aboutsummaryrefslogtreecommitdiffstats
path: root/epan/strutil.h
blob: 38da893a25bce0b9efa86b51a0ad963ef3e7559b (plain)
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
262
263
264
265
266
267
268
269
270
271
/* strutil.h
 * String utility definitions
 *
 * $Id$
 *
 * Wireshark - Network traffic analyzer
 * By Gerald Combs <gerald@wireshark.org>
 * Copyright 1998 Gerald Combs
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version 2
 * of the License, or (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
 */

#ifndef __STRUTIL_H__
#define __STRUTIL_H__

/* ... thus, config.h needs to be #included */

/** @file
 * String handling and conversion utilities.
 */

/** Given a pointer into a data buffer, and to the end of the buffer,
 *  find the end of the (putative) line at that position in the data
 *  buffer.
 *
 * @param data A pointer to the beginning of the data
 * @param dataend A pointer to the end of the data
 * @param eol A pointer that will receive the EOL location
 * @return A pointer to the EOL character(s) in "*eol".
 */
const guchar *find_line_end(const guchar *data, const guchar *dataend,
    const guchar **eol);

/** Get the length of the next token in a line, and the beginning of the
 *  next token after that (if any).
 * @param linep A pointer to the beginning of the line
 * @param lineend A pointer to the end of the line
 * @param next_token Receives the location of the next token
 * @return 0 if there is no next token.
 */
int        get_token_len(const guchar *linep, const guchar *lineend,
    const guchar **next_token);

/** Given a string, generate a string from it that shows non-printable
 *  characters as C-style escapes, and return a pointer to it.
 *
 * @param line A pointer to the input string
 * @param len The length of the input string
 * @return A pointer to the formatted string
 *
 * @see tvb_format_text()
 */
gchar*     format_text(const guchar *line, size_t len);

/**
 * Given a string, generate a string from it that shows non-printable
 * characters as C-style escapes except a whitespace character
 * (space, tab, carriage return, new line, vertical tab, or formfeed)
 * which will be replaced by a space, and return a pointer to it.
 *
 * @param line A pointer to the input string
 * @param len The length of the input string
 * @return A pointer to the formatted string
 *
 */
gchar*     format_text_wsp(const guchar *line, size_t len);

/** Turn an array of bytes into a string showing the bytes in hex.
 *
 * @param bd A pointer to the byte array
 * @param bd_len The length of the byte array
 * @return A pointer to the formatted string
 *
 * @see bytes_to_str_punct()
 */
gchar*     bytes_to_str(const guint8 *bd, int bd_len);

/** Turn an array of bytes into a string showing the bytes in hex,
 *  separated by a punctuation character.
 *
 * @param bd A pointer to the byte array
 * @param bd_len The length of the byte array
 * @param punct The punctuation character
 * @return A pointer to the formatted string
 *
 * @see bytes_to_str()
 */
gchar*     bytes_to_str_punct(const guint8 *bd, int bd_len, gchar punct);

/** Turn a string of hex digits with optional separators (defined by
 *  is_byte_sep() into a byte array.
 *
 * @param hex_str The string of hex digits.
 * @param bytes The GByteArray that will receive the bytes.  This
 *        must be initialized by the caller.
 * @param force_separators If set to TRUE, separators MUST exist between
 *        bytes.
 * @return True if the string was converted successfully
 */
gboolean   hex_str_to_bytes(const char *hex_str, GByteArray *bytes,
    gboolean force_separators);

/** Turn an RFC 3986 percent-encoded string into a byte array.
 *
 * @param uri_str The string of hex digits.
 * @param bytes The GByteArray that will receive the bytes.  This
 *        must be initialized by the caller.
 * @return True if the string was converted successfully
 * @see format_uri()
 */
gboolean   uri_str_to_bytes(const char *uri_str, GByteArray *bytes);

/** Turn a byte array into an RFC 3986 percent-encoded string.
 *
 * @param bytes The GByteArray that will receive the bytes.  This
 *        must be initialized by the caller.
 * @param reserved_chars Normally the "gen-delims" and "sub-delims"
 *        from RFC 3986 (":/?#[]@" and "!$&'()*+,;=" respectively)
 *        plus space (hex value 20) are treated as reserved characters.
 *        If this variable is non-NULL, its contents will be used
 *        instead.
 * @note Any non-printing character determined by isprint(), along
 *       with the % character itself are always reserved.
 * @see uri_str_to_bytes(),  format_text(), isprint()
 */
gchar*     format_uri(const GByteArray *bytes, const gchar *reserved_chars);

