diff --git a/.travis.yml b/.travis.yml index 972c1b4ba..9e2f58613 100644 --- a/.travis.yml +++ b/.travis.yml @@ -44,7 +44,7 @@ matrix: - qemu-user-static - os: linux sudo: required - env: PLATFORM="Ubuntu 12.04" CMD="make -C programs zstd-small && make -C programs zstd-decompress && make -C programs zstd-compress && make clean && make -C tests versionsTest" + env: PLATFORM="Ubuntu 12.04" CMD="make -C programs zstd-small && make -C programs zstd-decompress && make -C programs zstd-compress && make -C programs clean && make -C tests versionsTest" - os: linux sudo: required env: PLATFORM="Ubuntu 12.04" CMD="make asan32" diff --git a/NEWS b/NEWS index a9454b40b..570d66799 100644 --- a/NEWS +++ b/NEWS @@ -1,5 +1,6 @@ v1.1.1 New : command -M#, --memory=, --memlimit=, --memlimit-decompress= to limit allowed memory consumption +Changed : zstd_errors.h is now part of include installation v1.1.0 New : contrib/pzstd, parallel version of zstd, by Nick Terrell diff --git a/contrib/gen_html/Makefile b/contrib/gen_html/Makefile new file mode 100644 index 000000000..c68e560a1 --- /dev/null +++ b/contrib/gen_html/Makefile @@ -0,0 +1,36 @@ +# ########################################################################## +# Copyright (c) 2016-present, Facebook, Inc. +# All rights reserved. +# +# This source code is licensed under the BSD-style license found in the +# LICENSE file in the root directory of this source tree. An additional grant +# of patent rights can be found in the PATENTS file in the same directory. +# ########################################################################## + + +CFLAGS ?= -O3 +CFLAGS += -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow -Wstrict-aliasing=1 -Wswitch-enum -Wno-comment +CFLAGS += $(MOREFLAGS) +FLAGS = $(CPPFLAGS) $(CFLAGS) $(LDFLAGS) + + + +# Define *.exe as extension for Windows systems +ifneq (,$(filter Windows%,$(OS))) +EXT =.exe +else +EXT = +endif + + +.PHONY: default gen_html + +default: gen_html + +gen_html: gen_html.cpp + $(CXX) $(FLAGS) $^ -o $@$(EXT) + + +clean: + @$(RM) gen_html$(EXT) + @echo Cleaning completed diff --git a/contrib/gen_html/README.md b/contrib/gen_html/README.md new file mode 100644 index 000000000..63a4caa25 --- /dev/null +++ b/contrib/gen_html/README.md @@ -0,0 +1,31 @@ +gen_html - a program for automatic generation of zstd manual +============================================================ + +#### Introduction + +This simple C++ program generates a single-page HTML manual from `zstd.h`. + +The format of recognized comment blocks is following: +- comments of type `/*!` mean: this is a function declaration; switch comments with declarations +- comments of type `/**` and `/*-` mean: this is a comment; use a `

` header for the first line +- comments of type `/*=` and `/**=` mean: use a `

` header and show also all functions until first empty line +- comments of type `/*X` where `X` is different from above-mentioned are ignored + +Moreover: +- `ZSTDLIB_API` is removed to improve readability +- `typedef` are detected and included even if uncommented +- comments of type `/**<` and `/*!<` are detected and only function declaration is highlighted (bold) + + +#### Usage + +The program requires 3 parameters: +``` +gen_html [zstd_version] [input_file] [output_html] +``` + +To compile program and generate zstd manual we have used: +``` +make +./gen_html.exe 1.1.1 ../../lib/zstd.h zstd_manual.html +``` diff --git a/contrib/gen_html/gen_html.cpp b/contrib/gen_html/gen_html.cpp new file mode 100644 index 000000000..2157829f7 --- /dev/null +++ b/contrib/gen_html/gen_html.cpp @@ -0,0 +1,216 @@ +/* + * Copyright (c) 2016-present, Przemyslaw Skibinski, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under the BSD-style license found in the + * LICENSE file in the root directory of this source tree. An additional grant + * of patent rights can be found in the PATENTS file in the same directory. + */ + +#include +#include +#include +#include +using namespace std; + + +/* trim string at the beginning and at the end */ +void trim(string& s, string characters) +{ + size_t p = s.find_first_not_of(characters); + s.erase(0, p); + + p = s.find_last_not_of(characters); + if (string::npos != p) + s.erase(p+1); +} + + +/* trim C++ style comments */ +void trim_comments(string &s) +{ + size_t spos, epos; + + spos = s.find("/*"); + epos = s.find("*/"); + s = s.substr(spos+3, epos-(spos+3)); +} + + +/* get lines until a given terminator */ +vector get_lines(vector& input, int& linenum, string terminator) +{ + vector out; + string line; + size_t epos; + + while ((size_t)linenum < input.size()) { + line = input[linenum]; + + if (terminator.empty() && line.empty()) { linenum--; break; } + + epos = line.find(terminator); + if (!terminator.empty() && epos!=string::npos) { + out.push_back(line); + break; + } + out.push_back(line); + linenum++; + } + return out; +} + + +/* print line with ZSTDLIB_API removed and C++ comments not bold */ +void print_line(stringstream &sout, string line) +{ + size_t spos; + + if (line.substr(0,12) == "ZSTDLIB_API ") line = line.substr(12); + spos = line.find("/*"); + if (spos!=string::npos) { + sout << line.substr(0, spos); + sout << "" << line.substr(spos) << "" << endl; + } else { + // fprintf(stderr, "lines=%s\n", line.c_str()); + sout << line << endl; + } +} + + +int main(int argc, char *argv[]) { + char exclam; + int linenum, chapter = 1; + vector input, lines, comments, chapters; + string line, version; + size_t spos, l; + stringstream sout; + ifstream istream; + ofstream ostream; + + if (argc < 4) { + cout << "usage: " << argv[0] << " [zstd_version] [input_file] [output_html]" << endl; + exit(0); + } + + version = "zstd " + string(argv[1]) + " Manual"; + + istream.open(argv[2], ifstream::in); + if (!istream.is_open()) { + cout << "Error opening file " << argv[2] << endl; + exit(0); + } + + ostream.open(argv[3], ifstream::out); + if (!ostream.is_open()) { + cout << "Error opening file " << argv[3] << endl; + exit(0); + } + + while (getline(istream, line)) { + input.push_back(line); + } + + for (linenum=0; (size_t)linenum < input.size(); linenum++) { + line = input[linenum]; + + /* typedefs are detected and included even if uncommented */ + if (line.substr(0,7) == "typedef" && line.find("{")!=string::npos) { + lines = get_lines(input, linenum, "}"); + sout << "
";
+            for (l=0; l

" << endl; + continue; + } + + /* comments of type /**< and /*!< are detected and only function declaration is highlighted (bold) */ + if ((line.find("/**<")!=string::npos || line.find("/*!<")!=string::npos) && line.find("*/")!=string::npos) { + sout << "
";
+            print_line(sout, line);
+            sout << "

" << endl; + continue; + } + + /* comments of type /*= and /**= mean: use a

header and show also all functions until first empty line */ + if ((line.substr(0,3) == "/*=" || line.substr(0,4) == "/**=") && line.find("*/")!=string::npos) { + trim_comments(line); + trim(line, "= "); + sout << "

" << line << "

";
+            lines = get_lines(input, ++linenum, "");
+            for (l=0; l

" << endl; + continue; + } + + spos = line.find("/*!"); + if (spos==string::npos) + spos = line.find("/**"); + if (spos==string::npos) + spos = line.find("/*-"); + + if (spos==string::npos) + continue; + + exclam = line[spos+2]; + comments = get_lines(input, linenum, "*/"); + if (!comments.empty()) comments[0] = line.substr(spos+3); + if (!comments.empty()) comments[comments.size()-1] = comments[comments.size()-1].substr(0, comments[comments.size()-1].find("*/")); + for (l=0; l"; + for (l=0; l

"; + for (l=0; l
" << endl << endl; + } else { /* comments of type /** and /*- mean: this is a comment; use a

header for the first line */ + if (comments.empty()) continue; + + trim(comments[0], " "); + sout << "

" << comments[0] << "

";
+            chapters.push_back(comments[0]);
+            chapter++;
+
+            for (l=1; l 1)
+                sout << "
" << endl << endl; + else + sout << "" << endl << endl; + } + } + + ostream << "\n\n\n" << version << "\n\n" << endl; + ostream << "

" << version << "

\n"; + + ostream << "
\n

Contents

\n
    \n"; + for (size_t i=0; i" << chapters[i].c_str() << "\n"; + ostream << "
\n
\n"; + + ostream << sout.str(); + ostream << "" << endl << "" << endl; + + return 0; +} \ No newline at end of file diff --git a/zstd_compression_format.md b/doc/zstd_compression_format.md similarity index 100% rename from zstd_compression_format.md rename to doc/zstd_compression_format.md diff --git a/doc/zstd_manual.html b/doc/zstd_manual.html new file mode 100644 index 000000000..aac5af9c2 --- /dev/null +++ b/doc/zstd_manual.html @@ -0,0 +1,528 @@ + + + +zstd 1.1.1 Manual + + +

zstd 1.1.1 Manual

+
+

Contents

+
    +
  1. Introduction
  2. +
  3. Version
  4. +
  5. Simple API
  6. +
  7. Explicit memory management
  8. +
  9. Simple dictionary API
  10. +
  11. Fast dictionary API
  12. +
  13. Streaming
  14. +
  15. Streaming compression - HowTo
  16. +
  17. Streaming decompression - HowTo
  18. +
  19. START OF ADVANCED AND EXPERIMENTAL FUNCTIONS
  20. +
  21. Advanced types
  22. +
  23. Advanced compression functions
  24. +
  25. Advanced decompression functions
  26. +
  27. Advanced streaming functions
  28. +
  29. Buffer-less and synchronous inner streaming functions
  30. +
  31. Buffer-less streaming compression (synchronous mode)
  32. +
  33. Buffer-less streaming decompression (synchronous mode)
  34. +
  35. Block functions
  36. +
+
+

