1 /*
2 __ __ _
3 ___\ \/ /_ __ __ _| |_
4 / _ \\ /| '_ \ / _` | __|
5 | __// \| |_) | (_| | |_
6 \___/_/\_\ .__/ \__,_|\__|
7 |_| XML parser
8
9 Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
10 Copyright (c) 2000-2017 Expat development team
11 Licensed under the MIT license:
12
13 Permission is hereby granted, free of charge, to any person obtaining
14 a copy of this software and associated documentation files (the
15 "Software"), to deal in the Software without restriction, including
16 without limitation the rights to use, copy, modify, merge, publish,
17 distribute, sublicense, and/or sell copies of the Software, and to permit
18 persons to whom the Software is furnished to do so, subject to the
19 following conditions:
20
21 The above copyright notice and this permission notice shall be included
22 in all copies or substantial portions of the Software.
23
24 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
25 EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
26 MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
27 NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
28 DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
29 OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
30 USE OR OTHER DEALINGS IN THE SOFTWARE.
31 */
32
33 #define CHARSET_MAX 41
34
35 static const char *
getTok(const char ** pp)36 getTok(const char **pp) {
37 enum { inAtom, inString, init, inComment };
38 int state = init;
39 const char *tokStart = 0;
40 for (;;) {
41 switch (**pp) {
42 case '\0':
43 return 0;
44 case ' ':
45 case '\r':
46 case '\t':
47 case '\n':
48 if (state == inAtom)
49 return tokStart;
50 break;
51 case '(':
52 if (state == inAtom)
53 return tokStart;
54 if (state != inString)
55 state++;
56 break;
57 case ')':
58 if (state > init)
59 --state;
60 else if (state != inString)
61 return 0;
62 break;
63 case ';':
64 case '/':
65 case '=':
66 if (state == inAtom)
67 return tokStart;
68 if (state == init)
69 return (*pp)++;
70 break;
71 case '\\':
72 ++*pp;
73 if (**pp == '\0')
74 return 0;
75 break;
76 case '"':
77 switch (state) {
78 case inString:
79 ++*pp;
80 return tokStart;
81 case inAtom:
82 return tokStart;
83 case init:
84 tokStart = *pp;
85 state = inString;
86 break;
87 }
88 break;
89 default:
90 if (state == init) {
91 tokStart = *pp;
92 state = inAtom;
93 }
94 break;
95 }
96 ++*pp;
97 }
98 /* not reached */
99 }
100
101 /* key must be lowercase ASCII */
102
103 static int
matchkey(const char * start,const char * end,const char * key)104 matchkey(const char *start, const char *end, const char *key) {
105 if (! start)
106 return 0;
107 for (; start != end; start++, key++)
108 if (*start != *key && *start != 'A' + (*key - 'a'))
109 return 0;
110 return *key == '\0';
111 }
112
113 void
getXMLCharset(const char * buf,char * charset)114 getXMLCharset(const char *buf, char *charset) {
115 const char *next, *p;
116
117 charset[0] = '\0';
118 next = buf;
119 p = getTok(&next);
120 if (matchkey(p, next, "text"))
121 strcpy(charset, "us-ascii");
122 else if (! matchkey(p, next, "application"))
123 return;
124 p = getTok(&next);
125 if (! p || *p != '/')
126 return;
127 p = getTok(&next);
128 if (matchkey(p, next, "xml"))
129 isXml = 1;
130 p = getTok(&next);
131 while (p) {
132 if (*p == ';') {
133 p = getTok(&next);
134 if (matchkey(p, next, "charset")) {
135 p = getTok(&next);
136 if (p && *p == '=') {
137 p = getTok(&next);
138 if (p) {
139 char *s = charset;
140 if (*p == '"') {
141 while (++p != next - 1) {
142 if (*p == '\\')
143 ++p;
144 if (s == charset + CHARSET_MAX - 1) {
145 charset[0] = '\0';
146 break;
147 }
148 *s++ = *p;
149 }
150 *s++ = '\0';
151 } else {
152 if (next - p > CHARSET_MAX - 1)
153 break;
154 while (p != next)
155 *s++ = *p++;
156 *s = 0;
157 break;
158 }
159 }
160 }
161 }
162 } else
163 p = getTok(&next);
164 }
165 }
166
167 int
main(int argc,char ** argv)168 main(int argc, char **argv) {
169 char buf[CHARSET_MAX];
170 getXMLCharset(argv[1], buf);
171 printf("charset = \"%s\"\n", buf);
172 return 0;
173 }
174