@cpp.js/package-zlib 1.0.0-beta.20

package/.cppjs/build/source/deflate.h

@@ -0,0 +1,377 @@
+/* deflate.h -- internal compression state
+ * Copyright (C) 1995-2024 Jean-loup Gailly
+ * For conditions of distribution and use, see copyright notice in zlib.h
+ */
+
+/* WARNING: this file should *not* be used by applications. It is
+   part of the implementation of the compression library and is
+   subject to change. Applications should only use zlib.h.
+ */
+
+/* @(#) $Id$ */
+
+#ifndef DEFLATE_H
+#define DEFLATE_H
+
+#include "zutil.h"
+
+/* define NO_GZIP when compiling if you want to disable gzip header and
+   trailer creation by deflate().  NO_GZIP would be used to avoid linking in
+   the crc code when it is not needed.  For shared libraries, gzip encoding
+   should be left enabled. */
+#ifndef NO_GZIP
+#  define GZIP
+#endif
+
+/* define LIT_MEM to slightly increase the speed of deflate (order 1% to 2%) at
+   the cost of a larger memory footprint */
+/* #define LIT_MEM */
+
+/* ===========================================================================
+ * Internal compression state.
+ */
+
+#define LENGTH_CODES 29
+/* number of length codes, not counting the special END_BLOCK code */
+
+#define LITERALS  256
+/* number of literal bytes 0..255 */
+
+#define L_CODES (LITERALS+1+LENGTH_CODES)
+/* number of Literal or Length codes, including the END_BLOCK code */
+
+#define D_CODES   30
+/* number of distance codes */
+
+#define BL_CODES  19
+/* number of codes used to transfer the bit lengths */
+
+#define HEAP_SIZE (2*L_CODES+1)
+/* maximum heap size */
+
+#define MAX_BITS 15
+/* All codes must not exceed MAX_BITS bits */
+
+#define Buf_size 16
+/* size of bit buffer in bi_buf */
+
+#define INIT_STATE    42    /* zlib header -> BUSY_STATE */
+#ifdef GZIP
+#  define GZIP_STATE  57    /* gzip header -> BUSY_STATE | EXTRA_STATE */
+#endif
+#define EXTRA_STATE   69    /* gzip extra block -> NAME_STATE */
+#define NAME_STATE    73    /* gzip file name -> COMMENT_STATE */
+#define COMMENT_STATE 91    /* gzip comment -> HCRC_STATE */
+#define HCRC_STATE   103    /* gzip header CRC -> BUSY_STATE */
+#define BUSY_STATE   113    /* deflate -> FINISH_STATE */
+#define FINISH_STATE 666    /* stream complete */
+/* Stream status */
+
+
+/* Data structure describing a single value and its code string. */
+typedef struct ct_data_s {
+    union {
+        ush  freq;       /* frequency count */
+        ush  code;       /* bit string */
+    } fc;
+    union {
+        ush  dad;        /* father node in Huffman tree */
+        ush  len;        /* length of bit string */
+    } dl;
+} FAR ct_data;
+
+#define Freq fc.freq
+#define Code fc.code
+#define Dad  dl.dad
+#define Len  dl.len
+
+typedef struct static_tree_desc_s  static_tree_desc;
+
+typedef struct tree_desc_s {
+    ct_data *dyn_tree;           /* the dynamic tree */
+    int     max_code;            /* largest code with non zero frequency */
+    const static_tree_desc *stat_desc;  /* the corresponding static tree */
+} FAR tree_desc;
+
+typedef ush Pos;
+typedef Pos FAR Posf;
+typedef unsigned IPos;
+
+/* A Pos is an index in the character window. We use short instead of int to
+ * save space in the various tables. IPos is used only for parameter passing.