Introduction

+  Zstd, short for Zstandard, is a fast lossless compression algorithm, targeting real-time compression scenarios
+  at zlib-level and better compression ratios. The zstd compression library provides in-memory compression and
+  decompression functions. The library supports compression levels from 1 up to ZSTD_maxCLevel() which is 22.
+  Levels from 20 to 22 should be used with caution as they require about 300-1300 MB for compression.
+  Compression can be done in:
+    - a single step (described as Simple API)
+    - a single step, reusing a context (described as Explicit memory management)
+    - repeated calls of the compression function (described as Streaming compression)
+  The compression ratio achievable on small data can be highly improved using compression with a dictionary in:
+    - a single step (described as Simple dictionary API)
+    - a single step, reusing a dictionary (described as Fast dictionary API)
+
+  Advanced and experimantal functions can be accessed using #define ZSTD_STATIC_LINKING_ONLY before including zstd.h.
+  These APIs shall never be used with a dynamic library. 
+  They are not "stable", their definition may change in the future. Only static linking is allowed.
+
+ +

Version


+
+
unsigned ZSTD_versionNumber (void);  /**< returns version number of ZSTD */
+

+

Simple API


+
+
size_t ZSTD_compress( void* dst, size_t dstCapacity,
+                            const void* src, size_t srcSize,
+                                  int compressionLevel);
+

Compresses `src` content as a single zstd compressed frame into already allocated `dst`. + Hint : compression runs faster if `dstCapacity` >= `ZSTD_compressBound(srcSize)`. + @return : compressed size written into `dst` (<= `dstCapacity), + or an error code if it fails (which can be tested using ZSTD_isError()) +


+ +
size_t ZSTD_decompress( void* dst, size_t dstCapacity,
+                              const void* src, size_t compressedSize);
+

`compressedSize` : must be the _exact_ size of a single compressed frame. + `dstCapacity` is an upper bound of originalSize. + If user cannot imply a maximum upper bound, it's better to use streaming mode to decompress data. + @return : the number of bytes decompressed into `dst` (<= `dstCapacity`), + or an errorCode if it fails (which can be tested using ZSTD_isError()) +


+ +
unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize);
+

'src' is the start of a zstd compressed frame. + @return : content size to be decompressed, as a 64-bits value _if known_, 0 otherwise. + note 1 : decompressed size is an optional field, that may not be present, especially in streaming mode. + When `return==0`, data to decompress could be any size. + In which case, it's necessary to use streaming mode to decompress data. + Optionally, application can still use ZSTD_decompress() while relying on implied limits. + (For example, data may be necessarily cut into blocks <= 16 KB). + note 2 : decompressed size is always present when compression is done with ZSTD_compress() + note 3 : decompressed size can be very large (64-bits value), + potentially larger than what local system can handle as a single memory segment. + In which case, it's necessary to use streaming mode to decompress data. + note 4 : If source is untrusted, decompressed size could be wrong or intentionally modified. + Always ensure result fits within application's authorized limits. + Each application can set its own limits. + note 5 : when `return==0`, if precise failure cause is needed, use ZSTD_getFrameParams() to know more. +


+ +

Helper functions

int         ZSTD_maxCLevel(void);               /*!< maximum compression level available */
+size_t      ZSTD_compressBound(size_t srcSize); /*!< maximum compressed size in worst case scenario */
+unsigned    ZSTD_isError(size_t code);          /*!< tells if a `size_t` function result is an error code */
+const char* ZSTD_getErrorName(size_t code);     /*!< provides readable string from an error code */
+

+

Explicit memory management


+
+

Compression context

typedef struct ZSTD_CCtx_s ZSTD_CCtx;
+ZSTD_CCtx* ZSTD_createCCtx(void);
+size_t     ZSTD_freeCCtx(ZSTD_CCtx* cctx);
+

+
size_t ZSTD_compressCCtx(ZSTD_CCtx* ctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize, int compressionLevel);
+

Same as ZSTD_compress(), requires an allocated ZSTD_CCtx (see ZSTD_createCCtx()) +


+ +

Decompression context

typedef struct ZSTD_DCtx_s ZSTD_DCtx;
+ZSTD_DCtx* ZSTD_createDCtx(void);
+size_t     ZSTD_freeDCtx(ZSTD_DCtx* dctx);
+

+
size_t ZSTD_decompressDCtx(ZSTD_DCtx* ctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+

Same as ZSTD_decompress(), requires an allocated ZSTD_DCtx (see ZSTD_createDCtx()) +


+ +

Simple dictionary API


+
+
size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx,
+                                           void* dst, size_t dstCapacity,
+                                     const void* src, size_t srcSize,
+                                     const void* dict,size_t dictSize,
+                                           int compressionLevel);
+

Compression using a predefined Dictionary (see dictBuilder/zdict.h). + Note : This function load the dictionary, resulting in significant startup delay. +


+ +
size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx,
+                                             void* dst, size_t dstCapacity,
+                                       const void* src, size_t srcSize,
+                                       const void* dict,size_t dictSize);
+

Decompression using a predefined Dictionary (see dictBuilder/zdict.h). + Dictionary must be identical to the one used during compression. + Note : This function load the dictionary, resulting in significant startup delay +


+ +

Fast dictionary API


+
+
ZSTD_CDict* ZSTD_createCDict(const void* dict, size_t dictSize, int compressionLevel);
+

Create a digested dictionary, ready to start compression operation without startup delay. + `dict` can be released after ZSTD_CDict creation +


+ +
size_t      ZSTD_freeCDict(ZSTD_CDict* CDict);
+

Function frees memory allocated with ZSTD_createCDict() +


+ +
size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx,
+                                            void* dst, size_t dstCapacity,
+                                      const void* src, size_t srcSize,
+                                      const ZSTD_CDict* cdict);
+

Compression using a digested Dictionary. + Faster startup than ZSTD_compress_usingDict(), recommended when same dictionary is used multiple times. + Note that compression level is decided during dictionary creation +


+ +
ZSTD_DDict* ZSTD_createDDict(const void* dict, size_t dictSize);
+

Create a digested dictionary, ready to start decompression operation without startup delay. + `dict` can be released after creation +


+ +
size_t      ZSTD_freeDDict(ZSTD_DDict* ddict);
+

Function frees memory allocated with ZSTD_createDDict() +


+ +
size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx,
+                                              void* dst, size_t dstCapacity,
+                                        const void* src, size_t srcSize,
+                                        const ZSTD_DDict* ddict);
+

Decompression using a digested Dictionary + Faster startup than ZSTD_decompress_usingDict(), recommended when same dictionary is used multiple times. +


+ +

Streaming


+
+
typedef struct ZSTD_inBuffer_s {
+  const void* src;    /**< start of input buffer */
+  size_t size;        /**< size of input buffer */
+  size_t pos;         /**< position where reading stopped. Will be updated. Necessarily 0 <= pos <= size */
+} ZSTD_inBuffer;
+

+
typedef struct ZSTD_outBuffer_s {
+  void*  dst;         /**< start of output buffer */
+  size_t size;        /**< size of output buffer */
+  size_t pos;         /**< position where writing stopped. Will be updated. Necessarily 0 <= pos <= size */
+} ZSTD_outBuffer;
+

+

Streaming compression - HowTo

+  A ZSTD_CStream object is required to track streaming operation.
+  Use ZSTD_createCStream() and ZSTD_freeCStream() to create/release resources.
+  ZSTD_CStream objects can be reused multiple times on consecutive compression operations.
+
+  Start by initializing ZSTD_CStream.
+  Use ZSTD_initCStream() to start a new compression operation.
+  Use ZSTD_initCStream_usingDict() for a compression which requires a dictionary.
+
+  Use ZSTD_compressStream() repetitively to consume input stream.
+  The function will automatically update both `pos` fields.
+  Note that it may not consume the entire input, in which case `pos < size`,
+  and it's up to the caller to present again remaining data.
+  @return : a size hint, preferred nb of bytes to use as input for next function call
+           (it's just a hint, to help latency a little, any other value will work fine)
+           (note : the size hint is guaranteed to be <= ZSTD_CStreamInSize() )
+            or an error code, which can be tested using ZSTD_isError().
+
+  At any moment, it's possible to flush whatever data remains within buffer, using ZSTD_flushStream().
+  `output->pos` will be updated.
+  Note some content might still be left within internal buffer if `output->size` is too small.
+  @return : nb of bytes still present within internal buffer (0 if it's empty)
+            or an error code, which can be tested using ZSTD_isError().
+
+  ZSTD_endStream() instructs to finish a frame.
+  It will perform a flush and write frame epilogue.
+  The epilogue is required for decoders to consider a frame completed.
+  Similar to ZSTD_flushStream(), it may not be able to flush the full content if `output->size` is too small.
+  In which case, call again ZSTD_endStream() to complete the flush.
+  @return : nb of bytes still present within internal buffer (0 if it's empty)
+            or an error code, which can be tested using ZSTD_isError().
+
+ 
+
+ +

