mirror
/
gluon-packages
mirror of https://github.com/freifunk-gluon/packages.git
1
0
Fork 0
Code Releases Activity
gluon-packages/net/respondd/src/miniz.c

1869 lines
92 KiB
C
Raw Blame History

/* miniz.c v1.15 - public domain deflate/inflate, zlib-subset, ZIP reading/writing/appending, PNG writing
See "unlicense" statement at the end of this file.
Rich Geldreich <richgel99@gmail.com>, last updated Oct. 13, 2013
Implements RFC 1950: http://www.ietf.org/rfc/rfc1950.txt and RFC 1951: http://www.ietf.org/rfc/rfc1951.txt
Most API's defined in miniz.c are optional. For example, to disable the archive related functions just define
MINIZ_NO_ARCHIVE_APIS, or to get rid of all stdio usage define MINIZ_NO_STDIO (see the list below for more macros).
* Change History
10/13/13 v1.15 r4 - Interim bugfix release while I work on the next major release with Zip64 support (almost there!):
- Critical fix for the MZ_ZIP_FLAG_DO_NOT_SORT_CENTRAL_DIRECTORY bug (thanks kahmyong.moon@hp.com) which could cause locate files to not find files. This bug
would only have occured in earlier versions if you explicitly used this flag, OR if you used mz_zip_extract_archive_file_to_heap() or mz_zip_add_mem_to_archive_file_in_place()
(which used this flag). If you can't switch to v1.15 but want to fix this bug, just remove the uses of this flag from both helper funcs (and of course don't use the flag).
- Bugfix in mz_zip_reader_extract_to_mem_no_alloc() from kymoon when pUser_read_buf is not NULL and compressed size is > uncompressed size
- Fixing mz_zip_reader_extract_*() funcs so they don't try to extract compressed data from directory entries, to account for weird zipfiles which contain zero-size compressed data on dir entries.
Hopefully this fix won't cause any issues on weird zip archives, because it assumes the low 16-bits of zip external attributes are DOS attributes (which I believe they always are in practice).
- Fixing mz_zip_reader_is_file_a_directory() so it doesn't check the internal attributes, just the filename and external attributes
- mz_zip_reader_init_file() - missing MZ_FCLOSE() call if the seek failed
- Added cmake support for Linux builds which builds all the examples, tested with clang v3.3 and gcc v4.6.
- Clang fix for tdefl_write_image_to_png_file_in_memory() from toffaletti
- Merged MZ_FORCEINLINE fix from hdeanclark
- Fix <time.h> include before config #ifdef, thanks emil.brink
- Added tdefl_write_image_to_png_file_in_memory_ex(): supports Y flipping (super useful for OpenGL apps), and explicit control over the compression level (so you can
set it to 1 for real-time compression).
- Merged in some compiler fixes from paulharris's github repro.
- Retested this build under Windows (VS 2010, including static analysis), tcc 0.9.26, gcc v4.6 and clang v3.3.
- Added example6.c, which dumps an image of the mandelbrot set to a PNG file.
- Modified example2 to help test the MZ_ZIP_FLAG_DO_NOT_SORT_CENTRAL_DIRECTORY flag more.
- In r3: Bugfix to mz_zip_writer_add_file() found during merge: Fix possible src file fclose() leak if alignment bytes+local header file write faiiled
- In r4: Minor bugfix to mz_zip_writer_add_from_zip_reader(): Was pushing the wrong central dir header offset, appears harmless in this release, but it became a problem in the zip64 branch
5/20/12 v1.14 - MinGW32/64 GCC 4.6.1 compiler fixes: added MZ_FORCEINLINE, #include <time.h> (thanks fermtect).
5/19/12 v1.13 - From jason@cornsyrup.org and kelwert@mtu.edu - Fix mz_crc32() so it doesn't compute the wrong CRC-32's when mz_ulong is 64-bit.
- Temporarily/locally slammed in "typedef unsigned long mz_ulong" and re-ran a randomized regression test on ~500k files.
- Eliminated a bunch of warnings when compiling with GCC 32-bit/64.
- Ran all examples, miniz.c, and tinfl.c through MSVC 2008's /analyze (static analysis) option and fixed all warnings (except for the silly
"Use of the comma-operator in a tested expression.." analysis warning, which I purposely use to work around a MSVC compiler warning).
- Created 32-bit and 64-bit Codeblocks projects/workspace. Built and tested Linux executables. The codeblocks workspace is compatible with Linux+Win32/x64.
- Added miniz_tester solution/project, which is a useful little app derived from LZHAM's tester app that I use as part of the regression test.
- Ran miniz.c and tinfl.c through another series of regression testing on ~500,000 files and archives.
- Modified example5.c so it purposely disables a bunch of high-level functionality (MINIZ_NO_STDIO, etc.). (Thanks to corysama for the MINIZ_NO_STDIO bug report.)
- Fix ftell() usage in examples so they exit with an error on files which are too large (a limitation of the examples, not miniz itself).
4/12/12 v1.12 - More comments, added low-level example5.c, fixed a couple minor level_and_flags issues in the archive API's.
level_and_flags can now be set to MZ_DEFAULT_COMPRESSION. Thanks to Bruce Dawson <bruced@valvesoftware.com> for the feedback/bug report.
5/28/11 v1.11 - Added statement from unlicense.org
5/27/11 v1.10 - Substantial compressor optimizations:
- Level 1 is now ~4x faster than before. The L1 compressor's throughput now varies between 70-110MB/sec. on a
- Core i7 (actual throughput varies depending on the type of data, and x64 vs. x86).
- Improved baseline L2-L9 compression perf. Also, greatly improved compression perf. issues on some file types.
- Refactored the compression code for better readability and maintainability.
- Added level 10 compression level (L10 has slightly better ratio than level 9, but could have a potentially large
drop in throughput on some files).
5/15/11 v1.09 - Initial stable release.
* Low-level Deflate/Inflate implementation notes:
Compression: Use the "tdefl" API's. The compressor supports raw, static, and dynamic blocks, lazy or
greedy parsing, match length filtering, RLE-only, and Huffman-only streams. It performs and compresses
approximately as well as zlib.
Decompression: Use the "tinfl" API's. The entire decompressor is implemented as a single function
coroutine: see tinfl_decompress(). It supports decompression into a 32KB (or larger power of 2) wrapping buffer, or into a memory
block large enough to hold the entire file.
The low-level tdefl/tinfl API's do not make any use of dynamic memory allocation.
* zlib-style API notes:
miniz.c implements a fairly large subset of zlib. There's enough functionality present for it to be a drop-in
zlib replacement in many apps:
The z_stream struct, optional memory allocation callbacks
deflateInit/deflateInit2/deflate/deflateReset/deflateEnd/deflateBound
inflateInit/inflateInit2/inflate/inflateEnd
compress, compress2, compressBound, uncompress
CRC-32, Adler-32 - Using modern, minimal code size, CPU cache friendly routines.
Supports raw deflate streams or standard zlib streams with adler-32 checking.
Limitations:
The callback API's are not implemented yet. No support for gzip headers or zlib static dictionaries.
I've tried to closely emulate zlib's various flavors of stream flushing and return status codes, but
there are no guarantees that miniz.c pulls this off perfectly.
* PNG writing: See the tdefl_write_image_to_png_file_in_memory() function, originally written by
Alex Evans. Supports 1-4 bytes/pixel images.
* ZIP archive API notes:
The ZIP archive API's where designed with simplicity and efficiency in mind, with just enough abstraction to
get the job done with minimal fuss. There are simple API's to retrieve file information, read files from
existing archives, create new archives, append new files to existing archives, or clone archive data from
one archive to another. It supports archives located in memory or the heap, on disk (using stdio.h),
or you can specify custom file read/write callbacks.
- Archive reading: Just call this function to read a single file from a disk archive:
void *mz_zip_extract_archive_file_to_heap(const char *pZip_filename, const char *pArchive_name,
size_t *pSize, mz_uint zip_flags);
For more complex cases, use the "mz_zip_reader" functions. Upon opening an archive, the entire central
directory is located and read as-is into memory, and subsequent file access only occurs when reading individual files.
- Archives file scanning: The simple way is to use this function to scan a loaded archive for a specific file:
int mz_zip_reader_locate_file(mz_zip_archive *pZip, const char *pName, const char *pComment, mz_uint flags);
The locate operation can optionally check file comments too, which (as one example) can be used to identify
multiple versions of the same file in an archive. This function uses a simple linear search through the central
directory, so it's not very fast.
Alternately, you can iterate through all the files in an archive (using mz_zip_reader_get_num_files()) and
retrieve detailed info on each file by calling mz_zip_reader_file_stat().
- Archive creation: Use the "mz_zip_writer" functions. The ZIP writer immediately writes compressed file data
to disk and builds an exact image of the central directory in memory. The central directory image is written
all at once at the end of the archive file when the archive is finalized.
The archive writer can optionally align each file's local header and file data to any power of 2 alignment,
which can be useful when the archive will be read from optical media. Also, the writer supports placing
arbitrary data blobs at the very beginning of ZIP archives. Archives written using either feature are still
readable by any ZIP tool.
- Archive appending: The simple way to add a single file to an archive is to call this function:
mz_bool mz_zip_add_mem_to_archive_file_in_place(const char *pZip_filename, const char *pArchive_name,
const void *pBuf, size_t buf_size, const void *pComment, mz_uint16 comment_size, mz_uint level_and_flags);
The archive will be created if it doesn't already exist, otherwise it'll be appended to.
Note the appending is done in-place and is not an atomic operation, so if something goes wrong
during the operation it's possible the archive could be left without a central directory (although the local
file headers and file data will be fine, so the archive will be recoverable).
For more complex archive modification scenarios:
1. The safest way is to use a mz_zip_reader to read the existing archive, cloning only those bits you want to
preserve into a new archive using using the mz_zip_writer_add_from_zip_reader() function (which compiles the
compressed file data as-is). When you're done, delete the old archive and rename the newly written archive, and
you're done. This is safe but requires a bunch of temporary disk space or heap memory.
2. Or, you can convert an mz_zip_reader in-place to an mz_zip_writer using mz_zip_writer_init_from_reader(),
append new files as needed, then finalize the archive which will write an updated central directory to the
original archive. (This is basically what mz_zip_add_mem_to_archive_file_in_place() does.) There's a
possibility that the archive's central directory could be lost with this method if anything goes wrong, though.
- ZIP archive support limitations:
No zip64 or spanning support. Extraction functions can only handle unencrypted, stored or deflated files.
Requires streams capable of seeking.
* This is a header file library, like stb_image.c. To get only a header file, either cut and paste the
below header, or create miniz.h, #define MINIZ_HEADER_FILE_ONLY, and then include miniz.c from it.
* Important: For best perf. be sure to customize the below macros for your target platform:
#define MINIZ_USE_UNALIGNED_LOADS_AND_STORES 1
#define MINIZ_LITTLE_ENDIAN 1
#define MINIZ_HAS_64BIT_REGISTERS 1
* On platforms using glibc, Be sure to "#define _LARGEFILE64_SOURCE 1" before including miniz.c to ensure miniz
uses the 64-bit variants: fopen64(), stat64(), etc. Otherwise you won't be able to process large files
(i.e. 32-bit stat() fails for me on files > 0x7FFFFFFF bytes).
*/
#ifndef MINIZ_HEADER_INCLUDED
#define MINIZ_HEADER_INCLUDED
#include <stdlib.h>
// Defines to completely disable specific portions of miniz.c:
// If all macros here are defined the only functionality remaining will be CRC-32, adler-32, tinfl, and tdefl.
// Define MINIZ_NO_STDIO to disable all usage and any functions which rely on stdio for file I/O.
#define MINIZ_NO_STDIO
// If MINIZ_NO_TIME is specified then the ZIP archive functions will not be able to get the current time, or
// get/set file times, and the C run-time funcs that get/set times won't be called.
// The current downside is the times written to your archives will be from 1979.
#define MINIZ_NO_TIME
// Define MINIZ_NO_ARCHIVE_APIS to disable all ZIP archive API's.
#define MINIZ_NO_ARCHIVE_APIS
// Define MINIZ_NO_ARCHIVE_APIS to disable all writing related ZIP archive API's.
#define MINIZ_NO_ARCHIVE_WRITING_APIS
// Define MINIZ_NO_ZLIB_APIS to remove all ZLIB-style compression/decompression API's.
//#define MINIZ_NO_ZLIB_APIS
// Define MINIZ_NO_ZLIB_COMPATIBLE_NAME to disable zlib names, to prevent conflicts against stock zlib.
#define MINIZ_NO_ZLIB_COMPATIBLE_NAMES
// Define MINIZ_NO_MALLOC to disable all calls to malloc, free, and realloc.
// Note if MINIZ_NO_MALLOC is defined then the user must always provide custom user alloc/free/realloc
// callbacks to the zlib and archive API's, and a few stand-alone helper API's which don't provide custom user
// functions (such as tdefl_compress_mem_to_heap() and tinfl_decompress_mem_to_heap()) won't work.
//#define MINIZ_NO_MALLOC
#if defined(__TINYC__) && (defined(__linux) || defined(__linux__))
// TODO: Work around "error: include file 'sys\utime.h' when compiling with tcc on Linux
#define MINIZ_NO_TIME
#endif
#if !defined(MINIZ_NO_TIME) && !defined(MINIZ_NO_ARCHIVE_APIS)
#include <time.h>
#endif
#if defined(_M_IX86) || defined(_M_X64) || defined(__i386__) || defined(__i386) || defined(__i486__) || defined(__i486) || defined(i386) || defined(__ia64__) || defined(__x86_64__)
// MINIZ_X86_OR_X64_CPU is only used to help set the below macros.
#define MINIZ_X86_OR_X64_CPU 1
#endif
#if (__BYTE_ORDER__==__ORDER_LITTLE_ENDIAN__) || MINIZ_X86_OR_X64_CPU
// Set MINIZ_LITTLE_ENDIAN to 1 if the processor is little endian.
#define MINIZ_LITTLE_ENDIAN 1
#endif
#if MINIZ_X86_OR_X64_CPU
// Set MINIZ_USE_UNALIGNED_LOADS_AND_STORES to 1 on CPU's that permit efficient integer loads and stores from unaligned addresses.
