jk-ferret 0.11.8.2
Sign up to get free protection for your applications and to get access to all the features.
- data/CHANGELOG +24 -0
- data/MIT-LICENSE +20 -0
- data/README +90 -0
- data/RELEASE_CHANGES +137 -0
- data/RELEASE_NOTES +60 -0
- data/Rakefile +443 -0
- data/TODO +109 -0
- data/TUTORIAL +231 -0
- data/bin/ferret-browser +79 -0
- data/ext/BZLIB_blocksort.c +1094 -0
- data/ext/BZLIB_bzlib.c +1578 -0
- data/ext/BZLIB_compress.c +672 -0
- data/ext/BZLIB_crctable.c +104 -0
- data/ext/BZLIB_decompress.c +626 -0
- data/ext/BZLIB_huffman.c +205 -0
- data/ext/BZLIB_randtable.c +84 -0
- data/ext/STEMMER_api.c +66 -0
- data/ext/STEMMER_libstemmer.c +93 -0
- data/ext/STEMMER_stem_ISO_8859_1_danish.c +337 -0
- data/ext/STEMMER_stem_ISO_8859_1_dutch.c +624 -0
- data/ext/STEMMER_stem_ISO_8859_1_english.c +1117 -0
- data/ext/STEMMER_stem_ISO_8859_1_finnish.c +762 -0
- data/ext/STEMMER_stem_ISO_8859_1_french.c +1246 -0
- data/ext/STEMMER_stem_ISO_8859_1_german.c +503 -0
- data/ext/STEMMER_stem_ISO_8859_1_hungarian.c +1230 -0
- data/ext/STEMMER_stem_ISO_8859_1_italian.c +1065 -0
- data/ext/STEMMER_stem_ISO_8859_1_norwegian.c +297 -0
- data/ext/STEMMER_stem_ISO_8859_1_porter.c +749 -0
- data/ext/STEMMER_stem_ISO_8859_1_portuguese.c +1017 -0
- data/ext/STEMMER_stem_ISO_8859_1_spanish.c +1093 -0
- data/ext/STEMMER_stem_ISO_8859_1_swedish.c +307 -0
- data/ext/STEMMER_stem_ISO_8859_2_romanian.c +998 -0
- data/ext/STEMMER_stem_KOI8_R_russian.c +700 -0
- data/ext/STEMMER_stem_UTF_8_danish.c +339 -0
- data/ext/STEMMER_stem_UTF_8_dutch.c +634 -0
- data/ext/STEMMER_stem_UTF_8_english.c +1125 -0
- data/ext/STEMMER_stem_UTF_8_finnish.c +768 -0
- data/ext/STEMMER_stem_UTF_8_french.c +1256 -0
- data/ext/STEMMER_stem_UTF_8_german.c +509 -0
- data/ext/STEMMER_stem_UTF_8_hungarian.c +1234 -0
- data/ext/STEMMER_stem_UTF_8_italian.c +1073 -0
- data/ext/STEMMER_stem_UTF_8_norwegian.c +299 -0
- data/ext/STEMMER_stem_UTF_8_porter.c +755 -0
- data/ext/STEMMER_stem_UTF_8_portuguese.c +1023 -0
- data/ext/STEMMER_stem_UTF_8_romanian.c +1004 -0
- data/ext/STEMMER_stem_UTF_8_russian.c +694 -0
- data/ext/STEMMER_stem_UTF_8_spanish.c +1097 -0
- data/ext/STEMMER_stem_UTF_8_swedish.c +309 -0
- data/ext/STEMMER_stem_UTF_8_turkish.c +2205 -0
- data/ext/STEMMER_utilities.c +478 -0
- data/ext/analysis.c +1710 -0
- data/ext/analysis.h +266 -0
- data/ext/api.h +26 -0
- data/ext/array.c +125 -0
- data/ext/array.h +62 -0
- data/ext/bitvector.c +96 -0
- data/ext/bitvector.h +594 -0
- data/ext/bzlib.h +282 -0
- data/ext/bzlib_private.h +503 -0
- data/ext/compound_io.c +384 -0
- data/ext/config.h +52 -0
- data/ext/document.c +159 -0
- data/ext/document.h +63 -0
- data/ext/except.c +102 -0
- data/ext/except.h +176 -0
- data/ext/extconf.rb +15 -0
- data/ext/ferret.c +416 -0
- data/ext/ferret.h +94 -0
- data/ext/field_index.c +262 -0
- data/ext/field_index.h +52 -0
- data/ext/filter.c +157 -0
- data/ext/fs_store.c +493 -0
- data/ext/global.c +458 -0
- data/ext/global.h +302 -0
- data/ext/hash.c +524 -0
- data/ext/hash.h +515 -0
- data/ext/hashset.c +192 -0
- data/ext/hashset.h +215 -0
- data/ext/header.h +58 -0
- data/ext/helper.c +63 -0
- data/ext/helper.h +21 -0
- data/ext/index.c +6804 -0
- data/ext/index.h +935 -0
- data/ext/internal.h +1019 -0
- data/ext/lang.c +10 -0
- data/ext/lang.h +68 -0
- data/ext/libstemmer.h +79 -0