Streaming compression functions

typedef struct ZSTD_CStream_s ZSTD_CStream;
+ZSTD_CStream* ZSTD_createCStream(void);
+size_t ZSTD_freeCStream(ZSTD_CStream* zcs);
+size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel);
+size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
+size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
+size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
+

+
size_t ZSTD_CStreamInSize(void);    /**< recommended size for input buffer */
+

+
size_t ZSTD_CStreamOutSize(void);   /**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block in all circumstances. */
+

+

Streaming decompression - HowTo

+  A ZSTD_DStream object is required to track streaming operations.
+  Use ZSTD_createDStream() and ZSTD_freeDStream() to create/release resources.
+  ZSTD_DStream objects can be re-used multiple times.
+
+  Use ZSTD_initDStream() to start a new decompression operation,
+   or ZSTD_initDStream_usingDict() if decompression requires a dictionary.
+   @return : recommended first input size
+
+  Use ZSTD_decompressStream() repetitively to consume your input.
+  The function will update both `pos` fields.
+  If `input.pos < input.size`, some input has not been consumed.
+  It's up to the caller to present again remaining data.
+  If `output.pos < output.size`, decoder has flushed everything it could.
+  @return : 0 when a frame is completely decoded and fully flushed,
+            an error code, which can be tested using ZSTD_isError(),
+            any other value > 0, which means there is still some work to do to complete the frame.
+            The return value is a suggested next input size (just an hint, to help latency).
+ 
+
+ +

Streaming decompression functions

typedef struct ZSTD_DStream_s ZSTD_DStream;
+ZSTD_DStream* ZSTD_createDStream(void);
+size_t ZSTD_freeDStream(ZSTD_DStream* zds);
+size_t ZSTD_initDStream(ZSTD_DStream* zds);
+size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
+

+
size_t ZSTD_DStreamInSize(void);    /*!< recommended size for input buffer */
+

+
size_t ZSTD_DStreamOutSize(void);   /*!< recommended size for output buffer. Guarantee to successfully flush at least one complete block in all circumstances. */
+

+

START OF ADVANCED AND EXPERIMENTAL FUNCTIONS

 The definitions in this section are considered experimental.
+ They should never be used with a dynamic library, as they may change in the future.
+ They are provided for advanced usages.
+ Use them only in association with static linking.
+ 
+
+ +

Advanced types


+
+
typedef enum { ZSTD_fast, ZSTD_dfast, ZSTD_greedy, ZSTD_lazy, ZSTD_lazy2, ZSTD_btlazy2, ZSTD_btopt } ZSTD_strategy;   /* from faster to stronger */
+

+
typedef struct {
+    unsigned windowLog;      /**< largest match distance : larger == more compression, more memory needed during decompression */
+    unsigned chainLog;       /**< fully searched segment : larger == more compression, slower, more memory (useless for fast) */
+    unsigned hashLog;        /**< dispatch table : larger == faster, more memory */
+    unsigned searchLog;      /**< nb of searches : larger == more compression, slower */
+    unsigned searchLength;   /**< match length searched : larger == faster decompression, sometimes less compression */
+    unsigned targetLength;   /**< acceptable match size for optimal parser (only) : larger == more compression, slower */
+    ZSTD_strategy strategy;
+} ZSTD_compressionParameters;
+

+
typedef struct {
+    unsigned contentSizeFlag; /**< 1: content size will be in frame header (if known). */
+    unsigned checksumFlag;    /**< 1: will generate a 22-bits checksum at end of frame, to be used for error detection by decompressor */
+    unsigned noDictIDFlag;    /**< 1: no dict ID will be saved into frame header (if dictionary compression) */
+} ZSTD_frameParameters;
+

+
typedef struct {
+    ZSTD_compressionParameters cParams;
+    ZSTD_frameParameters fParams;
+} ZSTD_parameters;
+

+

Custom memory allocation functions

typedef void* (*ZSTD_allocFunction) (void* opaque, size_t size);
+typedef void  (*ZSTD_freeFunction) (void* opaque, void* address);
+typedef struct { ZSTD_allocFunction customAlloc; ZSTD_freeFunction customFree; void* opaque; } ZSTD_customMem;
+

+

Advanced compression functions


+
+
size_t ZSTD_estimateCCtxSize(ZSTD_compressionParameters cParams);
+

Gives the amount of memory allocated for a ZSTD_CCtx given a set of compression parameters. + `frameContentSize` is an optional parameter, provide `0` if unknown +


+ +
ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem);
+

Create a ZSTD compression context using external alloc and free functions +


+ +
size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx);
+

Gives the amount of memory used by a given ZSTD_CCtx +


+ +
ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize,
+                                                  ZSTD_parameters params, ZSTD_customMem customMem);
+

Create a ZSTD_CDict using external alloc and free, and customized compression parameters +


+ +
size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict);
+

Gives the amount of memory used by a given ZSTD_sizeof_CDict +


+ +
ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long srcSize, size_t dictSize);
+

same as ZSTD_getCParams(), but @return a full `ZSTD_parameters` object instead of a `ZSTD_compressionParameters`. + All fields of `ZSTD_frameParameters` are set to default (0) +


+ +
ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long srcSize, size_t dictSize);
+

@return ZSTD_compressionParameters structure for a selected compression level and srcSize. + `srcSize` value is optional, select 0 if not known +


+ +
size_t ZSTD_checkCParams(ZSTD_compressionParameters params);
+

Ensure param values remain within authorized range +


+ +
ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize);
+

optimize params for a given `srcSize` and `dictSize`. + both values are optional, select `0` if unknown. +


+ +
size_t ZSTD_compress_advanced (ZSTD_CCtx* ctx,
+                                           void* dst, size_t dstCapacity,
+                                     const void* src, size_t srcSize,
+                                     const void* dict,size_t dictSize,
+                                           ZSTD_parameters params);
+

Same as ZSTD_compress_usingDict(), with fine-tune control of each compression parameter +


+ +

Advanced decompression functions


+
+
size_t ZSTD_estimateDCtxSize(void);
+

Gives the potential amount of memory allocated to create a ZSTD_DCtx +


+ +
ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem);
+

Create a ZSTD decompression context using external alloc and free functions +


+ +
size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx);
+

Gives the amount of memory used by a given ZSTD_DCtx +


+ +
size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
+

Gives the amount of memory used by a given ZSTD_DDict +


+ +

Advanced streaming functions


+
+

Advanced Streaming compression functions

ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem);
+size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel);
+size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize,
+                                             ZSTD_parameters params, unsigned long long pledgedSrcSize);  /**< pledgedSrcSize is optional and can be zero == unknown */
+size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize);  /**< re-use compression parameters from previous init; saves dictionary loading */
+size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs);
+

+

Advanced Streaming decompression functions

typedef enum { ZSTDdsp_maxWindowSize } ZSTD_DStreamParameter_e;
+ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem);
+size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize);
+size_t ZSTD_setDStreamParameter(ZSTD_DStream* zds, ZSTD_DStreamParameter_e paramType, unsigned paramValue);
+size_t ZSTD_resetDStream(ZSTD_DStream* zds);  /**< re-use decompression parameters from previous init; saves dictionary loading */
+size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds);
+

+

Buffer-less and synchronous inner streaming functions

+  This is an advanced API, giving full control over buffer management, for users which need direct control over memory.
+  But it's also a complex one, with many restrictions (documented below).
+  Prefer using normal streaming API for an easier experience 
+ 
+
+ +

Buffer-less streaming compression (synchronous mode)

+  A ZSTD_CCtx object is required to track streaming operations.
+  Use ZSTD_createCCtx() / ZSTD_freeCCtx() to manage resource.
+  ZSTD_CCtx object can be re-used multiple times within successive compression operations.
+
+  Start by initializing a context.
+  Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary compression,
+  or ZSTD_compressBegin_advanced(), for finer parameter control.
+  It's also possible to duplicate a reference context which has already been initialized, using ZSTD_copyCCtx()
+
+  Then, consume your input using ZSTD_compressContinue().
+  There are some important considerations to keep in mind when using this advanced function :
+  - ZSTD_compressContinue() has no internal buffer. It uses externally provided buffer only.
+  - Interface is synchronous : input is consumed entirely and produce 1+ (or more) compressed blocks.
+  - Caller must ensure there is enough space in `dst` to store compressed data under worst case scenario.
+    Worst case evaluation is provided by ZSTD_compressBound().
+    ZSTD_compressContinue() doesn't guarantee recover after a failed compression.
+  - ZSTD_compressContinue() presumes prior input ***is still accessible and unmodified*** (up to maximum distance size, see WindowLog).
+    It remembers all previous contiguous blocks, plus one separated memory segment (which can itself consists of multiple contiguous blocks)
+  - ZSTD_compressContinue() detects that prior input has been overwritten when `src` buffer overlaps.
+    In which case, it will "discard" the relevant memory section from its history.
+
+  Finish a frame with ZSTD_compressEnd(), which will write the last block(s) and optional checksum.
+  It's possible to use a NULL,0 src content, in which case, it will write a final empty block to end the frame,
+  Without last block mark, frames will be considered unfinished (broken) by decoders.
+
+  You can then reuse `ZSTD_CCtx` (ZSTD_compressBegin()) to compress some new frame.
+
+ +

