chipper 0.4.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (134) hide show
  1. data/README.rdoc +51 -0
  2. data/ext/extconf.rb +58 -0
  3. data/ext/libstemmer_c/Makefile +10 -0
  4. data/ext/libstemmer_c/examples/stemwords.c +209 -0
  5. data/ext/libstemmer_c/include/libstemmer.h +79 -0
  6. data/ext/libstemmer_c/libstemmer/libstemmer.c +95 -0
  7. data/ext/libstemmer_c/libstemmer/libstemmer_utf8.c +95 -0
  8. data/ext/libstemmer_c/libstemmer/modules.h +190 -0
  9. data/ext/libstemmer_c/libstemmer/modules_utf8.h +121 -0
  10. data/ext/libstemmer_c/mkinc.mak +82 -0
  11. data/ext/libstemmer_c/mkinc_utf8.mak +52 -0
  12. data/ext/libstemmer_c/runtime/api.c +66 -0
  13. data/ext/libstemmer_c/runtime/api.h +26 -0
  14. data/ext/libstemmer_c/runtime/header.h +58 -0
  15. data/ext/libstemmer_c/runtime/utilities.c +478 -0
  16. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_danish.c +337 -0
  17. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_danish.h +16 -0
  18. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_dutch.c +624 -0
  19. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_dutch.h +16 -0
  20. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_english.c +1117 -0
  21. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_english.h +16 -0
  22. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_finnish.c +762 -0
  23. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_finnish.h +16 -0
  24. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_french.c +1246 -0
  25. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_french.h +16 -0
  26. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_german.c +521 -0
  27. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_german.h +16 -0
  28. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_hungarian.c +1230 -0
  29. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_hungarian.h +16 -0
  30. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_italian.c +1065 -0
  31. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_italian.h +16 -0
  32. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_norwegian.c +297 -0
  33. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_norwegian.h +16 -0
  34. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_porter.c +749 -0
  35. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_porter.h +16 -0
  36. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_portuguese.c +1017 -0
  37. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_portuguese.h +16 -0
  38. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_spanish.c +1093 -0
  39. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_spanish.h +16 -0
  40. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_swedish.c +307 -0
  41. data/ext/libstemmer_c/src_c/stem_ISO_8859_1_swedish.h +16 -0
  42. data/ext/libstemmer_c/src_c/stem_ISO_8859_2_romanian.c +998 -0
  43. data/ext/libstemmer_c/src_c/stem_ISO_8859_2_romanian.h +16 -0
  44. data/ext/libstemmer_c/src_c/stem_KOI8_R_russian.c +700 -0