- data/ext/mempool.c +88 -0
- data/ext/mempool.h +43 -0
- data/ext/modules.h +190 -0
- data/ext/multimapper.c +351 -0
- data/ext/multimapper.h +60 -0
- data/ext/posh.c +1006 -0
- data/ext/posh.h +973 -0
- data/ext/priorityqueue.c +149 -0
- data/ext/priorityqueue.h +155 -0
- data/ext/q_boolean.c +1621 -0
- data/ext/q_const_score.c +162 -0
- data/ext/q_filtered_query.c +212 -0
- data/ext/q_fuzzy.c +280 -0
- data/ext/q_match_all.c +149 -0
- data/ext/q_multi_term.c +673 -0
- data/ext/q_parser.c +3103 -0
- data/ext/q_phrase.c +1206 -0
- data/ext/q_prefix.c +98 -0
- data/ext/q_range.c +682 -0
- data/ext/q_span.c +2390 -0
- data/ext/q_term.c +337 -0
- data/ext/q_wildcard.c +167 -0
- data/ext/r_analysis.c +2626 -0
- data/ext/r_index.c +3468 -0
- data/ext/r_qparser.c +635 -0
- data/ext/r_search.c +4490 -0
- data/ext/r_store.c +513 -0
- data/ext/r_utils.c +1131 -0
- data/ext/ram_store.c +476 -0
- data/ext/scanner.c +895 -0
- data/ext/scanner.h +36 -0
- data/ext/scanner_mb.c +6701 -0
- data/ext/scanner_utf8.c +4415 -0
- data/ext/search.c +1864 -0
- data/ext/search.h +953 -0
- data/ext/similarity.c +151 -0
- data/ext/similarity.h +89 -0
- data/ext/sort.c +786 -0
- data/ext/stem_ISO_8859_1_danish.h +16 -0
- data/ext/stem_ISO_8859_1_dutch.h +16 -0
- data/ext/stem_ISO_8859_1_english.h +16 -0
- data/ext/stem_ISO_8859_1_finnish.h +16 -0
- data/ext/stem_ISO_8859_1_french.h +16 -0
- data/ext/stem_ISO_8859_1_german.h +16 -0
- data/ext/stem_ISO_8859_1_hungarian.h +16 -0
- data/ext/stem_ISO_8859_1_italian.h +16 -0
- data/ext/stem_ISO_8859_1_norwegian.h +16 -0
- data/ext/stem_ISO_8859_1_porter.h +16 -0
- data/ext/stem_ISO_8859_1_portuguese.h +16 -0
- data/ext/stem_ISO_8859_1_spanish.h +16 -0
- data/ext/stem_ISO_8859_1_swedish.h +16 -0
- data/ext/stem_ISO_8859_2_romanian.h +16 -0
- data/ext/stem_KOI8_R_russian.h +16 -0
- data/ext/stem_UTF_8_danish.h +16 -0
- data/ext/stem_UTF_8_dutch.h +16 -0
- data/ext/stem_UTF_8_english.h +16 -0
- data/ext/stem_UTF_8_finnish.h +16 -0
- data/ext/stem_UTF_8_french.h +16 -0
- data/ext/stem_UTF_8_german.h +16 -0
- data/ext/stem_UTF_8_hungarian.h +16 -0
- data/ext/stem_UTF_8_italian.h +16 -0
- data/ext/stem_UTF_8_norwegian.h +16 -0
- data/ext/stem_UTF_8_porter.h +16 -0
- data/ext/stem_UTF_8_portuguese.h +16 -0
- data/ext/stem_UTF_8_romanian.h +16 -0
- data/ext/stem_UTF_8_russian.h +16 -0
- data/ext/stem_UTF_8_spanish.h +16 -0
- data/ext/stem_UTF_8_swedish.h +16 -0
- data/ext/stem_UTF_8_turkish.h +16 -0
- data/ext/stopwords.c +410 -0
- data/ext/store.c +698 -0
- data/ext/store.h +799 -0
- data/ext/symbol.c +10 -0
- data/ext/symbol.h +23 -0
- data/ext/term_vectors.c +73 -0
- data/ext/threading.h +31 -0
- data/ext/win32.h +62 -0
- data/lib/ferret.rb +30 -0
- data/lib/ferret/browser.rb +246 -0
- data/lib/ferret/browser/s/global.js +192 -0
- data/lib/ferret/browser/s/style.css +148 -0
- data/lib/ferret/browser/views/document/list.rhtml +49 -0
- data/lib/ferret/browser/views/document/show.rhtml +27 -0
- data/lib/ferret/browser/views/error/index.rhtml +7 -0
- data/lib/ferret/browser/views/help/index.rhtml +8 -0
- data/lib/ferret/browser/views/home/index.rhtml +29 -0
- data/lib/ferret/browser/views/layout.rhtml +22 -0
- data/lib/ferret/browser/views/term-vector/index.rhtml +4 -0
- data/lib/ferret/browser/views/term/index.rhtml +199 -0
- data/lib/ferret/browser/views/term/termdocs.rhtml +1 -0