Buffer-less streaming compression functions

size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLevel);
+size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel);
+size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize);
+size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize);
+size_t ZSTD_compressContinue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+

+

Buffer-less streaming decompression (synchronous mode)

+  A ZSTD_DCtx object is required to track streaming operations.
+  Use ZSTD_createDCtx() / ZSTD_freeDCtx() to manage it.
+  A ZSTD_DCtx object can be re-used multiple times.
+
+  First typical operation is to retrieve frame parameters, using ZSTD_getFrameParams().
+  It fills a ZSTD_frameParams structure which provide important information to correctly decode the frame,
+  such as the minimum rolling buffer size to allocate to decompress data (`windowSize`),
+  and the dictionary ID used.
+  (Note : content size is optional, it may not be present. 0 means : content size unknown).
+  Note that these values could be wrong, either because of data malformation, or because an attacker is spoofing deliberate false information.
+  As a consequence, check that values remain within valid application range, especially `windowSize`, before allocation.
+  Each application can set its own limit, depending on local restrictions. For extended interoperability, it is recommended to support at least 8 MB.
+  Frame parameters are extracted from the beginning of the compressed frame.
+  Data fragment must be large enough to ensure successful decoding, typically `ZSTD_frameHeaderSize_max` bytes.
+  @result : 0 : successful decoding, the `ZSTD_frameParams` structure is correctly filled.
+           >0 : `srcSize` is too small, please provide at least @result bytes on next attempt.
+           errorCode, which can be tested using ZSTD_isError().
+
+  Start decompression, with ZSTD_decompressBegin() or ZSTD_decompressBegin_usingDict().
+  Alternatively, you can copy a prepared context, using ZSTD_copyDCtx().
+
+  Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue() alternatively.
+  ZSTD_nextSrcSizeToDecompress() tells how many bytes to provide as 'srcSize' to ZSTD_decompressContinue().
+  ZSTD_decompressContinue() requires this _exact_ amount of bytes, or it will fail.
+
+  @result of ZSTD_decompressContinue() is the number of bytes regenerated within 'dst' (necessarily <= dstCapacity).
+  It can be zero, which is not an error; it just means ZSTD_decompressContinue() has decoded some metadata item.
+  It can also be an error code, which can be tested with ZSTD_isError().
+
+  ZSTD_decompressContinue() needs previous data blocks during decompression, up to `windowSize`.
+  They should preferably be located contiguously, prior to current block.
+  Alternatively, a round buffer of sufficient size is also possible. Sufficient size is determined by frame parameters.
+  ZSTD_decompressContinue() is very sensitive to contiguity,
+  if 2 blocks don't follow each other, make sure that either the compressor breaks contiguity at the same place,
+  or that previous contiguous segment is large enough to properly handle maximum back-reference.
+
+  A frame is fully decoded when ZSTD_nextSrcSizeToDecompress() returns zero.
+  Context can then be reset to start a new decompression.
+
+  Note : it's possible to know if next input to present is a header or a block, using ZSTD_nextInputType().
+  This information is not required to properly decode a frame.
+
+  == Special case : skippable frames ==
+
+  Skippable frames allow integration of user-defined data into a flow of concatenated frames.
+  Skippable frames will be ignored (skipped) by a decompressor. The format of skippable frames is as follows :
+  a) Skippable frame ID - 4 Bytes, Little endian format, any value from 0x184D2A50 to 0x184D2A5F
+  b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits
+  c) Frame Content - any content (User Data) of length equal to Frame Size
+  For skippable frames ZSTD_decompressContinue() always returns 0.
+  For skippable frames ZSTD_getFrameParams() returns fparamsPtr->windowLog==0 what means that a frame is skippable.
+  It also returns Frame Size as fparamsPtr->frameContentSize.
+
+ +
typedef struct {
+    unsigned long long frameContentSize;
+    unsigned windowSize;
+    unsigned dictID;
+    unsigned checksumFlag;
+} ZSTD_frameParams;
+

+

Buffer-less streaming decompression functions

size_t ZSTD_getFrameParams(ZSTD_frameParams* fparamsPtr, const void* src, size_t srcSize);   /**< doesn't consume input, see details below */
+size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx);
+size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize);
+void   ZSTD_copyDCtx(ZSTD_DCtx* dctx, const ZSTD_DCtx* preparedDCtx);
+size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx* dctx);
+size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+typedef enum { ZSTDnit_frameHeader, ZSTDnit_blockHeader, ZSTDnit_block, ZSTDnit_lastBlock, ZSTDnit_checksum, ZSTDnit_skippableFrame } ZSTD_nextInputType_e;
+ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx);
+

+

Block functions

+    Block functions produce and decode raw zstd blocks, without frame metadata.
+    Frame metadata cost is typically ~18 bytes, which can be non-negligible for very small blocks (< 100 bytes).
+    User will have to take in charge required information to regenerate data, such as compressed and content sizes.
+
+    A few rules to respect :
+    - Compressing and decompressing require a context structure
+      + Use ZSTD_createCCtx() and ZSTD_createDCtx()
+    - It is necessary to init context before starting
+      + compression : ZSTD_compressBegin()
+      + decompression : ZSTD_decompressBegin()
+      + variants _usingDict() are also allowed
+      + copyCCtx() and copyDCtx() work too
+    - Block size is limited, it must be <= ZSTD_getBlockSizeMax()
+      + If you need to compress more, cut data into multiple blocks
+      + Consider using the regular ZSTD_compress() instead, as frame metadata costs become negligible when source size is large.
+    - When a block is considered not compressible enough, ZSTD_compressBlock() result will be zero.
+      In which case, nothing is produced into `dst`.
+      + User must test for such outcome and deal directly with uncompressed data
+      + ZSTD_decompressBlock() doesn't accept uncompressed data as input !!!
+      + In case of multiple successive blocks, decoder must be informed of uncompressed block existence to follow proper history.
+        Use ZSTD_insertBlock() in such a case.
+
+ +

Raw zstd block functions

size_t ZSTD_getBlockSizeMax(ZSTD_CCtx* cctx);
+size_t ZSTD_compressBlock  (ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+size_t ZSTD_decompressBlock(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+size_t ZSTD_insertBlock(ZSTD_DCtx* dctx, const void* blockStart, size_t blockSize);  /**< insert block into `dctx` history. Useful for uncompressed blocks */
+

