OpenBSD manual page server

Manual Page Search Parameters

COMPRESS(3) Library Functions Manual COMPRESS(3)

compress, zlibVersion, deflateInit, deflate, deflateEnd, inflateInit, inflate, inflateEnd, deflateInit2, deflateSetDictionary, deflateGetDictionary, deflateCopy, deflateReset, deflateParams, deflateTune, deflateBound, deflatePending, deflatePrime, deflateSetHeader, inflateInit2, inflateSetDictionary, inflateGetDictionary, inflateSync, inflateCopy, inflateReset, inflateReset2, inflatePrime, inflateMark, inflateGetHeader, inflateBackInit, inflateBack, inflateBackEnd, zlibCompileFlags, compress2, compressBound, uncompress, uncompress2, gzopen, gzdopen, gzbuffer, gzsetparams, gzread, gzfread, gzwrite, gzfwrite, gzprintf, gzputs, gzgets, gzputc, gzgetc, gzungetc, gzflush, gzseek, gzrewind, gztell, gzoffset, gzeof, gzdirect, gzclose, gzclose_r, gzclose_w, gzerror, gzclearerr, adler32, adler32_z, adler32_combine, crc32, crc32_z, crc32_combinezlib general purpose compression library

#include <zlib.h>

Basic functions


const char *
zlibVersion(void);

int
deflateInit(z_streamp strm, int level);

int
deflate(z_streamp strm, int flush);

int
deflateEnd(z_streamp strm);

int
inflateInit(z_streamp strm);

int
inflate(z_streamp strm, int flush);

int
inflateEnd(z_streamp strm);

Advanced functions


int
deflateInit2(z_streamp strm, int level, int method, int windowBits, int memLevel, int strategy);

int
deflateSetDictionary(z_streamp strm, const Bytef *dictionary, uInt dictLength);

int
deflateGetDictionary(z_streamp strm, Bytef *dictionary, uInt *dictLength);

int
deflateCopy(z_streamp dest, z_streamp source);

int
deflateReset(z_streamp strm);

int
deflateParams(z_streamp strm, int level, int strategy);

int
deflateTune(z_streamp strm, int good_length, int max_lazy, int nice_length, int max_chain);

uLong
deflateBound(z_streamp strm, uLong sourceLen);

int
deflatePending(z_streamp strm, unsigned *pending, int *bits);

int
deflatePrime(z_streamp strm, int bits, int value);

int
deflateSetHeader(z_streamp strm, gz_headerp head);

int
inflateInit2(z_streamp strm, int windowBits);

int
inflateSetDictionary(z_streamp strm, const Bytef *dictionary, uInt dictLength);

int
inflateGetDictionary(z_streamp strm, Bytef *dictionary, uInt *dictLength);

int
inflateSync(z_streamp strm);

int
inflateCopy(z_streamp dst, z_streamp source);

int
inflateReset(z_streamp strm);

int
inflateReset2(z_streamp strm, int windowBits);

int
inflatePrime(z_streamp strm, int bits, int value);

int
inflateMark(z_streamp strm);

int
inflateGetHeader(z_streamp strm, gz_headerp head);

int
inflateBackInit(z_stream *strm, int windowBits, unsigned char FAR *window);

int
inflateBack(z_stream *strm, in_func in, void FAR *in_desc, out_func out, void FAR *out_desc);

int
inflateBackEnd(z_stream *strm);

uLong
zlibCompileFlags(void);

Utility functions


typedef voidp gzFile;


int
compress(Bytef *dest, uLongf *destLen, const Bytef *source, uLong sourceLen);

int
compress2(Bytef *dest, uLongf *destLen, const Bytef *source, uLong sourceLen, int level);

uLong
compressBound(uLong sourceLen);

int
uncompress(Bytef *dest, uLongf *destLen, const Bytef *source, uLong sourceLen);

int
uncompress2(Bytef *dest, uLongf *destLen, const Bytef *source, uLong *sourceLen);

gzFile
gzopen(const char *path, const char *mode);

gzFile
gzdopen(int fd, const char *mode);

int
gzbuffer(gzFile file, unsigned size);

int
gzsetparams(gzFile file, int level, int strategy);

int
gzread(gzFile file, voidp buf, unsigned len);

int
gzfread(voidp buf, z_size_t size, z_size_t nitems, gzFile file);

int
gzwrite(gzFile file, voidpc buf, unsigned len);

int
gzfwrite(voidpc buf, z_size_t size, z_size_t nitems, gzFile file);

int
gzprintf(gzFile file, const char *format, ...);

int
gzputs(gzFile file, const char *s);

char *
gzgets(gzFile file, char *buf, int len);

int
gzputc(gzFile file, int c);

int
gzgetc(gzFile file);

int
gzungetc(int c, gzFile file);

int
gzflush(gzFile file, int flush);

z_off_t
gzseek(gzFile file, z_off_t offset, int whence);

int
gzrewind(gzFile file);

z_off_t
gztell(gzFile file);

int
gzoffset(gzFile file);

int
gzeof(gzFile file);

int
gzdirect(gzFile file);

int
gzclose(gzFile file);

int
gzclose_r(gzFile file);

int
gzclose_w(gzFile file);

const char *
gzerror(gzFile file, int *errnum);

void
gzclearerr(gzFile file);

Checksum functions


uLong
adler32(uLong adler, const Bytef *buf, uInt len);

uLong
adler32_z(uLong adler, const Bytef *buf, z_size_t len);

uLong
adler32_combine(uLong adler1, uLong adler2, z_off_t len2);

uLong
crc32(uLong crc, const Bytef *buf, uInt len);

uLong
crc32_z(uLong adler, const Bytef *buf, z_size_t len);

uLong
crc32_combine(uLong crc1, uLong crc2, z_off_t len2);

This manual page describes the zlib general purpose compression library, version 1.2.11.

The zlib compression library provides in-memory compression and decompression functions, including integrity checks of the uncompressed data. This version of the library supports only one compression method (deflation) but other algorithms will be added later and will have the same stream interface.

Compression can be done in a single step if the buffers are large enough or can be done by repeated calls of the compression function. In the latter case, the application must provide more input and/or consume the output (providing more output space) before each call.

The compressed data format used by default by the in-memory functions is the zlib format, which is a zlib wrapper documented in RFC 1950, wrapped around a deflate stream, which is itself documented in RFC 1951.

The library also supports reading and writing files in gzip(1) (.gz) format with an interface similar to that of stdio(3) using the functions that start with "gz". The gzip format is different from the zlib format. gzip is a gzip wrapper, documented in RFC 1952, wrapped around a deflate stream. This library can optionally read and write gzip and raw deflate streams in memory as well.

The zlib format was designed to be compact and fast for use in memory and on communications channels. The gzip format was designed for single-file compression on file systems, has a larger header than zlib to maintain directory information, and uses a different, slower, check method than zlib.

The library does not install any signal handler. The decoder checks the consistency of the compressed data, so the library should never crash even in the case of corrupted input.

The functions within the library are divided into the following sections:

const char * (void);

The application can compare () and ZLIB_VERSION for consistency. If the first character differs, the library code actually used is not compatible with the <zlib.h> header file used by the application. This check is automatically made by deflateInit() and inflateInit().

int deflateInit(z_streamp strm, int level);

The () function initializes the internal stream state for compression. The fields zalloc, zfree, and opaque must be initialized before by the caller. If zalloc and zfree are set to NULL, deflateInit() updates them to use default allocation functions. total_in, total_out, adler, and msg are initialized.

The compression level must be Z_DEFAULT_COMPRESSION, or between 0 and 9: 1 gives best speed, 9 gives best compression, 0 gives no compression at all (the input data is simply copied a block at a time).

Z_DEFAULT_COMPRESSION requests a default compromise between speed and compression (currently equivalent to level 6).

() returns Z_OK if successful, Z_MEM_ERROR if there was not enough memory, Z_STREAM_ERROR if level is not a valid compression level, Z_VERSION_ERROR if the zlib library version (zlib_version) is incompatible with the version assumed by the caller (ZLIB_VERSION). msg is set to null if there is no error message. deflateInit() does not perform any compression: this will be done by deflate().

int deflate(z_streamp strm, int flush);

() compresses as much data as possible, and stops when the input buffer becomes empty or the output buffer becomes full. It may introduce some output latency (reading input without producing any output) except when forced to flush.

The detailed semantics are as follows. () performs one or both of the following actions:

Compress more input starting at next_in and update next_in and avail_in accordingly. If not all input can be processed (because there is not enough room in the output buffer), next_in and avail_in are updated and processing will resume at this point for the next call to ().

Generate more output starting at next_out and update next_out and avail_out accordingly. This action is forced if the parameter flush is non-zero. Forcing flush frequently degrades the compression ratio, so this parameter should be set only when necessary. Some output may be provided even if flush is not set.