- data/lib/ferret/browser/webrick.rb +14 -0
- data/lib/ferret/document.rb +130 -0
- data/lib/ferret/field_infos.rb +44 -0
- data/lib/ferret/field_symbol.rb +87 -0
- data/lib/ferret/index.rb +973 -0
- data/lib/ferret/number_tools.rb +157 -0
- data/lib/ferret/version.rb +3 -0
- data/setup.rb +1555 -0
- data/test/long_running/largefile/tc_largefile.rb +46 -0
- data/test/test_all.rb +5 -0
- data/test/test_helper.rb +29 -0
- data/test/test_installed.rb +1 -0
- data/test/threading/number_to_spoken.rb +132 -0
- data/test/threading/thread_safety_index_test.rb +88 -0
- data/test/threading/thread_safety_read_write_test.rb +73 -0
- data/test/threading/thread_safety_test.rb +133 -0
- data/test/unit/analysis/tc_analyzer.rb +550 -0
- data/test/unit/analysis/tc_token_stream.rb +653 -0
- data/test/unit/index/tc_index.rb +867 -0
- data/test/unit/index/tc_index_reader.rb +699 -0
- data/test/unit/index/tc_index_writer.rb +447 -0
- data/test/unit/index/th_doc.rb +332 -0
- data/test/unit/query_parser/tc_query_parser.rb +238 -0
- data/test/unit/search/tc_filter.rb +156 -0
- data/test/unit/search/tc_fuzzy_query.rb +147 -0
- data/test/unit/search/tc_index_searcher.rb +67 -0
- data/test/unit/search/tc_multi_searcher.rb +128 -0
- data/test/unit/search/tc_multiple_search_requests.rb +58 -0
- data/test/unit/search/tc_search_and_sort.rb +179 -0
- data/test/unit/search/tc_sort.rb +49 -0
- data/test/unit/search/tc_sort_field.rb +27 -0
- data/test/unit/search/tc_spans.rb +190 -0
- data/test/unit/search/tm_searcher.rb +436 -0
- data/test/unit/store/tc_fs_store.rb +115 -0
- data/test/unit/store/tc_ram_store.rb +35 -0
- data/test/unit/store/tm_store.rb +34 -0
- data/test/unit/store/tm_store_lock.rb +68 -0
- data/test/unit/tc_document.rb +81 -0
- data/test/unit/tc_field_symbol.rb +26 -0
- data/test/unit/ts_analysis.rb +2 -0
- data/test/unit/ts_index.rb +2 -0
- data/test/unit/ts_largefile.rb +4 -0
- data/test/unit/ts_query_parser.rb +2 -0
- data/test/unit/ts_search.rb +2 -0
- data/test/unit/ts_store.rb +2 -0
- data/test/unit/ts_utils.rb +2 -0
- data/test/unit/utils/tc_bit_vector.rb +295 -0
- data/test/unit/utils/tc_number_tools.rb +117 -0
- data/test/unit/utils/tc_priority_queue.rb +106 -0
- data/test/utils/content_generator.rb +226 -0
- metadata +319 -0
data/ext/analysis.h
ADDED
@@ -0,0 +1,266 @@
|
|
1
|
+
#ifndef FRT_ANALYSIS_H
|
2
|
+
#define FRT_ANALYSIS_H
|
3
|
+
|
4
|
+
#ifdef __cplusplus
|
5
|
+
extern "C" {
|
6
|
+
#endif
|
7
|
+
|
8
|
+
#include "global.h"
|
9
|
+
#include "hash.h"
|
10
|
+
#include "symbol.h"
|
11
|
+
#include "multimapper.h"
|
12
|
+
#include <wchar.h>
|
13
|
+
|
14
|
+
/****************************************************************************
|
15
|
+
*
|
16
|
+
* FrtToken
|
17
|
+
*
|
18
|
+
****************************************************************************/
|
19
|
+
|
20
|
+
typedef struct FrtToken
|
21
|
+
{
|
22
|
+
char text[FRT_MAX_WORD_SIZE];
|
23
|
+
int len;
|
24
|
+
off_t start;
|
25
|
+
off_t end;
|
26
|
+
int pos_inc;
|
27
|
+
} FrtToken;
|
28
|
+
|
29
|
+
extern FrtToken *frt_tk_new();
|
30
|
+
extern void frt_tk_destroy(void *p);
|
31
|
+
extern FrtToken *frt_tk_set(FrtToken *tk, char *text, int tlen, off_t start, off_t end,
|
32
|
+
int pos_inc);
|
33
|
+
extern FrtToken *frt_tk_set_no_len(FrtToken *tk, char *text, off_t start, off_t end,
|
34
|
+
int pos_inc);
|
35
|
+
