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
|
<!--
Copyright (C) Daniel Stenberg, <daniel@haxx.se>, et al.
SPDX-License-Identifier: curl
-->
# String parsing with `strparse`
The functions take input via a pointer to a pointer, which allows the
functions to advance the pointer on success which then by extension allows
"chaining" of functions like this example that gets a word, a space and then a
second word:
~~~c
if(curlx_str_word(&line, &word1, MAX) ||
curlx_str_singlespace(&line) ||
curlx_str_word(&line, &word2, MAX))
fprintf(stderr, "ERROR\n");
~~~
The input pointer **must** point to a null-terminated buffer area or these
functions risk continuing "off the edge".
## Strings
The functions that return string information does so by populating a
`struct Curl_str`:
~~~c
struct Curl_str {
char *str;
size_t len;
};
~~~
Access the struct fields with `curlx_str()` for the pointer and `curlx_strlen()`
for the length rather than using the struct fields directly.
## `curlx_str_init`
~~~c
void curlx_str_init(struct Curl_str *out)
~~~
This initiates a string struct. The parser functions that store info in
strings always init the string themselves, so this stand-alone use is often
not necessary.
## `curlx_str_assign`
~~~c
void curlx_str_assign(struct Curl_str *out, const char *str, size_t len)
~~~
Set a pointer and associated length in the string struct.
## `curlx_str_word`
~~~c
int curlx_str_word(char **linep, struct Curl_str *out, const size_t max);
~~~
Get a sequence of bytes until the first space or the end of the string. Return
non-zero on error. There is no way to include a space in the word, no sort of
escaping. The word must be at least one byte, otherwise it is considered an
error.
`max` is the longest accepted word, or it returns error.
On a successful return, `linep` is updated to point to the byte immediately
following the parsed word.
## `curlx_str_until`
~~~c
int curlx_str_until(char **linep, struct Curl_str *out, const size_t max,
char delim);
~~~
Like `curlx_str_word` but instead of parsing to space, it parses to a given
custom delimiter non-zero byte `delim`.
`max` is the longest accepted word, or it returns error.
The parsed word must be at least one byte, otherwise it is considered an
error.
## `curlx_str_untilnl`
~~~c
int curlx_str_untilnl(char **linep, struct Curl_str *out, const size_t max);
~~~
Like `curlx_str_untilnl` but instead parses until it finds a "newline byte".
That means either a CR (ASCII 13) or an LF (ASCII 10) octet.
`max` is the longest accepted word, or it returns error.
The parsed word must be at least one byte, otherwise it is considered an
error.
## `curlx_str_cspn`
~~~c
int curlx_str_cspn(const char **linep, struct Curl_str *out, const char *cspn);
~~~
Get a sequence of characters until one of the bytes in the `cspn` string
matches. Similar to the `strcspn` function.
## `curlx_str_quotedword`
~~~c
int curlx_str_quotedword(char **linep, struct Curl_str *out, const size_t max);
~~~
Get a "quoted" word. This means everything that is provided within a leading
and an ending double quote character. No escaping possible.
`max` is the longest accepted word, or it returns error.
The parsed word must be at least one byte, otherwise it is considered an
error.
## `curlx_str_single`
~~~c
int curlx_str_single(char **linep, char byte);
~~~
Advance over a single character provided in `byte`. Return non-zero on error.
## `curlx_str_singlespace`
~~~c
int curlx_str_singlespace(char **linep);
~~~
Advance over a single ASCII space. Return non-zero on error.
## `curlx_str_passblanks`
~~~c
void curlx_str_passblanks(char **linep);
~~~
Advance over all spaces and tabs.
## `curlx_str_trimblanks`
~~~c
void curlx_str_trimblanks(struct Curl_str *out);
~~~
Trim off blanks (spaces and tabs) from the start and the end of the given
string.
## `curlx_str_number`
~~~c
int curlx_str_number(char **linep, curl_size_t *nump, size_t max);
~~~
Get an unsigned decimal number not larger than `max`. Leading zeroes are just
swallowed. Return non-zero on error. Returns error if there was not a single
digit.
## `curlx_str_numblanks`
~~~c
int curlx_str_numblanks(char **linep, curl_size_t *nump);
~~~
Get an unsigned 63-bit decimal number. Leading blanks and zeroes are skipped.
Returns non-zero on error. Returns error if there was not a single digit.
## `curlx_str_hex`
~~~c
int curlx_str_hex(char **linep, curl_size_t *nump, size_t max);
~~~
Get an unsigned hexadecimal number not larger than `max`. Leading zeroes are
just swallowed. Return non-zero on error. Returns error if there was not a
single digit. Does *not* handled `0x` prefix.
## `curlx_str_octal`
~~~c
int curlx_str_octal(char **linep, curl_size_t *nump, size_t max);
~~~
Get an unsigned octal number not larger than `max`. Leading zeroes are just
swallowed. Return non-zero on error. Returns error if there was not a single
digit.
## `curlx_str_newline`
~~~c
int curlx_str_newline(char **linep);
~~~
Check for a single CR or LF. Return non-zero on error */
## `curlx_str_casecompare`
~~~c
int curlx_str_casecompare(struct Curl_str *str, const char *check);
~~~
Returns true if the provided string in the `str` argument matches the `check`
string case insensitively.
## `curlx_str_cmp`
~~~c
int curlx_str_cmp(struct Curl_str *str, const char *check);
~~~
Returns true if the provided string in the `str` argument matches the `check`
string case sensitively. This is *not* the same return code as `strcmp`.
## `curlx_str_nudge`
~~~c
int curlx_str_nudge(struct Curl_str *str, size_t num);
~~~
Removes `num` bytes from the beginning (left) of the string kept in `str`. If
`num` is larger than the string, it instead returns an error.
|
