648db22b |
1 | /* zran.h -- example of deflated stream indexing and random access |
2 | * Copyright (C) 2005, 2012, 2018, 2023 Mark Adler |
3 | * For conditions of distribution and use, see copyright notice in zlib.h |
4 | * Version 1.3 18 Feb 2023 Mark Adler */ |
5 | |
6 | #include <stdio.h> |
7 | #include "zlib.h" |
8 | |
9 | // Access point. |
10 | typedef struct point { |
11 | off_t out; // offset in uncompressed data |
12 | off_t in; // offset in compressed file of first full byte |
13 | int bits; // 0, or number of bits (1-7) from byte at in-1 |
14 | unsigned char window[32768]; // preceding 32K of uncompressed data |
15 | } point_t; |
16 | |
17 | // Access point list. |
18 | struct deflate_index { |
19 | int have; // number of access points in list |
20 | int mode; // -15 for raw, 15 for zlib, or 31 for gzip |
21 | off_t length; // total length of uncompressed data |
22 | point_t *list; // allocated list of access points |
23 | }; |
24 | |
25 | // Make one pass through a zlib, gzip, or raw deflate compressed stream and |
26 | // build an index, with access points about every span bytes of uncompressed |
27 | // output. gzip files with multiple members are fully indexed. span should be |
28 | // chosen to balance the speed of random access against the memory requirements |
29 | // of the list, which is about 32K bytes per access point. The return value is |
30 | // the number of access points on success (>= 1), Z_MEM_ERROR for out of |
31 | // memory, Z_BUF_ERROR for a premature end of input, Z_DATA_ERROR for a format |
32 | // or verification error in the input file, or Z_ERRNO for a file read error. |
33 | // On success, *built points to the resulting index. |
34 | int deflate_index_build(FILE *in, off_t span, struct deflate_index **built); |
35 | |
36 | // Use the index to read len bytes from offset into buf. Return the number of |
37 | // bytes read or a negative error code. If data is requested past the end of |
38 | // the uncompressed data, then deflate_index_extract() will return a value less |
39 | // than len, indicating how much was actually read into buf. If given a valid |
40 | // index, this function should not return an error unless the file was modified |
41 | // somehow since the index was generated, given that deflate_index_build() had |
42 | // validated all of the input. If nevertheless there is a failure, Z_BUF_ERROR |
43 | // is returned if the compressed data ends prematurely, Z_DATA_ERROR if the |
44 | // deflate compressed data is not valid, Z_MEM_ERROR if out of memory, |
45 | // Z_STREAM_ERROR if the index is not valid, or Z_ERRNO if there is an error |
46 | // reading or seeking on the input file. |
47 | ptrdiff_t deflate_index_extract(FILE *in, struct deflate_index *index, |
48 | off_t offset, unsigned char *buf, size_t len); |
49 | |
50 | // Deallocate an index built by deflate_index_build(). |
51 | void deflate_index_free(struct deflate_index *index); |