extern int frt_tk_eq(FrtToken *tk1, FrtToken *tk2);
|
36
|
+
extern int frt_tk_cmp(FrtToken *tk1, FrtToken *tk2);
|
37
|
+
|
38
|
+
/****************************************************************************
|
39
|
+
*
|
40
|
+
* FrtTokenStream
|
41
|
+
*
|
42
|
+
****************************************************************************/
|
43
|
+
|
44
|
+
|
45
|
+
typedef struct FrtTokenStream FrtTokenStream;
|
46
|
+
struct FrtTokenStream
|
47
|
+
{
|
48
|
+
char *t; /* ptr used to scan text */
|
49
|
+
char *text;
|
50
|
+
FrtToken *(*next)(FrtTokenStream *ts);
|
51
|
+
FrtTokenStream *(*reset)(FrtTokenStream *ts, char *text);
|
52
|
+
FrtTokenStream *(*clone_i)(FrtTokenStream *ts);
|
53
|
+
void (*destroy_i)(FrtTokenStream *ts);
|
54
|
+
int ref_cnt;
|
55
|
+
};
|
56
|
+
|
57
|
+
#define frt_ts_new(type) frt_ts_new_i(sizeof(type))
|
58
|
+
extern FrtTokenStream *frt_ts_new_i(size_t size);
|
59
|
+
extern FrtTokenStream *frt_ts_clone_size(FrtTokenStream *orig_ts, size_t size);
|
60
|
+
|
61
|
+
typedef struct FrtCachedTokenStream
|
62
|
+
{
|
63
|
+
FrtTokenStream super;
|
64
|
+
FrtToken token;
|
65
|
+
} FrtCachedTokenStream;
|
66
|
+
|
67
|
+
typedef struct FrtMultiByteTokenStream
|
68
|
+
{
|
69
|
+
FrtCachedTokenStream super;
|
70
|
+
mbstate_t state;
|
71
|
+
} FrtMultiByteTokenStream;
|
72
|
+
|
73
|
+
typedef enum
|
74
|
+
{
|
75
|
+
FRT_STT_ASCII,
|
76
|
+
FRT_STT_MB,
|
77
|
+
FRT_STT_UTF8
|
78
|
+
} FrtStandardTokenizerType;
|
79
|
+
|
80
|
+
typedef struct FrtStandardTokenizer
|
81
|
+
{
|
82
|
+
FrtCachedTokenStream super;
|
83
|
+
FrtStandardTokenizerType type;
|
84
|
+
} FrtStandardTokenizer;
|
85
|
+
|
86
|
+
typedef struct FrtLegacyStandardTokenizer
|
87
|
+
{
|
88
|
+
FrtCachedTokenStream super;
|
89
|
+
bool (*advance_to_start)(FrtTokenStream *ts);
|
90
|
+
bool (*is_tok_char)(char *c);
|
91
|
+
int (*get_alpha)(FrtTokenStream *ts, char *token);
|
92
|
+
int (*get_apostrophe)(char *input);
|
93
|
+
} FrtLegacyStandardTokenizer;
|
94
|
+
|
95
|
+
typedef struct FrtTokenFilter
|
96
|
+
{
|
97
|
+
FrtTokenStream super;
|
98
|
+
FrtTokenStream *sub_ts;
|
99
|
+
} FrtTokenFilter;
|
100
|
+
|
101
|
+
extern FrtTokenStream *frt_filter_clone_size(FrtTokenStream *ts, size_t size);
|
102
|
+
#define tf_new(type, sub) frt_tf_new_i(sizeof(type), sub)
|
103
|
+
extern FrtTokenStream *frt_tf_new_i(size_t size, FrtTokenStream *sub_ts);
|
104
|
+
|
105
|
+
typedef struct FrtStopFilter
|
106
|
+
{
|
107
|
+
FrtTokenFilter super;
|
108
|
+
FrtHash *words;
|
109
|
+
} FrtStopFilter;
|
110
|
+
|
111
|
+
typedef struct FrtMappingFilter
|
112
|
+
{
|
113
|
+
FrtTokenFilter super;
|
114
|
+
FrtMultiMapper *mapper;
|
115
|
+
} FrtMappingFilter;
|
116
|
+
|
117
|
+
typedef struct FrtHyphenFilter
|
118
|
+
{
|
119
|
+
FrtTokenFilter super;
|
120
|
+
char text[FRT_MAX_WORD_SIZE];
|
121
|
+
int start;
|
122
|
+
int pos;
|
123
|
+
int len;
|
124
|
+
FrtToken *tk;
|
125
|
+
} FrtHyphenFilter;
|
126
|
+
|
127
|
+
typedef struct FrtStemFilter
|
128
|
+
{
|
129
|
+
FrtTokenFilter super;
|
130
|
+
struct sb_stemmer *stemmer;
|
131
|
+
char *algorithm;
|
132
|
+
char *charenc;
|
133
|
+
} FrtStemFilter;
|
134
|
+
|
135
|
+
#define frt_ts_next(mts) mts->next(mts)
|
136
|
+
#define frt_ts_clone(mts) mts->clone_i(mts)
|
137
|
+
|
138
|
+
extern void frt_ts_deref(FrtTokenStream *ts);
|
139
|
+
|
140
|
+