+ + diff --git a/lib/compress/huf_compress.c b/lib/compress/huf_compress.c index 41de7449a..78784aa36 100644 --- a/lib/compress/huf_compress.c +++ b/lib/compress/huf_compress.c @@ -155,13 +155,14 @@ size_t HUF_readCTable (HUF_CElt* CTable, U32 maxSymbolValue, const void* src, si } } /* fill val */ - { U16 nbPerRank[HUF_TABLELOG_MAX+2] = {0}; + { U16 nbPerRank[HUF_TABLELOG_MAX+2] = {0}; /* support w=0=>n=tableLog+1 */ U16 valPerRank[HUF_TABLELOG_MAX+2] = {0}; { U32 n; for (n=0; n0; n--) { - valPerRank[n] = min; /* get starting value within each rank */ + U32 n; for (n=tableLog; n>0; n--) { /* start at n=tablelog <-> w=1 */ + valPerRank[n] = min; /* get starting value within each rank */ min += nbPerRank[n]; min >>= 1; } } diff --git a/lib/compress/zstd_compress.c b/lib/compress/zstd_compress.c index fb12898e8..1d4450aa5 100644 --- a/lib/compress/zstd_compress.c +++ b/lib/compress/zstd_compress.c @@ -377,7 +377,7 @@ static void ZSTD_reduceIndex (ZSTD_CCtx* zc, const U32 reducerValue) * Block entropic compression *********************************************************/ -/* See zstd_compression_format.md for detailed format description */ +/* See doc/zstd_compression_format.md for detailed format description */ size_t ZSTD_noCompressBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize) { diff --git a/lib/compress/zstd_opt.h b/lib/compress/zstd_opt.h index cea67056a..5e4cb7c27 100644 --- a/lib/compress/zstd_opt.h +++ b/lib/compress/zstd_opt.h @@ -1,5 +1,5 @@ /** - * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. + * Copyright (c) 2016-present, Przemyslaw Skibinski, Yann Collet, Facebook, Inc. * All rights reserved. * * This source code is licensed under the BSD-style license found in the @@ -16,6 +16,7 @@ #define ZSTD_FREQ_DIV 5 +#define ZSTD_MAX_PRICE (1<<30) /*-************************************* * Price functions for optimal parser @@ -171,7 +172,7 @@ MEM_STATIC void ZSTD_updatePrice(seqStore_t* seqStorePtr, U32 litLength, const B #define SET_PRICE(pos, mlen_, offset_, litlen_, price_) \ { \ - while (last_pos < pos) { opt[last_pos+1].price = 1<<30; last_pos++; } \ + while (last_pos < pos) { opt[last_pos+1].price = ZSTD_MAX_PRICE; last_pos++; } \ opt[pos].mlen = mlen_; \ opt[pos].off = offset_; \ opt[pos].litlen = litlen_; \ @@ -401,7 +402,6 @@ void ZSTD_compressBlock_opt_generic(ZSTD_CCtx* ctx, ZSTD_rescaleFreqs(seqStorePtr); ip += (ip==prefixStart); { U32 i; for (i=0; irep[i]; } - //inr = ip; /* Match Loop */ while (ip < ilimit) { @@ -496,7 +496,7 @@ void ZSTD_compressBlock_opt_generic(ZSTD_CCtx* ctx, opt[cur].rep[0] = ((opt[cur].off==ZSTD_REP_MOVE_OPT) && (mlen != 1)) ? (opt[cur-mlen].rep[0] - 1) : (opt[cur-mlen].rep[opt[cur].off]); } - best_mlen = minMatch; + best_mlen = minMatch; { U32 i, last_i = ZSTD_REP_CHECK + (mlen != 1); for (i=(opt[cur].mlen != 1); i best_mlen) best_mlen = mlen; - if (opt[cur].mlen == 1) { - litlen = opt[cur].litlen; - if (cur > litlen) { - price = opt[cur - litlen].price + ZSTD_getPrice(seqStorePtr, litlen, inr-litlen, best_off, mlen - MINMATCH); - } else - price = ZSTD_getPrice(seqStorePtr, litlen, anchor, best_off, mlen - MINMATCH); - } else { - litlen = 0; - price = opt[cur].price + ZSTD_getPrice(seqStorePtr, 0, NULL, best_off, mlen - MINMATCH); - } + do { + if (opt[cur].mlen == 1) { + litlen = opt[cur].litlen; + if (cur > litlen) { + price = opt[cur - litlen].price + ZSTD_getPrice(seqStorePtr, litlen, inr-litlen, best_off, mlen - MINMATCH); + } else + price = ZSTD_getPrice(seqStorePtr, litlen, anchor, best_off, mlen - MINMATCH); + } else { + litlen = 0; + price = opt[cur].price + ZSTD_getPrice(seqStorePtr, 0, NULL, best_off, mlen - MINMATCH); + } - if (mlen > best_mlen) best_mlen = mlen; - - do { if (cur + mlen > last_pos || price <= opt[cur + mlen].price) SET_PRICE(cur + mlen, mlen, i, litlen, price); mlen--; @@ -657,7 +656,6 @@ void ZSTD_compressBlock_opt_extDict_generic(ZSTD_CCtx* ctx, ctx->nextToUpdate3 = ctx->nextToUpdate; ZSTD_rescaleFreqs(seqStorePtr); ip += (ip==prefixStart); - //inr = ip; /* Match Loop */ while (ip < ilimit) { @@ -666,7 +664,6 @@ void ZSTD_compressBlock_opt_extDict_generic(ZSTD_CCtx* ctx, U32 current = (U32)(ip-base); memset(opt, 0, sizeof(ZSTD_optimal_t)); last_pos = 0; - //inr = ip; opt[0].litlen = (U32)(ip - anchor); /* check repCode */ @@ -765,8 +762,7 @@ void ZSTD_compressBlock_opt_extDict_generic(ZSTD_CCtx* ctx, opt[cur].rep[0] = ((opt[cur].off==ZSTD_REP_MOVE_OPT) && (mlen != 1)) ? (opt[cur-mlen].rep[0] - 1) : (opt[cur-mlen].rep[opt[cur].off]); } - best_mlen = 0; - + best_mlen = minMatch; { U32 i, last_i = ZSTD_REP_CHECK + (mlen != 1); for (i = (mlen != 1); i litlen) { - price = opt[cur - litlen].price + ZSTD_getPrice(seqStorePtr, litlen, inr-litlen, best_off, mlen - MINMATCH); - } else - price = ZSTD_getPrice(seqStorePtr, litlen, anchor, best_off, mlen - MINMATCH); - } else { - litlen = 0; - price = opt[cur].price + ZSTD_getPrice(seqStorePtr, 0, NULL, best_off, mlen - MINMATCH); - } - - best_mlen = mlen; + if (mlen > best_mlen) best_mlen = mlen; do { + if (opt[cur].mlen == 1) { + litlen = opt[cur].litlen; + if (cur > litlen) { + price = opt[cur - litlen].price + ZSTD_getPrice(seqStorePtr, litlen, inr-litlen, best_off, mlen - MINMATCH); + } else + price = ZSTD_getPrice(seqStorePtr, litlen, anchor, best_off, mlen - MINMATCH); + } else { + litlen = 0; + price = opt[cur].price + ZSTD_getPrice(seqStorePtr, 0, NULL, best_off, mlen - MINMATCH); + } + if (cur + mlen > last_pos || price <= opt[cur + mlen].price) SET_PRICE(cur + mlen, mlen, i, litlen, price); mlen--; @@ -815,8 +811,6 @@ void ZSTD_compressBlock_opt_extDict_generic(ZSTD_CCtx* ctx, goto _storeSequence; } - best_mlen = (best_mlen > minMatch) ? best_mlen : minMatch; - /* set prices using matches at position = cur */ for (u = 0; u < match_num; u++) { mlen = (u>0) ? matches[u-1].len+1 : best_mlen; diff --git a/lib/decompress/zstd_decompress.c b/lib/decompress/zstd_decompress.c index de5f46eef..2a1232eee 100644 --- a/lib/decompress/zstd_decompress.c +++ b/lib/decompress/zstd_decompress.c @@ -191,7 +191,7 @@ static void ZSTD_refDCtx(ZSTD_DCtx* dstDCtx, const ZSTD_DCtx* srcDCtx) * Decompression section ***************************************************************/ -/* See compression format details in : zstd_compression_format.md */ +/* See compression format details in : doc/zstd_compression_format.md */ /** ZSTD_frameHeaderSize() : * srcSize must be >= ZSTD_frameHeaderSize_prefix. @@ -301,14 +301,16 @@ unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize) /** ZSTD_decodeFrameHeader() : -* `srcSize` must be the size provided by ZSTD_frameHeaderSize(). +* `headerSize` must be the size provided by ZSTD_frameHeaderSize(). * @return : 0 if success, or an error code, which can be tested using ZSTD_isError() */ -static size_t ZSTD_decodeFrameHeader(ZSTD_DCtx* dctx, const void* src, size_t srcSize) +static size_t ZSTD_decodeFrameHeader(ZSTD_DCtx* dctx, const void* src, size_t headerSize) { - size_t const result = ZSTD_getFrameParams(&(dctx->fParams), src, srcSize); + size_t const result = ZSTD_getFrameParams(&(dctx->fParams), src, headerSize); + if (ZSTD_isError(result)) return result; /* invalid header */ + if (result>0) return ERROR(srcSize_wrong); /* headerSize too small */ if (dctx->fParams.dictID && (dctx->dictID != dctx->fParams.dictID)) return ERROR(dictionary_wrong); if (dctx->fParams.checksumFlag) XXH64_reset(&dctx->xxhState, 0); - return result; + return 0; } @@ -810,7 +812,8 @@ static seq_t ZSTD_decodeSequence(seqState_t* seqState) if (ofCode <= 1) { offset += (llCode==0); if (offset) { - size_t const temp = (offset==3) ? seqState->prevOffset[0] - 1 : seqState->prevOffset[offset]; + size_t temp = (offset==3) ? seqState->prevOffset[0] - 1 : seqState->prevOffset[offset]; + temp += !temp; /* 0 is not valid; input is corrupted; force offset to 1 */ if (offset != 1) seqState->prevOffset[2] = seqState->prevOffset[1]; seqState->prevOffset[1] = seqState->prevOffset[0]; seqState->prevOffset[0] = offset = temp; @@ -882,7 +885,7 @@ size_t ZSTD_execSequence(BYTE* op, sequence.matchLength -= length1; match = base; if (op > oend_w) { - memmove(op, match, sequence.matchLength); + while (op < oMatchEnd) *op++ = *match++; return sequenceLength; } } } diff --git a/lib/dictBuilder/zdict.c b/lib/dictBuilder/zdict.c index a88e70520..b3f20b12b 100644 --- a/lib/dictBuilder/zdict.c +++ b/lib/dictBuilder/zdict.c @@ -371,21 +371,22 @@ static dictItem ZDICT_analyzePos( static U32 ZDICT_checkMerge(dictItem* table, dictItem elt, U32 eltNbToSkip) { const U32 tableSize = table->pos; - const U32 max = elt.pos + (elt.length-1); + const U32 eltEnd = elt.pos + elt.length; /* tail overlap */ U32 u; for (u=1; u elt.pos) && (table[u].pos < max)) { /* overlap */ + if ((table[u].pos > elt.pos) && (table[u].pos <= eltEnd)) { /* overlap, existing > new */ /* append */ U32 addedLength = table[u].pos - elt.pos; table[u].length += addedLength; table[u].pos = elt.pos; table[u].savings += elt.savings * addedLength / elt.length; /* rough approx */ - table[u].savings += elt.length / 8; /* rough approx */ + table[u].savings += elt.length / 8; /* rough approx bonus */ elt = table[u]; + /* sort : improve rank */ while ((u>1) && (table[u-1].savings < elt.savings)) - table[u] = table[u-1], u--; + table[u] = table[u-1], u--; table[u] = elt; return u; } } @@ -393,14 +394,15 @@ static U32 ZDICT_checkMerge(dictItem* table, dictItem elt, U32 eltNbToSkip) /* front overlap */ for (u=1; u elt.pos) && (table[u].pos < elt.pos)) { /* overlap */ + if ((table[u].pos + table[u].length >= elt.pos) && (table[u].pos < elt.pos)) { /* overlap, existing < new */ /* append */ - int addedLength = (elt.pos + elt.length) - (table[u].pos + table[u].length); - table[u].savings += elt.length / 8; /* rough approx */ - if (addedLength > 0) { /* otherwise, already included */ + int addedLength = (int)eltEnd - (table[u].pos + table[u].length); + table[u].savings += elt.length / 8; /* rough approx bonus */ + if (addedLength > 0) { /* otherwise, elt fully included into existing */ table[u].length += addedLength; table[u].savings += elt.savings * addedLength / elt.length; /* rough approx */ } + /* sort : improve rank */ elt = table[u]; while ((u>1) && (table[u-1].savings < elt.savings)) table[u] = table[u-1], u--; diff --git a/lib/legacy/zstd_v04.c b/lib/legacy/zstd_v04.c index 60479cb79..0a740baca 100644 --- a/lib/legacy/zstd_v04.c +++ b/lib/legacy/zstd_v04.c @@ -3111,7 +3111,7 @@ static size_t ZSTD_execSequence(BYTE* op, sequence.matchLength -= length1; match = base; if (op > oend_8) { - memmove(op, match, sequence.matchLength); + while (op < oMatchEnd) *op++ = *match++; return sequenceLength; } } diff --git a/lib/legacy/zstd_v05.c b/lib/legacy/zstd_v05.c index 2fde052c2..201bf3c6b 100644 --- a/lib/legacy/zstd_v05.c +++ b/lib/legacy/zstd_v05.c @@ -2035,13 +2035,14 @@ size_t HUFv05_decompress1X2_usingDTable( { BYTE* op = (BYTE*)dst; BYTE* const oend = op + dstSize; - size_t errorCode; const U32 dtLog = DTable[0]; const void* dtPtr = DTable; const HUFv05_DEltX2* const dt = ((const HUFv05_DEltX2*)dtPtr)+1; BITv05_DStream_t bitD; - errorCode = BITv05_initDStream(&bitD, cSrc, cSrcSize); - if (HUFv05_isError(errorCode)) return errorCode; + + if (dstSize <= cSrcSize) return ERROR(dstSize_tooSmall); + { size_t const errorCode = BITv05_initDStream(&bitD, cSrc, cSrcSize); + if (HUFv05_isError(errorCode)) return errorCode; } HUFv05_decodeStreamX2(op, &bitD, oend, dt, dtLog); @@ -3070,7 +3071,7 @@ size_t ZSTDv05_decodeLiteralsBlock(ZSTDv05_DCtx* dctx, size_t ZSTDv05_decodeSeqHeaders(int* nbSeq, const BYTE** dumpsPtr, size_t* dumpsLengthPtr, FSEv05_DTable* DTableLL, FSEv05_DTable* DTableML, FSEv05_DTable* DTableOffb, - const void* src, size_t srcSize) + const void* src, size_t srcSize, U32 flagStaticTable) { const BYTE* const istart = (const BYTE* const)src; const BYTE* ip = istart; @@ -3130,6 +3131,7 @@ size_t ZSTDv05_decodeSeqHeaders(int* nbSeq, const BYTE** dumpsPtr, size_t* dumps FSEv05_buildDTable_raw(DTableLL, LLbits); break; case FSEv05_ENCODING_STATIC: + if (!flagStaticTable) return ERROR(corruption_detected); break; case FSEv05_ENCODING_DYNAMIC : default : /* impossible */ @@ -3153,6 +3155,7 @@ size_t ZSTDv05_decodeSeqHeaders(int* nbSeq, const BYTE** dumpsPtr, size_t* dumps FSEv05_buildDTable_raw(DTableOffb, Offbits); break; case FSEv05_ENCODING_STATIC: + if (!flagStaticTable) return ERROR(corruption_detected); break; case FSEv05_ENCODING_DYNAMIC : default : /* impossible */ @@ -3176,6 +3179,7 @@ size_t ZSTDv05_decodeSeqHeaders(int* nbSeq, const BYTE** dumpsPtr, size_t* dumps FSEv05_buildDTable_raw(DTableML, MLbits); break; case FSEv05_ENCODING_STATIC: + if (!flagStaticTable) return ERROR(corruption_detected); break; case FSEv05_ENCODING_DYNAMIC : default : /* impossible */ @@ -3325,7 +3329,7 @@ static size_t ZSTDv05_execSequence(BYTE* op, sequence.matchLength -= length1; match = base; if (op > oend_8) { - memmove(op, match, sequence.matchLength); + while (op < oMatchEnd) *op++ = *match++; return sequenceLength; } } } @@ -3388,7 +3392,7 @@ static size_t ZSTDv05_decompressSequences( /* Build Decoding Tables */ errorCode = ZSTDv05_decodeSeqHeaders(&nbSeq, &dumps, &dumpsLength, DTableLL, DTableML, DTableOffb, - ip, seqSize); + ip, seqSize, dctx->flagStaticTables); if (ZSTDv05_isError(errorCode)) return errorCode; ip += errorCode; diff --git a/lib/legacy/zstd_v06.c b/lib/legacy/zstd_v06.c index 3d6512846..b6fde3aa6 100644 --- a/lib/legacy/zstd_v06.c +++ b/lib/legacy/zstd_v06.c @@ -3474,7 +3474,7 @@ size_t ZSTDv06_execSequence(BYTE* op, sequence.matchLength -= length1; match = base; if (op > oend_8) { - memmove(op, match, sequence.matchLength); + while (op < oMatchEnd) *op++ = *match++; return sequenceLength; } } } diff --git a/lib/legacy/zstd_v07.c b/lib/legacy/zstd_v07.c index ace64ede4..c7693f240 100644 --- a/lib/legacy/zstd_v07.c +++ b/lib/legacy/zstd_v07.c @@ -3697,7 +3697,7 @@ size_t ZSTDv07_execSequence(BYTE* op, sequence.matchLength -= length1; match = base; if (op > oend_w) { - memmove(op, match, sequence.matchLength); + while (op < oMatchEnd) *op++ = *match++; return sequenceLength; } } } diff --git a/lib/zstd.h b/lib/zstd.h index c2f5f5d4c..1b6665c2b 100644 --- a/lib/zstd.h +++ b/lib/zstd.h @@ -1,4 +1,4 @@ -/** +/* * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. * All rights reserved. * @@ -14,12 +14,12 @@ extern "C" { #endif -/*====== Dependency ======*/ +/* ====== Dependency ======*/ #include /* size_t */ -/*====== Export for Windows ======*/ -/*! +/* ====== Export for Windows ======*/ +/* * ZSTD_DLL_EXPORT : * Enable exporting of functions when building a Windows DLL */ @@ -30,7 +30,29 @@ extern "C" { #endif -/*======= Version =======*/ +/******************************************************************************************************* + Introduction + + Zstd, short for Zstandard, is a fast lossless compression algorithm, targeting real-time compression scenarios + at zlib-level and better compression ratios. The zstd compression library provides in-memory compression and + decompression functions. The library supports compression levels from 1 up to ZSTD_maxCLevel() which is 22. + Levels from 20 to 22 should be used with caution as they require about 300-1300 MB for compression. + Compression can be done in: + - a single step (described as Simple API) + - a single step, reusing a context (described as Explicit memory management) + - repeated calls of the compression function (described as Streaming compression) + The compression ratio achievable on small data can be highly improved using compression with a dictionary in: + - a single step (described as Simple dictionary API) + - a single step, reusing a dictionary (described as Fast dictionary API) + + Advanced and experimantal functions can be accessed using #define ZSTD_STATIC_LINKING_ONLY before including zstd.h. + These APIs shall never be used with a dynamic library. + They are not "stable", their definition may change in the future. Only static linking is allowed. +*********************************************************************************************************/ + +/*------ Version ------*/ +ZSTDLIB_API unsigned ZSTD_versionNumber (void); /**< returns version number of ZSTD */ + #define ZSTD_VERSION_MAJOR 1 #define ZSTD_VERSION_MINOR 1 #define ZSTD_VERSION_RELEASE 1 @@ -41,10 +63,9 @@ extern "C" { #define ZSTD_VERSION_STRING ZSTD_EXPAND_AND_QUOTE(ZSTD_LIB_VERSION) #define ZSTD_VERSION_NUMBER (ZSTD_VERSION_MAJOR *100*100 + ZSTD_VERSION_MINOR *100 + ZSTD_VERSION_RELEASE) -ZSTDLIB_API unsigned ZSTD_versionNumber (void); -/* ************************************* +/*************************************** * Simple API ***************************************/ /*! ZSTD_compress() : @@ -91,29 +112,29 @@ ZSTDLIB_API unsigned ZSTD_isError(size_t code); /*!< tells if a `siz ZSTDLIB_API const char* ZSTD_getErrorName(size_t code); /*!