+ */
+
+typedef struct internal_state {
+    z_streamp strm;      /* pointer back to this zlib stream */
+    int   status;        /* as the name implies */
+    Bytef *pending_buf;  /* output still pending */
+    ulg   pending_buf_size; /* size of pending_buf */
+    Bytef *pending_out;  /* next pending byte to output to the stream */
+    ulg   pending;       /* nb of bytes in the pending buffer */
+    int   wrap;          /* bit 0 true for zlib, bit 1 true for gzip */
+    gz_headerp  gzhead;  /* gzip header information to write */
+    ulg   gzindex;       /* where in extra, name, or comment */
+    Byte  method;        /* can only be DEFLATED */
+    int   last_flush;    /* value of flush param for previous deflate call */
+
+                /* used by deflate.c: */
+
+    uInt  w_size;        /* LZ77 window size (32K by default) */
+    uInt  w_bits;        /* log2(w_size)  (8..16) */
+    uInt  w_mask;        /* w_size - 1 */
+
+    Bytef *window;
+    /* Sliding window. Input bytes are read into the second half of the window,
+     * and move to the first half later to keep a dictionary of at least wSize
+     * bytes. With this organization, matches are limited to a distance of
+     * wSize-MAX_MATCH bytes, but this ensures that IO is always
+     * performed with a length multiple of the block size. Also, it limits
+     * the window size to 64K, which is quite useful on MSDOS.
+     * To do: use the user input buffer as sliding window.
+     */
+
+    ulg window_size;
+    /* Actual size of window: 2*wSize, except when the user input buffer
+     * is directly used as sliding window.
+     */
+
+    Posf *prev;
+    /* Link to older string with same hash index. To limit the size of this
+     * array to 64K, this link is maintained only for the last 32K strings.
+     * An index in this array is thus a window index modulo 32K.
+     */
+
+    Posf *head; /* Heads of the hash chains or NIL. */
+
+    uInt  ins_h;          /* hash index of string to be inserted */
+    uInt  hash_size;      /* number of elements in hash table */
+    uInt  hash_bits;      /* log2(hash_size) */
+    uInt  hash_mask;      /* hash_size-1 */
+
+    uInt  hash_shift;
+    /* Number of bits by which ins_h must be shifted at each input
+     * step. It must be such that after MIN_MATCH steps, the oldest
+     * byte no longer takes part in the hash key, that is:
+     *   hash_shift * MIN_MATCH >= hash_bits
+     */
+
+    long block_start;
+    /* Window position at the beginning of the current output block. Gets
+     * negative when the window is moved backwards.
+     */
+
+    uInt match_length;           /* length of best match */
+    IPos prev_match;             /* previous match */
+    int match_available;         /* set if previous match exists */
+    uInt strstart;               /* start of string to insert */
+    uInt match_start;            /* start of matching string */
+    uInt lookahead;              /* number of valid bytes ahead in window */
+
+    uInt prev_length;
+    /* Length of the best match at previous step. Matches not greater than this
+     * are discarded. This is used in the lazy match evaluation.
+     */
+
+    uInt max_chain_length;
+    /* To speed up deflation, hash chains are never searched beyond this
+     * length.  A higher limit improves compression ratio but degrades the
+     * speed.
+     */
+
+    uInt max_lazy_match;
+    /* Attempt to find a better match only when the current match is strictly
+     * smaller than this value. This mechanism is used only for compression
+     * levels >= 4.
+     */
+#   define max_insert_length  max_lazy_match
+    /* Insert new strings in the hash table only if the match length is not
+     * greater than this length. This saves time but degrades compression.
+     * max_insert_length is used only for compression levels <= 3.
+     */
+
+    int level;    /* compression level (1..9) */
+    int strategy; /* favor or force Huffman coding*/
+
+    uInt good_match;
+    /* Use a faster search when the previous match is longer than this */
+
+    int nice_match; /* Stop searching when current match exceeds this */
+
+                /* used by trees.c: */
+    /* Didn't use ct_data typedef below to suppress compiler warning */
+    struct ct_data_s dyn_ltree[HEAP_SIZE];   /* literal and length tree */
+    struct ct_data_s dyn_dtree[2*D_CODES+1]; /* distance tree */
+    struct ct_data_s bl_tree[2*BL_CODES+1];  /* Huffman tree for bit lengths */
+
+    struct tree_desc_s l_desc;               /* desc. for literal tree */
+    struct tree_desc_s d_desc;               /* desc. for distance tree */
+    struct tree_desc_s bl_desc;              /* desc. for bit length tree */
+
+    ush bl_count[MAX_BITS+1];
+    /* number of codes at each bit length for an optimal tree */
+
+    int heap[2*L_CODES+1];      /* heap used to build the Huffman trees */
+    int heap_len;               /* number of elements in the heap */
+    int heap_max;               /* element of largest frequency */
+    /* The sons of heap[n] are heap[2*n] and heap[2*n+1]. heap[0] is not used.