extern FrtTokenStream *frt_non_tokenizer_new();
|
141
|
+
|
142
|
+
extern FrtTokenStream *frt_whitespace_tokenizer_new();
|
143
|
+
extern FrtTokenStream *frt_mb_whitespace_tokenizer_new(bool lowercase);
|
144
|
+
|
145
|
+
extern FrtTokenStream *frt_letter_tokenizer_new();
|
146
|
+
extern FrtTokenStream *frt_mb_letter_tokenizer_new(bool lowercase);
|
147
|
+
|
148
|
+
extern FrtTokenStream *frt_standard_tokenizer_new();
|
149
|
+
extern FrtTokenStream *frt_mb_standard_tokenizer_new();
|
150
|
+
extern FrtTokenStream *frt_utf8_standard_tokenizer_new();
|
151
|
+
|
152
|
+
extern FrtTokenStream *frt_legacy_standard_tokenizer_new();
|
153
|
+
extern FrtTokenStream *frt_mb_legacy_standard_tokenizer_new();
|
154
|
+
|
155
|
+
extern FrtTokenStream *frt_hyphen_filter_new(FrtTokenStream *ts);
|
156
|
+
extern FrtTokenStream *frt_lowercase_filter_new(FrtTokenStream *ts);
|
157
|
+
extern FrtTokenStream *frt_mb_lowercase_filter_new(FrtTokenStream *ts);
|
158
|
+
|
159
|
+
extern const char *FRT_ENGLISH_STOP_WORDS[];
|
160
|
+
extern const char *FRT_FULL_ENGLISH_STOP_WORDS[];
|
161
|
+
extern const char *FRT_EXTENDED_ENGLISH_STOP_WORDS[];
|
162
|
+
extern const char *FRT_FULL_FRENCH_STOP_WORDS[];
|
163
|
+
extern const char *FRT_FULL_SPANISH_STOP_WORDS[];
|
164
|
+
extern const char *FRT_FULL_PORTUGUESE_STOP_WORDS[];
|
165
|
+
extern const char *FRT_FULL_ITALIAN_STOP_WORDS[];
|
166
|
+
extern const char *FRT_FULL_GERMAN_STOP_WORDS[];
|
167
|
+
extern const char *FRT_FULL_DUTCH_STOP_WORDS[];
|
168
|
+
extern const char *FRT_FULL_SWEDISH_STOP_WORDS[];
|
169
|
+
extern const char *FRT_FULL_NORWEGIAN_STOP_WORDS[];
|
170
|
+
extern const char *FRT_FULL_DANISH_STOP_WORDS[];
|
171
|
+
extern const char *FRT_FULL_RUSSIAN_STOP_WORDS[];
|
172
|
+
extern const char *FRT_FULL_FINNISH_STOP_WORDS[];
|
173
|
+
extern const char *FRT_FULL_HUNGARIAN_STOP_WORDS[];
|
174
|
+
extern const char *FRT_FULL_RUSSIAN_STOP_WORDS_KOI8_R[];
|
175
|
+
|
176
|
+
extern FrtTokenStream *frt_stop_filter_new_with_words_len(FrtTokenStream *ts,
|
177
|
+
const char **words, int len);
|
178
|
+
extern FrtTokenStream *frt_stop_filter_new_with_words(FrtTokenStream *ts,
|
179
|
+
const char **words);
|
180
|
+
extern FrtTokenStream *frt_stop_filter_new(FrtTokenStream *ts);
|
181
|
+
extern FrtTokenStream *frt_stem_filter_new(FrtTokenStream *ts, const char *algorithm,
|
182
|
+
const char *charenc);
|
183
|
+
|
184
|
+
extern FrtTokenStream *frt_mapping_filter_new(FrtTokenStream *ts);
|
185
|
+
extern FrtTokenStream *frt_mapping_filter_add(FrtTokenStream *ts, const char *pattern,
|
186
|
+
const char *replacement);
|
187
|
+
|
188
|
+
/****************************************************************************
|
189
|
+
*
|
190
|
+
* FrtAnalyzer
|
191
|
+
*
|
192
|
+
****************************************************************************/
|
193
|
+
|
194
|
+
typedef struct FrtAnalyzer
|
195
|
+
{
|
196
|
+
FrtTokenStream *current_ts;
|
197
|
+
FrtTokenStream *(*get_ts)(struct FrtAnalyzer *a, FrtSymbol field, char *text);
|
198
|
+
void (*destroy_i)(struct FrtAnalyzer *a);
|
199
|
+
int ref_cnt;
|
200
|
+
} FrtAnalyzer;
|
201
|
+
|
202
|
+
extern void frt_a_deref(FrtAnalyzer *a);
|
203
|
+
|
204
|
+
#define frt_a_get_ts(ma, field, text) ma->get_ts(ma, field, text)
|
205
|
+
|
206
|
+
extern FrtAnalyzer *frt_analyzer_new(FrtTokenStream *ts,
|
207
|
+
