ddidderr/zstd-rs
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #425 from inikep/dev11

Browse Source 
Doc
This commit is contained in:
Yann Collet
2016-10-24 11:11:40 -07:00
committed by GitHub
parent 97611611a3 86d9424c81
commit 4239a207dd
11 changed files with 959 additions and 124 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.travis.yml
+1 -1
View File
@@ -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"
contrib/gen_html/Makefile
+36
View File
@@ -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
contrib/gen_html/README.md
+31
View File
@@ -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 `<H2>` header for the first line
- comments of type `/*=` and `/**=` mean: use a `<H3>` 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
```
contrib/gen_html/gen_html.cpp
+216
View File
@@ -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 <iostream>
#include <fstream>
#include <sstream>
#include <vector>
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<string> get_lines(vector<string>& input, int& linenum, string terminator)
{
vector<string> 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 << "</b>" << line.substr(spos) << "<b>" << 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<string> 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 << "<pre><b>";
for (l=0; l<lines.size(); l++) {
print_line(sout, lines[l]);
}
sout << "</b></pre><BR>" << 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 << "<pre><b>";
print_line(sout, line);
sout << "</b></pre><BR>" << endl;
continue;
}
/* comments of type /*= and /**= mean: use a <H3> 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 << "<h3>" << line << "</h3><pre><b>";
lines = get_lines(input, ++linenum, "");
for (l=0; l<lines.size(); l++) {
print_line(sout, lines[l]);
}
sout << "</b></pre><BR>" << 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<comments.size(); l++) {
if (comments[l].find(" *")==0) comments[l] = comments[l].substr(2);
else if (comments[l].find(" *")==0) comments[l] = comments[l].substr(3);
trim(comments[l], "*-");
}
while (!comments.empty() && comments[comments.size()-1].empty()) comments.pop_back(); // remove empty line at the end
while (!comments.empty() && comments[0].empty()) comments.erase(comments.begin()); // remove empty line at the start
/* comments of type /*! mean: this is a function declaration; switch comments with declarations */
if (exclam == '!') {
if (!comments.empty()) comments.erase(comments.begin()); /* remove first line like "ZSTD_XXX() :" */
linenum++;
lines = get_lines(input, linenum, "");
sout << "<pre><b>";
for (l=0; l<lines.size(); l++) {
// fprintf(stderr, "line[%d]=%s\n", l, lines[l].c_str());
print_line(sout, lines[l]);
}
sout << "</b><p>";
for (l=0; l<comments.size(); l++) {
print_line(sout, comments[l]);
}
sout << "</p></pre><BR>" << endl << endl;
} else { /* comments of type /** and /*- mean: this is a comment; use a <H2> header for the first line */
if (comments.empty()) continue;
trim(comments[0], " ");
sout << "<a name=\"Chapter" << chapter << "\"></a><h2>" << comments[0] << "</h2><pre>";
chapters.push_back(comments[0]);
chapter++;
for (l=1; l<comments.size(); l++) {
print_line(sout, comments[l]);
}
if (comments.size() > 1)
sout << "<BR></pre>" << endl << endl;
else
sout << "</pre>" << endl << endl;
}
}
ostream << "<html>\n<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=ISO-8859-1\">\n<title>" << version << "</title>\n</head>\n<body>" << endl;
ostream << "<h1>" << version << "</h1>\n";
ostream << "<hr>\n<a name=\"Contents\"></a><h2>Contents</h2>\n<ol>\n";
for (size_t i=0; i<chapters.size(); i++)
ostream << "<li><a href=\"#Chapter" << i+1 << "\">" << chapters[i].c_str() << "</a></li>\n";
ostream << "</ol>\n<hr>\n";
ostream << sout.str();
ostream << "</html>" << endl << "</body>" << endl;
return 0;
}
zstd_compression_format.md → doc/zstd_compression_format.md
View File
doc/zstd_manual.html
+528
View File
@@ -0,0 +1,528 @@
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1">
<title>zstd 1.1.1 Manual</title>
</head>
<body>
<h1>zstd 1.1.1 Manual</h1>
<hr>
<a name="Contents"></a><h2>Contents</h2>
<ol>
<li><a href="#Chapter1">Introduction</a></li>
<li><a href="#Chapter2">Version</a></li>
<li><a href="#Chapter3">Simple API</a></li>
<li><a href="#Chapter4">Explicit memory management</a></li>
<li><a href="#Chapter5">Simple dictionary API</a></li>
<li><a href="#Chapter6">Fast dictionary API</a></li>
<li><a href="#Chapter7">Streaming</a></li>
<li><a href="#Chapter8">Streaming compression - HowTo</a></li>
<li><a href="#Chapter9">Streaming decompression - HowTo</a></li>
<li><a href="#Chapter10">START OF ADVANCED AND EXPERIMENTAL FUNCTIONS</a></li>
<li><a href="#Chapter11">Advanced types</a></li>
<li><a href="#Chapter12">Advanced compression functions</a></li>
<li><a href="#Chapter13">Advanced decompression functions</a></li>
<li><a href="#Chapter14">Advanced streaming functions</a></li>
<li><a href="#Chapter15">Buffer-less and synchronous inner streaming functions</a></li>
<li><a href="#Chapter16">Buffer-less streaming compression (synchronous mode)</a></li>
<li><a href="#Chapter17">Buffer-less streaming decompression (synchronous mode)</a></li>
<li><a href="#Chapter18">Block functions</a></li>
</ol>
<hr>
<a name="Chapter1"></a><h2>Introduction</h2><pre>
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.