+     * The same heap array is used to build all trees.
+     */
+
+    uch depth[2*L_CODES+1];
+    /* Depth of each subtree used as tie breaker for trees of equal frequency
+     */
+
+#ifdef LIT_MEM
+#   define LIT_BUFS 5
+    ushf *d_buf;          /* buffer for distances */
+    uchf *l_buf;          /* buffer for literals/lengths */
+#else
+#   define LIT_BUFS 4
+    uchf *sym_buf;        /* buffer for distances and literals/lengths */
+#endif
+
+    uInt  lit_bufsize;
+    /* Size of match buffer for literals/lengths.  There are 4 reasons for
+     * limiting lit_bufsize to 64K:
+     *   - frequencies can be kept in 16 bit counters
+     *   - if compression is not successful for the first block, all input
+     *     data is still in the window so we can still emit a stored block even
+     *     when input comes from standard input.  (This can also be done for
+     *     all blocks if lit_bufsize is not greater than 32K.)
+     *   - if compression is not successful for a file smaller than 64K, we can
+     *     even emit a stored file instead of a stored block (saving 5 bytes).
+     *     This is applicable only for zip (not gzip or zlib).
+     *   - creating new Huffman trees less frequently may not provide fast
+     *     adaptation to changes in the input data statistics. (Take for
+     *     example a binary file with poorly compressible code followed by
+     *     a highly compressible string table.) Smaller buffer sizes give
+     *     fast adaptation but have of course the overhead of transmitting
+     *     trees more frequently.
+     *   - I can't count above 4
+     */
+
+    uInt sym_next;      /* running index in symbol buffer */
+    uInt sym_end;       /* symbol table full when sym_next reaches this */
+
+    ulg opt_len;        /* bit length of current block with optimal trees */
+    ulg static_len;     /* bit length of current block with static trees */
+    uInt matches;       /* number of string matches in current block */
+    uInt insert;        /* bytes at end of window left to insert */
+
+#ifdef ZLIB_DEBUG
+    ulg compressed_len; /* total bit length of compressed file mod 2^32 */
+    ulg bits_sent;      /* bit length of compressed data sent mod 2^32 */
+#endif
+
+    ush bi_buf;
+    /* Output buffer. bits are inserted starting at the bottom (least
+     * significant bits).
+     */
+    int bi_valid;
+    /* Number of valid bits in bi_buf.  All bits above the last valid bit
+     * are always zero.
+     */
+
+    ulg high_water;
+    /* High water mark offset in window for initialized bytes -- bytes above
+     * this are set to zero in order to avoid memory check warnings when
+     * longest match routines access bytes past the input.  This is then
+     * updated to the new high water mark.
+     */
+
+} FAR deflate_state;
+
+/* Output a byte on the stream.
+ * IN assertion: there is enough room in pending_buf.
+ */
+#define put_byte(s, c) {s->pending_buf[s->pending++] = (Bytef)(c);}
+
+
+#define MIN_LOOKAHEAD (MAX_MATCH+MIN_MATCH+1)
+/* Minimum amount of lookahead, except at the end of the input file.
+ * See deflate.c for comments about the MIN_MATCH+1.
+ */
+
+#define MAX_DIST(s)  ((s)->w_size-MIN_LOOKAHEAD)
+/* In order to simplify the code, particularly on 16 bit machines, match
+ * distances are limited to MAX_DIST instead of WSIZE.