#define MINIZ_USE_UNALIGNED_LOADS_AND_STORES 1
#endif
#if defined(_M_X64) || defined(_WIN64) || defined(__MINGW64__) || defined(_LP64) || defined(__LP64__) || defined(__ia64__) || defined(__x86_64__)
// Set MINIZ_HAS_64BIT_REGISTERS to 1 if operations on 64-bit integers are reasonably fast (and don't involve compiler generated calls to helper functions).
#define MINIZ_HAS_64BIT_REGISTERS 1
#endif
// ------------------- zlib-style API Definitions.
// For more compatibility with zlib, miniz.c uses unsigned long for some parameters/struct members. Beware: mz_ulong can be either 32 or 64-bits!
typedef unsigned long mz_ulong;
// Compression strategies.
enum { MZ_DEFAULT_STRATEGY = 0, MZ_FILTERED = 1, MZ_HUFFMAN_ONLY = 2, MZ_RLE = 3, MZ_FIXED = 4 };
// Method
#define MZ_DEFLATED 8
#ifndef MINIZ_NO_ZLIB_APIS
// Heap allocation callbacks.
// Note that mz_alloc_func parameter types purpsosely differ from zlib's: items/size is size_t, not unsigned long.
typedef void *(*mz_alloc_func)(void *opaque, size_t items, size_t size);
typedef void (*mz_free_func)(void *opaque, void *address);
typedef void *(*mz_realloc_func)(void *opaque, void *address, size_t items, size_t size);
#define MZ_VERSION "9.1.15"
#define MZ_VERNUM 0x91F0
#define MZ_VER_MAJOR 9
#define MZ_VER_MINOR 1
#define MZ_VER_REVISION 15
#define MZ_VER_SUBREVISION 0
// Flush values. For typical usage you only need MZ_NO_FLUSH and MZ_FINISH. The other values are for advanced use (refer to the zlib docs).
enum { MZ_NO_FLUSH = 0, MZ_PARTIAL_FLUSH = 1, MZ_SYNC_FLUSH = 2, MZ_FULL_FLUSH = 3, MZ_FINISH = 4, MZ_BLOCK = 5 };
// Return status codes. MZ_PARAM_ERROR is non-standard.
enum { MZ_OK = 0, MZ_STREAM_END = 1, MZ_NEED_DICT = 2, MZ_ERRNO = -1, MZ_STREAM_ERROR = -2, MZ_DATA_ERROR = -3, MZ_MEM_ERROR = -4, MZ_BUF_ERROR = -5, MZ_VERSION_ERROR = -6, MZ_PARAM_ERROR = -10000 };
// Compression levels: 0-9 are the standard zlib-style levels, 10 is best possible compression (not zlib compatible, and may be very slow), MZ_DEFAULT_COMPRESSION=MZ_DEFAULT_LEVEL.
enum { MZ_NO_COMPRESSION = 0, MZ_BEST_SPEED = 1, MZ_BEST_COMPRESSION = 9, MZ_UBER_COMPRESSION = 10, MZ_DEFAULT_LEVEL = 6, MZ_DEFAULT_COMPRESSION = -1 };
// Window bits
#define MZ_DEFAULT_WINDOW_BITS 15
struct mz_internal_state;
// Compression/decompression stream struct.
typedef struct mz_stream_s
{
const unsigned char *next_in; // pointer to next byte to read
unsigned int avail_in; // number of bytes available at next_in
mz_ulong total_in; // total number of bytes consumed so far
unsigned char *next_out; // pointer to next byte to write
unsigned int avail_out; // number of bytes that can be written to next_out
mz_ulong total_out; // total number of bytes produced so far
char *msg; // error msg (unused)
struct mz_internal_state *state; // internal state, allocated by zalloc/zfree
mz_alloc_func zalloc; // optional heap allocation function (defaults to malloc)
mz_free_func zfree; // optional heap free function (defaults to free)
void *opaque; // heap alloc function user pointer
int data_type; // data_type (unused)
mz_ulong reserved; // not used
} mz_stream;
typedef mz_stream *mz_streamp;
// mz_deflateInit() initializes a compressor with default options:
// Parameters:
// pStream must point to an initialized mz_stream struct.
// level must be between [MZ_NO_COMPRESSION, MZ_BEST_COMPRESSION].
// level 1 enables a specially optimized compression function that's been optimized purely for performance, not ratio.
// (This special func. is currently only enabled when MINIZ_USE_UNALIGNED_LOADS_AND_STORES and MINIZ_LITTLE_ENDIAN are defined.)
// Return values:
// MZ_OK on success.
// MZ_STREAM_ERROR if the stream is bogus.
// MZ_PARAM_ERROR if the input parameters are bogus.
// MZ_MEM_ERROR on out of memory.
static int mz_deflateInit(mz_streamp pStream, int level);
// mz_deflateInit2() is like mz_deflate(), except with more control:
// Additional parameters:
// method must be MZ_DEFLATED
// window_bits must be MZ_DEFAULT_WINDOW_BITS (to wrap the deflate stream with zlib header/adler-32 footer) or -MZ_DEFAULT_WINDOW_BITS (raw deflate/no header or footer)
// mem_level must be between [1, 9] (it's checked but ignored by miniz.c)
static int mz_deflateInit2(mz_streamp pStream, int level, int method, int window_bits, int mem_level, int strategy);
// mz_deflate() compresses the input to output, consuming as much of the input and producing as much output as possible.
// Parameters:
// pStream is the stream to read from and write to. You must initialize/update the next_in, avail_in, next_out, and avail_out members.
// flush may be MZ_NO_FLUSH, MZ_PARTIAL_FLUSH/MZ_SYNC_FLUSH, MZ_FULL_FLUSH, or MZ_FINISH.
// Return values:
// MZ_OK on success (when flushing, or if more input is needed but not available, and/or there's more output to be written but the output buffer is full).
// MZ_STREAM_END if all input has been consumed and all output bytes have been written. Don't call mz_deflate() on the stream anymore.
// MZ_STREAM_ERROR if the stream is bogus.
// MZ_PARAM_ERROR if one of the parameters is invalid.
// MZ_BUF_ERROR if no forward progress is possible because the input and/or output buffers are empty. (Fill up the input buffer or free up some output space and try again.)
static int mz_deflate(mz_streamp pStream, int flush);
// mz_deflateEnd() deinitializes a compressor:
// Return values:
// MZ_OK on success.
// MZ_STREAM_ERROR if the stream is bogus.
static int mz_deflateEnd(mz_streamp pStream);
// mz_deflateBound() returns a (very) conservative upper bound on the amount of data that could be generated by deflate(), assuming flush is set to only MZ_NO_FLUSH or MZ_FINISH.
static mz_ulong mz_deflateBound(mz_streamp pStream, mz_ulong source_len);
// Single-call compression functions mz_compress() and mz_compress2():
// Returns MZ_OK on success, or one of the error codes from mz_deflate() on failure.
static int mz_compress(unsigned char *pDest, mz_ulong *pDest_len, const unsigned char *pSource, mz_ulong source_len);
static int mz_compress2(unsigned char *pDest, mz_ulong *pDest_len, const unsigned char *pSource, mz_ulong source_len, int level);
// mz_compressBound() returns a (very) conservative upper bound on the amount of data that could be generated by calling mz_compress().
static mz_ulong mz_compressBound(mz_ulong source_len);
// Returns a string description of the specified error code, or NULL if the error code is invalid.
static const char *mz_error(int err);
#endif // MINIZ_NO_ZLIB_APIS
// ------------------- Types and macros
typedef unsigned char mz_uint8;
typedef signed short mz_int16;
typedef unsigned short mz_uint16;
typedef unsigned int mz_uint32;
typedef unsigned int mz_uint;
typedef long long mz_int64;
typedef unsigned long long mz_uint64;
typedef int mz_bool;
#define MZ_FALSE (0)
#define MZ_TRUE (1)
// An attempt to work around MSVC's spammy "warning C4127: conditional expression is constant" message.
#ifdef _MSC_VER
#define MZ_MACRO_END while (0, 0)
#else
#define MZ_MACRO_END while (0)
#endif
// ------------------- ZIP archive reading/writing
#ifndef MINIZ_NO_ARCHIVE_APIS
enum
{
MZ_ZIP_MAX_IO_BUF_SIZE = 64*1024,
MZ_ZIP_MAX_ARCHIVE_FILENAME_SIZE = 260,
MZ_ZIP_MAX_ARCHIVE_FILE_COMMENT_SIZE = 256
};
typedef struct
{
mz_uint32 m_file_index;
mz_uint32 m_central_dir_ofs;
mz_uint16 m_version_made_by;
mz_uint16 m_version_needed;
mz_uint16 m_bit_flag;
mz_uint16 m_method;
#ifndef MINIZ_NO_TIME
time_t m_time;
#endif
mz_uint32 m_crc32;
mz_uint64 m_comp_size;
mz_uint64 m_uncomp_size;
mz_uint16 m_internal_attr;
mz_uint32 m_external_attr;
mz_uint64 m_local_header_ofs;
mz_uint32 m_comment_size;
char m_filename[MZ_ZIP_MAX_ARCHIVE_FILENAME_SIZE];
char m_comment[MZ_ZIP_MAX_ARCHIVE_FILE_COMMENT_SIZE];
} mz_zip_archive_file_stat;
typedef size_t (*mz_file_read_func)(void *pOpaque, mz_uint64 file_ofs, void *pBuf, size_t n);
typedef size_t (*mz_file_write_func)(void *pOpaque, mz_uint64 file_ofs, const void *pBuf, size_t n);
struct mz_zip_internal_state_tag;
typedef struct mz_zip_internal_state_tag mz_zip_internal_state;
typedef enum
{
MZ_ZIP_MODE_INVALID = 0,
MZ_ZIP_MODE_READING = 1,
MZ_ZIP_MODE_WRITING = 2,
MZ_ZIP_MODE_WRITING_HAS_BEEN_FINALIZED = 3
} mz_zip_mode;
typedef struct mz_zip_archive_tag
{
mz_uint64 m_archive_size;
mz_uint64 m_central_directory_file_ofs;
mz_uint m_total_files;
mz_zip_mode m_zip_mode;
mz_uint m_file_offset_alignment;
mz_alloc_func m_pAlloc;
mz_free_func m_pFree;
mz_realloc_func m_pRealloc;
void *m_pAlloc_opaque;
mz_file_read_func m_pRead;
mz_file_write_func m_pWrite;
void *m_pIO_opaque;
mz_zip_internal_state *m_pState;
} mz_zip_archive;
typedef enum
{
MZ_ZIP_FLAG_CASE_SENSITIVE = 0x0100,
MZ_ZIP_FLAG_IGNORE_PATH = 0x0200,
MZ_ZIP_FLAG_COMPRESSED_DATA = 0x0400,
MZ_ZIP_FLAG_DO_NOT_SORT_CENTRAL_DIRECTORY = 0x0800
} mz_zip_flags;
// ZIP archive reading
// Inits a ZIP archive reader.
// These functions read and validate the archive's central directory.
static mz_bool mz_zip_reader_init(mz_zip_archive *pZip, mz_uint64 size, mz_uint32 flags);
static mz_bool mz_zip_reader_init_mem(mz_zip_archive *pZip, const void *pMem, size_t size, mz_uint32 flags);
#ifndef MINIZ_NO_STDIO
static mz_bool mz_zip_reader_init_file(mz_zip_archive *pZip, const char *pFilename, mz_uint32 flags);
#endif
// Returns the total number of files in the archive.
static mz_uint mz_zip_reader_get_num_files(mz_zip_archive *pZip);
// Returns detailed information about an archive file entry.
static mz_bool mz_zip_reader_file_stat(mz_zip_archive *pZip, mz_uint file_index, mz_zip_archive_file_stat *pStat);
// Determines if an archive file entry is a directory entry.
static mz_bool mz_zip_reader_is_file_a_directory(mz_zip_archive *pZip, mz_uint file_index);
static mz_bool mz_zip_reader_is_file_encrypted(mz_zip_archive *pZip, mz_uint file_index);
// Retrieves the filename of an archive file entry.
// Returns the number of bytes written to pFilename, or if filename_buf_size is 0 this function returns the number of bytes needed to fully store the filename.
static mz_uint mz_zip_reader_get_filename(mz_zip_archive *pZip, mz_uint file_index, char *pFilename, mz_uint filename_buf_size);
// Attempts to locates a file in the archive's central directory.
// Valid flags: MZ_ZIP_FLAG_CASE_SENSITIVE, MZ_ZIP_FLAG_IGNORE_PATH
// Returns -1 if the file cannot be found.
static int mz_zip_reader_locate_file(mz_zip_archive *pZip, const char *pName, const char *pComment, mz_uint flags);
// Extracts a archive file to a memory buffer using no memory allocation.
static mz_bool mz_zip_reader_extract_to_mem_no_alloc(mz_zip_archive *pZip, mz_uint file_index, void *pBuf, size_t buf_size, mz_uint flags, void *pUser_read_buf, size_t user_read_buf_size);
static mz_bool mz_zip_reader_extract_file_to_mem_no_alloc(mz_zip_archive *pZip, const char *pFilename, void *pBuf, size_t buf_size, mz_uint flags, void *pUser_read_buf, size_t user_read_buf_size);
// Extracts a archive file to a memory buffer.
static mz_bool mz_zip_reader_extract_to_mem(mz_zip_archive *pZip, mz_uint file_index, void *pBuf, size_t buf_size, mz_uint flags);
static mz_bool mz_zip_reader_extract_file_to_mem(mz_zip_archive *pZip, const char *pFilename, void *pBuf, size_t buf_size, mz_uint flags);
// Extracts a archive file to a dynamically allocated heap buffer.
static void *mz_zip_reader_extract_to_heap(mz_zip_archive *pZip, mz_uint file_index, size_t *pSize, mz_uint flags);
static void *mz_zip_reader_extract_file_to_heap(mz_zip_archive *pZip, const char *pFilename, size_t *pSize, mz_uint flags);
// Extracts a archive file using a callback function to output the file's data.
static mz_bool mz_zip_reader_extract_to_callback(mz_zip_archive *pZip, mz_uint file_index, mz_file_write_func pCallback, void *pOpaque, mz_uint flags);
static mz_bool mz_zip_reader_extract_file_to_callback(mz_zip_archive *pZip, const char *pFilename, mz_file_write_func pCallback, void *pOpaque, mz_uint flags);
#ifndef MINIZ_NO_STDIO
// Extracts a archive file to a disk file and sets its last accessed and modified times.
