jk-ferret 0.11.8.2

data/ext/BZLIB_huffman.c

@@ -0,0 +1,205 @@
+
+/*-------------------------------------------------------------*/
+/*--- Huffman coding low-level stuff                        ---*/
+/*---                                             huffman.c ---*/
+/*-------------------------------------------------------------*/
+
+/* ------------------------------------------------------------------
+   This file is part of bzip2/libbzip2, a program and library for
+   lossless, block-sorting data compression.
+
+   bzip2/libbzip2 version 1.0.4 of 20 December 2006
+   Copyright (C) 1996-2006 Julian Seward <jseward@bzip.org>
+
+   Please read the WARNING, DISCLAIMER and PATENTS sections in the 
+   README file.
+
+   This program is released under the terms of the license contained
+   in the file LICENSE.
+   ------------------------------------------------------------------ */
+
+
+#include "bzlib_private.h"
+
+/*---------------------------------------------------*/
+#define WEIGHTOF(zz0)  ((zz0) & 0xffffff00)
+#define DEPTHOF(zz1)   ((zz1) & 0x000000ff)
+#define MYMAX(zz2,zz3) ((zz2) > (zz3) ? (zz2) : (zz3))
+
+#define ADDWEIGHTS(zw1,zw2)                           \
+   (WEIGHTOF(zw1)+WEIGHTOF(zw2)) |                    \
+   (1 + MYMAX(DEPTHOF(zw1),DEPTHOF(zw2)))
+
+#define UPHEAP(z)                                     \
+{                                                     \
+   Int32 zz, tmp;                                     \
+   zz = z; tmp = heap[zz];                            \
+   while (weight[tmp] < weight[heap[zz >> 1]]) {      \
+      heap[zz] = heap[zz >> 1];                       \
+      zz >>= 1;                                       \
+   }                                                  \
+   heap[zz] = tmp;                                    \
+}
+
+#define DOWNHEAP(z)                                   \
+{                                                     \
+   Int32 zz, yy, tmp;                                 \
+   zz = z; tmp = heap[zz];                            \
+   while (True) {                                     \
+      yy = zz << 1;                                   \
+      if (yy > nHeap) break;                          \
+      if (yy < nHeap &&                               \
+          weight[heap[yy+1]] < weight[heap[yy]])      \
+         yy++;                                        \
+      if (weight[tmp] < weight[heap[yy]]) break;      \
+      heap[zz] = heap[yy];                            \
+      zz = yy;                                        \
+   }                                                  \
+   heap[zz] = tmp;                                    \
+}
+
+
+/*---------------------------------------------------*/
+void BZ2_hbMakeCodeLengths ( UChar *len, 
+                             Int32 *freq,
+                             Int32 alphaSize,
+                             Int32 maxLen )
+{
+   /*--
+      Nodes and heap entries run from 1.  Entry 0
+      for both the heap and nodes is a sentinel.
+   --*/
+   Int32 nNodes, nHeap, n1, n2, i, j, k;
+   Bool  tooLong;
+
+   Int32 heap   [ BZ_MAX_ALPHA_SIZE + 2 ];
+   Int32 weight [ BZ_MAX_ALPHA_SIZE * 2 ];
+   Int32 parent [ BZ_MAX_ALPHA_SIZE * 2 ]; 
+
+   for (i = 0; i < alphaSize; i++)
+      weight[i+1] = (freq[i] == 0 ? 1 : freq[i]) << 8;
+
+   while (True) {
+
+      nNodes = alphaSize;
+      nHeap = 0;
+
+      heap[0] = 0;
+      weight[0] = 0;
+      parent[0] = -2;
+
+      for (i = 1; i <= alphaSize; i++) {
+         parent[i] = -1;
+         nHeap++;
+         heap[nHeap] = i;
+         UPHEAP(nHeap);
+      }
+
