Classes in this File | Line Coverage | Branch Coverage | Complexity | ||||||||
XMLTokener |
|
| 17.8;17.8 |
1 | package org.apache.tapestry.json; |
|
2 | ||
3 | /* |
|
4 | Copyright (c) 2002 JSON.org |
|
5 | ||
6 | Permission is hereby granted, free of charge, to any person obtaining a copy |
|
7 | of this software and associated documentation files (the "Software"), to deal |
|
8 | in the Software without restriction, including without limitation the rights |
|
9 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell |
|
10 | copies of the Software, and to permit persons to whom the Software is |
|
11 | furnished to do so, subject to the following conditions: |
|
12 | ||
13 | The above copyright notice and this permission notice shall be included in all |
|
14 | copies or substantial portions of the Software. |
|
15 | ||
16 | The Software shall be used for Good, not Evil. |
|
17 | ||
18 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR |
|
19 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, |
|
20 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE |
|
21 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER |
|
22 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, |
|
23 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE |
|
24 | SOFTWARE. |
|
25 | */ |
|
26 | ||
27 | import java.text.ParseException; |
|
28 | ||
29 | /** |
|
30 | * The XMLTokener extends the JSONTokener to provide additional methods |
|
31 | * for the parsing of XML texts. |
|
32 | * @author JSON.org |
|
33 | * @version 0.1 |
|
34 | */ |
|
35 | public class XMLTokener extends JSONTokener { |
|
36 | ||
37 | ||
38 | /** The table of entity values. It initially contains Character values for |
|
39 | * amp, apos, gt, lt, quot. |
|
40 | */ |
|
41 | public static final java.util.HashMap entity; |
|
42 | ||
43 | static { |
|
44 | 0 | entity = new java.util.HashMap(8); |
45 | 0 | entity.put("amp", XML.AMP); |
46 | 0 | entity.put("apos", XML.APOS); |
47 | 0 | entity.put("gt", XML.GT); |
48 | 0 | entity.put("lt", XML.LT); |
49 | 0 | entity.put("quot", XML.QUOT); |
50 | 0 | } |
51 | ||
52 | /** |
|
53 | * Construct an XMLTokener from a string. |
|
54 | * @param s A source string. |
|
55 | */ |
|
56 | public XMLTokener(String s) { |
|
57 | 0 | super(s); |
58 | 0 | } |
59 | ||
60 | ||
61 | /** |
|
62 | * Get the next XML outer token, trimming whitespace. There are two kinds |
|
63 | * of tokens: the '<' character which begins a markup tag, and the content |
|
64 | * text between markup tags. |
|
65 | * |
|
66 | * @return A string, or a '<' Character, or null if there is no more |
|
67 | * source text. |
|
68 | * @throws ParseException |
|
69 | */ |
|
70 | public Object nextContent() throws ParseException { |
|
71 | char c; |
|
72 | StringBuffer sb; |
|
73 | do { |
|
74 | 0 | c = next(); |
75 | 0 | } while (Character.isWhitespace(c)); |
76 | 0 | if (c == 0) { |
77 | 0 | return null; |
78 | } |
|
79 | 0 | if (c == '<') { |
80 | 0 | return XML.LT; |
81 | } |
|
82 | 0 | sb = new StringBuffer(); |
83 | while (true) { |
|
84 | 0 | if (c == '<' || c == 0) { |
85 | 0 | back(); |
86 | 0 | return sb.toString().trim(); |
87 | } |
|
88 | 0 | if (c == '&') { |
89 | 0 | sb.append(nextEntity(c)); |
90 | } else { |
|
91 | 0 | sb.append(c); |
92 | } |
|
93 | 0 | c = next(); |
94 | } |
|
95 | } |
|
96 | ||
97 | ||
98 | /** |
|
99 | * Return the next entity. These entities are translated to Characters: |
|
100 | * & ' > < " |
|
101 | * @param a An ampersand character. |
|
102 | * @return A Character or an entity String if the entity is not recognized. |
|
103 | * @throws ParseException Missing ';' in XML entity |
|
104 | */ |
|
105 | public Object nextEntity(char a) throws ParseException { |
|
106 | 0 | StringBuffer sb = new StringBuffer(); |
107 | while (true) { |
|
108 | 0 | char c = next(); |
109 | 0 | if (Character.isLetter(c)) { |
110 | 0 | sb.append(Character.toLowerCase(c)); |
111 | 0 | } else if (c == ';') { |
112 | 0 | break; |
113 | } else { |
|