// This function only extracts files, not archive directory records.
static mz_bool mz_zip_reader_extract_to_file(mz_zip_archive *pZip, mz_uint file_index, const char *pDst_filename, mz_uint flags);
static mz_bool mz_zip_reader_extract_file_to_file(mz_zip_archive *pZip, const char *pArchive_filename, const char *pDst_filename, mz_uint flags);
#endif
// Ends archive reading, freeing all allocations, and closing the input archive file if mz_zip_reader_init_file() was used.
static mz_bool mz_zip_reader_end(mz_zip_archive *pZip);
// ZIP archive writing
#ifndef MINIZ_NO_ARCHIVE_WRITING_APIS
// Inits a ZIP archive writer.
static mz_bool mz_zip_writer_init(mz_zip_archive *pZip, mz_uint64 existing_size);
static mz_bool mz_zip_writer_init_heap(mz_zip_archive *pZip, size_t size_to_reserve_at_beginning, size_t initial_allocation_size);
#ifndef MINIZ_NO_STDIO
static mz_bool mz_zip_writer_init_file(mz_zip_archive *pZip, const char *pFilename, mz_uint64 size_to_reserve_at_beginning);
#endif
// Converts a ZIP archive reader object into a writer object, to allow efficient in-place file appends to occur on an existing archive.
// For archives opened using mz_zip_reader_init_file, pFilename must be the archive's filename so it can be reopened for writing. If the file can't be reopened, mz_zip_reader_end() will be called.
// For archives opened using mz_zip_reader_init_mem, the memory block must be growable using the realloc callback (which defaults to realloc unless you've overridden it).
// Finally, for archives opened using mz_zip_reader_init, the mz_zip_archive's user provided m_pWrite function cannot be NULL.
// Note: In-place archive modification is not recommended unless you know what you're doing, because if execution stops or something goes wrong before
// the archive is finalized the file's central directory will be hosed.
static mz_bool mz_zip_writer_init_from_reader(mz_zip_archive *pZip, const char *pFilename);
// Adds the contents of a memory buffer to an archive. These functions record the current local time into the archive.
// To add a directory entry, call this method with an archive name ending in a forwardslash with empty buffer.
// level_and_flags - compression level (0-10, see MZ_BEST_SPEED, MZ_BEST_COMPRESSION, etc.) logically OR'd with zero or more mz_zip_flags, or just set to MZ_DEFAULT_COMPRESSION.
static mz_bool mz_zip_writer_add_mem(mz_zip_archive *pZip, const char *pArchive_name, const void *pBuf, size_t buf_size, mz_uint level_and_flags);
static mz_bool mz_zip_writer_add_mem_ex(mz_zip_archive *pZip, const char *pArchive_name, const void *pBuf, size_t buf_size, const void *pComment, mz_uint16 comment_size, mz_uint level_and_flags, mz_uint64 uncomp_size, mz_uint32 uncomp_crc32);
#ifndef MINIZ_NO_STDIO
// Adds the contents of a disk file to an archive. This function also records the disk file's modified time into the archive.
// level_and_flags - compression level (0-10, see MZ_BEST_SPEED, MZ_BEST_COMPRESSION, etc.) logically OR'd with zero or more mz_zip_flags, or just set to MZ_DEFAULT_COMPRESSION.
static mz_bool mz_zip_writer_add_file(mz_zip_archive *pZip, const char *pArchive_name, const char *pSrc_filename, const void *pComment, mz_uint16 comment_size, mz_uint level_and_flags);
#endif
// Adds a file to an archive by fully cloning the data from another archive.
// This function fully clones the source file's compressed data (no recompression), along with its full filename, extra data, and comment fields.
static mz_bool mz_zip_writer_add_from_zip_reader(mz_zip_archive *pZip, mz_zip_archive *pSource_zip, mz_uint file_index);
// Finalizes the archive by writing the central directory records followed by the end of central directory record.
// After an archive is finalized, the only valid call on the mz_zip_archive struct is mz_zip_writer_end().
// An archive must be manually finalized by calling this function for it to be valid.
static mz_bool mz_zip_writer_finalize_archive(mz_zip_archive *pZip);
static mz_bool mz_zip_writer_finalize_heap_archive(mz_zip_archive *pZip, void **pBuf, size_t *pSize);
// Ends archive writing, freeing all allocations, and closing the output file if mz_zip_writer_init_file() was used.
// Note for the archive to be valid, it must have been finalized before ending.
static mz_bool mz_zip_writer_end(mz_zip_archive *pZip);
// Misc. high-level helper functions:
// mz_zip_add_mem_to_archive_file_in_place() efficiently (but not atomically) appends a memory blob to a ZIP archive.
// level_and_flags - compression level (0-10, see MZ_BEST_SPEED, MZ_BEST_COMPRESSION, etc.) logically OR'd with zero or more mz_zip_flags, or just set to MZ_DEFAULT_COMPRESSION.
static mz_bool mz_zip_add_mem_to_archive_file_in_place(const char *pZip_filename, const char *pArchive_name, const void *pBuf, size_t buf_size, const void *pComment, mz_uint16 comment_size, mz_uint level_and_flags);
// Reads a single file from an archive into a heap block.
// Returns NULL on failure.
static void *mz_zip_extract_archive_file_to_heap(const char *pZip_filename, const char *pArchive_name, size_t *pSize, mz_uint zip_flags);
#endif // #ifndef MINIZ_NO_ARCHIVE_WRITING_APIS
#endif // #ifndef MINIZ_NO_ARCHIVE_APIS
// ------------------- Low-level Compression API Definitions
// Set TDEFL_LESS_MEMORY to 1 to use less memory (compression will be slightly slower, and raw/dynamic blocks will be output more frequently).
#define TDEFL_LESS_MEMORY 1
// tdefl_init() compression flags logically OR'd together (low 12 bits contain the max. number of probes per dictionary search):
// TDEFL_DEFAULT_MAX_PROBES: The compressor defaults to 128 dictionary probes per dictionary search. 0=Huffman only, 1=Huffman+LZ (fastest/crap compression), 4095=Huffman+LZ (slowest/best compression).
enum
{
TDEFL_HUFFMAN_ONLY = 0, TDEFL_DEFAULT_MAX_PROBES = 128, TDEFL_MAX_PROBES_MASK = 0xFFF
};
// TDEFL_GREEDY_PARSING_FLAG: Set to use faster greedy parsing, instead of more efficient lazy parsing.
// TDEFL_NONDETERMINISTIC_PARSING_FLAG: Enable to decrease the compressor's initialization time to the minimum, but the output may vary from run to run given the same input (depending on the contents of memory).
// TDEFL_RLE_MATCHES: Only look for RLE matches (matches with a distance of 1)
// TDEFL_FILTER_MATCHES: Discards matches <= 5 chars if enabled.
// TDEFL_FORCE_ALL_STATIC_BLOCKS: Disable usage of optimized Huffman tables.
// TDEFL_FORCE_ALL_RAW_BLOCKS: Only use raw (uncompressed) deflate blocks.
// The low 12 bits are reserved to control the max # of hash probes per dictionary lookup (see TDEFL_MAX_PROBES_MASK).
enum
{
TDEFL_GREEDY_PARSING_FLAG = 0x04000,
TDEFL_NONDETERMINISTIC_PARSING_FLAG = 0x08000,
TDEFL_RLE_MATCHES = 0x10000,
TDEFL_FILTER_MATCHES = 0x20000,
TDEFL_FORCE_ALL_STATIC_BLOCKS = 0x40000,
TDEFL_FORCE_ALL_RAW_BLOCKS = 0x80000
};
// Output stream interface. The compressor uses this interface to write compressed data. It'll typically be called TDEFL_OUT_BUF_SIZE at a time.
typedef mz_bool (*tdefl_put_buf_func_ptr)(const void* pBuf, int len, void *pUser);
enum { TDEFL_MAX_HUFF_TABLES = 3, TDEFL_MAX_HUFF_SYMBOLS_0 = 288, TDEFL_MAX_HUFF_SYMBOLS_1 = 32, TDEFL_MAX_HUFF_SYMBOLS_2 = 19, TDEFL_LZ_DICT_SIZE = 32768, TDEFL_LZ_DICT_SIZE_MASK = TDEFL_LZ_DICT_SIZE - 1, TDEFL_MIN_MATCH_LEN = 3, TDEFL_MAX_MATCH_LEN = 258 };
// TDEFL_OUT_BUF_SIZE MUST be large enough to hold a single entire compressed output block (using static/fixed Huffman codes).
#if TDEFL_LESS_MEMORY
enum { TDEFL_LZ_CODE_BUF_SIZE = 24 * 1024, TDEFL_OUT_BUF_SIZE = (TDEFL_LZ_CODE_BUF_SIZE * 13 ) / 10, TDEFL_MAX_HUFF_SYMBOLS = 288, TDEFL_LZ_HASH_BITS = 12, TDEFL_LEVEL1_HASH_SIZE_MASK = 4095, TDEFL_LZ_HASH_SHIFT = (TDEFL_LZ_HASH_BITS + 2) / 3, TDEFL_LZ_HASH_SIZE = 1 << TDEFL_LZ_HASH_BITS };
#else
enum { TDEFL_LZ_CODE_BUF_SIZE = 64 * 1024, TDEFL_OUT_BUF_SIZE = (TDEFL_LZ_CODE_BUF_SIZE * 13 ) / 10, TDEFL_MAX_HUFF_SYMBOLS = 288, TDEFL_LZ_HASH_BITS = 15, TDEFL_LEVEL1_HASH_SIZE_MASK = 4095, TDEFL_LZ_HASH_SHIFT = (TDEFL_LZ_HASH_BITS + 2) / 3, TDEFL_LZ_HASH_SIZE = 1 << TDEFL_LZ_HASH_BITS };
#endif
// The low-level tdefl functions below may be used directly if the above helper functions aren't flexible enough. The low-level functions don't make any heap allocations, unlike the above helper functions.
typedef enum
{
TDEFL_STATUS_BAD_PARAM = -2,
TDEFL_STATUS_PUT_BUF_FAILED = -1,
TDEFL_STATUS_OKAY = 0,
TDEFL_STATUS_DONE = 1,
} tdefl_status;
// Must map to MZ_NO_FLUSH, MZ_SYNC_FLUSH, etc. enums
typedef enum
{
TDEFL_NO_FLUSH = 0,
TDEFL_SYNC_FLUSH = 2,
TDEFL_FULL_FLUSH = 3,
TDEFL_FINISH = 4
} tdefl_flush;
// tdefl's compression state structure.
typedef struct
{
tdefl_put_buf_func_ptr m_pPut_buf_func;
void *m_pPut_buf_user;
mz_uint m_flags, m_max_probes[2];
int m_greedy_parsing;
mz_uint m_lookahead_pos, m_lookahead_size, m_dict_size;
mz_uint8 *m_pLZ_code_buf, *m_pLZ_flags, *m_pOutput_buf, *m_pOutput_buf_end;
mz_uint m_num_flags_left, m_total_lz_bytes, m_lz_code_buf_dict_pos, m_bits_in, m_bit_buffer;
mz_uint m_saved_match_dist, m_saved_match_len, m_saved_lit, m_output_flush_ofs, m_output_flush_remaining, m_finished, m_block_index, m_wants_to_finish;
tdefl_status m_prev_return_status;
const void *m_pIn_buf;
void *m_pOut_buf;
size_t *m_pIn_buf_size, *m_pOut_buf_size;
tdefl_flush m_flush;
const mz_uint8 *m_pSrc;
size_t m_src_buf_left, m_out_buf_ofs;
mz_uint8 m_dict[TDEFL_LZ_DICT_SIZE + TDEFL_MAX_MATCH_LEN - 1];
mz_uint16 m_huff_count[TDEFL_MAX_HUFF_TABLES][TDEFL_MAX_HUFF_SYMBOLS];
mz_uint16 m_huff_codes[TDEFL_MAX_HUFF_TABLES][TDEFL_MAX_HUFF_SYMBOLS];
mz_uint8 m_huff_code_sizes[TDEFL_MAX_HUFF_TABLES][TDEFL_MAX_HUFF_SYMBOLS];
mz_uint8 m_lz_code_buf[TDEFL_LZ_CODE_BUF_SIZE];
mz_uint16 m_next[TDEFL_LZ_DICT_SIZE];
mz_uint16 m_hash[TDEFL_LZ_HASH_SIZE];
mz_uint8 m_output_buf[TDEFL_OUT_BUF_SIZE];
} tdefl_compressor;
// Initializes the compressor.
// There is no corresponding deinit() function because the tdefl API's do not dynamically allocate memory.
// pBut_buf_func: If NULL, output data will be supplied to the specified callback. In this case, the user should call the tdefl_compress_buffer() API for compression.
// If pBut_buf_func is NULL the user should always call the tdefl_compress() API.
// flags: See the above enums (TDEFL_HUFFMAN_ONLY, TDEFL_WRITE_ZLIB_HEADER, etc.)
static tdefl_status tdefl_init(tdefl_compressor *d, tdefl_put_buf_func_ptr pPut_buf_func, void *pPut_buf_user, int flags);
// Compresses a block of data, consuming as much of the specified input buffer as possible, and writing as much compressed data to the specified output buffer as possible.
static tdefl_status tdefl_compress(tdefl_compressor *d, const void *pIn_buf, size_t *pIn_buf_size, void *pOut_buf, size_t *pOut_buf_size, tdefl_flush flush);
// Can't use tdefl_create_comp_flags_from_zip_params if MINIZ_NO_ZLIB_APIS isn't defined, because it uses some of its macros.
#ifndef MINIZ_NO_ZLIB_APIS
// Create tdefl_compress() flags given zlib-style compression parameters.
// level may range from [0,10] (where 10 is absolute max compression, but may be much slower on some files)
// window_bits may be -15 (raw deflate) or 15 (zlib)
// strategy may be either MZ_DEFAULT_STRATEGY, MZ_FILTERED, MZ_HUFFMAN_ONLY, MZ_RLE, or MZ_FIXED
static mz_uint tdefl_create_comp_flags_from_zip_params(int level, int window_bits, int strategy);
#endif // #ifndef MINIZ_NO_ZLIB_APIS
#ifdef __cplusplus
}
#endif
#endif // MINIZ_HEADER_INCLUDED
// ------------------- End of Header: Implementation follows. (If you only want the header, define MINIZ_HEADER_FILE_ONLY.)
