consts:
- .short FIX_1_847759065 /* v0.h[0] */
- .short -FIX_0_765366865 /* v0.h[1] */
- .short -FIX_0_211164243 /* v0.h[2] */
- .short FIX_1_451774981 /* v0.h[3] */
- .short -FIX_2_172734803 /* d1[0] */
- .short FIX_1_061594337 /* d1[1] */
- .short -FIX_0_509795579 /* d1[2] */
- .short -FIX_0_601344887 /* d1[3] */
- .short FIX_0_899976223 /* v2.h[0] */
- .short FIX_2_562915447 /* v2.h[1] */
- .short 1 << (CONST_BITS + 1) /* v2.h[2] */
- .short 0 /* v2.h[3] */
-
.macro idct_helper x4, x6, x8, x10, x12, x14, x16, shift, y26, y27, y28, y29
smull v28.4s, \x4, v2.h[2]
smlal v28.4s, \x8, v0.h[0]
sub sp, sp, 64
mov x9, sp
/* Load constants (v3.4h is just used for padding) */
- adr TMP4, Ljsimd_idct_4x4_neon_consts
+ get_symbol_loc TMP4, Ljsimd_idct_4x4_neon_consts
st1 {v8.8b, v9.8b, v10.8b, v11.8b}, [x9], 32
st1 {v12.8b, v13.8b, v14.8b, v15.8b}, [x9], 32
ld1 {v0.4h, v1.4h, v2.4h, v3.4h}, [TMP4]
* bit exact compatibility with jpeg-6b.
*/
-.balign 8
-Ljsimd_idct_2x2_neon_consts:
- .short -FIX_0_720959822 /* v14[0] */
- .short FIX_0_850430095 /* v14[1] */
- .short -FIX_1_272758580 /* v14[2] */
- .short FIX_3_624509785 /* v14[3] */
-
.macro idct_helper x4, x6, x10, x12, x16, shift, y26, y27
sshll v15.4s, \x4, #15
smull v26.4s, \x6, v14.h[3]
mov x9, sp
/* Load constants */
- adr TMP2, Ljsimd_idct_2x2_neon_consts
+ get_symbol_loc TMP2, Ljsimd_idct_2x2_neon_consts
st1 {v8.8b, v9.8b, v10.8b, v11.8b}, [x9], 32
st1 {v12.8b, v13.8b, v14.8b, v15.8b}, [x9], 32
ld1 {v14.4h}, [TMP2]
do_yuv_to_rgb_stage2
.endm
-/* Apple gas crashes on adrl, work around that by using adr.
- * But this requires a copy of these constants for each function.
- */
-
-.balign 16
-.if \fast_st3 == 1
-Ljsimd_ycc_\colorid\()_neon_consts:
-.else
-Ljsimd_ycc_\colorid\()_neon_slowst3_consts:
-.endif
- .short 0, 0, 0, 0
- .short 22971, -11277, -23401, 29033
- .short -128, -128, -128, -128
- .short -128, -128, -128, -128
-
.if \fast_st3 == 1
asm_function jsimd_ycc_\colorid\()_convert_neon
.else
mov x9, sp
/* Load constants to d1, d2, d3 (v0.4h is just used for padding) */
- .if \fast_st3 == 1
- adr x15, Ljsimd_ycc_\colorid\()_neon_consts
- .else
- adr x15, Ljsimd_ycc_\colorid\()_neon_slowst3_consts
- .endif
+ get_symbol_loc x15, Ljsimd_ycc_rgb_neon_consts
/* Save NEON registers */
st1 {v8.8b, v9.8b, v10.8b, v11.8b}, [x9], 32
do_rgb_to_yuv_stage1
.endm
-.balign 16
-.if \fast_ld3 == 1
-Ljsimd_\colorid\()_ycc_neon_consts:
-.else
-Ljsimd_\colorid\()_ycc_neon_slowld3_consts:
-.endif
- .short 19595, 38470, 7471, 11059
- .short 21709, 32768, 27439, 5329
- .short 32767, 128, 32767, 128
- .short 32767, 128, 32767, 128
-
.if \fast_ld3 == 1
asm_function jsimd_\colorid\()_ycc_convert_neon
.else
N .req w12
/* Load constants to d0, d1, d2, d3 */
- .if \fast_ld3 == 1
- adr x13, Ljsimd_\colorid\()_ycc_neon_consts
- .else
- adr x13, Ljsimd_\colorid\()_ycc_neon_slowld3_consts
- .endif
+ get_symbol_loc x13, Ljsimd_rgb_ycc_neon_consts
ld1 {v0.8h, v1.8h}, [x13]
ldr OUTPUT_BUF0, [OUTPUT_BUF]
#define DESCALE_P1 (CONST_BITS - PASS1_BITS)
#define DESCALE_P2 (CONST_BITS + PASS1_BITS)
-#define F_0_298 2446 /* FIX(0.298631336) */
-#define F_0_390 3196 /* FIX(0.390180644) */
-#define F_0_541 4433 /* FIX(0.541196100) */
-#define F_0_765 6270 /* FIX(0.765366865) */
-#define F_0_899 7373 /* FIX(0.899976223) */
-#define F_1_175 9633 /* FIX(1.175875602) */
-#define F_1_501 12299 /* FIX(1.501321110) */
-#define F_1_847 15137 /* FIX(1.847759065) */
-#define F_1_961 16069 /* FIX(1.961570560) */
-#define F_2_053 16819 /* FIX(2.053119869) */
-#define F_2_562 20995 /* FIX(2.562915447) */
-#define F_3_072 25172 /* FIX(3.072711026) */
-
-.balign 16
-Ljsimd_fdct_islow_neon_consts:
- .short F_0_298
- .short -F_0_390
- .short F_0_541
- .short F_0_765
- .short - F_0_899
- .short F_1_175
- .short F_1_501
- .short - F_1_847
- .short - F_1_961
- .short F_2_053
- .short - F_2_562
- .short F_3_072
- .short 0 /* padding */
- .short 0
- .short 0
- .short 0
-
-#undef F_0_298
-#undef F_0_390
-#undef F_0_541
-#undef F_0_765
-#undef F_0_899
-#undef F_1_175
-#undef F_1_501
-#undef F_1_847
-#undef F_1_961
-#undef F_2_053
-#undef F_2_562
-#undef F_3_072
#define XFIX_P_0_298 v0.h[0]
#define XFIX_N_0_390 v0.h[1]
#define XFIX_P_0_541 v0.h[2]
TMP .req x9
/* Load constants */
- adr TMP, Ljsimd_fdct_islow_neon_consts
+ get_symbol_loc TMP, Ljsimd_fdct_islow_neon_consts
ld1 {v0.8h, v1.8h}, [TMP]
/* Save NEON registers */
#define XFIX_0_707106781 v0.h[2]
#define XFIX_1_306562965 v0.h[3]
-.balign 16
-Ljsimd_fdct_ifast_neon_consts:
- .short (98 * 128) /* XFIX_0_382683433 */
- .short (139 * 128) /* XFIX_0_541196100 */
- .short (181 * 128) /* XFIX_0_707106781 */
- .short (334 * 128 - 256 * 128) /* XFIX_1_306562965 */
-
asm_function jsimd_fdct_ifast_neon
DATA .req x0
TMP .req x9
/* Load constants */
- adr TMP, Ljsimd_fdct_ifast_neon_consts
+ get_symbol_loc TMP, Ljsimd_fdct_ifast_neon_consts
ld1 {v0.4h}, [TMP]
/* Load all DATA into NEON registers with the following allocation:
* JSAMPARRAY input_data, JSAMPARRAY output_data);
*/
-.balign 16
-Ljsimd_h2_downsample_neon_consts:
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F /* diff 0 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0E /* diff 1 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0D, 0x0D /* diff 2 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0C, 0x0C, 0x0C /* diff 3 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x08, 0x09, 0x0A, 0x0B, 0x0B, 0x0B, 0x0B, 0x0B /* diff 4 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x08, 0x09, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A /* diff 5 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x08, 0x09, 0x09, 0x09, 0x09, 0x09, 0x09, 0x09 /* diff 6 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08 /* diff 7 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, \
- 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07 /* diff 8 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x06, \
- 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06 /* diff 9 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x05, 0x05, \
- 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05 /* diff 10 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x04, 0x04, 0x04, \
- 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04 /* diff 11 */
- .byte 0x00, 0x01, 0x02, 0x03, 0x03, 0x03, 0x03, 0x03, \
- 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03 /* diff 12 */
- .byte 0x00, 0x01, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, \
- 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02 /* diff 13 */
- .byte 0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, \
- 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01 /* diff 14 */
- .byte 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \
- 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 /* diff 15 */
-
asm_function jsimd_h2v1_downsample_neon
IMAGE_WIDTH .req x0
MAX_V_SAMP .req x1
mov TMPDUP, #0x10000
lsl TMP2, BLOCK_WIDTH, #4
sub TMP2, TMP2, IMAGE_WIDTH
- adr TMP3, Ljsimd_h2_downsample_neon_consts
+ get_symbol_loc TMP3, Ljsimd_h2_downsample_neon_consts
add TMP3, TMP3, TMP2, lsl #4
dup v16.4s, TMPDUP
ld1 {v18.16b}, [TMP3]
lsl TMP2, BLOCK_WIDTH, #4
lsl TMPDUP, TMPDUP, #17
sub TMP2, TMP2, IMAGE_WIDTH
- adr TMP3, Ljsimd_h2_downsample_neon_consts
+ get_symbol_loc TMP3, Ljsimd_h2_downsample_neon_consts
orr TMPDUP, TMPDUP, #1
add TMP3, TMP3, TMP2, lsl #4
dup v16.4s, TMPDUP
.macro generate_jsimd_huff_encode_one_block fast_tbl
-.balign 16
-.if \fast_tbl == 1
-Ljsimd_huff_encode_one_block_neon_consts:
-.else
-Ljsimd_huff_encode_one_block_neon_slowtbl_consts:
-.endif
- .byte 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, \
- 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80
-.if \fast_tbl == 1
- .byte 0, 1, 2, 3, 16, 17, 32, 33, \
- 18, 19, 4, 5, 6, 7, 20, 21 /* L0 => L3 : 4 lines OK */
- .byte 34, 35, 48, 49, 255, 255, 50, 51, \
- 36, 37, 22, 23, 8, 9, 10, 11 /* L0 => L3 : 4 lines OK */
- .byte 8, 9, 22, 23, 36, 37, 50, 51, \
- 255, 255, 255, 255, 255, 255, 52, 53 /* L1 => L4 : 4 lines OK */
- .byte 54, 55, 40, 41, 26, 27, 12, 13, \
- 14, 15, 28, 29, 42, 43, 56, 57 /* L0 => L3 : 4 lines OK */
- .byte 6, 7, 20, 21, 34, 35, 48, 49, \
- 50, 51, 36, 37, 22, 23, 8, 9 /* L4 => L7 : 4 lines OK */
- .byte 42, 43, 28, 29, 14, 15, 30, 31, \
- 44, 45, 58, 59, 255, 255, 255, 255 /* L1 => L4 : 4 lines OK */
- .byte 255, 255, 255, 255, 56, 57, 42, 43, \
- 28, 29, 14, 15, 30, 31, 44, 45 /* L3 => L6 : 4 lines OK */
- .byte 26, 27, 40, 41, 42, 43, 28, 29, \
- 14, 15, 30, 31, 44, 45, 46, 47 /* L5 => L7 : 3 lines OK */
- .byte 255, 255, 255, 255, 0, 1, 255, 255, \
- 255, 255, 255, 255, 255, 255, 255, 255 /* L4 : 1 lines OK */
- .byte 255, 255, 255, 255, 255, 255, 255, 255, \
- 0, 1, 16, 17, 2, 3, 255, 255 /* L5 => L6 : 2 lines OK */
- .byte 255, 255, 255, 255, 255, 255, 255, 255, \
- 255, 255, 255, 255, 8, 9, 22, 23 /* L5 => L6 : 2 lines OK */
- .byte 4, 5, 6, 7, 255, 255, 255, 255, \
- 255, 255, 255, 255, 255, 255, 255, 255 /* L7 : 1 line OK */
-.endif
-
.if \fast_tbl == 1
asm_function jsimd_huff_encode_one_block_neon
.else
sub BUFFER, BUFFER, #0x1 /* BUFFER=buffer-- */
/* Save ARM registers */
stp x19, x20, [sp]
-.if \fast_tbl == 1
- adr x15, Ljsimd_huff_encode_one_block_neon_consts
-.else
- adr x15, Ljsimd_huff_encode_one_block_neon_slowtbl_consts
-.endif
+ get_symbol_loc x15, Ljsimd_huff_encode_one_block_neon_consts
ldr PUT_BUFFER, [x0, #0x10]
ldr PUT_BITSw, [x0, #0x18]
ldrsh w12, [x2] /* load DC coeff in w12 */
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
test cl, SIZEOF_BYTE
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
- movzx eax, BYTE [esi+ecx]
+ movzx eax, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
- movzx edx, WORD [esi+ecx]
+ movzx edx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
xor eax, eax
- mov al, BYTE [esi+ecx]
+ mov al, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
xor edx, edx
- mov dx, WORD [esi+ecx]
+ mov dx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
test cl, SIZEOF_DWORD
jz short .column_ld8
sub ecx, byte SIZEOF_DWORD
- movd mmG, DWORD [esi+ecx]
+ movd mmG, dword [esi+ecx]
psllq mmA, DWORD_BIT
por mmA, mmG
.column_ld8:
test cl, SIZEOF_MMWORD/8
jz short .column_ld2
sub ecx, byte SIZEOF_MMWORD/8
- movd mmA, DWORD [esi+ecx*RGB_PIXELSIZE]
+ movd mmA, dword [esi+ecx*RGB_PIXELSIZE]
.column_ld2:
test cl, SIZEOF_MMWORD/4
jz short .column_ld4
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
test cl, SIZEOF_BYTE
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
- movzx eax, BYTE [esi+ecx]
+ movzx eax, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
- movzx edx, WORD [esi+ecx]
+ movzx edx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
test cl, SIZEOF_BYTE
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
- movzx eax, BYTE [esi+ecx]
+ movzx eax, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
- movzx edx, WORD [esi+ecx]
+ movzx edx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
xor eax, eax
- mov al, BYTE [esi+ecx]
+ mov al, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
xor edx, edx
- mov dx, WORD [esi+ecx]
+ mov dx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
test cl, SIZEOF_DWORD
jz short .column_ld8
sub ecx, byte SIZEOF_DWORD
- movd mmG, DWORD [esi+ecx]
+ movd mmG, dword [esi+ecx]
psllq mmA, DWORD_BIT
por mmA, mmG
.column_ld8:
test cl, SIZEOF_MMWORD/8
jz short .column_ld2
sub ecx, byte SIZEOF_MMWORD/8
- movd mmA, DWORD [esi+ecx*RGB_PIXELSIZE]
+ movd mmA, dword [esi+ecx*RGB_PIXELSIZE]
.column_ld2:
test cl, SIZEOF_MMWORD/4
jz short .column_ld4
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
test cl, SIZEOF_BYTE
jz short .column_ld2
sub ecx, byte SIZEOF_BYTE
- movzx eax, BYTE [esi+ecx]
+ movzx eax, byte [esi+ecx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub ecx, byte SIZEOF_WORD
- movzx edx, WORD [esi+ecx]
+ movzx edx, word [esi+ecx]
shl eax, WORD_BIT
or eax, edx
.column_ld4:
; This file contains an SSE2 implementation for Huffman coding of one block.
; The following code is based directly on jchuff.c; see jchuff.c for more
; details.
-;
-; [TAB8]
%include "jsimdext.inc"
push ebp
mov esi, POINTER [eax+8] ; (working_state *state)
- mov put_buffer, DWORD [esi+8] ; put_buffer = state->cur.put_buffer;
- mov put_bits, DWORD [esi+12] ; put_bits = state->cur.put_bits;
+ mov put_buffer, dword [esi+8] ; put_buffer = state->cur.put_buffer;
+ mov put_bits, dword [esi+12] ; put_bits = state->cur.put_bits;
push esi ; esi is now scratch
get_GOT edx ; get GOT address
; Encode the DC coefficient difference per section F.1.2.1
mov esi, POINTER [esp+block] ; block
movsx ecx, word [esi] ; temp = temp2 = block[0] - last_dc_val;
- sub ecx, DWORD [eax+20]
+ sub ecx, dword [eax+20]
mov esi, ecx
; This is a well-known technique for obtaining the absolute value
; For a negative input, want temp2 = bitwise complement of abs(input)
; This code assumes we are on a two's complement machine
add esi, edx ; temp2 += temp3;
- mov DWORD [esp+temp], esi ; backup temp2 in temp
+ mov dword [esp+temp], esi ; backup temp2 in temp
; Find the number of bits needed for the magnitude of the coefficient
movpic ebp, POINTER [esp+gotptr] ; load GOT address (ebp)
movzx edx, byte [GOTOFF(ebp, jpeg_nbits_table + ecx)] ; nbits = JPEG_NBITS(temp);
- mov DWORD [esp+temp2], edx ; backup nbits in temp2
+ mov dword [esp+temp2], edx ; backup nbits in temp2
; Emit the Huffman-coded symbol for the number of bits
mov ebp, POINTER [eax+24] ; After this point, arguments are not accessible anymore
movzx ecx, byte [ebp + edx + 1024] ; size = dctbl->ehufsi[nbits];
EMIT_BITS eax ; EMIT_BITS(code, size)
- mov ecx, DWORD [esp+temp2] ; restore nbits
+ mov ecx, dword [esp+temp2] ; restore nbits
; Mask off any extra bits in code
mov eax, 1
shl eax, cl
dec eax
- and eax, DWORD [esp+temp] ; temp2 &= (((JLONG)1)<<nbits) - 1;
+ and eax, dword [esp+temp] ; temp2 &= (((JLONG)1)<<nbits) - 1;
; Emit that number of bits of the value, if positive,
; or the complement of its magnitude, if negative.
jz near .ELOOP
lea esi, [esi+ecx*2] ; k += r;
shr edx, cl ; index >>= r;
- mov DWORD [esp+temp3], edx
+ mov dword [esp+temp3], edx
.BRLOOP:
cmp ecx, 16 ; while (r > 15) {
jl near .ERLOOP
sub ecx, 16 ; r -= 16;
- mov DWORD [esp+temp], ecx
+ mov dword [esp+temp], ecx
mov eax, INT [ebp + 240 * 4] ; code_0xf0 = actbl->ehufco[0xf0];
movzx ecx, byte [ebp + 1024 + 240] ; size_0xf0 = actbl->ehufsi[0xf0];
EMIT_BITS eax ; EMIT_BITS(code_0xf0, size_0xf0)
- mov ecx, DWORD [esp+temp]
+ mov ecx, dword [esp+temp]
jmp .BRLOOP
.ERLOOP:
movsx eax, word [esi] ; temp = t1[k];
movpic edx, POINTER [esp+gotptr] ; load GOT address (edx)
movzx eax, byte [GOTOFF(edx, jpeg_nbits_table + eax)] ; nbits = JPEG_NBITS(temp);
- mov DWORD [esp+temp2], eax
+ mov dword [esp+temp2], eax
; Emit Huffman symbol for run length / number of bits
shl ecx, 4 ; temp3 = (r << 4) + nbits;
add ecx, eax
movsx edx, word [esi+DCTSIZE2*2] ; temp2 = t2[k];
; Mask off any extra bits in code
- mov ecx, DWORD [esp+temp2]
+ mov ecx, dword [esp+temp2]
mov eax, 1
shl eax, cl
dec eax
and eax, edx ; temp2 &= (((JLONG)1)<<nbits) - 1;
EMIT_BITS eax ; PUT_BITS(temp2, nbits)
- mov edx, DWORD [esp+temp3]
+ mov edx, dword [esp+temp3]
add esi, 2 ; ++k;
shr edx, 1 ; index >>= 1;
shr edx, cl ; index >>= r;
add ecx, eax
lea esi, [esi+ecx*2] ; k += r;
- mov DWORD [esp+temp3], edx
+ mov dword [esp+temp3], edx
jmp .BRLOOP2
.BLOOP2:
bsf ecx, edx ; r = __builtin_ctzl(index);
jz near .ELOOP2
lea esi, [esi+ecx*2] ; k += r;
shr edx, cl ; index >>= r;
- mov DWORD [esp+temp3], edx
+ mov dword [esp+temp3], edx
.BRLOOP2:
cmp ecx, 16 ; while (r > 15) {
jl near .ERLOOP2
sub ecx, 16 ; r -= 16;
- mov DWORD [esp+temp], ecx
+ mov dword [esp+temp], ecx
mov eax, INT [ebp + 240 * 4] ; code_0xf0 = actbl->ehufco[0xf0];
movzx ecx, byte [ebp + 1024 + 240] ; size_0xf0 = actbl->ehufsi[0xf0];
EMIT_BITS eax ; EMIT_BITS(code_0xf0, size_0xf0)
- mov ecx, DWORD [esp+temp]
+ mov ecx, dword [esp+temp]
jmp .BRLOOP2
.ERLOOP2:
movsx eax, word [esi] ; temp = t1[k];
bsr eax, eax ; nbits = 32 - __builtin_clz(temp);
inc eax
- mov DWORD [esp+temp2], eax
+ mov dword [esp+temp2], eax
; Emit Huffman symbol for run length / number of bits
shl ecx, 4 ; temp3 = (r << 4) + nbits;
add ecx, eax
movsx edx, word [esi+DCTSIZE2*2] ; temp2 = t2[k];
; Mask off any extra bits in code
- mov ecx, DWORD [esp+temp2]
+ mov ecx, dword [esp+temp2]
mov eax, 1
shl eax, cl
dec eax
and eax, edx ; temp2 &= (((JLONG)1)<<nbits) - 1;
EMIT_BITS eax ; PUT_BITS(temp2, nbits)
- mov edx, DWORD [esp+temp3]
+ mov edx, dword [esp+temp3]
add esi, 2 ; ++k;
shr edx, 1 ; index >>= 1;
mov eax, [esp+buffer]
pop esi
; Save put_buffer & put_bits
- mov DWORD [esi+8], put_buffer ; state->cur.put_buffer = put_buffer;
- mov DWORD [esi+12], put_bits ; state->cur.put_bits = put_bits;
+ mov dword [esi+8], put_buffer ; state->cur.put_buffer = put_buffer;
+ mov dword [esi+12], put_bits ; state->cur.put_bits = put_bits;
pop ebp
pop edi
;
; This file contains an SSE2 implementation of data preparation for progressive
; Huffman encoding. See jcphuff.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
add LUT, 16*SIZEOF_INT
dec K
jnz .BLOOP16
+ test LEN, 15
+ je .PADDING
.ELOOP16:
mov LENEND, LEN
and LENEND, 7
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
vmovd eax, xmmA
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi], ax
+ mov word [edi], ax
add edi, byte SIZEOF_WORD
sub ecx, byte SIZEOF_WORD
shr eax, 16
; space.
test ecx, ecx
jz short .nextrow
- mov BYTE [edi], al
+ mov byte [edi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
movd eax, mmA
cmp ecx, byte SIZEOF_DWORD
jb short .column_st2
- mov DWORD [edi+0*SIZEOF_DWORD], eax
+ mov dword [edi+0*SIZEOF_DWORD], eax
psrlq mmA, DWORD_BIT
movd eax, mmA
sub ecx, byte SIZEOF_DWORD
.column_st2:
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi+0*SIZEOF_WORD], ax
+ mov word [edi+0*SIZEOF_WORD], ax
shr eax, WORD_BIT
sub ecx, byte SIZEOF_WORD
add edi, byte SIZEOF_WORD
.column_st1:
cmp ecx, byte SIZEOF_BYTE
jb short .nextrow
- mov BYTE [edi+0*SIZEOF_BYTE], al
+ mov byte [edi+0*SIZEOF_BYTE], al
%else ; RGB_PIXELSIZE == 4 ; -----------
.column_st4:
cmp ecx, byte SIZEOF_MMWORD/8
jb short .nextrow
- movd DWORD [edi+0*SIZEOF_DWORD], mmA
+ movd dword [edi+0*SIZEOF_DWORD], mmA
%endif ; RGB_PIXELSIZE ; ---------------
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
movd eax, xmmA
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi], ax
+ mov word [edi], ax
add edi, byte SIZEOF_WORD
sub ecx, byte SIZEOF_WORD
shr eax, 16
; space.
test ecx, ecx
jz short .nextrow
- mov BYTE [edi], al
+ mov byte [edi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
vmovd eax, xmmA
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi], ax
+ mov word [edi], ax
add edi, byte SIZEOF_WORD
sub ecx, byte SIZEOF_WORD
shr eax, 16
; space.
test ecx, ecx
jz short .endcolumn
- mov BYTE [edi], al
+ mov byte [edi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
movd eax, mmA
cmp ecx, byte SIZEOF_DWORD
jb short .column_st2
- mov DWORD [edi+0*SIZEOF_DWORD], eax
+ mov dword [edi+0*SIZEOF_DWORD], eax
psrlq mmA, DWORD_BIT
movd eax, mmA
sub ecx, byte SIZEOF_DWORD
.column_st2:
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi+0*SIZEOF_WORD], ax
+ mov word [edi+0*SIZEOF_WORD], ax
shr eax, WORD_BIT
sub ecx, byte SIZEOF_WORD
add edi, byte SIZEOF_WORD
.column_st1:
cmp ecx, byte SIZEOF_BYTE
jb short .endcolumn
- mov BYTE [edi+0*SIZEOF_BYTE], al
+ mov byte [edi+0*SIZEOF_BYTE], al
%else ; RGB_PIXELSIZE == 4 ; -----------
.column_st4:
cmp ecx, byte SIZEOF_MMWORD/8
jb short .endcolumn
- movd DWORD [edi+0*SIZEOF_DWORD], mmA
+ movd dword [edi+0*SIZEOF_DWORD], mmA
%endif ; RGB_PIXELSIZE ; ---------------
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
movd eax, xmmA
cmp ecx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [edi], ax
+ mov word [edi], ax
add edi, byte SIZEOF_WORD
sub ecx, byte SIZEOF_WORD
shr eax, 16
; space.