void (*destroy)(FrtAnalyzer *a),
|
208
|
+
FrtTokenStream *(*get_ts)(FrtAnalyzer *a,
|
209
|
+
FrtSymbol field,
|
210
|
+
char *text));
|
211
|
+
extern void frt_a_standard_destroy(FrtAnalyzer *a);
|
212
|
+
extern FrtAnalyzer *frt_non_analyzer_new();
|
213
|
+
|
214
|
+
extern FrtAnalyzer *frt_whitespace_analyzer_new(bool lowercase);
|
215
|
+
extern FrtAnalyzer *frt_mb_whitespace_analyzer_new(bool lowercase);
|
216
|
+
|
217
|
+
extern FrtAnalyzer *frt_letter_analyzer_new(bool lowercase);
|
218
|
+
extern FrtAnalyzer *frt_mb_letter_analyzer_new(bool lowercase);
|
219
|
+
|
220
|
+
extern FrtAnalyzer *frt_standard_analyzer_new(bool lowercase);
|
221
|
+
extern FrtAnalyzer *frt_mb_standard_analyzer_new(bool lowercase);
|
222
|
+
extern FrtAnalyzer *frt_utf8_standard_analyzer_new(bool lowercase);
|
223
|
+
|
224
|
+
extern FrtAnalyzer *frt_standard_analyzer_new_with_words(
|
225
|
+
const char **words, bool lowercase);
|
226
|
+
extern FrtAnalyzer *frt_standard_analyzer_new_with_words_len(
|
227
|
+
const char **words, int len, bool lowercase);
|
228
|
+
extern FrtAnalyzer *frt_mb_standard_analyzer_new_with_words(
|
229
|
+
const char **words, bool lowercase);
|
230
|
+
extern FrtAnalyzer *frt_mb_standard_analyzer_new_with_words_len(
|
231
|
+
const char **words, int len, bool lowercase);
|
232
|
+
extern FrtAnalyzer *frt_utf8_standard_analyzer_new_with_words(
|
233
|
+
const char **words, bool lowercase);
|
234
|
+
extern FrtAnalyzer *frt_utf8_standard_analyzer_new_with_words_len(
|
235
|
+
const char **words, int len, bool lowercase);
|
236
|
+
|
237
|
+
extern FrtAnalyzer *frt_legacy_standard_analyzer_new(bool lowercase);
|
238
|
+
extern FrtAnalyzer *frt_mb_legacy_standard_analyzer_new(bool lowercase);
|
239
|
+
|
240
|
+
extern FrtAnalyzer *frt_legacy_standard_analyzer_new_with_words(
|
241
|
+
const char **words, bool lowercase);
|
242
|
+
extern FrtAnalyzer *frt_legacy_standard_analyzer_new_with_words_len(
|
243
|
+
const char **words, int len, bool lowercase);
|
244
|
+
extern FrtAnalyzer *frt_mb_legacy_standard_analyzer_new_with_words(
|
245
|
+
const char **words, bool lowercase);
|
246
|
+
extern FrtAnalyzer *frt_mb_legacy_standard_analyzer_new_with_words_len(
|
247
|
+
const char **words, int len, bool lowercase);
|
248
|
+
|
249
|
+
#define PFA(analyzer) ((FrtPerFieldAnalyzer *)(analyzer))
|
250
|
+
typedef struct FrtPerFieldAnalyzer
|
251
|
+
{
|
252
|
+
FrtAnalyzer super;
|
253
|
+
FrtHash *dict;
|
254
|
+
FrtAnalyzer *default_a;
|
255
|
+
} FrtPerFieldAnalyzer;
|
256
|
+
|
257
|
+
extern FrtAnalyzer *frt_per_field_analyzer_new(FrtAnalyzer *a);
|
258
|
+
extern void frt_pfa_add_field(FrtAnalyzer *self,
|
259
|
+
FrtSymbol field,
|
260
|
+
FrtAnalyzer *analyzer);
|
261
|
+
|
262
|
+
#ifdef __cplusplus
|
263
|
+
} // extern "C"
|
264
|
+
#endif
|
265
|
+
|
266
|
+
#endif
|
data/ext/api.h
ADDED
@@ -0,0 +1,26 @@
|
|
1
|
+
|
2
|
+
typedef unsigned char symbol;
|
3
|
+
|
4
|
+
/* Or replace 'char' above with 'short' for 16 bit characters.
|
5
|
+
|
6
|
+
More precisely, replace 'char' with whatever type guarantees the
|
7
|
+
character width you need. Note however that sizeof(symbol) should divide
|
8
|
+
HEAD, defined in header.h as 2*sizeof(int), without remainder, otherwise
|
9
|
+
there is an alignment problem. In the unlikely event of a problem here,
|
10
|
+
consult Martin Porter.