#ifndef MINIZ_HEADER_FILE_ONLY
typedef unsigned char mz_validate_uint16[sizeof(mz_uint16)==2 ? 1 : -1];
typedef unsigned char mz_validate_uint32[sizeof(mz_uint32)==4 ? 1 : -1];
typedef unsigned char mz_validate_uint64[sizeof(mz_uint64)==8 ? 1 : -1];
#include <string.h>
#include <assert.h>
#define MZ_ASSERT(x) assert(x)
#ifdef MINIZ_NO_MALLOC
#define MZ_MALLOC(x) NULL
#define MZ_FREE(x) (void)x, ((void)0)
#define MZ_REALLOC(p, x) NULL
#else
#define MZ_MALLOC(x) malloc(x)
#define MZ_FREE(x) free(x)
#define MZ_REALLOC(p, x) realloc(p, x)
#endif
#define MZ_MAX(a,b) (((a)>(b))?(a):(b))
#define MZ_MIN(a,b) (((a)<(b))?(a):(b))
#define MZ_CLEAR_OBJ(obj) memset(&(obj), 0, sizeof(obj))
#if MINIZ_USE_UNALIGNED_LOADS_AND_STORES && MINIZ_LITTLE_ENDIAN
#define MZ_READ_LE16(p) *((const mz_uint16 *)(p))
#define MZ_READ_LE32(p) *((const mz_uint32 *)(p))
#else
#define MZ_READ_LE16(p) ((mz_uint32)(((const mz_uint8 *)(p))[0]) | ((mz_uint32)(((const mz_uint8 *)(p))[1]) << 8U))
#define MZ_READ_LE32(p) ((mz_uint32)(((const mz_uint8 *)(p))[0]) | ((mz_uint32)(((const mz_uint8 *)(p))[1]) << 8U) | ((mz_uint32)(((const mz_uint8 *)(p))[2]) << 16U) | ((mz_uint32)(((const mz_uint8 *)(p))[3]) << 24U))
#endif
#ifdef _MSC_VER
#define MZ_FORCEINLINE __forceinline
#elif defined(__GNUC__)
#define MZ_FORCEINLINE inline __attribute__((__always_inline__))
#else
#define MZ_FORCEINLINE inline
#endif
#ifdef __cplusplus
extern "C" {
#endif
// ------------------- zlib-style API's
#ifndef MINIZ_NO_ZLIB_APIS
static void *def_alloc_func(void *opaque, size_t items, size_t size) { (void)opaque, (void)items, (void)size; return MZ_MALLOC(items * size); }
static void def_free_func(void *opaque, void *address) { (void)opaque, (void)address; MZ_FREE(address); }
int mz_deflateInit(mz_streamp pStream, int level)
{
return mz_deflateInit2(pStream, level, MZ_DEFLATED, MZ_DEFAULT_WINDOW_BITS, 9, MZ_DEFAULT_STRATEGY);
}
int mz_deflateInit2(mz_streamp pStream, int level, int method, int window_bits, int mem_level, int strategy)
{
tdefl_compressor *pComp;
mz_uint comp_flags = tdefl_create_comp_flags_from_zip_params(level, window_bits, strategy);
if (!pStream) return MZ_STREAM_ERROR;
if ((method != MZ_DEFLATED) || ((mem_level < 1) || (mem_level > 9)) || ((window_bits != MZ_DEFAULT_WINDOW_BITS) && (-window_bits != MZ_DEFAULT_WINDOW_BITS))) return MZ_PARAM_ERROR;
pStream->data_type = 0;
pStream->msg = NULL;
pStream->reserved = 0;
pStream->total_in = 0;
pStream->total_out = 0;
if (!pStream->zalloc) pStream->zalloc = def_alloc_func;
if (!pStream->zfree) pStream->zfree = def_free_func;
pComp = (tdefl_compressor *)pStream->zalloc(pStream->opaque, 1, sizeof(tdefl_compressor));
if (!pComp)
return MZ_MEM_ERROR;
pStream->state = (struct mz_internal_state *)pComp;
if (tdefl_init(pComp, NULL, NULL, comp_flags) != TDEFL_STATUS_OKAY)
{
mz_deflateEnd(pStream);
return MZ_PARAM_ERROR;
}
return MZ_OK;
}
int mz_deflate(mz_streamp pStream, int flush)
{
size_t in_bytes, out_bytes;
mz_ulong orig_total_in, orig_total_out;
int mz_status = MZ_OK;
if ((!pStream) || (!pStream->state) || (flush < 0) || (flush > MZ_FINISH) || (!pStream->next_out)) return MZ_STREAM_ERROR;
if (!pStream->avail_out) return MZ_BUF_ERROR;
if (flush == MZ_PARTIAL_FLUSH) flush = MZ_SYNC_FLUSH;
if (((tdefl_compressor*)pStream->state)->m_prev_return_status == TDEFL_STATUS_DONE)
return (flush == MZ_FINISH) ? MZ_STREAM_END : MZ_BUF_ERROR;
orig_total_in = pStream->total_in; orig_total_out = pStream->total_out;
for ( ; ; )
{
tdefl_status defl_status;
in_bytes = pStream->avail_in; out_bytes = pStream->avail_out;
defl_status = tdefl_compress((tdefl_compressor*)pStream->state, pStream->next_in, &in_bytes, pStream->next_out, &out_bytes, (tdefl_flush)flush);
pStream->next_in += (mz_uint)in_bytes; pStream->avail_in -= (mz_uint)in_bytes;
pStream->total_in += (mz_uint)in_bytes;
pStream->next_out += (mz_uint)out_bytes; pStream->avail_out -= (mz_uint)out_bytes;
pStream->total_out += (mz_uint)out_bytes;
if (defl_status < 0)
{
mz_status = MZ_STREAM_ERROR;
break;
}
else if (defl_status == TDEFL_STATUS_DONE)
{
mz_status = MZ_STREAM_END;
break;
}
else if (!pStream->avail_out)
break;
else if ((!pStream->avail_in) && (flush != MZ_FINISH))
{
if ((flush) || (pStream->total_in != orig_total_in) || (pStream->total_out != orig_total_out))
break;
return MZ_BUF_ERROR; // Can't make forward progress without some input.
}
}
return mz_status;
}
int mz_deflateEnd(mz_streamp pStream)
{
if (!pStream) return MZ_STREAM_ERROR;
if (pStream->state)
{
pStream->zfree(pStream->opaque, pStream->state);
pStream->state = NULL;
}
return MZ_OK;
}
mz_ulong mz_deflateBound(mz_streamp pStream, mz_ulong source_len)
{
(void)pStream;
// This is really over conservative. (And lame, but it's actually pretty tricky to compute a true upper bound given the way tdefl's blocking works.)
return MZ_MAX(128 + (source_len * 110) / 100, 128 + source_len + ((source_len / (31 * 1024)) + 1) * 5);
}
int mz_compress2(unsigned char *pDest, mz_ulong *pDest_len, const unsigned char *pSource, mz_ulong source_len, int level)
{
int status;
mz_stream stream;
memset(&stream, 0, sizeof(stream));
// In case mz_ulong is 64-bits (argh I hate longs).
if ((source_len | *pDest_len) > 0xFFFFFFFFU) return MZ_PARAM_ERROR;
stream.next_in = pSource;
stream.avail_in = (mz_uint32)source_len;
stream.next_out = pDest;
stream.avail_out = (mz_uint32)*pDest_len;
status = mz_deflateInit(&stream, level);
if (status != MZ_OK) return status;
status = mz_deflate(&stream, MZ_FINISH);
if (status != MZ_STREAM_END)
{
mz_deflateEnd(&stream);
return (status == MZ_OK) ? MZ_BUF_ERROR : status;
}
*pDest_len = stream.total_out;
return mz_deflateEnd(&stream);
}
__attribute__((__unused__)) int mz_compress(unsigned char *pDest, mz_ulong *pDest_len, const unsigned char *pSource, mz_ulong source_len)
{
return mz_compress2(pDest, pDest_len, pSource, source_len, MZ_DEFAULT_COMPRESSION);
}
__attribute__((__unused__)) mz_ulong mz_compressBound(mz_ulong source_len)
{
return mz_deflateBound(NULL, source_len);
}
__attribute__((__unused__)) const char *mz_error(int err)
{
static struct { int m_err; const char *m_pDesc; } s_error_descs[] =
{
{ MZ_OK, "" }, { MZ_STREAM_END, "stream end" }, { MZ_NEED_DICT, "need dictionary" }, { MZ_ERRNO, "file error" }, { MZ_STREAM_ERROR, "stream error" },
{ MZ_DATA_ERROR, "data error" }, { MZ_MEM_ERROR, "out of memory" }, { MZ_BUF_ERROR, "buf error" }, { MZ_VERSION_ERROR, "version error" }, { MZ_PARAM_ERROR, "parameter error" }
};
mz_uint i; for (i = 0; i < sizeof(s_error_descs) / sizeof(s_error_descs[0]); ++i) if (s_error_descs[i].m_err == err) return s_error_descs[i].m_pDesc;
return NULL;
}
#endif //MINIZ_NO_ZLIB_APIS
// ------------------- Low-level Compression (independent from all decompression API's)
// Purposely making these tables static for faster init and thread safety.
static const mz_uint16 s_tdefl_len_sym[256] = {
257,258,259,260,261,262,263,264,265,265,266,266,267,267,268,268,269,269,269,269,270,270,270,270,271,271,271,271,272,272,272,272,
273,273,273,273,273,273,273,273,274,274,274,274,274,274,274,274,275,275,275,275,275,275,275,275,276,276,276,276,276,276,276,276,
277,277,277,277,277,277,277,277,277,277,277,277,277,277,277,277,278,278,278,278,278,278,278,278,278,278,278,278,278,278,278,278,
279,279,279,279,279,279,279,279,279,279,279,279,279,279,279,279,280,280,280,280,280,280,280,280,280,280,280,280,280,280,280,280,
281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,
282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,282,
283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,283,
284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,285 };
static const mz_uint8 s_tdefl_len_extra[256] = {
0,0,0,0,0,0,0,0,1,1,1,1,1,1,1,1,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,
4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,
5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,
5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,0 };
static const mz_uint8 s_tdefl_small_dist_sym[512] = {
0,1,2,3,4,4,5,5,6,6,6,6,7,7,7,7,8,8,8,8,8,8,8,8,9,9,9,9,9,9,9,9,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,11,11,11,11,11,11,
11,11,11,11,11,11,11,11,11,11,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,13,
13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,14,14,14,14,14,14,14,14,14,14,14,14,
14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,14,
14,14,14,14,14,14,14,14,14,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,
15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,16,16,16,16,16,16,16,16,16,16,16,16,16,
16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,
16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,
16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,17,17,17,17,17,17,17,17,17,17,17,17,17,17,
17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,
17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,
17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17,17 };
static const mz_uint8 s_tdefl_small_dist_extra[512] = {
0,0,0,0,1,1,1,1,2,2,2,2,2,2,2,2,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,5,5,5,5,5,5,5,5,
5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,
6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,
6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
7,7,7,7,7,7,7,7 };
static const mz_uint8 s_tdefl_large_dist_sym[128] = {
0,0,18,19,20,20,21,21,22,22,22,22,23,23,23,23,24,24,24,24,24,24,24,24,25,25,25,25,25,25,25,25,26,26,26,26,26,26,26,26,26,26,26,26,
26,26,26,26,27,27,27,27,27,27,27,27,27,27,27,27,27,27,27,27,28,28,28,28,28,28,28,28,28,28,28,28,28,28,28,28,28,28,28,28,28,28,28,28,
28,28,28,28,28,28,28,28,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29 };
static const mz_uint8 s_tdefl_large_dist_extra[128] = {
0,0,8,8,9,9,9,9,10,10,10,10,10,10,10,10,11,11,11,11,11,11,11,11,11,11,11,11,11,11,11,11,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,
12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,12,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,
13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13,13 };
// Radix sorts tdefl_sym_freq[] array by 16-bit key m_key. Returns ptr to sorted values.
typedef struct { mz_uint16 m_key, m_sym_index; } tdefl_sym_freq;
static tdefl_sym_freq* tdefl_radix_sort_syms(mz_uint num_syms, tdefl_sym_freq* pSyms0, tdefl_sym_freq* pSyms1)
{
mz_uint32 total_passes = 2, pass_shift, pass, i, hist[256 * 2]; tdefl_sym_freq* pCur_syms = pSyms0, *pNew_syms = pSyms1; MZ_CLEAR_OBJ(hist);
for (i = 0; i < num_syms; i++) { mz_uint freq = pSyms0[i].m_key; hist[freq & 0xFF]++; hist[256 + ((freq >> 8) & 0xFF)]++; }
while ((total_passes > 1) && (num_syms == hist[(total_passes - 1) * 256])) total_passes--;
for (pass_shift = 0, pass = 0; pass < total_passes; pass++, pass_shift += 8)
{
const mz_uint32* pHist = &hist[pass << 8];
mz_uint offsets[256], cur_ofs = 0;
for (i = 0; i < 256; i++) { offsets[i] = cur_ofs; cur_ofs += pHist[i]; }
for (i = 0; i < num_syms; i++) pNew_syms[offsets[(pCur_syms[i].m_key >> pass_shift) & 0xFF]++] = pCur_syms[i];
{ tdefl_sym_freq* t = pCur_syms; pCur_syms = pNew_syms; pNew_syms = t; }
}
return pCur_syms;
}
// tdefl_calculate_minimum_redundancy() originally written by: Alistair Moffat, alistair@cs.mu.oz.au, Jyrki Katajainen, jyrki@diku.dk, November 1996.