  45. data/ext/libstemmer_c/src_c/stem_KOI8_R_russian.h +16 -0
  46. data/ext/libstemmer_c/src_c/stem_UTF_8_danish.c +339 -0
  47. data/ext/libstemmer_c/src_c/stem_UTF_8_danish.h +16 -0
  48. data/ext/libstemmer_c/src_c/stem_UTF_8_dutch.c +634 -0
  49. data/ext/libstemmer_c/src_c/stem_UTF_8_dutch.h +16 -0
  50. data/ext/libstemmer_c/src_c/stem_UTF_8_english.c +1125 -0
  51. data/ext/libstemmer_c/src_c/stem_UTF_8_english.h +16 -0
  52. data/ext/libstemmer_c/src_c/stem_UTF_8_finnish.c +768 -0
  53. data/ext/libstemmer_c/src_c/stem_UTF_8_finnish.h +16 -0
  54. data/ext/libstemmer_c/src_c/stem_UTF_8_french.c +1256 -0
  55. data/ext/libstemmer_c/src_c/stem_UTF_8_french.h +16 -0
  56. data/ext/libstemmer_c/src_c/stem_UTF_8_german.c +527 -0
  57. data/ext/libstemmer_c/src_c/stem_UTF_8_german.h +16 -0
  58. data/ext/libstemmer_c/src_c/stem_UTF_8_hungarian.c +1234 -0
  59. data/ext/libstemmer_c/src_c/stem_UTF_8_hungarian.h +16 -0
  60. data/ext/libstemmer_c/src_c/stem_UTF_8_italian.c +1073 -0
  61. data/ext/libstemmer_c/src_c/stem_UTF_8_italian.h +16 -0
  62. data/ext/libstemmer_c/src_c/stem_UTF_8_norwegian.c +299 -0
  63. data/ext/libstemmer_c/src_c/stem_UTF_8_norwegian.h +16 -0
  64. data/ext/libstemmer_c/src_c/stem_UTF_8_porter.c +755 -0
  65. data/ext/libstemmer_c/src_c/stem_UTF_8_porter.h +16 -0
  66. data/ext/libstemmer_c/src_c/stem_UTF_8_portuguese.c +1023 -0
  67. data/ext/libstemmer_c/src_c/stem_UTF_8_portuguese.h +16 -0
  68. data/ext/libstemmer_c/src_c/stem_UTF_8_romanian.c +1004 -0
  69. data/ext/libstemmer_c/src_c/stem_UTF_8_romanian.h +16 -0
  70. data/ext/libstemmer_c/src_c/stem_UTF_8_russian.c +694 -0
  71. data/ext/libstemmer_c/src_c/stem_UTF_8_russian.h +16 -0
  72. data/ext/libstemmer_c/src_c/stem_UTF_8_spanish.c +1097 -0
  73. data/ext/libstemmer_c/src_c/stem_UTF_8_spanish.h +16 -0
  74. data/ext/libstemmer_c/src_c/stem_UTF_8_swedish.c +309 -0
  75. data/ext/libstemmer_c/src_c/stem_UTF_8_swedish.h +16 -0
  76. data/ext/libstemmer_c/src_c/stem_UTF_8_turkish.c +2205 -0
  77. data/ext/libstemmer_c/src_c/stem_UTF_8_turkish.h +16 -0
  78. data/ext/re2/bitstate.cc +378 -0
  79. data/ext/re2/compile.cc +1138 -0
  80. data/ext/re2/dfa.cc +2086 -0
  81. data/ext/re2/filtered_re2.cc +100 -0
  82. data/ext/re2/filtered_re2.h +99 -0
  83. data/ext/re2/hash.cc +231 -0
  84. data/ext/re2/mimics_pcre.cc +185 -0
  85. data/ext/re2/nfa.cc +709 -0
  86. data/ext/re2/onepass.cc +614 -0
  87. data/ext/re2/parse.cc +2202 -0
  88. data/ext/re2/perl_groups.cc +119 -0
  89. data/ext/re2/prefilter.cc +671 -0
  90. data/ext/re2/prefilter.h +105 -0
  91. data/ext/re2/prefilter_tree.cc +398 -0
  92. data/ext/re2/prefilter_tree.h +130 -0
  93. data/ext/re2/prog.cc +341 -0
  94. data/ext/re2/prog.h +376 -0
  95. data/ext/re2/re2.cc +1180 -0
  96. data/ext/re2/re2.h +837 -0
  97. data/ext/re2/regexp.cc +920 -0
  98. data/ext/re2/regexp.h +632 -0
  99. data/ext/re2/rune.cc +258 -0
  100. data/ext/re2/set.cc +113 -0
  101. data/ext/re2/set.h +55 -0
  102. data/ext/re2/simplify.cc +393 -0
