1 package org.apache.maven.doxia.parser;
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22 import java.io.Reader;
23 import java.util.HashMap;
24 import java.util.Map;
25 import java.util.Set;
26 import java.util.TreeSet;
27
28 import javax.swing.text.html.HTML.Attribute;
29
30 import org.apache.maven.doxia.macro.MacroExecutionException;
31 import org.apache.maven.doxia.markup.HtmlMarkup;
32 import org.apache.maven.doxia.sink.Sink;
33 import org.apache.maven.doxia.sink.SinkEventAttributes;
34 import org.apache.maven.doxia.sink.impl.SinkEventAttributeSet;
35 import org.apache.maven.doxia.util.DoxiaUtils;
36
37 import org.codehaus.plexus.util.StringUtils;
38 import org.codehaus.plexus.util.xml.pull.XmlPullParser;
39 import org.codehaus.plexus.util.xml.pull.XmlPullParserException;
40
41
42
43
44
45
46
47
48 public class XhtmlBaseParser
49 extends AbstractXmlParser
50 implements HtmlMarkup
51 {
52
53
54
55
56 private boolean scriptBlock;
57
58
59 private boolean isLink;
60
61
62 private boolean isAnchor;
63
64
65 private int orderedListDepth = 0;
66
67
68 private int sectionLevel;
69
70
71 private boolean inVerbatim;
72
73
74 private boolean inFigure;
75
76
77 boolean hasDefinitionListItem = false;
78
79
80
81 private Map<String, Set<String>> warnMessages;
82
83
84 @Override
85 public void parse( Reader source, Sink sink, String reference )
86 throws ParseException
87 {
88 init();
89
90 try
91 {
92 super.parse( source, sink, reference );
93 }
94 finally
95 {
96 logWarnings();
97
98 setSecondParsing( false );
99 init();
100 }
101 }
102
103
104
105
106
107
108
109 @Override
110 protected void initXmlParser( XmlPullParser parser )
111 throws XmlPullParserException
112 {
113 super.initXmlParser( parser );
114
115
116
117
118
119
120
121
122 parser.defineEntityReplacementText( "nbsp", "\u00a0" );
123 parser.defineEntityReplacementText( "iexcl", "\u00a1" );
124 parser.defineEntityReplacementText( "cent", "\u00a2" );
125 parser.defineEntityReplacementText( "pound", "\u00a3" );
126 parser.defineEntityReplacementText( "curren", "\u00a4" );
127 parser.defineEntityReplacementText( "yen", "\u00a5" );
128 parser.defineEntityReplacementText( "brvbar", "\u00a6" );
129 parser.defineEntityReplacementText( "sect", "\u00a7" );
130 parser.defineEntityReplacementText( "uml", "\u00a8" );
131 parser.defineEntityReplacementText( "copy", "\u00a9" );
132 parser.defineEntityReplacementText( "ordf", "\u00aa" );
133 parser.defineEntityReplacementText( "laquo", "\u00ab" );
134 parser.defineEntityReplacementText( "not", "\u00ac" );
135 parser.defineEntityReplacementText( "shy", "\u00ad" );
136 parser.defineEntityReplacementText( "reg", "\u00ae" );
137 parser.defineEntityReplacementText( "macr", "\u00af" );
138 parser.defineEntityReplacementText( "deg", "\u00b0" );
139 parser.defineEntityReplacementText( "plusmn", "\u00b1" );
140 parser.defineEntityReplacementText( "sup2", "\u00b2" );
141 parser.defineEntityReplacementText( "sup3", "\u00b3" );
142 parser.defineEntityReplacementText( "acute", "\u00b4" );
143 parser.defineEntityReplacementText( "micro", "\u00b5" );
144 parser.defineEntityReplacementText( "para", "\u00b6" );
145 parser.defineEntityReplacementText( "middot", "\u00b7" );
146 parser.defineEntityReplacementText( "cedil", "\u00b8" );
147 parser.defineEntityReplacementText( "sup1", "\u00b9" );
148 parser.defineEntityReplacementText( "ordm", "\u00ba" );
149 parser.defineEntityReplacementText( "raquo", "\u00bb" );
150 parser.defineEntityReplacementText( "frac14", "\u00bc" );
151 parser.defineEntityReplacementText( "frac12", "\u00bd" );
152 parser.defineEntityReplacementText( "frac34", "\u00be" );
153 parser.defineEntityReplacementText( "iquest", "\u00bf" );
154 parser.defineEntityReplacementText( "Agrave", "\u00c0" );
155 parser.defineEntityReplacementText( "Aacute", "\u00c1" );
156 parser.defineEntityReplacementText( "Acirc", "\u00c2" );
157 parser.defineEntityReplacementText( "Atilde", "\u00c3" );
158 parser.defineEntityReplacementText( "Auml", "\u00c4" );
159 parser.defineEntityReplacementText( "Aring", "\u00c5" );
160 parser.defineEntityReplacementText( "AElig", "\u00c6" );
161 parser.defineEntityReplacementText( "Ccedil", "\u00c7" );
162 parser.defineEntityReplacementText( "Egrave", "\u00c8" );
163 parser.defineEntityReplacementText( "Eacute", "\u00c9" );
164 parser.defineEntityReplacementText( "Ecirc", "\u00ca" );
165 parser.defineEntityReplacementText( "Euml", "\u00cb" );
166 parser.defineEntityReplacementText( "Igrave", "\u00cc" );
167 parser.defineEntityReplacementText( "Iacute", "\u00cd" );