test ecx, ecx
jz short .endcolumn
- mov BYTE [edi], al
+ mov byte [edi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; This file contains a floating-point implementation of the forward DCT
; (Discrete Cosine Transform). The following code is based directly on
; the IJG's original jfdctflt.c; see the jfdctflt.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; This file contains a floating-point implementation of the forward DCT
; (Discrete Cosine Transform). The following code is based directly on
; the IJG's original jfdctflt.c; see the jfdctflt.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; the forward DCT (Discrete Cosine Transform). The following code is
; based directly on the IJG's original jfdctfst.c; see the jfdctfst.c
; for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; the forward DCT (Discrete Cosine Transform). The following code is
; based directly on the IJG's original jfdctfst.c; see the jfdctfst.c
; for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; forward DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jfdctint.c; see the jfdctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; forward DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jfdctint.c; see the jfdctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; forward DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jfdctint.c; see the jfdctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; This file contains a floating-point implementation of the inverse DCT
; (Discrete Cosine Transform). The following code is based directly on
; the IJG's original jidctflt.c; see the jidctflt.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_FLOAT_3DNOW
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz short .columnDCT
pushpic ebx ; save GOT address
- mov ebx, DWORD [DWBLOCK(3,0,esi,SIZEOF_JCOEF)]
- mov eax, DWORD [DWBLOCK(4,0,esi,SIZEOF_JCOEF)]
- or ebx, DWORD [DWBLOCK(5,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(6,0,esi,SIZEOF_JCOEF)]
- or ebx, DWORD [DWBLOCK(7,0,esi,SIZEOF_JCOEF)]
+ mov ebx, dword [DWBLOCK(3,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(4,0,esi,SIZEOF_JCOEF)]
+ or ebx, dword [DWBLOCK(5,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(6,0,esi,SIZEOF_JCOEF)]
+ or ebx, dword [DWBLOCK(7,0,esi,SIZEOF_JCOEF)]
or eax, ebx
poppic ebx ; restore GOT address
jnz short .columnDCT
; -- AC terms all zero
- movd mm0, DWORD [DWBLOCK(0,0,esi,SIZEOF_JCOEF)]
+ movd mm0, dword [DWBLOCK(0,0,esi,SIZEOF_JCOEF)]
punpcklwd mm0, mm0
psrad mm0, (DWORD_BIT-WORD_BIT)
; -- Even part
- movd mm0, DWORD [DWBLOCK(0,0,esi,SIZEOF_JCOEF)]
- movd mm1, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
- movd mm2, DWORD [DWBLOCK(4,0,esi,SIZEOF_JCOEF)]
- movd mm3, DWORD [DWBLOCK(6,0,esi,SIZEOF_JCOEF)]
+ movd mm0, dword [DWBLOCK(0,0,esi,SIZEOF_JCOEF)]
+ movd mm1, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ movd mm2, dword [DWBLOCK(4,0,esi,SIZEOF_JCOEF)]
+ movd mm3, dword [DWBLOCK(6,0,esi,SIZEOF_JCOEF)]
punpcklwd mm0, mm0
punpcklwd mm1, mm1
; -- Odd part
- movd mm2, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- movd mm3, DWORD [DWBLOCK(3,0,esi,SIZEOF_JCOEF)]
- movd mm5, DWORD [DWBLOCK(5,0,esi,SIZEOF_JCOEF)]
- movd mm1, DWORD [DWBLOCK(7,0,esi,SIZEOF_JCOEF)]
+ movd mm2, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ movd mm3, dword [DWBLOCK(3,0,esi,SIZEOF_JCOEF)]
+ movd mm5, dword [DWBLOCK(5,0,esi,SIZEOF_JCOEF)]
+ movd mm1, dword [DWBLOCK(7,0,esi,SIZEOF_JCOEF)]
punpcklwd mm2, mm2
punpcklwd mm3, mm3
; This file contains a floating-point implementation of the inverse DCT
; (Discrete Cosine Transform). The following code is based directly on
; the IJG's original jidctflt.c; see the jidctflt.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_FLOAT_SSE
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz near .columnDCT
movq mm0, MMWORD [MMBLOCK(1,0,esi,SIZEOF_JCOEF)]
; This file contains a floating-point implementation of the inverse DCT
; (Discrete Cosine Transform). The following code is based directly on
; the IJG's original jidctflt.c; see the jidctflt.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_FLOAT_SSE
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz near .columnDCT
movq xmm1, XMM_MMWORD [MMBLOCK(1,0,esi,SIZEOF_JCOEF)]
; the inverse DCT (Discrete Cosine Transform). The following code is
; based directly on the IJG's original jidctfst.c; see the jidctfst.c
; for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_IFAST_MMX
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz short .columnDCT
movq mm0, MMWORD [MMBLOCK(1,0,esi,SIZEOF_JCOEF)]
; the inverse DCT (Discrete Cosine Transform). The following code is
; based directly on the IJG's original jidctfst.c; see the jidctfst.c
; for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
mov esi, JCOEFPTR [coef_block(eax)] ; inptr
%ifndef NO_ZERO_COLUMN_TEST_IFAST_SSE2
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,esi,SIZEOF_JCOEF)]
; inverse DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jidctint.c; see the jidctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
mov esi, JCOEFPTR [coef_block(eax)] ; inptr
%ifndef NO_ZERO_COLUMN_TEST_ISLOW_AVX2
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,esi,SIZEOF_JCOEF)]
; inverse DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jidctint.c; see the jidctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_ISLOW_MMX
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz short .columnDCT
movq mm0, MMWORD [MMBLOCK(1,0,esi,SIZEOF_JCOEF)]
; inverse DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jidctint.c; see the jidctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
mov esi, JCOEFPTR [coef_block(eax)] ; inptr
%ifndef NO_ZERO_COLUMN_TEST_ISLOW_SSE2
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,esi,SIZEOF_JCOEF)]
; output: either 4x4 or 2x2 pixels from an 8x8 DCT block.
; The following code is based directly on the IJG's original jidctred.c;
; see the jidctred.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
alignx 16, 7
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_4X4_MMX
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz short .columnDCT
movq mm0, MMWORD [MMBLOCK(1,0,esi,SIZEOF_JCOEF)]
mov edx, JSAMPROW [edi+0*SIZEOF_JSAMPROW]
mov esi, JSAMPROW [edi+2*SIZEOF_JSAMPROW]
- movd DWORD [edx+eax*SIZEOF_JSAMPLE], mm1
- movd DWORD [esi+eax*SIZEOF_JSAMPLE], mm0
+ movd dword [edx+eax*SIZEOF_JSAMPLE], mm1
+ movd dword [esi+eax*SIZEOF_JSAMPLE], mm0
psrlq mm1, 4*BYTE_BIT
psrlq mm0, 4*BYTE_BIT
mov edx, JSAMPROW [edi+1*SIZEOF_JSAMPROW]
mov esi, JSAMPROW [edi+3*SIZEOF_JSAMPROW]
- movd DWORD [edx+eax*SIZEOF_JSAMPLE], mm1
- movd DWORD [esi+eax*SIZEOF_JSAMPLE], mm0
+ movd dword [edx+eax*SIZEOF_JSAMPLE], mm1
+ movd dword [esi+eax*SIZEOF_JSAMPLE], mm0
emms ; empty MMX state
mov edx, JSAMPROW [edi+0*SIZEOF_JSAMPROW]
mov esi, JSAMPROW [edi+1*SIZEOF_JSAMPROW]
- mov WORD [edx+eax*SIZEOF_JSAMPLE], bx
- mov WORD [esi+eax*SIZEOF_JSAMPLE], cx
+ mov word [edx+eax*SIZEOF_JSAMPLE], bx
+ mov word [esi+eax*SIZEOF_JSAMPLE], cx
emms ; empty MMX state
; output: either 4x4 or 2x2 pixels from an 8x8 DCT block.
; The following code is based directly on the IJG's original jidctred.c;
; see the jidctred.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
mov esi, JCOEFPTR [coef_block(eax)] ; inptr
%ifndef NO_ZERO_COLUMN_TEST_4X4_SSE2
- mov eax, DWORD [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,esi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,esi,SIZEOF_JCOEF)]
jnz short .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,esi,SIZEOF_JCOEF)]
mov edx, JSAMPROW [edi+0*SIZEOF_JSAMPROW]
mov esi, JSAMPROW [edi+1*SIZEOF_JSAMPROW]
- mov WORD [edx+eax*SIZEOF_JSAMPLE], bx
- mov WORD [esi+eax*SIZEOF_JSAMPLE], cx
+ mov word [edx+eax*SIZEOF_JSAMPLE], bx
+ mov word [esi+eax*SIZEOF_JSAMPLE], cx
pop edi
pop esi
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
xor eax, edx
jz near .return ; CPUID is not supported
- ; Check for MMX instruction support
+ ; Check whether CPUID leaf 07H is supported
+ ; (leaf 07H is used to check for AVX2 instruction support)
xor eax, eax
cpuid
test eax, eax
jz near .return
-
- xor eax, eax
- inc eax
- cpuid
- mov eax, edx ; eax = Standard feature flags
-
- test eax, 1<<23 ; bit23:MMX
- jz short .no_mmx
- or edi, byte JSIMD_MMX
-.no_mmx:
- test eax, 1<<25 ; bit25:SSE
- jz short .no_sse
- or edi, byte JSIMD_SSE
-.no_sse:
- test eax, 1<<26 ; bit26:SSE2
- jz short .no_sse2
- or edi, byte JSIMD_SSE2
-.no_sse2:
+ cmp eax, 7
+ jl short .no_avx2 ; Maximum leaf < 07H
; Check for AVX2 instruction support
mov eax, 7
or edi, JSIMD_AVX2
.no_avx2:
+ ; Check CPUID leaf 01H for MMX, SSE, and SSE2 support
+ xor eax, eax
+ inc eax
+ cpuid
+ mov eax, edx ; eax = Standard feature flags
+
+ ; Check for MMX instruction support
+ test eax, 1<<23 ; bit23:MMX
+ jz short .no_mmx
+ or edi, byte JSIMD_MMX
+.no_mmx:
+ test eax, 1<<25 ; bit25:SSE
+ jz short .no_sse
+ or edi, byte JSIMD_SSE
+.no_sse:
+ test eax, 1<<26 ; bit26:SSE2
+ jz short .no_sse2
+ or edi, byte JSIMD_SSE2
+.no_sse2:
+
; Check for 3DNow! instruction support
mov eax, 0x80000000
cpuid
* Loongson MMI optimizations for libjpeg-turbo
*
* Copyright 2009 Pierre Ossman <ossman@cendio.se> for Cendio AB
- * Copyright (C) 2014-2015, D. R. Commander. All Rights Reserved.
- * Copyright (C) 2016-2017, Loongson Technology Corporation Limited, BeiJing.
+ * Copyright (C) 2014-2015, 2019, D. R. Commander. All Rights Reserved.
+ * Copyright (C) 2016-2018, Loongson Technology Corporation Limited, BeiJing.
* All Rights Reserved.
* Authors: ZhuChen <zhuchen@loongson.cn>
* SunZhangzhi <sunzhangzhi-cq@loongson.cn>
* CaiWanwei <caiwanwei@loongson.cn>
+ * ZhangLixia <zhanglixia-hf@loongson.cn>
*
* Based on the x86 SIMD extension for IJG JPEG library
* Copyright (C) 1999-2006, MIYASAKA Masaru.
"$14", "memory"
);
} else {
- mmA = _mm_load_si64((__m64 *)&inptr[0]);
- mmG = _mm_load_si64((__m64 *)&inptr[8]);
- mmF = _mm_load_si64((__m64 *)&inptr[16]);
+ if (!(((long)inptr) & 7)) {
+ mmA = _mm_load_si64((__m64 *)&inptr[0]);
+ mmG = _mm_load_si64((__m64 *)&inptr[8]);
+ mmF = _mm_load_si64((__m64 *)&inptr[16]);
+ } else {
+ mmA = _mm_loadu_si64((__m64 *)&inptr[0]);
+ mmG = _mm_loadu_si64((__m64 *)&inptr[8]);
+ mmF = _mm_loadu_si64((__m64 *)&inptr[16]);
+ }
inptr += RGB_PIXELSIZE * 8;
}
mmD = mmA;
: "$f0", "$f2", "$8", "$9", "$10", "$11", "$13", "memory"
);
} else {
- mmA = _mm_load_si64((__m64 *)&inptr[0]);
- mmF = _mm_load_si64((__m64 *)&inptr[8]);
- mmD = _mm_load_si64((__m64 *)&inptr[16]);
- mmC = _mm_load_si64((__m64 *)&inptr[24]);
+ if (!(((long)inptr) & 7)) {
+ mmA = _mm_load_si64((__m64 *)&inptr[0]);
+ mmF = _mm_load_si64((__m64 *)&inptr[8]);
+ mmD = _mm_load_si64((__m64 *)&inptr[16]);
+ mmC = _mm_load_si64((__m64 *)&inptr[24]);
+ } else {
+ mmA = _mm_loadu_si64((__m64 *)&inptr[0]);
+ mmF = _mm_loadu_si64((__m64 *)&inptr[8]);
+ mmD = _mm_loadu_si64((__m64 *)&inptr[16]);
+ mmC = _mm_loadu_si64((__m64 *)&inptr[24]);
+ }
inptr += RGB_PIXELSIZE * 8;
}
mmB = mmA;
/*
* Loongson MMI optimizations for libjpeg-turbo
*
- * Copyright (C) 2016-2017, Loongson Technology Corporation Limited, BeiJing.
+ * Copyright (C) 2016-2018, Loongson Technology Corporation Limited, BeiJing.
* All Rights Reserved.
+ * Copyright (C) 2019, D. R. Commander. All Rights Reserved.
*
* This software is provided 'as-is', without any express or implied
* warranty. In no event will the authors be held liable for any damages
/********** Set Operations **********/
-extern __inline __m64
+extern __inline __m64 FUNCTION_ATTRIBS
_mm_setzero_si64(void)
{
return 0.0;
asm("ldc1 %0, %1\n\t"
: "=f" (ret)
: "m" (*src)
+ : "memory"
+ );
+
+ return ret;
+}
+
+extern __inline __m64 FUNCTION_ATTRIBS
+_mm_loadu_si64(const __m64 *src)
+{
+ __m64 ret;
+
+ asm("gsldlc1 %0, 7(%1)\n\t"
+ "gsldrc1 %0, 0(%1)\n\t"
+ : "=f" (ret)
+ : "r" (src)
+ : "memory"
);
return ret;
; Based on the x86 SIMD extension for IJG JPEG library
; Copyright (C) 1999-2006, MIYASAKA Masaru.
; For conditions of distribution and use, see copyright notice in jsimdext.inc
-;
-; [TAB8]
; --------------------------------------------------------------------------
; Based on the x86 SIMD extension for IJG JPEG library
; Copyright (C) 1999-2006, MIYASAKA Masaru.
; For conditions of distribution and use, see copyright notice in jsimdext.inc
-;
-; [TAB8]
; Each IDCT routine is responsible for range-limiting its results and
; converting them to unsigned form (0..MAXJSAMPLE). The raw outputs could
; jsimdext.inc - common declarations
;
; Copyright 2009 Pierre Ossman <ossman@cendio.se> for Cendio AB
-; Copyright (C) 2010, 2016, D. R. Commander.
+; Copyright (C) 2010, 2016, 2019, D. R. Commander.
; Copyright (C) 2018, Matthieu Darbois.
;
; Based on the x86 SIMD extension for IJG JPEG library - version 1.02
; 2. Altered source versions must be plainly marked as such, and must not be
; misrepresented as being the original software.
; 3. This notice may not be removed or altered from any source distribution.
-;
-; [TAB8]
; ==========================================================================
; System-dependent configurations
%define XMM_DWORD
%define XMM_MMWORD
-%define SIZEOF_BYTE 1 ; sizeof(BYTE)
-%define SIZEOF_WORD 2 ; sizeof(WORD)
-%define SIZEOF_DWORD 4 ; sizeof(DWORD)
-%define SIZEOF_QWORD 8 ; sizeof(QWORD)
-%define SIZEOF_OWORD 16 ; sizeof(OWORD)
-%define SIZEOF_YWORD 32 ; sizeof(YWORD)
+%define SIZEOF_BYTE 1 ; sizeof(byte)
+%define SIZEOF_WORD 2 ; sizeof(word)
+%define SIZEOF_DWORD 4 ; sizeof(dword)
+%define SIZEOF_QWORD 8 ; sizeof(qword)
+%define SIZEOF_OWORD 16 ; sizeof(oword)
+%define SIZEOF_YWORD 32 ; sizeof(yword)
%define BYTE_BIT 8 ; CHAR_BIT in C
-%define WORD_BIT 16 ; sizeof(WORD)*BYTE_BIT
-%define DWORD_BIT 32 ; sizeof(DWORD)*BYTE_BIT
-%define QWORD_BIT 64 ; sizeof(QWORD)*BYTE_BIT
-%define OWORD_BIT 128 ; sizeof(OWORD)*BYTE_BIT
-%define YWORD_BIT 256 ; sizeof(YWORD)*BYTE_BIT
+%define WORD_BIT 16 ; sizeof(word)*BYTE_BIT
+%define DWORD_BIT 32 ; sizeof(dword)*BYTE_BIT
+%define QWORD_BIT 64 ; sizeof(qword)*BYTE_BIT
+%define OWORD_BIT 128 ; sizeof(oword)*BYTE_BIT
+%define YWORD_BIT 256 ; sizeof(yword)*BYTE_BIT
; --------------------------------------------------------------------------
; External Symbol Name
%ifdef __YASM_VER__
%define GLOBAL_FUNCTION(name) global EXTN(name):private_extern
%define GLOBAL_DATA(name) global EXTN(name):private_extern
+%else
+%if __NASM_VERSION_ID__ >= 0x020E0000
+%define GLOBAL_FUNCTION(name) global EXTN(name):private_extern
+%define GLOBAL_DATA(name) global EXTN(name):private_extern
+%endif
%endif
%endif
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
test cl, SIZEOF_BYTE
jz short .column_ld2
sub rcx, byte SIZEOF_BYTE
- movzx rax, BYTE [rsi+rcx]
+ movzx rax, byte [rsi+rcx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub rcx, byte SIZEOF_WORD
- movzx rdx, WORD [rsi+rcx]
+ movzx rdx, word [rsi+rcx]
shl rax, WORD_BIT
or rax, rdx
.column_ld4:
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
test cl, SIZEOF_BYTE
jz short .column_ld2
sub rcx, byte SIZEOF_BYTE
- movzx rax, BYTE [rsi+rcx]
+ movzx rax, byte [rsi+rcx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub rcx, byte SIZEOF_WORD
- movzx rdx, WORD [rsi+rcx]
+ movzx rdx, word [rsi+rcx]
shl rax, WORD_BIT
or rax, rdx
.column_ld4:
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
test cl, SIZEOF_BYTE
jz short .column_ld2
sub rcx, byte SIZEOF_BYTE
- movzx rax, BYTE [rsi+rcx]
+ movzx rax, byte [rsi+rcx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub rcx, byte SIZEOF_WORD
- movzx rdx, WORD [rsi+rcx]
+ movzx rdx, word [rsi+rcx]
shl rax, WORD_BIT
or rax, rdx
.column_ld4:
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
test cl, SIZEOF_BYTE
jz short .column_ld2
sub rcx, byte SIZEOF_BYTE
- movzx rax, BYTE [rsi+rcx]
+ movzx rax, byte [rsi+rcx]
.column_ld2:
test cl, SIZEOF_WORD
jz short .column_ld4
sub rcx, byte SIZEOF_WORD
- movzx rdx, WORD [rsi+rcx]
+ movzx rdx, word [rsi+rcx]
shl rax, WORD_BIT
or rax, rdx
.column_ld4:
; This file contains an SSE2 implementation for Huffman coding of one block.
; The following code is based directly on jchuff.c; see jchuff.c for more
; details.
-;
-; [TAB8]
%include "jsimdext.inc"
mov buffer, r11 ; r11 is now sratch
mov put_buffer, MMWORD [r10+16] ; put_buffer = state->cur.put_buffer;
- mov put_bits, DWORD [r10+24] ; put_bits = state->cur.put_bits;
+ mov put_bits, dword [r10+24] ; put_bits = state->cur.put_bits;
push r10 ; r10 is now scratch
; Encode the DC coefficient difference per section F.1.2.1
pop r10
; Save put_buffer & put_bits
mov MMWORD [r10+16], put_buffer ; state->cur.put_buffer = put_buffer;
- mov DWORD [r10+24], put_bits ; state->cur.put_bits = put_bits;
+ mov dword [r10+24], put_bits ; state->cur.put_bits = put_bits;
pop rbx
uncollect_args 6
;
; This file contains an SSE2 implementation of data preparation for progressive
; Huffman encoding. See jcphuff.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
add LUT, 16*SIZEOF_INT
dec K
jnz .BLOOP16
+ test LEN, 15
+ je .PADDING
.ELOOP16:
test LEN, 8
jz .TRY7
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
vmovd eax, xmmA
cmp rcx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [rdi], ax
+ mov word [rdi], ax
add rdi, byte SIZEOF_WORD
sub rcx, byte SIZEOF_WORD
shr rax, 16
; space.
test rcx, rcx
jz short .nextrow
- mov BYTE [rdi], al
+ mov byte [rdi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
movd eax, xmmA
cmp rcx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [rdi], ax
+ mov word [rdi], ax
add rdi, byte SIZEOF_WORD
sub rcx, byte SIZEOF_WORD
shr rax, 16
; space.
test rcx, rcx
jz short .nextrow
- mov BYTE [rdi], al
+ mov byte [rdi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
vmovd eax, xmmA
cmp rcx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [rdi], ax
+ mov word [rdi], ax
add rdi, byte SIZEOF_WORD
sub rcx, byte SIZEOF_WORD
shr rax, 16
; space.
test rcx, rcx
jz short .endcolumn
- mov BYTE [rdi], al
+ mov byte [rdi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jcolsamp.inc"
movd eax, xmmA
cmp rcx, byte SIZEOF_WORD
jb short .column_st1
- mov WORD [rdi], ax
+ mov word [rdi], ax
add rdi, byte SIZEOF_WORD
sub rcx, byte SIZEOF_WORD
shr rax, 16
; space.
test rcx, rcx
jz short .endcolumn
- mov BYTE [rdi], al
+ mov byte [rdi], al
%else ; RGB_PIXELSIZE == 4 ; -----------
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
; This file contains a floating-point implementation of the forward DCT
; (Discrete Cosine Transform). The following code is based directly on
; the IJG's original jfdctflt.c; see the jfdctflt.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; the forward DCT (Discrete Cosine Transform). The following code is
; based directly on the IJG's original jfdctfst.c; see the jfdctfst.c
; for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; forward DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jfdctint.c; see the jfdctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; forward DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jfdctint.c; see the jfdctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; This file contains a floating-point implementation of the inverse DCT
; (Discrete Cosine Transform). The following code is based directly on
; the IJG's original jidctflt.c; see the jidctflt.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
mov rcx, DCTSIZE/4 ; ctr
.columnloop:
%ifndef NO_ZERO_COLUMN_TEST_FLOAT_SSE
- mov eax, DWORD [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
jnz near .columnDCT
movq xmm1, XMM_MMWORD [MMBLOCK(1,0,rsi,SIZEOF_JCOEF)]
; the inverse DCT (Discrete Cosine Transform). The following code is
; based directly on the IJG's original jidctfst.c; see the jidctfst.c
; for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
mov rsi, r11 ; inptr
%ifndef NO_ZERO_COLUMN_TEST_IFAST_SSE2
- mov eax, DWORD [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,rsi,SIZEOF_JCOEF)]
; inverse DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jidctint.c; see the jidctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; ---- Pass 1: process columns.
%ifndef NO_ZERO_COLUMN_TEST_ISLOW_AVX2
- mov eax, DWORD [DWBLOCK(1,0,r11,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,r11,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,r11,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,r11,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,r11,SIZEOF_JCOEF)]
; inverse DCT (Discrete Cosine Transform). The following code is based
; directly on the IJG's original jidctint.c; see the jidctint.c for
; more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
mov rsi, r11 ; inptr
%ifndef NO_ZERO_COLUMN_TEST_ISLOW_SSE2
- mov eax, DWORD [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
jnz near .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,rsi,SIZEOF_JCOEF)]
; output: either 4x4 or 2x2 pixels from an 8x8 DCT block.
; The following code is based directly on the IJG's original jidctred.c;
; see the jidctred.c for more details.
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
mov rsi, r11 ; inptr
%ifndef NO_ZERO_COLUMN_TEST_4X4_SSE2
- mov eax, DWORD [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
- or eax, DWORD [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
+ mov eax, dword [DWBLOCK(1,0,rsi,SIZEOF_JCOEF)]
+ or eax, dword [DWBLOCK(2,0,rsi,SIZEOF_JCOEF)]
jnz short .columnDCT
movdqa xmm0, XMMWORD [XMMBLOCK(1,0,rsi,SIZEOF_JCOEF)]
mov rdx, JSAMPROW [rdi+0*SIZEOF_JSAMPROW]
mov rsi, JSAMPROW [rdi+1*SIZEOF_JSAMPROW]
- mov WORD [rdx+rax*SIZEOF_JSAMPLE], bx
- mov WORD [rsi+rax*SIZEOF_JSAMPLE], cx
+ mov word [rdx+rax*SIZEOF_JSAMPLE], bx
+ mov word [rsi+rax*SIZEOF_JSAMPLE], cx
pop rbx
uncollect_args 4
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
%include "jdct.inc"
; assembler (including Borland's Turbo Assembler).
; NASM is available from http://nasm.sourceforge.net/ or
; http://sourceforge.net/project/showfiles.php?group_id=6208
-;
-; [TAB8]
%include "jsimdext.inc"
xor rdi, rdi ; simd support flag
+ ; Assume that all x86-64 processors support SSE & SSE2 instructions
+ or rdi, JSIMD_SSE2
+ or rdi, JSIMD_SSE
+
+ ; Check whether CPUID leaf 07H is supported
+ ; (leaf 07H is used to check for AVX2 instruction support)
+ mov rax, 0
+ cpuid
+ cmp rax, 7
+ jl short .return ; Maximum leaf < 07H
+
; Check for AVX2 instruction support
mov rax, 7
xor rcx, rcx
cpuid
mov rax, rbx ; rax = Extended feature flags
- or rdi, JSIMD_SSE2
- or rdi, JSIMD_SSE
test rax, 1<<5 ; bit5:AVX2
jz short .return
--- /dev/null
+0 1 2: 0 0 0 0;
+0: 1 16 0 0;
+0: 17 63 0 0;
+1: 1 63 0 0;
+2: 1 63 0 0;
/*
- * Copyright (C)2009-2018 D. R. Commander. All Rights Reserved.