|
11
|
+
|
12
|
+
*/
|
13
|
+
|
14
|
+
struct SN_env {
|
15
|
+
symbol * p;
|
16
|
+
int c; int l; int lb; int bra; int ket;
|
17
|
+
symbol * * S;
|
18
|
+
int * I;
|
19
|
+
unsigned char * B;
|
20
|
+
};
|
21
|
+
|
22
|
+
extern struct SN_env * SN_create_env(int S_size, int I_size, int B_size);
|
23
|
+
extern void SN_close_env(struct SN_env * z, int S_size);
|
24
|
+
|
25
|
+
extern int SN_set_current(struct SN_env * z, int size, const symbol * s);
|
26
|
+
|
data/ext/array.c
ADDED
@@ -0,0 +1,125 @@
|
|
1
|
+
#include "array.h"
|
2
|
+
#include <string.h>
|
3
|
+
#include "internal.h"
|
4
|
+
|
5
|
+
#define META_CNT ARY_META_CNT
|
6
|
+
#define DATA_SZ sizeof(int) * META_CNT
|
7
|
+
|
8
|
+
void **ary_new_i(int type_size, int init_capa)
|
9
|
+
{
|
10
|
+
void **ary;
|
11
|
+
if (init_capa <= 0) {
|
12
|
+
init_capa = ARY_INIT_CAPA;
|
13
|
+
}
|
14
|
+
ary = (void **)&(((int *)ecalloc(DATA_SZ +
|
15
|
+
init_capa * type_size))[META_CNT]);
|
16
|
+
ary_type_size(ary) = type_size;
|
17
|
+
ary_capa(ary) = init_capa;
|
18
|
+
return ary;
|
19
|
+
}
|
20
|
+
|
21
|
+
INLINE void ary_resize_i(void ***ary, int size)
|
22
|
+
{
|
23
|
+
size++;
|
24
|
+
if (size > ary_sz(*ary)) {
|
25
|
+
int capa = ary_capa(*ary);
|
26
|
+
if (size >= capa) {
|
27
|
+
int *ary_start = &((int *)*ary)[-META_CNT];
|
28
|
+
while (size >= capa) {
|
29
|
+
capa <<= 1;
|
30
|
+
}
|
31
|
+
|
32
|
+
ary_start = (int *)erealloc(ary_start,
|
33
|
+
DATA_SZ + capa * ary_type_size(*ary));
|
34
|
+
*ary = (void **)&(ary_start[META_CNT]);
|
35
|
+
memset(((char *)*ary) + ary_type_size(*ary) * ary_sz(*ary), 0,
|
36
|
+
(capa - ary_sz(*ary)) * ary_type_size(*ary));
|
37
|
+
ary_capa(*ary) = capa;
|
38
|
+
}
|
39
|
+
ary_sz(*ary) = size;
|
40
|
+
}
|
41
|
+
}
|
42
|
+
|
43
|
+
void ary_set_i(void ***ary, int index, void *value)
|
44
|
+
{
|
45
|
+
if (index < 0) {
|
46
|
+
index += ary_sz(*ary);
|
47
|
+
if (index < 0) {
|
48
|
+
RAISE(INDEX_ERROR, "index %d out array", index);
|
49
|
+
}
|
50
|
+
}
|
51
|
+
ary_resize_i(ary, index);
|
52
|
+
(*ary)[index] = value;
|
53
|
+
}
|
54
|
+
|
55
|
+
void *ary_get_i(void **ary, int index)
|
56
|
+
{
|
57
|
+
if (index < 0) {
|
58
|
+
index += ary_sz(ary);
|
59
|
+
}
|
60
|
+
if (index >= 0 && index < ary_sz(ary)) {
|
61
|
+
return ary[index];
|
62
|
+
}
|
63
|
+
else {
|
64
|
+
return NULL;
|
65
|
+
}
|
66
|
+
}
|
67
|
+
|
68
|
+
void ary_push_i(void ***ary, void *value)
|
69
|
+
{
|
70
|
+
int size = ary_sz(*ary);
|
71
|
+
ary_resize_i(ary, size);
|
72
|
+
(*ary)[size] = value;
|
73
|
+
}
|
74
|
+
|
75
|
+
void *ary_pop_i(void **ary)
|
76
|
+
{
|
77
|
+
void *val = ary[--ary_sz(ary)];
|
78
|
+
ary[ary_sz(ary)] = NULL;
|
79
|
+
return val;
|
80
|
+
}
|
81
|
+
|
82
|
+
void ary_unshift_i(void ***ary, void *value)
|
83
|
+
{
|
84
|
+
int size = ary_sz(*ary);
|
85
|
+
ary_resize_i(ary, size);
|
86
|
+
memmove(*ary + 1, *ary, size * sizeof(void *));
|
87
|
+
(*ary)[0] = value;
|
88
|
+
}
|
89
|
+
|
90
|
+
void *ary_shift_i(void **ary)
|
91
|
+
{
|
92
|
+
void *val = ary[0];
|
93
|
+
int size = --ary_sz(ary);
|
94
|
+
memmove(ary, ary + 1, size * sizeof(void *));
|
95
|
+
ary[size] = NULL;
|
96
|
+
return val;
|
97
|
+
}
|
98
|
+
|
99
|
+
void *ary_remove_i(void **ary, int index)
|
100
|
+
{
|
101
|
+
if (index >= 0 && index < ary_sz(ary)) {
|
102
|
+
void *val = ary[index];
|
103
|
+
memmove(ary + index, ary + index + 1,
|
104
|
+
(ary_sz(ary) - index + 1) * sizeof(void *));
|
105
|
+
ary_sz(ary)--;
|
106
|
+
return val;
|
107
|
+
}
|
108
|
+
else {
|
109
|
+
return NULL;
|
110
|
+
}
|
111
|
+
}
|
112
|
+
|
113
|
+