168 parser.defineEntityReplacementText( "Icirc", "\u00ce" );
169 parser.defineEntityReplacementText( "Iuml", "\u00cf" );
170 parser.defineEntityReplacementText( "ETH", "\u00d0" );
171 parser.defineEntityReplacementText( "Ntilde", "\u00d1" );
172 parser.defineEntityReplacementText( "Ograve", "\u00d2" );
173 parser.defineEntityReplacementText( "Oacute", "\u00d3" );
174 parser.defineEntityReplacementText( "Ocirc", "\u00d4" );
175 parser.defineEntityReplacementText( "Otilde", "\u00d5" );
176 parser.defineEntityReplacementText( "Ouml", "\u00d6" );
177 parser.defineEntityReplacementText( "times", "\u00d7" );
178 parser.defineEntityReplacementText( "Oslash", "\u00d8" );
179 parser.defineEntityReplacementText( "Ugrave", "\u00d9" );
180 parser.defineEntityReplacementText( "Uacute", "\u00da" );
181 parser.defineEntityReplacementText( "Ucirc", "\u00db" );
182 parser.defineEntityReplacementText( "Uuml", "\u00dc" );
183 parser.defineEntityReplacementText( "Yacute", "\u00dd" );
184 parser.defineEntityReplacementText( "THORN", "\u00de" );
185 parser.defineEntityReplacementText( "szlig", "\u00df" );
186 parser.defineEntityReplacementText( "agrave", "\u00e0" );
187 parser.defineEntityReplacementText( "aacute", "\u00e1" );
188 parser.defineEntityReplacementText( "acirc", "\u00e2" );
189 parser.defineEntityReplacementText( "atilde", "\u00e3" );
190 parser.defineEntityReplacementText( "auml", "\u00e4" );
191 parser.defineEntityReplacementText( "aring", "\u00e5" );
192 parser.defineEntityReplacementText( "aelig", "\u00e6" );
193 parser.defineEntityReplacementText( "ccedil", "\u00e7" );
194 parser.defineEntityReplacementText( "egrave", "\u00e8" );
195 parser.defineEntityReplacementText( "eacute", "\u00e9" );
196 parser.defineEntityReplacementText( "ecirc", "\u00ea" );
197 parser.defineEntityReplacementText( "euml", "\u00eb" );
198 parser.defineEntityReplacementText( "igrave", "\u00ec" );
199 parser.defineEntityReplacementText( "iacute", "\u00ed" );
200 parser.defineEntityReplacementText( "icirc", "\u00ee" );
201 parser.defineEntityReplacementText( "iuml", "\u00ef" );
202 parser.defineEntityReplacementText( "eth", "\u00f0" );
203 parser.defineEntityReplacementText( "ntilde", "\u00f1" );
204 parser.defineEntityReplacementText( "ograve", "\u00f2" );
205 parser.defineEntityReplacementText( "oacute", "\u00f3" );
206 parser.defineEntityReplacementText( "ocirc", "\u00f4" );
207 parser.defineEntityReplacementText( "otilde", "\u00f5" );
208 parser.defineEntityReplacementText( "ouml", "\u00f6" );
209 parser.defineEntityReplacementText( "divide", "\u00f7" );
210 parser.defineEntityReplacementText( "oslash", "\u00f8" );
211 parser.defineEntityReplacementText( "ugrave", "\u00f9" );
212 parser.defineEntityReplacementText( "uacute", "\u00fa" );
213 parser.defineEntityReplacementText( "ucirc", "\u00fb" );
214 parser.defineEntityReplacementText( "uuml", "\u00fc" );
215 parser.defineEntityReplacementText( "yacute", "\u00fd" );
216 parser.defineEntityReplacementText( "thorn", "\u00fe" );
217 parser.defineEntityReplacementText( "yuml", "\u00ff" );
218
219
220
221
222
223 parser.defineEntityReplacementText( "OElig", "\u0152" );
224 parser.defineEntityReplacementText( "oelig", "\u0153" );
225 parser.defineEntityReplacementText( "Scaron", "\u0160" );
226 parser.defineEntityReplacementText( "scaron", "\u0161" );
227 parser.defineEntityReplacementText( "Yuml", "\u0178" );
228 parser.defineEntityReplacementText( "circ", "\u02c6" );
229 parser.defineEntityReplacementText( "tilde", "\u02dc" );
230 parser.defineEntityReplacementText( "ensp", "\u2002" );
231 parser.defineEntityReplacementText( "emsp", "\u2003" );
232 parser.defineEntityReplacementText( "thinsp", "\u2009" );
233 parser.defineEntityReplacementText( "zwnj", "\u200c" );
234 parser.defineEntityReplacementText( "zwj", "\u200d" );
235 parser.defineEntityReplacementText( "lrm", "\u200e" );
236 parser.defineEntityReplacementText( "rlm", "\u200f" );
237 parser.defineEntityReplacementText( "ndash", "\u2013" );
238 parser.defineEntityReplacementText( "mdash", "\u2014" );
239 parser.defineEntityReplacementText( "lsquo", "\u2018" );
240 parser.defineEntityReplacementText( "rsquo", "\u2019" );
241 parser.defineEntityReplacementText( "sbquo", "\u201a" );
242 parser.defineEntityReplacementText( "ldquo", "\u201c" );
243 parser.defineEntityReplacementText( "rdquo", "\u201d" );
244 parser.defineEntityReplacementText( "bdquo", "\u201e" );
245 parser.defineEntityReplacementText( "dagger", "\u2020" );
246 parser.defineEntityReplacementText( "Dagger", "\u2021" );
247 parser.defineEntityReplacementText( "permil", "\u2030" );