  103. data/ext/re2/stringpiece.cc +87 -0
  104. data/ext/re2/stringpiece.h +182 -0
  105. data/ext/re2/tostring.cc +341 -0
  106. data/ext/re2/unicode_casefold.cc +469 -0
  107. data/ext/re2/unicode_casefold.h +75 -0
  108. data/ext/re2/unicode_groups.cc +4851 -0
  109. data/ext/re2/unicode_groups.h +64 -0
  110. data/ext/re2/valgrind.cc +24 -0
  111. data/ext/re2/variadic_function.h +346 -0
  112. data/ext/re2/walker-inl.h +244 -0
  113. data/ext/src/chipper.cc +626 -0
  114. data/ext/src/version.h +1 -0
  115. data/ext/stemmer.rb +40 -0
  116. data/ext/util/arena.h +103 -0
  117. data/ext/util/atomicops.h +79 -0
  118. data/ext/util/benchmark.h +41 -0
  119. data/ext/util/flags.h +27 -0
  120. data/ext/util/logging.h +78 -0
  121. data/ext/util/mutex.h +190 -0
  122. data/ext/util/pcre.h +679 -0
  123. data/ext/util/random.h +29 -0
  124. data/ext/util/sparse_array.h +451 -0
  125. data/ext/util/sparse_set.h +177 -0
  126. data/ext/util/test.h +57 -0
  127. data/ext/util/thread.h +26 -0
  128. data/ext/util/utf.h +43 -0
  129. data/ext/util/util.h +127 -0
  130. data/ext/util/valgrind.h +4517 -0
  131. data/test/helper.rb +5 -0
  132. data/test/test_entities.rb +57 -0
  133. data/test/test_tokens.rb +118 -0
  134. metadata +199 -0
@@ -0,0 +1,16 @@
1
+
2
+ /* This file was generated automatically by the Snowball to ANSI C compiler */
3
+
4
+ #ifdef __cplusplus
5
+ extern "C" {
6
+ #endif
7
+
8
+ extern struct SN_env * french_UTF_8_create_env(void);
9
+ extern void french_UTF_8_close_env(struct SN_env * z);
10
+
11
+ extern int french_UTF_8_stem(struct SN_env * z);
12
+
13
+ #ifdef __cplusplus
14
+ }
15
+ #endif
16
+
@@ -0,0 +1,527 @@
1
+
2
+ /* This file was generated automatically by the Snowball to ANSI C compiler */
3
+
4
+ #include "../runtime/header.h"
5
+
6
+ #ifdef __cplusplus
7
+ extern "C" {
8
+ #endif
9
+ extern int german_UTF_8_stem(struct SN_env * z);
10
+ #ifdef __cplusplus
11
+ }
12
+ #endif
13
+ static int r_standard_suffix(struct SN_env * z);
14
+ static int r_R2(struct SN_env * z);
15
+ static int r_R1(struct SN_env * z);
16
+ static int r_mark_regions(struct SN_env * z);
17
+ static int r_postlude(struct SN_env * z);
18
+ static int r_prelude(struct SN_env * z);
19
+ #ifdef __cplusplus
20
+ extern "C" {
21
+ #endif
22
+
23
+
24
+ extern struct SN_env * german_UTF_8_create_env(void);
25
+ extern void german_UTF_8_close_env(struct SN_env * z);
26
+
27
+
28
+ #ifdef __cplusplus
29
+ }
30
+ #endif
31
+ static const symbol s_0_1[1] = { 'U' };
32
+ static const symbol s_0_2[1] = { 'Y' };
33
+ static const symbol s_0_3[2] = { 0xC3, 0xA4 };
34
+ static const symbol s_0_4[2] = { 0xC3, 0xB6 };
35
+ static const symbol s_0_5[2] = { 0xC3, 0xBC };
36
+
37
+ static const struct among a_0[6] =
38
+ {
39
+ /* 0 */ { 0, 0, -1, 6, 0},
40
+ /* 1 */ { 1, s_0_1, 0, 2, 0},
41
+ /* 2 */ { 1, s_0_2, 0, 1, 0},
42
+ /* 3 */ { 2, s_0_3, 0, 3, 0},
43
+ /* 4 */ { 2, s_0_4, 0, 4, 0},
44
+ /* 5 */ { 2, s_0_5, 0, 5, 0}
45
+ };
46
+
47
+ static const symbol s_1_0[1] = { 'e' };
48