<BR></pre>
<a name="Chapter2"></a><h2>Version</h2><pre></pre>
<pre><b>unsigned ZSTD_versionNumber (void); </b>/**< returns version number of ZSTD */<b>
</b></pre><BR>
<a name="Chapter3"></a><h2>Simple API</h2><pre></pre>
<pre><b>size_t ZSTD_compress( void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
int compressionLevel);
</b><p> 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())
</p></pre><BR>
<pre><b>size_t ZSTD_decompress( void* dst, size_t dstCapacity,
const void* src, size_t compressedSize);
</b><p> `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())
</p></pre><BR>
<pre><b>unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize);
</b><p> '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.
</p></pre><BR>
<h3>Helper functions</h3><pre><b>int ZSTD_maxCLevel(void); </b>/*!< maximum compression level available */<b>
size_t ZSTD_compressBound(size_t srcSize); </b>/*!< maximum compressed size in worst case scenario */<b>
unsigned ZSTD_isError(size_t code); </b>/*!< tells if a `size_t` function result is an error code */<b>
const char* ZSTD_getErrorName(size_t code); </b>/*!< provides readable string from an error code */<b>
</b></pre><BR>
<a name="Chapter4"></a><h2>Explicit memory management</h2><pre></pre>
<h3>Compression context</h3><pre><b>typedef struct ZSTD_CCtx_s ZSTD_CCtx;
ZSTD_CCtx* ZSTD_createCCtx(void);
size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx);
</b></pre><BR>
<pre><b>size_t ZSTD_compressCCtx(ZSTD_CCtx* ctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize, int compressionLevel);
</b><p> Same as ZSTD_compress(), requires an allocated ZSTD_CCtx (see ZSTD_createCCtx())
</p></pre><BR>
<h3>Decompression context</h3><pre><b>typedef struct ZSTD_DCtx_s ZSTD_DCtx;
ZSTD_DCtx* ZSTD_createDCtx(void);
size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx);
</b></pre><BR>
<pre><b>size_t ZSTD_decompressDCtx(ZSTD_DCtx* ctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
</b><p> Same as ZSTD_decompress(), requires an allocated ZSTD_DCtx (see ZSTD_createDCtx())
</p></pre><BR>
<a name="Chapter5"></a><h2>Simple dictionary API</h2><pre></pre>
<pre><b>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);
</b><p> Compression using a predefined Dictionary (see dictBuilder/zdict.h).
Note : This function load the dictionary, resulting in significant startup delay.
</p></pre><BR>
<pre><b>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);
</b><p> 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
</p></pre><BR>
<a name="Chapter6"></a><h2>Fast dictionary API</h2><pre></pre>
<pre><b>ZSTD_CDict* ZSTD_createCDict(const void* dict, size_t dictSize, int compressionLevel);
</b><p> Create a digested dictionary, ready to start compression operation without startup delay.
`dict` can be released after ZSTD_CDict creation
</p></pre><BR>
<pre><b>size_t ZSTD_freeCDict(ZSTD_CDict* CDict);
</b><p> Function frees memory allocated with ZSTD_createCDict()
</p></pre><BR>
<pre><b>size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
const ZSTD_CDict* cdict);
</b><p> 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
</p></pre><BR>
<pre><b>ZSTD_DDict* ZSTD_createDDict(const void* dict, size_t dictSize);
</b><p> Create a digested dictionary, ready to start decompression operation without startup delay.
`dict` can be released after creation
</p></pre><BR>
<pre><b>size_t ZSTD_freeDDict(ZSTD_DDict* ddict);
</b><p> Function frees memory allocated with ZSTD_createDDict()
</p></pre><BR>
<pre><b>size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
const ZSTD_DDict* ddict);
</b><p> Decompression using a digested Dictionary
Faster startup than ZSTD_decompress_usingDict(), recommended when same dictionary is used multiple times.