+ * Copyright (C)2009-2019 D. R. Commander. All Rights Reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
#include <ctype.h>
#include <math.h>
#include <errno.h>
+#include <limits.h>
#include <cdjpeg.h>
#include "./tjutil.h"
#include "./turbojpeg.h"
-#define _throw(op, err) { \
+#define THROW(op, err) { \
printf("ERROR in line %d while %s:\n%s\n", __LINE__, op, err); \
retval = -1; goto bailout; \
}
-#define _throwunix(m) _throw(m, strerror(errno))
+#define THROW_UNIX(m) THROW(m, strerror(errno))
char tjErrorStr[JMSG_LENGTH_MAX] = "\0", tjErrorMsg[JMSG_LENGTH_MAX] = "\0";
int tjErrorLine = -1, tjErrorCode = -1;
-#define _throwtjg(m) { \
+#define THROW_TJG(m) { \
printf("ERROR in line %d while %s:\n%s\n", __LINE__, m, \
tjGetErrorStr2(NULL)); \
retval = -1; goto bailout; \
}
-#define _throwtj(m) { \
+#define THROW_TJ(m) { \
int _tjErrorCode = tjGetErrorCode(handle); \
char *_tjErrorStr = tjGetErrorStr2(handle); \
\
double benchTime = 5.0, warmup = 1.0;
-char *formatName(int subsamp, int cs, char *buf)
+static char *formatName(int subsamp, int cs, char *buf)
{
if (cs == TJCS_YCbCr)
return (char *)subNameLong[subsamp];
}
-char *sigfig(double val, int figs, char *buf, int len)
+static char *sigfig(double val, int figs, char *buf, int len)
{
char format[80];
int digitsAfterDecimal = figs - (int)ceil(log10(fabs(val)));
/* Custom DCT filter which produces a negative of the image */
-int dummyDCTFilter(short *coeffs, tjregion arrayRegion, tjregion planeRegion,
- int componentIndex, int transformIndex,
- tjtransform *transform)
+static int dummyDCTFilter(short *coeffs, tjregion arrayRegion,
+ tjregion planeRegion, int componentIndex,
+ int transformIndex, tjtransform *transform)
{
int i;
/* Decompression test */
-int decomp(unsigned char *srcBuf, unsigned char **jpegBuf,
- unsigned long *jpegSize, unsigned char *dstBuf, int w, int h,
- int subsamp, int jpegQual, char *fileName, int tilew, int tileh)
+static int decomp(unsigned char *srcBuf, unsigned char **jpegBuf,
+ unsigned long *jpegSize, unsigned char *dstBuf, int w, int h,
+ int subsamp, int jpegQual, char *fileName, int tilew,
+ int tileh)
{
- char tempStr[1024], sizeStr[20] = "\0", qualStr[6] = "\0", *ptr;
+ char tempStr[1024], sizeStr[24] = "\0", qualStr[13] = "\0", *ptr;
FILE *file = NULL;
tjhandle handle = NULL;
int row, col, iter = 0, dstBufAlloc = 0, retval = 0;
unsigned char *dstPtr, *dstPtr2, *yuvBuf = NULL;
if (jpegQual > 0) {
- snprintf(qualStr, 6, "_Q%d", jpegQual);
- qualStr[5] = 0;
+ snprintf(qualStr, 13, "_Q%d", jpegQual);
+ qualStr[12] = 0;
}
if ((handle = tjInitDecompress()) == NULL)
- _throwtj("executing tjInitDecompress()");
+ THROW_TJ("executing tjInitDecompress()");
if (dstBuf == NULL) {
- if ((dstBuf = (unsigned char *)malloc(pitch * scaledh)) == NULL)
- _throwunix("allocating destination buffer");
+ if ((unsigned long long)pitch * (unsigned long long)scaledh >
+ (unsigned long long)((size_t)-1))
+ THROW("allocating destination buffer", "Image is too large");
+ if ((dstBuf = (unsigned char *)malloc((size_t)pitch * scaledh)) == NULL)
+ THROW_UNIX("allocating destination buffer");
dstBufAlloc = 1;
}
/* Set the destination buffer to gray so we know whether the decompressor
attempted to write to it */
- memset(dstBuf, 127, pitch * scaledh);
+ memset(dstBuf, 127, (size_t)pitch * scaledh);
if (doYUV) {
int width = doTile ? tilew : scaledw;
int height = doTile ? tileh : scaledh;
- int yuvSize = tjBufSizeYUV2(width, yuvPad, height, subsamp);
+ unsigned long yuvSize = tjBufSizeYUV2(width, yuvPad, height, subsamp);
+ if (yuvSize == (unsigned long)-1)
+ THROW_TJ("allocating YUV buffer");
if ((yuvBuf = (unsigned char *)malloc(yuvSize)) == NULL)
- _throwunix("allocating YUV buffer");
+ THROW_UNIX("allocating YUV buffer");
memset(yuvBuf, 127, yuvSize);
}
double start = getTime();
for (row = 0, dstPtr = dstBuf; row < ntilesh;
- row++, dstPtr += pitch * tileh) {
+ row++, dstPtr += (size_t)pitch * tileh) {
for (col = 0, dstPtr2 = dstPtr; col < ntilesw;
col++, tile++, dstPtr2 += ps * tilew) {
int width = doTile ? min(tilew, w - col * tilew) : scaledw;
if (tjDecompressToYUV2(handle, jpegBuf[tile], jpegSize[tile], yuvBuf,
width, yuvPad, height, flags) == -1)
- _throwtj("executing tjDecompressToYUV2()");
+ THROW_TJ("executing tjDecompressToYUV2()");
startDecode = getTime();
if (tjDecodeYUV(handle, yuvBuf, yuvPad, subsamp, dstPtr2, width,
pitch, height, pf, flags) == -1)
- _throwtj("executing tjDecodeYUV()");
+ THROW_TJ("executing tjDecodeYUV()");
if (iter >= 0) elapsedDecode += getTime() - startDecode;
} else if (tjDecompress2(handle, jpegBuf[tile], jpegSize[tile],
dstPtr2, width, pitch, height, pf,
flags) == -1)
- _throwtj("executing tjDecompress2()");
+ THROW_TJ("executing tjDecompress2()");
}
}
elapsed += getTime() - start;
}
if (doYUV) elapsed -= elapsedDecode;
- if (tjDestroy(handle) == -1) _throwtj("executing tjDestroy()");
+ if (tjDestroy(handle) == -1) THROW_TJ("executing tjDestroy()");
handle = NULL;
if (quiet) {
if (!doWrite) goto bailout;
if (sf.num != 1 || sf.denom != 1)
- snprintf(sizeStr, 20, "%d_%d", sf.num, sf.denom);
+ snprintf(sizeStr, 24, "%d_%d", sf.num, sf.denom);
else if (tilew != w || tileh != h)
- snprintf(sizeStr, 20, "%dx%d", tilew, tileh);
- else snprintf(sizeStr, 20, "full");
+ snprintf(sizeStr, 24, "%dx%d", tilew, tileh);
+ else snprintf(sizeStr, 24, "full");
if (decompOnly)
snprintf(tempStr, 1024, "%s_%s.%s", fileName, sizeStr, ext);
else
qualStr, sizeStr, ext);
if (tjSaveImage(tempStr, dstBuf, scaledw, 0, scaledh, pf, flags) == -1)
- _throwtjg("saving bitmap");
+ THROW_TJG("saving bitmap");
ptr = strrchr(tempStr, '.');
snprintf(ptr, 1024 - (ptr - tempStr), "-err.%s", ext);
if (srcBuf && sf.num == 1 && sf.denom == 1) {
if (!quiet) printf("Compression error written to %s.\n", tempStr);
if (subsamp == TJ_GRAYSCALE) {
- int index, index2;
+ unsigned long index, index2;
for (row = 0, index = 0; row < h; row++, index += pitch) {
for (col = 0, index2 = index; col < w; col++, index2 += ps) {
- int rindex = index2 + tjRedOffset[pf];
- int gindex = index2 + tjGreenOffset[pf];
- int bindex = index2 + tjBlueOffset[pf];
+ unsigned long rindex = index2 + tjRedOffset[pf];
+ unsigned long gindex = index2 + tjGreenOffset[pf];
+ unsigned long bindex = index2 + tjBlueOffset[pf];
int y = (int)((double)srcBuf[rindex] * 0.299 +
(double)srcBuf[gindex] * 0.587 +
(double)srcBuf[bindex] * 0.114 + 0.5);
abs(dstBuf[pitch * row + col] - srcBuf[pitch * row + col]);
}
if (tjSaveImage(tempStr, dstBuf, w, 0, h, pf, flags) == -1)
- _throwtjg("saving bitmap");
+ THROW_TJG("saving bitmap");
}
bailout:
}
-int fullTest(unsigned char *srcBuf, int w, int h, int subsamp, int jpegQual,
- char *fileName)
+static int fullTest(unsigned char *srcBuf, int w, int h, int subsamp,
+ int jpegQual, char *fileName)
{
char tempStr[1024], tempStr2[80];
FILE *file = NULL;
*srcPtr2;
double start, elapsed, elapsedEncode;
int totalJpegSize = 0, row, col, i, tilew = w, tileh = h, retval = 0;
- int iter, yuvSize = 0;
- unsigned long *jpegSize = NULL;
+ int iter;
+ unsigned long *jpegSize = NULL, yuvSize = 0;
int ps = tjPixelSize[pf];
int ntilesw = 1, ntilesh = 1, pitch = w * ps;
const char *pfStr = pixFormatStr[pf];
- if ((tmpBuf = (unsigned char *)malloc(pitch * h)) == NULL)
- _throwunix("allocating temporary image buffer");
+ if ((unsigned long long)pitch * (unsigned long long)h >
+ (unsigned long long)((size_t)-1))
+ THROW("allocating temporary image buffer", "Image is too large");
+ if ((tmpBuf = (unsigned char *)malloc((size_t)pitch * h)) == NULL)
+ THROW_UNIX("allocating temporary image buffer");
if (!quiet)
printf(">>>>> %s (%s) <--> JPEG %s Q%d <<<<<\n", pfStr,
if ((jpegBuf = (unsigned char **)malloc(sizeof(unsigned char *) *
ntilesw * ntilesh)) == NULL)
- _throwunix("allocating JPEG tile array");
+ THROW_UNIX("allocating JPEG tile array");
memset(jpegBuf, 0, sizeof(unsigned char *) * ntilesw * ntilesh);
if ((jpegSize = (unsigned long *)malloc(sizeof(unsigned long) *
ntilesw * ntilesh)) == NULL)
- _throwunix("allocating JPEG size array");
+ THROW_UNIX("allocating JPEG size array");
memset(jpegSize, 0, sizeof(unsigned long) * ntilesw * ntilesh);
if ((flags & TJFLAG_NOREALLOC) != 0)
for (i = 0; i < ntilesw * ntilesh; i++) {
+ if (tjBufSize(tilew, tileh, subsamp) > (unsigned long)INT_MAX)
+ THROW("getting buffer size", "Image is too large");
if ((jpegBuf[i] = (unsigned char *)
tjAlloc(tjBufSize(tilew, tileh, subsamp))) == NULL)
- _throwunix("allocating JPEG tiles");
+ THROW_UNIX("allocating JPEG tiles");
}
/* Compression test */
for (i = 0; i < h; i++)
memcpy(&tmpBuf[pitch * i], &srcBuf[w * ps * i], w * ps);
if ((handle = tjInitCompress()) == NULL)
- _throwtj("executing tjInitCompress()");
+ THROW_TJ("executing tjInitCompress()");
if (doYUV) {
yuvSize = tjBufSizeYUV2(tilew, yuvPad, tileh, subsamp);
+ if (yuvSize == (unsigned long)-1)
+ THROW_TJ("allocating YUV buffer");
if ((yuvBuf = (unsigned char *)malloc(yuvSize)) == NULL)
- _throwunix("allocating YUV buffer");
+ THROW_UNIX("allocating YUV buffer");
memset(yuvBuf, 127, yuvSize);
}
if (tjEncodeYUV3(handle, srcPtr2, width, pitch, height, pf, yuvBuf,
yuvPad, subsamp, flags) == -1)
- _throwtj("executing tjEncodeYUV3()");
+ THROW_TJ("executing tjEncodeYUV3()");
if (iter >= 0) elapsedEncode += getTime() - startEncode;
if (tjCompressFromYUV(handle, yuvBuf, width, yuvPad, height,
subsamp, &jpegBuf[tile], &jpegSize[tile],
jpegQual, flags) == -1)
- _throwtj("executing tjCompressFromYUV()");
+ THROW_TJ("executing tjCompressFromYUV()");
} else {
if (tjCompress2(handle, srcPtr2, width, pitch, height, pf,
&jpegBuf[tile], &jpegSize[tile], subsamp, jpegQual,
flags) == -1)
- _throwtj("executing tjCompress2()");
+ THROW_TJ("executing tjCompress2()");
}
totalJpegSize += jpegSize[tile];
}
}
if (doYUV) elapsed -= elapsedEncode;
- if (tjDestroy(handle) == -1) _throwtj("executing tjDestroy()");
+ if (tjDestroy(handle) == -1) THROW_TJ("executing tjDestroy()");
handle = NULL;
if (quiet == 1) printf("%-5d %-5d ", tilew, tileh);
if (doYUV) {
printf("Encode YUV --> Frame rate: %f fps\n",
(double)iter / elapsedEncode);
- printf(" Output image size: %d bytes\n", yuvSize);
+ printf(" Output image size: %lu bytes\n", yuvSize);
printf(" Compression ratio: %f:1\n",
(double)(w * h * ps) / (double)yuvSize);
printf(" Throughput: %f Megapixels/sec\n",
snprintf(tempStr, 1024, "%s_%s_Q%d.jpg", fileName, subName[subsamp],
jpegQual);
if ((file = fopen(tempStr, "wb")) == NULL)
- _throwunix("opening reference image");
+ THROW_UNIX("opening reference image");
if (fwrite(jpegBuf[0], jpegSize[0], 1, file) != 1)
- _throwunix("writing reference image");
+ THROW_UNIX("writing reference image");
fclose(file); file = NULL;
if (!quiet) printf("Reference image written to %s\n", tempStr);
}
if (decomp(srcBuf, jpegBuf, jpegSize, tmpBuf, w, h, subsamp, jpegQual,
fileName, tilew, tileh) == -1)
goto bailout;
- }
+ } else if (quiet == 1) printf("N/A\n");
for (i = 0; i < ntilesw * ntilesh; i++) {
if (jpegBuf[i]) tjFree(jpegBuf[i]);
}
-int decompTest(char *fileName)
+static int decompTest(char *fileName)
{
FILE *file = NULL;
tjhandle handle = NULL;
int tw, th, ttilew, ttileh, tntilesw, tntilesh, tsubsamp;
if ((file = fopen(fileName, "rb")) == NULL)
- _throwunix("opening file");
+ THROW_UNIX("opening file");
if (fseek(file, 0, SEEK_END) < 0 ||
(srcSize = ftell(file)) == (unsigned long)-1)
- _throwunix("determining file size");
+ THROW_UNIX("determining file size");
if ((srcBuf = (unsigned char *)malloc(srcSize)) == NULL)
- _throwunix("allocating memory");
+ THROW_UNIX("allocating memory");
if (fseek(file, 0, SEEK_SET) < 0)
- _throwunix("setting file position");
+ THROW_UNIX("setting file position");
if (fread(srcBuf, srcSize, 1, file) < 1)
- _throwunix("reading JPEG data");
+ THROW_UNIX("reading JPEG data");
fclose(file); file = NULL;
temp = strrchr(fileName, '.');
if (temp != NULL) *temp = '\0';
if ((handle = tjInitTransform()) == NULL)
- _throwtj("executing tjInitTransform()");
+ THROW_TJ("executing tjInitTransform()");
if (tjDecompressHeader3(handle, srcBuf, srcSize, &w, &h, &subsamp,
&cs) == -1)
- _throwtj("executing tjDecompressHeader3()");
+ THROW_TJ("executing tjDecompressHeader3()");
+ if (w < 1 || h < 1)
+ THROW("reading JPEG header", "Invalid image dimensions");
if (cs == TJCS_YCCK || cs == TJCS_CMYK) {
pf = TJPF_CMYK; ps = tjPixelSize[pf];
}
if ((jpegBuf = (unsigned char **)malloc(sizeof(unsigned char *) *
ntilesw * ntilesh)) == NULL)
- _throwunix("allocating JPEG tile array");
+ THROW_UNIX("allocating JPEG tile array");
memset(jpegBuf, 0, sizeof(unsigned char *) * ntilesw * ntilesh);
if ((jpegSize = (unsigned long *)malloc(sizeof(unsigned long) *
ntilesw * ntilesh)) == NULL)
- _throwunix("allocating JPEG size array");
+ THROW_UNIX("allocating JPEG size array");
memset(jpegSize, 0, sizeof(unsigned long) * ntilesw * ntilesh);
- if ((flags & TJFLAG_NOREALLOC) != 0 || !doTile)
+ if ((flags & TJFLAG_NOREALLOC) != 0 &&
+ (doTile || xformOp != TJXOP_NONE || xformOpt != 0 || customFilter))
for (i = 0; i < ntilesw * ntilesh; i++) {
+ if (tjBufSize(tilew, tileh, subsamp) > (unsigned long)INT_MAX)
+ THROW("getting buffer size", "Image is too large");
if ((jpegBuf[i] = (unsigned char *)
tjAlloc(tjBufSize(tilew, tileh, subsamp))) == NULL)
- _throwunix("allocating JPEG tiles");
+ THROW_UNIX("allocating JPEG tiles");
}
tw = w; th = h; ttilew = tilew; ttileh = tileh;
if (doTile || xformOp != TJXOP_NONE || xformOpt != 0 || customFilter) {
if ((t = (tjtransform *)malloc(sizeof(tjtransform) * ntilesw *
ntilesh)) == NULL)
- _throwunix("allocating image transform array");
+ THROW_UNIX("allocating image transform array");
if (xformOp == TJXOP_TRANSPOSE || xformOp == TJXOP_TRANSVERSE ||
xformOp == TJXOP_ROT90 || xformOp == TJXOP_ROT270) {
start = getTime();
if (tjTransform(handle, srcBuf, srcSize, tntilesw * tntilesh, jpegBuf,
jpegSize, t, flags) == -1)
- _throwtj("executing tjTransform()");
+ THROW_TJ("executing tjTransform()");
elapsed += getTime() - start;
if (iter >= 0) {
iter++;
}
} else {
if (quiet == 1) printf("N/A N/A ");
- tjFree(jpegBuf[0]);
+ if (jpegBuf[0]) tjFree(jpegBuf[0]);
jpegBuf[0] = NULL;
decompsrc = 1;
}
} else if (quiet == 1) printf("N/A\n");
for (i = 0; i < ntilesw * ntilesh; i++) {
- tjFree(jpegBuf[i]); jpegBuf[i] = NULL;
+ if (jpegBuf[i]) tjFree(jpegBuf[i]);
+ jpegBuf[i] = NULL;
}
free(jpegBuf); jpegBuf = NULL;
if (jpegSize) { free(jpegSize); jpegSize = NULL; }
}
-void usage(char *progName)
+static void usage(char *progName)
{
int i;
int minArg = 2, retval = 0, subsamp = -1;
if ((scalingFactors = tjGetScalingFactors(&nsf)) == NULL || nsf == 0)
- _throw("executing tjGetScalingFactors()", tjGetErrorStr());
+ THROW("executing tjGetScalingFactors()", tjGetErrorStr());
if (argc < minArg) usage(argv[0]);
else if (!strcasecmp(argv[i], "-copynone"))
xformOpt |= TJXOPT_COPYNONE;
else if (!strcasecmp(argv[i], "-benchtime") && i < argc - 1) {
- double temp = atof(argv[++i]);
+ double tempd = atof(argv[++i]);
- if (temp > 0.0) benchTime = temp;
+ if (tempd > 0.0) benchTime = tempd;
else usage(argv[0]);
} else if (!strcasecmp(argv[i], "-warmup") && i < argc - 1) {
- double temp = atof(argv[++i]);
+ double tempd = atof(argv[++i]);
- if (temp >= 0.0) warmup = temp;
+ if (tempd >= 0.0) warmup = tempd;
else usage(argv[0]);
printf("Warmup time = %.1f seconds\n\n", warmup);
} else if (!strcasecmp(argv[i], "-alloc"))
printf("Testing YUV planar encoding/decoding\n\n");
doYUV = 1;
} else if (!strcasecmp(argv[i], "-yuvpad") && i < argc - 1) {
- int temp = atoi(argv[++i]);
+ int tempi = atoi(argv[++i]);
- if (temp >= 1) yuvPad = temp;
+ if (tempi >= 1) yuvPad = tempi;
} else if (!strcasecmp(argv[i], "-subsamp") && i < argc - 1) {
i++;
if (toupper(argv[i][0]) == 'G') subsamp = TJSAMP_GRAY;
else {
- int temp = atoi(argv[i]);
+ int tempi = atoi(argv[i]);
- switch (temp) {
+ switch (tempi) {
case 444: subsamp = TJSAMP_444; break;
case 422: subsamp = TJSAMP_422; break;
case 440: subsamp = TJSAMP_440; break;
if (!decompOnly) {
if ((srcBuf = tjLoadImage(argv[1], &w, 1, &h, &pf, flags)) == NULL)
- _throwtjg("loading bitmap");
+ THROW_TJG("loading bitmap");
temp = strrchr(argv[1], '.');
if (temp != NULL) *temp = '\0';
}
/*
- * Copyright (C)2011-2012, 2014-2015, 2017 D. R. Commander.
- * All Rights Reserved.
+ * Copyright (C)2011-2012, 2014-2015, 2017, 2019 D. R. Commander.
+ * All Rights Reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
#define strncasecmp strnicmp
#endif
-#define _throw(action, message) { \
+#define THROW(action, message) { \
printf("ERROR in line %d while %s:\n%s\n", __LINE__, action, message); \
retval = -1; goto bailout; \
}
-#define _throwtj(action) _throw(action, tjGetErrorStr2(tjInstance))
+#define THROW_TJ(action) THROW(action, tjGetErrorStr2(tjInstance))
-#define _throwunix(action) _throw(action, strerror(errno))
+#define THROW_UNIX(action) THROW(action, strerror(errno))
#define DEFAULT_SUBSAMP TJSAMP_444
#define DEFAULT_QUALITY 95
/* DCT filter example. This produces a negative of the image. */
-int customFilter(short *coeffs, tjregion arrayRegion, tjregion planeRegion,
- int componentIndex, int transformIndex,
- tjtransform *transform)
+static int customFilter(short *coeffs, tjregion arrayRegion,
+ tjregion planeRegion, int componentIndex,
+ int transformIndex, tjtransform *transform)
{
int i;
}
-void usage(char *programName)
+static void usage(char *programName)
{
int i;
tjhandle tjInstance = NULL;
if ((scalingFactors = tjGetScalingFactors(&numScalingFactors)) == NULL)
- _throwtj("getting scaling factors");
+ THROW_TJ("getting scaling factors");
memset(&xform, 0, sizeof(tjtransform));
if (argc < 3)
/* Read the JPEG file into memory. */
if ((jpegFile = fopen(argv[1], "rb")) == NULL)
- _throwunix("opening input file");
+ THROW_UNIX("opening input file");
if (fseek(jpegFile, 0, SEEK_END) < 0 || ((size = ftell(jpegFile)) < 0) ||
fseek(jpegFile, 0, SEEK_SET) < 0)
- _throwunix("determining input file size");
+ THROW_UNIX("determining input file size");
if (size == 0)
- _throw("determining input file size", "Input file contains no data");
+ THROW("determining input file size", "Input file contains no data");
jpegSize = (unsigned long)size;
if ((jpegBuf = (unsigned char *)tjAlloc(jpegSize)) == NULL)
- _throwunix("allocating JPEG buffer");
+ THROW_UNIX("allocating JPEG buffer");
if (fread(jpegBuf, jpegSize, 1, jpegFile) < 1)
- _throwunix("reading input file");
+ THROW_UNIX("reading input file");
fclose(jpegFile); jpegFile = NULL;
if (doTransform) {
unsigned long dstSize = 0;
if ((tjInstance = tjInitTransform()) == NULL)
- _throwtj("initializing transformer");
+ THROW_TJ("initializing transformer");
xform.options |= TJXOPT_TRIM;
if (tjTransform(tjInstance, jpegBuf, jpegSize, 1, &dstBuf, &dstSize,
&xform, flags) < 0)
- _throwtj("transforming input image");
+ THROW_TJ("transforming input image");
tjFree(jpegBuf);
jpegBuf = dstBuf;
jpegSize = dstSize;
} else {
if ((tjInstance = tjInitDecompress()) == NULL)
- _throwtj("initializing decompressor");
+ THROW_TJ("initializing decompressor");
}
if (tjDecompressHeader3(tjInstance, jpegBuf, jpegSize, &width, &height,
&inSubsamp, &inColorspace) < 0)
- _throwtj("reading JPEG header");
+ THROW_TJ("reading JPEG header");
printf("%s Image: %d x %d pixels, %s subsampling, %s colorspace\n",
(doTransform ? "Transformed" : "Input"), width, height,
/* Input image has been transformed, and no re-compression options
have been selected. Write the transformed image to disk and exit. */
if ((jpegFile = fopen(argv[2], "wb")) == NULL)
- _throwunix("opening output file");
+ THROW_UNIX("opening output file");
if (fwrite(jpegBuf, jpegSize, 1, jpegFile) < 1)
- _throwunix("writing output file");
+ THROW_UNIX("writing output file");
fclose(jpegFile); jpegFile = NULL;
goto bailout;
}
pixelFormat = TJPF_BGRX;
if ((imgBuf = (unsigned char *)tjAlloc(width * height *
tjPixelSize[pixelFormat])) == NULL)
- _throwunix("allocating uncompressed image buffer");
+ THROW_UNIX("allocating uncompressed image buffer");
if (tjDecompress2(tjInstance, jpegBuf, jpegSize, imgBuf, width, 0, height,
pixelFormat, flags) < 0)
- _throwtj("decompressing JPEG image");
+ THROW_TJ("decompressing JPEG image");
tjFree(jpegBuf); jpegBuf = NULL;
tjDestroy(tjInstance); tjInstance = NULL;
} else {
/* Input image is not a JPEG image. Load it into memory. */
if ((imgBuf = tjLoadImage(argv[1], &width, 1, &height, &pixelFormat,
0)) == NULL)
- _throwtj("loading input image");
+ THROW_TJ("loading input image");
if (outSubsamp < 0) {
if (pixelFormat == TJPF_GRAY)
outSubsamp = TJSAMP_GRAY;
if (!strcasecmp(outFormat, "jpg")) {
/* Output image format is JPEG. Compress the uncompressed image. */
- unsigned char *jpegBuf = NULL; /* Dynamically allocate the JPEG buffer */
unsigned long jpegSize = 0;
+ jpegBuf = NULL; /* Dynamically allocate the JPEG buffer */
+
if (outQual < 0)
outQual = DEFAULT_QUALITY;
printf(", %s subsampling, quality = %d\n", subsampName[outSubsamp],
outQual);
if ((tjInstance = tjInitCompress()) == NULL)
- _throwtj("initializing compressor");
+ THROW_TJ("initializing compressor");
if (tjCompress2(tjInstance, imgBuf, width, 0, height, pixelFormat,
&jpegBuf, &jpegSize, outSubsamp, outQual, flags) < 0)
- _throwtj("compressing image");
+ THROW_TJ("compressing image");
tjDestroy(tjInstance); tjInstance = NULL;
/* Write the JPEG image to disk. */
if ((jpegFile = fopen(argv[2], "wb")) == NULL)
- _throwunix("opening output file");
+ THROW_UNIX("opening output file");
if (fwrite(jpegBuf, jpegSize, 1, jpegFile) < 1)
- _throwunix("writing output file");
+ THROW_UNIX("writing output file");
tjDestroy(tjInstance); tjInstance = NULL;
fclose(jpegFile); jpegFile = NULL;
tjFree(jpegBuf); jpegBuf = NULL;
directly to disk. */
printf("\n");
if (tjSaveImage(argv[2], imgBuf, width, 0, height, pixelFormat, 0) < 0)
- _throwtj("saving output image");
+ THROW_TJ("saving output image");
}
bailout:
/*
- * Copyright (C)2009-2014, 2017-2018 D. R. Commander. All Rights Reserved.