+ static const symbol s_1_1[2] = { 'e', 'm' };
49
+ static const symbol s_1_2[2] = { 'e', 'n' };
50
+ static const symbol s_1_3[3] = { 'e', 'r', 'n' };
51
+ static const symbol s_1_4[2] = { 'e', 'r' };
52
+ static const symbol s_1_5[1] = { 's' };
53
+ static const symbol s_1_6[2] = { 'e', 's' };
54
+
55
+ static const struct among a_1[7] =
56
+ {
57
+ /* 0 */ { 1, s_1_0, -1, 2, 0},
58
+ /* 1 */ { 2, s_1_1, -1, 1, 0},
59
+ /* 2 */ { 2, s_1_2, -1, 2, 0},
60
+ /* 3 */ { 3, s_1_3, -1, 1, 0},
61
+ /* 4 */ { 2, s_1_4, -1, 1, 0},
62
+ /* 5 */ { 1, s_1_5, -1, 3, 0},
63
+ /* 6 */ { 2, s_1_6, 5, 2, 0}
64
+ };
65
+
66
+ static const symbol s_2_0[2] = { 'e', 'n' };
67
+ static const symbol s_2_1[2] = { 'e', 'r' };
68
+ static const symbol s_2_2[2] = { 's', 't' };
69
+ static const symbol s_2_3[3] = { 'e', 's', 't' };
70
+
71
+ static const struct among a_2[4] =
72
+ {
73
+ /* 0 */ { 2, s_2_0, -1, 1, 0},
74
+ /* 1 */ { 2, s_2_1, -1, 1, 0},
75
+ /* 2 */ { 2, s_2_2, -1, 2, 0},
76
+ /* 3 */ { 3, s_2_3, 2, 1, 0}
77
+ };
78
+
79
+ static const symbol s_3_0[2] = { 'i', 'g' };
80
+ static const symbol s_3_1[4] = { 'l', 'i', 'c', 'h' };
81
+
82
+ static const struct among a_3[2] =
83
+ {
84
+ /* 0 */ { 2, s_3_0, -1, 1, 0},
85
+ /* 1 */ { 4, s_3_1, -1, 1, 0}
86
+ };
87
+
88
+ static const symbol s_4_0[3] = { 'e', 'n', 'd' };
89
+ static const symbol s_4_1[2] = { 'i', 'g' };
90
+ static const symbol s_4_2[3] = { 'u', 'n', 'g' };
91
+ static const symbol s_4_3[4] = { 'l', 'i', 'c', 'h' };
92
+ static const symbol s_4_4[4] = { 'i', 's', 'c', 'h' };
93
+ static const symbol s_4_5[2] = { 'i', 'k' };
94
+ static const symbol s_4_6[4] = { 'h', 'e', 'i', 't' };
95
+ static const symbol s_4_7[4] = { 'k', 'e', 'i', 't' };
96
+
97
+ static const struct among a_4[8] =
98
+ {
99
+ /* 0 */ { 3, s_4_0, -1, 1, 0},
100
+ /* 1 */ { 2, s_4_1, -1, 2, 0},
101
+ /* 2 */ { 3, s_4_2, -1, 1, 0},
102
+ /* 3 */ { 4, s_4_3, -1, 3, 0},
103
+ /* 4 */ { 4, s_4_4, -1, 2, 0},
104
+ /* 5 */ { 2, s_4_5, -1, 2, 0},
105
+ /* 6 */ { 4, s_4_6, -1, 3, 0},
106
+ /* 7 */ { 4, s_4_7, -1, 4, 0}
107
+ };
108
+
109
+ static const unsigned char g_v[] = { 17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 32, 8 };
110
+
111
+ static const unsigned char g_s_ending[] = { 117, 30, 5 };
112
+
113
+ static const unsigned char g_st_ending[] = { 117, 30, 4 };
114
+
115
+ static const symbol s_0[] = { 0xC3, 0x9F };
116
+ static const symbol s_1[] = { 's', 's' };
117
+ static const symbol s_2[] = { 'u' };
118
+ static const symbol s_3[] = { 'U' };
119
+ static const symbol s_4[] = { 'y' };
120
+ static const symbol s_5[] = { 'Y' };
121
+ static const symbol s_6[] = { 'y' };
122
+ static const symbol s_7[] = { 'u' };
123
+ static const symbol s_8[] = { 'a' };
124
+ static const symbol s_9[] = { 'o' };
125
+ static const symbol s_10[] = { 'u' };
126
+ static const symbol s_11[] = { 's' };
127
+ static const symbol s_12[] = { 'n', 'i', 's' };
128
+ static const symbol s_13[] = { 'i', 'g' };
129
+ static const symbol s_14[] = { 'e' };
130
+ static const symbol s_15[] = { 'e' };