static void tdefl_calculate_minimum_redundancy(tdefl_sym_freq *A, int n)
{
int root, leaf, next, avbl, used, dpth;
if (n==0) return; else if (n==1) { A[0].m_key = 1; return; }
A[0].m_key += A[1].m_key; root = 0; leaf = 2;
for (next=1; next < n-1; next++)
{
if (leaf>=n || A[root].m_key<A[leaf].m_key) { A[next].m_key = A[root].m_key; A[root++].m_key = (mz_uint16)next; } else A[next].m_key = A[leaf++].m_key;
if (leaf>=n || (root<next && A[root].m_key<A[leaf].m_key)) { A[next].m_key = (mz_uint16)(A[next].m_key + A[root].m_key); A[root++].m_key = (mz_uint16)next; } else A[next].m_key = (mz_uint16)(A[next].m_key + A[leaf++].m_key);
}
A[n-2].m_key = 0; for (next=n-3; next>=0; next--) A[next].m_key = A[A[next].m_key].m_key+1;
avbl = 1; used = dpth = 0; root = n-2; next = n-1;
while (avbl>0)
{
while (root>=0 && (int)A[root].m_key==dpth) { used++; root--; }
while (avbl>used) { A[next--].m_key = (mz_uint16)(dpth); avbl--; }
avbl = 2*used; dpth++; used = 0;
}
}
// Limits canonical Huffman code table's max code size.
enum { TDEFL_MAX_SUPPORTED_HUFF_CODESIZE = 32 };
static void tdefl_huffman_enforce_max_code_size(int *pNum_codes, int code_list_len, int max_code_size)
{
int i; mz_uint32 total = 0; if (code_list_len <= 1) return;
for (i = max_code_size + 1; i <= TDEFL_MAX_SUPPORTED_HUFF_CODESIZE; i++) pNum_codes[max_code_size] += pNum_codes[i];
for (i = max_code_size; i > 0; i--) total += (((mz_uint32)pNum_codes[i]) << (max_code_size - i));
while (total != (1UL << max_code_size))
{
pNum_codes[max_code_size]--;
for (i = max_code_size - 1; i > 0; i--) if (pNum_codes[i]) { pNum_codes[i]--; pNum_codes[i + 1] += 2; break; }
total--;
}
}
static void tdefl_optimize_huffman_table(tdefl_compressor *d, int table_num, int table_len, int code_size_limit, int static_table)
{
int i, j, l, num_codes[1 + TDEFL_MAX_SUPPORTED_HUFF_CODESIZE]; mz_uint next_code[TDEFL_MAX_SUPPORTED_HUFF_CODESIZE + 1]; MZ_CLEAR_OBJ(num_codes);
if (static_table)
{
for (i = 0; i < table_len; i++) num_codes[d->m_huff_code_sizes[table_num][i]]++;
}
else
{
tdefl_sym_freq syms0[TDEFL_MAX_HUFF_SYMBOLS], syms1[TDEFL_MAX_HUFF_SYMBOLS], *pSyms;
int num_used_syms = 0;
const mz_uint16 *pSym_count = &d->m_huff_count[table_num][0];
for (i = 0; i < table_len; i++) if (pSym_count[i]) { syms0[num_used_syms].m_key = (mz_uint16)pSym_count[i]; syms0[num_used_syms++].m_sym_index = (mz_uint16)i; }
pSyms = tdefl_radix_sort_syms(num_used_syms, syms0, syms1); tdefl_calculate_minimum_redundancy(pSyms, num_used_syms);
for (i = 0; i < num_used_syms; i++) num_codes[pSyms[i].m_key]++;
tdefl_huffman_enforce_max_code_size(num_codes, num_used_syms, code_size_limit);
MZ_CLEAR_OBJ(d->m_huff_code_sizes[table_num]); MZ_CLEAR_OBJ(d->m_huff_codes[table_num]);
for (i = 1, j = num_used_syms; i <= code_size_limit; i++)
for (l = num_codes[i]; l > 0; l--) d->m_huff_code_sizes[table_num][pSyms[--j].m_sym_index] = (mz_uint8)(i);
}
next_code[1] = 0; for (j = 0, i = 2; i <= code_size_limit; i++) next_code[i] = j = ((j + num_codes[i - 1]) << 1);
for (i = 0; i < table_len; i++)
{
mz_uint rev_code = 0, code, code_size; if ((code_size = d->m_huff_code_sizes[table_num][i]) == 0) continue;
code = next_code[code_size]++; for (l = code_size; l > 0; l--, code >>= 1) rev_code = (rev_code << 1) | (code & 1);
d->m_huff_codes[table_num][i] = (mz_uint16)rev_code;
}
}
#define TDEFL_PUT_BITS(b, l) do { \
mz_uint bits = b; mz_uint len = l; MZ_ASSERT(bits <= ((1U << len) - 1U)); \
d->m_bit_buffer |= (bits << d->m_bits_in); d->m_bits_in += len; \
while (d->m_bits_in >= 8) { \
if (d->m_pOutput_buf < d->m_pOutput_buf_end) \
*d->m_pOutput_buf++ = (mz_uint8)(d->m_bit_buffer); \
d->m_bit_buffer >>= 8; \
d->m_bits_in -= 8; \
} \
} MZ_MACRO_END
#define TDEFL_RLE_PREV_CODE_SIZE() { if (rle_repeat_count) { \
if (rle_repeat_count < 3) { \
d->m_huff_count[2][prev_code_size] = (mz_uint16)(d->m_huff_count[2][prev_code_size] + rle_repeat_count); \
while (rle_repeat_count--) packed_code_sizes[num_packed_code_sizes++] = prev_code_size; \
} else { \
d->m_huff_count[2][16] = (mz_uint16)(d->m_huff_count[2][16] + 1); packed_code_sizes[num_packed_code_sizes++] = 16; packed_code_sizes[num_packed_code_sizes++] = (mz_uint8)(rle_repeat_count - 3); \
} rle_repeat_count = 0; } }
#define TDEFL_RLE_ZERO_CODE_SIZE() { if (rle_z_count) { \
if (rle_z_count < 3) { \
d->m_huff_count[2][0] = (mz_uint16)(d->m_huff_count[2][0] + rle_z_count); while (rle_z_count--) packed_code_sizes[num_packed_code_sizes++] = 0; \
} else if (rle_z_count <= 10) { \
d->m_huff_count[2][17] = (mz_uint16)(d->m_huff_count[2][17] + 1); packed_code_sizes[num_packed_code_sizes++] = 17; packed_code_sizes[num_packed_code_sizes++] = (mz_uint8)(rle_z_count - 3); \
} else { \
d->m_huff_count[2][18] = (mz_uint16)(d->m_huff_count[2][18] + 1); packed_code_sizes[num_packed_code_sizes++] = 18; packed_code_sizes[num_packed_code_sizes++] = (mz_uint8)(rle_z_count - 11); \
} rle_z_count = 0; } }
static mz_uint8 s_tdefl_packed_code_size_syms_swizzle[] = { 16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15 };
static void tdefl_start_dynamic_block(tdefl_compressor *d)
{
int num_lit_codes, num_dist_codes, num_bit_lengths; mz_uint i, total_code_sizes_to_pack, num_packed_code_sizes, rle_z_count, rle_repeat_count, packed_code_sizes_index;
mz_uint8 code_sizes_to_pack[TDEFL_MAX_HUFF_SYMBOLS_0 + TDEFL_MAX_HUFF_SYMBOLS_1], packed_code_sizes[TDEFL_MAX_HUFF_SYMBOLS_0 + TDEFL_MAX_HUFF_SYMBOLS_1], prev_code_size = 0xFF;
d->m_huff_count[0][256] = 1;
tdefl_optimize_huffman_table(d, 0, TDEFL_MAX_HUFF_SYMBOLS_0, 15, MZ_FALSE);
tdefl_optimize_huffman_table(d, 1, TDEFL_MAX_HUFF_SYMBOLS_1, 15, MZ_FALSE);
for (num_lit_codes = 286; num_lit_codes > 257; num_lit_codes--) if (d->m_huff_code_sizes[0][num_lit_codes - 1]) break;
for (num_dist_codes = 30; num_dist_codes > 1; num_dist_codes--) if (d->m_huff_code_sizes[1][num_dist_codes - 1]) break;
memcpy(code_sizes_to_pack, &d->m_huff_code_sizes[0][0], num_lit_codes);
memcpy(code_sizes_to_pack + num_lit_codes, &d->m_huff_code_sizes[1][0], num_dist_codes);
total_code_sizes_to_pack = num_lit_codes + num_dist_codes; num_packed_code_sizes = 0; rle_z_count = 0; rle_repeat_count = 0;
memset(&d->m_huff_count[2][0], 0, sizeof(d->m_huff_count[2][0]) * TDEFL_MAX_HUFF_SYMBOLS_2);
for (i = 0; i < total_code_sizes_to_pack; i++)
{
mz_uint8 code_size = code_sizes_to_pack[i];
if (!code_size)
{
TDEFL_RLE_PREV_CODE_SIZE();
if (++rle_z_count == 138) { TDEFL_RLE_ZERO_CODE_SIZE(); }
}
else
{
TDEFL_RLE_ZERO_CODE_SIZE();
if (code_size != prev_code_size)
{
TDEFL_RLE_PREV_CODE_SIZE();
d->m_huff_count[2][code_size] = (mz_uint16)(d->m_huff_count[2][code_size] + 1); packed_code_sizes[num_packed_code_sizes++] = code_size;
}
else if (++rle_repeat_count == 6)
{
TDEFL_RLE_PREV_CODE_SIZE();
}
}
prev_code_size = code_size;
}
if (rle_repeat_count) { TDEFL_RLE_PREV_CODE_SIZE(); } else { TDEFL_RLE_ZERO_CODE_SIZE(); }
tdefl_optimize_huffman_table(d, 2, TDEFL_MAX_HUFF_SYMBOLS_2, 7, MZ_FALSE);
TDEFL_PUT_BITS(2, 2);
TDEFL_PUT_BITS(num_lit_codes - 257, 5);
TDEFL_PUT_BITS(num_dist_codes - 1, 5);
for (num_bit_lengths = 18; num_bit_lengths >= 0; num_bit_lengths--) if (d->m_huff_code_sizes[2][s_tdefl_packed_code_size_syms_swizzle[num_bit_lengths]]) break;
num_bit_lengths = MZ_MAX(4, (num_bit_lengths + 1)); TDEFL_PUT_BITS(num_bit_lengths - 4, 4);
for (i = 0; (int)i < num_bit_lengths; i++) TDEFL_PUT_BITS(d->m_huff_code_sizes[2][s_tdefl_packed_code_size_syms_swizzle[i]], 3);
for (packed_code_sizes_index = 0; packed_code_sizes_index < num_packed_code_sizes; )
{
mz_uint code = packed_code_sizes[packed_code_sizes_index++]; MZ_ASSERT(code < TDEFL_MAX_HUFF_SYMBOLS_2);
TDEFL_PUT_BITS(d->m_huff_codes[2][code], d->m_huff_code_sizes[2][code]);
if (code >= 16) TDEFL_PUT_BITS(packed_code_sizes[packed_code_sizes_index++], "\02\03\07"[code - 16]);
}
}
static void tdefl_start_static_block(tdefl_compressor *d)
{
mz_uint i;
mz_uint8 *p = &d->m_huff_code_sizes[0][0];
for (i = 0; i <= 143; ++i) *p++ = 8;
for ( ; i <= 255; ++i) *p++ = 9;
for ( ; i <= 279; ++i) *p++ = 7;
for ( ; i <= 287; ++i) *p++ = 8;
memset(d->m_huff_code_sizes[1], 5, 32);
tdefl_optimize_huffman_table(d, 0, 288, 15, MZ_TRUE);
tdefl_optimize_huffman_table(d, 1, 32, 15, MZ_TRUE);
TDEFL_PUT_BITS(1, 2);
}
static const mz_uint mz_bitmasks[17] = { 0x0000, 0x0001, 0x0003, 0x0007, 0x000F, 0x001F, 0x003F, 0x007F, 0x00FF, 0x01FF, 0x03FF, 0x07FF, 0x0FFF, 0x1FFF, 0x3FFF, 0x7FFF, 0xFFFF };
#if MINIZ_USE_UNALIGNED_LOADS_AND_STORES && MINIZ_LITTLE_ENDIAN && MINIZ_HAS_64BIT_REGISTERS
static mz_bool tdefl_compress_lz_codes(tdefl_compressor *d)
{
mz_uint flags;
mz_uint8 *pLZ_codes;
mz_uint8 *pOutput_buf = d->m_pOutput_buf;
mz_uint8 *pLZ_code_buf_end = d->m_pLZ_code_buf;
mz_uint64 bit_buffer = d->m_bit_buffer;
mz_uint bits_in = d->m_bits_in;
#define TDEFL_PUT_BITS_FAST(b, l) { bit_buffer |= (((mz_uint64)(b)) << bits_in); bits_in += (l); }
flags = 1;
for (pLZ_codes = d->m_lz_code_buf; pLZ_codes < pLZ_code_buf_end; flags >>= 1)
{
if (flags == 1)
flags = *pLZ_codes++ | 0x100;
if (flags & 1)
{
mz_uint s0, s1, n0, n1, sym, num_extra_bits;
mz_uint match_len = pLZ_codes[0], match_dist = *(const mz_uint16 *)(pLZ_codes + 1); pLZ_codes += 3;
MZ_ASSERT(d->m_huff_code_sizes[0][s_tdefl_len_sym[match_len]]);
TDEFL_PUT_BITS_FAST(d->m_huff_codes[0][s_tdefl_len_sym[match_len]], d->m_huff_code_sizes[0][s_tdefl_len_sym[match_len]]);
TDEFL_PUT_BITS_FAST(match_len & mz_bitmasks[s_tdefl_len_extra[match_len]], s_tdefl_len_extra[match_len]);
// This sequence coaxes MSVC into using cmov's vs. jmp's.
