]>
Commit | Line | Data |
---|---|---|
1 | ############################################################################## | |
2 | # | |
3 | # Zope Public License (ZPL) Version 1.0 | |
4 | # ------------------------------------- | |
5 | # | |
6 | # Copyright (c) Digital Creations. All rights reserved. | |
7 | # | |
8 | # This license has been certified as Open Source(tm). | |
9 | # | |
10 | # Redistribution and use in source and binary forms, with or without | |
11 | # modification, are permitted provided that the following conditions are | |
12 | # met: | |
13 | # | |
14 | # 1. Redistributions in source code must retain the above copyright | |
15 | # notice, this list of conditions, and the following disclaimer. | |
16 | # | |
17 | # 2. Redistributions in binary form must reproduce the above copyright | |
18 | # notice, this list of conditions, and the following disclaimer in | |
19 | # the documentation and/or other materials provided with the | |
20 | # distribution. | |
21 | # | |
22 | # 3. Digital Creations requests that attribution be given to Zope | |
23 | # in any manner possible. Zope includes a "Powered by Zope" | |
24 | # button that is installed by default. While it is not a license | |
25 | # violation to remove this button, it is requested that the | |
26 | # attribution remain. A significant investment has been put | |
27 | # into Zope, and this effort will continue if the Zope community | |
28 | # continues to grow. This is one way to assure that growth. | |
29 | # | |
30 | # 4. All advertising materials and documentation mentioning | |
31 | # features derived from or use of this software must display | |
32 | # the following acknowledgement: | |
33 | # | |
34 | # "This product includes software developed by Digital Creations | |
35 | # for use in the Z Object Publishing Environment | |
36 | # (http://www.zope.org/)." | |
37 | # | |
38 | # In the event that the product being advertised includes an | |
39 | # intact Zope distribution (with copyright and license included) | |
40 | # then this clause is waived. | |
41 | # | |
42 | # 5. Names associated with Zope or Digital Creations must not be used to | |
43 | # endorse or promote products derived from this software without | |
44 | # prior written permission from Digital Creations. | |
45 | # | |
46 | # 6. Modified redistributions of any form whatsoever must retain | |
47 | # the following acknowledgment: | |
48 | # | |
49 | # "This product includes software developed by Digital Creations | |
50 | # for use in the Z Object Publishing Environment | |
51 | # (http://www.zope.org/)." | |
52 | # | |
53 | # Intact (re-)distributions of any official Zope release do not | |
54 | # require an external acknowledgement. | |
55 | # | |
56 | # 7. Modifications are encouraged but must be packaged separately as | |
57 | # patches to official Zope releases. Distributions that do not | |
58 | # clearly separate the patches from the original work must be clearly | |
59 | # labeled as unofficial distributions. Modifications which do not | |
60 | # carry the name Zope may be packaged in any form, as long as they | |
61 | # conform to all of the clauses above. | |
62 | # | |
63 | # | |
64 | # Disclaimer | |
65 | # | |
66 | # THIS SOFTWARE IS PROVIDED BY DIGITAL CREATIONS ``AS IS'' AND ANY | |
67 | # EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE | |
68 | # IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR | |
69 | # PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL DIGITAL CREATIONS OR ITS | |
70 | # CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, | |