Before the call to (), the application should ensure that at least one of the actions is possible, by providing more input and/or consuming more output, and updating avail_in or avail_out accordingly; avail_out should never be zero before the call. The application can consume the compressed output when it wants, for example when the output buffer is full (avail_out == 0), or after each call to deflate(). If deflate() returns Z_OK and with zero avail_out, it must be called again after making room in the output buffer because there might be more output pending. See deflatePending(), which can be used if desired to determine whether or not there is more output in that case.

Normally the parameter flush is set to Z_NO_FLUSH, which allows () to decide how much data to accumulate before producing output, in order to maximise compression.

If the parameter flush is set to Z_SYNC_FLUSH, all pending output is flushed to the output buffer and the output is aligned on a byte boundary, so that the decompressor can get all input data available so far. (In particular avail_in is zero after the call if enough output space has been provided before the call.) Flushing may degrade compression for some compression algorithms and so it should be used only when necessary. This completes the current deflate block and follows it with an empty stored block that is three bits plus filler bits to the next byte, followed by four bytes (00 00 ff ff).

If flush is set to Z_PARTIAL_FLUSH, all pending output is flushed to the output buffer, but the output is not aligned to a byte boundary. All of the input data so far will be available to the decompressor, as for Z_SYNC_FLUSH. This completes the current deflate block and follows it with an empty fixed code block that is 10 bits long. This assures that enough bytes are output in order for the decompressor to finish the block before the empty fixed codes block.

If flush is set to Z_BLOCK, a deflate block is completed and emitted, as for Z_SYNC_FLUSH, but the output is not aligned on a byte boundary, and up to seven bits of the current block are held to be written as the next byte after the next deflate block is completed. In this case, the decompressor may not be provided enough bits at this point in order to complete decompression of the data provided so far to the compressor. It may need to wait for the next block to be emitted. This is for advanced applications that need to control the emission of deflate blocks.

If flush is set to Z_FULL_FLUSH, all output is flushed as with Z_SYNC_FLUSH, and the compression state is reset so that decompression can restart from this point if previous compressed data has been damaged or if random access is desired. Using Z_FULL_FLUSH too often can seriously degrade compression.

If () returns with avail_out == 0, this function must be called again with the same value of the flush parameter and more output space (updated avail_out), until the flush is complete (deflate() returns with non-zero avail_out). In the case of a Z_FULL_FLUSH or a Z_SYNC_FLUSH, make sure that avail_out is greater than six when the flush marker begins, in order to avoid repeated flush markers upon calling deflate() again when avail_out == 0.

If the parameter flush is set to Z_FINISH, pending input is processed, pending output is flushed and () returns with Z_STREAM_END if there was enough output space. If deflate() returns with Z_OK or Z_BUF_ERROR, this function must be called again with Z_FINISH and more output space (updated avail_out but no more input data, until it returns with Z_STREAM_END or an error. After deflate() has returned Z_STREAM_END, the only possible operations on the stream are deflateReset() or deflateEnd().

Z_FINISH can be used in the first deflate call after () if all the compression is to be done in a single step. In order to complete in one call, avail_out must be at least the value returned by deflateBound() (see below). Then deflate() is guaranteed to return Z_STREAM_END. If not enough output space is provided, deflate() will not return Z_STREAM_END, and it must be called again as described above.

() sets strm->adler to the Adler-32 checksum of all input read so far (that is, total_in bytes). If a gzip stream is being generated, then strm->adler will be the CRC-32 checksum of the input read so far. (See deflateInit2() below.)

() may update strm->data_type if it can make a good guess about the input data type (Z_BINARY or Z_TEXT). If in doubt, the data is considered binary. This field is only for information purposes and does not affect the compression algorithm in any manner.

() returns Z_OK if some progress has been made (more input processed or more output produced), Z_STREAM_END if all input has been consumed and all output has been produced (only when flush is set to Z_FINISH), Z_STREAM_ERROR if the stream state was inconsistent (for example, if next_in or next_out was NULL or the state was inadvertently written over by the application), or Z_BUF_ERROR if no progress is possible (for example, avail_in or avail_out was zero). Note that Z_BUF_ERROR is not fatal, and deflate() can be called again with more input and more output space to continue compressing.

int deflateEnd(z_streamp strm);

All dynamically allocated data structures for this stream are freed. This function discards any unprocessed input and does not flush any pending output.

() returns Z_OK if successful, Z_STREAM_ERROR if the stream state was inconsistent, Z_DATA_ERROR if the stream was freed prematurely (some input or output was discarded). In the error case, msg may be set but then points to a static string (which must not be deallocated).

int inflateInit(z_streamp strm);
The inflateInit() function initializes the internal stream state for decompression. The fields next_in, avail_in, zalloc, zfree, and opaque must be initialized before by the caller. In the current version of inflate(), the provided input is not read or consumed. The allocation of a sliding window will be deferred to the first call of inflate() (if the decompression does not complete on the first call). If zalloc and zfree are set to NULL, inflateInit() updates them to use default allocation functions. total_in, total_out, adler, and msg are initialized.

() returns Z_OK if successful, Z_MEM_ERROR if there was not enough memory, Z_VERSION_ERROR if the zlib library version is incompatible with the version assumed by the caller or Z_STREAM_ERROR if the parameters are invalid, such as a null pointer to the structure. msg is set to null if there is no error message. inflateInit() does not perform any decompression. Actual decompression will be done by inflate(). So next_in, avail_in, next_out, and avail_out are unused and unchanged. The current implementation of inflateInit() does not process any header information — that is deferred until inflate() is called.

int inflate(z_streamp strm, int flush);
inflate() decompresses as much data as possible, and stops when the input buffer becomes empty or the output buffer becomes full. It may introduce some output latency (reading input without producing any output) except when forced to flush.

The detailed semantics are as follows. () performs one or both of the following actions:

Decompress more input starting at next_in and update next_in and avail_in accordingly. If not all input can be processed (because there is not enough room in the output buffer), then next_in and avail_in are updated accordingly, and processing will resume at this point for the next call to ().

Generate more output starting at next_out and update next_out and avail_out accordingly. () provides as much output as possible, until there is no more input data or no more space in the output buffer (see below about the flush parameter).

Before the call to (), the application should ensure that at least one of the actions is possible, by providing more input and/or consuming more output, and updating the next_* and avail_* values accordingly. If the caller of inflate() does not provide both available input and available output space, it is possible that there will be no progress made. The application can consume the uncompressed output when it wants, for example when the output buffer is full (avail_out == 0), or after each call to inflate(). If inflate() returns Z_OK and with zero avail_out, it must be called again after making room in the output buffer because there might be more output pending.

The flush parameter of () can be Z_NO_FLUSH, Z_SYNC_FLUSH, Z_FINISH, Z_BLOCK or Z_TREES. Z_SYNC_FLUSH requests that inflate() flush as much output as possible to the output buffer. Z_BLOCK requests that inflate() stop if and when it gets to the next deflate block boundary. When decoding the zlib or gzip format, this will cause inflate() to return immediately after the header and before the first block. When doing a raw inflate, inflate() will go ahead and process the first block, and will return when it gets to the end of that block, or when it runs out of data.

The Z_BLOCK option assists in appending to or combining deflate streams. To assist in this, on return () always sets strm->data_type to the number of unused bits in the last byte taken from strm->next_in, plus 64 if inflate() is currently decoding the last block in the deflate stream, plus 128 if inflate() returned immediately after decoding an end-of-block code or decoding the complete header up to just before the first byte of the deflate stream. The end-of-block will not be indicated until all of the uncompressed data from that block has been written to strm->next_out. The number of unused bits may in general be greater than seven, except when bit 7 of data_type is set, in which case the number of unused bits will be less than eight. data_type is set as noted here every time inflate() returns for all flush options, and so can be used to determine the amount of currently consumed input in bits.

The Z_TREES option behaves as Z_BLOCK does, but it also returns when the end of each deflate block header is reached, before any actual data in that block is decoded. This allows the caller to determine the length of the deflate block header for later use in random access within a deflate block. 256 is added to the value of strm->data_type when () returns immediately after reaching the end of the deflate block header.

() should normally be called until it returns Z_STREAM_END or an error. However if all decompression is to be performed in a single step (a single call to inflate), the parameter flush should be set to Z_FINISH. In this case all pending input is processed and all pending output is flushed; avail_out must be large enough to hold all the uncompressed data for the operation to complete. (The size of the uncompressed data may have been saved by the compressor for this purpose.) The use of Z_FINISH is not required to perform an inflation in one step. However it may be used to inform inflate() that a faster approach can be used for the single inflate() call. Z_FINISH also informs inflate() to not maintain a sliding window if the stream completes, which reduces its memory footprint. If the stream does not complete, either because not all of the stream is provided or not enough output space is provided, then a sliding window will be allocated and inflate() can be called again to continue the operation as if Z_NO_FLUSH had been used.

In this implementation, () always flushes as much output as possible to the output buffer, and always uses the faster approach on the first call. So the effects of the flush parameter in this implementation are on the return value of inflate() as noted below, when inflate() returns early when Z_BLOCK or Z_TREES is used, and when inflate() avoids the allocation of memory for a sliding window when Z_FINISH is used.