248 parser.defineEntityReplacementText( "lsaquo", "\u2039" );
249 parser.defineEntityReplacementText( "rsaquo", "\u203a" );
250 parser.defineEntityReplacementText( "euro", "\u20ac" );
251
252
253
254
255
256 parser.defineEntityReplacementText( "fnof", "\u0192" );
257 parser.defineEntityReplacementText( "Alpha", "\u0391" );
258 parser.defineEntityReplacementText( "Beta", "\u0392" );
259 parser.defineEntityReplacementText( "Gamma", "\u0393" );
260 parser.defineEntityReplacementText( "Delta", "\u0394" );
261 parser.defineEntityReplacementText( "Epsilon", "\u0395" );
262 parser.defineEntityReplacementText( "Zeta", "\u0396" );
263 parser.defineEntityReplacementText( "Eta", "\u0397" );
264 parser.defineEntityReplacementText( "Theta", "\u0398" );
265 parser.defineEntityReplacementText( "Iota", "\u0399" );
266 parser.defineEntityReplacementText( "Kappa", "\u039a" );
267 parser.defineEntityReplacementText( "Lambda", "\u039b" );
268 parser.defineEntityReplacementText( "Mu", "\u039c" );
269 parser.defineEntityReplacementText( "Nu", "\u039d" );
270 parser.defineEntityReplacementText( "Xi", "\u039e" );
271 parser.defineEntityReplacementText( "Omicron", "\u039f" );
272 parser.defineEntityReplacementText( "Pi", "\u03a0" );
273 parser.defineEntityReplacementText( "Rho", "\u03a1" );
274 parser.defineEntityReplacementText( "Sigma", "\u03a3" );
275 parser.defineEntityReplacementText( "Tau", "\u03a4" );
276 parser.defineEntityReplacementText( "Upsilon", "\u03a5" );
277 parser.defineEntityReplacementText( "Phi", "\u03a6" );
278 parser.defineEntityReplacementText( "Chi", "\u03a7" );
279 parser.defineEntityReplacementText( "Psi", "\u03a8" );
280 parser.defineEntityReplacementText( "Omega", "\u03a9" );
281 parser.defineEntityReplacementText( "alpha", "\u03b1" );
282 parser.defineEntityReplacementText( "beta", "\u03b2" );
283 parser.defineEntityReplacementText( "gamma", "\u03b3" );
284 parser.defineEntityReplacementText( "delta", "\u03b4" );
285 parser.defineEntityReplacementText( "epsilon", "\u03b5" );
286 parser.defineEntityReplacementText( "zeta", "\u03b6" );
287 parser.defineEntityReplacementText( "eta", "\u03b7" );
288 parser.defineEntityReplacementText( "theta", "\u03b8" );
289 parser.defineEntityReplacementText( "iota", "\u03b9" );
290 parser.defineEntityReplacementText( "kappa", "\u03ba" );
291 parser.defineEntityReplacementText( "lambda", "\u03bb" );
292 parser.defineEntityReplacementText( "mu", "\u03bc" );
293 parser.defineEntityReplacementText( "nu", "\u03bd" );
294 parser.defineEntityReplacementText( "xi", "\u03be" );
295 parser.defineEntityReplacementText( "omicron", "\u03bf" );
296 parser.defineEntityReplacementText( "pi", "\u03c0" );
297 parser.defineEntityReplacementText( "rho", "\u03c1" );
298 parser.defineEntityReplacementText( "sigmaf", "\u03c2" );
299 parser.defineEntityReplacementText( "sigma", "\u03c3" );
300 parser.defineEntityReplacementText( "tau", "\u03c4" );
301 parser.defineEntityReplacementText( "upsilon", "\u03c5" );
302 parser.defineEntityReplacementText( "phi", "\u03c6" );
303 parser.defineEntityReplacementText( "chi", "\u03c7" );
304 parser.defineEntityReplacementText( "psi", "\u03c8" );
305 parser.defineEntityReplacementText( "omega", "\u03c9" );
306 parser.defineEntityReplacementText( "thetasym", "\u03d1" );
307 parser.defineEntityReplacementText( "upsih", "\u03d2" );
308 parser.defineEntityReplacementText( "piv", "\u03d6" );
309 parser.defineEntityReplacementText( "bull", "\u2022" );
310 parser.defineEntityReplacementText( "hellip", "\u2026" );
311 parser.defineEntityReplacementText( "prime", "\u2032" );
312 parser.defineEntityReplacementText( "Prime", "\u2033" );
313 parser.defineEntityReplacementText( "oline", "\u203e" );
314 parser.defineEntityReplacementText( "frasl", "\u2044" );
315 parser.defineEntityReplacementText( "weierp", "\u2118" );
316 parser.defineEntityReplacementText( "image", "\u2111" );
317 parser.defineEntityReplacementText( "real", "\u211c" );
318 parser.defineEntityReplacementText( "trade", "\u2122" );
319 parser.defineEntityReplacementText( "alefsym", "\u2135" );
320 parser.defineEntityReplacementText( "larr", "\u2190" );
321 parser.defineEntityReplacementText( "uarr", "\u2191" );
322 parser.defineEntityReplacementText( "rarr", "\u2192" );
323 parser.defineEntityReplacementText( "darr", "\u2193" );
324 parser.defineEntityReplacementText( "harr", "\u2194" );
325 parser.defineEntityReplacementText( "crarr", "\u21b5" );
326 parser.defineEntityReplacementText( "lArr", "\u21d0" );
327 parser.defineEntityReplacementText( "uArr", "\u21d1" );