</p></pre><BR>
<a name="Chapter7"></a><h2>Streaming</h2><pre></pre>
<pre><b>typedef struct ZSTD_inBuffer_s {
const void* src; </b>/**< start of input buffer */<b>
size_t size; </b>/**< size of input buffer */<b>
size_t pos; </b>/**< position where reading stopped. Will be updated. Necessarily 0 <= pos <= size */<b>
} ZSTD_inBuffer;
</b></pre><BR>
<pre><b>typedef struct ZSTD_outBuffer_s {
void* dst; </b>/**< start of output buffer */<b>
size_t size; </b>/**< size of output buffer */<b>
size_t pos; </b>/**< position where writing stopped. Will be updated. Necessarily 0 <= pos <= size */<b>
} ZSTD_outBuffer;
</b></pre><BR>
<a name="Chapter8"></a><h2>Streaming compression - HowTo</h2><pre>
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().
<BR></pre>
<h3>Streaming compression functions</h3><pre><b>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);
</b></pre><BR>
<pre><b>size_t ZSTD_CStreamInSize(void); </b>/**< recommended size for input buffer */<b>
</b></pre><BR>
<pre><b>size_t ZSTD_CStreamOutSize(void); </b>/**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block in all circumstances. */<b>
</b></pre><BR>
<a name="Chapter9"></a><h2>Streaming decompression - HowTo</h2><pre>
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).
<BR></pre>
<h3>Streaming decompression functions</h3><pre><b>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);
</b></pre><BR>
<pre><b>size_t ZSTD_DStreamInSize(void); </b>/*!< recommended size for input buffer */<b>
</b></pre><BR>
<pre><b>size_t ZSTD_DStreamOutSize(void); </b>/*!< recommended size for output buffer. Guarantee to successfully flush at least one complete block in all circumstances. */<b>
</b></pre><BR>
<a name="Chapter10"></a><h2>START OF ADVANCED AND EXPERIMENTAL FUNCTIONS</h2><pre> 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.
<BR></pre>
<a name="Chapter11"></a><h2>Advanced types</h2><pre></pre>
<pre><b>typedef enum { ZSTD_fast, ZSTD_dfast, ZSTD_greedy, ZSTD_lazy, ZSTD_lazy2, ZSTD_btlazy2, ZSTD_btopt } ZSTD_strategy; </b>/* from faster to stronger */<b>
</b></pre><BR>
<pre><b>typedef struct {
unsigned windowLog; </b>/**< largest match distance : larger == more compression, more memory needed during decompression */<b>
unsigned chainLog; </b>/**< fully searched segment : larger == more compression, slower, more memory (useless for fast) */<b>
unsigned hashLog; </b>/**< dispatch table : larger == faster, more memory */<b>
unsigned searchLog; </b>/**< nb of searches : larger == more compression, slower */<b>
unsigned searchLength; </b>/**< match length searched : larger == faster decompression, sometimes less compression */<b>
unsigned targetLength; </b>/**< acceptable match size for optimal parser (only) : larger == more compression, slower */<b>
ZSTD_strategy strategy;
} ZSTD_compressionParameters;
</b></pre><BR>
<pre><b>typedef struct {
unsigned contentSizeFlag; </b>/**< 1: content size will be in frame header (if known). */<b>
unsigned checksumFlag; </b>/**< 1: will generate a 22-bits checksum at end of frame, to be used for error detection by decompressor */<b>
unsigned noDictIDFlag; </b>/**< 1: no dict ID will be saved into frame header (if dictionary compression) */<b>
} ZSTD_frameParameters;
</b></pre><BR>
<pre><b>typedef struct {
ZSTD_compressionParameters cParams;
ZSTD_frameParameters fParams;
} ZSTD_parameters;
</b></pre><BR>
<h3>Custom memory allocation functions</h3><pre><b>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;
</b></pre><BR>
<a name="Chapter12"></a><h2>Advanced compression functions</h2><pre></pre>
<pre><b>size_t ZSTD_estimateCCtxSize(ZSTD_compressionParameters cParams);
</b><p> 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
</p></pre><BR>
<pre><b>ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem);
</b><p> Create a ZSTD compression context using external alloc and free functions
</p></pre><BR>
<pre><b>size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx);
</b><p> Gives the amount of memory used by a given ZSTD_CCtx
</p></pre><BR>
<pre><b>ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize,
ZSTD_parameters params, ZSTD_customMem customMem);
</b><p> Create a ZSTD_CDict using external alloc and free, and customized compression parameters
</p></pre><BR>
<pre><b>size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict);
</b><p> Gives the amount of memory used by a given ZSTD_sizeof_CDict
</p></pre><BR>
<pre><b>ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long srcSize, size_t dictSize);
</b><p> 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)
</p></pre><BR>
<pre><b>ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long srcSize, size_t dictSize);
</b><p> @return ZSTD_compressionParameters structure for a selected compression level and srcSize.