s0 = s_tdefl_small_dist_sym[match_dist & 511];
n0 = s_tdefl_small_dist_extra[match_dist & 511];
s1 = s_tdefl_large_dist_sym[match_dist >> 8];
n1 = s_tdefl_large_dist_extra[match_dist >> 8];
sym = (match_dist < 512) ? s0 : s1;
num_extra_bits = (match_dist < 512) ? n0 : n1;
MZ_ASSERT(d->m_huff_code_sizes[1][sym]);
TDEFL_PUT_BITS_FAST(d->m_huff_codes[1][sym], d->m_huff_code_sizes[1][sym]);
TDEFL_PUT_BITS_FAST(match_dist & mz_bitmasks[num_extra_bits], num_extra_bits);
}
else
{
mz_uint lit = *pLZ_codes++;
MZ_ASSERT(d->m_huff_code_sizes[0][lit]);
TDEFL_PUT_BITS_FAST(d->m_huff_codes[0][lit], d->m_huff_code_sizes[0][lit]);
if (((flags & 2) == 0) && (pLZ_codes < pLZ_code_buf_end))
{
flags >>= 1;
lit = *pLZ_codes++;
MZ_ASSERT(d->m_huff_code_sizes[0][lit]);
TDEFL_PUT_BITS_FAST(d->m_huff_codes[0][lit], d->m_huff_code_sizes[0][lit]);
if (((flags & 2) == 0) && (pLZ_codes < pLZ_code_buf_end))
{
flags >>= 1;
lit = *pLZ_codes++;
MZ_ASSERT(d->m_huff_code_sizes[0][lit]);
TDEFL_PUT_BITS_FAST(d->m_huff_codes[0][lit], d->m_huff_code_sizes[0][lit]);
}
}
}
if (pOutput_buf >= d->m_pOutput_buf_end)
return MZ_FALSE;
*(mz_uint64*)pOutput_buf = bit_buffer;
pOutput_buf += (bits_in >> 3);
bit_buffer >>= (bits_in & ~7);
bits_in &= 7;
}
#undef TDEFL_PUT_BITS_FAST
d->m_pOutput_buf = pOutput_buf;
d->m_bits_in = 0;
d->m_bit_buffer = 0;
while (bits_in)
{
mz_uint32 n = MZ_MIN(bits_in, 16);
TDEFL_PUT_BITS((mz_uint)bit_buffer & mz_bitmasks[n], n);
bit_buffer >>= n;
bits_in -= n;
}
TDEFL_PUT_BITS(d->m_huff_codes[0][256], d->m_huff_code_sizes[0][256]);
return (d->m_pOutput_buf < d->m_pOutput_buf_end);
}
#else
static mz_bool tdefl_compress_lz_codes(tdefl_compressor *d)
{
mz_uint flags;
mz_uint8 *pLZ_codes;
flags = 1;
for (pLZ_codes = d->m_lz_code_buf; pLZ_codes < d->m_pLZ_code_buf; flags >>= 1)
{
if (flags == 1)
flags = *pLZ_codes++ | 0x100;
if (flags & 1)
{
mz_uint sym, num_extra_bits;
mz_uint match_len = pLZ_codes[0], match_dist = (pLZ_codes[1] | (pLZ_codes[2] << 8)); pLZ_codes += 3;
MZ_ASSERT(d->m_huff_code_sizes[0][s_tdefl_len_sym[match_len]]);
TDEFL_PUT_BITS(d->m_huff_codes[0][s_tdefl_len_sym[match_len]], d->m_huff_code_sizes[0][s_tdefl_len_sym[match_len]]);
TDEFL_PUT_BITS(match_len & mz_bitmasks[s_tdefl_len_extra[match_len]], s_tdefl_len_extra[match_len]);
if (match_dist < 512)
{
sym = s_tdefl_small_dist_sym[match_dist]; num_extra_bits = s_tdefl_small_dist_extra[match_dist];
}
else
{
sym = s_tdefl_large_dist_sym[match_dist >> 8]; num_extra_bits = s_tdefl_large_dist_extra[match_dist >> 8];
}
MZ_ASSERT(d->m_huff_code_sizes[1][sym]);
TDEFL_PUT_BITS(d->m_huff_codes[1][sym], d->m_huff_code_sizes[1][sym]);
TDEFL_PUT_BITS(match_dist & mz_bitmasks[num_extra_bits], num_extra_bits);
}
else
{
mz_uint lit = *pLZ_codes++;
MZ_ASSERT(d->m_huff_code_sizes[0][lit]);
TDEFL_PUT_BITS(d->m_huff_codes[0][lit], d->m_huff_code_sizes[0][lit]);
}
}
TDEFL_PUT_BITS(d->m_huff_codes[0][256], d->m_huff_code_sizes[0][256]);
return (d->m_pOutput_buf < d->m_pOutput_buf_end);
}
#endif // MINIZ_USE_UNALIGNED_LOADS_AND_STORES && MINIZ_LITTLE_ENDIAN && MINIZ_HAS_64BIT_REGISTERS
static mz_bool tdefl_compress_block(tdefl_compressor *d, mz_bool static_block)
{
if (static_block)
tdefl_start_static_block(d);
else
tdefl_start_dynamic_block(d);
return tdefl_compress_lz_codes(d);
}
static int tdefl_flush_block(tdefl_compressor *d, int flush)
{
mz_uint saved_bit_buf, saved_bits_in;
mz_uint8 *pSaved_output_buf;
mz_bool comp_block_succeeded = MZ_FALSE;
int n, use_raw_block = ((d->m_flags & TDEFL_FORCE_ALL_RAW_BLOCKS) != 0) && (d->m_lookahead_pos - d->m_lz_code_buf_dict_pos) <= d->m_dict_size;
mz_uint8 *pOutput_buf_start = ((d->m_pPut_buf_func == NULL) && ((*d->m_pOut_buf_size - d->m_out_buf_ofs) >= TDEFL_OUT_BUF_SIZE)) ? ((mz_uint8 *)d->m_pOut_buf + d->m_out_buf_ofs) : d->m_output_buf;
d->m_pOutput_buf = pOutput_buf_start;
d->m_pOutput_buf_end = d->m_pOutput_buf + TDEFL_OUT_BUF_SIZE - 16;
MZ_ASSERT(!d->m_output_flush_remaining);
d->m_output_flush_ofs = 0;
d->m_output_flush_remaining = 0;
*d->m_pLZ_flags = (mz_uint8)(*d->m_pLZ_flags >> d->m_num_flags_left);
d->m_pLZ_code_buf -= (d->m_num_flags_left == 8);
TDEFL_PUT_BITS(flush == TDEFL_FINISH, 1);
pSaved_output_buf = d->m_pOutput_buf; saved_bit_buf = d->m_bit_buffer; saved_bits_in = d->m_bits_in;
if (!use_raw_block)
comp_block_succeeded = tdefl_compress_block(d, (d->m_flags & TDEFL_FORCE_ALL_STATIC_BLOCKS) || (d->m_total_lz_bytes < 48));
// If the block gets expanded, forget the current contents of the output buffer and send a raw block instead.
if ( ((use_raw_block) || ((d->m_total_lz_bytes) && ((d->m_pOutput_buf - pSaved_output_buf + 1U) >= d->m_total_lz_bytes))) &&
((d->m_lookahead_pos - d->m_lz_code_buf_dict_pos) <= d->m_dict_size) )
{
mz_uint i; d->m_pOutput_buf = pSaved_output_buf; d->m_bit_buffer = saved_bit_buf, d->m_bits_in = saved_bits_in;
TDEFL_PUT_BITS(0, 2);
if (d->m_bits_in) { TDEFL_PUT_BITS(0, 8 - d->m_bits_in); }
for (i = 2; i; --i, d->m_total_lz_bytes ^= 0xFFFF)
{
TDEFL_PUT_BITS(d->m_total_lz_bytes & 0xFFFF, 16);
}
for (i = 0; i < d->m_total_lz_bytes; ++i)
{
TDEFL_PUT_BITS(d->m_dict[(d->m_lz_code_buf_dict_pos + i) & TDEFL_LZ_DICT_SIZE_MASK], 8);
}
}
// Check for the extremely unlikely (if not impossible) case of the compressed block not fitting into the output buffer when using dynamic codes.
else if (!comp_block_succeeded)
{
d->m_pOutput_buf = pSaved_output_buf; d->m_bit_buffer = saved_bit_buf, d->m_bits_in = saved_bits_in;
tdefl_compress_block(d, MZ_TRUE);
}
if (flush)
{
if (flush == TDEFL_FINISH)
{
if (d->m_bits_in) { TDEFL_PUT_BITS(0, 8 - d->m_bits_in); }
}
else
{
mz_uint i, z = 0; TDEFL_PUT_BITS(0, 3); if (d->m_bits_in) { TDEFL_PUT_BITS(0, 8 - d->m_bits_in); } for (i = 2; i; --i, z ^= 0xFFFF) { TDEFL_PUT_BITS(z & 0xFFFF, 16); }
}
}
MZ_ASSERT(d->m_pOutput_buf < d->m_pOutput_buf_end);
memset(&d->m_huff_count[0][0], 0, sizeof(d->m_huff_count[0][0]) * TDEFL_MAX_HUFF_SYMBOLS_0);
memset(&d->m_huff_count[1][0], 0, sizeof(d->m_huff_count[1][0]) * TDEFL_MAX_HUFF_SYMBOLS_1);
d->m_pLZ_code_buf = d->m_lz_code_buf + 1; d->m_pLZ_flags = d->m_lz_code_buf; d->m_num_flags_left = 8; d->m_lz_code_buf_dict_pos += d->m_total_lz_bytes; d->m_total_lz_bytes = 0; d->m_block_index++;
if ((n = (int)(d->m_pOutput_buf - pOutput_buf_start)) != 0)
{
if (d->m_pPut_buf_func)
{
*d->m_pIn_buf_size = d->m_pSrc - (const mz_uint8 *)d->m_pIn_buf;
if (!(*d->m_pPut_buf_func)(d->m_output_buf, n, d->m_pPut_buf_user))
return (d->m_prev_return_status = TDEFL_STATUS_PUT_BUF_FAILED);
}
else if (pOutput_buf_start == d->m_output_buf)
{
int bytes_to_copy = (int)MZ_MIN((size_t)n, (size_t)(*d->m_pOut_buf_size - d->m_out_buf_ofs));
memcpy((mz_uint8 *)d->m_pOut_buf + d->m_out_buf_ofs, d->m_output_buf, bytes_to_copy);
d->m_out_buf_ofs += bytes_to_copy;
if ((n -= bytes_to_copy) != 0)
{
d->m_output_flush_ofs = bytes_to_copy;
d->m_output_flush_remaining = n;
}
}
else
{
d->m_out_buf_ofs += n;
}
}
return d->m_output_flush_remaining;
}
#if MINIZ_USE_UNALIGNED_LOADS_AND_STORES
#define TDEFL_READ_UNALIGNED_WORD(p) *(const mz_uint16*)(p)
static MZ_FORCEINLINE void tdefl_find_match(tdefl_compressor *d, mz_uint lookahead_pos, mz_uint max_dist, mz_uint max_match_len, mz_uint *pMatch_dist, mz_uint *pMatch_len)
{
mz_uint dist, pos = lookahead_pos & TDEFL_LZ_DICT_SIZE_MASK, match_len = *pMatch_len, probe_pos = pos, next_probe_pos, probe_len;
mz_uint num_probes_left = d->m_max_probes[match_len >= 32];
const mz_uint16 *s = (const mz_uint16*)(d->m_dict + pos), *p, *q;
mz_uint16 c01 = TDEFL_READ_UNALIGNED_WORD(&d->m_dict[pos + match_len - 1]), s01 = TDEFL_READ_UNALIGNED_WORD(s);
MZ_ASSERT(max_match_len <= TDEFL_MAX_MATCH_LEN); if (max_match_len <= match_len) return;
for ( ; ; )
{
for ( ; ; )
{
if (--num_probes_left == 0) return;
#define TDEFL_PROBE \
next_probe_pos = d->m_next[probe_pos]; \
if ((!next_probe_pos) || ((dist = (mz_uint16)(lookahead_pos - next_probe_pos)) > max_dist)) return; \
probe_pos = next_probe_pos & TDEFL_LZ_DICT_SIZE_MASK; \
if (TDEFL_READ_UNALIGNED_WORD(&d->m_dict[probe_pos + match_len - 1]) == c01) break;
TDEFL_PROBE; TDEFL_PROBE; TDEFL_PROBE;
}
if (!dist) break;
q = (const mz_uint16*)(d->m_dict + probe_pos);
if (TDEFL_READ_UNALIGNED_WORD(q) != s01) continue;
p = s; probe_len = 32;
do { } while ( (TDEFL_READ_UNALIGNED_WORD(++p) == TDEFL_READ_UNALIGNED_WORD(++q)) && (TDEFL_READ_UNALIGNED_WORD(++p) == TDEFL_READ_UNALIGNED_WORD(++q)) &&
(TDEFL_READ_UNALIGNED_WORD(++p) == TDEFL_READ_UNALIGNED_WORD(++q)) && (TDEFL_READ_UNALIGNED_WORD(++p) == TDEFL_READ_UNALIGNED_WORD(++q)) && (--probe_len > 0) );
if (!probe_len)
{
*pMatch_dist = dist; *pMatch_len = MZ_MIN(max_match_len, TDEFL_MAX_MATCH_LEN); break;
}
else if ((probe_len = ((mz_uint)(p - s) * 2) + (mz_uint)(*(const mz_uint8*)p == *(const mz_uint8*)q)) > match_len)
{
*pMatch_dist = dist; if ((*pMatch_len = match_len = MZ_MIN(max_match_len, probe_len)) == max_match_len) break;
c01 = TDEFL_READ_UNALIGNED_WORD(&d->m_dict[pos + match_len - 1]);
}
}
}
#else
static MZ_FORCEINLINE void tdefl_find_match(tdefl_compressor *d, mz_uint lookahead_pos, mz_uint max_dist, mz_uint max_match_len, mz_uint *pMatch_dist, mz_uint *pMatch_len)
{
mz_uint dist, pos = lookahead_pos & TDEFL_LZ_DICT_SIZE_MASK, match_len = *pMatch_len, probe_pos = pos, next_probe_pos, probe_len;
mz_uint num_probes_left = d->m_max_probes[match_len >= 32];
const mz_uint8 *s = d->m_dict + pos, *p, *q;
mz_uint8 c0 = d->m_dict[pos + match_len], c1 = d->m_dict[pos + match_len - 1];
MZ_ASSERT(max_match_len <= TDEFL_MAX_MATCH_LEN); if (max_match_len <= match_len) return;
for ( ; ; )
{
for ( ; ; )
{
if (--num_probes_left == 0) return;
#define TDEFL_PROBE \
next_probe_pos = d->m_next[probe_pos]; \
if ((!next_probe_pos) || ((dist = (mz_uint16)(lookahead_pos - next_probe_pos)) > max_dist)) return; \
probe_pos = next_probe_pos & TDEFL_LZ_DICT_SIZE_MASK; \
if ((d->m_dict[probe_pos + match_len] == c0) && (d->m_dict[probe_pos + match_len - 1] == c1)) break;
TDEFL_PROBE; TDEFL_PROBE; TDEFL_PROBE;
}
if (!dist) break; p = s; q = d->m_dict + probe_pos; for (probe_len = 0; probe_len < max_match_len; probe_len++) if (*p++ != *q++) break;
if (probe_len > match_len)
{
*pMatch_dist = dist; if ((*pMatch_len = match_len = probe_len) == max_match_len) return;
c0 = d->m_dict[pos + match_len]; c1 = d->m_dict[pos + match_len - 1];
}
}
}
#endif // #if MINIZ_USE_UNALIGNED_LOADS_AND_STORES
#if MINIZ_USE_UNALIGNED_LOADS_AND_STORES && MINIZ_LITTLE_ENDIAN
static mz_bool tdefl_compress_fast(tdefl_compressor *d)
{
// Faster, minimally featured LZRW1-style match+parse loop with better register utilization. Intended for applications where raw throughput is valued more highly than ratio.