+ */
+
+#define WIN_INIT MAX_MATCH
+/* Number of bytes after end of data in window to initialize in order to avoid
+   memory checker errors from longest match routines */
+
+        /* in trees.c */
+void ZLIB_INTERNAL _tr_init(deflate_state *s);
+int ZLIB_INTERNAL _tr_tally(deflate_state *s, unsigned dist, unsigned lc);
+void ZLIB_INTERNAL _tr_flush_block(deflate_state *s, charf *buf,
+                                   ulg stored_len, int last);
+void ZLIB_INTERNAL _tr_flush_bits(deflate_state *s);
+void ZLIB_INTERNAL _tr_align(deflate_state *s);
+void ZLIB_INTERNAL _tr_stored_block(deflate_state *s, charf *buf,
+                                    ulg stored_len, int last);
+
+#define d_code(dist) \
+   ((dist) < 256 ? _dist_code[dist] : _dist_code[256+((dist)>>7)])
+/* Mapping from a distance to a distance code. dist is the distance - 1 and
+ * must not have side effects. _dist_code[256] and _dist_code[257] are never
+ * used.
+ */
+
+#ifndef ZLIB_DEBUG
+/* Inline versions of _tr_tally for speed: */
+
+#if defined(GEN_TREES_H) || !defined(STDC)
+  extern uch ZLIB_INTERNAL _length_code[];
+  extern uch ZLIB_INTERNAL _dist_code[];
+#else
+  extern const uch ZLIB_INTERNAL _length_code[];
+  extern const uch ZLIB_INTERNAL _dist_code[];
+#endif
+
+#ifdef LIT_MEM
+# define _tr_tally_lit(s, c, flush) \
+  { uch cc = (c); \
+    s->d_buf[s->sym_next] = 0; \
+    s->l_buf[s->sym_next++] = cc; \
+    s->dyn_ltree[cc].Freq++; \
+    flush = (s->sym_next == s->sym_end); \
+   }
+# define _tr_tally_dist(s, distance, length, flush) \
+  { uch len = (uch)(length); \
+    ush dist = (ush)(distance); \
+    s->d_buf[s->sym_next] = dist; \
+    s->l_buf[s->sym_next++] = len; \
+    dist--; \
+    s->dyn_ltree[_length_code[len]+LITERALS+1].Freq++; \
+    s->dyn_dtree[d_code(dist)].Freq++; \
+    flush = (s->sym_next == s->sym_end); \
+  }
+#else
+# define _tr_tally_lit(s, c, flush) \
+  { uch cc = (c); \
+    s->sym_buf[s->sym_next++] = 0; \
+    s->sym_buf[s->sym_next++] = 0; \
+    s->sym_buf[s->sym_next++] = cc; \
+    s->dyn_ltree[cc].Freq++; \
+    flush = (s->sym_next == s->sym_end); \
+   }
+# define _tr_tally_dist(s, distance, length, flush) \
+  { uch len = (uch)(length); \
+    ush dist = (ush)(distance); \
+    s->sym_buf[s->sym_next++] = (uch)dist; \
+    s->sym_buf[s->sym_next++] = (uch)(dist >> 8); \
+    s->sym_buf[s->sym_next++] = len; \
+    dist--; \
+    s->dyn_ltree[_length_code[len]+LITERALS+1].Freq++; \
+    s->dyn_dtree[d_code(dist)].Freq++; \
+    flush = (s->sym_next == s->sym_end); \
+  }
+#endif
+#else
+# define _tr_tally_lit(s, c, flush) flush = _tr_tally(s, 0, c)
+# define _tr_tally_dist(s, distance, length, flush) \
+              flush = _tr_tally(s, distance, length)
+#endif
+
+#endif /* DEFLATE_H */

package/.cppjs/build/source/doc/algorithm.txt

@@ -0,0 +1,209 @@
+1. Compression algorithm (deflate)
+
+The deflation algorithm used by gzip (also zip and zlib) is a variation of
+LZ77 (Lempel-Ziv 1977, see reference below). It finds duplicated strings in
+the input data.  The second occurrence of a string is replaced by a
+pointer to the previous string, in the form of a pair (distance,
+length).  Distances are limited to 32K bytes, and lengths are limited
+to 258 bytes. When a string does not occur anywhere in the previous
+32K bytes, it is emitted as a sequence of literal bytes.  (In this
+description, `string' must be taken as an arbitrary sequence of bytes,
+and is not restricted to printable characters.)