< provides readable string from an error code */ -/*-************************************* +/*************************************** * Explicit memory management ***************************************/ -/** Compression context */ +/*= Compression context */ typedef struct ZSTD_CCtx_s ZSTD_CCtx; ZSTDLIB_API ZSTD_CCtx* ZSTD_createCCtx(void); ZSTDLIB_API size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx); -/** ZSTD_compressCCtx() : +/*! ZSTD_compressCCtx() : Same as ZSTD_compress(), requires an allocated ZSTD_CCtx (see ZSTD_createCCtx()) */ ZSTDLIB_API size_t ZSTD_compressCCtx(ZSTD_CCtx* ctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize, int compressionLevel); -/** Decompression context */ +/*= Decompression context */ typedef struct ZSTD_DCtx_s ZSTD_DCtx; ZSTDLIB_API ZSTD_DCtx* ZSTD_createDCtx(void); ZSTDLIB_API size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx); -/** ZSTD_decompressDCtx() : +/*! ZSTD_decompressDCtx() : * Same as ZSTD_decompress(), requires an allocated ZSTD_DCtx (see ZSTD_createDCtx()) */ ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* ctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); -/*-************************ +/************************** * Simple dictionary API ***************************/ /*! ZSTD_compress_usingDict() : @@ -135,14 +156,18 @@ ZSTDLIB_API size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx, const void* dict,size_t dictSize); -/*-************************** -* Fast Dictionary API +/**************************** +* Fast dictionary API ****************************/ +typedef struct ZSTD_CDict_s ZSTD_CDict; + /*! ZSTD_createCDict() : * Create a digested dictionary, ready to start compression operation without startup delay. * `dict` can be released after ZSTD_CDict creation */ -typedef struct ZSTD_CDict_s ZSTD_CDict; ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dict, size_t dictSize, int compressionLevel); + +/*! ZSTD_freeCDict() : +* Function frees memory allocated with ZSTD_createCDict() */ ZSTDLIB_API size_t ZSTD_freeCDict(ZSTD_CDict* CDict); /*! ZSTD_compress_usingCDict() : @@ -154,11 +179,16 @@ ZSTDLIB_API size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx, const void* src, size_t srcSize, const ZSTD_CDict* cdict); + +typedef struct ZSTD_DDict_s ZSTD_DDict; + /*! ZSTD_createDDict() : * Create a digested dictionary, ready to start decompression operation without startup delay. * `dict` can be released after creation */ -typedef struct ZSTD_DDict_s ZSTD_DDict; ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict(const void* dict, size_t dictSize); + +/*! ZSTD_freeDDict() : +* Function frees memory allocated with ZSTD_createDDict() */ ZSTDLIB_API size_t ZSTD_freeDDict(ZSTD_DDict* ddict); /*! ZSTD_decompress_usingDDict() : @@ -170,7 +200,7 @@ ZSTDLIB_API size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict); -/*-************************** +/**************************** * Streaming ****************************/ @@ -187,10 +217,9 @@ typedef struct ZSTD_outBuffer_s { } ZSTD_outBuffer; -/*====== streaming compression ======*/ /*-*********************************************************************** -* Streaming compression - howto +* Streaming compression - HowTo * * A ZSTD_CStream object is required to track streaming operation. * Use ZSTD_createCStream() and ZSTD_freeCStream() to create/release resources. @@ -225,23 +254,22 @@ typedef struct ZSTD_outBuffer_s { * * *******************************************************************/ +/*===== Streaming compression functions ======*/ typedef struct ZSTD_CStream_s ZSTD_CStream; ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream(void); ZSTDLIB_API size_t ZSTD_freeCStream(ZSTD_CStream* zcs); - -ZSTDLIB_API size_t ZSTD_CStreamInSize(void); /**< recommended size for input buffer */ -ZSTDLIB_API size_t ZSTD_CStreamOutSize(void); /**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block in all circumstances. */ - ZSTDLIB_API size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel); ZSTDLIB_API size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input); ZSTDLIB_API size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); +ZSTDLIB_API size_t ZSTD_CStreamInSize(void); /**< recommended size for input buffer */ +ZSTDLIB_API size_t ZSTD_CStreamOutSize(void); /**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block in all circumstances. */ + -/*====== decompression ======*/ /*-*************************************************************************** -* Streaming decompression howto +* Streaming decompression - HowTo * * A ZSTD_DStream object is required to track streaming operations. * Use ZSTD_createDStream() and ZSTD_freeDStream() to create/release resources. @@ -262,28 +290,29 @@ ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); * The return value is a suggested next input size (just an hint, to help latency). * *******************************************************************************/ +/*===== Streaming decompression functions =====*/ typedef struct ZSTD_DStream_s ZSTD_DStream; ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream(void); ZSTDLIB_API size_t ZSTD_freeDStream(ZSTD_DStream* zds); +ZSTDLIB_API size_t ZSTD_initDStream(ZSTD_DStream* zds); +ZSTDLIB_API size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input); ZSTDLIB_API size_t ZSTD_DStreamInSize(void); /*!< recommended size for input buffer */ ZSTDLIB_API size_t ZSTD_DStreamOutSize(void); /*!< recommended size for output buffer. Guarantee to successfully flush at least one complete block in all circumstances. */ -ZSTDLIB_API size_t ZSTD_initDStream(ZSTD_DStream* zds); -ZSTDLIB_API size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input); - #ifdef ZSTD_STATIC_LINKING_ONLY -/* ==================================================================================== +/**************************************************************************************** + * START OF ADVANCED AND EXPERIMENTAL FUNCTIONS * The definitions in this section are considered experimental. * They should never be used with a dynamic library, as they may change in the future. * They are provided for advanced usages. * Use them only in association with static linking. - * ==================================================================================== */ + * ***************************************************************************************/ -/*--- Constants ---*/ +/* --- Constants ---*/ #define ZSTD_MAGICNUMBER 0xFD2FB528 /* v0.8 */ #define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50U @@ -310,7 +339,7 @@ static const size_t ZSTD_frameHeaderSize_max = ZSTD_FRAMEHEADERSIZE_MAX; static const size_t ZSTD_skippableHeaderSize = 8; /* magic number + skippable frame length */ -/*--- Types ---*/ +/*--- Advanced types ---*/ typedef enum { ZSTD_fast, ZSTD_dfast, ZSTD_greedy, ZSTD_lazy, ZSTD_lazy2, ZSTD_btlazy2, ZSTD_btopt } ZSTD_strategy; /* from faster to stronger */ typedef struct { @@ -334,13 +363,13 @@ typedef struct { ZSTD_frameParameters fParams; } ZSTD_parameters; -/* custom memory allocation functions */ +/*= Custom memory allocation functions */ typedef void* (*ZSTD_allocFunction) (void* opaque, size_t size); typedef void (*ZSTD_freeFunction) (void* opaque, void* address); typedef struct { ZSTD_allocFunction customAlloc; ZSTD_freeFunction customFree; void* opaque; } ZSTD_customMem; -/*-************************************* +/*************************************** * Advanced compression functions ***************************************/ /*! ZSTD_estimateCCtxSize() : @@ -393,7 +422,7 @@ ZSTDLIB_API size_t ZSTD_compress_advanced (ZSTD_CCtx* ctx, ZSTD_parameters params); -/*--- Advanced Decompression functions ---*/ +/*--- Advanced decompression functions ---*/ /*! ZSTD_estimateDCtxSize() : * Gives the potential amount of memory allocated to create a ZSTD_DCtx */ @@ -412,12 +441,11 @@ ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx); ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); -/* ****************************************************************** -* Advanced Streaming functions +/******************************************************************** +* Advanced streaming functions ********************************************************************/ -/*====== compression ======*/ - +/*===== Advanced Streaming compression functions =====*/ ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem); ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); ZSTDLIB_API size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize, @@ -426,10 +454,8 @@ ZSTDLIB_API size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledg ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs); -/*====== decompression ======*/ - +/*===== Advanced Streaming decompression functions =====*/ typedef enum { ZSTDdsp_maxWindowSize } ZSTD_DStreamParameter_e; - ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem); ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); ZSTDLIB_API size_t ZSTD_setDStreamParameter(ZSTD_DStream* zds, ZSTD_DStreamParameter_e paramType, unsigned paramValue); @@ -437,22 +463,17 @@ ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); /**< re-use decompress ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds); -/* ****************************************************************** +/********************************************************************* * Buffer-less and synchronous inner streaming functions -********************************************************************/ -/* This is an advanced API, giving full control over buffer management, for users which need direct control over memory. +* +* This is an advanced API, giving full control over buffer management, for users which need direct control over memory. * But it's also a complex one, with many