+      AssertH( nHeap < (BZ_MAX_ALPHA_SIZE+2), 2001 );
+   
+      while (nHeap > 1) {
+         n1 = heap[1]; heap[1] = heap[nHeap]; nHeap--; DOWNHEAP(1);
+         n2 = heap[1]; heap[1] = heap[nHeap]; nHeap--; DOWNHEAP(1);
+         nNodes++;
+         parent[n1] = parent[n2] = nNodes;
+         weight[nNodes] = ADDWEIGHTS(weight[n1], weight[n2]);
+         parent[nNodes] = -1;
+         nHeap++;
+         heap[nHeap] = nNodes;
+         UPHEAP(nHeap);
+      }
+
+      AssertH( nNodes < (BZ_MAX_ALPHA_SIZE * 2), 2002 );
+
+      tooLong = False;
+      for (i = 1; i <= alphaSize; i++) {
+         j = 0;
+         k = i;
+         while (parent[k] >= 0) { k = parent[k]; j++; }
+         len[i-1] = j;
+         if (j > maxLen) tooLong = True;
+      }
+      
+      if (! tooLong) break;
+
+      /* 17 Oct 04: keep-going condition for the following loop used
+         to be 'i < alphaSize', which missed the last element,
+         theoretically leading to the possibility of the compressor
+         looping.  However, this count-scaling step is only needed if
+         one of the generated Huffman code words is longer than
+         maxLen, which up to and including version 1.0.2 was 20 bits,
+         which is extremely unlikely.  In version 1.0.3 maxLen was
+         changed to 17 bits, which has minimal effect on compression
+         ratio, but does mean this scaling step is used from time to
+         time, enough to verify that it works.
+
+         This means that bzip2-1.0.3 and later will only produce
+         Huffman codes with a maximum length of 17 bits.  However, in
+         order to preserve backwards compatibility with bitstreams
+         produced by versions pre-1.0.3, the decompressor must still
+         handle lengths of up to 20. */
+
+      for (i = 1; i <= alphaSize; i++) {
+         j = weight[i] >> 8;
+         j = 1 + (j / 2);
+         weight[i] = j << 8;
+      }
+   }
+}
+
+
+/*---------------------------------------------------*/
+void BZ2_hbAssignCodes ( Int32 *code,
+                         UChar *length,
+                         Int32 minLen,
+                         Int32 maxLen,
+                         Int32 alphaSize )
+{
+   Int32 n, vec, i;
+
+   vec = 0;
+   for (n = minLen; n <= maxLen; n++) {
+      for (i = 0; i < alphaSize; i++)
+         if (length[i] == n) { code[i] = vec; vec++; };
+      vec <<= 1;
+   }
+}
+
+
+/*---------------------------------------------------*/
+void BZ2_hbCreateDecodeTables ( Int32 *limit,
+                                Int32 *base,
+                                Int32 *perm,
+                                UChar *length,
+                                Int32 minLen,
+                                Int32 maxLen,
+                                Int32 alphaSize )
+{
+   Int32 pp, i, j, vec;
+
+   pp = 0;
+   for (i = minLen; i <= maxLen; i++)
+      for (j = 0; j < alphaSize; j++)
+         if (length[j] == i) { perm[pp] = j; pp++; };
+
+   for (i = 0; i < BZ_MAX_CODE_LEN; i++) base[i] = 0;
+   for (i = 0; i < alphaSize; i++) base[length[i]+1]++;
+
+   for (i = 1; i < BZ_MAX_CODE_LEN; i++) base[i] += base[i-1];
+
+   for (i = 0; i < BZ_MAX_CODE_LEN; i++) limit[i] = 0;
+   vec = 0;
+
+   for (i = minLen; i <= maxLen; i++) {
+      vec += (base[i+1] - base[i]);
+      limit[i] = vec-1;
+      vec <<= 1;
+   }
+   for (i = minLen + 1; i <= maxLen; i++)
+      base[i] = ((limit[i-1] + 1) << 1) - base[i];
+}
+
+
+/*-------------------------------------------------------------*/
+/*--- end                                         huffman.c ---*/
+/*-------------------------------------------------------------*/