If a preset dictionary is needed after this call (see () below), inflate() sets strm->adler to the Adler-32 checksum of the dictionary chosen by the compressor and returns Z_NEED_DICT; otherwise it sets strm->adler to the Adler-32 checksum of all output produced so far (that is, total_out bytes) and returns Z_OK, Z_STREAM_END or an error code as described below. At the end of the stream, inflate() checks that its computed Adler-32 checksum is equal to that saved by the compressor and returns Z_STREAM_END only if the checksum is correct.

() can decompress and check either zlib-wrapped or gzip-wrapped deflate data. The header type is detected automatically, if requested when initializing with inflateInit2(). Any information contained in the gzip header is not retained unless inflateGetHeader() is used. When processing gzip-wrapped deflate data, strm->adler32 is set to the CRC-32 of the output produced so far. The CRC-32 is checked against the gzip trailer, as is the uncompressed length, modulo 2^32.

() returns Z_OK if some progress has been made (more input processed or more output produced), Z_STREAM_END if the end of the compressed data has been reached and all uncompressed output has been produced, Z_NEED_DICT if a preset dictionary is needed at this point, Z_DATA_ERROR if the input data was corrupted (input stream not conforming to the zlib format or incorrect check value, in which case strm->msg points to a string with a more specific error), Z_STREAM_ERROR if the stream structure was inconsistent (for example, next_in or next_out was NULL, or the state was inadvertently over by the application), Z_MEM_ERROR if there was not enough memory, Z_BUF_ERROR if no progress was possible or if there was not enough room in the output buffer when Z_FINISH is used. Note that Z_BUF_ERROR is not fatal, and inflate() can be called again with more input and more output space to continue compressing. If Z_DATA_ERROR is returned, the application may then call inflateSync() to look for a good compression block if a partial recovery of the data is desired.

int inflateEnd(z_streamp strm);
All dynamically allocated data structures for this stream are freed. This function discards any unprocessed input and does not flush any pending output.

() returns Z_OK if successful, or Z_STREAM_ERROR if the stream state was inconsistent. In the error case, msg may be set but then points to a static string (which must not be deallocated).

The following functions are needed only in some special applications.

int deflateInit2(z_streamp strm, int level, int method, int windowBits, int memLevel, int strategy);

This is another version of () with more compression options. The fields next_in, zalloc, zfree, and opaque must be initialized before by the caller.

The method parameter is the compression method. It must be Z_DEFLATED in this version of the library.

The windowBits parameter is the base two logarithm of the window size (the size of the history buffer). It should be in the range 8..15 for this version of the library. Larger values of this parameter result in better compression at the expense of memory usage. The default value is 15 if () is used instead.

For the current implementation of (), a windowBits value of 8 (a window size of 256 bytes) is not supported. As a result, a request for 8 will result in 9 (a 512-byte window). In that case, providing 8 to inflateInit2() will result in an error when the zlib header with 9 is checked against the initialization of inflate(). The remedy is to not use 8 with deflateInit2() with this initialization, or at least in that case use 9 with inflateInit2().

windowBits can also be -8..-15 for raw deflate. In this case, -windowBits determines the window size. () will then generate raw deflate data with no zlib header or trailer, and will not compute a check value.

windowBits can also be greater than 15 for optional gzip encoding. Add 16 to windowBits to write a simple gzip header and trailer around the compressed data instead of a zlib wrapper. The gzip header will have no file name, no extra data, no comment, no modification time (set to zero), no header crc, and the operating system will be set to the appropriate value, if the operating system was determined at compile time. If a gzip stream is being written, strm->adler is a CRC-32 instead of an Adler-32.

For raw deflate or gzip encoding, a request for a 256-byte window is rejected as invalid, since only the zlib header provides a means of transmitting the window size to the decompressor.

The memLevel parameter specifies how much memory should be allocated for the internal compression state. memLevel=1 uses minimum memory but is slow and reduces compression ratio; memLevel=9 uses maximum memory for optimal speed. The default value is 8. See <zconf.h> for total memory usage as a function of windowBits and memLevel.

The strategy parameter is used to tune the compression algorithm. Use the value Z_DEFAULT_STRATEGY for normal data; Z_FILTERED for data produced by a filter (or predictor); Z_HUFFMAN_ONLY to force Huffman encoding only (no string match), or Z_RLE to limit match distances to one (run-length encoding). Filtered data consists mostly of small values with a somewhat random distribution. In this case, the compression algorithm is tuned to compress them better. The effect of Z_FILTERED is to force more Huffman coding and less string matching; it is somewhat intermediate between Z_DEFAULT_STRATEGY and Z_HUFFMAN_ONLY. Z_RLE is designed to be almost as fast as Z_HUFFMAN_ONLY, but gives better compression for PNG image data. The strategy parameter only affects the compression ratio but not the correctness of the compressed output, even if it is not set appropriately. Z_FIXED prevents the use of dynamic Huffman codes, allowing for a simpler decoder for special applications.

() returns Z_OK if successful, Z_MEM_ERROR if there was not enough memory, Z_STREAM_ERROR if any parameter is invalid (such as an invalid method), or Z_VERSION_ERROR if the zlib library version (zlib_version) is incompatible with the version assumed by the caller (ZLIB_VERSION). msg is set to null if there is no error message. deflateInit2() does not perform any compression: this will be done by deflate().

int deflateSetDictionary(z_streamp strm, const Bytef *dictionary, uInt dictLength);

Initializes the compression dictionary from the given byte sequence without producing any compressed output. When using the zlib format, this function must be called immediately after (), deflateInit2 or deflateReset(), and before any call of deflate(). When doing raw deflate, this function must be called either before any call of deflate(), or immediately after the completion of a deflate block, i.e. after all input has been consumed and all output has been delivered when using any of the flush options Z_BLOCK, Z_PARTIAL_FLUSH, Z_SYNC_FLUSH, or Z_FULL_FLUSH. The compressor and decompressor must use exactly the same dictionary (see inflateSetDictionary()).

The dictionary should consist of strings (byte sequences) that are likely to be encountered later in the data to be compressed, with the most commonly used strings preferably put towards the end of the dictionary. Using a dictionary is most useful when the data to be compressed is short and can be predicted with good accuracy; the data can then be compressed better than with the default empty dictionary.

Depending on the size of the compression data structures selected by () or deflateInit2(), a part of the dictionary may in effect be discarded, for example if the dictionary is larger than the window size provided in deflateInit() or deflateInit2(). Thus the strings most likely to be useful should be put at the end of the dictionary, not at the front. In addition, the current implementation of deflate() will use at most the window size minus 262 bytes of the provided dictionary.

Upon return of this function, strm->adler is set to the Adler-32 value of the dictionary; the decompressor may later use this value to determine which dictionary has been used by the compressor. (The Adler-32 value applies to the whole dictionary even if only a subset of the dictionary is actually used by the compressor.) If a raw deflate was requested, then the Adler-32 value is not computed and strm->adler is not set.

() returns Z_OK if successful, or Z_STREAM_ERROR if a parameter is invalid (e.g. dictionary being NULL) or the stream state is inconsistent (for example if deflate() has already been called for this stream or if not at a block boundary for raw deflate). deflateSetDictionary() does not perform any compression: this will be done by deflate().

int deflateGetDictionary(z_streamp strm, Bytef *dictionary uInt *dictLength);

Returns the sliding dictionary being maintained by (). dictLength is set to the number of bytes in the dictionary, and that many bytes are copied to dictionary. dictionary must have enough space, where 32768 bytes is always enough. If deflateGetDictionary() is called with dictionary equal to NULL, then only the dictionary length is returned, and nothing is copied. Similarly, if dictLength is NULL, then it is not set.

() may return a length less than the window size, even when more than the window size in input has been provided. It may return up to 258 bytes less in that case, due to how zlib's implementation of deflate() manages the sliding window and lookahead for matches, where matches can be up to 258 bytes long. If the application needs the last window-size bytes of input, then that would need to be saved by the application outside of zlib.

() returns Z_OK on success, or Z_STREAM_ERROR if the stream state is inconsistent.

int deflateCopy(z_streamp dest, z_streamp source);

The () function sets the destination stream as a complete copy of the source stream.

This function can be useful when several compression strategies will be tried, for example when there are several ways of pre-processing the input data with a filter. The streams that will be discarded should then be freed by calling (). Note that deflateCopy() duplicates the internal compression state which can be quite large, so this strategy is slow and can consume lots of memory.

() returns Z_OK if successful, Z_MEM_ERROR if there was not enough memory, Z_STREAM_ERROR if the source stream state was inconsistent (such as zalloc being NULL). msg is left unchanged in both source and destination.

int deflateReset(z_streamp strm);

This function is equivalent to () followed by deflateInit(), but does not free and reallocate the internal compression state. The stream will leave the compression level and any other attributes that may have been set unchanged. total_in, total_out, adler, and msg are initialized.

