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
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
|
/*
* psql - the PostgreSQL interactive terminal
*
* Copyright (c) 2000-2005, PostgreSQL Global Development Group
*
* $PostgreSQL: pgsql/src/bin/psql/stringutils.c,v 1.40 2005/01/01 05:43:08 momjian Exp $
*/
#include "postgres_fe.h"
#include <ctype.h>
#include "libpq-fe.h"
#include "common.h"
#include "settings.h"
#include "stringutils.h"
static void strip_quotes(char *source, char quote, char escape, int encoding);
/*
* Replacement for strtok() (a.k.a. poor man's flex)
*
* Splits a string into tokens, returning one token per call, then NULL
* when no more tokens exist in the given string.
*
* The calling convention is similar to that of strtok, but with more
* frammishes.
*
* s - string to parse, if NULL continue parsing the last string
* whitespace - set of whitespace characters that separate tokens
* delim - set of non-whitespace separator characters (or NULL)
* quote - set of characters that can quote a token (NULL if none)
* escape - character that can quote quotes (0 if none)
* del_quotes - if TRUE, strip quotes from the returned token, else return
* it exactly as found in the string
* encoding - the active character-set encoding
*
* Characters in 'delim', if any, will be returned as single-character
* tokens unless part of a quoted token.
*
* Double occurrences of the quoting character are always taken to represent
* a single quote character in the data. If escape isn't 0, then escape
* followed by anything (except \0) is a data character too.
*
* Note that the string s is _not_ overwritten in this implementation.
*
* NB: it's okay to vary delim, quote, and escape from one call to the
* next on a single source string, but changing whitespace is a bad idea
* since you might lose data.
*/
char *
strtokx(const char *s,
const char *whitespace,
const char *delim,
const char *quote,
char escape,
bool del_quotes,
int encoding)
{
static char *storage = NULL;/* store the local copy of the users
* string here */
static char *string = NULL; /* pointer into storage where to continue
* on next call */
/* variously abused variables: */
unsigned int offset;
char *start;
char *p;
if (s)
{
free(storage);
/*
* We may need extra space to insert delimiter nulls for adjacent
* tokens. 2X the space is a gross overestimate, but it's
* unlikely that this code will be used on huge strings anyway.
*/
storage = pg_malloc(2 * strlen(s) + 1);
strcpy(storage, s);
string = storage;
}
if (!storage)
return NULL;
/* skip leading whitespace */
offset = strspn(string, whitespace);
start = &string[offset];
/* end of string reached? */
if (*start == '\0')
{
/* technically we don't need to free here, but we're nice */
free(storage);
storage = NULL;
string = NULL;
return NULL;
}
/* test if delimiter character */
if (delim && strchr(delim, *start))
{
/*
* If not at end of string, we need to insert a null to terminate
* the returned token. We can just overwrite the next character
* if it happens to be in the whitespace set ... otherwise move
* over the rest of the string to make room. (This is why we
* allocated extra space above).
*/
p = start + 1;
if (*p != '\0')
{
if (!strchr(whitespace, *p))
memmove(p + 1, p, strlen(p) + 1);
*p = '\0';
string = p + 1;
}
else
{
/* at end of string, so no extra work */
string = p;
}
return start;
}
/* test if quoting character */
if (quote && strchr(quote, *start))
{
/* okay, we have a quoted token, now scan for the closer */
char thisquote = *start;
for (p = start + 1; *p; p += PQmblen(p, encoding))
{
if (*p == escape && p[1] != '\0')
p++; /* process escaped anything */
else if (*p == thisquote && p[1] == thisquote)
p++; /* process doubled quote */
else if (*p == thisquote)
{
p++; /* skip trailing quote */
break;
}
}
/*
* If not at end of string, we need to insert a null to terminate
* the returned token. See notes above.
*/
if (*p != '\0')
{
if (!strchr(whitespace, *p))
memmove(p + 1, p, strlen(p) + 1);
*p = '\0';
string = p + 1;
}
else
{
/* at end of string, so no extra work */
string = p;
}
/* Clean up the token if caller wants that */
if (del_quotes)
strip_quotes(start, thisquote, escape, encoding);
return start;
}
/*
* Otherwise no quoting character. Scan till next whitespace,
* delimiter or quote. NB: at this point, *start is known not to be
* '\0', whitespace, delim, or quote, so we will consume at least one
* character.
*/
offset = strcspn(start, whitespace);
if (delim)
{
unsigned int offset2 = strcspn(start, delim);
if (offset > offset2)
offset = offset2;
}
if (quote)
{
unsigned int offset2 = strcspn(start, quote);
if (offset > offset2)
offset = offset2;
}
p = start + offset;
/*
* If not at end of string, we need to insert a null to terminate the
* returned token. See notes above.
*/
if (*p != '\0')
{
if (!strchr(whitespace, *p))
memmove(p + 1, p, strlen(p) + 1);
*p = '\0';
string = p + 1;
}
else
{
/* at end of string, so no extra work */
string = p;
}
return start;
}
/*
* strip_quotes
*
* Remove quotes from the string at *source. Leading and trailing occurrences
* of 'quote' are removed; embedded double occurrences of 'quote' are reduced
* to single occurrences; if 'escape' is not 0 then 'escape' removes special
* significance of next character.
*
* Note that the source string is overwritten in-place.
*/
static void
strip_quotes(char *source, char quote, char escape, int encoding)
{
char *src;
char *dst;
psql_assert(source);
psql_assert(quote);
src = dst = source;
if (*src && *src == quote)
src++; /* skip leading quote */
while (*src)
{
char c = *src;
int i;
if (c == quote && src[1] == '\0')
break; /* skip trailing quote */
else if (c == quote && src[1] == quote)
src++; /* process doubled quote */
else if (c == escape && src[1] != '\0')
src++; /* process escaped character */
i = PQmblen(src, encoding);
while (i--)
*dst++ = *src++;
}
*dst = '\0';
}
|