71 | # SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT | |
72 | # LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF | |
73 | # USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND | |
74 | # ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, | |
75 | # OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT | |
76 | # OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF | |
77 | # SUCH DAMAGE. | |
78 | # | |
79 | # | |
80 | # This software consists of contributions made by Digital Creations and | |
81 | # many individuals on behalf of Digital Creations. Specific | |
82 | # attributions are listed in the accompanying credits file. | |
83 | # | |
84 | ############################################################################## | |
85 | ||
86 | import re, ST, STDOM | |
87 | from string import split, join, replace, expandtabs, strip, find | |
88 | from STletters import letters,lettpunc,punctuations | |
89 | ||
90 | StringType=type('') | |
91 | ListType=type([]) | |
92 | ||
93 | class StructuredTextExample(ST.StructuredTextParagraph): | |
94 | """Represents a section of document with literal text, as for examples""" | |
95 | ||
96 | def __init__(self, subs, **kw): | |
97 | t=[]; a=t.append | |
98 | for s in subs: a(s.getNodeValue()) | |
99 | apply(ST.StructuredTextParagraph.__init__, | |
100 | (self, join(t,'\n\n'), ()), | |
101 | kw) | |
102 | ||
103 | def getColorizableTexts(self): return () | |
104 | def setColorizableTexts(self, src): pass # never color examples | |
105 | ||
106 | class StructuredTextBullet(ST.StructuredTextParagraph): | |
107 | """Represents a section of a document with a title and a body""" | |
108 | ||
109 | class StructuredTextNumbered(ST.StructuredTextParagraph): | |
110 | """Represents a section of a document with a title and a body""" | |
111 | ||
112 | class StructuredTextDescriptionTitle(ST.StructuredTextParagraph): | |
113 | """Represents a section of a document with a title and a body""" | |
114 | ||
115 | class StructuredTextDescriptionBody(ST.StructuredTextParagraph): | |
116 | """Represents a section of a document with a title and a body""" | |
117 | ||
118 | class StructuredTextDescription(ST.StructuredTextParagraph): | |
119 | """Represents a section of a document with a title and a body""" | |
120 | ||
121 | def __init__(self, title, src, subs, **kw): | |
122 | apply(ST.StructuredTextParagraph.__init__, (self, src, subs), kw) | |
123 | self._title=title | |
124 | ||
125 | def getColorizableTexts(self): return self._title, self._src | |
126 | def setColorizableTexts(self, src): self._title, self._src = src | |
127 | ||
128 | def getChildren(self): | |
129 | return (StructuredTextDescriptionTitle(self._title), | |
130 | StructuredTextDescriptionBody(self._src, self._subs)) | |
131 | ||
132 | class StructuredTextSectionTitle(ST.StructuredTextParagraph): | |
133 | """Represents a section of a document with a title and a body""" | |
134 | ||
135 | class StructuredTextSection(ST.StructuredTextParagraph): | |
136 | """Represents a section of a document with a title and a body""" | |
137 | def __init__(self, src, subs=None, **kw): | |
138 | apply(ST.StructuredTextParagraph.__init__, | |
139 | (self, StructuredTextSectionTitle(src), subs), | |
140 | kw) | |
141 | ||
142 | def getColorizableTexts(self): | |
143 | return self._src.getColorizableTexts() | |
144 | ||
145 | def setColorizableTexts(self,src): | |
146 | self._src.setColorizableTexts(src) | |
147 | ||
148 | # a StructuredTextTable holds StructuredTextRows | |