mz_uint lookahead_pos = d->m_lookahead_pos, lookahead_size = d->m_lookahead_size, dict_size = d->m_dict_size, total_lz_bytes = d->m_total_lz_bytes, num_flags_left = d->m_num_flags_left;
mz_uint8 *pLZ_code_buf = d->m_pLZ_code_buf, *pLZ_flags = d->m_pLZ_flags;
mz_uint cur_pos = lookahead_pos & TDEFL_LZ_DICT_SIZE_MASK;
while ((d->m_src_buf_left) || ((d->m_flush) && (lookahead_size)))
{
const mz_uint TDEFL_COMP_FAST_LOOKAHEAD_SIZE = 4096;
mz_uint dst_pos = (lookahead_pos + lookahead_size) & TDEFL_LZ_DICT_SIZE_MASK;
mz_uint num_bytes_to_process = (mz_uint)MZ_MIN(d->m_src_buf_left, TDEFL_COMP_FAST_LOOKAHEAD_SIZE - lookahead_size);
d->m_src_buf_left -= num_bytes_to_process;
lookahead_size += num_bytes_to_process;
while (num_bytes_to_process)
{
mz_uint32 n = MZ_MIN(TDEFL_LZ_DICT_SIZE - dst_pos, num_bytes_to_process);
memcpy(d->m_dict + dst_pos, d->m_pSrc, n);
if (dst_pos < (TDEFL_MAX_MATCH_LEN - 1))
memcpy(d->m_dict + TDEFL_LZ_DICT_SIZE + dst_pos, d->m_pSrc, MZ_MIN(n, (TDEFL_MAX_MATCH_LEN - 1) - dst_pos));
d->m_pSrc += n;
dst_pos = (dst_pos + n) & TDEFL_LZ_DICT_SIZE_MASK;
num_bytes_to_process -= n;
}
dict_size = MZ_MIN(TDEFL_LZ_DICT_SIZE - lookahead_size, dict_size);
if ((!d->m_flush) && (lookahead_size < TDEFL_COMP_FAST_LOOKAHEAD_SIZE)) break;
while (lookahead_size >= 4)
{
mz_uint cur_match_dist, cur_match_len = 1;
mz_uint8 *pCur_dict = d->m_dict + cur_pos;
mz_uint first_trigram = (*(const mz_uint32 *)pCur_dict) & 0xFFFFFF;
mz_uint hash = (first_trigram ^ (first_trigram >> (24 - (TDEFL_LZ_HASH_BITS - 8)))) & TDEFL_LEVEL1_HASH_SIZE_MASK;
mz_uint probe_pos = d->m_hash[hash];
d->m_hash[hash] = (mz_uint16)lookahead_pos;
if (((cur_match_dist = (mz_uint16)(lookahead_pos - probe_pos)) <= dict_size) && ((*(const mz_uint32 *)(d->m_dict + (probe_pos &= TDEFL_LZ_DICT_SIZE_MASK)) & 0xFFFFFF) == first_trigram))
{
const mz_uint16 *p = (const mz_uint16 *)pCur_dict;
const mz_uint16 *q = (const mz_uint16 *)(d->m_dict + probe_pos);
mz_uint32 probe_len = 32;
do { } while ( (TDEFL_READ_UNALIGNED_WORD(++p) == TDEFL_READ_UNALIGNED_WORD(++q)) && (TDEFL_READ_UNALIGNED_WORD(++p) == TDEFL_READ_UNALIGNED_WORD(++q)) &&
(TDEFL_READ_UNALIGNED_WORD(++p) == TDEFL_READ_UNALIGNED_WORD(++q)) && (TDEFL_READ_UNALIGNED_WORD(++p) == TDEFL_READ_UNALIGNED_WORD(++q)) && (--probe_len > 0) );
cur_match_len = ((mz_uint)(p - (const mz_uint16 *)pCur_dict) * 2) + (mz_uint)(*(const mz_uint8 *)p == *(const mz_uint8 *)q);
if (!probe_len)
cur_match_len = cur_match_dist ? TDEFL_MAX_MATCH_LEN : 0;
if ((cur_match_len < TDEFL_MIN_MATCH_LEN) || ((cur_match_len == TDEFL_MIN_MATCH_LEN) && (cur_match_dist >= 8U*1024U)))
{
cur_match_len = 1;
*pLZ_code_buf++ = (mz_uint8)first_trigram;
*pLZ_flags = (mz_uint8)(*pLZ_flags >> 1);
d->m_huff_count[0][(mz_uint8)first_trigram]++;
}
else
{
mz_uint32 s0, s1;
cur_match_len = MZ_MIN(cur_match_len, lookahead_size);
MZ_ASSERT((cur_match_len >= TDEFL_MIN_MATCH_LEN) && (cur_match_dist >= 1) && (cur_match_dist <= TDEFL_LZ_DICT_SIZE));
cur_match_dist--;
pLZ_code_buf[0] = (mz_uint8)(cur_match_len - TDEFL_MIN_MATCH_LEN);
*(mz_uint16 *)(&pLZ_code_buf[1]) = (mz_uint16)cur_match_dist;
pLZ_code_buf += 3;
*pLZ_flags = (mz_uint8)((*pLZ_flags >> 1) | 0x80);
s0 = s_tdefl_small_dist_sym[cur_match_dist & 511];
s1 = s_tdefl_large_dist_sym[cur_match_dist >> 8];
d->m_huff_count[1][(cur_match_dist < 512) ? s0 : s1]++;
d->m_huff_count[0][s_tdefl_len_sym[cur_match_len - TDEFL_MIN_MATCH_LEN]]++;
}
}
else
{
*pLZ_code_buf++ = (mz_uint8)first_trigram;
*pLZ_flags = (mz_uint8)(*pLZ_flags >> 1);
d->m_huff_count[0][(mz_uint8)first_trigram]++;
}
if (--num_flags_left == 0) { num_flags_left = 8; pLZ_flags = pLZ_code_buf++; }
total_lz_bytes += cur_match_len;
lookahead_pos += cur_match_len;
dict_size = MZ_MIN(dict_size + cur_match_len, TDEFL_LZ_DICT_SIZE);
cur_pos = (cur_pos + cur_match_len) & TDEFL_LZ_DICT_SIZE_MASK;
MZ_ASSERT(lookahead_size >= cur_match_len);
lookahead_size -= cur_match_len;
if (pLZ_code_buf > &d->m_lz_code_buf[TDEFL_LZ_CODE_BUF_SIZE - 8])
{
int n;
d->m_lookahead_pos = lookahead_pos; d->m_lookahead_size = lookahead_size; d->m_dict_size = dict_size;
d->m_total_lz_bytes = total_lz_bytes; d->m_pLZ_code_buf = pLZ_code_buf; d->m_pLZ_flags = pLZ_flags; d->m_num_flags_left = num_flags_left;
if ((n = tdefl_flush_block(d, 0)) != 0)
return (n < 0) ? MZ_FALSE : MZ_TRUE;
total_lz_bytes = d->m_total_lz_bytes; pLZ_code_buf = d->m_pLZ_code_buf; pLZ_flags = d->m_pLZ_flags; num_flags_left = d->m_num_flags_left;
}
}
while (lookahead_size)
{
mz_uint8 lit = d->m_dict[cur_pos];
total_lz_bytes++;
*pLZ_code_buf++ = lit;
*pLZ_flags = (mz_uint8)(*pLZ_flags >> 1);
if (--num_flags_left == 0) { num_flags_left = 8; pLZ_flags = pLZ_code_buf++; }
d->m_huff_count[0][lit]++;
lookahead_pos++;
dict_size = MZ_MIN(dict_size + 1, TDEFL_LZ_DICT_SIZE);
cur_pos = (cur_pos + 1) & TDEFL_LZ_DICT_SIZE_MASK;
lookahead_size--;
if (pLZ_code_buf > &d->m_lz_code_buf[TDEFL_LZ_CODE_BUF_SIZE - 8])
{
int n;
d->m_lookahead_pos = lookahead_pos; d->m_lookahead_size = lookahead_size; d->m_dict_size = dict_size;
d->m_total_lz_bytes = total_lz_bytes; d->m_pLZ_code_buf = pLZ_code_buf; d->m_pLZ_flags = pLZ_flags; d->m_num_flags_left = num_flags_left;
if ((n = tdefl_flush_block(d, 0)) != 0)
return (n < 0) ? MZ_FALSE : MZ_TRUE;
total_lz_bytes = d->m_total_lz_bytes; pLZ_code_buf = d->m_pLZ_code_buf; pLZ_flags = d->m_pLZ_flags; num_flags_left = d->m_num_flags_left;
}
}
}
d->m_lookahead_pos = lookahead_pos; d->m_lookahead_size = lookahead_size; d->m_dict_size = dict_size;
d->m_total_lz_bytes = total_lz_bytes; d->m_pLZ_code_buf = pLZ_code_buf; d->m_pLZ_flags = pLZ_flags; d->m_num_flags_left = num_flags_left;
return MZ_TRUE;
}
#endif // MINIZ_USE_UNALIGNED_LOADS_AND_STORES && MINIZ_LITTLE_ENDIAN
static MZ_FORCEINLINE void tdefl_record_literal(tdefl_compressor *d, mz_uint8 lit)
{
d->m_total_lz_bytes++;
*d->m_pLZ_code_buf++ = lit;
*d->m_pLZ_flags = (mz_uint8)(*d->m_pLZ_flags >> 1); if (--d->m_num_flags_left == 0) { d->m_num_flags_left = 8; d->m_pLZ_flags = d->m_pLZ_code_buf++; }
d->m_huff_count[0][lit]++;
}
static MZ_FORCEINLINE void tdefl_record_match(tdefl_compressor *d, mz_uint match_len, mz_uint match_dist)
{
mz_uint32 s0, s1;
MZ_ASSERT((match_len >= TDEFL_MIN_MATCH_LEN) && (match_dist >= 1) && (match_dist <= TDEFL_LZ_DICT_SIZE));
d->m_total_lz_bytes += match_len;
d->m_pLZ_code_buf[0] = (mz_uint8)(match_len - TDEFL_MIN_MATCH_LEN);
match_dist -= 1;
d->m_pLZ_code_buf[1] = (mz_uint8)(match_dist & 0xFF);
d->m_pLZ_code_buf[2] = (mz_uint8)(match_dist >> 8); d->m_pLZ_code_buf += 3;
*d->m_pLZ_flags = (mz_uint8)((*d->m_pLZ_flags >> 1) | 0x80); if (--d->m_num_flags_left == 0) { d->m_num_flags_left = 8; d->m_pLZ_flags = d->m_pLZ_code_buf++; }
s0 = s_tdefl_small_dist_sym[match_dist & 511]; s1 = s_tdefl_large_dist_sym[(match_dist >> 8) & 127];
d->m_huff_count[1][(match_dist < 512) ? s0 : s1]++;
if (match_len >= TDEFL_MIN_MATCH_LEN) d->m_huff_count[0][s_tdefl_len_sym[match_len - TDEFL_MIN_MATCH_LEN]]++;
}
static mz_bool tdefl_compress_normal(tdefl_compressor *d)
{
const mz_uint8 *pSrc = d->m_pSrc; size_t src_buf_left = d->m_src_buf_left;
tdefl_flush flush = d->m_flush;
while ((src_buf_left) || ((flush) && (d->m_lookahead_size)))
{
mz_uint len_to_move, cur_match_dist, cur_match_len, cur_pos;
// Update dictionary and hash chains. Keeps the lookahead size equal to TDEFL_MAX_MATCH_LEN.