131
+ static const symbol s_16[] = { 'e', 'r' };
132
+ static const symbol s_17[] = { 'e', 'n' };
133
+
134
+ static int r_prelude(struct SN_env * z) {
135
+ { int c_test = z->c; /* test, line 35 */
136
+ while(1) { /* repeat, line 35 */
137
+ int c1 = z->c;
138
+ { int c2 = z->c; /* or, line 38 */
139
+ z->bra = z->c; /* [, line 37 */
140
+ if (!(eq_s(z, 2, s_0))) goto lab2;
141
+ z->ket = z->c; /* ], line 37 */
142
+ { int ret = slice_from_s(z, 2, s_1); /* <-, line 37 */
143
+ if (ret < 0) return ret;
144
+ }
145
+ goto lab1;
146
+ lab2:
147
+ z->c = c2;
148
+ { int ret = skip_utf8(z->p, z->c, 0, z->l, 1);
149
+ if (ret < 0) goto lab0;
150
+ z->c = ret; /* next, line 38 */
151
+ }
152
+ }
153
+ lab1:
154
+ continue;
155
+ lab0:
156
+ z->c = c1;
157
+ break;
158
+ }
159
+ z->c = c_test;
160
+ }
161
+ while(1) { /* repeat, line 41 */
162
+ int c3 = z->c;
163
+ while(1) { /* goto, line 41 */
164
+ int c4 = z->c;
165
+ if (in_grouping_U(z, g_v, 97, 252, 0)) goto lab4;
166
+ z->bra = z->c; /* [, line 42 */
167
+ { int c5 = z->c; /* or, line 42 */
168
+ if (!(eq_s(z, 1, s_2))) goto lab6;
169
+ z->ket = z->c; /* ], line 42 */
170
+ if (in_grouping_U(z, g_v, 97, 252, 0)) goto lab6;
171
+ { int ret = slice_from_s(z, 1, s_3); /* <-, line 42 */
172
+ if (ret < 0) return ret;
173
+ }
174
+ goto lab5;
175
+ lab6:
176
+ z->c = c5;
177
+ if (!(eq_s(z, 1, s_4))) goto lab4;
178
+ z->ket = z->c; /* ], line 43 */
179
+ if (in_grouping_U(z, g_v, 97, 252, 0)) goto lab4;
180
+ { int ret = slice_from_s(z, 1, s_5); /* <-, line 43 */
181
+ if (ret < 0) return ret;
182
+ }
183
+ }
184
+ lab5:
185
+ z->c = c4;
186
+ break;
187
+ lab4:
188
+ z->c = c4;
189
+ { int ret = skip_utf8(z->p, z->c, 0, z->l, 1);
190
+ if (ret < 0) goto lab3;
191
+ z->c = ret; /* goto, line 41 */
192
+ }
193
+ }
194
+ continue;
195
+ lab3:
196
+ z->c = c3;
197
+ break;
198
+ }
199
+ return 1;
200
+ }
201
+
202
+ static int r_mark_regions(struct SN_env * z) {
203
+ z->I[0] = z->l;
204
+ z->I[1] = z->l;
205
+ { int c_test = z->c; /* test, line 52 */
206
+ { int ret = skip_utf8(z->p, z->c, 0, z->l, + 3);
207
+ if (ret < 0) return 0;
208
+ z->c = ret; /* hop, line 52 */
209
+ }
210
+ z->I[2] = z->c; /* setmark x, line 52 */
211
+ z->c = c_test;
212
+ }
213
+ { /* gopast */ /* grouping v, line 54 */
214
+ int ret = out_grouping_U(z, g_v, 97, 252, 1);
215
+ if (ret < 0) return 0;
216
+ z->c += ret;
217
+ }
218
+ { /* gopast */ /* non v, line 54 */
219
+ int ret = in_grouping_U(z, g_v, 97, 252, 1);
220
+ if (ret < 0) return 0;
221
+ z->c += ret;
222
+ }
223
+ z->I[0] = z->c; /* setmark p1, line 54 */
224
+ /* try, line 55 */
225
+ if (!(z->I[0] < z->I[2])) goto lab0;
226
+ z->I[0] = z->I[2];
227
+ lab0:
228
+ { /* gopast */ /* grouping v, line 56 */
229
+ int ret = out_grouping_U(z, g_v, 97, 252, 1);
230
+ if (ret < 0) return 0;
231
+ z->c += ret;
232
+ }
233
+ { /* gopast */ /* non v, line 56 */
234
+ int ret = in_grouping_U(z, g_v, 97, 252, 1);
235
+ if (ret < 0) return 0;
236
+ z->c += ret;
237
+ }
238
