isomorfeus-ferret 0.12.1 → 0.12.5
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/LICENSE +612 -612
- data/README.md +80 -44
- data/ext/isomorfeus_ferret_ext/bm_hash.c +9 -6
- data/ext/isomorfeus_ferret_ext/bm_micro_string.c +4 -2
- data/ext/isomorfeus_ferret_ext/frb_search.c +14 -2
- data/ext/isomorfeus_ferret_ext/frb_store.c +34 -5
- data/ext/isomorfeus_ferret_ext/frt_fs_store.c +1 -1
- data/ext/isomorfeus_ferret_ext/frt_posh.h +11 -19
- data/ext/isomorfeus_ferret_ext/frt_q_parser.c +1844 -1911
- data/ext/isomorfeus_ferret_ext/frt_q_phrase.c +7 -7
- data/ext/isomorfeus_ferret_ext/frt_scanner.c +1 -0
- data/ext/isomorfeus_ferret_ext/frt_scanner_mb.c +1 -0
- data/ext/isomorfeus_ferret_ext/frt_scanner_utf8.c +1 -0
- data/ext/isomorfeus_ferret_ext/frt_search.h +1 -1
- data/ext/isomorfeus_ferret_ext/libstemmer.c +14 -11
- data/ext/isomorfeus_ferret_ext/libstemmer.h +4 -9
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_basque.c +1167 -0
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_basque.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_catalan.c +1433 -0
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_catalan.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_danish.c +120 -143
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_danish.h +1 -2
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_dutch.c +217 -237
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_dutch.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_english.c +377 -432
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_english.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_finnish.c +298 -342
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_finnish.h +1 -2
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_french.c +530 -524
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_french.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_german.c +201 -214
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_german.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_hungarian.c +1 -1
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_indonesian.c +394 -0
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_indonesian.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_irish.c +457 -0
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_irish.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_italian.c +396 -439
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_italian.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_norwegian.c +104 -128
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_norwegian.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_porter.c +242 -273
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_porter.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_portuguese.c +406 -461
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_portuguese.h +1 -2
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_spanish.c +405 -456
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_spanish.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_swedish.c +108 -126
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_1_swedish.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_2_hungarian.c +849 -0
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_2_hungarian.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_2_romanian.c +373 -405
- data/ext/isomorfeus_ferret_ext/stem_ISO_8859_2_romanian.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_KOI8_R_russian.c +288 -305
- data/ext/isomorfeus_ferret_ext/stem_KOI8_R_russian.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_arabic.c +1651 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_arabic.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_armenian.c +546 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_armenian.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_basque.c +1171 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_basque.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_catalan.c +1436 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_catalan.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_danish.c +121 -141
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_danish.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_dutch.c +221 -241
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_dutch.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_english.c +381 -431
