summaryrefslogtreecommitdiff
path: root/src/commonlib/lz4.c.inc
blob: b3be4e5b443b618a704b9b8ec6e1106f530a4d10 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
/*
   LZ4 - Fast LZ compression algorithm
   Copyright (C) 2011-2015, Yann Collet.

   BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)

   Redistribution and use in source and binary forms, with or without
   modification, are permitted provided that the following conditions are
   met:

       * Redistributions of source code must retain the above copyright
   notice, this list of conditions and the following disclaimer.
       * Redistributions in binary form must reproduce the above
   copyright notice, this list of conditions and the following disclaimer
   in the documentation and/or other materials provided with the
   distribution.

   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

   You can contact the author at :
   - LZ4 source repository : https://github.com/Cyan4973/lz4
   - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c
*/


/**************************************
*  Reading and writing into memory
**************************************/

/* customized variant of memcpy, which can overwrite up to 7 bytes beyond dstEnd */
static void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd)
{
    BYTE* d = (BYTE*)dstPtr;
    const BYTE* s = (const BYTE*)srcPtr;
    BYTE* const e = (BYTE*)dstEnd;

#if 0
    const size_t l2 = 8 - (((size_t)d) & (sizeof(void*)-1));
    LZ4_copy8(d,s); if (d>e-9) return;
    d+=l2; s+=l2;
#endif /* join to align */

    do { LZ4_copy8(d,s); d+=8; s+=8; } while (d<e);
}


/**************************************
*  Common Constants
**************************************/
#define MINMATCH 4

#define WILDCOPYLENGTH 8
#define LASTLITERALS 5
#define MFLIMIT (WILDCOPYLENGTH+MINMATCH)
static const int LZ4_minLength = (MFLIMIT+1);

#define KB *(1 <<10)
#define MB *(1 <<20)
#define GB *(1U<<30)

#define MAXD_LOG 16
#define MAX_DISTANCE ((1 << MAXD_LOG) - 1)

#define ML_BITS  4
#define ML_MASK  ((1U<<ML_BITS)-1)
#define RUN_BITS (8-ML_BITS)
#define RUN_MASK ((1U<<RUN_BITS)-1)


/**************************************
*  Local Structures and types
**************************************/
typedef enum { noDict = 0, withPrefix64k, usingExtDict } dict_directive;
typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
typedef enum { full = 0, partial = 1 } earlyEnd_directive;



/*******************************
*  Decompression functions
*******************************/
/*
 * This generic decompression function cover all use cases.
 * It shall be instantiated several times, using different sets of directives
 * Note that it is essential this generic function is really inlined,
 * in order to remove useless branches during compilation optimization.
 */
FORCE_INLINE int LZ4_decompress_generic(
                 const char* const source,
                 char* const dest,
                 int inputSize,
                 int outputSize,         /* If endOnInput==endOnInputSize, this value is the max size of Output Buffer. */

                 int endOnInput,         /* endOnOutputSize, endOnInputSize */
                 int partialDecoding,    /* full, partial */
                 int targetOutputSize,   /* only used if partialDecoding==partial */
                 int dict,               /* noDict, withPrefix64k, usingExtDict */
                 const BYTE* const lowPrefix,  /* == dest if dict == noDict */
                 const BYTE* const dictStart,  /* only if dict==usingExtDict */
                 const size_t dictSize         /* note : = 0 if noDict */
                 )
{
    /* Local Variables */
    const BYTE* ip = (const BYTE*) source;
    const BYTE* const iend = ip + inputSize;

    BYTE* op = (BYTE*) dest;
    BYTE* const oend = op + outputSize;
    BYTE* cpy;
    BYTE* oexit = op + targetOutputSize;
    const BYTE* const lowLimit = lowPrefix - dictSize;

    const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize;
    const unsigned dec32table[] = {4, 1, 2, 1, 4, 4, 4, 4};
    const int dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3};

    const int safeDecode = (endOnInput==endOnInputSize);
    const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB)));
    const int inPlaceDecode = ((ip >= op) && (ip < oend));


    /* Special cases */
    if ((partialDecoding) && (oexit> oend-MFLIMIT)) oexit = oend-MFLIMIT;                         /* targetOutputSize too high => decode everything */
    if ((endOnInput) && (unlikely(outputSize==0))) return ((inputSize==1) && (*ip==0)) ? 0 : -1;  /* Empty output buffer */
    if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1);