+ z->I[1] = z->c; /* setmark p2, line 56 */
239
+ return 1;
240
+ }
241
+
242
+ static int r_postlude(struct SN_env * z) {
243
+ int among_var;
244
+ while(1) { /* repeat, line 60 */
245
+ int c1 = z->c;
246
+ z->bra = z->c; /* [, line 62 */
247
+ among_var = find_among(z, a_0, 6); /* substring, line 62 */
248
+ if (!(among_var)) goto lab0;
249
+ z->ket = z->c; /* ], line 62 */
250
+ switch(among_var) {
251
+ case 0: goto lab0;
252
+ case 1:
253
+ { int ret = slice_from_s(z, 1, s_6); /* <-, line 63 */
254
+ if (ret < 0) return ret;
255
+ }
256
+ break;
257
+ case 2:
258
+ { int ret = slice_from_s(z, 1, s_7); /* <-, line 64 */
259
+ if (ret < 0) return ret;
260
+ }
261
+ break;
262
+ case 3:
263
+ { int ret = slice_from_s(z, 1, s_8); /* <-, line 65 */
264
+ if (ret < 0) return ret;
265
+ }
266
+ break;
267
+ case 4:
268
+ { int ret = slice_from_s(z, 1, s_9); /* <-, line 66 */
269
+ if (ret < 0) return ret;
270
+ }
271
+ break;
272
+ case 5:
273
+ { int ret = slice_from_s(z, 1, s_10); /* <-, line 67 */
274
+ if (ret < 0) return ret;
275
+ }
276
+ break;
277
+ case 6:
278
+ { int ret = skip_utf8(z->p, z->c, 0, z->l, 1);
279
+ if (ret < 0) goto lab0;
280
+ z->c = ret; /* next, line 68 */
281
+ }
282
+ break;
283
+ }
284
+ continue;
285
+ lab0:
286
+ z->c = c1;
287
+ break;
288
+ }
289
+ return 1;
290
+ }
291
+
292
+ static int r_R1(struct SN_env * z) {
293
+ if (!(z->I[0] <= z->c)) return 0;
294
+ return 1;
295
+ }
296
+
297
+ static int r_R2(struct SN_env * z) {
298
+ if (!(z->I[1] <= z->c)) return 0;
299
+ return 1;
300
+ }
301
+
302
+ static int r_standard_suffix(struct SN_env * z) {
303
+ int among_var;
304
+ { int m1 = z->l - z->c; (void)m1; /* do, line 79 */
305
+ z->ket = z->c; /* [, line 80 */
306
+ if (z->c <= z->lb || z->p[z->c - 1] >> 5 != 3 || !((811040 >> (z->p[z->c - 1] & 0x1f)) & 1)) goto lab0;
307
+ among_var = find_among_b(z, a_1, 7); /* substring, line 80 */
308
+ if (!(among_var)) goto lab0;
309
+ z->bra = z->c; /* ], line 80 */
310
+ { int ret = r_R1(z);
311
+ if (ret == 0) goto lab0; /* call R1, line 80 */
312
+ if (ret < 0) return ret;
313
+ }
314
+ switch(among_var) {
315
+ case 0: goto lab0;
316
+ case 1:
317
+ { int ret = slice_del(z); /* delete, line 82 */
318
+ if (ret < 0) return ret;
319
+ }
320
+ break;
321
+ case 2:
322
+ { int ret = slice_del(z); /* delete, line 85 */
323
+ if (ret < 0) return ret;
324
+ }
325
+ { int m_keep = z->l - z->c;/* (void) m_keep;*/ /* try, line 86 */
326
+ z->ket = z->c; /* [, line 86 */
327
+ if (!(eq_s_b(z, 1, s_11))) { z->c = z->l - m_keep; goto lab1; }
328
+ z->bra = z->c; /* ], line 86 */
329
+ if (!(eq_s_b(z, 3, s_12))) { z->c = z->l - m_keep; goto lab1; }
330
+ { int ret = slice_del(z); /* delete, line 86 */
331
+ if (ret < 0) return ret;
332
+ }
333
+ lab1:
334
+ ;
335
+ }
336
+ break;
337
+ case 3:
338
+ if (in_grouping_b_U(z, g_s_ending, 98, 116, 0)) goto lab0;
339
+ { int ret = slice_del(z); /* delete, line 89 */
340
+ if (ret < 0) return ret;
341
+ }
342
+ break;
343
+ }
344
+ lab0:
345
+ z->c = z->l - m1;
346