() returns Z_OK if successful, or Z_STREAM_ERROR if the source stream state was inconsistent (such as zalloc or state being NULL).

int deflateParams(z_streamp strm, int level, int strategy);

The () function dynamically updates the compression level and compression strategy. The interpretation of level and strategy is as in deflateInit2(). This can be used to switch between compression and straight copy of the input data, or to switch to a different kind of input data requiring a different strategy. If the compression approach (which is a function of the level) or the strategy is changed, and if any input has been consumed in a previous deflate() call, then the input available so far is compressed with the old level and strategy using deflate(strm, Z_BLOCK). There are three approaches for the compression levels 0, 1..3, and 4..9, respectively. The new level and strategy will take effect at the next call of deflate().

If a deflate(strm, Z_BLOCK) is performed by (), and it does not have enough output space to complete, then the parameter change will not take effect. In this case, deflateParams() can be called again with the same parameters and more output space to try again.

In order to assure a change in the parameters on the first try, the deflate stream should be flushed using () with Z_BLOCK or other flush request until strm.avail_out is not zero, before calling deflateParams(). Then no more input data should be provided before the deflateParams() call. If this is done, the old level and strategy will be applied to the data compressed before deflateParams(), and the new level and strategy will be applied to the data compressed after deflateParams().

() returns Z_OK on success, Z_STREAM_ERROR if the source stream state was inconsistent or if a parameter was invalid, or Z_BUF_ERROR if there was not enough output space to complete the compression of the available input data before a change in the strategy or approach. Note that in the case of a Z_BUF_ERROR, the parameters are not changed. A return value of Z_BUF_ERROR is not fatal, in which case deflateParams() can be retried with more output space.

int deflateTune(z_streamp strm, int good_length, int max_lazy, int nice_length, int max_chain);

Fine tune ()'s internal compression parameters. This should only be used by someone who understands the algorithm used by zlib's deflate for searching for the best matching string, and even then only by the most fanatic optimizer trying to squeeze out the last compressed bit for their specific input data. Read the deflate.c source code for the meaning of the max_lazy, good_length, nice_length, and max_chain parameters.

() can be called after deflateInit() or deflateInit2(), and returns Z_OK on success, or Z_STREAM_ERROR for an invalid deflate stream.

uLong deflateBound(z_streamp strm, uLong sourceLen);

() returns an upper bound on the compressed size after deflation of sourceLen bytes. It must be called after deflateInit() or deflateInit2(). and after deflateSetHeader(), if used. This would be used to allocate an output buffer for deflation in a single pass, and so would be called before deflate(). If that first deflate() call is provided the sourceLen input bytes, an output buffer allocated to the size returned by deflateBound(), and the flush value Z_FINISH, then deflate() is guaranteed to return Z_STREAM_END. Note that it is possible for the compressed size to be larger than the value returned by deflateBound() if flush options other than Z_FINISH or Z_NO_FLUSH are used.

int deflatePending(z_streamp strm, unsigned *pending, int *bits);

() returns the number of bytes and bits of output that have been generated, but not yet provided in the available output. The bytes not provided would be due to the available output space having been consumed. The number of bits of output not provided are between 0 and 7, where they await more bits to join them in order to fill out a full byte. If pending or bits are NULL, then those values are not set.

(returns) Z_OK if success, or Z_STREAM_ERROR if the source stream state was inconsistent.

int deflatePrime(z_streamp strm, int bits, int value);

() inserts bits in the deflate output stream. The intent is that this function is used to start off the deflate output with the bits left over from a previous deflate stream when appending to it. As such, this function can only be used for raw deflate, and must be used before the first deflate() call after a deflateInit2() or deflateReset(). bits must be less than or equal to 16, and that many of the least significant bits of value will be inserted in the output.

() returns Z_OK if successful, Z_BUF_ERROR if there was not enough room in the internal buffer to insert the bits, or Z_STREAM_ERROR if the source stream state was inconsistent.

int deflateSetHeader(z_streamp strm, gz_headerp head);

() provides gzip header information for when a gzip stream is requested by deflateInit2(). deflateSetHeader() may be called after deflateInit2() or deflateReset() and before the first call of deflate(). The text, time, os, extra field, name, and comment information in the provided gz_header structure are written to the gzip header (xflag is ignored - the extra flags are set according to the compression level). The caller must assure that, if not NULL, name and comment are terminated with a zero byte, and that if extra is not NULL, that extra_len bytes are available there. If hcrc is true, a gzip header CRC is included. Note that the current versions of the command-line version of gzip(1) do not support header CRCs, and will report that it is a “multi-part gzip file” and give up.

If () is not used, the default gzip header has text false, the time set to zero, and os set to the current operating system, with no extra, name, or comment fields. The gzip header is returned to the default state by deflateReset().

() returns Z_OK if successful, or Z_STREAM_ERROR if the source stream state was inconsistent.

int inflateInit2(z_streamp strm, int windowBits);

This is another version of () with an extra parameter. The fields next_in, avail_in, zalloc, zfree, and opaque must be initialized before by the caller.

The windowBits parameter is the base two logarithm of the maximum window size (the size of the history buffer). It should be in the range 8..15 for this version of the library. The default value is 15 if () is used instead. windowBits must be greater than or equal to the windowBits value provided to deflateInit2() while compressing, or it must be equal to 15 if deflateInit2() was not used. If a compressed stream with a larger window size is given as input, inflate() will return with the error code Z_DATA_ERROR instead of trying to allocate a larger window.

windowBits can also be zero to request that inflate use the window size in the zlib header of the compressed stream.

windowBits can also be -8..-15 for raw inflate. In this case, -windowBits determines the window size. () will then process raw deflate data, not looking for a zlib or gzip header, not generating a check value, and not looking for any check values for comparison at the end of the stream. This is for use with other formats that use the deflate compressed data format such as zip. Those formats provide their own check values. If a custom format is developed using the raw deflate format for compressed data, it is recommended that a check value such as an Adler-32 or a CRC-32 be applied to the uncompressed data as is done in the zlib, gzip, and zip formats. For most applications, the zlib format should be used as is. Note that comments above on the use in deflateInit2() applies to the magnitude of windowBits.

windowBits can also be greater than 15 for optional gzip decoding. Add 32 to windowBits to enable zlib and gzip decoding with automatic header detection, or add 16 to decode only the gzip format (the zlib format will return a Z_DATA_ERROR). If a gzip stream is being decoded, strm->adler is a CRC-32 instead of an Adler-32. Unlike the gunzip(1) utility and () (see below), inflate() will not automatically decode concatenated gzip streams. inflate() will return Z_STREAM_END at the end of the gzip stream. The state would need to be reset to continue decoding a subsequent gzip stream.

() returns Z_OK if successful, Z_MEM_ERROR if there was not enough memory, Z_VERSION_ERROR if the zlib library version is incompatible with the version assumed by the caller, or Z_STREAM_ERROR if the parameters are invalid, such as a null pointer to the structure. msg is set to null if there is no error message. inflateInit2() does not perform any decompression apart from possibly reading the zlib header if present: actual decompression will be done by inflate(). (So next_in and avail_in may be modified, but next_out and avail_out are unused and unchanged.) The current implementation of inflateInit2() does not process any header information — that is deferred until inflate() is called.

int inflateSetDictionary(z_streamp strm, const Bytef *dictionary, uInt dictLength);

Initializes the decompression dictionary from the given uncompressed byte sequence. This function must be called immediately after a call to () if that call returned Z_NEED_DICT. The dictionary chosen by the compressor can be determined from the Adler-32 value returned by that call to inflate(). The compressor and decompressor must use exactly the same dictionary (see deflateSetDictionary()). For raw inflate, this function can be called at any time to set the dictionary. If the provided dictionary is smaller than the window and there is already data in the window, then the provided dictionary will amend what's there. The application must ensure that the dictionary that was used for compression is provided.

() returns Z_OK if successful, Z_STREAM_ERROR if a parameter is invalid (e.g. dictionary being NULL) or the stream state is inconsistent, Z_DATA_ERROR if the given dictionary doesn't match the expected one (incorrect Adler-32 value). inflateSetDictionary() does not perform any decompression: this will be done by subsequent calls of inflate().

int inflateGetDictionary(z_streamp strm, Bytef *dictionary, uInt *dictLength);

Returns the sliding dictionary being maintained by (). dictLength is set to the number of bytes in the dictionary, and that many bytes are copied to dictionary. dictionary must have enough space, where 32768 bytes is always enough. If inflateGetDictionary() is called with dictionary equal to NULL, then only the dictionary length is returned, and nothing is copied. Similarly, if dictLength is NULL, then it is not set.

() returns Z_OK on success, or Z_STREAM_ERROR if the stream state is inconsistent.

int inflateSync(z_streamp strm);

Skips invalid compressed data until a possible full flush point (see above the description of () with Z_FULL_FLUSH) can be found, or until all available input is skipped. No output is provided.

() searches for a 00 00 FF FF pattern in the compressed data. All full flush points have this pattern, but not all occurrences of this pattern are full flush points.