if ((d->m_lookahead_size + d->m_dict_size) >= (TDEFL_MIN_MATCH_LEN - 1))
{
mz_uint dst_pos = (d->m_lookahead_pos + d->m_lookahead_size) & TDEFL_LZ_DICT_SIZE_MASK, ins_pos = d->m_lookahead_pos + d->m_lookahead_size - 2;
mz_uint hash = (d->m_dict[ins_pos & TDEFL_LZ_DICT_SIZE_MASK] << TDEFL_LZ_HASH_SHIFT) ^ d->m_dict[(ins_pos + 1) & TDEFL_LZ_DICT_SIZE_MASK];
mz_uint num_bytes_to_process = (mz_uint)MZ_MIN(src_buf_left, TDEFL_MAX_MATCH_LEN - d->m_lookahead_size);
const mz_uint8 *pSrc_end = pSrc + num_bytes_to_process;
src_buf_left -= num_bytes_to_process;
d->m_lookahead_size += num_bytes_to_process;
while (pSrc != pSrc_end)
{
mz_uint8 c = *pSrc++; d->m_dict[dst_pos] = c; if (dst_pos < (TDEFL_MAX_MATCH_LEN - 1)) d->m_dict[TDEFL_LZ_DICT_SIZE + dst_pos] = c;
hash = ((hash << TDEFL_LZ_HASH_SHIFT) ^ c) & (TDEFL_LZ_HASH_SIZE - 1);
d->m_next[ins_pos & TDEFL_LZ_DICT_SIZE_MASK] = d->m_hash[hash]; d->m_hash[hash] = (mz_uint16)(ins_pos);
dst_pos = (dst_pos + 1) & TDEFL_LZ_DICT_SIZE_MASK; ins_pos++;
}
}
else
{
while ((src_buf_left) && (d->m_lookahead_size < TDEFL_MAX_MATCH_LEN))
{
mz_uint8 c = *pSrc++;
mz_uint dst_pos = (d->m_lookahead_pos + d->m_lookahead_size) & TDEFL_LZ_DICT_SIZE_MASK;
src_buf_left--;
d->m_dict[dst_pos] = c;
if (dst_pos < (TDEFL_MAX_MATCH_LEN - 1))
d->m_dict[TDEFL_LZ_DICT_SIZE + dst_pos] = c;
if ((++d->m_lookahead_size + d->m_dict_size) >= TDEFL_MIN_MATCH_LEN)
{
mz_uint ins_pos = d->m_lookahead_pos + (d->m_lookahead_size - 1) - 2;
mz_uint hash = ((d->m_dict[ins_pos & TDEFL_LZ_DICT_SIZE_MASK] << (TDEFL_LZ_HASH_SHIFT * 2)) ^ (d->m_dict[(ins_pos + 1) & TDEFL_LZ_DICT_SIZE_MASK] << TDEFL_LZ_HASH_SHIFT) ^ c) & (TDEFL_LZ_HASH_SIZE - 1);
d->m_next[ins_pos & TDEFL_LZ_DICT_SIZE_MASK] = d->m_hash[hash]; d->m_hash[hash] = (mz_uint16)(ins_pos);
}
}
}
d->m_dict_size = MZ_MIN(TDEFL_LZ_DICT_SIZE - d->m_lookahead_size, d->m_dict_size);
if ((!flush) && (d->m_lookahead_size < TDEFL_MAX_MATCH_LEN))
break;
// Simple lazy/greedy parsing state machine.
len_to_move = 1; cur_match_dist = 0; cur_match_len = d->m_saved_match_len ? d->m_saved_match_len : (TDEFL_MIN_MATCH_LEN - 1); cur_pos = d->m_lookahead_pos & TDEFL_LZ_DICT_SIZE_MASK;
if (d->m_flags & (TDEFL_RLE_MATCHES | TDEFL_FORCE_ALL_RAW_BLOCKS))
{
if ((d->m_dict_size) && (!(d->m_flags & TDEFL_FORCE_ALL_RAW_BLOCKS)))
{
mz_uint8 c = d->m_dict[(cur_pos - 1) & TDEFL_LZ_DICT_SIZE_MASK];
cur_match_len = 0; while (cur_match_len < d->m_lookahead_size) { if (d->m_dict[cur_pos + cur_match_len] != c) break; cur_match_len++; }
if (cur_match_len < TDEFL_MIN_MATCH_LEN) cur_match_len = 0; else cur_match_dist = 1;
}
}
else
{
tdefl_find_match(d, d->m_lookahead_pos, d->m_dict_size, d->m_lookahead_size, &cur_match_dist, &cur_match_len);
}
if (((cur_match_len == TDEFL_MIN_MATCH_LEN) && (cur_match_dist >= 8U*1024U)) || (cur_pos == cur_match_dist) || ((d->m_flags & TDEFL_FILTER_MATCHES) && (cur_match_len <= 5)))
{
cur_match_dist = cur_match_len = 0;
}
if (d->m_saved_match_len)
{
if (cur_match_len > d->m_saved_match_len)
{
tdefl_record_literal(d, (mz_uint8)d->m_saved_lit);
if (cur_match_len >= 128)
{
tdefl_record_match(d, cur_match_len, cur_match_dist);
d->m_saved_match_len = 0; len_to_move = cur_match_len;
}
else
{
d->m_saved_lit = d->m_dict[cur_pos]; d->m_saved_match_dist = cur_match_dist; d->m_saved_match_len = cur_match_len;
}
}
else
{
tdefl_record_match(d, d->m_saved_match_len, d->m_saved_match_dist);
len_to_move = d->m_saved_match_len - 1; d->m_saved_match_len = 0;
}
}
else if (!cur_match_dist)
tdefl_record_literal(d, d->m_dict[MZ_MIN(cur_pos, sizeof(d->m_dict) - 1)]);
else if ((d->m_greedy_parsing) || (d->m_flags & TDEFL_RLE_MATCHES) || (cur_match_len >= 128))
{
tdefl_record_match(d, cur_match_len, cur_match_dist);
len_to_move = cur_match_len;
}
else
{
d->m_saved_lit = d->m_dict[MZ_MIN(cur_pos, sizeof(d->m_dict) - 1)]; d->m_saved_match_dist = cur_match_dist; d->m_saved_match_len = cur_match_len;
}
// Move the lookahead forward by len_to_move bytes.
d->m_lookahead_pos += len_to_move;
MZ_ASSERT(d->m_lookahead_size >= len_to_move);
d->m_lookahead_size -= len_to_move;
d->m_dict_size = MZ_MIN(d->m_dict_size + len_to_move, TDEFL_LZ_DICT_SIZE);
// Check if it's time to flush the current LZ codes to the internal output buffer.
if ( (d->m_pLZ_code_buf > &d->m_lz_code_buf[TDEFL_LZ_CODE_BUF_SIZE - 8]) ||
( (d->m_total_lz_bytes > 31*1024) && (((((mz_uint)(d->m_pLZ_code_buf - d->m_lz_code_buf) * 115) >> 7) >= d->m_total_lz_bytes) || (d->m_flags & TDEFL_FORCE_ALL_RAW_BLOCKS))) )
{
int n;
d->m_pSrc = pSrc; d->m_src_buf_left = src_buf_left;
if ((n = tdefl_flush_block(d, 0)) != 0)
return (n < 0) ? MZ_FALSE : MZ_TRUE;
}
}
d->m_pSrc = pSrc; d->m_src_buf_left = src_buf_left;
return MZ_TRUE;
}
static tdefl_status tdefl_flush_output_buffer(tdefl_compressor *d)
{
if (d->m_pIn_buf_size)
{
*d->m_pIn_buf_size = d->m_pSrc - (const mz_uint8 *)d->m_pIn_buf;
}
if (d->m_pOut_buf_size)
{
size_t n = MZ_MIN(*d->m_pOut_buf_size - d->m_out_buf_ofs, d->m_output_flush_remaining);
memcpy((mz_uint8 *)d->m_pOut_buf + d->m_out_buf_ofs, d->m_output_buf + d->m_output_flush_ofs, n);
d->m_output_flush_ofs += (mz_uint)n;
d->m_output_flush_remaining -= (mz_uint)n;
d->m_out_buf_ofs += n;
*d->m_pOut_buf_size = d->m_out_buf_ofs;
}
return (d->m_finished && !d->m_output_flush_remaining) ? TDEFL_STATUS_DONE : TDEFL_STATUS_OKAY;
}
tdefl_status tdefl_compress(tdefl_compressor *d, const void *pIn_buf, size_t *pIn_buf_size, void *pOut_buf, size_t *pOut_buf_size, tdefl_flush flush)
{
if (!d)
{
if (pIn_buf_size) *pIn_buf_size = 0;
if (pOut_buf_size) *pOut_buf_size = 0;
return TDEFL_STATUS_BAD_PARAM;
}
d->m_pIn_buf = pIn_buf; d->m_pIn_buf_size = pIn_buf_size;
d->m_pOut_buf = pOut_buf; d->m_pOut_buf_size = pOut_buf_size;
d->m_pSrc = (const mz_uint8 *)(pIn_buf); d->m_src_buf_left = pIn_buf_size ? *pIn_buf_size : 0;
d->m_out_buf_ofs = 0;
d->m_flush = flush;
if ( ((d->m_pPut_buf_func != NULL) == ((pOut_buf != NULL) || (pOut_buf_size != NULL))) || (d->m_prev_return_status != TDEFL_STATUS_OKAY) ||
(d->m_wants_to_finish && (flush != TDEFL_FINISH)) || (pIn_buf_size && *pIn_buf_size && !pIn_buf) || (pOut_buf_size && *pOut_buf_size && !pOut_buf) )
{
if (pIn_buf_size) *pIn_buf_size = 0;
if (pOut_buf_size) *pOut_buf_size = 0;
return (d->m_prev_return_status = TDEFL_STATUS_BAD_PARAM);
}
d->m_wants_to_finish |= (flush == TDEFL_FINISH);
if ((d->m_output_flush_remaining) || (d->m_finished))
return (d->m_prev_return_status = tdefl_flush_output_buffer(d));
#if MINIZ_USE_UNALIGNED_LOADS_AND_STORES && MINIZ_LITTLE_ENDIAN
if (((d->m_flags & TDEFL_MAX_PROBES_MASK) == 1) &&
((d->m_flags & TDEFL_GREEDY_PARSING_FLAG) != 0) &&
((d->m_flags & (TDEFL_FILTER_MATCHES | TDEFL_FORCE_ALL_RAW_BLOCKS | TDEFL_RLE_MATCHES)) == 0))
{
if (!tdefl_compress_fast(d))
return d->m_prev_return_status;
}
else
#endif // #if MINIZ_USE_UNALIGNED_LOADS_AND_STORES && MINIZ_LITTLE_ENDIAN
{
if (!tdefl_compress_normal(d))
return d->m_prev_return_status;
}
if ((flush) && (!d->m_lookahead_size) && (!d->m_src_buf_left) && (!d->m_output_flush_remaining))
{
if (tdefl_flush_block(d, flush) < 0)
return d->m_prev_return_status;
d->m_finished = (flush == TDEFL_FINISH);
if (flush == TDEFL_FULL_FLUSH) { MZ_CLEAR_OBJ(d->m_hash); MZ_CLEAR_OBJ(d->m_next); d->m_dict_size = 0; }
}
return (d->m_prev_return_status = tdefl_flush_output_buffer(d));
}
tdefl_status tdefl_init(tdefl_compressor *d, tdefl_put_buf_func_ptr pPut_buf_func, void *pPut_buf_user, int flags)
{
d->m_pPut_buf_func = pPut_buf_func; d->m_pPut_buf_user = pPut_buf_user;
d->m_flags = (mz_uint)(flags); d->m_max_probes[0] = 1 + ((flags & 0xFFF) + 2) / 3; d->m_greedy_parsing = (flags & TDEFL_GREEDY_PARSING_FLAG) != 0;
d->m_max_probes[1] = 1 + (((flags & 0xFFF) >> 2) + 2) / 3;
if (!(flags & TDEFL_NONDETERMINISTIC_PARSING_FLAG)) MZ_CLEAR_OBJ(d->m_hash);
d->m_lookahead_pos = d->m_lookahead_size = d->m_dict_size = d->m_total_lz_bytes = d->m_lz_code_buf_dict_pos = d->m_bits_in = 0;
d->m_output_flush_ofs = d->m_output_flush_remaining = d->m_finished = d->m_block_index = d->m_bit_buffer = d->m_wants_to_finish = 0;
d->m_pLZ_code_buf = d->m_lz_code_buf + 1; d->m_pLZ_flags = d->m_lz_code_buf; d->m_num_flags_left = 8;
d->m_pOutput_buf = d->m_output_buf; d->m_pOutput_buf_end = d->m_output_buf; d->m_prev_return_status = TDEFL_STATUS_OKAY;
d->m_saved_match_dist = d->m_saved_match_len = d->m_saved_lit = 0;
d->m_pIn_buf = NULL; d->m_pOut_buf = NULL;
d->m_pIn_buf_size = NULL; d->m_pOut_buf_size = NULL;
d->m_flush = TDEFL_NO_FLUSH; d->m_pSrc = NULL; d->m_src_buf_left = 0; d->m_out_buf_ofs = 0;
memset(&d->m_huff_count[0][0], 0, sizeof(d->m_huff_count[0][0]) * TDEFL_MAX_HUFF_SYMBOLS_0);
memset(&d->m_huff_count[1][0], 0, sizeof(d->m_huff_count[1][0]) * TDEFL_MAX_HUFF_SYMBOLS_1);
return TDEFL_STATUS_OKAY;
}
typedef struct
{
size_t m_size, m_capacity;
mz_uint8 *m_pBuf;
mz_bool m_expandable;
} tdefl_output_buffer;
#ifndef MINIZ_NO_ZLIB_APIS
static const mz_uint s_tdefl_num_probes[11] = { 0, 1, 6, 32, 16, 32, 128, 256, 512, 768, 1500 };
// level may actually range from [0,10] (10 is a "hidden" max level, where we want a bit more compression and it's fine if throughput to fall off a cliff on some files).
mz_uint tdefl_create_comp_flags_from_zip_params(int level, int window_bits, int strategy)
{
mz_uint comp_flags = s_tdefl_num_probes[(level >= 0) ? MZ_MIN(10, level) : MZ_DEFAULT_LEVEL] | ((level <= 3) ? TDEFL_GREEDY_PARSING_FLAG : 0);
(void)window_bits;
if (!level) comp_flags |= TDEFL_FORCE_ALL_RAW_BLOCKS;
else if (strategy == MZ_FILTERED) comp_flags |= TDEFL_FILTER_MATCHES;
else if (strategy == MZ_HUFFMAN_ONLY) comp_flags &= ~TDEFL_MAX_PROBES_MASK;
else if (strategy == MZ_FIXED) comp_flags |= TDEFL_FORCE_ALL_STATIC_BLOCKS;
else if (strategy == MZ_RLE) comp_flags |= TDEFL_RLE_MATCHES;
return comp_flags;
}
#endif //MINIZ_NO_ZLIB_APIS
#endif // MINIZ_HEADER_FILE_ONLY
/*
This is free and unencumbered software released into the public domain.
Anyone is free to copy, modify, publish, use, compile, sell, or
distribute this software, either in source code form or as a compiled
binary, for any purpose, commercial or non-commercial, and by any
means.
In jurisdictions that recognize copyright laws, the author or authors
of this software dedicate any and all copyright interest in the
software to the public domain. We make this dedication for the benefit
of the public at large and to the detriment of our heirs and
successors. We intend this dedication to be an overt act of
relinquishment in perpetuity of all present and future rights to this
software under copyright law.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
OTHER DEALINGS IN THE SOFTWARE.
For more information, please refer to <http://unlicense.org/>
*/
View Git Blame Copy Permalink