+ * Copyright (C)2009-2014, 2017-2019 D. R. Commander. All Rights Reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
#endif
-void usage(char *progName)
+static void usage(char *progName)
{
printf("\nUSAGE: %s [options]\n\n", progName);
printf("Options:\n");
}
-#define _throwtj() { \
+#define THROW_TJ() { \
printf("TurboJPEG ERROR:\n%s\n", tjGetErrorStr()); \
- bailout() \
+ BAILOUT() \
}
-#define _tj(f) { if ((f) == -1) _throwtj(); }
-#define _throw(m) { printf("ERROR: %s\n", m); bailout() }
-#define _throwmd5(filename, md5sum, ref) { \
+#define TRY_TJ(f) { if ((f) == -1) THROW_TJ(); }
+#define THROW(m) { printf("ERROR: %s\n", m); BAILOUT() }
+#define THROW_MD5(filename, md5sum, ref) { \
printf("\n%s has an MD5 sum of %s.\n Should be %s.\n", filename, md5sum, \
ref); \
- bailout() \
+ BAILOUT() \
}
const char *subNameLong[TJ_NUMSAMP] = {
int doYUV = 0, alloc = 0, pad = 4;
int exitStatus = 0;
-#define bailout() { exitStatus = -1; goto bailout; }
+#define BAILOUT() { exitStatus = -1; goto bailout; }
-void initBuf(unsigned char *buf, int w, int h, int pf, int flags)
+static void initBuf(unsigned char *buf, int w, int h, int pf, int flags)
{
int roffset = tjRedOffset[pf];
int goffset = tjGreenOffset[pf];
}
-#define checkval(v, cv) { \
+#define CHECKVAL(v, cv) { \
if (v < cv - 1 || v > cv + 1) { \
printf("\nComp. %s at %d,%d should be %d, not %d\n", #v, row, col, cv, \
v); \
} \
}
-#define checkval0(v) { \
+#define CHECKVAL0(v) { \
if (v > 1) { \
printf("\nComp. %s at %d,%d should be 0, not %d\n", #v, row, col, v); \
retval = 0; exitStatus = -1; goto bailout; \
} \
}
-#define checkval255(v) { \
+#define CHECKVAL255(v) { \
if (v < 254) { \
printf("\nComp. %s at %d,%d should be 255, not %d\n", #v, row, col, v); \
retval = 0; exitStatus = -1; goto bailout; \
}
-int checkBuf(unsigned char *buf, int w, int h, int pf, int subsamp,
- tjscalingfactor sf, int flags)
+static int checkBuf(unsigned char *buf, int w, int h, int pf, int subsamp,
+ tjscalingfactor sf, int flags)
{
int roffset = tjRedOffset[pf];
int goffset = tjGreenOffset[pf];
y = buf[index * ps + 2];
k = buf[index * ps + 3];
if (((row / blocksize) + (col / blocksize)) % 2 == 0) {
- checkval255(c); checkval255(m); checkval255(y);
- if (row < halfway) checkval255(k)
- else checkval0(k)
+ CHECKVAL255(c); CHECKVAL255(m); CHECKVAL255(y);
+ if (row < halfway) CHECKVAL255(k)
+ else CHECKVAL0(k)
} else {
- checkval255(c); checkval0(y); checkval255(k);
- if (row < halfway) checkval0(m)
- else checkval255(m)
+ CHECKVAL255(c); CHECKVAL0(y); CHECKVAL255(k);
+ if (row < halfway) CHECKVAL0(m)
+ else CHECKVAL255(m)
}
}
}
a = aoffset >= 0 ? buf[index * ps + aoffset] : 0xFF;
if (((row / blocksize) + (col / blocksize)) % 2 == 0) {
if (row < halfway) {
- checkval255(r); checkval255(g); checkval255(b);
+ CHECKVAL255(r); CHECKVAL255(g); CHECKVAL255(b);
} else {
- checkval0(r); checkval0(g); checkval0(b);
+ CHECKVAL0(r); CHECKVAL0(g); CHECKVAL0(b);
}
} else {
if (subsamp == TJSAMP_GRAY) {
if (row < halfway) {
- checkval(r, 76); checkval(g, 76); checkval(b, 76);
+ CHECKVAL(r, 76); CHECKVAL(g, 76); CHECKVAL(b, 76);
} else {
- checkval(r, 226); checkval(g, 226); checkval(b, 226);
+ CHECKVAL(r, 226); CHECKVAL(g, 226); CHECKVAL(b, 226);
}
} else {
if (row < halfway) {
- checkval255(r); checkval0(g); checkval0(b);
+ CHECKVAL255(r); CHECKVAL0(g); CHECKVAL0(b);
} else {
- checkval255(r); checkval255(g); checkval0(b);
+ CHECKVAL255(r); CHECKVAL255(g); CHECKVAL0(b);
}
}
}
- checkval255(a);
+ CHECKVAL255(a);
}
}
#define PAD(v, p) ((v + (p) - 1) & (~((p) - 1)))
-int checkBufYUV(unsigned char *buf, int w, int h, int subsamp,
- tjscalingfactor sf)
+static int checkBufYUV(unsigned char *buf, int w, int h, int subsamp,
+ tjscalingfactor sf)
{
int row, col;
int hsf = tjMCUWidth[subsamp] / 8, vsf = tjMCUHeight[subsamp] / 8;
unsigned char y = buf[ypitch * row + col];
if (((row / blocksize) + (col / blocksize)) % 2 == 0) {
- if (row < halfway) checkval255(y)
- else checkval0(y);
+ if (row < halfway) CHECKVAL255(y)
+ else CHECKVAL0(y);
} else {
- if (row < halfway) checkval(y, 76)
- else checkval(y, 226);
+ if (row < halfway) CHECKVAL(y, 76)
+ else CHECKVAL(y, 226);
}
}
}
if (subsamp != TJSAMP_GRAY) {
- int halfway = 16 / vsf * sf.num / sf.denom;
+ halfway = 16 / vsf * sf.num / sf.denom;
for (row = 0; row < ch; row++) {
for (col = 0; col < cw; col++) {
v = buf[ypitch * ph + uvpitch * ch + (uvpitch * row + col)];
if (((row * vsf / blocksize) + (col * hsf / blocksize)) % 2 == 0) {
- checkval(u, 128); checkval(v, 128);
+ CHECKVAL(u, 128); CHECKVAL(v, 128);
} else {
if (row < halfway) {
- checkval(u, 85); checkval255(v);
+ CHECKVAL(u, 85); CHECKVAL255(v);
} else {
- checkval0(u); checkval(v, 149);
+ CHECKVAL0(u); CHECKVAL(v, 149);
}
}
}
}
-void writeJPEG(unsigned char *jpegBuf, unsigned long jpegSize, char *filename)
+static void writeJPEG(unsigned char *jpegBuf, unsigned long jpegSize,
+ char *filename)
{
FILE *file = fopen(filename, "wb");
if (!file || fwrite(jpegBuf, jpegSize, 1, file) != 1) {
printf("ERROR: Could not write to %s.\n%s\n", filename, strerror(errno));
- bailout()
+ BAILOUT()
}
bailout:
}
-void compTest(tjhandle handle, unsigned char **dstBuf, unsigned long *dstSize,
- int w, int h, int pf, char *basename, int subsamp, int jpegQual,
- int flags)
+static void compTest(tjhandle handle, unsigned char **dstBuf,
+ unsigned long *dstSize, int w, int h, int pf,
+ char *basename, int subsamp, int jpegQual, int flags)
{
char tempStr[1024];
unsigned char *srcBuf = NULL, *yuvBuf = NULL;
const char *buStr = (flags & TJFLAG_BOTTOMUP) ? "BU" : "TD";
if ((srcBuf = (unsigned char *)malloc(w * h * tjPixelSize[pf])) == NULL)
- _throw("Memory allocation failure");
+ THROW("Memory allocation failure");
initBuf(srcBuf, w, h, pf, flags);
if (*dstBuf && *dstSize > 0) memset(*dstBuf, 0, *dstSize);
tjscalingfactor sf = { 1, 1 };
tjhandle handle2 = tjInitCompress();
- if (!handle2) _throwtj();
+ if (!handle2) THROW_TJ();
if ((yuvBuf = (unsigned char *)malloc(yuvSize)) == NULL)
- _throw("Memory allocation failure");
+ THROW("Memory allocation failure");
memset(yuvBuf, 0, yuvSize);
printf("%s %s -> YUV %s ... ", pfStr, buStrLong, subNameLong[subsamp]);
- _tj(tjEncodeYUV3(handle2, srcBuf, w, 0, h, pf, yuvBuf, pad, subsamp,
- flags));
+ TRY_TJ(tjEncodeYUV3(handle2, srcBuf, w, 0, h, pf, yuvBuf, pad, subsamp,
+ flags));
tjDestroy(handle2);
if (checkBufYUV(yuvBuf, w, h, subsamp, sf)) printf("Passed.\n");
else printf("FAILED!\n");
printf("YUV %s %s -> JPEG Q%d ... ", subNameLong[subsamp], buStrLong,
jpegQual);
- _tj(tjCompressFromYUV(handle, yuvBuf, w, pad, h, subsamp, dstBuf, dstSize,
- jpegQual, flags));
+ TRY_TJ(tjCompressFromYUV(handle, yuvBuf, w, pad, h, subsamp, dstBuf,
+ dstSize, jpegQual, flags));
} else {
printf("%s %s -> %s Q%d ... ", pfStr, buStrLong, subNameLong[subsamp],
jpegQual);
- _tj(tjCompress2(handle, srcBuf, w, 0, h, pf, dstBuf, dstSize, subsamp,
- jpegQual, flags));
+ TRY_TJ(tjCompress2(handle, srcBuf, w, 0, h, pf, dstBuf, dstSize, subsamp,
+ jpegQual, flags));
}
snprintf(tempStr, 1024, "%s_enc_%s_%s_%s_Q%d.jpg", basename, pfStr, buStr,
}
-void _decompTest(tjhandle handle, unsigned char *jpegBuf,
- unsigned long jpegSize, int w, int h, int pf, char *basename,
- int subsamp, int flags, tjscalingfactor sf)
+static void _decompTest(tjhandle handle, unsigned char *jpegBuf,
+ unsigned long jpegSize, int w, int h, int pf,
+ char *basename, int subsamp, int flags,
+ tjscalingfactor sf)
{
unsigned char *dstBuf = NULL, *yuvBuf = NULL;
int _hdrw = 0, _hdrh = 0, _hdrsubsamp = -1;
int scaledHeight = TJSCALED(h, sf);
unsigned long dstSize = 0;
- _tj(tjDecompressHeader2(handle, jpegBuf, jpegSize, &_hdrw, &_hdrh,
- &_hdrsubsamp));
+ TRY_TJ(tjDecompressHeader2(handle, jpegBuf, jpegSize, &_hdrw, &_hdrh,
+ &_hdrsubsamp));
if (_hdrw != w || _hdrh != h || _hdrsubsamp != subsamp)
- _throw("Incorrect JPEG header");
+ THROW("Incorrect JPEG header");
dstSize = scaledWidth * scaledHeight * tjPixelSize[pf];
if ((dstBuf = (unsigned char *)malloc(dstSize)) == NULL)
- _throw("Memory allocation failure");
+ THROW("Memory allocation failure");
memset(dstBuf, 0, dstSize);
if (doYUV) {
subsamp);
tjhandle handle2 = tjInitDecompress();
- if (!handle2) _throwtj();
+ if (!handle2) THROW_TJ();
if ((yuvBuf = (unsigned char *)malloc(yuvSize)) == NULL)
- _throw("Memory allocation failure");
+ THROW("Memory allocation failure");
memset(yuvBuf, 0, yuvSize);
printf("JPEG -> YUV %s ", subNameLong[subsamp]);
if (sf.num != 1 || sf.denom != 1)
printf("%d/%d ... ", sf.num, sf.denom);
else printf("... ");
- _tj(tjDecompressToYUV2(handle, jpegBuf, jpegSize, yuvBuf, scaledWidth, pad,
- scaledHeight, flags));
+ TRY_TJ(tjDecompressToYUV2(handle, jpegBuf, jpegSize, yuvBuf, scaledWidth,
+ pad, scaledHeight, flags));
if (checkBufYUV(yuvBuf, scaledWidth, scaledHeight, subsamp, sf))
printf("Passed.\n");
else printf("FAILED!\n");
printf("YUV %s -> %s %s ... ", subNameLong[subsamp], pixFormatStr[pf],
(flags & TJFLAG_BOTTOMUP) ? "Bottom-Up" : "Top-Down ");
- _tj(tjDecodeYUV(handle2, yuvBuf, pad, subsamp, dstBuf, scaledWidth, 0,
- scaledHeight, pf, flags));
+ TRY_TJ(tjDecodeYUV(handle2, yuvBuf, pad, subsamp, dstBuf, scaledWidth, 0,
+ scaledHeight, pf, flags));
tjDestroy(handle2);
} else {
printf("JPEG -> %s %s ", pixFormatStr[pf],
if (sf.num != 1 || sf.denom != 1)
printf("%d/%d ... ", sf.num, sf.denom);
else printf("... ");
- _tj(tjDecompress2(handle, jpegBuf, jpegSize, dstBuf, scaledWidth, 0,
- scaledHeight, pf, flags));
+ TRY_TJ(tjDecompress2(handle, jpegBuf, jpegSize, dstBuf, scaledWidth, 0,
+ scaledHeight, pf, flags));
}
if (checkBuf(dstBuf, scaledWidth, scaledHeight, pf, subsamp, sf, flags))
}
-void decompTest(tjhandle handle, unsigned char *jpegBuf,
- unsigned long jpegSize, int w, int h, int pf, char *basename,
- int subsamp, int flags)
+static void decompTest(tjhandle handle, unsigned char *jpegBuf,
+ unsigned long jpegSize, int w, int h, int pf,
+ char *basename, int subsamp, int flags)
{
int i, n = 0;
tjscalingfactor *sf = tjGetScalingFactors(&n);
- if (!sf || !n) _throwtj();
+ if (!sf || !n) THROW_TJ();
for (i = 0; i < n; i++) {
if (subsamp == TJSAMP_444 || subsamp == TJSAMP_GRAY ||
}
-void doTest(int w, int h, const int *formats, int nformats, int subsamp,
- char *basename)
+static void doTest(int w, int h, const int *formats, int nformats, int subsamp,
+ char *basename)
{
tjhandle chandle = NULL, dhandle = NULL;
unsigned char *dstBuf = NULL;
size = tjBufSize(w, h, subsamp);
if (size != 0)
if ((dstBuf = (unsigned char *)tjAlloc(size)) == NULL)
- _throw("Memory allocation failure.");
+ THROW("Memory allocation failure.");
if ((chandle = tjInitCompress()) == NULL ||
(dhandle = tjInitDecompress()) == NULL)
- _throwtj();
+ THROW_TJ();
for (pfi = 0; pfi < nformats; pfi++) {
for (i = 0; i < 2; i++) {
}
-void bufSizeTest(void)
+#if SIZEOF_SIZE_T == 8
+#define CHECKSIZE(function) { \
+ if ((unsigned long long)size < (unsigned long long)0xFFFFFFFF) \
+ THROW(#function " overflow"); \
+}
+#else
+#define CHECKSIZE(function) { \
+ if (size != (unsigned long)(-1) || \
+ !strcmp(tjGetErrorStr2(NULL), "No error")) \
+ THROW(#function " overflow"); \
+}
+#endif
+
+static void overflowTest(void)
+{
+ /* Ensure that the various buffer size functions don't overflow */
+ unsigned long size;
+
+ size = tjBufSize(26755, 26755, TJSAMP_444);
+ CHECKSIZE(tjBufSize());
+ size = TJBUFSIZE(26755, 26755);
+ CHECKSIZE(TJBUFSIZE());
+ size = tjBufSizeYUV2(37838, 1, 37838, TJSAMP_444);
+ CHECKSIZE(tjBufSizeYUV2());
+ size = TJBUFSIZEYUV(37838, 37838, TJSAMP_444);
+ CHECKSIZE(TJBUFSIZEYUV());
+ size = tjBufSizeYUV(37838, 37838, TJSAMP_444);
+ CHECKSIZE(tjBufSizeYUV());
+ size = tjPlaneSizeYUV(0, 65536, 0, 65536, TJSAMP_444);
+ CHECKSIZE(tjPlaneSizeYUV());
+
+bailout:
+ return;
+}
+
+
+static void bufSizeTest(void)
{
int w, h, i, subsamp;
unsigned char *srcBuf = NULL, *dstBuf = NULL;
tjhandle handle = NULL;
unsigned long dstSize = 0;
- if ((handle = tjInitCompress()) == NULL) _throwtj();
+ if ((handle = tjInitCompress()) == NULL) THROW_TJ();
printf("Buffer size regression test\n");
for (subsamp = 0; subsamp < TJ_NUMSAMP; subsamp++) {
for (h = 1; h < maxh; h++) {
if (h % 100 == 0) printf("%.4d x %.4d\b\b\b\b\b\b\b\b\b\b\b", w, h);
if ((srcBuf = (unsigned char *)malloc(w * h * 4)) == NULL)
- _throw("Memory allocation failure");
+ THROW("Memory allocation failure");
if (!alloc || doYUV) {
if (doYUV) dstSize = tjBufSizeYUV2(w, pad, h, subsamp);
else dstSize = tjBufSize(w, h, subsamp);
if ((dstBuf = (unsigned char *)tjAlloc(dstSize)) == NULL)
- _throw("Memory allocation failure");
+ THROW("Memory allocation failure");
}
for (i = 0; i < w * h * 4; i++) {
}
if (doYUV) {
- _tj(tjEncodeYUV3(handle, srcBuf, w, 0, h, TJPF_BGRX, dstBuf, pad,
- subsamp, 0));
+ TRY_TJ(tjEncodeYUV3(handle, srcBuf, w, 0, h, TJPF_BGRX, dstBuf, pad,
+ subsamp, 0));
} else {
- _tj(tjCompress2(handle, srcBuf, w, 0, h, TJPF_BGRX, &dstBuf,
- &dstSize, subsamp, 100,
- alloc ? 0 : TJFLAG_NOREALLOC));
+ TRY_TJ(tjCompress2(handle, srcBuf, w, 0, h, TJPF_BGRX, &dstBuf,
+ &dstSize, subsamp, 100,
+ alloc ? 0 : TJFLAG_NOREALLOC));
}
free(srcBuf); srcBuf = NULL;
if (!alloc || doYUV) {
}
if ((srcBuf = (unsigned char *)malloc(h * w * 4)) == NULL)
- _throw("Memory allocation failure");
+ THROW("Memory allocation failure");
if (!alloc || doYUV) {
if (doYUV) dstSize = tjBufSizeYUV2(h, pad, w, subsamp);
else dstSize = tjBufSize(h, w, subsamp);
if ((dstBuf = (unsigned char *)tjAlloc(dstSize)) == NULL)
- _throw("Memory allocation failure");
+ THROW("Memory allocation failure");
}
for (i = 0; i < h * w * 4; i++) {
}
if (doYUV) {
- _tj(tjEncodeYUV3(handle, srcBuf, h, 0, w, TJPF_BGRX, dstBuf, pad,
- subsamp, 0));
+ TRY_TJ(tjEncodeYUV3(handle, srcBuf, h, 0, w, TJPF_BGRX, dstBuf, pad,
+ subsamp, 0));
} else {
- _tj(tjCompress2(handle, srcBuf, h, 0, w, TJPF_BGRX, &dstBuf,
- &dstSize, subsamp, 100,
- alloc ? 0 : TJFLAG_NOREALLOC));
+ TRY_TJ(tjCompress2(handle, srcBuf, h, 0, w, TJPF_BGRX, &dstBuf,
+ &dstSize, subsamp, 100,
+ alloc ? 0 : TJFLAG_NOREALLOC));
}
free(srcBuf); srcBuf = NULL;
if (!alloc || doYUV) {
}
-void initBitmap(unsigned char *buf, int width, int pitch, int height, int pf,
- int flags)
+static void initBitmap(unsigned char *buf, int width, int pitch, int height,
+ int pf, int flags)
{
int roffset = tjRedOffset[pf];
int goffset = tjGreenOffset[pf];
}
-int cmpBitmap(unsigned char *buf, int width, int pitch, int height, int pf,
- int flags, int gray2rgb)
+static int cmpBitmap(unsigned char *buf, int width, int pitch, int height,
+ int pf, int flags, int gray2rgb)
{
int roffset = tjRedOffset[pf];
int goffset = tjGreenOffset[pf];
}
-int doBmpTest(const char *ext, int width, int align, int height, int pf,
- int flags)
+static int doBmpTest(const char *ext, int width, int align, int height, int pf,
+ int flags)
{
char filename[80], *md5sum, md5buf[65];
int ps = tjPixelSize[pf], pitch = PAD(width * ps, align), loadWidth = 0,
}
if ((buf = (unsigned char *)tjAlloc(pitch * height)) == NULL)
- _throw("Could not allocate memory");
+ THROW("Could not allocate memory");
initBitmap(buf, width, pitch, height, pf, flags);
snprintf(filename, 80, "test_bmp_%s_%d_%s.%s", pixFormatStr[pf], align,
(flags & TJFLAG_BOTTOMUP) ? "bu" : "td", ext);
- _tj(tjSaveImage(filename, buf, width, pitch, height, pf, flags));
+ TRY_TJ(tjSaveImage(filename, buf, width, pitch, height, pf, flags));
md5sum = MD5File(filename, md5buf);
if (strcasecmp(md5sum, md5ref))
- _throwmd5(filename, md5sum, md5ref);
+ THROW_MD5(filename, md5sum, md5ref);
tjFree(buf); buf = NULL;
if ((buf = tjLoadImage(filename, &loadWidth, align, &loadHeight, &pf,
flags)) == NULL)
- _throwtj();
+ THROW_TJ();
if (width != loadWidth || height != loadHeight) {
printf("\n Image dimensions of %s are bogus\n", filename);
retval = -1; goto bailout;
pf = TJPF_XBGR;
if ((buf = tjLoadImage(filename, &loadWidth, align, &loadHeight, &pf,
flags)) == NULL)
- _throwtj();
+ THROW_TJ();
pitch = PAD(width * tjPixelSize[pf], align);
if (!cmpBitmap(buf, width, pitch, height, pf, flags, 1)) {
printf("\n Converting %s to RGB failed\n", filename);
pf = TJPF_CMYK;
if ((buf = tjLoadImage(filename, &loadWidth, align, &loadHeight, &pf,
flags)) == NULL)
- _throwtj();
+ THROW_TJ();
pitch = PAD(width * tjPixelSize[pf], align);
if (!cmpBitmap(buf, width, pitch, height, pf, flags, 1)) {
printf("\n Converting %s to CMYK failed\n", filename);
pixelFormat = TJPF_UNKNOWN;
if ((buf = tjLoadImage(filename, &loadWidth, align, &loadHeight,
&pixelFormat, flags)) == NULL)
- _throwtj();
+ THROW_TJ();
if ((pf == TJPF_GRAY && pixelFormat != TJPF_GRAY) ||
(pf != TJPF_GRAY && !strcasecmp(ext, "bmp") &&
pixelFormat != TJPF_BGR) ||
}
-int bmpTest(void)
+static int bmpTest(void)
{
int align, width = 35, height = 39, format;
}
if (alloc) printf("Testing automatic buffer allocation\n");
if (doYUV) num4bf = 4;
+ overflowTest();
doTest(35, 39, _3byteFormats, 2, TJSAMP_444, "test");
doTest(39, 41, _4byteFormats, num4bf, TJSAMP_444, "test");
doTest(41, 35, _3byteFormats, 2, TJSAMP_422, "test");
/*
- * Copyright (C)2011 D. R. Commander. All Rights Reserved.
+ * Copyright (C)2011, 2019 D. R. Commander. All Rights Reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
#ifdef _WIN32
#include <windows.h>
+#include "tjutil.h"
static double getFreq(void)
{
#include <stdlib.h>
#include <sys/time.h>
+#include "tjutil.h"
double getTime(void)
{
/*
- * Copyright (C)2011-2018 D. R. Commander. All Rights Reserved.
+ * Copyright (C)2011-2019 D. R. Commander. All Rights Reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
#include <jni.h>
#include "java/org_libjpegturbo_turbojpeg_TJCompressor.h"
#include "java/org_libjpegturbo_turbojpeg_TJDecompressor.h"
+#include "java/org_libjpegturbo_turbojpeg_TJTransformer.h"
#include "java/org_libjpegturbo_turbojpeg_TJ.h"
-#define PAD(v, p) ((v + (p) - 1) & (~((p) - 1)))
-
-#define bailif0(f) { \
+#define BAILIF0(f) { \
if (!(f) || (*env)->ExceptionCheck(env)) { \
goto bailout; \
} \
}
-#define _throw(msg, exceptionClass) { \
+#define THROW(msg, exceptionClass) { \
jclass _exccls = (*env)->FindClass(env, exceptionClass); \
\
- bailif0(_exccls); \
+ BAILIF0(_exccls); \
(*env)->ThrowNew(env, _exccls, msg); \
goto bailout; \
}
-#define _throwtj() { \
+#define THROW_TJ() { \
jclass _exccls; \
jmethodID _excid; \
jobject _excobj; \
jstring _errstr; \
\
- bailif0(_errstr = (*env)->NewStringUTF(env, tjGetErrorStr2(handle))); \
- bailif0(_exccls = (*env)->FindClass(env, \
+ BAILIF0(_errstr = (*env)->NewStringUTF(env, tjGetErrorStr2(handle))); \
+ BAILIF0(_exccls = (*env)->FindClass(env, \
"org/libjpegturbo/turbojpeg/TJException")); \
- bailif0(_excid = (*env)->GetMethodID(env, _exccls, "<init>", \
+ BAILIF0(_excid = (*env)->GetMethodID(env, _exccls, "<init>", \
"(Ljava/lang/String;I)V")); \
- bailif0(_excobj = (*env)->NewObject(env, _exccls, _excid, _errstr, \
+ BAILIF0(_excobj = (*env)->NewObject(env, _exccls, _excid, _errstr, \
tjGetErrorCode(handle))); \
(*env)->Throw(env, _excobj); \
goto bailout; \
}
-#define _throwarg(msg) _throw(msg, "java/lang/IllegalArgumentException")
+#define THROW_ARG(msg) THROW(msg, "java/lang/IllegalArgumentException")
-#define _throwmem() \
- _throw("Memory allocation failure", "java/lang/OutOfMemoryError");
+#define THROW_MEM() \
+ THROW("Memory allocation failure", "java/lang/OutOfMemoryError");
-#define gethandle() \
+#define GET_HANDLE() \
jclass _cls = (*env)->GetObjectClass(env, obj); \
jfieldID _fid; \
\
- bailif0(_cls); \
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "handle", "J")); \
+ BAILIF0(_cls); \
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "handle", "J")); \
handle = (tjhandle)(size_t)(*env)->GetLongField(env, obj, _fid);
#ifdef _WIN32
#define setenv(envvar, value, dummy) _putenv_s(envvar, value)
#endif
-#define prop2env(property, envvar) { \
+#define PROP2ENV(property, envvar) { \
if ((jName = (*env)->NewStringUTF(env, property)) != NULL && \
(jValue = (*env)->CallStaticObjectMethod(env, cls, mid, \
jName)) != NULL) { \
} \
}
-int ProcessSystemProperties(JNIEnv *env)
+#define SAFE_RELEASE(javaArray, cArray) { \
+ if (javaArray && cArray) \
+ (*env)->ReleasePrimitiveArrayCritical(env, javaArray, (void *)cArray, 0); \
+ cArray = NULL; \
+}
+
+static int ProcessSystemProperties(JNIEnv *env)
{
jclass cls;
jmethodID mid;
jstring jName, jValue;
const char *value;
- bailif0(cls = (*env)->FindClass(env, "java/lang/System"));
- bailif0(mid = (*env)->GetStaticMethodID(env, cls, "getProperty",
+ BAILIF0(cls = (*env)->FindClass(env, "java/lang/System"));
+ BAILIF0(mid = (*env)->GetStaticMethodID(env, cls, "getProperty",
"(Ljava/lang/String;)Ljava/lang/String;"));
- prop2env("turbojpeg.optimize", "TJ_OPTIMIZE");
- prop2env("turbojpeg.arithmetic", "TJ_ARITHMETIC");
- prop2env("turbojpeg.restart", "TJ_RESTART");
- prop2env("turbojpeg.progressive", "TJ_PROGRESSIVE");
+ PROP2ENV("turbojpeg.optimize", "TJ_OPTIMIZE");
+ PROP2ENV("turbojpeg.arithmetic", "TJ_ARITHMETIC");
+ PROP2ENV("turbojpeg.restart", "TJ_RESTART");
+ PROP2ENV("turbojpeg.progressive", "TJ_PROGRESSIVE");
return 0;
bailout:
{
jint retval = (jint)tjBufSize(width, height, jpegSubsamp);
- if (retval == -1) _throwarg(tjGetErrorStr());
+ if (retval == -1) THROW_ARG(tjGetErrorStr());
bailout:
return retval;
{
jint retval = (jint)tjBufSizeYUV2(width, pad, height, subsamp);
- if (retval == -1) _throwarg(tjGetErrorStr());
+ if (retval == -1) THROW_ARG(tjGetErrorStr());
bailout:
return retval;
jint retval = (jint)tjPlaneSizeYUV(componentID, width, stride, height,
subsamp);
- if (retval == -1) _throwarg(tjGetErrorStr());
+ if (retval == -1) THROW_ARG(tjGetErrorStr());
bailout:
return retval;
{
jint retval = (jint)tjPlaneWidth(componentID, width, subsamp);
- if (retval == -1) _throwarg(tjGetErrorStr());
+ if (retval == -1) THROW_ARG(tjGetErrorStr());
bailout:
return retval;
{
jint retval = (jint)tjPlaneHeight(componentID, height, subsamp);
- if (retval == -1) _throwarg(tjGetErrorStr());
+ if (retval == -1) THROW_ARG(tjGetErrorStr());
bailout:
return retval;
tjhandle handle;
if ((handle = tjInitCompress()) == NULL)
- _throw(tjGetErrorStr(), "org/libjpegturbo/turbojpeg/TJException");
+ THROW(tjGetErrorStr(), "org/libjpegturbo/turbojpeg/TJException");
- bailif0(cls = (*env)->GetObjectClass(env, obj));
- bailif0(fid = (*env)->GetFieldID(env, cls, "handle", "J"));
+ BAILIF0(cls = (*env)->GetObjectClass(env, obj));
+ BAILIF0(fid = (*env)->GetFieldID(env, cls, "handle", "J"));
(*env)->SetLongField(env, obj, fid, (size_t)handle);
bailout:
jsize arraySize = 0, actualPitch;
unsigned char *srcBuf = NULL, *jpegBuf = NULL;
- gethandle();
+ GET_HANDLE();
if (pf < 0 || pf >= org_libjpegturbo_turbojpeg_TJ_NUMPF || width < 1 ||
height < 1 || pitch < 0)
- _throwarg("Invalid argument in compress()");
+ THROW_ARG("Invalid argument in compress()");
if (org_libjpegturbo_turbojpeg_TJ_NUMPF != TJ_NUMPF)
- _throwarg("Mismatch between Java and C API");
+ THROW_ARG("Mismatch between Java and C API");
actualPitch = (pitch == 0) ? width * tjPixelSize[pf] : pitch;
arraySize = (y + height - 1) * actualPitch + (x + width) * tjPixelSize[pf];
if ((*env)->GetArrayLength(env, src) * srcElementSize < arraySize)
- _throwarg("Source buffer is not large enough");
+ THROW_ARG("Source buffer is not large enough");
jpegSize = tjBufSize(width, height, jpegSubsamp);
if ((*env)->GetArrayLength(env, dst) < (jsize)jpegSize)
- _throwarg("Destination buffer is not large enough");
+ THROW_ARG("Destination buffer is not large enough");
if (ProcessSystemProperties(env) < 0) goto bailout;
- bailif0(srcBuf = (*env)->GetPrimitiveArrayCritical(env, src, 0));
- bailif0(jpegBuf = (*env)->GetPrimitiveArrayCritical(env, dst, 0));
+ BAILIF0(srcBuf = (*env)->GetPrimitiveArrayCritical(env, src, 0));
+ BAILIF0(jpegBuf = (*env)->GetPrimitiveArrayCritical(env, dst, 0));
if (tjCompress2(handle, &srcBuf[y * actualPitch + x * tjPixelSize[pf]],
width, pitch, height, pf, &jpegBuf, &jpegSize, jpegSubsamp,
- jpegQual, flags | TJFLAG_NOREALLOC) == -1)
- _throwtj();
+ jpegQual, flags | TJFLAG_NOREALLOC) == -1) {
+ SAFE_RELEASE(dst, jpegBuf);
+ SAFE_RELEASE(src, srcBuf);
+ THROW_TJ();
+ }
bailout:
- if (jpegBuf) (*env)->ReleasePrimitiveArrayCritical(env, dst, jpegBuf, 0);
- if (srcBuf) (*env)->ReleasePrimitiveArrayCritical(env, src, srcBuf, 0);
+ SAFE_RELEASE(dst, jpegBuf);
+ SAFE_RELEASE(src, srcBuf);
return (jint)jpegSize;
}
jint jpegQual, jint flags)
{
if (pf < 0 || pf >= org_libjpegturbo_turbojpeg_TJ_NUMPF)
- _throwarg("Invalid argument in compress()");
+ THROW_ARG("Invalid argument in compress()");
if (tjPixelSize[pf] != sizeof(jint))
- _throwarg("Pixel format must be 32-bit when compressing from an integer buffer.");
+ THROW_ARG("Pixel format must be 32-bit when compressing from an integer buffer.");
return TJCompressor_compress(env, obj, src, sizeof(jint), x, y, width,
stride * sizeof(jint), height, pf, dst,
jint flags)
{
if (pf < 0 || pf >= org_libjpegturbo_turbojpeg_TJ_NUMPF)
- _throwarg("Invalid argument in compress()");
+ THROW_ARG("Invalid argument in compress()");
if (tjPixelSize[pf] != sizeof(jint))
- _throwarg("Pixel format must be 32-bit when compressing from an integer buffer.");
+ THROW_ARG("Pixel format must be 32-bit when compressing from an integer buffer.");
return TJCompressor_compress(env, obj, src, sizeof(jint), 0, 0, width,
stride * sizeof(jint), height, pf, dst,
int *srcOffsets = NULL, *srcStrides = NULL;
int nc = (subsamp == org_libjpegturbo_turbojpeg_TJ_SAMP_GRAY ? 1 : 3), i;
- gethandle();
+ GET_HANDLE();
if (subsamp < 0 || subsamp >= org_libjpegturbo_turbojpeg_TJ_NUMSAMP)
- _throwarg("Invalid argument in compressFromYUV()");
+ THROW_ARG("Invalid argument in compressFromYUV()");
if (org_libjpegturbo_turbojpeg_TJ_NUMSAMP != TJ_NUMSAMP)
- _throwarg("Mismatch between Java and C API");
+ THROW_ARG("Mismatch between Java and C API");
if ((*env)->GetArrayLength(env, srcobjs) < nc)
- _throwarg("Planes array is too small for the subsampling type");
+ THROW_ARG("Planes array is too small for the subsampling type");
if ((*env)->GetArrayLength(env, jSrcOffsets) < nc)
- _throwarg("Offsets array is too small for the subsampling type");
+ THROW_ARG("Offsets array is too small for the subsampling type");
if ((*env)->GetArrayLength(env, jSrcStrides) < nc)
- _throwarg("Strides array is too small for the subsampling type");
+ THROW_ARG("Strides array is too small for the subsampling type");
jpegSize = tjBufSize(width, height, subsamp);
if ((*env)->GetArrayLength(env, dst) < (jsize)jpegSize)
- _throwarg("Destination buffer is not large enough");
+ THROW_ARG("Destination buffer is not large enough");
if (ProcessSystemProperties(env) < 0) goto bailout;
- bailif0(srcOffsets = (*env)->GetPrimitiveArrayCritical(env, jSrcOffsets, 0));
- bailif0(srcStrides = (*env)->GetPrimitiveArrayCritical(env, jSrcStrides, 0));
+#define RELEASE_ARRAYS_COMPRESSFROMYUV() { \
+ SAFE_RELEASE(dst, jpegBuf); \
+ for (i = 0; i < nc; i++) \
+ SAFE_RELEASE(jSrcPlanes[i], srcPlanes[i]); \
+ SAFE_RELEASE(jSrcStrides, srcStrides); \
+ SAFE_RELEASE(jSrcOffsets, srcOffsets); \
+}
+
+ BAILIF0(srcOffsets = (*env)->GetPrimitiveArrayCritical(env, jSrcOffsets, 0));
+ BAILIF0(srcStrides = (*env)->GetPrimitiveArrayCritical(env, jSrcStrides, 0));
for (i = 0; i < nc; i++) {
int planeSize = tjPlaneSizeYUV(i, width, srcStrides[i], height, subsamp);
int pw = tjPlaneWidth(i, width, subsamp);
- if (planeSize < 0 || pw < 0)
- _throwarg(tjGetErrorStr());
+ if (planeSize < 0 || pw < 0) {
+ RELEASE_ARRAYS_COMPRESSFROMYUV();
+ THROW_ARG(tjGetErrorStr());
+ }
- if (srcOffsets[i] < 0)
- _throwarg("Invalid argument in compressFromYUV()");
- if (srcStrides[i] < 0 && srcOffsets[i] - planeSize + pw < 0)
- _throwarg("Negative plane stride would cause memory to be accessed below plane boundary");
+ if (srcOffsets[i] < 0) {
+ RELEASE_ARRAYS_COMPRESSFROMYUV();
+ THROW_ARG("Invalid argument in compressFromYUV()");
+ }
+ if (srcStrides[i] < 0 && srcOffsets[i] - planeSize + pw < 0) {
+ RELEASE_ARRAYS_COMPRESSFROMYUV();
+ THROW_ARG("Negative plane stride would cause memory to be accessed below plane boundary");
+ }
- bailif0(jSrcPlanes[i] = (*env)->GetObjectArrayElement(env, srcobjs, i));
- if ((*env)->GetArrayLength(env, jSrcPlanes[i]) < srcOffsets[i] + planeSize)
- _throwarg("Source plane is not large enough");
+ BAILIF0(jSrcPlanes[i] = (*env)->GetObjectArrayElement(env, srcobjs, i));
+ if ((*env)->GetArrayLength(env, jSrcPlanes[i]) <
+ srcOffsets[i] + planeSize) {
+ RELEASE_ARRAYS_COMPRESSFROMYUV();
+ THROW_ARG("Source plane is not large enough");
+ }
- bailif0(srcPlanes[i] =
+ BAILIF0(srcPlanes[i] =
(*env)->GetPrimitiveArrayCritical(env, jSrcPlanes[i], 0));
srcPlanes[i] = &srcPlanes[i][srcOffsets[i]];
}
- bailif0(jpegBuf = (*env)->GetPrimitiveArrayCritical(env, dst, 0));
+ BAILIF0(jpegBuf = (*env)->GetPrimitiveArrayCritical(env, dst, 0));
if (tjCompressFromYUVPlanes(handle, srcPlanes, width, srcStrides, height,
subsamp, &jpegBuf, &jpegSize, jpegQual,
- flags | TJFLAG_NOREALLOC) == -1)
- _throwtj();
+ flags | TJFLAG_NOREALLOC) == -1) {
+ RELEASE_ARRAYS_COMPRESSFROMYUV();
+ THROW_TJ();
+ }
bailout:
- if (jpegBuf) (*env)->ReleasePrimitiveArrayCritical(env, dst, jpegBuf, 0);
- for (i = 0; i < nc; i++) {
- if (srcPlanes[i] && jSrcPlanes[i])
- (*env)->ReleasePrimitiveArrayCritical(env, jSrcPlanes[i],
- (unsigned char *)srcPlanes[i], 0);
- }
- if (srcStrides)
- (*env)->ReleasePrimitiveArrayCritical(env, jSrcStrides, srcStrides, 0);
- if (srcOffsets)
- (*env)->ReleasePrimitiveArrayCritical(env, jSrcOffsets, srcOffsets, 0);
+ RELEASE_ARRAYS_COMPRESSFROMYUV();
return (jint)jpegSize;
}
int *dstOffsets = NULL, *dstStrides = NULL;
int nc = (subsamp == org_libjpegturbo_turbojpeg_TJ_SAMP_GRAY ? 1 : 3), i;
- gethandle();
+ GET_HANDLE();
if (pf < 0 || pf >= org_libjpegturbo_turbojpeg_TJ_NUMPF || width < 1 ||
height < 1 || pitch < 0 || subsamp < 0 ||
subsamp >= org_libjpegturbo_turbojpeg_TJ_NUMSAMP)
- _throwarg("Invalid argument in encodeYUV()");
+ THROW_ARG("Invalid argument in encodeYUV()");
if (org_libjpegturbo_turbojpeg_TJ_NUMPF != TJ_NUMPF ||
org_libjpegturbo_turbojpeg_TJ_NUMSAMP != TJ_NUMSAMP)
- _throwarg("Mismatch between Java and C API");
+ THROW_ARG("Mismatch between Java and C API");
if ((*env)->GetArrayLength(env, dstobjs) < nc)
- _throwarg("Planes array is too small for the subsampling type");
+ THROW_ARG("Planes array is too small for the subsampling type");
if ((*env)->GetArrayLength(env, jDstOffsets) < nc)
- _throwarg("Offsets array is too small for the subsampling type");
+ THROW_ARG("Offsets array is too small for the subsampling type");
if ((*env)->GetArrayLength(env, jDstStrides) < nc)
- _throwarg("Strides array is too small for the subsampling type");
+ THROW_ARG("Strides array is too small for the subsampling type");
actualPitch = (pitch == 0) ? width * tjPixelSize[pf] : pitch;
arraySize = (y + height - 1) * actualPitch + (x + width) * tjPixelSize[pf];
if ((*env)->GetArrayLength(env, src) * srcElementSize < arraySize)
- _throwarg("Source buffer is not large enough");
+ THROW_ARG("Source buffer is not large enough");
+
+#define RELEASE_ARRAYS_ENCODEYUV() { \
+ SAFE_RELEASE(src, srcBuf); \
+ for (i = 0; i < nc; i++) \
+ SAFE_RELEASE(jDstPlanes[i], dstPlanes[i]); \
+ SAFE_RELEASE(jDstStrides, dstStrides); \
+ SAFE_RELEASE(jDstOffsets, dstOffsets); \
+}
- bailif0(dstOffsets = (*env)->GetPrimitiveArrayCritical(env, jDstOffsets, 0));
- bailif0(dstStrides = (*env)->GetPrimitiveArrayCritical(env, jDstStrides, 0));
+ BAILIF0(dstOffsets = (*env)->GetPrimitiveArrayCritical(env, jDstOffsets, 0));
+ BAILIF0(dstStrides = (*env)->GetPrimitiveArrayCritical(env, jDstStrides, 0));
for (i = 0; i < nc; i++) {
int planeSize = tjPlaneSizeYUV(i, width, dstStrides[i], height, subsamp);
int pw = tjPlaneWidth(i, width, subsamp);
- if (planeSize < 0 || pw < 0)
- _throwarg(tjGetErrorStr());
+ if (planeSize < 0 || pw < 0) {
+ RELEASE_ARRAYS_ENCODEYUV();
+ THROW_ARG(tjGetErrorStr());
+ }
- if (dstOffsets[i] < 0)
- _throwarg("Invalid argument in encodeYUV()");
- if (dstStrides[i] < 0 && dstOffsets[i] - planeSize + pw < 0)
- _throwarg("Negative plane stride would cause memory to be accessed below plane boundary");
+ if (dstOffsets[i] < 0) {
+ RELEASE_ARRAYS_ENCODEYUV();
+ THROW_ARG("Invalid argument in encodeYUV()");
+ }
+ if (dstStrides[i] < 0 && dstOffsets[i] - planeSize + pw < 0) {
+ RELEASE_ARRAYS_ENCODEYUV();
+ THROW_ARG("Negative plane stride would cause memory to be accessed below plane boundary");
+ }
- bailif0(jDstPlanes[i] = (*env)->GetObjectArrayElement(env, dstobjs, i));
- if ((*env)->GetArrayLength(env, jDstPlanes[i]) < dstOffsets[i] + planeSize)
- _throwarg("Destination plane is not large enough");
+ BAILIF0(jDstPlanes[i] = (*env)->GetObjectArrayElement(env, dstobjs, i));
+ if ((*env)->GetArrayLength(env, jDstPlanes[i]) <
+ dstOffsets[i] + planeSize) {
+ RELEASE_ARRAYS_ENCODEYUV();
+ THROW_ARG("Destination plane is not large enough");
+ }
- bailif0(dstPlanes[i] =
+ BAILIF0(dstPlanes[i] =
(*env)->GetPrimitiveArrayCritical(env, jDstPlanes[i], 0));
dstPlanes[i] = &dstPlanes[i][dstOffsets[i]];
}
- bailif0(srcBuf = (*env)->GetPrimitiveArrayCritical(env, src, 0));
+ BAILIF0(srcBuf = (*env)->GetPrimitiveArrayCritical(env, src, 0));
if (tjEncodeYUVPlanes(handle, &srcBuf[y * actualPitch + x * tjPixelSize[pf]],
width, pitch, height, pf, dstPlanes, dstStrides,
- subsamp, flags) == -1)
- _throwtj();
+ subsamp, flags) == -1) {
+ RELEASE_ARRAYS_ENCODEYUV();
+ THROW_TJ();
+ }
bailout:
- if (srcBuf) (*env)->ReleasePrimitiveArrayCritical(env, src, srcBuf, 0);
- for (i = 0; i < nc; i++) {
- if (dstPlanes[i] && jDstPlanes[i])
- (*env)->ReleasePrimitiveArrayCritical(env, jDstPlanes[i], dstPlanes[i],
- 0);
- }
- if (dstStrides)
- (*env)->ReleasePrimitiveArrayCritical(env, jDstStrides, dstStrides, 0);
- if (dstOffsets)
- (*env)->ReleasePrimitiveArrayCritical(env, jDstOffsets, dstOffsets, 0);
+ RELEASE_ARRAYS_ENCODEYUV();
}
/* TurboJPEG 1.4.x: TJCompressor::encodeYUV() byte source */
jintArray jDstOffsets, jintArray jDstStrides, jint subsamp, jint flags)
{
if (pf < 0 || pf >= org_libjpegturbo_turbojpeg_TJ_NUMPF)
- _throwarg("Invalid argument in encodeYUV()");
+ THROW_ARG("Invalid argument in encodeYUV()");
if (tjPixelSize[pf] != sizeof(jint))
- _throwarg("Pixel format must be 32-bit when encoding from an integer buffer.");
+ THROW_ARG("Pixel format must be 32-bit when encoding from an integer buffer.");
TJCompressor_encodeYUV(env, obj, src, sizeof(jint), x, y, width,
stride * sizeof(jint), height, pf, dstobjs,
return;
}
-JNIEXPORT void JNICALL TJCompressor_encodeYUV_12
+static void JNICALL TJCompressor_encodeYUV_12
(JNIEnv *env, jobject obj, jarray src, jint srcElementSize, jint width,
jint pitch, jint height, jint pf, jbyteArray dst, jint subsamp, jint flags)
{
jsize arraySize = 0;
unsigned char *srcBuf = NULL, *dstBuf = NULL;
- gethandle();
+ GET_HANDLE();
if (pf < 0 || pf >= org_libjpegturbo_turbojpeg_TJ_NUMPF || width < 1 ||
height < 1 || pitch < 0)
- _throwarg("Invalid argument in encodeYUV()");
+ THROW_ARG("Invalid argument in encodeYUV()");
if (org_libjpegturbo_turbojpeg_TJ_NUMPF != TJ_NUMPF)
- _throwarg("Mismatch between Java and C API");
+ THROW_ARG("Mismatch between Java and C API");
arraySize = (pitch == 0) ? width * tjPixelSize[pf] * height : pitch * height;
if ((*env)->GetArrayLength(env, src) * srcElementSize < arraySize)
- _throwarg("Source buffer is not large enough");
+ THROW_ARG("Source buffer is not large enough");
if ((*env)->GetArrayLength(env, dst) <
(jsize)tjBufSizeYUV(width, height, subsamp))
- _throwarg("Destination buffer is not large enough");
+ THROW_ARG("Destination buffer is not large enough");
- bailif0(srcBuf = (*env)->GetPrimitiveArrayCritical(env, src, 0));
- bailif0(dstBuf = (*env)->GetPrimitiveArrayCritical(env, dst, 0));
+ BAILIF0(srcBuf = (*env)->GetPrimitiveArrayCritical(env, src, 0));
+ BAILIF0(dstBuf = (*env)->GetPrimitiveArrayCritical(env, dst, 0));
if (tjEncodeYUV2(handle, srcBuf, width, pitch, height, pf, dstBuf, subsamp,
- flags) == -1)
- _throwtj();
+ flags) == -1) {
+ SAFE_RELEASE(dst, dstBuf);
+ SAFE_RELEASE(src, srcBuf);
+ THROW_TJ();
+ }
bailout:
- if (dstBuf) (*env)->ReleasePrimitiveArrayCritical(env, dst, dstBuf, 0);
- if (srcBuf) (*env)->ReleasePrimitiveArrayCritical(env, src, srcBuf, 0);
+ SAFE_RELEASE(dst, dstBuf);
+ SAFE_RELEASE(src, srcBuf);
}
/* TurboJPEG 1.2.x: TJCompressor::encodeYUV() byte source */
jint height, jint pf, jbyteArray dst, jint subsamp, jint flags)
{
if (pf < 0 || pf >= org_libjpegturbo_turbojpeg_TJ_NUMPF)
- _throwarg("Invalid argument in encodeYUV()");
+ THROW_ARG("Invalid argument in encodeYUV()");
if (tjPixelSize[pf] != sizeof(jint))
- _throwarg("Pixel format must be 32-bit when encoding from an integer buffer.");
+ THROW_ARG("Pixel format must be 32-bit when encoding from an integer buffer.");
TJCompressor_encodeYUV_12(env, obj, src, sizeof(jint), width,
stride * sizeof(jint), height, pf, dst, subsamp,
{
tjhandle handle = 0;
- gethandle();
+ GET_HANDLE();
- if (tjDestroy(handle) == -1) _throwtj();
+ if (tjDestroy(handle) == -1) THROW_TJ();
(*env)->SetLongField(env, obj, _fid, 0);
bailout:
tjhandle handle;
if ((handle = tjInitDecompress()) == NULL)
- _throw(tjGetErrorStr(), "org/libjpegturbo/turbojpeg/TJException");
+ THROW(tjGetErrorStr(), "org/libjpegturbo/turbojpeg/TJException");
- bailif0(cls = (*env)->GetObjectClass(env, obj));
- bailif0(fid = (*env)->GetFieldID(env, cls, "handle", "J"));
+ BAILIF0(cls = (*env)->GetObjectClass(env, obj));
+ BAILIF0(fid = (*env)->GetFieldID(env, cls, "handle", "J"));
(*env)->SetLongField(env, obj, fid, (size_t)handle);
bailout:
jobjectArray sfjava = NULL;
if ((sf = tjGetScalingFactors(&n)) == NULL || n == 0)
- _throwarg(tjGetErrorStr());
+ THROW_ARG(tjGetErrorStr());
- bailif0(sfcls = (*env)->FindClass(env,
+ BAILIF0(sfcls = (*env)->FindClass(env,
"org/libjpegturbo/turbojpeg/TJScalingFactor"));
- bailif0(sfjava = (jobjectArray)(*env)->NewObjectArray(env, n, sfcls, 0));
+ BAILIF0(sfjava = (jobjectArray)(*env)->NewObjectArray(env, n, sfcls, 0));
for (i = 0; i < n; i++) {
- bailif0(sfobj = (*env)->AllocObject(env, sfcls));
- bailif0(fid = (*env)->GetFieldID(env, sfcls, "num", "I"));
+ BAILIF0(sfobj = (*env)->AllocObject(env, sfcls));
+ BAILIF0(fid = (*env)->GetFieldID(env, sfcls, "num", "I"));
(*env)->SetIntField(env, sfobj, fid, sf[i].num);
- bailif0(fid = (*env)->GetFieldID(env, sfcls, "denom", "I"));
+ BAILIF0(fid = (*env)->GetFieldID(env, sfcls, "denom", "I"));
(*env)->SetIntField(env, sfobj, fid, sf[i].denom);
(*env)->SetObjectArrayElement(env, sfjava, i, sfobj);
}
unsigned char *jpegBuf = NULL;
int width = 0, height = 0, jpegSubsamp = -1, jpegColorspace = -1;
- gethandle();
+ GET_HANDLE();
if ((*env)->GetArrayLength(env, src) < jpegSize)
- _throwarg("Source buffer is not large enough");
+ THROW_ARG("Source buffer is not large enough");
- bailif0(jpegBuf = (*env)->GetPrimitiveArrayCritical(env, src, 0));
+ BAILIF0(jpegBuf = (*env)->GetPrimitiveArrayCritical(env, src, 0));
if (tjDecompressHeader3(handle, jpegBuf, (unsigned long)jpegSize, &width,
- &height, &jpegSubsamp, &jpegColorspace) == -1)
- _throwtj();
+ &height, &jpegSubsamp, &jpegColorspace) == -1) {
+ SAFE_RELEASE(src, jpegBuf);
+ THROW_TJ();
+ }
- (*env)->ReleasePrimitiveArrayCritical(env, src, jpegBuf, 0);
- jpegBuf = NULL;
+ SAFE_RELEASE(src, jpegBuf);
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "jpegSubsamp", "I"));
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "jpegSubsamp", "I"));
(*env)->SetIntField(env, obj, _fid, jpegSubsamp);
if ((_fid = (*env)->GetFieldID(env, _cls, "jpegColorspace", "I")) == 0)
(*env)->ExceptionClear(env);
else
(*env)->SetIntField(env, obj, _fid, jpegColorspace);
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "jpegWidth", "I"));
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "jpegWidth", "I"));
(*env)->SetIntField(env, obj, _fid, width);
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "jpegHeight", "I"));
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "jpegHeight", "I"));
(*env)->SetIntField(env, obj, _fid, height);
bailout:
- if (jpegBuf) (*env)->ReleasePrimitiveArrayCritical(env, src, jpegBuf, 0);
+ SAFE_RELEASE(src, jpegBuf);
}
static void TJDecompressor_decompress
jsize arraySize = 0, actualPitch;
unsigned char *jpegBuf = NULL, *dstBuf = NULL;
- gethandle();
+ GET_HANDLE();
if (pf < 0 || pf >= org_libjpegturbo_turbojpeg_TJ_NUMPF)