+
+Literals or match lengths are compressed with one Huffman tree, and
+match distances are compressed with another tree. The trees are stored
+in a compact form at the start of each block. The blocks can have any
+size (except that the compressed data for one block must fit in
+available memory). A block is terminated when deflate() determines that
+it would be useful to start another block with fresh trees. (This is
+somewhat similar to the behavior of LZW-based _compress_.)
+
+Duplicated strings are found using a hash table. All input strings of
+length 3 are inserted in the hash table. A hash index is computed for
+the next 3 bytes. If the hash chain for this index is not empty, all
+strings in the chain are compared with the current input string, and
+the longest match is selected.
+
+The hash chains are searched starting with the most recent strings, to
+favor small distances and thus take advantage of the Huffman encoding.
+The hash chains are singly linked. There are no deletions from the
+hash chains, the algorithm simply discards matches that are too old.
+
+To avoid a worst-case situation, very long hash chains are arbitrarily
+truncated at a certain length, determined by a runtime option (level
+parameter of deflateInit). So deflate() does not always find the longest
+possible match but generally finds a match which is long enough.
+
+deflate() also defers the selection of matches with a lazy evaluation
+mechanism. After a match of length N has been found, deflate() searches for
+a longer match at the next input byte. If a longer match is found, the
+previous match is truncated to a length of one (thus producing a single
+literal byte) and the process of lazy evaluation begins again. Otherwise,
+the original match is kept, and the next match search is attempted only N
+steps later.
+
+The lazy match evaluation is also subject to a runtime parameter. If
+the current match is long enough, deflate() reduces the search for a longer
+match, thus speeding up the whole process. If compression ratio is more
+important than speed, deflate() attempts a complete second search even if
+the first match is already long enough.
+
+The lazy match evaluation is not performed for the fastest compression
+modes (level parameter 1 to 3). For these fast modes, new strings
+are inserted in the hash table only when no match was found, or
+when the match is not too long. This degrades the compression ratio
+but saves time since there are both fewer insertions and fewer searches.
+
+
+2. Decompression algorithm (inflate)
+
+2.1 Introduction
+
+The key question is how to represent a Huffman code (or any prefix code) so
+that you can decode fast.  The most important characteristic is that shorter
+codes are much more common than longer codes, so pay attention to decoding the
+short codes fast, and let the long codes take longer to decode.
+
+inflate() sets up a first level table that covers some number of bits of
+input less than the length of longest code.  It gets that many bits from the
+stream, and looks it up in the table.  The table will tell if the next
+code is that many bits or less and how many, and if it is, it will tell
+the value, else it will point to the next level table for which inflate()
+grabs more bits and tries to decode a longer code.
+
+How many bits to make the first lookup is a tradeoff between the time it
+takes to decode and the time it takes to build the table.  If building the
+table took no time (and if you had infinite memory), then there would only
+be a first level table to cover all the way to the longest code.  However,
+building the table ends up taking a lot longer for more bits since short
+codes are replicated many times in such a table.  What inflate() does is
+simply to make the number of bits in the first table a variable, and then
+to set that variable for the maximum speed.
+
+For inflate, which has 286 possible codes for the literal/length tree, the size
+of the first table is nine bits.  Also the distance trees have 30 possible
+values, and the size of the first table is six bits.  Note that for each of
+those cases, the table ended up one bit longer than the ``average'' code
+length, i.e. the code length of an approximately flat code which would be a
+little more than eight bits for 286 symbols and a little less than five bits
+for 30 symbols.