149 | class StructuredTextTable(ST.StructuredTextDocument): | |
150 | """ | |
151 | rows is a list of lists containing tuples, which | |
152 | represent the columns/cells in each rows. | |
153 | EX | |
154 | rows = [[('row 1:column1',1)],[('row2:column1',1)]] | |
155 | """ | |
156 | ||
157 | def __init__(self, rows, src, subs, **kw): | |
158 | apply(ST.StructuredTextDocument.__init__,(self,subs),kw) | |
159 | self._rows = [] | |
160 | for row in rows: | |
161 | if row: | |
162 | self._rows.append(StructuredTextRow(row,kw)) | |
163 | ||
164 | def getRows(self): | |
165 | return [self._rows] | |
166 | ||
167 | def _getRows(self): | |
168 | return self.getRows() | |
169 | ||
170 | def getColorizableTexts(self): | |
171 | """ | |
172 | return a tuple where each item is a column/cell's | |
173 | contents. The tuple, result, will be of this format. | |
174 | ("r1 col1", "r1=col2", "r2 col1", "r2 col2") | |
175 | """ | |
176 | ||
177 | #result = () | |
178 | result = [] | |
179 | for row in self._rows: | |
180 | for column in row.getColumns()[0]: | |
181 | #result = result[:] + (column.getColorizableTexts(),) | |
182 | result.append(column.getColorizableTexts()[0]) | |
183 | return result | |
184 | ||
185 | def setColorizableTexts(self,texts): | |
186 | """ | |
187 | texts is going to a tuple where each item is the | |
188 | result of being mapped to the colortext function. | |
189 | Need to insert the results appropriately into the | |
190 | individual columns/cells | |
191 | """ | |
192 | for row_index in range(len(self._rows)): | |
193 | for column_index in range(len(self._rows[row_index]._columns)): | |
194 | self._rows[row_index]._columns[column_index].setColorizableTexts((texts[0],)) | |
195 | texts = texts[1:] | |
196 | ||
197 | def _getColorizableTexts(self): | |
198 | return self.getColorizableTexts() | |
199 | ||
200 | def _setColorizableTexts(self): | |
201 | return self.setColorizableTexts() | |
202 | ||
203 | # StructuredTextRow holds StructuredTextColumns | |
204 | class StructuredTextRow(ST.StructuredTextDocument): | |
205 | ||
206 | def __init__(self,row,kw): | |
207 | """ | |
208 | row is a list of tuples, where each tuple is | |
209 | the raw text for a cell/column and the span | |
210 | of that cell/column". | |
211 | EX | |
212 | [('this is column one',1), ('this is column two',1)] | |
213 | """ | |
214 | ||
215 | apply(ST.StructuredTextDocument.__init__,(self,[]),kw) | |
216 | self._columns = [] | |
217 | for column in row: | |
218 | self._columns.append(StructuredTextColumn(column[0],column[1],kw)) | |
219 | def getColumns(self): | |
220 | return [self._columns] | |
221 | ||
222 | def _getColumns(self): | |
223 | return [self._columns] | |
224 | ||
225 | # this holds the raw text of a table cell | |
226 | class StructuredTextColumn(ST.StructuredTextParagraph): | |
227 | """ | |
228 | StructuredTextColumn is a cell/column in a table. | |
229 | This contains the actual text of a column and is | |
230 | thus a StructuredTextParagraph. A StructuredTextColumn | |
231 | also holds the span of its column | |
232 | """ | |
233 | ||
234 | def __init__(self,text,span,kw): | |
235 | apply(ST.StructuredTextParagraph.__init__,(self,text,[]),kw) | |
236 | self._span = span | |
237 | ||
238 | def getSpan(self): | |
239 | return self._span | |
240 | ||
241 | def _getSpan(self): | |
242 | return self._span | |
243 | ||
244 | class StructuredTextMarkup(STDOM.Element): | |
245 | ||
246 | def __init__(self, v, **kw): | |
247 | self._value=v | |
248 | self._attributes=kw.keys() | |