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_english.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_finnish.c +300 -345
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_finnish.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_french.c +518 -511
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_french.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_german.c +201 -209
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_german.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_greek.c +3660 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_greek.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_hindi.c +309 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_hindi.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_hungarian.c +306 -671
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_hungarian.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_indonesian.c +394 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_indonesian.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_irish.c +457 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_irish.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_italian.c +400 -442
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_italian.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_lithuanian.c +824 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_lithuanian.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_nepali.c +408 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_nepali.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_norwegian.c +105 -127
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_norwegian.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_porter.c +245 -276
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_porter.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_portuguese.c +409 -464
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_portuguese.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_romanian.c +376 -408
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_romanian.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_russian.c +272 -287
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_russian.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_serbian.c +6530 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_serbian.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_spanish.c +407 -458
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_spanish.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_swedish.c +110 -125
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_swedish.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_tamil.c +1865 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_tamil.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_turkish.c +698 -806
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_turkish.h +1 -1
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_yiddish.c +1220 -0
- data/ext/isomorfeus_ferret_ext/stem_UTF_8_yiddish.h +6 -0
- data/ext/isomorfeus_ferret_ext/stem_api.c +1 -9
- data/ext/isomorfeus_ferret_ext/stem_api.h +1 -3
- data/ext/isomorfeus_ferret_ext/stem_header.h +30 -26
- data/ext/isomorfeus_ferret_ext/stem_modules.h +113 -26
- data/ext/isomorfeus_ferret_ext/stem_modules.txt +18 -5
- data/ext/isomorfeus_ferret_ext/stem_utilities.c +167 -132
- data/ext/isomorfeus_ferret_ext/test.c +7 -1
- data/ext/isomorfeus_ferret_ext/test_search.c +0 -1
- data/lib/isomorfeus/ferret/index/index.rb +1 -1
- data/lib/isomorfeus/ferret/version.rb +1 -1
- metadata +43 -7
- data/ext/isomorfeus_ferret_ext/q_parser.y +0 -1366
@@ -104,11 +104,12 @@ static int pp_cmp(const void *const p1, const void *const p2)
|
|
104
104
|
{
|
105
105
|
int cmp = PP_pp(p1)->doc - PP_pp(p2)->doc;
|
106
106
|
if (cmp == 0) {
|
107
|
-
|
108
|
-
|
109
|
-
|
110
|
-
|
107
|
+
cmp = PP_pp(p1)->position - PP_pp(p2)->position;
|
108
|
+
if (cmp == 0) {
|
109
|
+
cmp = PP_pp(p1)->offset - PP_pp(p2)->offset;
|
110
|
+
}
|
111
111
|
}
|
112
|
+
return cmp;
|
112
113
|
}
|
113
114
|
|
114
115
|
static int pp_pos_cmp(const void *const p1, const void *const p2)
|
@@ -490,7 +491,6 @@ static float sphsc_phrase_freq(FrtScorer *self)
|
|
490
491
|
if (pqsize == 0) { done = true; }
|
491
492
|
} while (!done);
|
492
493
|
return_freq:
|
493
|
-
|
494
494
|
frt_pq_destroy(pq);