114 | 0 | throw syntaxError("Missing ';' in XML entity: &" + sb); |
115 | } |
|
116 | 0 | } |
117 | 0 | String s = sb.toString(); |
118 | 0 | Object e = entity.get(s); |
119 | 0 | return e != null ? e : a + s + ";"; |
120 | } |
|
121 | ||
122 | ||
123 | /** |
|
124 | * Returns the next XML meta token. This is used for skipping over <!...> |
|
125 | * and <?...?> structures. |
|
126 | * @return Syntax characters (< > / = ! ?) are returned as Character, and |
|
127 | * strings and names are returned as Boolean. We don't care what the |
|
128 | * values actually are. |
|
129 | * @throws ParseException |
|
130 | */ |
|
131 | public Object nextMeta() throws ParseException { |
|
132 | char c; |
|
133 | char q; |
|
134 | do { |
|
135 | 0 | c = next(); |
136 | 0 | } while (Character.isWhitespace(c)); |
137 | 0 | switch (c) { |
138 | case 0: |
|
139 | 0 | throw syntaxError("Misshaped meta tag."); |
140 | case '<': |
|
141 | 0 | return XML.LT; |
142 | case '>': |
|
143 | 0 | return XML.GT; |
144 | case '/': |
|
145 | 0 | return XML.SLASH; |
146 | case '=': |
|
147 | 0 | return XML.EQ; |
148 | case '!': |
|
149 | 0 | return XML.BANG; |
150 | case '?': |
|
151 | 0 | return XML.QUEST; |
152 | case '"': |
|
153 | case '\'': |
|
154 | 0 | q = c; |
155 | while (true) { |
|
156 | 0 | c = next(); |
157 | 0 | if (c == 0) { |
158 | 0 | throw syntaxError("Unterminated string."); |
159 | } |
|
160 | 0 | if (c == q) { |
161 | 0 | return Boolean.TRUE; |
162 | } |
|
163 | } |
|
164 | default: |
|
165 | while (true) { |
|
166 | 0 | c = next(); |
167 | 0 | if (Character.isWhitespace(c)) { |
168 | 0 | return Boolean.TRUE; |
169 | } |
|
170 | 0 | switch (c) { |
171 | case 0: |
|
172 | case '<': |
|
173 | case '>': |
|
174 | case '/': |
|
175 | case '=': |
|
176 | case '!': |
|
177 | case '?': |
|
178 | case '"': |
|
179 | case '\'': |
|
180 | 0 | back(); |
181 | 0 | return Boolean.TRUE; |
182 | } |
|
183 | } |
|
184 | } |
|
185 | } |
|
186 | ||
187 | ||
188 | /** |
|
189 | * Get the next XML Token. These tokens are found inside of angle |
|
190 | * brackets. It may be one of these characters: / > = ! ? or it may be a |
|
191 | * string wrapped in single quotes or double quotes, or it may be a name. |
|
192 | * @return a String or a Character. |
|
193 | * @throws ParseException |
|
194 | */ |
|
195 | public Object nextToken() throws ParseException { |
|
196 | char c; |
|
197 | char q; |
|
198 | StringBuffer sb; |
|
199 | do { |
|
200 | 0 | c = next(); |
201 | 0 | } while (Character.isWhitespace(c)); |
202 | 0 | switch (c) { |
203 | case 0: |
|
204 | 0 | throw syntaxError("Misshaped element."); |
205 | case '<': |
|
206 | 0 | throw syntaxError("Misplaced '<'."); |
207 | case '>': |
|
208 | 0 | return XML.GT; |
209 | case '/': |
|
210 | 0 | return XML.SLASH; |
211 | case '=': |
|
212 | 0 | return XML.EQ; |
213 | case '!': |
|
214 | 0 | return XML.BANG; |
215 | case '?': |
|
216 | 0 | return XML.QUEST; |
217 | ||
218 | // Quoted string |
|
219 | ||
220 | case '"': |
|
221 | case '\'': |
|
222 | 0 | q = c; |
223 | 0 | sb = new StringBuffer(); |
224 | while (true) { |
|
225 | 0 | c = next(); |
226 | 0 | if (c == 0) { |
227 | 0 | throw syntaxError("Unterminated string."); |
228 | } |
|
229 | 0 | if (c == q) { |
230 | 0 | return sb.toString(); |
231 | } |
|
232 | 0 | if (c == '&') { |
233 | 0 | sb.append(nextEntity(c)); |
234 | } else { |
|
235 | 0 | sb.append(c); |
236 | } |
|
237 | } |
|
238 | default: |
|
239 | ||
240 | // Name |
|
241 | ||
242 | 0 | sb = new StringBuffer(); |
243 | while (true) { |
|
244 | 0 | sb.append(c); |
245 | 0 | c = next(); |
246 | 0 | if (Character.isWhitespace(c)) { |
247 | 0 | return sb.toString(); |
248 | } |
|
249 | 0 | switch (c) { |
250 | case 0: |
|
251 | case '>': |
|
252 | case '/': |
|
253 | case '=': |
|
254 | case '!': |
|
255 | case '?': |
|
256 | 0 | back(); |
257 | 0 | return sb.toString(); |
258 | case '<': |
|
259 | case '"': |
|
260 | case '\'': |
|
261 | 0 | throw syntaxError("Bad character in a name."); |
262 | } |
|
263 | } |
|
264 | } |
|
265 | } |
|
266 | } |