data/ext/BZLIB_randtable.c

@@ -0,0 +1,84 @@
+
+/*-------------------------------------------------------------*/
+/*--- Table for randomising repetitive blocks               ---*/
+/*---                                           randtable.c ---*/
+/*-------------------------------------------------------------*/
+
+/* ------------------------------------------------------------------
+   This file is part of bzip2/libbzip2, a program and library for
+   lossless, block-sorting data compression.
+
+   bzip2/libbzip2 version 1.0.4 of 20 December 2006
+   Copyright (C) 1996-2006 Julian Seward <jseward@bzip.org>
+
+   Please read the WARNING, DISCLAIMER and PATENTS sections in the 
+   README file.
+
+   This program is released under the terms of the license contained
+   in the file LICENSE.
+   ------------------------------------------------------------------ */
+
+
+#include "bzlib_private.h"
+
+
+/*---------------------------------------------*/
+Int32 BZ2_rNums[512] = { 
+   619, 720, 127, 481, 931, 816, 813, 233, 566, 247, 
+   985, 724, 205, 454, 863, 491, 741, 242, 949, 214, 
+   733, 859, 335, 708, 621, 574, 73, 654, 730, 472, 
+   419, 436, 278, 496, 867, 210, 399, 680, 480, 51, 
+   878, 465, 811, 169, 869, 675, 611, 697, 867, 561, 
+   862, 687, 507, 283, 482, 129, 807, 591, 733, 623, 
+   150, 238, 59, 379, 684, 877, 625, 169, 643, 105, 
+   170, 607, 520, 932, 727, 476, 693, 425, 174, 647, 
+   73, 122, 335, 530, 442, 853, 695, 249, 445, 515, 
+   909, 545, 703, 919, 874, 474, 882, 500, 594, 612, 
+   641, 801, 220, 162, 819, 984, 589, 513, 495, 799, 
+   161, 604, 958, 533, 221, 400, 386, 867, 600, 782, 
+   382, 596, 414, 171, 516, 375, 682, 485, 911, 276, 
+   98, 553, 163, 354, 666, 933, 424, 341, 533, 870, 
+   227, 730, 475, 186, 263, 647, 537, 686, 600, 224, 
+   469, 68, 770, 919, 190, 373, 294, 822, 808, 206, 
+   184, 943, 795, 384, 383, 461, 404, 758, 839, 887, 
+   715, 67, 618, 276, 204, 918, 873, 777, 604, 560, 
+   951, 160, 578, 722, 79, 804, 96, 409, 713, 940, 
+   652, 934, 970, 447, 318, 353, 859, 672, 112, 785, 
+   645, 863, 803, 350, 139, 93, 354, 99, 820, 908, 
+   609, 772, 154, 274, 580, 184, 79, 626, 630, 742, 
+   653, 282, 762, 623, 680, 81, 927, 626, 789, 125, 
+   411, 521, 938, 300, 821, 78, 343, 175, 128, 250, 
+   170, 774, 972, 275, 999, 639, 495, 78, 352, 126, 
+   857, 956, 358, 619, 580, 124, 737, 594, 701, 612, 
+   669, 112, 134, 694, 363, 992, 809, 743, 168, 974, 
+   944, 375, 748, 52, 600, 747, 642, 182, 862, 81, 
+   344, 805, 988, 739, 511, 655, 814, 334, 249, 515, 
+   897, 955, 664, 981, 649, 113, 974, 459, 893, 228, 
+   433, 837, 553, 268, 926, 240, 102, 654, 459, 51, 
+   686, 754, 806, 760, 493, 403, 415, 394, 687, 700, 
+   946, 670, 656, 610, 738, 392, 760, 799, 887, 653, 
+   978, 321, 576, 617, 626, 502, 894, 679, 243, 440, 
+   680, 879, 194, 572, 640, 724, 926, 56, 204, 700, 
+   707, 151, 457, 449, 797, 195, 791, 558, 945, 679, 
+   297, 59, 87, 824, 713, 663, 412, 693, 342, 606, 
+   134, 108, 571, 364, 631, 212, 174, 643, 304, 329, 
+   343, 97, 430, 751, 497, 314, 983, 374, 822, 928, 
+   140, 206, 73, 263, 980, 736, 876, 478, 430, 305, 
+   170, 514, 364, 692, 829, 82, 855, 953, 676, 246, 
+   369, 970, 294, 750, 807, 827, 150, 790, 288, 923, 
+   804, 378, 215, 828, 592, 281, 565, 555, 710, 82, 
+   896, 831, 547, 261, 524, 462, 293, 465, 502, 56, 
+   661, 821, 976, 991, 658, 869, 905, 758, 745, 193, 
+   768, 550, 608, 933, 378, 286, 215, 979, 792, 961, 
+   61, 688, 793, 644, 986, 403, 106, 366, 905, 644, 
+   372, 567, 466, 434, 645, 210, 389, 550, 919, 135, 
+   780, 773, 635, 389, 707, 100, 626, 958, 165, 504, 
+   920, 176, 193, 713, 857, 265, 203, 50, 668, 108, 
+   645, 990, 626, 197, 510, 357, 358, 850, 858, 364, 
+   936, 638
+};
+
+
+/*-------------------------------------------------------------*/
+/*--- end                                       randtable.c ---*/
+/*-------------------------------------------------------------*/