- _throwarg("Invalid argument in decompress()");
+ THROW_ARG("Invalid argument in decompress()");
if (org_libjpegturbo_turbojpeg_TJ_NUMPF != TJ_NUMPF)
- _throwarg("Mismatch between Java and C API");
+ THROW_ARG("Mismatch between Java and C API");
if ((*env)->GetArrayLength(env, src) < jpegSize)
- _throwarg("Source buffer is not large enough");
+ THROW_ARG("Source buffer is not large enough");
actualPitch = (pitch == 0) ? width * tjPixelSize[pf] : pitch;
arraySize = (y + height - 1) * actualPitch + (x + width) * tjPixelSize[pf];
if ((*env)->GetArrayLength(env, dst) * dstElementSize < arraySize)
- _throwarg("Destination buffer is not large enough");
+ THROW_ARG("Destination buffer is not large enough");
- bailif0(jpegBuf = (*env)->GetPrimitiveArrayCritical(env, src, 0));
- bailif0(dstBuf = (*env)->GetPrimitiveArrayCritical(env, dst, 0));
+ BAILIF0(jpegBuf = (*env)->GetPrimitiveArrayCritical(env, src, 0));
+ BAILIF0(dstBuf = (*env)->GetPrimitiveArrayCritical(env, dst, 0));
if (tjDecompress2(handle, jpegBuf, (unsigned long)jpegSize,
&dstBuf[y * actualPitch + x * tjPixelSize[pf]], width,
- pitch, height, pf, flags) == -1)
- _throwtj();
+ pitch, height, pf, flags) == -1) {
+ SAFE_RELEASE(dst, dstBuf);
+ SAFE_RELEASE(src, jpegBuf);
+ THROW_TJ();
+ }
bailout:
- if (dstBuf) (*env)->ReleasePrimitiveArrayCritical(env, dst, dstBuf, 0);
- if (jpegBuf) (*env)->ReleasePrimitiveArrayCritical(env, src, jpegBuf, 0);
+ SAFE_RELEASE(dst, dstBuf);
+ SAFE_RELEASE(src, jpegBuf);
}
/* TurboJPEG 1.3.x: TJDecompressor::decompress() byte destination */
jint x, jint y, jint width, jint stride, jint height, jint pf, jint flags)
{
if (pf < 0 || pf >= org_libjpegturbo_turbojpeg_TJ_NUMPF)
- _throwarg("Invalid argument in decompress()");
+ THROW_ARG("Invalid argument in decompress()");
if (tjPixelSize[pf] != sizeof(jint))
- _throwarg("Pixel format must be 32-bit when decompressing to an integer buffer.");
+ THROW_ARG("Pixel format must be 32-bit when decompressing to an integer buffer.");
TJDecompressor_decompress(env, obj, src, jpegSize, dst, sizeof(jint), x, y,
width, stride * sizeof(jint), height, pf, flags);
jint width, jint stride, jint height, jint pf, jint flags)
{
if (pf < 0 || pf >= org_libjpegturbo_turbojpeg_TJ_NUMPF)
- _throwarg("Invalid argument in decompress()");
+ THROW_ARG("Invalid argument in decompress()");
if (tjPixelSize[pf] != sizeof(jint))
- _throwarg("Pixel format must be 32-bit when decompressing to an integer buffer.");
+ THROW_ARG("Pixel format must be 32-bit when decompressing to an integer buffer.");
TJDecompressor_decompress(env, obj, src, jpegSize, dst, sizeof(jint), 0, 0,
width, stride * sizeof(jint), height, pf, flags);
int nc = 0, i, width, height, scaledWidth, scaledHeight, nsf = 0;
tjscalingfactor *sf;
- gethandle();
+ GET_HANDLE();
if ((*env)->GetArrayLength(env, src) < jpegSize)
- _throwarg("Source buffer is not large enough");
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "jpegSubsamp", "I"));
+ THROW_ARG("Source buffer is not large enough");
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "jpegSubsamp", "I"));
jpegSubsamp = (int)(*env)->GetIntField(env, obj, _fid);
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "jpegWidth", "I"));
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "jpegWidth", "I"));
jpegWidth = (int)(*env)->GetIntField(env, obj, _fid);
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "jpegHeight", "I"));
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "jpegHeight", "I"));
jpegHeight = (int)(*env)->GetIntField(env, obj, _fid);
nc = (jpegSubsamp == org_libjpegturbo_turbojpeg_TJ_SAMP_GRAY ? 1 : 3);
if (height == 0) height = jpegHeight;
sf = tjGetScalingFactors(&nsf);
if (!sf || nsf < 1)
- _throwarg(tjGetErrorStr());
+ THROW_ARG(tjGetErrorStr());
for (i = 0; i < nsf; i++) {
scaledWidth = TJSCALED(jpegWidth, sf[i]);
scaledHeight = TJSCALED(jpegHeight, sf[i]);
break;
}
if (i >= nsf)
- _throwarg("Could not scale down to desired image dimensions");
+ THROW_ARG("Could not scale down to desired image dimensions");
+
+#define RELEASE_ARRAYS_DECOMPRESSTOYUV() { \
+ SAFE_RELEASE(src, jpegBuf); \
+ for (i = 0; i < nc; i++) \
+ SAFE_RELEASE(jDstPlanes[i], dstPlanes[i]); \
+ SAFE_RELEASE(jDstStrides, dstStrides); \
+ SAFE_RELEASE(jDstOffsets, dstOffsets); \
+}
- bailif0(dstOffsets = (*env)->GetPrimitiveArrayCritical(env, jDstOffsets, 0));
- bailif0(dstStrides = (*env)->GetPrimitiveArrayCritical(env, jDstStrides, 0));
+ BAILIF0(dstOffsets = (*env)->GetPrimitiveArrayCritical(env, jDstOffsets, 0));
+ BAILIF0(dstStrides = (*env)->GetPrimitiveArrayCritical(env, jDstStrides, 0));
for (i = 0; i < nc; i++) {
int planeSize = tjPlaneSizeYUV(i, scaledWidth, dstStrides[i], scaledHeight,
jpegSubsamp);
int pw = tjPlaneWidth(i, scaledWidth, jpegSubsamp);
- if (planeSize < 0 || pw < 0)
- _throwarg(tjGetErrorStr());
+ if (planeSize < 0 || pw < 0) {
+ RELEASE_ARRAYS_DECOMPRESSTOYUV();
+ THROW_ARG(tjGetErrorStr());
+ }
- if (dstOffsets[i] < 0)
- _throwarg("Invalid argument in decompressToYUV()");
- if (dstStrides[i] < 0 && dstOffsets[i] - planeSize + pw < 0)
- _throwarg("Negative plane stride would cause memory to be accessed below plane boundary");
+ if (dstOffsets[i] < 0) {
+ RELEASE_ARRAYS_DECOMPRESSTOYUV();
+ THROW_ARG("Invalid argument in decompressToYUV()");
+ }
+ if (dstStrides[i] < 0 && dstOffsets[i] - planeSize + pw < 0) {
+ RELEASE_ARRAYS_DECOMPRESSTOYUV();
+ THROW_ARG("Negative plane stride would cause memory to be accessed below plane boundary");
+ }
- bailif0(jDstPlanes[i] = (*env)->GetObjectArrayElement(env, dstobjs, i));
- if ((*env)->GetArrayLength(env, jDstPlanes[i]) < dstOffsets[i] + planeSize)
- _throwarg("Destination plane is not large enough");
+ BAILIF0(jDstPlanes[i] = (*env)->GetObjectArrayElement(env, dstobjs, i));
+ if ((*env)->GetArrayLength(env, jDstPlanes[i]) <
+ dstOffsets[i] + planeSize) {
+ RELEASE_ARRAYS_DECOMPRESSTOYUV();
+ THROW_ARG("Destination plane is not large enough");
+ }
- bailif0(dstPlanes[i] =
+ BAILIF0(dstPlanes[i] =
(*env)->GetPrimitiveArrayCritical(env, jDstPlanes[i], 0));
dstPlanes[i] = &dstPlanes[i][dstOffsets[i]];
}
- bailif0(jpegBuf = (*env)->GetPrimitiveArrayCritical(env, src, 0));
+ BAILIF0(jpegBuf = (*env)->GetPrimitiveArrayCritical(env, src, 0));
if (tjDecompressToYUVPlanes(handle, jpegBuf, (unsigned long)jpegSize,
dstPlanes, desiredWidth, dstStrides,
- desiredHeight, flags) == -1)
- _throwtj();
+ desiredHeight, flags) == -1) {
+ RELEASE_ARRAYS_DECOMPRESSTOYUV();
+ THROW_TJ();
+ }
bailout:
- if (jpegBuf) (*env)->ReleasePrimitiveArrayCritical(env, src, jpegBuf, 0);
- for (i = 0; i < nc; i++) {
- if (dstPlanes[i] && jDstPlanes[i])
- (*env)->ReleasePrimitiveArrayCritical(env, jDstPlanes[i], dstPlanes[i],
- 0);
- }
- if (dstStrides)
- (*env)->ReleasePrimitiveArrayCritical(env, jDstStrides, dstStrides, 0);
- if (dstOffsets)
- (*env)->ReleasePrimitiveArrayCritical(env, jDstOffsets, dstOffsets, 0);
+ RELEASE_ARRAYS_DECOMPRESSTOYUV();
}
/* TurboJPEG 1.2.x: TJDecompressor::decompressToYUV() */
unsigned char *jpegBuf = NULL, *dstBuf = NULL;
int jpegSubsamp = -1, jpegWidth = 0, jpegHeight = 0;
- gethandle();
+ GET_HANDLE();
if ((*env)->GetArrayLength(env, src) < jpegSize)
- _throwarg("Source buffer is not large enough");
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "jpegSubsamp", "I"));
+ THROW_ARG("Source buffer is not large enough");
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "jpegSubsamp", "I"));
jpegSubsamp = (int)(*env)->GetIntField(env, obj, _fid);
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "jpegWidth", "I"));
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "jpegWidth", "I"));
jpegWidth = (int)(*env)->GetIntField(env, obj, _fid);
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "jpegHeight", "I"));
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "jpegHeight", "I"));
jpegHeight = (int)(*env)->GetIntField(env, obj, _fid);
if ((*env)->GetArrayLength(env, dst) <
(jsize)tjBufSizeYUV(jpegWidth, jpegHeight, jpegSubsamp))
- _throwarg("Destination buffer is not large enough");
+ THROW_ARG("Destination buffer is not large enough");
- bailif0(jpegBuf = (*env)->GetPrimitiveArrayCritical(env, src, 0));
- bailif0(dstBuf = (*env)->GetPrimitiveArrayCritical(env, dst, 0));
+ BAILIF0(jpegBuf = (*env)->GetPrimitiveArrayCritical(env, src, 0));
+ BAILIF0(dstBuf = (*env)->GetPrimitiveArrayCritical(env, dst, 0));
if (tjDecompressToYUV(handle, jpegBuf, (unsigned long)jpegSize, dstBuf,
- flags) == -1)
- _throwtj();
+ flags) == -1) {
+ SAFE_RELEASE(dst, dstBuf);
+ SAFE_RELEASE(src, jpegBuf);
+ THROW_TJ();
+ }
bailout:
- if (dstBuf) (*env)->ReleasePrimitiveArrayCritical(env, dst, dstBuf, 0);
- if (jpegBuf) (*env)->ReleasePrimitiveArrayCritical(env, src, jpegBuf, 0);
+ SAFE_RELEASE(dst, dstBuf);
+ SAFE_RELEASE(src, jpegBuf);
}
static void TJDecompressor_decodeYUV
int *srcOffsets = NULL, *srcStrides = NULL;
int nc = (subsamp == org_libjpegturbo_turbojpeg_TJ_SAMP_GRAY ? 1 : 3), i;
- gethandle();
+ GET_HANDLE();
if (pf < 0 || pf >= org_libjpegturbo_turbojpeg_TJ_NUMPF || subsamp < 0 ||
subsamp >= org_libjpegturbo_turbojpeg_TJ_NUMSAMP)
- _throwarg("Invalid argument in decodeYUV()");
+ THROW_ARG("Invalid argument in decodeYUV()");
if (org_libjpegturbo_turbojpeg_TJ_NUMPF != TJ_NUMPF ||
org_libjpegturbo_turbojpeg_TJ_NUMSAMP != TJ_NUMSAMP)
- _throwarg("Mismatch between Java and C API");
+ THROW_ARG("Mismatch between Java and C API");
if ((*env)->GetArrayLength(env, srcobjs) < nc)
- _throwarg("Planes array is too small for the subsampling type");
+ THROW_ARG("Planes array is too small for the subsampling type");
if ((*env)->GetArrayLength(env, jSrcOffsets) < nc)
- _throwarg("Offsets array is too small for the subsampling type");
+ THROW_ARG("Offsets array is too small for the subsampling type");
if ((*env)->GetArrayLength(env, jSrcStrides) < nc)
- _throwarg("Strides array is too small for the subsampling type");
+ THROW_ARG("Strides array is too small for the subsampling type");
actualPitch = (pitch == 0) ? width * tjPixelSize[pf] : pitch;
arraySize = (y + height - 1) * actualPitch + (x + width) * tjPixelSize[pf];
if ((*env)->GetArrayLength(env, dst) * dstElementSize < arraySize)
- _throwarg("Destination buffer is not large enough");
+ THROW_ARG("Destination buffer is not large enough");
+
+#define RELEASE_ARRAYS_DECODEYUV() { \
+ SAFE_RELEASE(dst, dstBuf); \
+ for (i = 0; i < nc; i++) \
+ SAFE_RELEASE(jSrcPlanes[i], srcPlanes[i]); \
+ SAFE_RELEASE(jSrcStrides, srcStrides); \
+ SAFE_RELEASE(jSrcOffsets, srcOffsets); \
+}
- bailif0(srcOffsets = (*env)->GetPrimitiveArrayCritical(env, jSrcOffsets, 0));
- bailif0(srcStrides = (*env)->GetPrimitiveArrayCritical(env, jSrcStrides, 0));
+ BAILIF0(srcOffsets = (*env)->GetPrimitiveArrayCritical(env, jSrcOffsets, 0));
+ BAILIF0(srcStrides = (*env)->GetPrimitiveArrayCritical(env, jSrcStrides, 0));
for (i = 0; i < nc; i++) {
int planeSize = tjPlaneSizeYUV(i, width, srcStrides[i], height, subsamp);
int pw = tjPlaneWidth(i, width, subsamp);
- if (planeSize < 0 || pw < 0)
- _throwarg(tjGetErrorStr());
+ if (planeSize < 0 || pw < 0) {
+ RELEASE_ARRAYS_DECODEYUV();
+ THROW_ARG(tjGetErrorStr());
+ }
- if (srcOffsets[i] < 0)
- _throwarg("Invalid argument in decodeYUV()");
- if (srcStrides[i] < 0 && srcOffsets[i] - planeSize + pw < 0)
- _throwarg("Negative plane stride would cause memory to be accessed below plane boundary");
+ if (srcOffsets[i] < 0) {
+ RELEASE_ARRAYS_DECODEYUV();
+ THROW_ARG("Invalid argument in decodeYUV()");
+ }
+ if (srcStrides[i] < 0 && srcOffsets[i] - planeSize + pw < 0) {
+ RELEASE_ARRAYS_DECODEYUV();
+ THROW_ARG("Negative plane stride would cause memory to be accessed below plane boundary");
+ }
- bailif0(jSrcPlanes[i] = (*env)->GetObjectArrayElement(env, srcobjs, i));
- if ((*env)->GetArrayLength(env, jSrcPlanes[i]) < srcOffsets[i] + planeSize)
- _throwarg("Source plane is not large enough");
+ BAILIF0(jSrcPlanes[i] = (*env)->GetObjectArrayElement(env, srcobjs, i));
+ if ((*env)->GetArrayLength(env, jSrcPlanes[i]) <
+ srcOffsets[i] + planeSize) {
+ RELEASE_ARRAYS_DECODEYUV();
+ THROW_ARG("Source plane is not large enough");
+ }
- bailif0(srcPlanes[i] =
+ BAILIF0(srcPlanes[i] =
(*env)->GetPrimitiveArrayCritical(env, jSrcPlanes[i], 0));
srcPlanes[i] = &srcPlanes[i][srcOffsets[i]];
}
- bailif0(dstBuf = (*env)->GetPrimitiveArrayCritical(env, dst, 0));
+ BAILIF0(dstBuf = (*env)->GetPrimitiveArrayCritical(env, dst, 0));
if (tjDecodeYUVPlanes(handle, srcPlanes, srcStrides, subsamp,
&dstBuf[y * actualPitch + x * tjPixelSize[pf]], width,
- pitch, height, pf, flags) == -1)
- _throwtj();
+ pitch, height, pf, flags) == -1) {
+ RELEASE_ARRAYS_DECODEYUV();
+ THROW_TJ();
+ }
bailout:
- if (dstBuf) (*env)->ReleasePrimitiveArrayCritical(env, dst, dstBuf, 0);
- for (i = 0; i < nc; i++) {
- if (srcPlanes[i] && jSrcPlanes[i])
- (*env)->ReleasePrimitiveArrayCritical(env, jSrcPlanes[i],
- (unsigned char *)srcPlanes[i], 0);
- }
- if (srcStrides)
- (*env)->ReleasePrimitiveArrayCritical(env, jSrcStrides, srcStrides, 0);
- if (srcOffsets)
- (*env)->ReleasePrimitiveArrayCritical(env, jSrcOffsets, srcOffsets, 0);
+ RELEASE_ARRAYS_DECODEYUV();
}
/* TurboJPEG 1.4.x: TJDecompressor::decodeYUV() byte destination */
jint width, jint stride, jint height, jint pf, jint flags)
{
if (pf < 0 || pf >= org_libjpegturbo_turbojpeg_TJ_NUMPF)
- _throwarg("Invalid argument in decodeYUV()");
+ THROW_ARG("Invalid argument in decodeYUV()");
if (tjPixelSize[pf] != sizeof(jint))
- _throwarg("Pixel format must be 32-bit when decoding to an integer buffer.");
+ THROW_ARG("Pixel format must be 32-bit when decoding to an integer buffer.");
TJDecompressor_decodeYUV(env, obj, srcobjs, jSrcOffsets, jSrcStrides,
subsamp, dst, sizeof(jint), x, y, width,
tjhandle handle;
if ((handle = tjInitTransform()) == NULL)
- _throw(tjGetErrorStr(), "org/libjpegturbo/turbojpeg/TJException");
+ THROW(tjGetErrorStr(), "org/libjpegturbo/turbojpeg/TJException");
- bailif0(cls = (*env)->GetObjectClass(env, obj));
- bailif0(fid = (*env)->GetFieldID(env, cls, "handle", "J"));
+ BAILIF0(cls = (*env)->GetObjectClass(env, obj));
+ BAILIF0(fid = (*env)->GetFieldID(env, cls, "handle", "J"));
(*env)->SetLongField(env, obj, fid, (size_t)handle);
bailout:
jmethodID mid;
jfieldID fid;
- bailif0(bufobj = (*env)->NewDirectByteBuffer(env, coeffs,
+ BAILIF0(bufobj = (*env)->NewDirectByteBuffer(env, coeffs,
sizeof(short) * arrayRegion.w * arrayRegion.h));
- bailif0(cls = (*env)->FindClass(env, "java/nio/ByteOrder"));
- bailif0(mid = (*env)->GetStaticMethodID(env, cls, "nativeOrder",
+ BAILIF0(cls = (*env)->FindClass(env, "java/nio/ByteOrder"));
+ BAILIF0(mid = (*env)->GetStaticMethodID(env, cls, "nativeOrder",
"()Ljava/nio/ByteOrder;"));
- bailif0(borobj = (*env)->CallStaticObjectMethod(env, cls, mid));
- bailif0(cls = (*env)->GetObjectClass(env, bufobj));
- bailif0(mid = (*env)->GetMethodID(env, cls, "order",
+ BAILIF0(borobj = (*env)->CallStaticObjectMethod(env, cls, mid));
+ BAILIF0(cls = (*env)->GetObjectClass(env, bufobj));
+ BAILIF0(mid = (*env)->GetMethodID(env, cls, "order",
"(Ljava/nio/ByteOrder;)Ljava/nio/ByteBuffer;"));
(*env)->CallObjectMethod(env, bufobj, mid, borobj);
- bailif0(mid = (*env)->GetMethodID(env, cls, "asShortBuffer",
+ BAILIF0(mid = (*env)->GetMethodID(env, cls, "asShortBuffer",
"()Ljava/nio/ShortBuffer;"));
- bailif0(bufobj = (*env)->CallObjectMethod(env, bufobj, mid));
+ BAILIF0(bufobj = (*env)->CallObjectMethod(env, bufobj, mid));
- bailif0(cls = (*env)->FindClass(env, "java/awt/Rectangle"));
- bailif0(arrayRegionObj = (*env)->AllocObject(env, cls));
- bailif0(fid = (*env)->GetFieldID(env, cls, "x", "I"));
+ BAILIF0(cls = (*env)->FindClass(env, "java/awt/Rectangle"));
+ BAILIF0(arrayRegionObj = (*env)->AllocObject(env, cls));
+ BAILIF0(fid = (*env)->GetFieldID(env, cls, "x", "I"));
(*env)->SetIntField(env, arrayRegionObj, fid, arrayRegion.x);
- bailif0(fid = (*env)->GetFieldID(env, cls, "y", "I"));
+ BAILIF0(fid = (*env)->GetFieldID(env, cls, "y", "I"));
(*env)->SetIntField(env, arrayRegionObj, fid, arrayRegion.y);
- bailif0(fid = (*env)->GetFieldID(env, cls, "width", "I"));
+ BAILIF0(fid = (*env)->GetFieldID(env, cls, "width", "I"));
(*env)->SetIntField(env, arrayRegionObj, fid, arrayRegion.w);
- bailif0(fid = (*env)->GetFieldID(env, cls, "height", "I"));
+ BAILIF0(fid = (*env)->GetFieldID(env, cls, "height", "I"));
(*env)->SetIntField(env, arrayRegionObj, fid, arrayRegion.h);
- bailif0(planeRegionObj = (*env)->AllocObject(env, cls));
- bailif0(fid = (*env)->GetFieldID(env, cls, "x", "I"));
+ BAILIF0(planeRegionObj = (*env)->AllocObject(env, cls));
+ BAILIF0(fid = (*env)->GetFieldID(env, cls, "x", "I"));
(*env)->SetIntField(env, planeRegionObj, fid, planeRegion.x);
- bailif0(fid = (*env)->GetFieldID(env, cls, "y", "I"));
+ BAILIF0(fid = (*env)->GetFieldID(env, cls, "y", "I"));
(*env)->SetIntField(env, planeRegionObj, fid, planeRegion.y);
- bailif0(fid = (*env)->GetFieldID(env, cls, "width", "I"));
+ BAILIF0(fid = (*env)->GetFieldID(env, cls, "width", "I"));
(*env)->SetIntField(env, planeRegionObj, fid, planeRegion.w);
- bailif0(fid = (*env)->GetFieldID(env, cls, "height", "I"));
+ BAILIF0(fid = (*env)->GetFieldID(env, cls, "height", "I"));
(*env)->SetIntField(env, planeRegionObj, fid, planeRegion.h);
- bailif0(cls = (*env)->GetObjectClass(env, cfobj));
- bailif0(mid = (*env)->GetMethodID(env, cls, "customFilter",
+ BAILIF0(cls = (*env)->GetObjectClass(env, cfobj));
+ BAILIF0(mid = (*env)->GetMethodID(env, cls, "customFilter",
"(Ljava/nio/ShortBuffer;Ljava/awt/Rectangle;Ljava/awt/Rectangle;IILorg/libjpegturbo/turbojpeg/TJTransform;)V"));
(*env)->CallVoidMethod(env, cfobj, mid, bufobj, arrayRegionObj,
planeRegionObj, componentIndex, transformIndex, tobj);
jint *dstSizesi = NULL;
JNICustomFilterParams *params = NULL;
- gethandle();
+ GET_HANDLE();
if ((*env)->GetArrayLength(env, jsrcBuf) < jpegSize)
- _throwarg("Source buffer is not large enough");
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "jpegWidth", "I"));
+ THROW_ARG("Source buffer is not large enough");
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "jpegWidth", "I"));
jpegWidth = (int)(*env)->GetIntField(env, obj, _fid);
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "jpegHeight", "I"));
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "jpegHeight", "I"));
jpegHeight = (int)(*env)->GetIntField(env, obj, _fid);
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "jpegSubsamp", "I"));
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "jpegSubsamp", "I"));
jpegSubsamp = (int)(*env)->GetIntField(env, obj, _fid);
n = (*env)->GetArrayLength(env, dstobjs);
if (n != (*env)->GetArrayLength(env, tobjs))
- _throwarg("Mismatch between size of transforms array and destination buffers array");
+ THROW_ARG("Mismatch between size of transforms array and destination buffers array");
if ((dstBufs =
(unsigned char **)malloc(sizeof(unsigned char *) * n)) == NULL)
- _throwmem();
+ THROW_MEM();
if ((jdstBufs = (jbyteArray *)malloc(sizeof(jbyteArray) * n)) == NULL)
- _throwmem();
+ THROW_MEM();
if ((dstSizes = (unsigned long *)malloc(sizeof(unsigned long) * n)) == NULL)
- _throwmem();
+ THROW_MEM();
if ((t = (tjtransform *)malloc(sizeof(tjtransform) * n)) == NULL)
- _throwmem();
+ THROW_MEM();
if ((params = (JNICustomFilterParams *)malloc(sizeof(JNICustomFilterParams) *
n)) == NULL)
- _throwmem();
+ THROW_MEM();
for (i = 0; i < n; i++) {
dstBufs[i] = NULL; jdstBufs[i] = NULL; dstSizes[i] = 0;
memset(&t[i], 0, sizeof(tjtransform));
for (i = 0; i < n; i++) {
jobject tobj, cfobj;
- bailif0(tobj = (*env)->GetObjectArrayElement(env, tobjs, i));
- bailif0(_cls = (*env)->GetObjectClass(env, tobj));
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "op", "I"));
+ BAILIF0(tobj = (*env)->GetObjectArrayElement(env, tobjs, i));
+ BAILIF0(_cls = (*env)->GetObjectClass(env, tobj));
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "op", "I"));
t[i].op = (*env)->GetIntField(env, tobj, _fid);
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "options", "I"));
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "options", "I"));
t[i].options = (*env)->GetIntField(env, tobj, _fid);
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "x", "I"));
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "x", "I"));
t[i].r.x = (*env)->GetIntField(env, tobj, _fid);
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "y", "I"));
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "y", "I"));
t[i].r.y = (*env)->GetIntField(env, tobj, _fid);
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "width", "I"));
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "width", "I"));
t[i].r.w = (*env)->GetIntField(env, tobj, _fid);
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "height", "I"));
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "height", "I"));
t[i].r.h = (*env)->GetIntField(env, tobj, _fid);
- bailif0(_fid = (*env)->GetFieldID(env, _cls, "cf",
+ BAILIF0(_fid = (*env)->GetFieldID(env, _cls, "cf",
"Lorg/libjpegturbo/turbojpeg/TJCustomFilter;"));
cfobj = (*env)->GetObjectField(env, tobj, _fid);
if (cfobj) {
if (t[i].r.w != 0) w = t[i].r.w;
if (t[i].r.h != 0) h = t[i].r.h;
- bailif0(jdstBufs[i] = (*env)->GetObjectArrayElement(env, dstobjs, i));
+ BAILIF0(jdstBufs[i] = (*env)->GetObjectArrayElement(env, dstobjs, i));
if ((unsigned long)(*env)->GetArrayLength(env, jdstBufs[i]) <
tjBufSize(w, h, jpegSubsamp))
- _throwarg("Destination buffer is not large enough");
+ THROW_ARG("Destination buffer is not large enough");
}
- bailif0(jpegBuf = (*env)->GetPrimitiveArrayCritical(env, jsrcBuf, 0));
+ BAILIF0(jpegBuf = (*env)->GetPrimitiveArrayCritical(env, jsrcBuf, 0));
for (i = 0; i < n; i++)
- bailif0(dstBufs[i] =
+ BAILIF0(dstBufs[i] =
(*env)->GetPrimitiveArrayCritical(env, jdstBufs[i], 0));
if (tjTransform(handle, jpegBuf, jpegSize, n, dstBufs, dstSizes, t,
- flags | TJFLAG_NOREALLOC) == -1)
- _throwtj();
-
- for (i = 0; i < n; i++) {
- (*env)->ReleasePrimitiveArrayCritical(env, jdstBufs[i], dstBufs[i], 0);
- dstBufs[i] = NULL;
+ flags | TJFLAG_NOREALLOC) == -1) {
+ for (i = 0; i < n; i++)
+ SAFE_RELEASE(jdstBufs[i], dstBufs[i]);
+ SAFE_RELEASE(jsrcBuf, jpegBuf);
+ THROW_TJ();
}
- (*env)->ReleasePrimitiveArrayCritical(env, jsrcBuf, jpegBuf, 0);
- jpegBuf = NULL;
+
+ for (i = 0; i < n; i++)
+ SAFE_RELEASE(jdstBufs[i], dstBufs[i]);
+ SAFE_RELEASE(jsrcBuf, jpegBuf);
jdstSizes = (*env)->NewIntArray(env, n);
- bailif0(dstSizesi = (*env)->GetIntArrayElements(env, jdstSizes, 0));
+ BAILIF0(dstSizesi = (*env)->GetIntArrayElements(env, jdstSizes, 0));
for (i = 0; i < n; i++) dstSizesi[i] = (int)dstSizes[i];
bailout:
}
free(dstBufs);
}
- if (jpegBuf) (*env)->ReleasePrimitiveArrayCritical(env, jsrcBuf, jpegBuf, 0);
+ SAFE_RELEASE(jsrcBuf, jpegBuf);
if (jdstBufs) free(jdstBufs);
if (dstSizes) free(dstSizes);
if (t) free(t);
/*
- * Copyright (C)2009-2018 D. R. Commander. All Rights Reserved.