|
495
495
|
return freq;
|
496
496
|
}
|
@@ -545,12 +545,12 @@ static FrtScorer *phw_scorer(FrtWeight *self, FrtIndexReader *ir)
|
|
545
545
|
const int t_cnt = frt_ary_size(terms);
|
546
546
|
if (t_cnt == 1) {
|
547
547
|
tps[i] = ir->term_positions(ir);
|
548
|
+
assert(NULL != tps[i]); /* neither frt_mtdpe_new nor ir->term_positions should return NULL */
|
548
549
|
tps[i]->seek(tps[i], field_num, terms[0]);
|
549
550
|
} else {
|
550
551
|
tps[i] = frt_mtdpe_new(ir, field_num, terms, t_cnt);
|
552
|
+
assert(NULL != tps[i]); /* neither frt_mtdpe_new nor ir->term_positions should return NULL */
|
551
553
|
}
|
552
|
-
/* neither frt_mtdpe_new nor ir->term_positions should return NULL */
|
553
|
-
assert(NULL != tps[i]);
|
554
554
|
}
|
555
555
|
|
556
556
|
if (phq->slop == 0) { /* optimize exact (common) case */
|
@@ -909,7 +909,7 @@ typedef struct FrtQueryParser
|
|
909
909
|
bool use_keywords : 1;
|
910
910
|
bool use_typed_range_query : 1;
|
911
911
|
} FrtQueryParser;
|
912
|
-
typedef FrtQueryParser FrtQParser; /*
|
912
|
+
typedef FrtQueryParser FrtQParser; /* FrtQParser is an alias for FrtQueryParser */
|
913
913
|
|
914
914
|
extern FrtQParser *frt_qp_new(FrtAnalyzer *analyzer);
|
915
915
|
extern void frt_qp_add_field(FrtQParser *self, FrtSymbol field,
|
@@ -22,10 +22,10 @@ sb_stemmer_list(void)
|
|
22
22
|
static stemmer_encoding_t
|
23
23
|
sb_getenc(const char * charenc)
|
24
24
|
{
|
25
|
-
struct stemmer_encoding * encoding;
|
25
|
+
const struct stemmer_encoding * encoding;
|
26
26
|
if (charenc == NULL) return ENC_UTF_8;
|
27
27
|
for (encoding = encodings; encoding->name != 0; encoding++) {
|
28
|
-
|
28
|
+
if (strcmp(encoding->name, charenc) == 0) break;
|
29
29
|
}
|
30
30
|
if (encoding->name == NULL) return ENC_UNKNOWN;
|
31
31
|
return encoding->enc;
|
@@ -35,18 +35,20 @@ extern struct sb_stemmer *
|
|
35
35
|
sb_stemmer_new(const char * algorithm, const char * charenc)
|
36
36
|
{
|
37
37
|
stemmer_encoding_t enc;
|
38
|
-
struct stemmer_modules * module;
|
39
|
-
struct sb_stemmer * stemmer
|
40
|
-
|
41
|
-
if (stemmer == NULL) return NULL;
|
38
|
+
const struct stemmer_modules * module;
|
39
|
+
struct sb_stemmer * stemmer;
|
40
|
+
|
42
41
|
enc = sb_getenc(charenc);
|
43
42
|
if (enc == ENC_UNKNOWN) return NULL;
|
44
43
|
|
45
44
|
for (module = modules; module->name != 0; module++) {
|
46
|
-
|
45
|
+
if (strcmp(module->name, algorithm) == 0 && module->enc == enc) break;
|
47
46
|
}
|
48
47
|
if (module->name == NULL) return NULL;
|
49
|
-
|
48
|
+
|
49
|
+
stemmer = (struct sb_stemmer *) malloc(sizeof(struct sb_stemmer));
|
50
|
+
if (stemmer == NULL) return NULL;
|
51
|
+
|
50
52
|
stemmer->create = module->create;
|
51
53
|
stemmer->close = module->close;
|
52
54
|
stemmer->stem = module->stem;
|
@@ -65,9 +67,10 @@ void
|
|
65
67
|
sb_stemmer_delete(struct sb_stemmer * stemmer)
|
66
68
|
{
|
67
69
|
if (stemmer == 0) return;
|
68
|
-
if (stemmer->close
|
69
|
-
|
70
|
-
|
70
|
+
if (stemmer->close) {
|
71
|
+
stemmer->close(stemmer->env);
|
72
|
+
stemmer->close = 0;
|
73
|
+
}
|
71
74
|
free(stemmer);
|
72
75
|
}
|
73
76
|
|
@@ -26,9 +26,9 @@ const char ** sb_stemmer_list(void);
|
|
26
26
|
*
|
27
27
|
* @param charenc The character encoding. NULL may be passed as
|
28
28
|
* this value, in which case UTF-8 encoding will be assumed. Otherwise,
|
29
|
-
* the argument may be one of "UTF_8", "ISO_8859_1" (
|
30
|
-
* "
|
31
|
-
*
|
29
|
+
* the argument may be one of "UTF_8", "ISO_8859_1" (i.e. Latin 1),
|
30
|
+
* "ISO_8859_2" (i.e. Latin 2) or "KOI8_R" (Russian). Note that case is
|
31
|
+
* significant in this parameter.
|
32
32
|
*
|
33
33
|
* @return NULL if the specified algorithm is not recognised, or the
|
34
34
|
* algorithm is not available for the requested encoding. Otherwise,
|
@@ -60,14 +60,9 @@ void sb_stemmer_delete(struct sb_stemmer * stemmer);
|
|
60
60
|
* If an out-of-memory error occurs, this will return NULL.
|
61
61
|
*/
|
62
62
|
const sb_symbol * sb_stemmer_stem(struct sb_stemmer * stemmer,
|
63
|
-
|
63
|
+
const sb_symbol * word, int size);
|
64
64
|
|
65
65
|
/** Get the length of the result of the last stemmed word.
|
66
66
|
* This should not be called before sb_stemmer_stem() has been called.
|
67
67
|
*/
|
68
68
|
int sb_stemmer_length(struct sb_stemmer * stemmer);
|
69
|
-
|
70
|
-
#ifdef __cplusplus
|
71
|
-
}
|
72
|
-
#endif
|
73
|
-
|