/** Turn a OID string representation (dot notation) into a byte array.
 *
 * @param oid_str The OID string (dot notaion).
 * @param bytes The GByteArray that will receive the bytes.  This
 *        must be initialized by the caller.
 * @return True if the string was converted successfully
 */
gboolean   oid_str_to_bytes(const char *oid_str, GByteArray *bytes);

/**
 * Create a copy of a GByteArray
 *
 * @param ba The byte array to be copied.
 * @return If ba exists, a freshly allocated copy.  NULL otherwise.
 *
 * @todo - Should this be in strutil.c?
 */
GByteArray *byte_array_dup(GByteArray *ba);

/**
 * Compare the contents of two GByteArrays
 *
 * @param ba1 A byte array
 * @param ba2 A byte array
 * @return If both arrays are non-NULL and their lengths are equal and
 *         their contents are equal, returns TRUE.  Otherwise, returns
 *         FALSE.
 *
 * @todo - Should this be in strutil.c?
 */
gboolean byte_array_equal(GByteArray *ba1, GByteArray *ba2);


/** Return a XML escaped representation of the unescaped string.
 *  The returned string must be freed when no longer in use.
 *
 * @param unescaped The unescaped string
 * @return An XML-escaped representation of the input string
 */
gchar*     xml_escape(const gchar *unescaped);

/**
 * Return the first occurrence of needle in haystack.
 * Algorithm copied from GNU's glibc 2.3.2 memcmp()
 *
 * @param haystack The data to search
 * @param haystack_len The length of the search data
 * @param needle The string to look for
 * @param needle_len The length of the search string
 * @return A pointer to the first occurrence of "needle" in
 *         "haystack".  If "needle" isn't found or is NULL, or if
 *         "needle_len" is 0, NULL is returned.
 */
const guint8 * epan_memmem(const guint8 *haystack, guint haystack_len,
		const guint8 *needle, guint needle_len);

/** Surround a string or a macro, resolved to a string, with double quotes */
#define _STRINGIFY(a)           # a
#define STRINGIFY(a)            _STRINGIFY(a)

/** Scan a string to make sure it's valid hex.
 *
 * @param string The string to validate
 * @param nbytes The length of the return buffer
 * @return A pointer to a buffer containing the converted raw bytes.  This
 *         buffer must be g_free()d by the caller.
 */
guint8 * convert_string_to_hex(const char *string, size_t *nbytes);

/** Prep a string for case-sensitive vs case-insensitive searching.
 *
 * @param string The search string
 * @param case_insensitive TRUE if case-insensitive, FALSE if not
 * @return A direct copy of the string if it's a case-sensitive search and
 * an uppercased version if not.  In either case the string must be g_free()d
 * by the caller.
 */
char * convert_string_case(const char *string, gboolean case_insensitive);

/** Finds the first occurence of string 'needle' in string 'haystack'.
 *  The matching is done in a case insensitive manner.
 *
 * @param haystack The string possibly containing the substring
 * @param needle The substring to be searched
 * @return A pointer into 'haystack' where 'needle' is first found.
 *   Otherwise it returns NULL.
 */
char * epan_strcasestr(const char *haystack, const char *needle);

/** Guarantee a non-null string.
 *
 * @param string The string to check
 * @return A pointer 'string' if it's non-null, otherwise "[NULL]".
 */
const char * string_or_null(const char *string);

int escape_string_len(const char *string);
char * escape_string(char *dst, const char *string);


void IA5_7BIT_decode(unsigned char * dest, const unsigned char* src, int len);

/** Copy a string, escaping the 'chr' characters in it
 *
 * @param str The string to be copied
 * @param char The character to be escaped
 * @return A copy of the string with every original 'chr' being
 * transformed into double 'chr'.
 */
gchar* ws_strdup_escape_char (const gchar *str, const gchar chr);

/** Copy a string, unescaping the 'chr' characters in it
 *
 * @param str The string to be copied
 * @param char The character to be escaped
 * @return A copy of the string with every occurence of double 'chr' in
 * the original string being copied as a single 'chr'.
 */
gchar* ws_strdup_unescape_char (const gchar *str, const gchar chr);

/** Replace values in a string
 *
 * @param str String containing 0 or more values to be replaced.
 * @param old_val Old value.
 * @param new_val New value. May be NULL, in which case occurences of
 *                           old_value will be removed.
 * @return A newly-allocated version of str with replacement values or
 * NULL on failure.
 */
gchar *string_replace(const gchar* str, const gchar *old_val, const gchar *new_val);

#endif /* __STRUTIL_H__ */