void ary_delete_i(void **ary, int index, void (*free_elem)(void *p))
|
114
|
+
{
|
115
|
+
free_elem(ary_remove(ary, index));
|
116
|
+
}
|
117
|
+
|
118
|
+
void ary_destroy_i(void **ary, void (*free_elem)(void *p))
|
119
|
+
{
|
120
|
+
int i;
|
121
|
+
for (i = ary_sz(ary) - 1; i >= 0; i--) {
|
122
|
+
free_elem(ary[i]);
|
123
|
+
}
|
124
|
+
ary_free(ary);
|
125
|
+
}
|
data/ext/array.h
ADDED
@@ -0,0 +1,62 @@
|
|
1
|
+
#ifndef FRT_ARRAY_H
|
2
|
+
#define FRT_ARRAY_H
|
3
|
+
|
4
|
+
#ifdef __cplusplus
|
5
|
+
extern "C" {
|
6
|
+
#endif
|
7
|
+
|
8
|
+
#include "global.h"
|
9
|
+
|
10
|
+
#if defined POSH_OS_SOLARIS || defined POSH_OS_SUNOS
|
11
|
+
# define FRT_ARY_META_CNT 4
|
12
|
+
#else
|
13
|
+
# define FRT_ARY_META_CNT 3
|
14
|
+
#endif
|
15
|
+
|
16
|
+
#define FRT_ARY_INIT_CAPA 8
|
17
|
+
#define frt_ary_size(ary) frt_ary_sz(ary)
|
18
|
+
#define frt_ary_sz(ary) (((int *)ary)[-1])
|
19
|
+
#define frt_ary_capa(ary) (((int *)ary)[-2])
|
20
|
+
#define frt_ary_type_size(ary) (((int *)ary)[-3])
|
21
|
+
#define frt_ary_start(ary) ((void **)&(((int *)ary)[-FRT_ARY_META_CNT]))
|
22
|
+
#define frt_ary_free(ary) free(frt_ary_start(ary))
|
23
|
+
|
24
|
+
#define frt_ary_new_type_capa(type, init_capa)\
|
25
|
+
(type *)frt_ary_new_i(sizeof(type), init_capa)
|
26
|
+
#define frt_ary_new_type(type) (type *)frt_ary_new_i(sizeof(type), 0)
|
27
|
+
#define frt_ary_new_capa(init_capa) frt_ary_new_i(sizeof(void *), init_capa)
|
28
|
+
#define frt_ary_new() frt_ary_new_i(sizeof(void *), 0)
|
29
|
+
#define frt_ary_resize(ary, size) frt_ary_resize_i(((void ***)(void *)&ary), size)
|
30
|
+
#define frt_ary_set(ary, i, val) frt_ary_set_i(((void ***)(void *)&ary), i, val)
|
31
|
+
#define frt_ary_get(ary, i) frt_ary_get_i(((void **)ary), i)
|
32
|
+
#define frt_ary_push(ary, val) frt_ary_push_i(((void ***)(void *)&ary), val)
|
33
|
+
#define frt_ary_pop(ary) frt_ary_pop_i(((void **)ary))
|
34
|
+
#define frt_ary_unshift(ary, val) frt_ary_unshift_i(((void ***)(void *)&ary), val)
|
35
|
+
#define frt_ary_shift(ary) frt_ary_shift_i(((void **)ary))
|
36
|
+
#define frt_ary_remove(ary, i) frt_ary_remove_i(((void **)ary), i)
|
37
|
+
#define frt_ary_delete(ary, i, f) frt_ary_delete_i(((void **)ary), i, (free_ft)f)
|
38
|
+
#define frt_ary_destroy(ary, f) frt_ary_destroy_i(((void **)ary), (free_ft)f)
|
39
|
+
#define frt_ary_rsz(ary, size) frt_ary_resize(ary, size)
|
40
|
+
#define frt_ary_grow(ary) frt_ary_resize(ary, frt_ary_sz(ary))
|
41
|
+
#define frt_ary_last(ary) ary[frt_ary_sz(ary) - 1]
|
42
|
+
#define frt_ary_sort(ary, cmp) qsort(ary, frt_ary_size(ary), frt_ary_type_size(ary), cmp)
|
43
|
+
#define frt_ary_each_rev(ary, i) for (i = frt_ary_size(ary) - 1; i >= 0; i--)
|
44
|
+
#define frt_ary_each(ary, i) for (i = 0; i < frt_ary_size(ary); i++)
|
45
|
+
|
46
|
+
extern void frt_ary_resize_i(void ***ary, int size);
|
47
|
+
extern void **frt_ary_new_i(int type_size, int init_capa);
|
48
|
+
extern void frt_ary_set_i(void ***ary, int index, void *value);
|
49
|
+
extern void *frt_ary_get_i(void **ary, int index);
|
50
|
+
extern void frt_ary_push_i(void ***ary, void *value);
|
51
|
+
extern void *frt_ary_pop_i(void **ary);
|
52
|
+
extern void frt_ary_unshift_i(void ***ary, void *value);
|
53
|
+
extern void *frt_ary_shift_i(void **ary);
|
54
|
+
extern void *frt_ary_remove_i(void **ary, int index);
|
55
|
+
extern void frt_ary_delete_i(void **ary, int index, frt_free_ft p);
|
56
|
+
extern void frt_ary_destroy_i(void **ary, frt_free_ft p);
|
57
|
+
|
58
|
+
#ifdef __cplusplus
|
59
|
+
} // extern "C"
|
60
|
+
#endif
|
61
|
+
|
62
|
+
#endif
|