249 | for k, v in kw.items(): setattr(self, k, v) | |
250 | ||
251 | def getChildren(self, type=type, lt=type([])): | |
252 | v=self._value | |
253 | if type(v) is not lt: v=[v] | |
254 | return v | |
255 | ||
256 | def getColorizableTexts(self): return self._value, | |
257 | def setColorizableTexts(self, v): self._value=v[0] | |
258 | ||
259 | def __repr__(self): | |
260 | return '%s(%s)' % (self.__class__.__name__, `self._value`) | |
261 | ||
262 | class StructuredTextLiteral(StructuredTextMarkup): | |
263 | def getColorizableTexts(self): return () | |
264 | def setColorizableTexts(self, v): pass | |
265 | ||
266 | class StructuredTextEmphasis(StructuredTextMarkup): pass | |
267 | ||
268 | class StructuredTextStrong(StructuredTextMarkup): pass | |
269 | ||
270 | class StructuredTextInnerLink(StructuredTextMarkup): pass | |
271 | ||
272 | class StructuredTextNamedLink(StructuredTextMarkup): pass | |
273 | ||
274 | class StructuredTextUnderline(StructuredTextMarkup): pass | |
275 | ||
276 | class StructuredTextLink(StructuredTextMarkup): | |
277 | "A simple hyperlink" | |
278 | ||
279 | class DocumentClass: | |
280 | """ | |
281 | Class instance calls [ex.=> x()] require a structured text | |
282 | structure. Doc will then parse each paragraph in the structure | |
283 | and will find the special structures within each paragraph. | |
284 | Each special structure will be stored as an instance. Special | |
285 | structures within another special structure are stored within | |
286 | the 'top' structure | |
287 | EX : '-underline this-' => would be turned into an underline | |
288 | instance. '-underline **this**' would be stored as an underline | |
289 | instance with a strong instance stored in its string | |
290 | """ | |
291 | ||
292 | paragraph_types = [ | |
293 | 'doc_bullet', | |
294 | 'doc_numbered', | |
295 | 'doc_description', | |
296 | 'doc_header', | |
297 | 'doc_table', | |
298 | ] | |
299 | ||
300 | text_types = [ | |
301 | 'doc_href', | |
302 | 'doc_strong', | |
303 | 'doc_emphasize', | |
304 | 'doc_literal', | |
305 | 'doc_inner_link', | |
306 | 'doc_named_link', | |
307 | 'doc_underline', | |
308 | ] | |
309 | ||
310 | def __call__(self, doc): | |
311 | if type(doc) is type(''): | |
312 | doc=ST.StructuredText(doc) | |
313 | doc.setSubparagraphs(self.color_paragraphs( | |
314 | doc.getSubparagraphs())) | |
315 | else: | |
316 | doc=ST.StructuredTextDocument(self.color_paragraphs( | |
317 | doc.getSubparagraphs())) | |
318 | return doc | |
319 | ||
320 | def parse(self, raw_string, text_type, | |
321 | type=type, st=type(''), lt=type([])): | |
322 | ||
323 | """ | |
324 | Parse accepts a raw_string, an expr to test the raw_string, | |
325 | and the raw_string's subparagraphs. | |
326 | ||
327 | Parse will continue to search through raw_string until | |
328 | all instances of expr in raw_string are found. | |
329 | ||
330 | If no instances of expr are found, raw_string is returned. | |
331 | Otherwise a list of substrings and instances is returned | |
332 | """ | |
333 | ||
334 | tmp = [] # the list to be returned if raw_string is split | |
335 | append=tmp.append | |
336 | ||
337 | if type(text_type) is st: text_type=getattr(self, text_type) | |
338 | ||
339 | while 1: | |
340 | t = text_type(raw_string) | |
341 | if not t: break | |
342 | #an instance of expr was found | |
343 | t, start, end = t | |
344 | ||
345 | if start: append(raw_string[0:start]) | |
346 | ||
347 | tt=type(t) | |
348 | if tt is st: | |
349 | # if we get a string back, add it to text to be parsed | |
350 | raw_string = t+raw_string[end:len(raw_string)] | |
