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
|
/*-------------------------------------------------------------------------
*
* dict_synonym.c
* Synonym dictionary: replace word by its synonym
*
* Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
*
*
* IDENTIFICATION
* src/backend/tsearch/dict_synonym.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "commands/defrem.h"
#include "tsearch/ts_locale.h"
#include "tsearch/ts_utils.h"
#include "utils/builtins.h"
typedef struct
{
char *in;
char *out;
int outlen;
uint16 flags;
} Syn;
typedef struct
{
int len; /* length of syn array */
Syn *syn;
bool case_sensitive;
} DictSyn;
/*
* Finds the next whitespace-delimited word within the 'in' string.
* Returns a pointer to the first character of the word, and a pointer
* to the next byte after the last character in the word (in *end).
* Character '*' at the end of word will not be treated as word
* character if flags is not null.
*/
static char *
findwrd(char *in, char **end, uint16 *flags)
{
char *start;
char *lastchar;
/* Skip leading spaces */
while (*in && t_isspace(in))
in += pg_mblen(in);
/* Return NULL on empty lines */
if (*in == '\0')
{
*end = NULL;
return NULL;
}
lastchar = start = in;
/* Find end of word */
while (*in && !t_isspace(in))
{
lastchar = in;
in += pg_mblen(in);
}
if (in - lastchar == 1 && t_iseq(lastchar, '*') && flags)
{
*flags = TSL_PREFIX;
*end = lastchar;
}
else
{
if (flags)
*flags = 0;
*end = in;
}
return start;
}
static int
compareSyn(const void *a, const void *b)
{
return strcmp(((const Syn *) a)->in, ((const Syn *) b)->in);
}
Datum
dsynonym_init(PG_FUNCTION_ARGS)
{
List *dictoptions = (List *) PG_GETARG_POINTER(0);
DictSyn *d;
ListCell *l;
char *filename = NULL;
bool case_sensitive = false;
tsearch_readline_state trst;
char *starti,
*starto,
*end = NULL;
int cur = 0;
char *line = NULL;
uint16 flags = 0;
foreach(l, dictoptions)
{
DefElem *defel = (DefElem *) lfirst(l);
if (strcmp(defel->defname, "synonyms") == 0)
filename = defGetString(defel);
else if (strcmp(defel->defname, "casesensitive") == 0)
case_sensitive = defGetBoolean(defel);
else
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("unrecognized synonym parameter: \"%s\"",
defel->defname)));
}
if (!filename)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("missing Synonyms parameter")));
filename = get_tsearch_config_filename(filename, "syn");
if (!tsearch_readline_begin(&trst, filename))
ereport(ERROR,
(errcode(ERRCODE_CONFIG_FILE_ERROR),
errmsg("could not open synonym file \"%s\": %m",
filename)));
d = (DictSyn *) palloc0(sizeof(DictSyn));
while ((line = tsearch_readline(&trst)) != NULL)
{
starti = findwrd(line, &end, NULL);
if (!starti)
{
/* Empty line */
goto skipline;
}
if (*end == '\0')
{
/* A line with only one word. Ignore silently. */
goto skipline;
}
*end = '\0';
starto = findwrd(end + 1, &end, &flags);
if (!starto)
{
/* A line with only one word (+whitespace). Ignore silently. */
goto skipline;
}
*end = '\0';
/*
* starti now points to the first word, and starto to the second word
* on the line, with a \0 terminator at the end of both words.
*/
if (cur >= d->len)
{
if (d->len == 0)
{
d->len = 64;
d->syn = (Syn *) palloc(sizeof(Syn) * d->len);
}
else
{
d->len *= 2;
d->syn = (Syn *) repalloc(d->syn, sizeof(Syn) * d->len);
}
}
if (case_sensitive)
{
d->syn[cur].in = pstrdup(starti);
d->syn[cur].out = pstrdup(starto);
}
else
{
d->syn[cur].in = lowerstr(starti);
d->syn[cur].out = lowerstr(starto);
}
d->syn[cur].outlen = strlen(starto);
d->syn[cur].flags = flags;
cur++;
skipline:
pfree(line);
}
tsearch_readline_end(&trst);
d->len = cur;
qsort(d->syn, d->len, sizeof(Syn), compareSyn);
d->case_sensitive = case_sensitive;
PG_RETURN_POINTER(d);
}
Datum
dsynonym_lexize(PG_FUNCTION_ARGS)
{
DictSyn *d = (DictSyn *) PG_GETARG_POINTER(0);
char *in = (char *) PG_GETARG_POINTER(1);
int32 len = PG_GETARG_INT32(2);
Syn key,
*found;
TSLexeme *res;
/* note: d->len test protects against Solaris bsearch-of-no-items bug */
if (len <= 0 || d->len <= 0)
PG_RETURN_POINTER(NULL);
if (d->case_sensitive)
key.in = pnstrdup(in, len);
else
key.in = lowerstr_with_len(in, len);
key.out = NULL;
found = (Syn *) bsearch(&key, d->syn, d->len, sizeof(Syn), compareSyn);
pfree(key.in);
if (!found)
PG_RETURN_POINTER(NULL);
res = palloc0(sizeof(TSLexeme) * 2);
res[0].lexeme = pnstrdup(found->out, found->outlen);
res[0].flags = found->flags;
PG_RETURN_POINTER(res);
}
|