328 parser.defineEntityReplacementText( "rArr", "\u21d2" );
329 parser.defineEntityReplacementText( "dArr", "\u21d3" );
330 parser.defineEntityReplacementText( "hArr", "\u21d4" );
331 parser.defineEntityReplacementText( "forall", "\u2200" );
332 parser.defineEntityReplacementText( "part", "\u2202" );
333 parser.defineEntityReplacementText( "exist", "\u2203" );
334 parser.defineEntityReplacementText( "empty", "\u2205" );
335 parser.defineEntityReplacementText( "nabla", "\u2207" );
336 parser.defineEntityReplacementText( "isin", "\u2208" );
337 parser.defineEntityReplacementText( "notin", "\u2209" );
338 parser.defineEntityReplacementText( "ni", "\u220b" );
339 parser.defineEntityReplacementText( "prod", "\u220f" );
340 parser.defineEntityReplacementText( "sum", "\u2211" );
341 parser.defineEntityReplacementText( "minus", "\u2212" );
342 parser.defineEntityReplacementText( "lowast", "\u2217" );
343 parser.defineEntityReplacementText( "radic", "\u221a" );
344 parser.defineEntityReplacementText( "prop", "\u221d" );
345 parser.defineEntityReplacementText( "infin", "\u221e" );
346 parser.defineEntityReplacementText( "ang", "\u2220" );
347 parser.defineEntityReplacementText( "and", "\u2227" );
348 parser.defineEntityReplacementText( "or", "\u2228" );
349 parser.defineEntityReplacementText( "cap", "\u2229" );
350 parser.defineEntityReplacementText( "cup", "\u222a" );
351 parser.defineEntityReplacementText( "int", "\u222b" );
352 parser.defineEntityReplacementText( "there4", "\u2234" );
353 parser.defineEntityReplacementText( "sim", "\u223c" );
354 parser.defineEntityReplacementText( "cong", "\u2245" );
355 parser.defineEntityReplacementText( "asymp", "\u2248" );
356 parser.defineEntityReplacementText( "ne", "\u2260" );
357 parser.defineEntityReplacementText( "equiv", "\u2261" );
358 parser.defineEntityReplacementText( "le", "\u2264" );
359 parser.defineEntityReplacementText( "ge", "\u2265" );
360 parser.defineEntityReplacementText( "sub", "\u2282" );
361 parser.defineEntityReplacementText( "sup", "\u2283" );
362 parser.defineEntityReplacementText( "nsub", "\u2284" );
363 parser.defineEntityReplacementText( "sube", "\u2286" );
364 parser.defineEntityReplacementText( "supe", "\u2287" );
365 parser.defineEntityReplacementText( "oplus", "\u2295" );
366 parser.defineEntityReplacementText( "otimes", "\u2297" );
367 parser.defineEntityReplacementText( "perp", "\u22a5" );
368 parser.defineEntityReplacementText( "sdot", "\u22c5" );
369 parser.defineEntityReplacementText( "lceil", "\u2308" );
370 parser.defineEntityReplacementText( "rceil", "\u2309" );
371 parser.defineEntityReplacementText( "lfloor", "\u230a" );
372 parser.defineEntityReplacementText( "rfloor", "\u230b" );
373 parser.defineEntityReplacementText( "lang", "\u2329" );
374 parser.defineEntityReplacementText( "rang", "\u232a" );
375 parser.defineEntityReplacementText( "loz", "\u25ca" );
376 parser.defineEntityReplacementText( "spades", "\u2660" );
377 parser.defineEntityReplacementText( "clubs", "\u2663" );
378 parser.defineEntityReplacementText( "hearts", "\u2665" );
379 parser.defineEntityReplacementText( "diams", "\u2666" );
380 }
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403 protected boolean baseStartTag( XmlPullParser parser, Sink sink )
404 {
405 boolean visited = true;
406
407 SinkEventAttributeSet attribs = getAttributesFromParser( parser );
408
409 if ( parser.getName().equals( HtmlMarkup.H2.toString() ) )
410 {
411 handleSectionStart( sink, Sink.SECTION_LEVEL_1, attribs );
412 }
413 else if ( parser.getName().equals( HtmlMarkup.H3.toString() ) )
414 {
415 handleSectionStart( sink, Sink.SECTION_LEVEL_2, attribs );
416 }
417 else if ( parser.getName().equals( HtmlMarkup.H4.toString() ) )
418 {
419 handleSectionStart( sink, Sink.SECTION_LEVEL_3, attribs );
420 }
421 else if ( parser.getName().equals( HtmlMarkup.H5.toString() ) )
422 {
423 handleSectionStart( sink, Sink.SECTION_LEVEL_4, attribs );
424 }
425 else if ( parser.getName().equals( HtmlMarkup.H6.toString() ) )
426 {
427 handleSectionStart( sink, Sink.SECTION_LEVEL_5, attribs );
428 }
429 else if ( parser.getName().equals( HtmlMarkup.U.toString() ) )
430 {
431 attribs.addAttributes( SinkEventAttributeSet.Semantics.ANNOTATION );
432 sink.inline( attribs );
433 }
434 else if ( parser.getName().equals( HtmlMarkup.S.toString() )
435 || parser.getName().equals( HtmlMarkup.STRIKE.toString() )
436 || parser.getName().equals( "del" ) )
437 {
438 attribs.addAttributes( SinkEventAttributeSet.Semantics.LINE_THROUGH );
439 sink.inline( attribs );
440 }
441 else if ( parser.getName().equals( HtmlMarkup.SUB.toString() ) )