restrictions (documented below). -* Prefer using normal streaming API for an easier experience */ +* Prefer using normal streaming API for an easier experience +********************************************************************* */ -ZSTDLIB_API size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLevel); -ZSTDLIB_API size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel); -ZSTDLIB_API size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize); -ZSTDLIB_API size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); +/** + Buffer-less streaming compression (synchronous mode) -ZSTDLIB_API size_t ZSTD_compressContinue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); -ZSTDLIB_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); - -/* A ZSTD_CCtx object is required to track streaming operations. Use ZSTD_createCCtx() / ZSTD_freeCCtx() to manage resource. ZSTD_CCtx object can be re-used multiple times within successive compression operations. @@ -481,26 +502,17 @@ ZSTDLIB_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapaci You can then reuse `ZSTD_CCtx` (ZSTD_compressBegin()) to compress some new frame. */ -typedef struct { - unsigned long long frameContentSize; - unsigned windowSize; - unsigned dictID; - unsigned checksumFlag; -} ZSTD_frameParams; +/*===== Buffer-less streaming compression functions =====*/ +ZSTDLIB_API size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLevel); +ZSTDLIB_API size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel); +ZSTDLIB_API size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize); +ZSTDLIB_API size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); +ZSTDLIB_API size_t ZSTD_compressContinue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); +ZSTDLIB_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); -ZSTDLIB_API size_t ZSTD_getFrameParams(ZSTD_frameParams* fparamsPtr, const void* src, size_t srcSize); /**< doesn't consume input, see details below */ -ZSTDLIB_API size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx); -ZSTDLIB_API size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize); -ZSTDLIB_API void ZSTD_copyDCtx(ZSTD_DCtx* dctx, const ZSTD_DCtx* preparedDCtx); -ZSTDLIB_API size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx* dctx); -ZSTDLIB_API size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); - -typedef enum { ZSTDnit_frameHeader, ZSTDnit_blockHeader, ZSTDnit_block, ZSTDnit_lastBlock, ZSTDnit_checksum, ZSTDnit_skippableFrame } ZSTD_nextInputType_e; -ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx); - -/* +/*- Buffer-less streaming decompression (synchronous mode) A ZSTD_DCtx object is required to track streaming operations. @@ -557,11 +569,27 @@ ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx); It also returns Frame Size as fparamsPtr->frameContentSize. */ +typedef struct { + unsigned long long frameContentSize; + unsigned windowSize; + unsigned dictID; + unsigned checksumFlag; +} ZSTD_frameParams; -/* ************************************** -* Block functions -****************************************/ -/*! Block functions produce and decode raw zstd blocks, without frame metadata. +/*===== Buffer-less streaming decompression functions =====*/ +ZSTDLIB_API size_t ZSTD_getFrameParams(ZSTD_frameParams* fparamsPtr, const void* src, size_t srcSize); /**< doesn't consume input, see details below */ +ZSTDLIB_API size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx); +ZSTDLIB_API size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize); +ZSTDLIB_API void ZSTD_copyDCtx(ZSTD_DCtx* dctx, const ZSTD_DCtx* preparedDCtx); +ZSTDLIB_API size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx* dctx); +ZSTDLIB_API size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); +typedef enum { ZSTDnit_frameHeader, ZSTDnit_blockHeader, ZSTDnit_block, ZSTDnit_lastBlock, ZSTDnit_checksum, ZSTDnit_skippableFrame } ZSTD_nextInputType_e; +ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx); + +/** + Block functions + + Block functions produce and decode raw zstd blocks, without frame metadata. Frame metadata cost is typically ~18 bytes, which can be non-negligible for very small blocks (< 100 bytes). User will have to take in charge required information to regenerate data, such as compressed and content sizes. @@ -585,6 +613,7 @@ ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx); */ #define ZSTD_BLOCKSIZE_ABSOLUTEMAX (128 * 1024) /* define, for static allocation */ +/*===== Raw zstd block functions =====*/ ZSTDLIB_API size_t ZSTD_getBlockSizeMax(ZSTD_CCtx* cctx); ZSTDLIB_API size_t ZSTD_compressBlock (ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); ZSTDLIB_API size_t ZSTD_decompressBlock(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); diff --git a/programs/Makefile b/programs/Makefile index 06da7c44b..0ed7f3d07 100644 --- a/programs/Makefile +++ b/programs/Makefile @@ -76,17 +76,18 @@ default: zstd all: zstd - +$(ZSTDDECOMP_O): CPPFLAGS += -DZSTD_LEGACY_SUPPORT=$(ZSTD_LEGACY_SUPPORT) +$(ZSTDDECOMP_O): CFLAGS += $(ALIGN_LOOP) $(ZSTDDECOMP_O): $(ZSTDDIR)/decompress/zstd_decompress.c - $(CC) $(ALIGN_LOOP) $(FLAGS) -DZSTD_LEGACY_SUPPORT=$(ZSTD_LEGACY_SUPPORT) $^ -c -o $@ - -$(ZSTDDECOMP32_O): $(ZSTDDIR)/decompress/zstd_decompress.c - $(CC) -m32 $(ALIGN_LOOP) $(FLAGS) -DZSTD_LEGACY_SUPPORT=$(ZSTD_LEGACY_SUPPORT) $^ -c -o $@ zstd : $(ZSTDDECOMP_O) $(ZSTD_FILES) $(ZSTDLEGACY_FILES) $(ZDICT_FILES) \ zstdcli.c fileio.c bench.c datagen.c dibio.c $(CC) $(FLAGS) -DZSTD_LEGACY_SUPPORT=$(ZSTD_LEGACY_SUPPORT) $^ $(RES_FILE) -o $@$(EXT) + +$(ZSTDDECOMP32_O): $(ZSTDDIR)/decompress/zstd_decompress.c + $(CC) -m32 $(ALIGN_LOOP) $(FLAGS) -DZSTD_LEGACY_SUPPORT=$(ZSTD_LEGACY_SUPPORT) $^ -c -o $@ + zstd32 : $(ZSTDDECOMP32_O) $(ZSTD_FILES) $(ZSTDLEGACY_FILES) $(ZDICT_FILES) \ zstdcli.c fileio.c bench.c datagen.c dibio.c $(CC) -m32 $(FLAGS) -DZSTD_LEGACY_SUPPORT=$(ZSTD_LEGACY_SUPPORT) $^ $(RES32_FILE) -o $@$(EXT) diff --git a/programs/zstdcli.c b/programs/zstdcli.c index 2df410431..9aa97cdd2 100644 --- a/programs/zstdcli.c +++ b/programs/zstdcli.c @@ -25,7 +25,6 @@ **************************************/ #include "util.h" /* Compiler options, UTIL_HAS_CREATEFILELIST */ #include /* strcmp, strlen */ -#include /* toupper */ #include /* errno */ #include "fileio.h" #ifndef ZSTD_NOBENCH @@ -182,10 +181,13 @@ static unsigned readU32FromChar(const char** stringPtr) unsigned result = 0; while ((**stringPtr >='0') && (**stringPtr <='9')) result *= 10, result += **stringPtr - '0', (*stringPtr)++ ; - if (toupper(**stringPtr)=='K') result <<= 10, (*stringPtr)++ ; - else if (toupper(**stringPtr)=='M') result <<= 20, (*stringPtr)++ ; - if (toupper(**stringPtr)=='i') (*stringPtr)++; - if (toupper(**stringPtr)=='B') (*stringPtr)++; + if ((**stringPtr=='K') || (**stringPtr=='M')) { + result <<= 10; + if (**stringPtr=='M') result <<= 10; + (*stringPtr)++ ; + if (**stringPtr=='i') (*stringPtr)++; + if (**stringPtr=='B') (*stringPtr)++; + } return result; } diff --git a/zlibWrapper/Makefile b/zlibWrapper/Makefile index 69c976fa5..0e4ca9e6f 100644 --- a/zlibWrapper/Makefile +++ b/zlibWrapper/Makefile @@ -14,6 +14,7 @@ ZSTDLIBRARY = $(ZSTDLIBDIR)/libzstd.a ZLIBWRAPPER_PATH = . EXAMPLE_PATH = examples PROGRAMS_PATH = ../programs +TEST_FILE = ../doc/zstd_compression_format.md CC ?= gcc CFLAGS ?= -O3 CFLAGS += $(LOC) -I$(PROGRAMS_PATH) -I$(ZSTDLIBDIR) -I$(ZSTDLIBDIR)/common -I$(ZLIBWRAPPER_PATH) -std=gnu99 @@ -27,11 +28,11 @@ all: clean fitblk example zwrapbench test: example fitblk example_zstd fitblk_zstd zwrapbench ./example ./example_zstd - ./fitblk 10240 <../zstd_compression_format.md - ./fitblk 40960 <../zstd_compression_format.md - ./fitblk_zstd 10240 <../zstd_compression_format.md - ./fitblk_zstd 40960 <../zstd_compression_format.md - ./zwrapbench -qb3B1K ../zstd_compression_format.md + ./fitblk 10240 <$(TEST_FILE) + ./fitblk 40960 <$(TEST_FILE) + ./fitblk_zstd 10240 <$(TEST_FILE) + ./fitblk_zstd 40960 <$(TEST_FILE) + ./zwrapbench -qb3B1K $(TEST_FILE) ./zwrapbench -rqb1e5 ../lib ../programs ../tests #valgrindTest: ZSTDLIBRARY = $(ZSTDLIBDIR)/libzstd.so @@ -40,11 +41,11 @@ valgrindTest: clean example fitblk example_zstd fitblk_zstd zwrapbench @echo "\n ---- valgrind tests ----" $(VALGRIND) ./example $(VALGRIND) ./example_zstd - $(VALGRIND) ./fitblk 10240 <../zstd_compression_format.md - $(VALGRIND) ./fitblk 40960 <../zstd_compression_format.md - $(VALGRIND) ./fitblk_zstd 10240 <../zstd_compression_format.md - $(VALGRIND) ./fitblk_zstd 40960 <../zstd_compression_format.md - $(VALGRIND) ./zwrapbench -qb3B1K ../zstd_compression_format.md + $(VALGRIND) ./fitblk 10240 <$(TEST_FILE) + $(VALGRIND) ./fitblk 40960 <$(TEST_FILE) + $(VALGRIND) ./fitblk_zstd 10240 <$(TEST_FILE) + $(VALGRIND) ./fitblk_zstd 40960 <$(TEST_FILE) + $(VALGRIND) ./zwrapbench -qb3B1K $(TEST_FILE) $(VALGRIND) ./zwrapbench -rqb1e5 ../lib ../programs ../tests .c.o: