1 // SPDX-License-Identifier: Zlib
2 /* inftrees.c -- generate Huffman trees for efficient decoding
3 * Copyright (C) 1995-2022 Mark Adler
4 * For conditions of distribution and use, see copyright notice in zlib.h
5 */
6
7 #include "zutil.h"
8 #include "inftrees.h"
9
10 #define MAXBITS 15
11
12 const char inflate_copyright[] =
13 " inflate 1.2.12 Copyright 1995-2022 Mark Adler ";
14 /*
15 If you use the zlib library in a product, an acknowledgment is welcome
16 in the documentation of your product. If for some reason you cannot
17 include such an acknowledgment, I would appreciate that you keep this
18 copyright string in the executable of your product.
19 */
20
21 /*
22 Build a set of tables to decode the provided canonical Huffman code.
23 The code lengths are lens[0..codes-1]. The result starts at *table,
24 whose indices are 0..2^bits-1. work is a writable array of at least
25 lens shorts, which is used as a work area. type is the type of code
26 to be generated, CODES, LENS, or DISTS. On return, zero is success,
27 -1 is an invalid code, and +1 means that ENOUGH isn't enough. table
28 on return points to the next available entry's address. bits is the
29 requested root table index bits, and on return it is the actual root
30 table index bits. It will differ if the request is greater than the
31 longest code or if it is less than the shortest code.
32 */
inflate_table(type,lens,codes,table,bits,work)33 int ZLIB_INTERNAL inflate_table(type, lens, codes, table, bits, work)
34 codetype type;
35 unsigned short FAR *lens;
36 unsigned codes;
37 code FAR * FAR *table;
38 unsigned FAR *bits;
39 unsigned short FAR *work;
40 {
41 unsigned len; /* a code's length in bits */
42 unsigned sym; /* index of code symbols */
43 unsigned min, max; /* minimum and maximum code lengths */
44 unsigned root; /* number of index bits for root table */
45 unsigned curr; /* number of index bits for current table */
46 unsigned drop; /* code bits to drop for sub-table */
47 int left; /* number of prefix codes available */
48 unsigned used; /* code entries in table used */
49 unsigned huff; /* Huffman code */
50 unsigned incr; /* for incrementing code, index */
51 unsigned fill; /* index for replicating entries */
52 unsigned low; /* low bits for current root entry */
53 unsigned mask; /* mask for low root bits */
54 code here; /* table entry for duplication */
55 code FAR *next; /* next available space in table */
56 const unsigned short FAR *base; /* base value table to use */
57 const unsigned short FAR *extra; /* extra bits table to use */
58 unsigned match; /* use base and extra for symbol >= match */
59 unsigned short count[MAXBITS+1]; /* number of codes of each length */
60 unsigned short offs[MAXBITS+1]; /* offsets in table for each length */
61 static const unsigned short lbase[31] = { /* Length codes 257..285 base */
62 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17, 19, 23, 27, 31,
63 35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258, 0, 0};
64 static const unsigned short lext[31] = { /* Length codes 257..285 extra */
65 16, 16, 16, 16, 16, 16, 16, 16, 17, 17, 17, 17, 18, 18, 18, 18,
66 19, 19, 19, 19, 20, 20, 20, 20, 21, 21, 21, 21, 16, 199, 202};
67 static const unsigned short dbase[32] = { /* Distance codes 0..29 base */
68 1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193,
69 257, 385, 513, 769, 1025, 1537, 2049, 3073, 4097, 6145,
70 8193, 12289, 16385, 24577, 0, 0};
71 static const unsigned short dext[32] = { /* Distance codes 0..29 extra */
72 16, 16, 16, 16, 17, 17, 18, 18, 19, 19, 20, 20, 21, 21, 22, 22,
73 23, 23, 24, 24, 25, 25, 26, 26, 27, 27,
74 28, 28, 29, 29, 64, 64};
75
76 /*
77 Process a set of code lengths to create a canonical Huffman code. The
78 code lengths are lens[0..codes-1]. Each length corresponds to the
79 symbols 0..codes-1. The Huffman code is generated by first sorting the
80 symbols by length from short to long, and retaining the symbol order
81 for codes with equal lengths. Then the code starts with all zero bits
82 for the first code of the shortest length, and the codes are integer
83 increments for the same length, and zeros are appended as the length
84 increases. For the deflate format, these bits are stored backwards
85 from their more natural integer increment ordering, and so when the
86 decoding tables are built in the large loop below, the integer codes
87 are incremented backwards.