() returns Z_OK if a possible full flush point has been found, Z_BUF_ERROR if no more input was provided, Z_DATA_ERROR if no flush point has been found, or Z_STREAM_ERROR if the stream structure was inconsistent. In the success case, the application may save the current value of total_in which indicates where valid compressed data was found. In the error case, the application may repeatedly call inflateSync(), providing more input each time, until success or end of the input data.

int inflateCopy(z_streamp dest, z_streamp source);

Sets the destination stream as a complete copy of the source stream.

This function can be useful when randomly accessing a large stream. The first pass through the stream can periodically record the inflate state, allowing restarting inflate at those points when randomly accessing the stream.

() returns Z_OK if success, Z_MEM_ERROR if there was not enough memory, Z_STREAM_ERROR if the source stream state was inconsistent (such as zalloc being NULL). msg is left unchanged in both source and dest.

int inflateReset(z_streamp strm);

This function is equivalent to () followed by inflateInit(), but does not free and reallocate the internal decompression state. The stream will keep attributes that may have been set by inflateInit2(). total_in, total_out, adler, and msg are initialized.

() returns Z_OK if successful, or Z_STREAM_ERROR if the source stream state was inconsistent (such as zalloc or state being NULL).

int inflateReset2(z_streamp strm, int windowBits);

This function is the same as (), but it also permits changing the wrap and window size requests. The windowBits parameter is interpreted the same as it is for inflateInit2. If the window size is changed, then the memory allocated for the window is freed, and the window will be reallocated by inflate() if needed.

() returns Z_OK if success, or Z_STREAM_ERROR if the source stream state was inconsistent (such as zalloc or state being NULL), or if the windowBits parameter is invalid.

int inflatePrime(z_stream strm, int bits, int value);

This function inserts bits in the inflate input stream. The intent is that this function is used to start inflating at a bit position in the middle of a byte. The provided bits will be used before any bytes are used from next_in. This function should only be used with raw inflate, and should be used before the first () call after inflateInit2() or inflateReset(). bits must be less than or equal to 16, and that many of the least significant bits of value will be inserted in the input.

If bits is negative, then the input stream bit buffer is emptied. Then () can be called again to put bits in the buffer. This is used to clear out bits left over after feeding inflate() a block description prior to feeding it codes.

() returns Z_OK if successful, or Z_STREAM_ERROR if the source stream state was inconsistent.

long inflateMark(z_streamp strm);

This function returns two values: one in the lower 16 bits of the return value, and the other in the remaining upper bits, obtained by shifting the return value down 16 bits. If the upper value is -1 and the lower value is zero, then () is currently decoding information outside of a block. If the upper value is -1 and the lower value is non-zero, then inflate() is in the middle of a stored block, with the lower value equaling the number of bytes from the input remaining to copy. If the upper value is not -1, then it is the number of bits back from the current bit position in the input of the code (literal or length/distance pair) currently being processed. In that case the lower value is the number of bytes already emitted for that code.

A code is being processed if () is waiting for more input to complete decoding of the code, or if it has completed decoding but is waiting for more output space to write the literal or match data.

() is used to mark locations in the input data for random access, which may be at bit positions, and to note those cases where the output of a code may span boundaries of random access blocks. The current location in the input stream can be determined from avail_in and data_type as noted in the description for the Z_BLOCK flush parameter for inflate().

() returns the value noted above, or -65536 if the provided source stream state was inconsistent.

int inflateGetHeader(z_streamp strm, gz_headerp head);

() requests that gzip header information be stored in the provided gz_header structure. inflateGetHeader() may be called after inflateInit2() or inflateReset(), and before the first call of inflate(). As inflate() processes the gzip stream, head->done is zero until the header is completed, at which time head->done is set to one. If a zlib stream is being decoded, then head->done is set to -1 to indicate that there will be no gzip header information forthcoming. Note that Z_BLOCK or Z_TREES can be used to force inflate() to return immediately after header processing is complete and before any actual data is decompressed.

The text, time, xflags, and os fields are filled in with the gzip header contents. hcrc is set to true if there is a header CRC. (The header CRC was valid if done is set to one.) If extra is not NULL, then extra_max contains the maximum number of bytes to write to extra. Once done is true, extra_len contains the actual extra field length, and extra contains the extra field, or that field truncated if extra_max is less than extra_len. If name is not NULL, then up to name_max characters are written there, terminated with a zero unless the length is greater than name_max. If comment is not NULL, then up to comm_max characters are written there, terminated with a zero unless the length is greater than comm_max. When any of extra, name, or comment are not NULL and the respective field is not present in the header, then that field is set to NULL to signal its absence. This allows the use of () with the returned structure to duplicate the header. However if those fields are set to allocated memory, then the application will need to save those pointers elsewhere so that they can be eventually freed.

If () is not used, then the header information is simply discarded. The header is always checked for validity, including the header CRC if present. inflateReset() will reset the process to discard the header information. The application would need to call inflateGetHeader() again to retrieve the header from the next gzip stream.

() returns Z_OK if successful, or Z_STREAM_ERROR if the source stream state was inconsistent.

int inflateBackInit(z_stream *strm, int windowBits, unsigned char FAR *window);

Initialize the internal stream state for decompression using () calls. The fields zalloc, zfree and opaque in strm must be initialized before the call. If zalloc and zfree are NULL, then the default library-derived memory allocation routines are used. windowBits is the base two logarithm of the window size, in the range 8..15. window is a caller supplied buffer of that size. Except for special applications where it is assured that deflate() was used with small window sizes, windowBits must be 15 and a 32K byte window must be supplied to be able to decompress general deflate streams.

See () for the usage of these routines.

() will return Z_OK on success, Z_STREAM_ERROR if any of the parameters are invalid, Z_MEM_ERROR if the internal state could not be allocated, or Z_VERSION_ERROR if the version of the library does not match the version of the header file.

int inflateBack(z_stream *strm, in_func in, void FAR *in_desc, out_func out, void FAR *out_desc);

() does a raw inflate with a single call using a call-back interface for input and output. This is potentially more efficient than inflate() for file I/O applications, in that it avoids copying between the output and the sliding window by simply making the window itself the output buffer. inflate() can be faster on modern CPUs when used with large buffers. inflateBack() trusts the application to not change the output buffer passed by the output function, at least until inflateBack() returns.

() must be called first to allocate the internal state and to initialize the state with the user-provided window buffer. inflateBack() may then be used multiple times to inflate a complete, raw deflate stream with each call. inflateBackEnd() is then called to free the allocated state.

A raw deflate stream is one with no zlib or gzip header or trailer. This routine would normally be used in a utility that reads zip or gzip files and writes out uncompressed files. The utility would decode the header and process the trailer on its own, hence this routine expects only the raw deflate stream to decompress. This is different from the default behavior of (), which expects either a zlib header and trailer around the deflate stream.

() uses two subroutines supplied by the caller that are then called by inflateBack() for input and output. inflateBack() calls those routines until it reads a complete deflate stream and writes out all of the uncompressed data, or until it encounters an error. The function's parameters and return types are defined above in the in_func and out_func typedefs. inflateBack() will call in(in_desc, &buf) which should return the number of bytes of provided input, and a pointer to that input in buf. If there is no input available, in() must return zero — buf is ignored in that case — and inflateBack() will return a buffer error. inflateBack() will call out(out_desc, buf, len) to write the uncompressed data buf[0..len-1]. out() should return zero on success, or non-zero on failure. If out() returns non-zero, inflateBack() will return with an error. Neither in() nor out() are permitted to change the contents of the window provided to inflateBackInit(), which is also the buffer that out() uses to write from. The length written by out() will be at most the window size. Any non-zero amount of input may be provided by in().

For convenience, () can be provided input on the first call by setting strm->next_in and strm->avail_in. If that input is exhausted, then () will be called. Therefore strm->next_in must be initialized before calling inflateBack(). If strm->next_in is NULL, then in() will be called immediately for input. If strm->next_in is not NULL, then strm->avail_in must also be initialized, and then if strm->avail_in is not zero, input will initially be taken from strm->next_in[0 .. strm->avail_in - 1].

The in_desc and out_desc parameters of () are passed as the first parameter of () and (), respectively, when they are called. These descriptors can be optionally used to pass any information that the caller-supplied in() and out() functions need to do their job.

On return, () will set strm->next_in and strm->avail_in to pass back any unused input that was provided by the last () call. The return values of inflateBack() can be Z_STREAM_END on success, Z_BUF_ERROR if in() or out() returned an error, Z_DATA_ERROR if there was a format error in the deflate stream (in which case strm->msg is set to indicate the nature of the error), or Z_STREAM_ERROR if the stream was not properly initialized. In the case of Z_BUF_ERROR, an input or output error can be distinguished using strm->next_in which will be NULL only if in() returned an error. If strm->next is not NULL, then the Z_BUF_ERROR was due to out() returning non-zero. (in() will always be called before out(), so strm->next_in is assured to be defined if out() returns non-zero.) Note that inflateBack() cannot return Z_OK.

int inflateBackEnd(z_stream *strm);

All memory allocated by () is freed.