data/ext/STEMMER_api.c

@@ -0,0 +1,66 @@
+
+#include <stdlib.h> /* for calloc, free */
+#include "header.h"
+
+extern struct SN_env * SN_create_env(int S_size, int I_size, int B_size)
+{
+    struct SN_env * z = (struct SN_env *) calloc(1, sizeof(struct SN_env));
+    if (z == NULL) return NULL;
+    z->p = create_s();
+    if (z->p == NULL) goto error;
+    if (S_size)
+    {
+        int i;
+        z->S = (symbol * *) calloc(S_size, sizeof(symbol *));
+        if (z->S == NULL) goto error;
+
+        for (i = 0; i < S_size; i++)
+        {
+            z->S[i] = create_s();
+            if (z->S[i] == NULL) goto error;
+        }
+    }
+
+    if (I_size)
+    {
+        z->I = (int *) calloc(I_size, sizeof(int));
+        if (z->I == NULL) goto error;
+    }
+
+    if (B_size)
+    {
+        z->B = (unsigned char *) calloc(B_size, sizeof(unsigned char));
+        if (z->B == NULL) goto error;
+    }
+
+    return z;
+error:
+    SN_close_env(z, S_size);
+    return NULL;
+}
+
+extern void SN_close_env(struct SN_env * z, int S_size)
+{
+    if (z == NULL) return;
+    if (S_size)
+    {
+        int i;
+        for (i = 0; i < S_size; i++)
+        {
+            lose_s(z->S[i]);
+        }
+        free(z->S);
+    }
+    free(z->I);
+    free(z->B);
+    if (z->p) lose_s(z->p);
+    free(z);
+}
+
+extern int SN_set_current(struct SN_env * z, int size, const symbol * s)
+{
+    int err = replace_s(z, 0, z->l, size, s, NULL);
+    z->c = 0;
+    return err;
+}
+

data/ext/STEMMER_libstemmer.c

@@ -0,0 +1,93 @@
+
+#include <stdlib.h>
+#include <string.h>
+#include "libstemmer.h"
+#include "api.h"
+#include "modules.h"
+
+struct sb_stemmer {
+    struct SN_env * (*create)(void);
+    void (*close)(struct SN_env *);
+    int (*stem)(struct SN_env *);
+
+    struct SN_env * env;
+};
+
+extern const char **
+sb_stemmer_list(void)
+{
+    return algorithm_names;
+}
+
+static stemmer_encoding_t
+sb_getenc(const char * charenc)
+{
+    struct stemmer_encoding * encoding;
+    if (charenc == NULL) return ENC_UTF_8;
+    for (encoding = encodings; encoding->name != 0; encoding++) {
+	if (strcmp(encoding->name, charenc) == 0) break;
+    }
+    if (encoding->name == NULL) return ENC_UNKNOWN;
+    return encoding->enc;
+}
+
+extern struct sb_stemmer *
+sb_stemmer_new(const char * algorithm, const char * charenc)
+{
+    stemmer_encoding_t enc;
+    struct stemmer_modules * module;
+    struct sb_stemmer * stemmer =
+	    (struct sb_stemmer *) malloc(sizeof(struct sb_stemmer));
+    if (stemmer == NULL) return NULL;
+    enc = sb_getenc(charenc);
+    if (enc == ENC_UNKNOWN) return NULL;
+
+    for (module = modules; module->name != 0; module++) {
+	if (strcmp(module->name, algorithm) == 0 && module->enc == enc) break;
+    }
+    if (module->name == NULL) return NULL;
+    
+    stemmer->create = module->create;
+    stemmer->close = module->close;
+    stemmer->stem = module->stem;
+
+    stemmer->env = stemmer->create();
+    if (stemmer->env == NULL)
+    {
+        sb_stemmer_delete(stemmer);
+        return NULL;
+    }
+
+    return stemmer;
+}
+
+void
+sb_stemmer_delete(struct sb_stemmer * stemmer)
+{
+    if (stemmer == 0) return;
+    if (stemmer->close == 0) return;
+    stemmer->close(stemmer->env);
+    stemmer->close = 0;
+    free(stemmer);
+}
+
+const sb_symbol *
+sb_stemmer_stem(struct sb_stemmer * stemmer, const sb_symbol * word, int size)
+{
+    int ret;
+    if (SN_set_current(stemmer->env, size, (const symbol *)(word)))
+    {
+        stemmer->env->l = 0;
+        return NULL;
+    }
+    ret = stemmer->stem(stemmer->env);
+    if (ret < 0) return NULL;
+    stemmer->env->p[stemmer->env->l] = 0;
+    return (const sb_symbol *)(stemmer->env->p);
+}
+
+int
+sb_stemmer_length(struct sb_stemmer * stemmer)
+{
+    return stemmer->env->l;
+}