+ }
347
+ { int m2 = z->l - z->c; (void)m2; /* do, line 93 */
348
+ z->ket = z->c; /* [, line 94 */
349
+ if (z->c - 1 <= z->lb || z->p[z->c - 1] >> 5 != 3 || !((1327104 >> (z->p[z->c - 1] & 0x1f)) & 1)) goto lab2;
350
+ among_var = find_among_b(z, a_2, 4); /* substring, line 94 */
351
+ if (!(among_var)) goto lab2;
352
+ z->bra = z->c; /* ], line 94 */
353
+ { int ret = r_R1(z);
354
+ if (ret == 0) goto lab2; /* call R1, line 94 */
355
+ if (ret < 0) return ret;
356
+ }
357
+ switch(among_var) {
358
+ case 0: goto lab2;
359
+ case 1:
360
+ { int ret = slice_del(z); /* delete, line 96 */
361
+ if (ret < 0) return ret;
362
+ }
363
+ break;
364
+ case 2:
365
+ if (in_grouping_b_U(z, g_st_ending, 98, 116, 0)) goto lab2;
366
+ { int ret = skip_utf8(z->p, z->c, z->lb, z->l, - 3);
367
+ if (ret < 0) goto lab2;
368
+ z->c = ret; /* hop, line 99 */
369
+ }
370
+ { int ret = slice_del(z); /* delete, line 99 */
371
+ if (ret < 0) return ret;
372
+ }
373
+ break;
374
+ }
375
+ lab2:
376
+ z->c = z->l - m2;
377
+ }
378
+ { int m3 = z->l - z->c; (void)m3; /* do, line 103 */
379
+ z->ket = z->c; /* [, line 104 */
380
+ if (z->c - 1 <= z->lb || z->p[z->c - 1] >> 5 != 3 || !((1051024 >> (z->p[z->c - 1] & 0x1f)) & 1)) goto lab3;
381
+ among_var = find_among_b(z, a_4, 8); /* substring, line 104 */
382
+ if (!(among_var)) goto lab3;
383
+ z->bra = z->c; /* ], line 104 */
384
+ { int ret = r_R2(z);
385
+ if (ret == 0) goto lab3; /* call R2, line 104 */
386
+ if (ret < 0) return ret;
387
+ }
388
+ switch(among_var) {
389
+ case 0: goto lab3;
390
+ case 1:
391
+ { int ret = slice_del(z); /* delete, line 106 */
392
+ if (ret < 0) return ret;
393
+ }
394
+ { int m_keep = z->l - z->c;/* (void) m_keep;*/ /* try, line 107 */
395
+ z->ket = z->c; /* [, line 107 */
396
+ if (!(eq_s_b(z, 2, s_13))) { z->c = z->l - m_keep; goto lab4; }
397
+ z->bra = z->c; /* ], line 107 */
398
+ { int m4 = z->l - z->c; (void)m4; /* not, line 107 */
399
+ if (!(eq_s_b(z, 1, s_14))) goto lab5;
400
+ { z->c = z->l - m_keep; goto lab4; }
401
+ lab5:
402
+ z->c = z->l - m4;
403
+ }
404
+ { int ret = r_R2(z);
405
+ if (ret == 0) { z->c = z->l - m_keep; goto lab4; } /* call R2, line 107 */
406
+ if (ret < 0) return ret;
407
+ }
408
+ { int ret = slice_del(z); /* delete, line 107 */
409
+ if (ret < 0) return ret;
410
+ }
411
+ lab4:
412
+ ;
413
+ }
414
+ break;
415
+ case 2:
416
+ { int m5 = z->l - z->c; (void)m5; /* not, line 110 */
417
+ if (!(eq_s_b(z, 1, s_15))) goto lab6;
418
+ goto lab3;
419
+ lab6:
420
+ z->c = z->l - m5;
421
+ }
422
+ { int ret = slice_del(z); /* delete, line 110 */
423
+ if (ret < 0) return ret;
424
+ }
425
+ break;
426
+ case 3:
427
+ { int ret = slice_del(z); /* delete, line 113 */
428
+ if (ret < 0) return ret;
429
+ }
430
+ { int m_keep = z->l - z->c;/* (void) m_keep;*/ /* try, line 114 */
431
+ z->ket = z->c; /* [, line 115 */
432
+ { int m6 = z->l - z->c; (void)m6; /* or, line 115 */
433
+ if (!(eq_s_b(z, 2, s_16))) goto lab9;
434
+ goto lab8;
435
+ lab9:
436
+ z->c = z->l - m6;
437