+ * Copyright (C)2009-2019 D. R. Commander. All Rights Reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
unsigned long);
#define PAD(v, p) ((v + (p) - 1) & (~((p) - 1)))
-#define isPow2(x) (((x) & (x - 1)) == 0)
+#define IS_POW2(x) (((x) & (x - 1)) == 0)
/* Error handling (based on example in example.txt) */
TJPF_UNKNOWN
};
-#define _throwg(m) { \
+#define THROWG(m) { \
snprintf(errStr, JMSG_LENGTH_MAX, "%s", m); \
retval = -1; goto bailout; \
}
-#define _throwunix(m) { \
+#define THROW_UNIX(m) { \
snprintf(errStr, JMSG_LENGTH_MAX, "%s\n%s", m, strerror(errno)); \
retval = -1; goto bailout; \
}
-#define _throw(m) { \
+#define THROW(m) { \
snprintf(this->errStr, JMSG_LENGTH_MAX, "%s", m); \
- this->isInstanceError = TRUE; _throwg(m) \
+ this->isInstanceError = TRUE; THROWG(m) \
}
-#define getinstance(handle) \
+#define GET_INSTANCE(handle) \
tjinstance *this = (tjinstance *)handle; \
j_compress_ptr cinfo = NULL; \
j_decompress_ptr dinfo = NULL; \
this->jerr.warning = FALSE; \
this->isInstanceError = FALSE;
-#define getcinstance(handle) \
+#define GET_CINSTANCE(handle) \
tjinstance *this = (tjinstance *)handle; \
j_compress_ptr cinfo = NULL; \
\
this->jerr.warning = FALSE; \
this->isInstanceError = FALSE;
-#define getdinstance(handle) \
+#define GET_DINSTANCE(handle) \
tjinstance *this = (tjinstance *)handle; \
j_decompress_ptr dinfo = NULL; \
\
int subsamp, int jpegQual, int flags)
{
int retval = 0;
+#ifndef NO_GETENV
char *env = NULL;
+#endif
cinfo->in_color_space = pf2cs[pixelFormat];
cinfo->input_components = tjPixelSize[pixelFormat];
retval = i; break;
}
}
+ /* Handle 4:4:4 images whose sampling factors are specified in
+ non-standard ways. */
+ if (dinfo->comp_info[0].h_samp_factor *
+ dinfo->comp_info[0].v_samp_factor <=
+ D_MAX_BLOCKS_IN_MCU / pixelsize[i] && i == TJSAMP_444) {
+ int match = 0;
+ for (k = 1; k < dinfo->num_components; k++) {
+ if (dinfo->comp_info[k].h_samp_factor ==
+ dinfo->comp_info[0].h_samp_factor &&
+ dinfo->comp_info[k].v_samp_factor ==
+ dinfo->comp_info[0].v_samp_factor)
+ match++;
+ if (match == dinfo->num_components - 1) {
+ retval = i; break;
+ }
+ }
+ }
}
}
return retval;
DLLEXPORT int tjDestroy(tjhandle handle)
{
- getinstance(handle);
+ GET_INSTANCE(handle);
if (setjmp(this->jerr.setjmp_buffer)) return -1;
if (this->init & COMPRESS) jpeg_destroy_compress(cinfo);
DLLEXPORT unsigned long tjBufSize(int width, int height, int jpegSubsamp)
{
- unsigned long retval = 0;
+ unsigned long long retval = 0;
int mcuw, mcuh, chromasf;
if (width < 1 || height < 1 || jpegSubsamp < 0 || jpegSubsamp >= NUMSUBOPT)
- _throwg("tjBufSize(): Invalid argument");
+ THROWG("tjBufSize(): Invalid argument");
/* This allows for rare corner cases in which a JPEG image can actually be
larger than the uncompressed input (we wouldn't mention it if it hadn't
mcuw = tjMCUWidth[jpegSubsamp];
mcuh = tjMCUHeight[jpegSubsamp];
chromasf = jpegSubsamp == TJSAMP_GRAY ? 0 : 4 * 64 / (mcuw * mcuh);
- retval = PAD(width, mcuw) * PAD(height, mcuh) * (2 + chromasf) + 2048;
+ retval = PAD(width, mcuw) * PAD(height, mcuh) * (2ULL + chromasf) + 2048ULL;
+ if (retval > (unsigned long long)((unsigned long)-1))
+ THROWG("tjBufSize(): Image is too large");
bailout:
- return retval;
+ return (unsigned long)retval;
}
DLLEXPORT unsigned long TJBUFSIZE(int width, int height)
{
- unsigned long retval = 0;
+ unsigned long long retval = 0;
if (width < 1 || height < 1)
- _throwg("TJBUFSIZE(): Invalid argument");
+ THROWG("TJBUFSIZE(): Invalid argument");
/* This allows for rare corner cases in which a JPEG image can actually be
larger than the uncompressed input (we wouldn't mention it if it hadn't
happened before.) */
- retval = PAD(width, 16) * PAD(height, 16) * 6 + 2048;
+ retval = PAD(width, 16) * PAD(height, 16) * 6ULL + 2048ULL;
+ if (retval > (unsigned long long)((unsigned long)-1))
+ THROWG("TJBUFSIZE(): Image is too large");
bailout:
- return retval;
+ return (unsigned long)retval;
}
DLLEXPORT unsigned long tjBufSizeYUV2(int width, int pad, int height,
int subsamp)
{
- int retval = 0, nc, i;
+ unsigned long long retval = 0;
+ int nc, i;
if (subsamp < 0 || subsamp >= NUMSUBOPT)
- _throwg("tjBufSizeYUV2(): Invalid argument");
+ THROWG("tjBufSizeYUV2(): Invalid argument");
nc = (subsamp == TJSAMP_GRAY ? 1 : 3);
for (i = 0; i < nc; i++) {
int ph = tjPlaneHeight(i, height, subsamp);
if (pw < 0 || ph < 0) return -1;
- else retval += stride * ph;
+ else retval += (unsigned long long)stride * ph;
}
+ if (retval > (unsigned long long)((unsigned long)-1))
+ THROWG("tjBufSizeYUV2(): Image is too large");
bailout:
- return retval;
+ return (unsigned long)retval;
}
DLLEXPORT unsigned long tjBufSizeYUV(int width, int height, int subsamp)
int pw, nc, retval = 0;
if (width < 1 || subsamp < 0 || subsamp >= TJ_NUMSAMP)
- _throwg("tjPlaneWidth(): Invalid argument");
+ THROWG("tjPlaneWidth(): Invalid argument");
nc = (subsamp == TJSAMP_GRAY ? 1 : 3);
if (componentID < 0 || componentID >= nc)
- _throwg("tjPlaneWidth(): Invalid argument");
+ THROWG("tjPlaneWidth(): Invalid argument");
pw = PAD(width, tjMCUWidth[subsamp] / 8);
if (componentID == 0)
int ph, nc, retval = 0;
if (height < 1 || subsamp < 0 || subsamp >= TJ_NUMSAMP)
- _throwg("tjPlaneHeight(): Invalid argument");
+ THROWG("tjPlaneHeight(): Invalid argument");
nc = (subsamp == TJSAMP_GRAY ? 1 : 3);
if (componentID < 0 || componentID >= nc)
- _throwg("tjPlaneHeight(): Invalid argument");
+ THROWG("tjPlaneHeight(): Invalid argument");
ph = PAD(height, tjMCUHeight[subsamp] / 8);
if (componentID == 0)
DLLEXPORT unsigned long tjPlaneSizeYUV(int componentID, int width, int stride,
int height, int subsamp)
{
- unsigned long retval = 0;
+ unsigned long long retval = 0;
int pw, ph;
if (width < 1 || height < 1 || subsamp < 0 || subsamp >= NUMSUBOPT)
- _throwg("tjPlaneSizeYUV(): Invalid argument");
+ THROWG("tjPlaneSizeYUV(): Invalid argument");
pw = tjPlaneWidth(componentID, width, subsamp);
ph = tjPlaneHeight(componentID, height, subsamp);
if (stride == 0) stride = pw;
else stride = abs(stride);
- retval = stride * (ph - 1) + pw;
+ retval = (unsigned long long)stride * (ph - 1) + pw;
+ if (retval > (unsigned long long)((unsigned long)-1))
+ THROWG("tjPlaneSizeYUV(): Image is too large");
bailout:
- return retval;
+ return (unsigned long)retval;
}
int i, retval = 0, alloc = 1;
JSAMPROW *row_pointer = NULL;
- getcinstance(handle)
+ GET_CINSTANCE(handle)
this->jerr.stopOnWarning = (flags & TJFLAG_STOPONWARNING) ? TRUE : FALSE;
if ((this->init & COMPRESS) == 0)
- _throw("tjCompress2(): Instance has not been initialized for compression");
+ THROW("tjCompress2(): Instance has not been initialized for compression");
if (srcBuf == NULL || width <= 0 || pitch < 0 || height <= 0 ||
pixelFormat < 0 || pixelFormat >= TJ_NUMPF || jpegBuf == NULL ||
jpegSize == NULL || jpegSubsamp < 0 || jpegSubsamp >= NUMSUBOPT ||
jpegQual < 0 || jpegQual > 100)
- _throw("tjCompress2(): Invalid argument");
+ THROW("tjCompress2(): Invalid argument");
if (pitch == 0) pitch = width * tjPixelSize[pixelFormat];
if ((row_pointer = (JSAMPROW *)malloc(sizeof(JSAMPROW) * height)) == NULL)
- _throw("tjCompress2(): Memory allocation failure");
+ THROW("tjCompress2(): Memory allocation failure");
if (setjmp(this->jerr.setjmp_buffer)) {
/* If we get here, the JPEG code has signaled an error. */
jpeg_start_compress(cinfo, TRUE);
for (i = 0; i < height; i++) {
if (flags & TJFLAG_BOTTOMUP)
- row_pointer[i] = (JSAMPROW)&srcBuf[(height - i - 1) * pitch];
+ row_pointer[i] = (JSAMPROW)&srcBuf[(height - i - 1) * (size_t)pitch];
else
- row_pointer[i] = (JSAMPROW)&srcBuf[i * pitch];
+ row_pointer[i] = (JSAMPROW)&srcBuf[i * (size_t)pitch];
}
while (cinfo->next_scanline < cinfo->image_height)
jpeg_write_scanlines(cinfo, &row_pointer[cinfo->next_scanline],
JSAMPLE *ptr;
jpeg_component_info *compptr;
- getcinstance(handle);
+ GET_CINSTANCE(handle);
this->jerr.stopOnWarning = (flags & TJFLAG_STOPONWARNING) ? TRUE : FALSE;
for (i = 0; i < MAX_COMPONENTS; i++) {
}
if ((this->init & COMPRESS) == 0)
- _throw("tjEncodeYUVPlanes(): Instance has not been initialized for compression");
+ THROW("tjEncodeYUVPlanes(): Instance has not been initialized for compression");
if (srcBuf == NULL || width <= 0 || pitch < 0 || height <= 0 ||
pixelFormat < 0 || pixelFormat >= TJ_NUMPF || !dstPlanes ||
!dstPlanes[0] || subsamp < 0 || subsamp >= NUMSUBOPT)
- _throw("tjEncodeYUVPlanes(): Invalid argument");
+ THROW("tjEncodeYUVPlanes(): Invalid argument");
if (subsamp != TJSAMP_GRAY && (!dstPlanes[1] || !dstPlanes[2]))
- _throw("tjEncodeYUVPlanes(): Invalid argument");
+ THROW("tjEncodeYUVPlanes(): Invalid argument");
if (pixelFormat == TJPF_CMYK)
- _throw("tjEncodeYUVPlanes(): Cannot generate YUV images from CMYK pixels");
+ THROW("tjEncodeYUVPlanes(): Cannot generate YUV images from CMYK pixels");
if (pitch == 0) pitch = width * tjPixelSize[pixelFormat];
to write the file headers, which could overflow the output buffer if the
YUV image were very small. */
if (cinfo->global_state != CSTATE_START)
- _throw("tjEncodeYUVPlanes(): libjpeg API is in the wrong state");
+ THROW("tjEncodeYUVPlanes(): libjpeg API is in the wrong state");
(*cinfo->err->reset_error_mgr) ((j_common_ptr)cinfo);
jinit_c_master_control(cinfo, FALSE);
jinit_color_converter(cinfo);
ph0 = PAD(height, cinfo->max_v_samp_factor);
if ((row_pointer = (JSAMPROW *)malloc(sizeof(JSAMPROW) * ph0)) == NULL)
- _throw("tjEncodeYUVPlanes(): Memory allocation failure");
+ THROW("tjEncodeYUVPlanes(): Memory allocation failure");
for (i = 0; i < height; i++) {
if (flags & TJFLAG_BOTTOMUP)
- row_pointer[i] = (JSAMPROW)&srcBuf[(height - i - 1) * pitch];
+ row_pointer[i] = (JSAMPROW)&srcBuf[(height - i - 1) * (size_t)pitch];
else
- row_pointer[i] = (JSAMPROW)&srcBuf[i * pitch];
+ row_pointer[i] = (JSAMPROW)&srcBuf[i * (size_t)pitch];
}
if (height < ph0)
for (i = height; i < ph0; i++) row_pointer[i] = row_pointer[height - 1];
compptr->h_samp_factor, 32) *
cinfo->max_v_samp_factor + 32);
if (!_tmpbuf[i])
- _throw("tjEncodeYUVPlanes(): Memory allocation failure");
+ THROW("tjEncodeYUVPlanes(): Memory allocation failure");
tmpbuf[i] =
(JSAMPROW *)malloc(sizeof(JSAMPROW) * cinfo->max_v_samp_factor);
if (!tmpbuf[i])
- _throw("tjEncodeYUVPlanes(): Memory allocation failure");
+ THROW("tjEncodeYUVPlanes(): Memory allocation failure");
for (row = 0; row < cinfo->max_v_samp_factor; row++) {
unsigned char *_tmpbuf_aligned =
(unsigned char *)PAD((size_t)_tmpbuf[i], 32);
(JSAMPLE *)malloc(PAD(compptr->width_in_blocks * DCTSIZE, 32) *
compptr->v_samp_factor + 32);
if (!_tmpbuf2[i])
- _throw("tjEncodeYUVPlanes(): Memory allocation failure");
+ THROW("tjEncodeYUVPlanes(): Memory allocation failure");
tmpbuf2[i] = (JSAMPROW *)malloc(sizeof(JSAMPROW) * compptr->v_samp_factor);
if (!tmpbuf2[i])
- _throw("tjEncodeYUVPlanes(): Memory allocation failure");
+ THROW("tjEncodeYUVPlanes(): Memory allocation failure");
for (row = 0; row < compptr->v_samp_factor; row++) {
unsigned char *_tmpbuf2_aligned =
(unsigned char *)PAD((size_t)_tmpbuf2[i], 32);
ph[i] = ph0 * compptr->v_samp_factor / cinfo->max_v_samp_factor;
outbuf[i] = (JSAMPROW *)malloc(sizeof(JSAMPROW) * ph[i]);
if (!outbuf[i])
- _throw("tjEncodeYUVPlanes(): Memory allocation failure");
+ THROW("tjEncodeYUVPlanes(): Memory allocation failure");
ptr = dstPlanes[i];
for (row = 0; row < ph[i]; row++) {
outbuf[i][row] = ptr;
int pw0, ph0, strides[3], retval = -1;
tjinstance *this = (tjinstance *)handle;
- if (!this) _throwg("tjEncodeYUV3(): Invalid handle");
+ if (!this) THROWG("tjEncodeYUV3(): Invalid handle");
this->isInstanceError = FALSE;
- if (width <= 0 || height <= 0 || dstBuf == NULL || pad < 0 || !isPow2(pad) ||
- subsamp < 0 || subsamp >= NUMSUBOPT)
- _throw("tjEncodeYUV3(): Invalid argument");
+ if (width <= 0 || height <= 0 || dstBuf == NULL || pad < 0 ||
+ !IS_POW2(pad) || subsamp < 0 || subsamp >= NUMSUBOPT)
+ THROW("tjEncodeYUV3(): Invalid argument");
pw0 = tjPlaneWidth(0, width, subsamp);
ph0 = tjPlaneHeight(0, height, subsamp);
JSAMPLE *_tmpbuf = NULL, *ptr;
JSAMPROW *inbuf[MAX_COMPONENTS], *tmpbuf[MAX_COMPONENTS];
- getcinstance(handle)
+ GET_CINSTANCE(handle)
this->jerr.stopOnWarning = (flags & TJFLAG_STOPONWARNING) ? TRUE : FALSE;
for (i = 0; i < MAX_COMPONENTS; i++) {
}
if ((this->init & COMPRESS) == 0)
- _throw("tjCompressFromYUVPlanes(): Instance has not been initialized for compression");
+ THROW("tjCompressFromYUVPlanes(): Instance has not been initialized for compression");
if (!srcPlanes || !srcPlanes[0] || width <= 0 || height <= 0 ||
subsamp < 0 || subsamp >= NUMSUBOPT || jpegBuf == NULL ||
jpegSize == NULL || jpegQual < 0 || jpegQual > 100)
- _throw("tjCompressFromYUVPlanes(): Invalid argument");
+ THROW("tjCompressFromYUVPlanes(): Invalid argument");
if (subsamp != TJSAMP_GRAY && (!srcPlanes[1] || !srcPlanes[2]))
- _throw("tjCompressFromYUVPlanes(): Invalid argument");
+ THROW("tjCompressFromYUVPlanes(): Invalid argument");
if (setjmp(this->jerr.setjmp_buffer)) {
/* If we get here, the JPEG code has signaled an error. */
th[i] = compptr->v_samp_factor * DCTSIZE;
tmpbufsize += iw[i] * th[i];
if ((inbuf[i] = (JSAMPROW *)malloc(sizeof(JSAMPROW) * ph[i])) == NULL)
- _throw("tjCompressFromYUVPlanes(): Memory allocation failure");
+ THROW("tjCompressFromYUVPlanes(): Memory allocation failure");
ptr = (JSAMPLE *)srcPlanes[i];
for (row = 0; row < ph[i]; row++) {
inbuf[i][row] = ptr;
}
if (usetmpbuf) {
if ((_tmpbuf = (JSAMPLE *)malloc(sizeof(JSAMPLE) * tmpbufsize)) == NULL)
- _throw("tjCompressFromYUVPlanes(): Memory allocation failure");
+ THROW("tjCompressFromYUVPlanes(): Memory allocation failure");
ptr = _tmpbuf;
for (i = 0; i < cinfo->num_components; i++) {
if ((tmpbuf[i] = (JSAMPROW *)malloc(sizeof(JSAMPROW) * th[i])) == NULL)
- _throw("tjCompressFromYUVPlanes(): Memory allocation failure");
+ THROW("tjCompressFromYUVPlanes(): Memory allocation failure");
for (row = 0; row < th[i]; row++) {
tmpbuf[i][row] = ptr;
ptr += iw[i];
int pw0, ph0, strides[3], retval = -1;
tjinstance *this = (tjinstance *)handle;
- if (!this) _throwg("tjCompressFromYUV(): Invalid handle");
+ if (!this) THROWG("tjCompressFromYUV(): Invalid handle");
this->isInstanceError = FALSE;
if (srcBuf == NULL || width <= 0 || pad < 1 || height <= 0 || subsamp < 0 ||
subsamp >= NUMSUBOPT)
- _throw("tjCompressFromYUV(): Invalid argument");
+ THROW("tjCompressFromYUV(): Invalid argument");
pw0 = tjPlaneWidth(0, width, subsamp);
ph0 = tjPlaneHeight(0, height, subsamp);
{
int retval = 0;
- getdinstance(handle);
+ GET_DINSTANCE(handle);
if ((this->init & DECOMPRESS) == 0)
- _throw("tjDecompressHeader3(): Instance has not been initialized for decompression");
+ THROW("tjDecompressHeader3(): Instance has not been initialized for decompression");
if (jpegBuf == NULL || jpegSize <= 0 || width == NULL || height == NULL ||
jpegSubsamp == NULL || jpegColorspace == NULL)
- _throw("tjDecompressHeader3(): Invalid argument");
+ THROW("tjDecompressHeader3(): Invalid argument");
if (setjmp(this->jerr.setjmp_buffer)) {
/* If we get here, the JPEG code has signaled an error. */
jpeg_abort_decompress(dinfo);
if (*jpegSubsamp < 0)
- _throw("tjDecompressHeader3(): Could not determine subsampling type for JPEG image");
+ THROW("tjDecompressHeader3(): Could not determine subsampling type for JPEG image");
if (*jpegColorspace < 0)
- _throw("tjDecompressHeader3(): Could not determine colorspace of JPEG image");
+ THROW("tjDecompressHeader3(): Could not determine colorspace of JPEG image");
if (*width < 1 || *height < 1)
- _throw("tjDecompressHeader3(): Invalid data returned in header");
+ THROW("tjDecompressHeader3(): Invalid data returned in header");
bailout:
if (this->jerr.warning) retval = -1;
JSAMPROW *row_pointer = NULL;
int i, retval = 0, jpegwidth, jpegheight, scaledw, scaledh;
- getdinstance(handle);
+ GET_DINSTANCE(handle);
this->jerr.stopOnWarning = (flags & TJFLAG_STOPONWARNING) ? TRUE : FALSE;
if ((this->init & DECOMPRESS) == 0)
- _throw("tjDecompress2(): Instance has not been initialized for decompression");
+ THROW("tjDecompress2(): Instance has not been initialized for decompression");
if (jpegBuf == NULL || jpegSize <= 0 || dstBuf == NULL || width < 0 ||
pitch < 0 || height < 0 || pixelFormat < 0 || pixelFormat >= TJ_NUMPF)
- _throw("tjDecompress2(): Invalid argument");
+ THROW("tjDecompress2(): Invalid argument");
#ifndef NO_PUTENV
if (flags & TJFLAG_FORCEMMX) putenv("JSIMD_FORCEMMX=1");
break;
}
if (i >= NUMSF)
- _throw("tjDecompress2(): Could not scale down to desired image dimensions");
+ THROW("tjDecompress2(): Could not scale down to desired image dimensions");
width = scaledw; height = scaledh;
dinfo->scale_num = sf[i].num;
dinfo->scale_denom = sf[i].denom;
if ((row_pointer =
(JSAMPROW *)malloc(sizeof(JSAMPROW) * dinfo->output_height)) == NULL)
- _throw("tjDecompress2(): Memory allocation failure");
+ THROW("tjDecompress2(): Memory allocation failure");
if (setjmp(this->jerr.setjmp_buffer)) {
/* If we get here, the JPEG code has signaled an error. */
retval = -1; goto bailout;
}
for (i = 0; i < (int)dinfo->output_height; i++) {
if (flags & TJFLAG_BOTTOMUP)