88
89 This routine assumes, but does not check, that all of the entries in
90 lens[] are in the range 0..MAXBITS. The caller must assure this.
91 1..MAXBITS is interpreted as that code length. zero means that that
92 symbol does not occur in this code.
93
94 The codes are sorted by computing a count of codes for each length,
95 creating from that a table of starting indices for each length in the
96 sorted table, and then entering the symbols in order in the sorted
97 table. The sorted table is work[], with that space being provided by
98 the caller.
99
100 The length counts are used for other purposes as well, i.e. finding
101 the minimum and maximum length codes, determining if there are any
102 codes at all, checking for a valid set of lengths, and looking ahead
103 at length counts to determine sub-table sizes when building the
104 decoding tables.
105 */
106
107 /* accumulate lengths for codes (assumes lens[] all in 0..MAXBITS) */
108 for (len = 0; len <= MAXBITS; len++)
109 count[len] = 0;
110 for (sym = 0; sym < codes; sym++)
111 count[lens[sym]]++;
112
113 /* bound code lengths, force root to be within code lengths */
114 root = *bits;
115 for (max = MAXBITS; max >= 1; max--)
116 if (count[max] != 0) break;
117 if (root > max) root = max;
118 if (max == 0) { /* no symbols to code at all */
119 here.op = (unsigned char)64; /* invalid code marker */
120 here.bits = (unsigned char)1;
121 here.val = (unsigned short)0;
122 *(*table)++ = here; /* make a table to force an error */
123 *(*table)++ = here;
124 *bits = 1;
125 return 0; /* no symbols, but wait for decoding to report error */
126 }
127 for (min = 1; min < max; min++)
128 if (count[min] != 0) break;
129 if (root < min) root = min;
130
131 /* check for an over-subscribed or incomplete set of lengths */
132 left = 1;
133 for (len = 1; len <= MAXBITS; len++) {
134 left <<= 1;
135 left -= count[len];
136 if (left < 0) return -1; /* over-subscribed */
137 }
138 if (left > 0 && (type == CODES || max != 1))
139 return -1; /* incomplete set */
140
141 /* generate offsets into symbol table for each length for sorting */
142 offs[1] = 0;
143 for (len = 1; len < MAXBITS; len++)
144 offs[len + 1] = offs[len] + count[len];
145
146 /* sort symbols by length, by symbol order within each length */
147 for (sym = 0; sym < codes; sym++)
148 if (lens[sym] != 0) work[offs[lens[sym]]++] = (unsigned short)sym;
149
150 /*
151 Create and fill in decoding tables. In this loop, the table being
152 filled is at next and has curr index bits. The code being used is huff
153 with length len. That code is converted to an index by dropping drop
154 bits off of the bottom. For codes where len is less than drop + curr,
155 those top drop + curr - len bits are incremented through all values to
156 fill the table with replicated entries.
157
158 root is the number of index bits for the root table. When len exceeds
159 root, sub-tables are created pointed to by the root entry with an index
160 of the low root bits of huff. This is saved in low to check for when a
161 new sub-table should be started. drop is zero when the root table is
162 being filled, and drop is root when sub-tables are being filled.
163
164 When a new sub-table is needed, it is necessary to look ahead in the
165 code lengths to determine what size sub-table is needed. The length
166 counts are used for this, and so count[] is decremented as codes are
167 entered in the tables.
168
169 used keeps track of how many table entries have been allocated from the
170 provided *table space. It is checked for LENS and DIST tables against
171 the constants ENOUGH_LENS and ENOUGH_DISTS to guard against changes in
172 the initial root table size constants. See the comments in inftrees.h
173 for more information.