+ if (!(eq_s_b(z, 2, s_17))) { z->c = z->l - m_keep; goto lab7; }
438
+ }
439
+ lab8:
440
+ z->bra = z->c; /* ], line 115 */
441
+ { int ret = r_R1(z);
442
+ if (ret == 0) { z->c = z->l - m_keep; goto lab7; } /* call R1, line 115 */
443
+ if (ret < 0) return ret;
444
+ }
445
+ { int ret = slice_del(z); /* delete, line 115 */
446
+ if (ret < 0) return ret;
447
+ }
448
+ lab7:
449
+ ;
450
+ }
451
+ break;
452
+ case 4:
453
+ { int ret = slice_del(z); /* delete, line 119 */
454
+ if (ret < 0) return ret;
455
+ }
456
+ { int m_keep = z->l - z->c;/* (void) m_keep;*/ /* try, line 120 */
457
+ z->ket = z->c; /* [, line 121 */
458
+ if (z->c - 1 <= z->lb || (z->p[z->c - 1] != 103 && z->p[z->c - 1] != 104)) { z->c = z->l - m_keep; goto lab10; }
459
+ among_var = find_among_b(z, a_3, 2); /* substring, line 121 */
460
+ if (!(among_var)) { z->c = z->l - m_keep; goto lab10; }
461
+ z->bra = z->c; /* ], line 121 */
462
+ { int ret = r_R2(z);
463
+ if (ret == 0) { z->c = z->l - m_keep; goto lab10; } /* call R2, line 121 */
464
+ if (ret < 0) return ret;
465
+ }
466
+ switch(among_var) {
467
+ case 0: { z->c = z->l - m_keep; goto lab10; }
468
+ case 1:
469
+ { int ret = slice_del(z); /* delete, line 123 */
470
+ if (ret < 0) return ret;
471
+ }
472
+ break;
473
+ }
474
+ lab10:
475
+ ;
476
+ }
477
+ break;
478
+ }
479
+ lab3:
480
+ z->c = z->l - m3;
481
+ }
482
+ return 1;
483
+ }
484
+
485
+ extern int german_UTF_8_stem(struct SN_env * z) {
486
+ { int c1 = z->c; /* do, line 134 */
487
+ { int ret = r_prelude(z);
488
+ if (ret == 0) goto lab0; /* call prelude, line 134 */
489
+ if (ret < 0) return ret;
490
+ }
491
+ lab0:
492
+ z->c = c1;
493
+ }
494
+ { int c2 = z->c; /* do, line 135 */
495
+ { int ret = r_mark_regions(z);
496
+ if (ret == 0) goto lab1; /* call mark_regions, line 135 */
497
+ if (ret < 0) return ret;
498
+ }
499
+ lab1:
500
+ z->c = c2;
501
+ }
502
+ z->lb = z->c; z->c = z->l; /* backwards, line 136 */
503
+
504
+ { int m3 = z->l - z->c; (void)m3; /* do, line 137 */
505
+ { int ret = r_standard_suffix(z);
506
+ if (ret == 0) goto lab2; /* call standard_suffix, line 137 */
507
+ if (ret < 0) return ret;
508
+ }
509
+ lab2:
510
+ z->c = z->l - m3;
511
+ }
512
+ z->c = z->lb;
513
+ { int c4 = z->c; /* do, line 138 */
514
+ { int ret = r_postlude(z);
515
+ if (ret == 0) goto lab3; /* call postlude, line 138 */
516
+ if (ret < 0) return ret;
517
+ }
518
+ lab3:
519
+ z->c = c4;
520
+ }
521
+ return 1;
522
+ }
523
+
524
+ extern struct SN_env * german_UTF_8_create_env(void) { return SN_create_env(0, 3, 0); }
525
+
526
+ extern void german_UTF_8_close_env(struct SN_env * z) { SN_close_env(z, 0); }
527
+
@@ -0,0 +1,16 @@
1
+
2
+ /* This file was generated automatically by the Snowball to ANSI C compiler */
3
+
4
+ #ifdef __cplusplus
5
+ extern "C" {
6
+ #endif
7
+
8
+ extern struct SN_env * german_UTF_8_create_env(void);
9
+ extern void german_UTF_8_close_env(struct SN_env * z);
10
+
11
+ extern int german_UTF_8_stem(struct SN_env * z);
12
+
13
+ #ifdef __cplusplus
14
+ }
15
+ #endif
16
+