- row_pointer[i] = &dstBuf[(dinfo->output_height - i - 1) * pitch];
+ row_pointer[i] = &dstBuf[(dinfo->output_height - i - 1) * (size_t)pitch];
else
- row_pointer[i] = &dstBuf[i * pitch];
+ row_pointer[i] = &dstBuf[i * (size_t)pitch];
}
while (dinfo->output_scanline < dinfo->output_height)
jpeg_read_scanlines(dinfo, &row_pointer[dinfo->output_scanline],
}
-int my_read_markers(j_decompress_ptr dinfo)
+static int my_read_markers(j_decompress_ptr dinfo)
{
return JPEG_REACHED_SOS;
}
-void my_reset_marker_reader(j_decompress_ptr dinfo)
+static void my_reset_marker_reader(j_decompress_ptr dinfo)
{
}
int (*old_read_markers) (j_decompress_ptr);
void (*old_reset_marker_reader) (j_decompress_ptr);
- getdinstance(handle);
+ GET_DINSTANCE(handle);
this->jerr.stopOnWarning = (flags & TJFLAG_STOPONWARNING) ? TRUE : FALSE;
for (i = 0; i < MAX_COMPONENTS; i++) {
}
if ((this->init & DECOMPRESS) == 0)
- _throw("tjDecodeYUVPlanes(): Instance has not been initialized for decompression");
+ THROW("tjDecodeYUVPlanes(): Instance has not been initialized for decompression");
if (!srcPlanes || !srcPlanes[0] || subsamp < 0 || subsamp >= NUMSUBOPT ||
dstBuf == NULL || width <= 0 || pitch < 0 || height <= 0 ||
pixelFormat < 0 || pixelFormat >= TJ_NUMPF)
- _throw("tjDecodeYUVPlanes(): Invalid argument");
+ THROW("tjDecodeYUVPlanes(): Invalid argument");
if (subsamp != TJSAMP_GRAY && (!srcPlanes[1] || !srcPlanes[2]))
- _throw("tjDecodeYUVPlanes(): Invalid argument");
+ THROW("tjDecodeYUVPlanes(): Invalid argument");
if (setjmp(this->jerr.setjmp_buffer)) {
/* If we get here, the JPEG code has signaled an error. */
}
if (pixelFormat == TJPF_CMYK)
- _throw("tjDecodeYUVPlanes(): Cannot decode YUV images into CMYK pixels.");
+ THROW("tjDecodeYUVPlanes(): Cannot decode YUV images into CMYK pixels.");
if (pitch == 0) pitch = width * tjPixelSize[pixelFormat];
dinfo->image_width = width;
else if (flags & TJFLAG_FORCESSE2) putenv("JSIMD_FORCESSE2=1");
#endif
+ dinfo->progressive_mode = dinfo->inputctl->has_multiple_scans = FALSE;
+ dinfo->Ss = dinfo->Ah = dinfo->Al = 0;
+ dinfo->Se = DCTSIZE2 - 1;
if (setDecodeDefaults(dinfo, pixelFormat, subsamp, flags) == -1) {
retval = -1; goto bailout;
}
if (pitch == 0) pitch = dinfo->output_width * tjPixelSize[pixelFormat];
if ((row_pointer = (JSAMPROW *)malloc(sizeof(JSAMPROW) * ph0)) == NULL)
- _throw("tjDecodeYUVPlanes(): Memory allocation failure");
+ THROW("tjDecodeYUVPlanes(): Memory allocation failure");
for (i = 0; i < height; i++) {
if (flags & TJFLAG_BOTTOMUP)
- row_pointer[i] = &dstBuf[(height - i - 1) * pitch];
+ row_pointer[i] = &dstBuf[(height - i - 1) * (size_t)pitch];
else
- row_pointer[i] = &dstBuf[i * pitch];
+ row_pointer[i] = &dstBuf[i * (size_t)pitch];
}
if (height < ph0)
for (i = height; i < ph0; i++) row_pointer[i] = row_pointer[height - 1];
(JSAMPLE *)malloc(PAD(compptr->width_in_blocks * DCTSIZE, 32) *
compptr->v_samp_factor + 32);
if (!_tmpbuf[i])
- _throw("tjDecodeYUVPlanes(): Memory allocation failure");
+ THROW("tjDecodeYUVPlanes(): Memory allocation failure");
tmpbuf[i] = (JSAMPROW *)malloc(sizeof(JSAMPROW) * compptr->v_samp_factor);
if (!tmpbuf[i])
- _throw("tjDecodeYUVPlanes(): Memory allocation failure");
+ THROW("tjDecodeYUVPlanes(): Memory allocation failure");
for (row = 0; row < compptr->v_samp_factor; row++) {
unsigned char *_tmpbuf_aligned =
(unsigned char *)PAD((size_t)_tmpbuf[i], 32);
ph[i] = ph0 * compptr->v_samp_factor / dinfo->max_v_samp_factor;
inbuf[i] = (JSAMPROW *)malloc(sizeof(JSAMPROW) * ph[i]);
if (!inbuf[i])
- _throw("tjDecodeYUVPlanes(): Memory allocation failure");
+ THROW("tjDecodeYUVPlanes(): Memory allocation failure");
ptr = (JSAMPLE *)srcPlanes[i];
for (row = 0; row < ph[i]; row++) {
inbuf[i][row] = ptr;
int pw0, ph0, strides[3], retval = -1;
tjinstance *this = (tjinstance *)handle;
- if (!this) _throwg("tjDecodeYUV(): Invalid handle");
+ if (!this) THROWG("tjDecodeYUV(): Invalid handle");
this->isInstanceError = FALSE;
- if (srcBuf == NULL || pad < 0 || !isPow2(pad) || subsamp < 0 ||
+ if (srcBuf == NULL || pad < 0 || !IS_POW2(pad) || subsamp < 0 ||
subsamp >= NUMSUBOPT || width <= 0 || height <= 0)
- _throw("tjDecodeYUV(): Invalid argument");
+ THROW("tjDecodeYUV(): Invalid argument");
pw0 = tjPlaneWidth(0, width, subsamp);
ph0 = tjPlaneHeight(0, height, subsamp);
JSAMPROW *outbuf[MAX_COMPONENTS], *tmpbuf[MAX_COMPONENTS];
int dctsize;
- getdinstance(handle);
+ GET_DINSTANCE(handle);
this->jerr.stopOnWarning = (flags & TJFLAG_STOPONWARNING) ? TRUE : FALSE;
for (i = 0; i < MAX_COMPONENTS; i++) {
}
if ((this->init & DECOMPRESS) == 0)
- _throw("tjDecompressToYUVPlanes(): Instance has not been initialized for decompression");
+ THROW("tjDecompressToYUVPlanes(): Instance has not been initialized for decompression");
if (jpegBuf == NULL || jpegSize <= 0 || !dstPlanes || !dstPlanes[0] ||
width < 0 || height < 0)
- _throw("tjDecompressToYUVPlanes(): Invalid argument");
+ THROW("tjDecompressToYUVPlanes(): Invalid argument");
#ifndef NO_PUTENV
if (flags & TJFLAG_FORCEMMX) putenv("JSIMD_FORCEMMX=1");
this->headerRead = 0;
jpegSubsamp = getSubsamp(dinfo);
if (jpegSubsamp < 0)
- _throw("tjDecompressToYUVPlanes(): Could not determine subsampling type for JPEG image");
+ THROW("tjDecompressToYUVPlanes(): Could not determine subsampling type for JPEG image");
if (jpegSubsamp != TJSAMP_GRAY && (!dstPlanes[1] || !dstPlanes[2]))
- _throw("tjDecompressToYUVPlanes(): Invalid argument");
+ THROW("tjDecompressToYUVPlanes(): Invalid argument");
jpegwidth = dinfo->image_width; jpegheight = dinfo->image_height;
if (width == 0) width = jpegwidth;
break;
}
if (i >= NUMSF)
- _throw("tjDecompressToYUVPlanes(): Could not scale down to desired image dimensions");
+ THROW("tjDecompressToYUVPlanes(): Could not scale down to desired image dimensions");
if (dinfo->num_components > 3)
- _throw("tjDecompressToYUVPlanes(): JPEG image must have 3 or fewer components");
+ THROW("tjDecompressToYUVPlanes(): JPEG image must have 3 or fewer components");
width = scaledw; height = scaledh;
dinfo->scale_num = sf[i].num;
iw[i] = compptr->width_in_blocks * dctsize;
ih = compptr->height_in_blocks * dctsize;
- pw[i] = PAD(dinfo->output_width, dinfo->max_h_samp_factor) *
- compptr->h_samp_factor / dinfo->max_h_samp_factor;
- ph[i] = PAD(dinfo->output_height, dinfo->max_v_samp_factor) *
- compptr->v_samp_factor / dinfo->max_v_samp_factor;
+ pw[i] = tjPlaneWidth(i, dinfo->output_width, jpegSubsamp);
+ ph[i] = tjPlaneHeight(i, dinfo->output_height, jpegSubsamp);
if (iw[i] != pw[i] || ih != ph[i]) usetmpbuf = 1;
th[i] = compptr->v_samp_factor * dctsize;
tmpbufsize += iw[i] * th[i];
if ((outbuf[i] = (JSAMPROW *)malloc(sizeof(JSAMPROW) * ph[i])) == NULL)
- _throw("tjDecompressToYUVPlanes(): Memory allocation failure");
+ THROW("tjDecompressToYUVPlanes(): Memory allocation failure");
ptr = dstPlanes[i];
for (row = 0; row < ph[i]; row++) {
outbuf[i][row] = ptr;
}
if (usetmpbuf) {
if ((_tmpbuf = (JSAMPLE *)malloc(sizeof(JSAMPLE) * tmpbufsize)) == NULL)
- _throw("tjDecompressToYUVPlanes(): Memory allocation failure");
+ THROW("tjDecompressToYUVPlanes(): Memory allocation failure");
ptr = _tmpbuf;
for (i = 0; i < dinfo->num_components; i++) {
if ((tmpbuf[i] = (JSAMPROW *)malloc(sizeof(JSAMPROW) * th[i])) == NULL)
- _throw("tjDecompressToYUVPlanes(): Memory allocation failure");
+ THROW("tjDecompressToYUVPlanes(): Memory allocation failure");
for (row = 0; row < th[i]; row++) {
tmpbuf[i][row] = ptr;
ptr += iw[i];
int pw0, ph0, strides[3], retval = -1, jpegSubsamp = -1;
int i, jpegwidth, jpegheight, scaledw, scaledh;
- getdinstance(handle);
+ GET_DINSTANCE(handle);
this->jerr.stopOnWarning = (flags & TJFLAG_STOPONWARNING) ? TRUE : FALSE;
if (jpegBuf == NULL || jpegSize <= 0 || dstBuf == NULL || width < 0 ||
- pad < 1 || !isPow2(pad) || height < 0)
- _throw("tjDecompressToYUV2(): Invalid argument");
+ pad < 1 || !IS_POW2(pad) || height < 0)
+ THROW("tjDecompressToYUV2(): Invalid argument");
if (setjmp(this->jerr.setjmp_buffer)) {
/* If we get here, the JPEG code has signaled an error. */
jpeg_read_header(dinfo, TRUE);
jpegSubsamp = getSubsamp(dinfo);
if (jpegSubsamp < 0)
- _throw("tjDecompressToYUV2(): Could not determine subsampling type for JPEG image");
+ THROW("tjDecompressToYUV2(): Could not determine subsampling type for JPEG image");
jpegwidth = dinfo->image_width; jpegheight = dinfo->image_height;
if (width == 0) width = jpegwidth;
break;
}
if (i >= NUMSF)
- _throw("tjDecompressToYUV2(): Could not scale down to desired image dimensions");
+ THROW("tjDecompressToYUV2(): Could not scale down to desired image dimensions");
pw0 = tjPlaneWidth(0, width, jpegSubsamp);
ph0 = tjPlaneHeight(0, height, jpegSubsamp);
jvirt_barray_ptr *srccoefs, *dstcoefs;
int retval = 0, i, jpegSubsamp, saveMarkers = 0;
- getinstance(handle);
+ GET_INSTANCE(handle);
this->jerr.stopOnWarning = (flags & TJFLAG_STOPONWARNING) ? TRUE : FALSE;
if ((this->init & COMPRESS) == 0 || (this->init & DECOMPRESS) == 0)
- _throw("tjTransform(): Instance has not been initialized for transformation");
+ THROW("tjTransform(): Instance has not been initialized for transformation");
if (jpegBuf == NULL || jpegSize <= 0 || n < 1 || dstBufs == NULL ||
dstSizes == NULL || t == NULL || flags < 0)
- _throw("tjTransform(): Invalid argument");
+ THROW("tjTransform(): Invalid argument");
#ifndef NO_PUTENV
if (flags & TJFLAG_FORCEMMX) putenv("JSIMD_FORCEMMX=1");
if ((xinfo =
(jpeg_transform_info *)malloc(sizeof(jpeg_transform_info) * n)) == NULL)
- _throw("tjTransform(): Memory allocation failure");
+ THROW("tjTransform(): Memory allocation failure");
MEMZERO(xinfo, sizeof(jpeg_transform_info) * n);
if (setjmp(this->jerr.setjmp_buffer)) {
jpeg_read_header(dinfo, TRUE);
jpegSubsamp = getSubsamp(dinfo);
if (jpegSubsamp < 0)
- _throw("tjTransform(): Could not determine subsampling type for JPEG image");
+ THROW("tjTransform(): Could not determine subsampling type for JPEG image");
for (i = 0; i < n; i++) {
if (!jtransform_request_workspace(dinfo, &xinfo[i]))
- _throw("tjTransform(): Transform is not perfect");
+ THROW("tjTransform(): Transform is not perfect");
if (xinfo[i].crop) {
if ((t[i].r.x % xinfo[i].iMCU_sample_width) != 0 ||
(t[i].r.y % xinfo[i].iMCU_sample_height) != 0) {
- snprintf(errStr, JMSG_LENGTH_MAX,
+ snprintf(this->errStr, JMSG_LENGTH_MAX,
"To crop this JPEG image, x must be a multiple of %d\n"
"and y must be a multiple of %d.\n",
xinfo[i].iMCU_sample_width, xinfo[i].iMCU_sample_height);
+ this->isInstanceError = TRUE;
retval = -1; goto bailout;
}
}
for (y = 0; y < compptr->v_samp_factor; y++) {
if (t[i].customFilter(barray[y][0], arrayRegion, planeRegion, ci,
i, &t[i]) == -1)
- _throw("tjTransform(): Error in custom filter");
+ THROW("tjTransform(): Error in custom filter");
arrayRegion.y += DCTSIZE;
}
}
int align, int *height, int *pixelFormat,
int flags)
{
- int retval = 0, tempc, pitch;
+ int retval = 0, tempc;
+ size_t pitch;
tjhandle handle = NULL;
tjinstance *this;
j_compress_ptr cinfo = NULL;
if (!filename || !width || align < 1 || !height || !pixelFormat ||
*pixelFormat < TJPF_UNKNOWN || *pixelFormat >= TJ_NUMPF)
- _throwg("tjLoadImage(): Invalid argument");
+ THROWG("tjLoadImage(): Invalid argument");
if ((align & (align - 1)) != 0)
- _throwg("tjLoadImage(): Alignment must be a power of 2");
+ THROWG("tjLoadImage(): Alignment must be a power of 2");
if ((handle = tjInitCompress()) == NULL) return NULL;
this = (tjinstance *)handle;
cinfo = &this->cinfo;
if ((file = fopen(filename, "rb")) == NULL)
- _throwunix("tjLoadImage(): Cannot open input file");
+ THROW_UNIX("tjLoadImage(): Cannot open input file");
if ((tempc = getc(file)) < 0 || ungetc(tempc, file) == EOF)
- _throwunix("tjLoadImage(): Could not read input file")
+ THROW_UNIX("tjLoadImage(): Could not read input file")
else if (tempc == EOF)
- _throwg("tjLoadImage(): Input file contains no data");
+ THROWG("tjLoadImage(): Input file contains no data");
if (setjmp(this->jerr.setjmp_buffer)) {
/* If we get here, the JPEG code has signaled an error. */
else cinfo->in_color_space = pf2cs[*pixelFormat];
if (tempc == 'B') {
if ((src = jinit_read_bmp(cinfo, FALSE)) == NULL)
- _throwg("tjLoadImage(): Could not initialize bitmap loader");
+ THROWG("tjLoadImage(): Could not initialize bitmap loader");
invert = (flags & TJFLAG_BOTTOMUP) == 0;
} else if (tempc == 'P') {
if ((src = jinit_read_ppm(cinfo)) == NULL)
- _throwg("tjLoadImage(): Could not initialize bitmap loader");
+ THROWG("tjLoadImage(): Could not initialize bitmap loader");
invert = (flags & TJFLAG_BOTTOMUP) != 0;
} else
- _throwg("tjLoadImage(): Unsupported file type");
+ THROWG("tjLoadImage(): Unsupported file type");
src->input_file = file;
(*src->start_input) (cinfo, src);
*pixelFormat = cs2pf[cinfo->in_color_space];
pitch = PAD((*width) * tjPixelSize[*pixelFormat], align);
- if ((dstBuf = (unsigned char *)malloc(pitch * (*height))) == NULL)
- _throwg("tjLoadImage(): Memory allocation failure");
+ if ((unsigned long long)pitch * (unsigned long long)(*height) >
+ (unsigned long long)((size_t)-1) ||
+ (dstBuf = (unsigned char *)malloc(pitch * (*height))) == NULL)
+ THROWG("tjLoadImage(): Memory allocation failure");
if (setjmp(this->jerr.setjmp_buffer)) {
/* If we get here, the JPEG code has signaled an error. */
if (!filename || !buffer || width < 1 || pitch < 0 || height < 1 ||
pixelFormat < 0 || pixelFormat >= TJ_NUMPF)
- _throwg("tjSaveImage(): Invalid argument");
+ THROWG("tjSaveImage(): Invalid argument");
if ((handle = tjInitDecompress()) == NULL)
return -1;
dinfo = &this->dinfo;
if ((file = fopen(filename, "wb")) == NULL)
- _throwunix("tjSaveImage(): Cannot open output file");
+ THROW_UNIX("tjSaveImage(): Cannot open output file");
if (setjmp(this->jerr.setjmp_buffer)) {
/* If we get here, the JPEG code has signaled an error. */
ptr = strrchr(filename, '.');
if (ptr && !strcasecmp(ptr, ".bmp")) {
if ((dst = jinit_write_bmp(dinfo, FALSE, FALSE)) == NULL)
- _throwg("tjSaveImage(): Could not initialize bitmap writer");
+ THROWG("tjSaveImage(): Could not initialize bitmap writer");
invert = (flags & TJFLAG_BOTTOMUP) == 0;
} else {
if ((dst = jinit_write_ppm(dinfo)) == NULL)
- _throwg("tjSaveImage(): Could not initialize PPM writer");
+ THROWG("tjSaveImage(): Could not initialize PPM writer");
invert = (flags & TJFLAG_BOTTOMUP) != 0;
}
* Copyright (C) 1994-1996, Thomas G. Lane.
* libjpeg-turbo Modifications:
* Copyright (C) 2013, Linaro Limited.
- * Copyright (C) 2014-2015, 2017, D. R. Commander.
+ * Copyright (C) 2014-2015, 2017, 2019, D. R. Commander.
* For conditions of distribution and use, see the accompanying README.ijg
* file.
*
int bits_per_pixel, cmap_entries;
/* Compute colormap size and total file size */
- if (cinfo->out_color_space == JCS_RGB ||
- (cinfo->out_color_space >= JCS_EXT_RGB &&
- cinfo->out_color_space <= JCS_EXT_ARGB)) {
+ if (IsExtRGB(cinfo->out_color_space)) {
if (cinfo->quantize_colors) {
/* Colormapped RGB */
bits_per_pixel = 8;
if (cinfo->out_color_space == JCS_GRAYSCALE) {
dest->pub.put_pixel_rows = put_gray_rows;
- } else if (cinfo->out_color_space == JCS_RGB ||
- (cinfo->out_color_space >= JCS_EXT_RGB &&
- cinfo->out_color_space <= JCS_EXT_ARGB)) {
+ } else if (IsExtRGB(cinfo->out_color_space)) {
if (cinfo->quantize_colors)
dest->pub.put_pixel_rows = put_gray_rows;
else
dest->pub.put_pixel_rows = put_pixel_rows;
- } else if (cinfo->out_color_space == JCS_RGB565 ||
- cinfo->out_color_space == JCS_CMYK) {
+ } else if (!cinfo->quantize_colors &&
+ (cinfo->out_color_space == JCS_RGB565 ||
+ cinfo->out_color_space == JCS_CMYK)) {
dest->pub.put_pixel_rows = put_pixel_rows;
} else {
ERREXIT(cinfo, JERR_BMP_COLORSPACE);
* Copyright (C) 1991-1996, Thomas G. Lane.
* Modified 2009 by Guido Vollbeding.
* libjpeg-turbo Modifications:
- * Copyright (C) 2017, D. R. Commander.
+ * Copyright (C) 2017, 2019, D. R. Commander.
* For conditions of distribution and use, see the accompanying README.ijg
* file.
*
case JCS_EXT_ABGR:
case JCS_EXT_ARGB:
case JCS_CMYK:
+ if (!IsExtRGB(cinfo->out_color_space) && cinfo->quantize_colors)
+ ERREXIT(cinfo, JERR_PPM_COLORSPACE);
/* emit header for raw PPM format */
fprintf(dest->pub.output_file, "P6\n%ld %ld\n%d\n",
(long)cinfo->output_width, (long)cinfo->output_height, PPM_MAXVAL);
((j_common_ptr)cinfo, JPOOL_IMAGE,
cinfo->output_width * cinfo->output_components, (JDIMENSION)1);
dest->pub.buffer_height = 1;
- if (IsExtRGB(cinfo->out_color_space))
- dest->pub.put_pixel_rows = put_rgb;
- else if (cinfo->out_color_space == JCS_CMYK)
- dest->pub.put_pixel_rows = put_cmyk;
- else if (!cinfo->quantize_colors)
- dest->pub.put_pixel_rows = copy_pixel_rows;
- else if (cinfo->out_color_space == JCS_GRAYSCALE)
+ if (!cinfo->quantize_colors) {
+ if (IsExtRGB(cinfo->out_color_space))
+ dest->pub.put_pixel_rows = put_rgb;
+ else if (cinfo->out_color_space == JCS_CMYK)
+ dest->pub.put_pixel_rows = put_cmyk;
+ else
+ dest->pub.put_pixel_rows = copy_pixel_rows;
+ } else if (cinfo->out_color_space == JCS_GRAYSCALE)
dest->pub.put_pixel_rows = put_demapped_gray;
else
dest->pub.put_pixel_rows = put_demapped_rgb;
projects / platform / upstream / libjpeg-turbo.git / commitdiff