() returns Z_OK on success, or Z_STREAM_ERROR if the stream state was inconsistent.

uLong (void);

This function returns flags indicating compile-time options.

Type sizes, two bits each:

00
16 bits
01
32 bits
10
64 bits
11
other:

1.0
size of uInt
3.2
size of uLong
5.4
size of voidpf (pointer)
7.6
size of z_off_t

Compiler, assembler, and debug options:

8
ZLIB_DEBUG
9
ASMV or ASMINF — use ASM code
10
ZLIB_WINAPI — exported functions use the WINAPI calling convention
11
0 (reserved)

One-time table building (smaller code, but not thread-safe if true):

12
BUILDFIXED — build static block decoding tables when needed
13
DYNAMIC_CRC_TABLE — build CRC calculation tables when needed
14,15
0 (reserved)

Library content (indicates missing functionality):

16
NO_GZCOMPRESS — gz* functions cannot compress (to avoid linking deflate code when not needed)
17
NO_GZIP — deflate can't write gzip streams, and inflate can't detect and decode gzip streams (to avoid linking CRC code)
18-19
0 (reserved)

Operation variations (changes in library functionality):

20
PKZIP_BUG_WORKAROUND — slightly more permissive inflate
21
FASTEST — deflate algorithm with only one, lowest compression level
22,23
0 (reserved)

The sprintf variant used by gzprintf (zero is best):

24
0 = vs*, 1 = s* — 1 means limited to 20 arguments after the format
25
0 = *nprintf, 1 = *printf — 1 means () not secure!
26
0 = returns value, 1 = void — 1 means inferred string length returned

Remainder:

27-31
0 (reserved)

The following utility functions are implemented on top of the basic stream-oriented functions. To simplify the interface, some default options are assumed (compression level and memory usage, standard memory allocation functions). The source code of these utility functions can be modified if you need special options.

int (Bytef *dest, uLongf *destLen, const Bytef *source, uLong sourceLen);

The () function compresses the source buffer into the destination buffer. sourceLen is the byte length of the source buffer. Upon entry, destLen is the total size of the destination buffer, which must be at least the value returned by compressBound(sourcelen). Upon exit, destLen is the actual size of the compressed data. compress() is equivalent to compress2() with a level parameter of Z_DEFAULT_COMPRESSION.

() returns Z_OK if successful, Z_MEM_ERROR if there was not enough memory, or Z_BUF_ERROR if there was not enough room in the output buffer.

int compress2(Bytef *dest, uLongf *destLen, const Bytef *source, uLong sourceLen, int level);

The () function compresses the source buffer into the destination buffer. The level parameter has the same meaning as in deflateInit(). sourceLen is the byte length of the source buffer. Upon entry, destLen is the total size of the destination buffer, which must be at least the value returned by compressBound(sourceLen). Upon exit, destLen is the actual size of the compressed buffer.

() returns Z_OK if successful, Z_MEM_ERROR if there was not enough memory, Z_BUF_ERROR if there was not enough room in the output buffer, or Z_STREAM_ERROR if the level parameter is invalid.

uLong compressBound(uLong sourceLen);

() returns an upper bound on the compressed size after compress() or compress2() on sourceLen bytes. It would be used before a compress() or compress2() call to allocate the destination buffer.

int uncompress(Bytef *dest, uLongf *destLen, const Bytef *source, uLong sourceLen);

The () function decompresses the source buffer into the destination buffer. sourceLen is the byte length of the source buffer. Upon entry, destLen is the total size of the destination buffer, which must be large enough to hold the entire uncompressed data. (The size of the uncompressed data must have been saved previously by the compressor and transmitted to the decompressor by some mechanism outside the scope of this compression library.) Upon exit, destLen is the actual size of the uncompressed data. This function can be used to decompress a whole file at once if the input file is mmap'ed.

() returns Z_OK if successful, Z_MEM_ERROR if there was not enough memory, Z_BUF_ERROR if there was not enough room in the output buffer, or Z_DATA_ERROR if the input data was corrupted or incomplete. In the case where there is not enough room, uncompress() will fill the output buffer with the uncompressed data up to that point.

int (Bytef *dest, uLongf *destLen, const Bytef *source, uLong *sourceLen);

Same as (), except that sourceLen is a pointer, where the length of the source is *sourceLen. On return, *sourceLen is the number of source bytes consumed.

gzFile gzopen(const char *path, const char *mode);

This library supports reading and writing files in gzip (.gz) format with an interface similar to that of stdio, using the functions that start with "gz". The gzip format is different from the zlib format. gzip is a gzip wrapper, documented in RFC 1952, wrapped around a deflate stream.

The () function opens a gzip (.gz) file for reading or writing. The mode parameter is as in fopen(3) ("rb" or "wb") but can also include a compression level (wb9) or a strategy: ‘f’ for filtered data, as in "wb6f"; ‘h’ for Huffman only compression, as in "wb1h", or ‘R’ for run-length encoding as in "wb1R", or ‘F’ for fixed code compression as in "wb9F". (See the description of deflateInit2() for more information about the strategy parameter.) ‘T’ will request transparent writing or appending with no compression and not using the gzip format.

‘a’ can be used instead of ‘w’ to request that the gzip stream that will be written be appended to the file. ‘+’ will result in an error, since reading and writing to the same gzip file is not supported. The addition of ‘x’ when writing will create the file exclusively, which fails if the file already exists. On systems that support it, the addition of ‘e’ when reading or writing will set the flag to close the file on an execve(2) call.

These functions, as well as gzip, will read and decode a sequence of gzip streams in a file. The append function of () can be used to create such a file. (Also see gzflush() for another way to do this.) When appending, gzopen() does not test whether the file begins with a gzip stream, nor does it look for the end of the gzip streams to begin appending. gzopen() will simply append a gzip stream to the existing file.

() can be used to read a file which is not in gzip format; in this case gzread() will directly read from the file without decompression. When reading, this will be detected automatically by looking for the magic two-byte gzip header.

() returns NULL if the file could not be opened, if there was insufficient memory to allocate the gzFile state, or if an invalid mode was specified (an ‘r’, ‘w’, or ‘a’ was not provided, or ‘+’ was provided). errno can be checked to determine if the reason gzopen() failed was that the file could not be opened.

gzFile gzdopen(int fd, const char *mode);

The () function associates a gzFile with the file descriptor fd. File descriptors are obtained from calls like open(2), dup(2), creat(3), pipe(2), or fileno(3) (if the file has been previously opened with fopen(3)). The mode parameter is as in gzopen().

The next call to () on the returned gzFile will also close the file descriptor fd, just like fclose(fdopen(fd), mode) closes the file descriptor fd. If you want to keep fd open, use “fd = dup(fd_keep); gz = gzdopen(fd, mode);”. The duplicated descriptor should be saved to avoid a leak, since gzdopen() does not close fd if it fails. If you are using () to get the file descriptor from a FILE *, then you will have to use dup(2) to avoid double-closing the file descriptor. Both gzclose() and () will close the associated file descriptor, so they need to have different file descriptors.

() returns NULL if there was insufficient memory to allocate the gzFile state, if an invalid mode was specified (an 'r', 'w', or 'a' was not provided, or '+' was provided), or if fd is -1. The file descriptor is not used until the next gz* read, write, seek, or close operation, so gzdopen() will not detect if fd is invalid (unless fd is -1).

int gzbuffer(gzFile file, unsigned size);

Set the internal buffer size used by this library's functions. The default buffer size is 8192 bytes. This function must be called after () or gzdopen(), and before any other calls that read or write the file. The buffer memory allocation is always deferred to the first read or write. Three times that size in buffer space is allocated. A larger buffer size of, for example, 64K or 128K bytes, will noticeably increase the speed of decompression (reading).

The new buffer size also affects the maximum length for ().

() returns 0 on success, or -1 on failure, such as being called too late.

int gzsetparams(gzFile file, int level, int strategy);

The () function dynamically updates the compression level or strategy. See the description of deflateInit2() for the meaning of these parameters. Previously provided data is flushed before the parameter change.

() returns Z_OK if successful, Z_STREAM_ERROR if the file was not opened for writing, Z_ERRNO if there is an error writing the flushed data, or Z_MEM_ERROR if there is a memory allocation error.

int gzread(gzFile file, voidp buf, unsigned len);

Reads the given number of uncompressed bytes from the compressed file. If the input file is not in gzip format, () copies the given number ofbytes into the buffer directly from the file.

After reaching the end of a gzip stream in the input, () will continue to read, looking for another gzip stream. Any number of gzip streams may be concatenated in the input file, and will all be decompressed by gzread(). If something other than a gzip stream is encountered after a gzip stream, that remaining trailing garbage is ignored (and no error is returned).