+
+
+2.2 More details on the inflate table lookup
+
+Ok, you want to know what this cleverly obfuscated inflate tree actually
+looks like.  You are correct that it's not a Huffman tree.  It is simply a
+lookup table for the first, let's say, nine bits of a Huffman symbol.  The
+symbol could be as short as one bit or as long as 15 bits.  If a particular
+symbol is shorter than nine bits, then that symbol's translation is duplicated
+in all those entries that start with that symbol's bits.  For example, if the
+symbol is four bits, then it's duplicated 32 times in a nine-bit table.  If a
+symbol is nine bits long, it appears in the table once.
+
+If the symbol is longer than nine bits, then that entry in the table points
+to another similar table for the remaining bits.  Again, there are duplicated
+entries as needed.  The idea is that most of the time the symbol will be short
+and there will only be one table look up.  (That's whole idea behind data
+compression in the first place.)  For the less frequent long symbols, there
+will be two lookups.  If you had a compression method with really long
+symbols, you could have as many levels of lookups as is efficient.  For
+inflate, two is enough.
+
+So a table entry either points to another table (in which case nine bits in
+the above example are gobbled), or it contains the translation for the symbol
+and the number of bits to gobble.  Then you start again with the next
+ungobbled bit.
+
+You may wonder: why not just have one lookup table for how ever many bits the
+longest symbol is?  The reason is that if you do that, you end up spending
+more time filling in duplicate symbol entries than you do actually decoding.
+At least for deflate's output that generates new trees every several 10's of
+kbytes.  You can imagine that filling in a 2^15 entry table for a 15-bit code
+would take too long if you're only decoding several thousand symbols.  At the
+other extreme, you could make a new table for every bit in the code.  In fact,
+that's essentially a Huffman tree.  But then you spend too much time
+traversing the tree while decoding, even for short symbols.
+
+So the number of bits for the first lookup table is a trade of the time to
+fill out the table vs. the time spent looking at the second level and above of
+the table.
+
+Here is an example, scaled down:
+
+The code being decoded, with 10 symbols, from 1 to 6 bits long:
+
+A: 0
+B: 10
+C: 1100
+D: 11010
+E: 11011
+F: 11100
+G: 11101
+H: 11110
+I: 111110
+J: 111111
+
+Let's make the first table three bits long (eight entries):
+
+000: A,1
+001: A,1
+010: A,1
+011: A,1
+100: B,2
+101: B,2
+110: -> table X (gobble 3 bits)
+111: -> table Y (gobble 3 bits)
+
+Each entry is what the bits decode as and how many bits that is, i.e. how
+many bits to gobble.  Or the entry points to another table, with the number of
+bits to gobble implicit in the size of the table.
+
+Table X is two bits long since the longest code starting with 110 is five bits
+long:
+
+00: C,1
+01: C,1
+10: D,2
+11: E,2
+
+Table Y is three bits long since the longest code starting with 111 is six
+bits long:
+
+000: F,2
+001: F,2
+010: G,2
+011: G,2
+100: H,2
+101: H,2
+110: I,3
+111: J,3
+
+So what we have here are three tables with a total of 20 entries that had to
+be constructed.  That's compared to 64 entries for a single table.  Or
+compared to 16 entries for a Huffman tree (six two entry tables and one four
+entry table).  Assuming that the code ideally represents the probability of
+the symbols, it takes on the average 1.25 lookups per symbol.  That's compared
+to one lookup for the single table, or 1.66 lookups per symbol for the
+Huffman tree.
+
+There, I think that gives you a picture of what's going on.  For inflate, the
+meaning of a particular symbol is often more than just a letter.  It can be a
+byte (a "literal"), or it can be either a length or a distance which
+indicates a base value and a number of bits to fetch after the code that is
+added to the base value.  Or it might be the special end-of-block code.  The
+data structures created in inftrees.c try to encode all that information
+compactly in the tables.
+
+
+Jean-loup Gailly        Mark Adler
+jloup@gzip.org          madler@alumni.caltech.edu
+
+
+References:
+
+[LZ77] Ziv J., Lempel A., ``A Universal Algorithm for Sequential Data
+Compression,'' IEEE Transactions on Information Theory, Vol. 23, No. 3,
+pp. 337-343.
+
+``DEFLATE Compressed Data Format Specification'' available in
+http://tools.ietf.org/html/rfc1951