351 | else: | |
352 | if tt is lt: | |
353 | # is we get a list, append it's elements | |
354 | tmp[len(tmp):]=t | |
355 | else: | |
356 | # normal case, an object | |
357 | append(t) | |
358 | raw_string = raw_string[end:len(raw_string)] | |
359 | ||
360 | if not tmp: return raw_string # nothing found | |
361 | ||
362 | if raw_string: append(raw_string) | |
363 | elif len(tmp)==1: return tmp[0] | |
364 | ||
365 | return tmp | |
366 | ||
367 | ||
368 | def color_text(self, str, types=None): | |
369 | """Search the paragraph for each special structure | |
370 | """ | |
371 | if types is None: types=self.text_types | |
372 | ||
373 | for text_type in types: | |
374 | ||
375 | if type(str) is StringType: | |
376 | str = self.parse(str, text_type) | |
377 | elif type(str) is ListType: | |
378 | r=[]; a=r.append | |
379 | for s in str: | |
380 | if type(s) is StringType: | |
381 | s=self.parse(s, text_type) | |
382 | if type(s) is ListType: r[len(r):]=s | |
383 | else: a(s) | |
384 | else: | |
385 | s.setColorizableTexts( | |
386 | map(self.color_text, | |
387 | s.getColorizableTexts() | |
388 | )) | |
389 | a(s) | |
390 | str=r | |
391 | else: | |
392 | r=[]; a=r.append; color=self.color_text | |
393 | for s in str.getColorizableTexts(): | |
394 | color(s, (text_type,)) | |
395 | a(s) | |
396 | ||
397 | str.setColorizableTexts(r) | |
398 | ||
399 | return str | |
400 | ||
401 | def color_paragraphs(self, raw_paragraphs, | |
402 | type=type, sequence_types=(type([]), type(())), | |
403 | st=type('')): | |
404 | result=[] | |
405 | for paragraph in raw_paragraphs: | |
406 | ||
407 | if paragraph.getNodeName() != 'StructuredTextParagraph': | |
408 | result.append(paragraph) | |
409 | continue | |
410 | ||
411 | for pt in self.paragraph_types: | |
412 | if type(pt) is st: | |
413 | # grab the corresponding function | |
414 | pt=getattr(self, pt) | |
415 | # evaluate the paragraph | |
416 | r=pt(paragraph) | |
417 | if r: | |
418 | if type(r) not in sequence_types: | |
419 | r=r, | |
420 | new_paragraphs=r | |
421 | for paragraph in new_paragraphs: | |
422 | paragraph.setSubparagraphs(self.color_paragraphs(paragraph.getSubparagraphs())) | |
423 | break | |
424 | else: | |
425 | new_paragraphs=ST.StructuredTextParagraph(paragraph.getColorizableTexts()[0], | |
426 | self.color_paragraphs(paragraph.getSubparagraphs()), | |
427 | indent=paragraph.indent), | |
428 | # color the inline StructuredText types | |
429 | # for each StructuredTextParagraph | |
430 | for paragraph in new_paragraphs: | |
431 | paragraph.setColorizableTexts( | |
432 | map(self.color_text, | |
433 | paragraph.getColorizableTexts() | |
434 | )) | |
435 | result.append(paragraph) | |
436 | ||
437 | return result | |
438 | ||
439 | def doc_table(self,paragraph, expr = re.compile('(\s*)([||]+)').match): | |
440 | #print "paragraph=>", type(paragraph), paragraph, paragraph._src | |
441 | text = paragraph.getColorizableTexts()[0] | |
442 | m = expr(text) | |
443 | ||
444 | if not (m): | |
445 | return None | |
446 | rows = [] | |
447 | ||
448 | # initial split | |
449 | for row in split(text,"\n"): | |
450 | rows.append(row) | |
451 | ||
452 | # clean up the rows | |
453 | for index in range(len(rows)): | |
454 | tmp = [] | |
455 | rows[index] = strip(rows[index]) | |
456 | l = len(rows[index])-2 | |
457 | result = split(rows[index][:l],"||") | |
458 | for text in result: | |
459 | if text: | |
460 | tmp.append(text) | |
461 | tmp.append('') | |
462 | else: | |
463 | tmp.append(text) | |
464 | rows[index] = tmp | |
465 | # remove trailing '''s | |
466 | for index in range(len(rows)): | |
467 | l = len(rows[index])-1 | |
468 | rows[index] = rows[index][:l] | |
469 | ||
470 | result = [] | |
471 | for row in rows: | |
472 | cspan = 0 | |
473 | tmp = [] | |
474 | for item in row: | |
475 | if item: | |
476 | tmp.append((item,cspan)) | |
477 | cspan = 0 | |
478 | else: | |
479 | cspan = cspan + 1 | |
480 | result.append(tmp) | |
481 | ||
482 | subs = paragraph.getSubparagraphs() | |
483 | indent=paragraph.indent | |
484 | return StructuredTextTable(result,text,subs,indent=paragraph.indent) | |
485 | ||
486 | def doc_bullet(self, paragraph, expr = re.compile('\s*[-*o]\s+').match): | |
487 | top=paragraph.getColorizableTexts()[0] | |
488 | m=expr(top) | |
489 | ||
490 | if not m: | |
491 | return None | |
492 | ||
493 | subs=paragraph.getSubparagraphs() | |
494 | if top[-2:]=='::': | |
495 | subs=[StructuredTextExample(subs)] | |
496 | top=top[:-1] | |
497 | return StructuredTextBullet(top[m.span()[1]:], subs, | |
498 | indent=paragraph.indent, | |
499 | bullet=top[:m.span()[1]] | |
500 | ) | |
501 | ||
502 | def doc_numbered( | |
503 | self, paragraph, | |
504 | expr = re.compile('(\s*[%s]+\.)|(\s*[0-9]+\.)|(\s*[0-9]+\s+)' % letters).match): | |
505 | ||
506 | # This is the old expression. It had a nasty habit | |
507 | # of grabbing paragraphs that began with a single | |
508 | # letter word even if there was no following period. | |
509 | ||
510 | #expr = re.compile('\s*' | |
511 | # '(([a-zA-Z]|[0-9]+|[ivxlcdmIVXLCDM]+)\.)*' | |
512 | # '([a-zA-Z]|[0-9]+|[ivxlcdmIVXLCDM]+)\.?' | |
513 | # '\s+').match): | |
514 | ||
515 | top=paragraph.getColorizableTexts()[0] | |
516 | m=expr(top) | |
517 | if not m: return None | |
518 | subs=paragraph.getSubparagraphs() | |
519 | if top[-2:]=='::': | |
520 | subs=[StructuredTextExample(subs)] | |
521 | top=top[:-1] | |
522 | return StructuredTextNumbered(top[m.span()[1]:], subs, | |
523 | indent=paragraph.indent, | |
524 | number=top[:m.span()[1]]) | |
525 | ||
526 | def doc_description( | |
527 | self, paragraph, | |
528 | delim = re.compile('\s+--\s+').search, | |
529 | nb=re.compile(r'[^\000- ]').search, | |
530 | ): | |
531 | ||
532 | top=paragraph.getColorizableTexts()[0] | |
533 | d=delim(top) | |
534 | if not d: return None | |
535 | start, end = d.span() | |
536 | title=top[:start] | |
537 | if find(title, '\n') >= 0: return None | |
538 | if not nb(title): return None | |
539 | d=top[start:end] | |
540 | top=top[end:] | |
541 | ||
542 | subs=paragraph.getSubparagraphs() | |
543 | if top[-2:]=='::': | |
544 | subs=[StructuredTextExample(subs)] | |
545 | top=top[:-1] | |
546 | ||
547 | return StructuredTextDescription( | |
548 | title, top, subs, | |
549 | indent=paragraph.indent, | |
550 | delim=d) | |
551 | ||
552 | def doc_header(self, paragraph, | |
553 | expr = re.compile('[ %s0-9.:/,-_*<>\?\'\"]+' % letters).match | |
554 | ): | |
555 | subs=paragraph.getSubparagraphs() | |
556 | if not subs: return None | |
557 | top=paragraph.getColorizableTexts()[0] | |
558 | if not strip(top): return None | |
559 | if top[-2:]=='::': | |
560 | subs=StructuredTextExample(subs) | |
561 | if strip(top)=='::': return subs | |
562 | return ST.StructuredTextParagraph(top[:-1], | |
563 | [subs], | |
564 | indent=paragraph.indent, | |
565 | level=paragraph.level) | |
566 | ||
567 | if find(top,'\n') >= 0: return None | |
568 | return StructuredTextSection(top, subs, indent=paragraph.indent, level=paragraph.level) | |
569 | ||
570 | def doc_literal( | |
571 | self, s, | |
572 | expr=re.compile( | |