() can be used to read a gzip file that is being concurrently written. Upon reaching the end of the input, gzread() will return with the available data. If the error code returned by gzerror() is Z_OK or Z_BUF_ERROR, then gzclearerr() can be used to clear the end of file indicator in order to permit gzread() to be tried again. Z_OK indicates that a gzip stream was completed on the last gzread(). Z_BUF_ERROR indicates that the input file ended in the middle of a gzip stream. Note that gzread() does not return -1 in the event of an incomplete gzip stream. This error is deferred until gzclose(), which will return Z_BUF_ERROR if the last gzread() ended in the middle of a gzip stream. Alternatively, gzerror() can be used before gzclose() to detect this case.

() returns the number of uncompressed bytes actually read, less than len for end of file, or -1 for error. If len is too large to fit in an int, then nothing is read, -1 is returned, and the error state is set to Z_STREAM_ERROR.

z_size_t gzfread(voidp buf, z_size_t size, z_size_t nitems, gzFile file);

Read up to nitems items of size size from file to buf, otherwise operating as () does. This duplicates the interface of stdio's fread(3), with size_t request and return types. If the library defines size_t, then z_size_t is identical to size_t. If not, then z_size_t is an unsigned integer type that can contain a pointer.

() returns the number of full items read of size size, or zero if the end of the file was reached and a full item could not be read, or if there was an error. gzerror() must be consulted if zero is returned in order to determine if there was an error. If the multiplication of size and nitems overflows, i.e. the product does not fit in a z_size_t, then nothing is read, zero is returned, and the error state is set to Z_STREAM_ERROR.

In the event that the end of file is reached and only a partial item is available at the end, i.e. the remaining uncompressed data length is not a multiple of size, then the final partial item is nevetheless read into buf and the end-of-file flag is set. The length of the partial item read is not provided, but could be inferred from the result of (). This behavior is the same as the behavior of fread(3) implementations in common libraries, but it prevents the direct use of gzfread() to read a concurrently written file, resetting and retrying on end-of-file, when size is not 1.

int gzwrite(gzFile file, voidpc buf, unsigned len);

The () function writes the given number of uncompressed bytes into the compressed file. gzwrite() returns the number of uncompressed bytes written or 0 in case of error.

z_size_t gzfwrite(voidpc buf, z_size_t size, z_size_t nitems, gzFile file);

() writes nitems items of size size from buf to file, duplicating the interface of stdio's fwrite(3), with size_t request and return types. If the library defines size_t, then z_size_t is identical to size_t. If not, then z_size_t is an unsigned integer type that can contain a pointer.

() returns the number of full items written of size size, or zero if there was an error. If the multiplication of size and nitems overflows, i.e. the product does not fit in a z_size_t, then nothing is written, zero is returned, and the error state is set to Z_STREAM_ERROR.

int gzprintf(gzFile file, const char *format, ...);

The () function converts, formats, and writes the args to the compressed file under control of the format string, as in fprintf(3). gzprintf() returns the number of uncompressed bytes actually written, or a negative zlib error code in case of error. The number of uncompressed bytes written is limited to 8191, or one less than the buffer size given to gzbuffer(). The caller should ensure that this limit is not exceeded. If it is exceeded, then gzprintf() will return an error (0) with nothing written. In this case, there may also be a buffer overflow with unpredictable consequences, which is possible only if zlib was compiled with the insecure functions () or () because the secure () or () functions were not available. This can be determined using zlibCompileFlags().

int gzputs(gzFile file, const char *s);

The () function writes the given NUL-terminated string to the compressed file, excluding the terminating NUL character.

() returns the number of characters written, or -1 in case of error.

char * gzgets(gzFile file, char *buf, int len);

The () function reads bytes from the compressed file until len-1 characters are read, or a newline character is read and transferred to buf, or an end-of-file condition is encountered. If any characters are read or if len == 1, the string is terminated with a NUL character. If no characters are read due to an end-of-file or len < 1, then the buffer is left untouched.

() returns buf, which is a NUL-terminated string, or it returns NULL for end-of-file or in case of error. If there was an error, the contents at buf are indeterminate.

() returns buf, or NULL in case of error.

int gzputc(gzFile file, int c);

The () function writes c, converted to an unsigned char, into the compressed file. gzputc() returns the value that was written, or -1 in case of error.

int gzgetc(gzFile file);

The () function reads one byte from the compressed file. gzgetc() returns this byte or -1 in case of end of file or error. This is implemented as a macro for speed. As such, it does not do all of the checking the other functions do. That is, it does not check to see if file is NULL, nor whether the structure file points to has been clobbered or not.

int gzungetc(int c, gzFile file);

Push one character back onto the stream to be read as the first character on the next read. At least one character of push-back is allowed. () returns the character pushed, or -1 on failure. gzungetc() will fail if c is -1, and may fail if a character has been pushed but not read yet. If gzungetc() is used immediately after gzopen() or gzdopen(), at least the output buffer size of pushed characters is allowed. (See gzbuffer() above.) The pushed character will be discarded if the stream is repositioned with gzseek() or gzrewind().

int gzflush(gzFile file, int flush);

The () function flushes all pending output into the compressed file. The parameter flush is as in the deflate() function. The return value is the zlib error number (see function gzerror() below). gzflush() is only permitted when writing.

If the flush parameter is Z_FINISH, the remaining data is written and the gzip stream is completed in the output. If () is called again, a new gzip stream will be started in the output. gzread() is able to read such concatenated gzip streams.

() should be called only when strictly necessary because it will degrade compression if called too often.

z_off_t gzseek(gzFile file, z_off_t offset, int whence);

Sets the starting position for the next () or gzwrite() on the given compressed file. The offset represents a number of bytes in the uncompressed data stream. The whence parameter is defined as in lseek(2); the value SEEK_END is not supported.

If the file is opened for reading, this function is emulated but can be extremely slow. If the file is opened for writing, only forward seeks are supported; () then compresses a sequence of zeroes up to the new starting position.

() returns the resulting offset location as measured in bytes from the beginning of the uncompressed stream, or -1 in case of error, in particular if the file is opened for writing and the new starting position would be before the current position.

int gzrewind(gzFile file);

The () function rewinds the given file. This function is supported only for reading.

gzrewind(file) is equivalent to (int)gzseek(file, 0L, SEEK_SET).

z_off_t (gzFile file);

The () function returns the starting position for the next gzread() or gzwrite() on the given compressed file. This position represents a number of bytes in the uncompressed data stream, and is zero when starting, even if appending or reading a gzip stream from the middle of a file using gzdopen().

gztell(file) is equivalent to gzseek(file, 0L, SEEK_CUR).

int (gzFile file);

Returns the current offset in the file being read or written. This offset includes the count of bytes that precede the gzip stream, for example when appending or when using () for reading. When reading, the offset does not include as yet unused buffered input. This information can be used for a progress indicator. On error, () returns -1.

int gzeof(gzFile file);

Returns true (1) if the end-of-file indicator has been set while reading, false (0) otherwise. Note that the end-of-file indicator is set only if the read tried to go past the end of the input, but came up short. Therefore just like feof(3), () may return false even if there is no more data to read, in the event that the last read request was for the exact number of bytes remaining in the input file. This will happen if the input file size is an exact multiple of the buffer size.

If () returns true, then the read functions will return no more data, unless the end-of-file indicator is reset by () and the input file has grown since the previous end of file was detected.

int gzdirect(gzFile file);

Returns true (1) if file is being copied directly while reading, or false (0) if file is a gzip stream being decompressed.

If the input file is empty, () will return true, since the input does not contain a gzip stream.

If () is used immediately after gzopen() or gzdopen(), it will cause buffers to be allocated to allow reading the file to determine if it is a gzip file. Therefore if gzbuffer() is used, it should be called before gzdirect().

When writing, () returns true (1) if transparent writing was requested ("wT" for the gzopen() mode), or false (0) otherwise. (Note: gzdirect() is not needed when writing. Transparent writing must be explicitly requested, so the application already knows the answer. When linking statically, using gzdirect() will include all of the zlib code for gzip file reading and decompression, which may not be desired.)

int gzclose(gzFile file);

Flushes all pending output if necessary, closes the compressed file and deallocates the (de)compression state. Note that once file is closed, you cannot call () with file, since its structures have been deallocated. gzclose() must not be called more than once on the same file, just as free(3) must not be called more than once on the same allocation.

() will return Z_STREAM_ERROR if file is not valid, Z_ERRNO on a file operation error, Z_MEM_ERROR if out of memory, Z_BUF_ERROR if the last read ended in the middle of a gzip stream, or Z_OK on success.

int (gzFile file);
 
int (gzFile file);

Same as (), but () is only for use when reading, and () is only for use when writing or appending. The advantage to using these instead of gzclose() is that they avoid linking in zlib compression or decompression code that is not used when only reading or only writing, respectively. If gzclose() is used, then both compression and decompression code will be included in the application when linking to a static zlib library.

const char * gzerror(gzFile file, int *errnum);

The () function returns the error message for the last error which occurred on the given compressed file. errnum is set to the zlib error number. If an error occurred in the file system and not in the compression library, errnum is set to Z_ERRNO and the application may consult errno to get the exact error code.

