-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathEntities.java
378 lines (341 loc) · 13.3 KB
/
Entities.java
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
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
package org.jsoup.nodes;
import org.jsoup.internal.StringUtil;
import org.jsoup.helper.Validate;
import org.jsoup.parser.CharacterReader;
import org.jsoup.parser.Parser;
import java.io.IOException;
import java.nio.charset.CharsetEncoder;
import java.util.Arrays;
import java.util.HashMap;
import static org.jsoup.nodes.Entities.EscapeMode.base;
import static org.jsoup.nodes.Entities.EscapeMode.extended;
/**
* HTML entities, and escape routines. Source:
* <a href="http://www.w3.org/TR/html5/named-character-references.html#named-character-references">W3C
* HTML named character references</a>.
*/
public class Entities {
private static final int empty = -1;
private static final String emptyName = "";
static final int codepointRadix = 36;
private static final char[] codeDelims = {',', ';'};
private static final HashMap<String, String> multipoints = new HashMap<>(); // name -> multiple character references
private static final Document.OutputSettings DefaultOutput = new Document.OutputSettings();
public enum EscapeMode {
/**
* Restricted entities suitable for XHTML output: lt, gt, amp, and quot
* only.
*/
xhtml(EntitiesData.xmlPoints, 4),
/**
* Default HTML output entities.
*/
base(EntitiesData.basePoints, 106),
/**
* Complete HTML entities.
*/
extended(EntitiesData.fullPoints, 2125);
// table of named references to their codepoints. sorted so we can binary search. built by BuildEntities.
private String[] nameKeys;
private int[] codeVals; // limitation is the few references with multiple characters; those go into multipoints.
// table of codepoints to named entities.
private int[] codeKeys; // we don' support multicodepoints to single named value currently
private String[] nameVals;
EscapeMode(String file, int size) {
load(this, file, size);
}
int codepointForName(final String name) {
int index = Arrays.binarySearch(nameKeys, name);
return index >= 0 ? codeVals[index] : empty;
}
String nameForCodepoint(final int codepoint) {
final int index = Arrays.binarySearch(codeKeys, codepoint);
if (index >= 0) {
// the results are ordered so lower case versions of same codepoint come after uppercase, and we prefer to emit lower
// (and binary search for same item with multi results is undefined
return (index < nameVals.length - 1 && codeKeys[index + 1] == codepoint)
? nameVals[index + 1] : nameVals[index];
}
return emptyName;
}
private int size() {
return nameKeys.length;
}
}
private Entities() {
}
/**
* Check if the input is a known named entity
*
* @param name the possible entity name (e.g. "lt" or "amp")
* @return true if a known named entity
*/
public static boolean isNamedEntity(final String name) {
return extended.codepointForName(name) != empty;
}
/**
* Check if the input is a known named entity in the base entity set.
*
* @param name the possible entity name (e.g. "lt" or "amp")
* @return true if a known named entity in the base set
* @see #isNamedEntity(String)
*/
public static boolean isBaseNamedEntity(final String name) {
return base.codepointForName(name) != empty;
}
/**
* Get the Character value of the named entity
*
* @param name named entity (e.g. "lt" or "amp")
* @return the Character value of the named entity (e.g. '{@literal <}' or
* '{@literal &}')
* @deprecated does not support characters outside the BMP or multiple
* character names
*/
public static Character getCharacterByName(String name) {
return (char) extended.codepointForName(name);
}
/**
* Get the character(s) represented by the named entity
*
* @param name entity (e.g. "lt" or "amp")
* @return the string value of the character(s) represented by this entity,
* or "" if not defined
*/
public static String getByName(String name) {
String val = multipoints.get(name);
if (val != null) {
return val;
}
int codepoint = extended.codepointForName(name);
if (codepoint != empty) {
return new String(new int[]{codepoint}, 0, 1);
}
return emptyName;
}
public static int codepointsForName(final String name, final int[] codepoints) {
String val = multipoints.get(name);
if (val != null) {
codepoints[0] = val.codePointAt(0);
codepoints[1] = val.codePointAt(1);
return 2;
}
int codepoint = extended.codepointForName(name);
if (codepoint != empty) {
codepoints[0] = codepoint;
return 1;
}
return 0;
}
/**
* HTML escape an input string. That is, {@code <} is returned as
* {@code <}
*
* @param string the un-escaped string to escape
* @param out the output settings to use
* @return the escaped string
*/
public static String escape(String string, Document.OutputSettings out) {
if (string == null) {
return "";
}
StringBuilder accum = StringUtil.borrowBuilder();
try {
escape(accum, string, out, false, false, false);
} catch (IOException e) {
}
return StringUtil.releaseBuilder(accum);
}
/**
* HTML escape an input string, using the default settings (UTF-8, base
* entities). That is, {@code <} is returned as {@code <}
*
* @param string the un-escaped string to escape
* @return the escaped string
*/
public static String escape(String string) {