    /* Main Loop */
    while (1)
    {
        unsigned token;
        size_t length;
        const BYTE* match;
        size_t offset;

        if (unlikely((inPlaceDecode) && (op + WILDCOPYLENGTH > ip))) goto _output_error;   /* output stream ran over input stream */

        /* get literal length */
        token = *ip++;
        if ((length=(token>>ML_BITS)) == RUN_MASK)
        {
            unsigned s;
            do
            {
                s = *ip++;
                length += s;
            }
            while ( likely(endOnInput ? ip<iend-RUN_MASK : 1) && (s==255) );
            if ((safeDecode) && unlikely((size_t)(op+length)<(size_t)(op))) goto _output_error;   /* overflow detection */
            if ((safeDecode) && unlikely((size_t)(ip+length)<(size_t)(ip))) goto _output_error;   /* overflow detection */
        }

        /* copy literals */
        cpy = op+length;
        if (((endOnInput) && ((cpy>(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) )
            || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)))
        {
            if (partialDecoding)
            {
                if (cpy > oend) goto _output_error;                           /* Error : write attempt beyond end of output buffer */
                if ((endOnInput) && (ip+length > iend)) goto _output_error;   /* Error : read attempt beyond end of input buffer */
            }
            else
            {
                if ((!endOnInput) && (cpy != oend)) goto _output_error;       /* Error : block decoding must stop exactly there */
                if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) goto _output_error;   /* Error : input must be consumed */
            }
            memmove(op, ip, length);
            ip += length;
            op += length;
            break;     /* Necessarily EOF, due to parsing restrictions */
        }
        LZ4_wildCopy(op, ip, cpy);
        ip += length; op = cpy;

        /* get offset */
        offset = LZ4_readLE16(ip); ip+=2;
        match = op - offset;
        if ((checkOffset) && (unlikely(match < lowLimit))) goto _output_error;   /* Error : offset outside buffers */

        /* get matchlength */
        length = token & ML_MASK;
        if (length == ML_MASK)
        {
            unsigned s;
            do
            {
                if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error;
                s = *ip++;
                length += s;
            } while (s==255);
            if ((safeDecode) && unlikely((size_t)(op+length)<(size_t)op)) goto _output_error;   /* overflow detection */
        }
        length += MINMATCH;

        /* check external dictionary */
        if ((dict==usingExtDict) && (match < lowPrefix))
        {
            if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error;   /* doesn't respect parsing restriction */

            if (length <= (size_t)(lowPrefix-match))
            {
                /* match can be copied as a single segment from external dictionary */
                match = dictEnd - (lowPrefix-match);
                memmove(op, match, length); op += length;
            }
            else
            {
                /* match encompass external dictionary and current block */
                size_t copySize = (size_t)(lowPrefix-match);
                memcpy(op, dictEnd - copySize, copySize);
                op += copySize;
                copySize = length - copySize;
                if (copySize > (size_t)(op-lowPrefix))   /* overlap copy */
                {
                    BYTE* const endOfMatch = op + copySize;
                    const BYTE* copyFrom = lowPrefix;
                    while (op < endOfMatch) *op++ = *copyFrom++;
                }
                else
                {
                    memcpy(op, lowPrefix, copySize);
                    op += copySize;
                }
            }
            continue;
        }

        /* copy match within block */
        cpy = op + length;
        if (unlikely(offset<8))
        {
            const int dec64 = dec64table[offset];
            op[0] = match[0];
            op[1] = match[1];
            op[2] = match[2];
            op[3] = match[3];
            match += dec32table[offset];
            memcpy(op+4, match, 4);
            match -= dec64;
        } else { LZ4_copy8(op, match); match+=8; }
        op += 8;

        if (unlikely(cpy>oend-12))
        {
            BYTE* const oCopyLimit = oend-(WILDCOPYLENGTH-1);
            if (cpy > oend-LASTLITERALS) goto _output_error;    /* Error : last LASTLITERALS bytes must be literals (uncompressed) */
            if (op < oCopyLimit)
            {
                LZ4_wildCopy(op, match, oCopyLimit);
                match += oCopyLimit - op;
                op = oCopyLimit;
            }
            while (op<cpy) *op++ = *match++;
        }
        else
            LZ4_wildCopy(op, match, cpy);
        op=cpy;   /* correction */
    }

    /* end of decoding */
    if (endOnInput)
       return (int) (((char*)op)-dest);     /* Nb of output bytes decoded */
    else
       return (int) (((const char*)ip)-source);   /* Nb of input bytes read */

    /* Overflow error detected */
_output_error:
    return (int) (-(((const char*)ip)-source))-1;
}