The application must not modify the returned string. Future calls to this function may invalidate the previously returned string. If file is closed, then the string previously returned by () will no longer be available.

() should be used to distinguish errors from end-of-file for those functions above that do not distinguish those cases in their return values.

void (gzFile file);
Clears the error and end-of-file flags for file. This is analogous to the () function in stdio. This is useful for continuing to read a gzip file that is being written concurrently.

These functions are not related to compression but are exported anyway because they might be useful in applications using the compression library.

uLong adler32(uLong adler, const Bytef *buf, uInt len);
The adler32() function updates a running Adler-32 checksum with the bytes buf[0..len-1] and returns the updated checksum. If buf is NULL, this function returns the required initial value for the checksum.

An Adler-32 checksum is almost as reliable as a CRC-32 but can be computed much faster. Usage example:

uLong adler = adler32(0L, NULL, 0);

while (read_buffer(buffer, length) != EOF) {
adler = adler32(adler, buffer, length);
}
if (adler != original_adler) error();
uLong (uLong adler, const Bytef *buf, z_size_t len);

The same as (), but with a size_t length.

uLong adler32_combine(uLong adler1, uLong adler2, z_off_t len2);

The () function combines two Adler-32 checksums into one. For two sequences of bytes, seq1 and seq2 with lengths len1 and len2, Adler-32 checksums are calculated for each, adler1 and adler2. adler32_combine() returns the Adler-32 checksum of seq1 and seq2 concatenated, requiring only adler1, adler2, and len2. Note that the z_off_t type (like off_t) is a signed integer. If len2 is negative, the result has no meaning or utility.

uLong crc32(uLong crc, const Bytef *buf, uInt len);

The () function updates a running CRC-32 with the bytes buf[0..len-1] and returns the updated CRC-32. If buf is NULL, this function returns the required initial value for the CRC. Pre- and post-conditioning (one's complement) is performed within this function so it shouldn't be done by the application. Usage example:

uLong crc = crc32(0L, NULL, 0);

while (read_buffer(buffer, length) != EOF) {
crc = crc32(crc, buffer, length);
}
if (crc != original_crc) error();
uLong (uLong adler , const, Bytef, *buf", z_size_t len);

The same as (), but with a size_t length.

uLong crc32_combine(uLong crc1, uLong crc2, z_off_t len2);

The () function combines two CRC-32 check values into one. For two sequences of bytes, seq1 and seq2 with lengths len1 and len2, CRC-32 check values are calculated for each, crc1 and crc2. crc32_combine() returns the CRC-32 check value of seq1 and seq2 concatenated, requiring only crc1, crc2, and len2.

struct internal_state;

typedef struct z_stream_s {
    Bytef    *next_in;  /* next input byte */
    uInt     avail_in;  /* number of bytes available at next_in */
    off_t    total_in;  /* total number of input bytes read so far */

    Bytef    *next_out; /* next output byte will go here */
    uInt     avail_out; /* remaining free space at next_out */
    off_t    total_out; /* total number of bytes output so far */

    char     *msg;      /* last error message, NULL if no error */
    struct internal_state FAR *state; /* not visible by applications */

    alloc_func zalloc;  /* used to allocate the internal state */
    free_func  zfree;   /* used to free the internal state */
    voidpf     opaque;  /* private data object passed to zalloc and zfree*/

    int     data_type;  /* best guess about the data type: binary or text
                           for deflate, or the decoding state for inflate */
    uLong   adler;      /* Adler-32 or CRC-32 value of the uncompressed data */
    uLong   reserved;   /* reserved for future use */
} z_stream;

typedef z_stream FAR * z_streamp;
/*
     gzip header information passed to and from zlib routines.
  See RFC 1952 for more details on the meanings of these fields.
*/
typedef struct gz_header_s {
    int     text;       /* true if compressed data believed to be text */
    uLong   time;       /* modification time */
    int     xflags;     /*extra flags (not used when writing a gzip file)*/
    int     os;         /* operating system */
    Bytef   *extra;     /* pointer to extra field or NULL if none */
    uInt    extra_len;  /* extra field length (valid if extra != NULL) */
    uInt    extra_max;  /* space at extra (only when reading header) */
    Bytef   *name;      /* pointer to zero-terminated file name or NULL*/
    uInt    name_max;   /* space at name (only when reading header) */
    Bytef   *comment;   /* pointer to zero-terminated comment or NULL */
    uInt    comm_max;   /* space at comment (only when reading header) */
    int     hcrc;       /* true if there was or will be a header crc */
    int     done;       /* true when done reading gzip header (not used
                           when writing a gzip file) */
} gz_header;

typedef gz_header FAR *gz_headerp;

The application must update next_in and avail_in when avail_in has dropped to zero. It must update next_out and avail_out when avail_out has dropped to zero. The application must initialize zalloc, zfree, and opaque before calling the init function. All other fields are set by the compression library and must not be updated by the application.

The opaque value provided by the application will be passed as the first parameter for calls to () and (). This can be useful for custom memory management. The compression library attaches no meaning to the opaque value.

zalloc must return NULL if there is not enough memory for the object. If zlib is used in a multi-threaded application, zalloc and zfree must be thread safe. In that case, zlib is thread-safe. When zalloc and zfree are NULL on entry to the initialization function, they are set to internal routines that use the standard library functions malloc(3) and free(3).

On 16-bit systems, the functions zalloc and zfree must be able to allocate exactly 65536 bytes, but will not be required to allocate more than this if the symbol MAXSEG_64K is defined (see <zconf.h>).

WARNING: On MSDOS, pointers returned by zalloc for objects of exactly 65536 bytes *must* have their offset normalized to zero. The default allocation function provided by this library ensures this (see zutil.c). To reduce memory requirements and avoid any allocation of 64K objects, at the expense of compression ratio, compile the library with -DMAX_WBITS=14 (see <zconf.h>).

The fields total_in and total_out can be used for statistics or progress reports. After compression, total_in holds the total size of the uncompressed data and may be saved for use in the decompressor (particularly if the decompressor wants to decompress everything in a single step).

#define Z_NO_FLUSH      0
#define Z_PARTIAL_FLUSH 1
#define Z_SYNC_FLUSH    2
#define Z_FULL_FLUSH    3
#define Z_FINISH        4
#define Z_BLOCK         5
#define Z_TREES         6
/* Allowed flush values; see deflate() and inflate() below for details */

#define Z_OK            0
#define Z_STREAM_END    1
#define Z_NEED_DICT     2
#define Z_ERRNO        (-1)
#define Z_STREAM_ERROR (-2)
#define Z_DATA_ERROR   (-3)
#define Z_MEM_ERROR    (-4)
#define Z_BUF_ERROR    (-5)
#define Z_VERSION_ERROR (-6)
/* Return codes for the compression/decompression functions.
 * Negative values are errors,
 * positive values are used for special but normal events.
 */

#define Z_NO_COMPRESSION         0
#define Z_BEST_SPEED             1
#define Z_BEST_COMPRESSION       9
#define Z_DEFAULT_COMPRESSION  (-1)
/* compression levels */

#define Z_FILTERED            1
#define Z_HUFFMAN_ONLY        2
#define Z_RLE                 3
#define Z_FIXED               4
#define Z_DEFAULT_STRATEGY    0
/* compression strategy; see deflateInit2() below for details */

#define Z_BINARY   0
#define Z_TEXT     1
#define Z_ASCII    Z_TEXT /* for compatibility with 1.2.2 and earlier */
#define Z_UNKNOWN  2
/* Possible values of the data_type field for deflate() */

#define Z_DEFLATED   8
/* The deflate compression method
 * (the only one supported in this version)
*/

#define Z_NULL  0  /* for initializing zalloc, zfree, opaque */

#define zlib_version zlibVersion()
/* for compatibility with versions < 1.0.2 */

deflateInit and inflateInit are macros to allow checking the zlib version and the compiler's view of z_stream.

int (z_stream strm, int level, const char *version, int stream_size);
 
int (z_stream strm, const char *version, int stream_size);
 
int (z_stream strm, int level, int method, int windowBits, int memLevel, int strategy, const char *version, int stream_size);;
 
int (z_stream strm, int windowBits, const char *version, int stream_size);
 
int (z_stream *strm, int windowBits, unsigned char FAR *window, const char *version, int stream_size);
 
const char * (int err);
 
int (z_streamp z);
 
const uLongf * (void);
 

compress(1), gzip(1)

P. Deutsch and J-L. Gailly, ZLIB Compressed Data Format Specification version 3.3, RFC 1950, May 1996.

P. Deutsch, DEFLATE Compressed Data Format Specification version 1.3, RFC 1951, May 1996.

P. Deutsch, GZIP file format specification version 4.3, RFC 1952, May 1996.

This manual page is based on an HTML version of <zlib.h> converted by piaip <piaip@csie.ntu.edu.tw> and was converted to mdoc format by the OpenBSD project.

Jean-loup Gailly <jloup@gzip.org>
Mark Adler <madler@alumni.caltech.edu>

August 18, 2023 OpenBSD-7.4