return escape(string, DefaultOutput);
}
// this method is ugly, and does a lot. but other breakups cause rescanning and stringbuilder generations
static void escape(Appendable accum, String string, Document.OutputSettings out,
boolean inAttribute, boolean normaliseWhite, boolean stripLeadingWhite) throws IOException {
boolean lastWasWhite = false;
boolean reachedNonWhite = false;
final EscapeMode escapeMode = out.escapeMode();
final CharsetEncoder encoder = out.encoder();
final CoreCharset coreCharset = out.coreCharset; // init in out.prepareEncoder()
final int length = string.length();
int codePoint;
for (int offset = 0; offset < length; offset += Character.charCount(codePoint)) {
codePoint = string.codePointAt(offset);
if (normaliseWhite) {
if (StringUtil.isWhitespace(codePoint)) {
if ((stripLeadingWhite && !reachedNonWhite) || lastWasWhite) {
continue;
}
accum.append(' ');
lastWasWhite = true;
continue;
} else {
lastWasWhite = false;
reachedNonWhite = true;
}
}
// surrogate pairs, split implementation for efficiency on single char common case (saves creating strings, char[]):
if (codePoint < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
final char c = (char) codePoint;
// html specific and required escapes:
switch (c) {
case '&':
accum.append("&");
break;
case 0xA0:
if (escapeMode != EscapeMode.xhtml) {
accum.append(" ");
} else {
accum.append(" ");
}
break;
case '<':
// escape when in character data or when in a xml attribue val; not needed in html attr val
if (!inAttribute || escapeMode == EscapeMode.xhtml) {
accum.append("<");
} else {
accum.append(c);
}
break;
case '>':
if (!inAttribute) {
accum.append(">");
} else {
accum.append(c);
}
break;
case '"':
if (inAttribute) {
accum.append(""");
} else {
accum.append(c);
}
break;
default:
if (canEncode(coreCharset, c, encoder)) {
accum.append(c);
} else {
appendEncoded(accum, escapeMode, codePoint);
}
}
} else {
final String c = new String(Character.toChars(codePoint));
if (encoder.canEncode(c)) // uses fallback encoder for simplicity
{
accum.append(c);
} else {
appendEncoded(accum, escapeMode, codePoint);
}
}
}
}
private static void appendEncoded(Appendable accum, EscapeMode escapeMode, int codePoint) throws IOException {
final String name = escapeMode.nameForCodepoint(codePoint);
if (name != emptyName) // ok for identity check
{
accum.append('&').append(name).append(';');
} else {
accum.append("&#x").append(Integer.toHexString(codePoint)).append(';');
}
}
/**
* Un-escape an HTML escaped string. That is, {@code <} is returned as
* {@code <}.
*
* @param string the HTML string to un-escape
* @return the unescaped string
*/
public static String unescape(String string) {
return unescape(string, false);
}
/**
* Unescape the input string.
*
* @param string to un-HTML-escape
* @param strict if "strict" (that is, requires trailing ';' char, otherwise
* that's optional)
* @return unescaped string
*/
static String unescape(String string, boolean strict) {
return Parser.unescapeEntities(string, strict);
}
/*
* Provides a fast-path for Encoder.canEncode, which drastically improves performance on Android post JellyBean.
* After KitKat, the implementation of canEncode degrades to the point of being useless. For non ASCII or UTF,
* performance may be bad. We can add more encoders for common character sets that are impacted by performance
* issues on Android if required.
*
* Benchmarks: *
* OLD toHtml() impl v New (fastpath) in millis
* Wiki: 1895, 16
* CNN: 6378, 55
* Alterslash: 3013, 28
* Jsoup: 167, 2
*/
private static boolean canEncode(final CoreCharset charset, final char c, final CharsetEncoder fallback) {
// todo add more charset tests if impacted by Android's bad perf in canEncode
switch (charset) {
case ascii:
return c < 0x80;
case utf:
return true; // real is:!(Character.isLowSurrogate(c) || Character.isHighSurrogate(c)); - but already check above
default:
return fallback.canEncode(c);
}
}
enum CoreCharset {
ascii, utf, fallback;
static CoreCharset byName(final String name) {
if (name.equals("US-ASCII")) {
return ascii;
}
if (name.startsWith("UTF-")) // covers UTF-8, UTF-16, et al
{
return utf;
}
return fallback;
}
}
private static void load(EscapeMode e, String pointsData, int size) {
e.nameKeys = new String[size];
e.codeVals = new int[size];
e.codeKeys = new int[size];
e.nameVals = new String[size];
int i = 0;
CharacterReader reader = new CharacterReader(pointsData);
while (!reader.isEmpty()) {
// NotNestedLessLess=10913,824;1887&
final String name = reader.consumeTo('=');
reader.advance();
final int cp1 = Integer.parseInt(reader.consumeToAny(codeDelims), codepointRadix);
final char codeDelim = reader.current();
reader.advance();
final int cp2;
if (codeDelim == ',') {
cp2 = Integer.parseInt(reader.consumeTo(';'), codepointRadix);
reader.advance();
} else {
cp2 = empty;
}
final String indexS = reader.consumeTo('&');
final int index = Integer.parseInt(indexS, codepointRadix);
reader.advance();
e.nameKeys[i] = name;
e.codeVals[i] = cp1;
e.codeKeys[index] = cp1;
e.nameVals[index] = name;
if (cp2 != empty) {
multipoints.put(name, new String(new int[]{cp1, cp2}, 0, 2));
}
i++;
}
Validate.isTrue(i == size, "Unexpected count of entities loaded");
}
}