174
175 sym increments through all symbols, and the loop terminates when
176 all codes of length max, i.e. all codes, have been processed. This
177 routine permits incomplete codes, so another loop after this one fills
178 in the rest of the decoding tables with invalid code markers.
179 */
180
181 /* set up for code type */
182 switch (type) {
183 case CODES:
184 base = extra = work; /* dummy value--not used */
185 match = 20;
186 break;
187 case LENS:
188 base = lbase;
189 extra = lext;
190 match = 257;
191 break;
192 default: /* DISTS */
193 base = dbase;
194 extra = dext;
195 match = 0;
196 }
197
198 /* initialize state for loop */
199 huff = 0; /* starting code */
200 sym = 0; /* starting code symbol */
201 len = min; /* starting code length */
202 next = *table; /* current table to fill in */
203 curr = root; /* current table index bits */
204 drop = 0; /* current bits to drop from code for index */
205 low = (unsigned)(-1); /* trigger new sub-table when len > root */
206 used = 1U << root; /* use root table entries */
207 mask = used - 1; /* mask for comparing low */
208
209 /* check available table space */
210 if ((type == LENS && used > ENOUGH_LENS) ||
211 (type == DISTS && used > ENOUGH_DISTS))
212 return 1;
213
214 /* process all codes and make table entries */
215 for (;;) {
216 /* create table entry */
217 here.bits = (unsigned char)(len - drop);
218 if (work[sym] + 1U < match) {
219 here.op = (unsigned char)0;
220 here.val = work[sym];
221 }
222 else if (work[sym] >= match) {
223 here.op = (unsigned char)(extra[work[sym] - match]);
224 here.val = base[work[sym] - match];
225 }
226 else {
227 here.op = (unsigned char)(32 + 64); /* end of block */
228 here.val = 0;
229 }
230
231 /* replicate for those indices with low len bits equal to huff */
232 incr = 1U << (len - drop);
233 fill = 1U << curr;
234 min = fill; /* save offset to next table */
235 do {
236 fill -= incr;
237 next[(huff >> drop) + fill] = here;
238 } while (fill != 0);
239
240 /* backwards increment the len-bit code huff */
241 incr = 1U << (len - 1);
242 while (huff & incr)
243 incr >>= 1;
244 if (incr != 0) {
245 huff &= incr - 1;
246 huff += incr;
247 }
248 else
249 huff = 0;
250
251 /* go to next symbol, update count, len */
252 sym++;
253 if (--(count[len]) == 0) {
254 if (len == max) break;
255 len = lens[work[sym]];
256 }
257
258 /* create new sub-table if needed */
259 if (len > root && (huff & mask) != low) {
260 /* if first time, transition to sub-tables */
261 if (drop == 0)
262 drop = root;
263
264 /* increment past last table */
265 next += min; /* here min is 1 << curr */
266
267 /* determine length of next table */
268 curr = len - drop;
269 left = (int)(1 << curr);
270 while (curr + drop < max) {
271 left -= count[curr + drop];
272 if (left <= 0) break;
273 curr++;
274 left <<= 1;
275 }
276
277 /* check for enough space */
278 used += 1U << curr;
279 if ((type == LENS && used > ENOUGH_LENS) ||
280 (type == DISTS && used > ENOUGH_DISTS))
281 return 1;
282
283 /* point entry in root table to sub-table */
284 low = huff & mask;
285 (*table)[low].op = (unsigned char)curr;
286 (*table)[low].bits = (unsigned char)root;
287 (*table)[low].val = (unsigned short)(next - *table);
288 }
289 }
290
291 /* fill in remaining table entry if code is incomplete (guaranteed to have
292 at most one remaining entry, since if the code is incomplete, the
293 maximum code length that was allowed to get this far is one bit) */
294 if (huff != 0) {
295 here.op = (unsigned char)64; /* invalid code marker */
296 here.bits = (unsigned char)(len - drop);
297 here.val = (unsigned short)0;
298 next[huff] = here;
299 }
300
301 /* set return parameters */
302 *table += used;
303 *bits = root;
304 return 0;
305 }
306