442 {
443 attribs.addAttributes( SinkEventAttributeSet.Semantics.SUBSCRIPT );
444 sink.inline( attribs );
445 }
446 else if ( parser.getName().equals( HtmlMarkup.SUP.toString() ) )
447 {
448 attribs.addAttributes( SinkEventAttributeSet.Semantics.SUPERSCRIPT );
449 sink.inline( attribs );
450 }
451 else if ( parser.getName().equals( HtmlMarkup.P.toString() ) )
452 {
453 handlePStart( sink, attribs );
454 }
455 else if ( parser.getName().equals( HtmlMarkup.DIV.toString() ) )
456 {
457 visited = handleDivStart( parser, attribs, sink );
458 }
459 else if ( parser.getName().equals( HtmlMarkup.PRE.toString() ) )
460 {
461 handlePreStart( attribs, sink );
462 }
463 else if ( parser.getName().equals( HtmlMarkup.UL.toString() ) )
464 {
465 sink.list( attribs );
466 }
467 else if ( parser.getName().equals( HtmlMarkup.OL.toString() ) )
468 {
469 handleOLStart( parser, sink, attribs );
470 }
471 else if ( parser.getName().equals( HtmlMarkup.LI.toString() ) )
472 {
473 handleLIStart( sink, attribs );
474 }
475 else if ( parser.getName().equals( HtmlMarkup.DL.toString() ) )
476 {
477 sink.definitionList( attribs );
478 }
479 else if ( parser.getName().equals( HtmlMarkup.DT.toString() ) )
480 {
481 if ( hasDefinitionListItem )
482 {
483
484 sink.definitionListItem_();
485 }
486 sink.definitionListItem( attribs );
487 hasDefinitionListItem = true;
488 sink.definedTerm( attribs );
489 }
490 else if ( parser.getName().equals( HtmlMarkup.DD.toString() ) )
491 {
492 if ( !hasDefinitionListItem )
493 {
494 sink.definitionListItem( attribs );
495 }
496 sink.definition( attribs );
497 }
498 else if ( ( parser.getName().equals( HtmlMarkup.B.toString() ) )
499 || ( parser.getName().equals( HtmlMarkup.STRONG.toString() ) ) )
500 {
501 sink.inline( SinkEventAttributeSet.Semantics.BOLD );
502 }
503 else if ( ( parser.getName().equals( HtmlMarkup.I.toString() ) )
504 || ( parser.getName().equals( HtmlMarkup.EM.toString() ) ) )
505 {
506 handleFigureCaptionStart( sink, attribs );
507 }
508 else if ( ( parser.getName().equals( HtmlMarkup.CODE.toString() ) )
509 || ( parser.getName().equals( HtmlMarkup.SAMP.toString() ) )
510 || ( parser.getName().equals( HtmlMarkup.TT.toString() ) ) )
511 {
512 attribs.addAttributes( SinkEventAttributeSet.Semantics.CODE );
513 sink.inline( attribs );
514 }
515 else if ( parser.getName().equals( HtmlMarkup.A.toString() ) )
516 {
517 handleAStart( parser, sink, attribs );
518 }
519 else if ( parser.getName().equals( HtmlMarkup.TABLE.toString() ) )
520 {
521 handleTableStart( sink, attribs, parser );
522 }
523 else if ( parser.getName().equals( HtmlMarkup.TR.toString() ) )
524 {
525 sink.tableRow( attribs );
526 }
527 else if ( parser.getName().equals( HtmlMarkup.TH.toString() ) )
528 {
529 sink.tableHeaderCell( attribs );
530 }
531 else if ( parser.getName().equals( HtmlMarkup.TD.toString() ) )
532 {
533 sink.tableCell( attribs );
534 }
535 else if ( parser.getName().equals( HtmlMarkup.CAPTION.toString() ) )
536 {
537 sink.tableCaption( attribs );
538 }
539 else if ( parser.getName().equals( HtmlMarkup.BR.toString() ) )
540 {
541 sink.lineBreak( attribs );
542 }
543 else if ( parser.getName().equals( HtmlMarkup.HR.toString() ) )
544 {
545 sink.horizontalRule( attribs );
546 }
547 else if ( parser.getName().equals( HtmlMarkup.IMG.toString() ) )
548 {
549 handleImgStart( parser, sink, attribs );
550 }
551 else if ( parser.getName().equals( HtmlMarkup.SCRIPT.toString() )
552 || parser.getName().equals( HtmlMarkup.STYLE.toString() ) )
553 {
554 handleUnknown( parser, sink, TAG_TYPE_START );
555 scriptBlock = true;
556 }
557 else
558 {
559 visited = false;
560 }
561
562 return visited;
563 }
564
565
566
567
568
569
570
571
572
573
574
575
576
577 protected boolean baseEndTag( XmlPullParser parser, Sink sink )
578 {
579 boolean visited = true;
580
581 if ( parser.getName().equals( HtmlMarkup.P.toString() ) )
582 {
583 if ( !inFigure )
584 {
585 sink.paragraph_();
586 }
587 }
588 else if ( parser.getName().equals( HtmlMarkup.U.toString() )
589 || parser.getName().equals( HtmlMarkup.S.toString() )
590 || parser.getName().equals( HtmlMarkup.STRIKE.toString() )
591 || parser.getName().equals( "del" ) )
592 {
593 sink.inline_();
594 }
595 else if ( parser.getName().equals( HtmlMarkup.SUB.toString() )
596 || parser.getName().equals( HtmlMarkup.SUP.toString() ) )
597 {
598 sink.inline_();
599 }
600 else if ( parser.getName().equals( HtmlMarkup.DIV.toString() ) )
601 {
602 if ( inFigure )
603 {
604 sink.figure_();
605 this.inFigure = false;
606 }
607 else
608 {
609 visited = false;
610 }
611 }
612 else if ( parser.getName().equals( HtmlMarkup.PRE.toString() ) )
613 {
614 verbatim_();
615
616 sink.verbatim_();
617 }
618 else if ( parser.getName().equals( HtmlMarkup.UL.toString() ) )
619 {
620 sink.list_();
621 }
622 else if ( parser.getName().equals( HtmlMarkup.OL.toString() ) )
623 {
624 sink.numberedList_();
625 orderedListDepth--;
626 }
627 else if ( parser.getName().equals( HtmlMarkup.LI.toString() ) )
628 {
629 handleListItemEnd( sink );
630 }
631 else if ( parser.getName().equals( HtmlMarkup.DL.toString() ) )
632 {
633 if ( hasDefinitionListItem )
634 {
635 sink.definitionListItem_();
636 hasDefinitionListItem = false;
637 }
638 sink.definitionList_();
639 }
640 else if ( parser.getName().equals( HtmlMarkup.DT.toString() ) )
641 {
642 sink.definedTerm_();
643 }
644 else if ( parser.getName().equals( HtmlMarkup.DD.toString() ) )
645 {
646 sink.definition_();
647 sink.definitionListItem_();
648 hasDefinitionListItem = false;
649 }
650 else if ( ( parser.getName().equals( HtmlMarkup.B.toString() ) )
651 || ( parser.getName().equals( HtmlMarkup.STRONG.toString() ) ) )
652 {
653 sink.inline_();
654 }
655 else if ( ( parser.getName().equals( HtmlMarkup.I.toString() ) )
656 || ( parser.getName().equals( HtmlMarkup.EM.toString() ) ) )
657 {
658 handleFigureCaptionEnd( sink );
659 }
660 else if ( ( parser.getName().equals( HtmlMarkup.CODE.toString() ) )
661 || ( parser.getName().equals( HtmlMarkup.SAMP.toString() ) )
662 || ( parser.getName().equals( HtmlMarkup.TT.toString() ) ) )
663 {
664 sink.inline_();
665 }
666 else if ( parser.getName().equals( HtmlMarkup.A.toString() ) )
667 {
668 handleAEnd( sink );
669 }
670
671
672
673
674
675 else if ( parser.getName().equals( HtmlMarkup.TABLE.toString() ) )
676 {
677 sink.tableRows_();
678
679 sink.table_();
680 }
681 else if ( parser.getName().equals( HtmlMarkup.TR.toString() ) )
682 {
683 sink.tableRow_();
684 }
685 else if ( parser.getName().equals( HtmlMarkup.TH.toString() ) )
686 {
687 sink.tableHeaderCell_();
688 }
689 else if ( parser.getName().equals( HtmlMarkup.TD.toString() ) )
690 {
691 sink.tableCell_();
692 }
693 else if ( parser.getName().equals( HtmlMarkup.CAPTION.toString() ) )
694 {
695 sink.tableCaption_();
696 }
697 else if ( parser.getName().equals( HtmlMarkup.H2.toString() ) )
698 {
699 sink.sectionTitle1_();
700 }
701 else if ( parser.getName().equals( HtmlMarkup.H3.toString() ) )
702 {
703 sink.sectionTitle2_();
704 }
705 else if ( parser.getName().equals( HtmlMarkup.H4.toString() ) )
706 {
707 sink.sectionTitle3_();
708 }
709 else if ( parser.getName().equals( HtmlMarkup.H5.toString() ) )
710 {
711 sink.sectionTitle4_();
712 }
713 else if ( parser.getName().equals( HtmlMarkup.H6.toString() ) )
714 {
715 sink.sectionTitle5_();
716 }
717 else if ( parser.getName().equals( HtmlMarkup.SCRIPT.toString() )
718 || parser.getName().equals( HtmlMarkup.STYLE.toString() ) )
719 {
720 handleUnknown( parser, sink, TAG_TYPE_END );
721
722 scriptBlock = false;
723 }
724 else
725 {
726 visited = false;
727 }
728
729 return visited;
730 }
731
732
733
734
735
736
737
738 protected void handleStartTag( XmlPullParser parser, Sink sink )
739 throws XmlPullParserException, MacroExecutionException
740 {
741 if ( !baseStartTag( parser, sink ) )
742 {
743 if ( getLog().isWarnEnabled() )
744 {
745 String position = "[" + parser.getLineNumber() + ":"
746 + parser.getColumnNumber() + "]";
747 String tag = "<" + parser.getName() + ">";
748
749 getLog().warn( "Unrecognized xml tag: " + tag + " at " + position );
750 }
751 }
752 }
753
754
755
756
757
758
759
760 protected void handleEndTag( XmlPullParser parser, Sink sink )
761 throws XmlPullParserException, MacroExecutionException
762 {
763 if ( !baseEndTag( parser, sink ) )
764 {
765
766 }
767 }
768
769
770 @Override
771 protected void handleText( XmlPullParser parser, Sink sink )
772 throws XmlPullParserException
773 {
774 String text = getText( parser );
775
776
777
778
779
780
781
782 if ( StringUtils.isNotEmpty( text ) && !isScriptBlock() )
783 {
784 sink.text( text );
785 }
786 }
787
788
789 @Override
790 protected void handleComment( XmlPullParser parser, Sink sink )
791 throws XmlPullParserException
792 {
793 String text = getText( parser );
794
795 if ( "PB".equals( text.trim() ) )
796 {
797 sink.pageBreak();
798 }
799 else
800 {
801 if ( isEmitComments() )
802 {
803 sink.comment( text );
804 }
805 }
806 }
807
808
809 @Override
810 protected void handleCdsect( XmlPullParser parser, Sink sink )
811 throws XmlPullParserException
812 {
813 String text = getText( parser );
814
815 if ( isScriptBlock() )
816 {
817 sink.unknown( CDATA, new Object[] { CDATA_TYPE, text }, null );
818 }
819 else
820 {
821 sink.text( text );
822 }
823 }
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857 protected void consecutiveSections( int newLevel, Sink sink )
858 {
859 closeOpenSections( newLevel, sink );
860 openMissingSections( newLevel, sink );
861
862 this.sectionLevel = newLevel;
863 }
864
865
866
867
868
869
870
871 private void closeOpenSections( int newLevel, Sink sink )
872 {
873 while ( this.sectionLevel >= newLevel )
874 {
875 if ( sectionLevel == Sink.SECTION_LEVEL_5 )
876 {
877 sink.section5_();
878 }
879 else if ( sectionLevel == Sink.SECTION_LEVEL_4 )
880 {
881 sink.section4_();
882 }
883 else if ( sectionLevel == Sink.SECTION_LEVEL_3 )
884 {
885 sink.section3_();
886 }
887 else if ( sectionLevel == Sink.SECTION_LEVEL_2 )
888 {
889 sink.section2_();
890 }
891 else if ( sectionLevel == Sink.SECTION_LEVEL_1 )
892 {
893 sink.section1_();
894 }
895
896 this.sectionLevel--;
897 }
898 }
899
900
901
902
903
904
905
906 private void openMissingSections( int newLevel, Sink sink )
907 {
908 while ( this.sectionLevel < newLevel - 1 )
909 {
910 this.sectionLevel++;
911
912 if ( sectionLevel == Sink.SECTION_LEVEL_5 )
913 {
914 sink.section5();
915 }
916 else if ( sectionLevel == Sink.SECTION_LEVEL_4 )
917 {
918 sink.section4();
919 }
920 else if ( sectionLevel == Sink.SECTION_LEVEL_3 )
921 {
922 sink.section3();
923 }
924 else if ( sectionLevel == Sink.SECTION_LEVEL_2 )
925 {
926 sink.section2();
927 }
928 else if ( sectionLevel == Sink.SECTION_LEVEL_1 )
929 {
930 sink.section1();
931 }
932 }
933 }
934
935
936
937
938
939
940 protected int getSectionLevel()
941 {
942 return this.sectionLevel;
943 }
944
945
946
947
948
949
950 protected void setSectionLevel( int newLevel )
951 {
952 this.sectionLevel = newLevel;
953 }
954
955
956
957
958 protected void verbatim_()
959 {
960 this.inVerbatim = false;
961 }
962
963
964
965
966 protected void verbatim()
967 {
968 this.inVerbatim = true;
969 }
970
971
972
973
974
975
976 protected boolean isVerbatim()
977 {
978 return this.inVerbatim;
979 }
980
981
982
983
984
985
986
987 protected boolean isScriptBlock()
988 {
989 return this.scriptBlock;
990 }
991
992
993
994
995
996
997
998
999 protected String validAnchor( String id )
1000 {
1001 if ( !DoxiaUtils.isValidId( id ) )
1002 {
1003 String linkAnchor = DoxiaUtils.encodeId( id, true );
1004
1005 String msg = "Modified invalid link: '" + id + "' to '" + linkAnchor + "'";
1006 logMessage( "modifiedLink", msg );
1007
1008 return linkAnchor;
1009 }
1010
1011 return id;
1012 }
1013
1014
1015 @Override
1016 protected void init()
1017 {
1018 super.init();
1019
1020 this.scriptBlock = false;
1021 this.isLink = false;
1022 this.isAnchor = false;
1023 this.orderedListDepth = 0;
1024 this.sectionLevel = 0;
1025 this.inVerbatim = false;
1026 this.inFigure = false;
1027 this.warnMessages = null;
1028 }
1029
1030 private void handleAEnd( Sink sink )
1031 {
1032 if ( isLink )
1033 {
1034 sink.link_();
1035 isLink = false;
1036 }
1037 else if ( isAnchor )
1038 {
1039 sink.anchor_();
1040 isAnchor = false;
1041 }
1042 }
1043
1044 private void handleAStart( XmlPullParser parser, Sink sink, SinkEventAttributeSet attribs )
1045 {
1046 String href = parser.getAttributeValue( null, Attribute.HREF.toString() );
1047
1048 if ( href != null )
1049 {
1050 int hashIndex = href.indexOf( '#' );
1051 if ( hashIndex != -1 && !DoxiaUtils.isExternalLink( href ) )
1052 {
1053 String hash = href.substring( hashIndex + 1 );
1054
1055 if ( !DoxiaUtils.isValidId( hash ) )
1056 {
1057 href = href.substring( 0, hashIndex ) + "#" + DoxiaUtils.encodeId( hash, true );
1058
1059 String msg = "Modified invalid link: '" + hash + "' to '" + href + "'";
1060 logMessage( "modifiedLink", msg );
1061 }
1062 }
1063 sink.link( href, attribs );
1064 isLink = true;
1065 }
1066 else
1067 {
1068 String name = parser.getAttributeValue( null, Attribute.NAME.toString() );
1069
1070 if ( name != null )
1071 {
1072 sink.anchor( validAnchor( name ), attribs );
1073 isAnchor = true;
1074 }
1075 else
1076 {
1077 String id = parser.getAttributeValue( null, Attribute.ID.toString() );
1078 if ( id != null )
1079 {
1080 sink.anchor( validAnchor( id ), attribs );
1081 isAnchor = true;
1082 }
1083 }
1084 }
1085 }
1086
1087 private boolean handleDivStart( XmlPullParser parser, SinkEventAttributeSet attribs, Sink sink )
1088 {
1089 boolean visited = true;
1090
1091 String divclass = parser.getAttributeValue( null, Attribute.CLASS.toString() );
1092
1093 if ( "figure".equals( divclass ) )
1094 {
1095 this.inFigure = true;
1096 SinkEventAttributeSet atts = new SinkEventAttributeSet( attribs );
1097 atts.removeAttribute( SinkEventAttributes.CLASS );
1098 sink.figure( atts );
1099 }
1100 else
1101 {
1102 visited = false;
1103 }
1104
1105 return visited;
1106 }
1107
1108 private void handleFigureCaptionEnd( Sink sink )
1109 {
1110 if ( inFigure )
1111 {
1112 sink.figureCaption_();
1113 }
1114 else
1115 {
1116 sink.inline_();
1117 }
1118 }
1119
1120 private void handleFigureCaptionStart( Sink sink, SinkEventAttributeSet attribs )
1121 {
1122 if ( inFigure )
1123 {
1124 sink.figureCaption( attribs );
1125 }
1126 else
1127 {
1128 sink.inline( SinkEventAttributeSet.Semantics.ITALIC );
1129 }
1130 }
1131
1132 private void handleImgStart( XmlPullParser parser, Sink sink, SinkEventAttributeSet attribs )
1133 {
1134 String src = parser.getAttributeValue( null, Attribute.SRC.toString() );
1135
1136 if ( src != null )
1137 {
1138 sink.figureGraphics( src, attribs );
1139 }
1140 }
1141
1142 private void handleLIStart( Sink sink, SinkEventAttributeSet attribs )
1143 {
1144 if ( orderedListDepth == 0 )
1145 {
1146 sink.listItem( attribs );
1147 }
1148 else
1149 {
1150 sink.numberedListItem( attribs );
1151 }
1152 }
1153
1154 private void handleListItemEnd( Sink sink )
1155 {
1156 if ( orderedListDepth == 0 )
1157 {
1158 sink.listItem_();
1159 }
1160 else
1161 {
1162 sink.numberedListItem_();
1163 }
1164 }
1165
1166 private void handleOLStart( XmlPullParser parser, Sink sink, SinkEventAttributeSet attribs )
1167 {
1168 int numbering = Sink.NUMBERING_DECIMAL;
1169
1170 String style = parser.getAttributeValue( null, Attribute.STYLE.toString() );
1171
1172 if ( style != null )
1173 {
1174 switch ( style )
1175 {
1176 case "list-style-type: upper-alpha":
1177 numbering = Sink.NUMBERING_UPPER_ALPHA;
1178 break;
1179 case "list-style-type: lower-alpha":
1180 numbering = Sink.NUMBERING_LOWER_ALPHA;
1181 break;
1182 case "list-style-type: upper-roman":
1183 numbering = Sink.NUMBERING_UPPER_ROMAN;
1184 break;
1185 case "list-style-type: lower-roman":
1186 numbering = Sink.NUMBERING_LOWER_ROMAN;
1187 break;
1188 case "list-style-type: decimal":
1189 numbering = Sink.NUMBERING_DECIMAL;
1190 break;
1191 default:
1192
1193 }
1194 }
1195
1196 sink.numberedList( numbering, attribs );
1197 orderedListDepth++;
1198 }
1199
1200 private void handlePStart( Sink sink, SinkEventAttributeSet attribs )
1201 {
1202 if ( !inFigure )
1203 {
1204 sink.paragraph( attribs );
1205 }
1206 }
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218 private void handlePreStart( SinkEventAttributeSet attribs, Sink sink )
1219 {
1220 verbatim();
1221 sink.verbatim( attribs );
1222 }
1223
1224 private void handleSectionStart( Sink sink, int level, SinkEventAttributeSet attribs )
1225 {
1226 consecutiveSections( level, sink );
1227 sink.section( level, attribs );
1228 sink.sectionTitle( level, attribs );
1229 }
1230
1231 private void handleTableStart( Sink sink, SinkEventAttributeSet attribs, XmlPullParser parser )
1232 {
1233 sink.table( attribs );
1234 String border = parser.getAttributeValue( null, Attribute.BORDER.toString() );
1235 boolean grid = true;
1236
1237 if ( border == null || "0".equals( border ) )
1238 {
1239 grid = false;
1240 }
1241
1242 String align = parser.getAttributeValue( null, Attribute.ALIGN.toString() );
1243 int[] justif = {Sink.JUSTIFY_LEFT};
1244
1245 if ( "center".equals( align ) )
1246 {
1247 justif[0] = Sink.JUSTIFY_CENTER;
1248 }
1249 else if ( "right".equals( align ) )
1250 {
1251 justif[0] = Sink.JUSTIFY_RIGHT;
1252 }
1253
1254 sink.tableRows( justif, grid );
1255 }
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265 private void logMessage( String key, String msg )
1266 {
1267 final String log = "[XHTML Parser] " + msg;
1268 if ( getLog().isDebugEnabled() )
1269 {
1270 getLog().debug( log );
1271
1272 return;
1273 }
1274
1275 if ( warnMessages == null )
1276 {
1277 warnMessages = new HashMap<>();
1278 }
1279
1280 Set<String> set = warnMessages.get( key );
1281 if ( set == null )
1282 {
1283 set = new TreeSet<>();
1284 }
1285 set.add( log );
1286 warnMessages.put( key, set );
1287 }
1288
1289
1290
1291
1292 private void logWarnings()
1293 {
1294 if ( getLog().isWarnEnabled() && this.warnMessages != null && !isSecondParsing() )
1295 {
1296 for ( Map.Entry<String, Set<String>> entry : this.warnMessages.entrySet() )
1297 {
1298 for ( String msg : entry.getValue() )
1299 {
1300 getLog().warn( msg );
1301 }
1302 }
1303
1304 this.warnMessages = null;
1305 }
1306 }
1307 }