573 | "(?:\s|^)'" # open | |
574 | "([^ \t\n\r\f\v']|[^ \t\n\r\f\v'][^\n']*[^ \t\n\r\f\v'])" # contents | |
575 | "'(?:\s|[,.;:!?]|$)" # close | |
576 | ).search): | |
577 | ||
578 | r=expr(s) | |
579 | if r: | |
580 | start, end = r.span(1) | |
581 | return (StructuredTextLiteral(s[start:end]), start-1, end+1) | |
582 | else: | |
583 | return None | |
584 | ||
585 | def doc_emphasize( | |
586 | self, s, | |
587 | expr = re.compile('\s*\*([ \n%s0-9]+)\*(?!\*|-)' % lettpunc).search | |
588 | ): | |
589 | ||
590 | r=expr(s) | |
591 | if r: | |
592 | start, end = r.span(1) | |
593 | return (StructuredTextEmphasis(s[start:end]), start-1, end+1) | |
594 | else: | |
595 | return None | |
596 | ||
597 | def doc_inner_link(self, | |
598 | s, | |
599 | expr1 = re.compile("\.\.\s*").search, | |
600 | expr2 = re.compile("\[[%s0-9]+\]" % letters).search): | |
601 | ||
602 | # make sure we dont grab a named link | |
603 | if expr2(s) and expr1(s): | |
604 | start1,end1 = expr1(s).span() | |
605 | start2,end2 = expr2(s).span() | |
606 | if end1 == start2: | |
607 | # uh-oh, looks like a named link | |
608 | return None | |
609 | else: | |
610 | # the .. is somewhere else, ignore it | |
611 | return (StructuredTextInnerLink(s[start2+1:end2-1]),start2,end2) | |
612 | return None | |
613 | elif expr2(s) and not expr1(s): | |
614 | start,end = expr2(s).span() | |
615 | return (StructuredTextInnerLink(s[start+1:end-1]),start,end) | |
616 | return None | |
617 | ||
618 | def doc_named_link(self, | |
619 | s, | |
620 | expr=re.compile("(\.\.\s)(\[[%s0-9]+\])" % letters).search): | |
621 | ||
622 | result = expr(s) | |
623 | if result: | |
624 | start,end = result.span(2) | |
625 | a,b = result.span(1) | |
626 | str = strip(s[a:b]) + s[start:end] | |
627 | str = s[start+1:end-1] | |
628 | st,en = result.span() | |
629 | return (StructuredTextNamedLink(str),st,en) | |
630 | #return (StructuredTextNamedLink(s[st:en]),st,en) | |
631 | return None | |
632 | ||
633 | def doc_underline(self, | |
634 | s, | |
635 | expr=re.compile("\s+\_([0-9%s ]+)\_" % lettpunc).search): | |
636 | ||
637 | result = expr(s) | |
638 | if result: | |
639 | start,end = result.span(1) | |
640 | st,e = result.span() | |
641 | return (StructuredTextUnderline(s[start:end]),st,e) | |
642 | else: | |
643 | return None | |
644 | ||
645 | def doc_strong(self, | |
646 | s, | |
647 | expr = re.compile('\s*\*\*([ \n%s0-9]+)\*\*' % lettpunc).search | |
648 | ): | |
649 | ||
650 | r=expr(s) | |
651 | if r: | |
652 | start, end = r.span(1) | |
653 | return (StructuredTextStrong(s[start:end]), start-2, end+2) | |
654 | else: | |
655 | return None | |
656 | ||
657 | def doc_href( | |
658 | ||
659 | self, s, | |
660 | expr1 = re.compile("(\"[ %s0-9\n\-\.\,\;\(\)\/\:\/\*\']+\")(:)([a-zA-Z0-9\@\.\,\?\!\/\:\;\-\#\~]+)([,]*\s*)" % letters).search, | |
661 | expr2 = re.compile('(\"[ %s0-9\n\-\.\:\;\(\)\/\*\']+\")([,]+\s+)([a-zA-Z0-9\@\.\,\?\!\/\:\;\-\#\~]+)(\s*)' % letters).search): | |
662 | ||
663 | r=expr1(s) or expr2(s) | |
664 | ||
665 | if r: | |
666 | # need to grab the href part and the | |
667 | # beginning part | |
668 | ||
669 | start,e = r.span(1) | |
670 | name = s[start:e] | |
671 | name = replace(name,'"','',2) | |
672 | st,end = r.span(3) | |
673 | ||
674 | if s[end-1:end] in punctuations: end-=1 | |
675 | link = s[st:end] | |
676 | ||
677 | # name is the href title, link is the target | |
678 | # of the href | |
679 | return (StructuredTextLink(name, href=link), | |
680 | start, end) | |
681 | ||
682 | ||
683 | else: | |
684 | return None |