`srcSize` value is optional, select 0 if not known
</p></pre><BR>
<pre><b>size_t ZSTD_checkCParams(ZSTD_compressionParameters params);
</b><p> Ensure param values remain within authorized range
</p></pre><BR>
<pre><b>ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize);
</b><p> optimize params for a given `srcSize` and `dictSize`.
both values are optional, select `0` if unknown.
</p></pre><BR>
<pre><b>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);
</b><p> Same as ZSTD_compress_usingDict(), with fine-tune control of each compression parameter
</p></pre><BR>
<a name="Chapter13"></a><h2>Advanced decompression functions</h2><pre></pre>
<pre><b>size_t ZSTD_estimateDCtxSize(void);
</b><p> Gives the potential amount of memory allocated to create a ZSTD_DCtx
</p></pre><BR>
<pre><b>ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem);
</b><p> Create a ZSTD decompression context using external alloc and free functions
</p></pre><BR>
<pre><b>size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx);
</b><p> Gives the amount of memory used by a given ZSTD_DCtx
</p></pre><BR>
<pre><b>size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
</b><p> Gives the amount of memory used by a given ZSTD_DDict
</p></pre><BR>
<a name="Chapter14"></a><h2>Advanced streaming functions</h2><pre></pre>
<h3>Advanced Streaming compression functions</h3><pre><b>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); </b>/**< pledgedSrcSize is optional and can be zero == unknown */<b>
size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize); </b>/**< re-use compression parameters from previous init; saves dictionary loading */<b>
size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs);
</b></pre><BR>
<h3>Advanced Streaming decompression functions</h3><pre><b>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); </b>/**< re-use decompression parameters from previous init; saves dictionary loading */<b>
size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds);
</b></pre><BR>
<a name="Chapter15"></a><h2>Buffer-less and synchronous inner streaming functions</h2><pre>
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
<BR></pre>
<a name="Chapter16"></a><h2>Buffer-less streaming compression (synchronous mode)</h2><pre>
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.
<BR></pre>
<h3>Buffer-less streaming compression functions</h3><pre><b>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);
</b></pre><BR>
<a name="Chapter17"></a><h2>Buffer-less streaming decompression (synchronous mode)</h2><pre>
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.
<BR></pre>
<pre><b>typedef struct {
unsigned long long frameContentSize;
unsigned windowSize;
unsigned dictID;
unsigned checksumFlag;
} ZSTD_frameParams;
</b></pre><BR>
<h3>Buffer-less streaming decompression functions</h3><pre><b>size_t ZSTD_getFrameParams(ZSTD_frameParams* fparamsPtr, const void* src, size_t srcSize); </b>/**< doesn't consume input, see details below */<b>
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);
</b></pre><BR>
<a name="Chapter18"></a><h2>Block functions</h2><pre>
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.
<BR></pre>
<h3>Raw zstd block functions</h3><pre><b>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); </b>/**< insert block into `dctx` history. Useful for uncompressed blocks */<b>
</b></pre><BR>
</html>
</body>
lib/compress/zstd_compress.c
+1 -1
View File
@@ -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)
{
lib/compress/zstd_opt.h
+29 -35
View File
@@ -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; i<ZSTD_REP_NUM; i++) rep[i]=ctx->rep[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<last_i; i++) { /* check rep */
const S32 repCur = ((i==ZSTD_REP_MOVE_OPT) && (opt[cur].mlen != 1)) ? (opt[cur].rep[0] - 1) : opt[cur].rep[i];
@@ -510,21 +510,20 @@ void ZSTD_compressBlock_opt_generic(ZSTD_CCtx* ctx,
}
best_off = i - (opt[cur].mlen != 1);
if (mlen > 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<last_i; i++) {
const S32 repCur = ((i==ZSTD_REP_MOVE_OPT) && (opt[cur].mlen != 1)) ? (opt[cur].rep[0] - 1) : opt[cur].rep[i];
@@ -786,20 +782,20 @@ void ZSTD_compressBlock_opt_extDict_generic(ZSTD_CCtx* ctx,
}
best_off = i - (opt[cur].mlen != 1);
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);
}
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;
lib/decompress/zstd_decompress.c
+1 -1
View File
@@ -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.
lib/zstd.h
+105 -76
View File
@@ -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 <stddef.h> /* 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);
zlibWrapper/Makefile
+11 -10
View File
@@ -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: