| 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, rstrip |
| 88 | from STletters import * |
| 89 | |
| 90 | |
| 91 | StringType=type('') |
| 92 | ListType=type([]) |
| 93 | |
| 94 | def flatten(obj, append): |
| 95 | if obj.getNodeType()==STDOM.TEXT_NODE: |
| 96 | append(obj.getNodeValue()) |
| 97 | else: |
| 98 | for child in obj.getChildNodes(): |
| 99 | flatten(child, append) |
| 100 | |
| 101 | |
| 102 | class StructuredTextExample(ST.StructuredTextParagraph): |
| 103 | """Represents a section of document with literal text, as for examples""" |
| 104 | |
| 105 | def __init__(self, subs, **kw): |
| 106 | t=[] |
| 107 | a=t.append |
| 108 | for s in subs: |
| 109 | flatten(s, a) |
| 110 | apply(ST.StructuredTextParagraph.__init__, |
| 111 | (self, join(t,'\n\n'), ()), |
| 112 | kw) |
| 113 | |
| 114 | def getColorizableTexts(self): return () |
| 115 | def setColorizableTexts(self, src): pass # never color examples |
| 116 | |
| 117 | class StructuredTextBullet(ST.StructuredTextParagraph): |
| 118 | """Represents a section of a document with a title and a body""" |
| 119 | |
| 120 | class StructuredTextNumbered(ST.StructuredTextParagraph): |
| 121 | """Represents a section of a document with a title and a body""" |
| 122 | |
| 123 | class StructuredTextDescriptionTitle(ST.StructuredTextParagraph): |
| 124 | """Represents a section of a document with a title and a body""" |
| 125 | |
| 126 | class StructuredTextDescriptionBody(ST.StructuredTextParagraph): |
| 127 | """Represents a section of a document with a title and a body""" |
| 128 | |
| 129 | class StructuredTextDescription(ST.StructuredTextParagraph): |
| 130 | """Represents a section of a document with a title and a body""" |
| 131 | |
| 132 | def __init__(self, title, src, subs, **kw): |
| 133 | apply(ST.StructuredTextParagraph.__init__, (self, src, subs), kw) |
| 134 | self._title=title |
| 135 | |
| 136 | def getColorizableTexts(self): return self._title, self._src |
| 137 | def setColorizableTexts(self, src): self._title, self._src = src |
| 138 | |
| 139 | def getChildren(self): |
| 140 | return (StructuredTextDescriptionTitle(self._title), |
| 141 | StructuredTextDescriptionBody(self._src, self._subs)) |
| 142 | |
| 143 | class StructuredTextSectionTitle(ST.StructuredTextParagraph): |
| 144 | """Represents a section of a document with a title and a body""" |
| 145 | |
| 146 | class StructuredTextSection(ST.StructuredTextParagraph): |
| 147 | """Represents a section of a document with a title and a body""" |
| 148 | def __init__(self, src, subs=None, **kw): |
| 149 | apply(ST.StructuredTextParagraph.__init__, |
| 150 | (self, StructuredTextSectionTitle(src), subs), |
| 151 | kw) |
| 152 | |
| 153 | def getColorizableTexts(self): |
| 154 | return self._src.getColorizableTexts() |
| 155 | |
| 156 | def setColorizableTexts(self,src): |
| 157 | self._src.setColorizableTexts(src) |
| 158 | |
| 159 | # a StructuredTextTable holds StructuredTextRows |
| 160 | class StructuredTextTable(ST.StructuredTextParagraph): |
| 161 | """ |
| 162 | rows is a list of lists containing tuples, which |
| 163 | represent the columns/cells in each rows. |
| 164 | EX |
| 165 | rows = [[('row 1:column1',1)],[('row2:column1',1)]] |
| 166 | """ |
| 167 | |
| 168 | def __init__(self, rows, src, subs, **kw): |
| 169 | apply(ST.StructuredTextParagraph.__init__,(self,subs),kw) |
| 170 | self._rows = [] |
| 171 | for row in rows: |
| 172 | if row: |
| 173 | self._rows.append(StructuredTextRow(row,kw)) |
| 174 | |
| 175 | def getRows(self): |
| 176 | return [self._rows] |
| 177 | |
| 178 | def _getRows(self): |
| 179 | return self.getRows() |
| 180 | |
| 181 | def getColumns(self): |
| 182 | result = [] |
| 183 | for row in self._rows: |
| 184 | result.append(row.getColumns()) |
| 185 | return result |
| 186 | |
| 187 | def _getColumns(self): |
| 188 | return self.getColumns() |
| 189 | |
| 190 | def setColumns(self,columns): |
| 191 | for index in range(len(self._rows)): |
| 192 | self._rows[index].setColumns(columns[index]) |
| 193 | |
| 194 | def _setColumns(self,columns): |
| 195 | return self.setColumns(columns) |
| 196 | |
| 197 | def getColorizableTexts(self): |
| 198 | """ |
| 199 | return a tuple where each item is a column/cell's |
| 200 | contents. The tuple, result, will be of this format. |
| 201 | ("r1 col1", "r1=col2", "r2 col1", "r2 col2") |
| 202 | """ |
| 203 | |
| 204 | result = [] |
| 205 | for row in self._rows: |
| 206 | for column in row.getColumns()[0]: |
| 207 | result.append(column.getColorizableTexts()[0]) |
| 208 | return result |
| 209 | |
| 210 | def setColorizableTexts(self,texts): |
| 211 | """ |
| 212 | texts is going to a tuple where each item is the |
| 213 | result of being mapped to the colortext function. |
| 214 | Need to insert the results appropriately into the |
| 215 | individual columns/cells |
| 216 | """ |
| 217 | for row_index in range(len(self._rows)): |
| 218 | for column_index in range(len(self._rows[row_index]._columns)): |
| 219 | self._rows[row_index]._columns[column_index].setColorizableTexts((texts[0],)) |
| 220 | texts = texts[1:] |
| 221 | |
| 222 | def _getColorizableTexts(self): |
| 223 | return self.getColorizableTexts() |
| 224 | |
| 225 | def _setColorizableTexts(self): |
| 226 | return self.setColorizableTexts() |
| 227 | |
| 228 | # StructuredTextRow holds StructuredTextColumns |
| 229 | class StructuredTextRow(ST.StructuredTextParagraph): |
| 230 | |
| 231 | def __init__(self,row,kw): |
| 232 | """ |
| 233 | row is a list of tuples, where each tuple is |
| 234 | the raw text for a cell/column and the span |
| 235 | of that cell/column. |
| 236 | EX |
| 237 | [('this is column one',1), ('this is column two',1)] |
| 238 | """ |
| 239 | |
| 240 | apply(ST.StructuredTextParagraph.__init__,(self,[]),kw) |
| 241 | |
| 242 | self._columns = [] |
| 243 | for column in row: |
| 244 | self._columns.append(StructuredTextColumn(column[0], |
| 245 | column[1], |
| 246 | column[2], |
| 247 | column[3], |
| 248 | column[4], |
| 249 | kw)) |
| 250 | |
| 251 | def getColumns(self): |
| 252 | return [self._columns] |
| 253 | |
| 254 | def _getColumns(self): |
| 255 | return [self._columns] |
| 256 | |
| 257 | def setColumns(self,columns): |
| 258 | self._columns = columns |
| 259 | |
| 260 | def _setColumns(self,columns): |
| 261 | return self.setColumns(columns) |
| 262 | |
| 263 | # this holds the text of a table cell |
| 264 | class StructuredTextColumn(ST.StructuredTextParagraph): |
| 265 | """ |
| 266 | StructuredTextColumn is a cell/column in a table. |
| 267 | A cell can hold multiple paragraphs. The cell |
| 268 | is either classified as a StructuredTextTableHeader |
| 269 | or StructuredTextTableData. |
| 270 | """ |
| 271 | |
| 272 | def __init__(self,text,span,align,valign,typ,kw): |
| 273 | apply(ST.StructuredTextParagraph.__init__,(self,text,[]),kw) |
| 274 | self._span = span |
| 275 | self._align = align |
| 276 | self._valign = valign |
| 277 | self._type = typ |
| 278 | |
| 279 | def getSpan(self): |
| 280 | return self._span |
| 281 | |
| 282 | def _getSpan(self): |
| 283 | return self._span |
| 284 | |
| 285 | def getAlign(self): |
| 286 | return self._align |
| 287 | |
| 288 | def _getAlign(self): |
| 289 | return self.getAlign() |
| 290 | |
| 291 | def getValign(self): |
| 292 | return self._valign |
| 293 | |
| 294 | def _getValign(self): |
| 295 | return self.getValign() |
| 296 | |
| 297 | def getType(self): |
| 298 | return self._type |
| 299 | |
| 300 | def _getType(self): |
| 301 | return self.getType() |
| 302 | |
| 303 | class StructuredTextTableHeader(ST.StructuredTextParagraph): pass |
| 304 | |
| 305 | class StructuredTextTableData(ST.StructuredTextParagraph): pass |
| 306 | |
| 307 | class StructuredTextMarkup(STDOM.Element): |
| 308 | |
| 309 | def __init__(self, v, **kw): |
| 310 | self._value=v |
| 311 | self._attributes=kw.keys() |
| 312 | for k, v in kw.items(): setattr(self, k, v) |
| 313 | |
| 314 | def getChildren(self, type=type, lt=type([])): |
| 315 | v=self._value |
| 316 | if type(v) is not lt: v=[v] |
| 317 | return v |
| 318 | |
| 319 | def getColorizableTexts(self): return self._value, |
| 320 | def setColorizableTexts(self, v): self._value=v[0] |
| 321 | |
| 322 | def __repr__(self): |
| 323 | return '%s(%s)' % (self.__class__.__name__, `self._value`) |
| 324 | |
| 325 | class StructuredTextLiteral(StructuredTextMarkup): |
| 326 | def getColorizableTexts(self): return () |
| 327 | def setColorizableTexts(self, v): pass |
| 328 | |
| 329 | class StructuredTextEmphasis(StructuredTextMarkup): pass |
| 330 | |
| 331 | class StructuredTextStrong(StructuredTextMarkup): pass |
| 332 | |
| 333 | class StructuredTextInnerLink(StructuredTextMarkup): pass |
| 334 | |
| 335 | class StructuredTextNamedLink(StructuredTextMarkup): pass |
| 336 | |
| 337 | class StructuredTextUnderline(StructuredTextMarkup): pass |
| 338 | |
| 339 | class StructuredTextSGML(StructuredTextMarkup): pass |
| 340 | |
| 341 | class StructuredTextLink(StructuredTextMarkup): pass |
| 342 | |
| 343 | class StructuredTextXref(StructuredTextMarkup): pass |
| 344 | |
| 345 | class DocumentClass: |
| 346 | """ |
| 347 | Class instance calls [ex.=> x()] require a structured text |
| 348 | structure. Doc will then parse each paragraph in the structure |
| 349 | and will find the special structures within each paragraph. |
| 350 | Each special structure will be stored as an instance. Special |
| 351 | structures within another special structure are stored within |
| 352 | the 'top' structure |
| 353 | EX : '-underline this-' => would be turned into an underline |
| 354 | instance. '-underline **this**' would be stored as an underline |
| 355 | instance with a strong instance stored in its string |
| 356 | """ |
| 357 | |
| 358 | paragraph_types = [ |
| 359 | 'doc_bullet', |
| 360 | 'doc_numbered', |
| 361 | 'doc_description', |
| 362 | 'doc_header', |
| 363 | 'doc_table', |
| 364 | ] |
| 365 | |
| 366 | #'doc_inner_link', |
| 367 | #'doc_named_link', |
| 368 | #'doc_underline', |
| 369 | text_types = [ |
| 370 | 'doc_sgml', |
| 371 | 'doc_href', |
| 372 | 'doc_strong', |
| 373 | 'doc_emphasize', |
| 374 | 'doc_literal', |
| 375 | 'doc_sgml', |
| 376 | 'doc_xref', |
| 377 | ] |
| 378 | |
| 379 | def __call__(self, doc): |
| 380 | if type(doc) is type(''): |
| 381 | doc=ST.StructuredText(doc) |
| 382 | doc.setSubparagraphs(self.color_paragraphs( |
| 383 | doc.getSubparagraphs())) |
| 384 | else: |
| 385 | doc=ST.StructuredTextDocument(self.color_paragraphs( |
| 386 | doc.getSubparagraphs())) |
| 387 | return doc |
| 388 | |
| 389 | def parse(self, raw_string, text_type, |
| 390 | type=type, st=type(''), lt=type([])): |
| 391 | |
| 392 | """ |
| 393 | Parse accepts a raw_string, an expr to test the raw_string, |
| 394 | and the raw_string's subparagraphs. |
| 395 | |
| 396 | Parse will continue to search through raw_string until |
| 397 | all instances of expr in raw_string are found. |
| 398 | |
| 399 | If no instances of expr are found, raw_string is returned. |
| 400 | Otherwise a list of substrings and instances is returned |
| 401 | """ |
| 402 | |
| 403 | tmp = [] # the list to be returned if raw_string is split |
| 404 | append=tmp.append |
| 405 | |
| 406 | if type(text_type) is st: text_type=getattr(self, text_type) |
| 407 | |
| 408 | while 1: |
| 409 | t = text_type(raw_string) |
| 410 | if not t: break |
| 411 | #an instance of expr was found |
| 412 | t, start, end = t |
| 413 | |
| 414 | if start: append(raw_string[0:start]) |
| 415 | |
| 416 | tt=type(t) |
| 417 | if tt is st: |
| 418 | # if we get a string back, add it to text to be parsed |
| 419 | raw_string = t+raw_string[end:len(raw_string)] |
| 420 | else: |
| 421 | if tt is lt: |
| 422 | # is we get a list, append it's elements |
| 423 | tmp[len(tmp):]=t |
| 424 | else: |
| 425 | # normal case, an object |
| 426 | append(t) |
| 427 | raw_string = raw_string[end:len(raw_string)] |
| 428 | |
| 429 | if not tmp: return raw_string # nothing found |
| 430 | |
| 431 | if raw_string: append(raw_string) |
| 432 | elif len(tmp)==1: return tmp[0] |
| 433 | |
| 434 | return tmp |
| 435 | |
| 436 | |
| 437 | def color_text(self, str, types=None): |
| 438 | """Search the paragraph for each special structure |
| 439 | """ |
| 440 | if types is None: types=self.text_types |
| 441 | |
| 442 | for text_type in types: |
| 443 | |
| 444 | if type(str) is StringType: |
| 445 | str = self.parse(str, text_type) |
| 446 | elif type(str) is ListType: |
| 447 | r=[]; a=r.append |
| 448 | for s in str: |
| 449 | if type(s) is StringType: |
| 450 | s=self.parse(s, text_type) |
| 451 | if type(s) is ListType: r[len(r):]=s |
| 452 | else: a(s) |
| 453 | else: |
| 454 | s.setColorizableTexts( |
| 455 | map(self.color_text, |
| 456 | s.getColorizableTexts() |
| 457 | )) |
| 458 | a(s) |
| 459 | str=r |
| 460 | else: |
| 461 | r=[]; a=r.append; color=self.color_text |
| 462 | for s in str.getColorizableTexts(): |
| 463 | color(s, (text_type,)) |
| 464 | a(s) |
| 465 | |
| 466 | str.setColorizableTexts(r) |
| 467 | |
| 468 | return str |
| 469 | |
| 470 | def color_paragraphs(self, raw_paragraphs, |
| 471 | type=type, sequence_types=(type([]), type(())), |
| 472 | st=type('')): |
| 473 | result=[] |
| 474 | for paragraph in raw_paragraphs: |
| 475 | if paragraph.getNodeName() != 'StructuredTextParagraph': |
| 476 | result.append(paragraph) |
| 477 | continue |
| 478 | |
| 479 | for pt in self.paragraph_types: |
| 480 | if type(pt) is st: |
| 481 | # grab the corresponding function |
| 482 | pt=getattr(self, pt) |
| 483 | # evaluate the paragraph |
| 484 | r=pt(paragraph) |
| 485 | if r: |
| 486 | if type(r) not in sequence_types: |
| 487 | r=r, |
| 488 | new_paragraphs=r |
| 489 | for paragraph in new_paragraphs: |
| 490 | paragraph.setSubparagraphs(self.color_paragraphs(paragraph.getSubparagraphs())) |
| 491 | break |
| 492 | else: |
| 493 | new_paragraphs=ST.StructuredTextParagraph(paragraph.getColorizableTexts()[0], |
| 494 | self.color_paragraphs(paragraph.getSubparagraphs()), |
| 495 | indent=paragraph.indent), |
| 496 | |
| 497 | # color the inline StructuredText types |
| 498 | # for each StructuredTextParagraph |
| 499 | for paragraph in new_paragraphs: |
| 500 | |
| 501 | if paragraph.getNodeName() is "StructuredTextTable": |
| 502 | cells = paragraph.getColumns() |
| 503 | text = paragraph.getColorizableTexts() |
| 504 | text = map(ST.StructuredText,text) |
| 505 | text = map(self.__call__,text) |
| 506 | for t in range(len(text)): |
| 507 | text[t] = text[t].getSubparagraphs() |
| 508 | paragraph.setColorizableTexts(text) |
| 509 | |
| 510 | paragraph.setColorizableTexts( |
| 511 | map(self.color_text, |
| 512 | paragraph.getColorizableTexts() |
| 513 | )) |
| 514 | result.append(paragraph) |
| 515 | |
| 516 | return result |
| 517 | |
| 518 | def doc_table(self, paragraph, expr = re.compile(r'\s*\|[-]+\|').match): |
| 519 | text = paragraph.getColorizableTexts()[0] |
| 520 | m = expr(text) |
| 521 | |
| 522 | subs = paragraph.getSubparagraphs() |
| 523 | |
| 524 | if not (m): |
| 525 | return None |
| 526 | rows = [] |
| 527 | |
| 528 | spans = [] |
| 529 | ROWS = [] |
| 530 | COLS = [] |
| 531 | indexes = [] |
| 532 | ignore = [] |
| 533 | |
| 534 | TDdivider = re.compile("[\-]+").match |
| 535 | THdivider = re.compile("[\=]+").match |
| 536 | col = re.compile('\|').search |
| 537 | innertable = re.compile('\|([-]+|[=]+)\|').search |
| 538 | |
| 539 | text = strip(text) |
| 540 | rows = split(text,'\n') |
| 541 | foo = "" |
| 542 | |
| 543 | for row in range(len(rows)): |
| 544 | rows[row] = strip(rows[row]) |
| 545 | |
| 546 | # have indexes store if a row is a divider |
| 547 | # or a cell part |
| 548 | for index in range(len(rows)): |
| 549 | tmpstr = rows[index][1:len(rows[index])-1] |
| 550 | if TDdivider(tmpstr): |
| 551 | indexes.append("TDdivider") |
| 552 | elif THdivider(tmpstr): |
| 553 | indexes.append("THdivider") |
| 554 | else: |
| 555 | indexes.append("cell") |
| 556 | |
| 557 | for index in range(len(indexes)): |
| 558 | if indexes[index] is "TDdivider" or indexes[index] is THdivider: |
| 559 | ignore = [] # reset ignore |
| 560 | #continue # skip dividers |
| 561 | |
| 562 | tmp = strip(rows[index]) # clean the row up |
| 563 | tmp = tmp[1:len(tmp)-1] # remove leading + trailing | |
| 564 | offset = 0 |
| 565 | |
| 566 | # find the start and end of inner |
| 567 | # tables. ignore everything between |
| 568 | if innertable(tmp): |
| 569 | tmpstr = strip(tmp) |
| 570 | while innertable(tmpstr): |
| 571 | start,end = innertable(tmpstr).span() |
| 572 | if not (start,end-1) in ignore: |
| 573 | ignore.append(start,end-1) |
| 574 | tmpstr = " " + tmpstr[end:] |
| 575 | |
| 576 | # find the location of column dividers |
| 577 | # NOTE: |'s in inner tables do not count |
| 578 | # as column dividers |
| 579 | if col(tmp): |
| 580 | while col(tmp): |
| 581 | bar = 1 # true if start is not in ignore |
| 582 | start,end = col(tmp).span() |
| 583 | |
| 584 | if not start+offset in spans: |
| 585 | for s,e in ignore: |
| 586 | if start+offset >= s or start+offset <= e: |
| 587 | bar = None |
| 588 | break |
| 589 | if bar: # start is clean |
| 590 | spans.append(start+offset) |
| 591 | if not bar: |
| 592 | foo = foo + tmp[:end] |
| 593 | tmp = tmp[end:] |
| 594 | offset = offset + end |
| 595 | else: |
| 596 | COLS.append((foo + tmp[0:start],start+offset)) |
| 597 | foo = "" |
| 598 | tmp = " " + tmp[end:] |
| 599 | offset = offset + start |
| 600 | if not offset+len(tmp) in spans: |
| 601 | spans.append(offset+len(tmp)) |
| 602 | COLS.append((foo + tmp,offset+len(tmp))) |
| 603 | foo = "" |
| 604 | ROWS.append(COLS) |
| 605 | COLS = [] |
| 606 | |
| 607 | spans.sort() |
| 608 | ROWS = ROWS[1:len(ROWS)] |
| 609 | |
| 610 | # find each column span |
| 611 | cols = [] |
| 612 | tmp = [] |
| 613 | |
| 614 | for row in ROWS: |
| 615 | for c in row: |
| 616 | tmp.append(c[1]) |
| 617 | cols.append(tmp) |
| 618 | tmp = [] |
| 619 | |
| 620 | cur = 1 |
| 621 | tmp = [] |
| 622 | C = [] |
| 623 | for col in cols: |
| 624 | for span in spans: |
| 625 | if not span in col: |
| 626 | cur = cur + 1 |
| 627 | else: |
| 628 | tmp.append(cur) |
| 629 | cur = 1 |
| 630 | C.append(tmp) |
| 631 | tmp = [] |
| 632 | |
| 633 | for index in range(len(C)): |
| 634 | for i in range(len(C[index])): |
| 635 | ROWS[index][i] = (ROWS[index][i][0],C[index][i]) |
| 636 | rows = ROWS |
| 637 | |
| 638 | # label things as either TableData or |
| 639 | # Table header |
| 640 | TD = [] |
| 641 | TH = [] |
| 642 | all = [] |
| 643 | for index in range(len(indexes)): |
| 644 | if indexes[index] is "TDdivider": |
| 645 | TD.append(index) |
| 646 | all.append(index) |
| 647 | if indexes[index] is "THdivider": |
| 648 | TH.append(index) |
| 649 | all.append(index) |
| 650 | TD = TD[1:] |
| 651 | dividers = all[1:] |
| 652 | #print "TD => ", TD |
| 653 | #print "TH => ", TH |
| 654 | #print "all => ", all, "\n" |
| 655 | |
| 656 | for div in dividers: |
| 657 | if div in TD: |
| 658 | index = all.index(div) |
| 659 | for rowindex in range(all[index-1],all[index]): |
| 660 | for i in range(len(rows[rowindex])): |
| 661 | rows[rowindex][i] = (rows[rowindex][i][0], |
| 662 | rows[rowindex][i][1], |
| 663 | "td") |
| 664 | else: |
| 665 | index = all.index(div) |
| 666 | for rowindex in range(all[index-1],all[index]): |
| 667 | for i in range(len(rows[rowindex])): |
| 668 | rows[rowindex][i] = (rows[rowindex][i][0], |
| 669 | rows[rowindex][i][1], |
| 670 | "th") |
| 671 | |
| 672 | # now munge the multi-line cells together |
| 673 | # as paragraphs |
| 674 | ROWS = [] |
| 675 | COLS = [] |
| 676 | for row in rows: |
| 677 | for index in range(len(row)): |
| 678 | if not COLS: |
| 679 | COLS = range(len(row)) |
| 680 | for i in range(len(COLS)): |
| 681 | COLS[i] = ["",1,""] |
| 682 | if TDdivider(row[index][0]) or THdivider(row[index][0]): |
| 683 | ROWS.append(COLS) |
| 684 | COLS = [] |
| 685 | else: |
| 686 | COLS[index][0] = COLS[index][0] + (row[index][0]) + "\n" |
| 687 | COLS[index][1] = row[index][1] |
| 688 | COLS[index][2] = row[index][2] |
| 689 | |
| 690 | # now that each cell has been munged together, |
| 691 | # determine the cell's alignment. |
| 692 | # Default is to center. Also determine the cell's |
| 693 | # vertical alignment, top, middle, bottom. Default is |
| 694 | # to middle |
| 695 | rows = [] |
| 696 | cols = [] |
| 697 | for row in ROWS: |
| 698 | for index in range(len(row)): |
| 699 | topindent = 0 |
| 700 | bottomindent = 0 |
| 701 | leftindent = 0 |
| 702 | rightindent = 0 |
| 703 | left = [] |
| 704 | right = [] |
| 705 | text = row[index][0] |
| 706 | text = split(text,'\n') |
| 707 | text = text[:len(text)-1] |
| 708 | align = "" |
| 709 | valign = "" |
| 710 | for t in text: |
| 711 | t = strip(t) |
| 712 | if not t: |
| 713 | topindent = topindent + 1 |
| 714 | else: |
| 715 | break |
| 716 | text.reverse() |
| 717 | for t in text: |
| 718 | t = strip(t) |
| 719 | if not t: |
| 720 | bottomindent = bottomindent + 1 |
| 721 | else: |
| 722 | break |
| 723 | text.reverse() |
| 724 | tmp = join(text[topindent:len(text)-bottomindent],"\n") |
| 725 | pars = re.compile("\n\s*\n").split(tmp) |
| 726 | for par in pars: |
| 727 | if index > 0: |
| 728 | par = par[1:] |
| 729 | par = split(par, ' ') |
| 730 | for p in par: |
| 731 | if not p: |
| 732 | leftindent = leftindent+1 |
| 733 | else: |
| 734 | break |
| 735 | left.append(leftindent) |
| 736 | leftindent = 0 |
| 737 | par.reverse() |
| 738 | for p in par: |
| 739 | if not p: |
| 740 | rightindent = rightindent + 1 |
| 741 | else: |
| 742 | break |
| 743 | right.append(rightindent) |
| 744 | rightindent = 0 |
| 745 | left.sort() |
| 746 | right.sort() |
| 747 | |
| 748 | if topindent == bottomindent: |
| 749 | valign="middle" |
| 750 | elif topindent < 1: |
| 751 | valign="top" |
| 752 | elif bottomindent < 1: |
| 753 | valign="bottom" |
| 754 | else: |
| 755 | valign="middle" |
| 756 | |
| 757 | if left[0] < 1: |
| 758 | align = "left" |
| 759 | elif right[0] < 1: |
| 760 | align = "right" |
| 761 | elif left[0] > 1 and right[0] > 1: |
| 762 | align="center" |
| 763 | else: |
| 764 | align="left" |
| 765 | |
| 766 | cols.append(row[index][0],row[index][1],align,valign,row[index][2]) |
| 767 | rows.append(cols) |
| 768 | cols = [] |
| 769 | return StructuredTextTable(rows,text,subs,indent=paragraph.indent) |
| 770 | |
| 771 | def doc_bullet(self, paragraph, expr = re.compile(r'\s*[-*o]\s+').match): |
| 772 | top=paragraph.getColorizableTexts()[0] |
| 773 | m=expr(top) |
| 774 | |
| 775 | if not m: |
| 776 | return None |
| 777 | |
| 778 | subs=paragraph.getSubparagraphs() |
| 779 | if top[-2:]=='::': |
| 780 | subs=[StructuredTextExample(subs)] |
| 781 | top=top[:-1] |
| 782 | return StructuredTextBullet(top[m.span()[1]:], subs, |
| 783 | indent=paragraph.indent, |
| 784 | bullet=top[:m.span()[1]] |
| 785 | ) |
| 786 | |
| 787 | def doc_numbered( |
| 788 | self, paragraph, |
| 789 | expr = re.compile(r'(\s*[%s]+\.)|(\s*[0-9]+\.)|(\s*[0-9]+\s+)' % letters).match): |
| 790 | |
| 791 | # This is the old expression. It had a nasty habit |
| 792 | # of grabbing paragraphs that began with a single |
| 793 | # letter word even if there was no following period. |
| 794 | |
| 795 | #expr = re.compile('\s*' |
| 796 | # '(([a-zA-Z]|[0-9]+|[ivxlcdmIVXLCDM]+)\.)*' |
| 797 | # '([a-zA-Z]|[0-9]+|[ivxlcdmIVXLCDM]+)\.?' |
| 798 | # '\s+').match): |
| 799 | |
| 800 | top=paragraph.getColorizableTexts()[0] |
| 801 | m=expr(top) |
| 802 | if not m: return None |
| 803 | subs=paragraph.getSubparagraphs() |
| 804 | if top[-2:]=='::': |
| 805 | subs=[StructuredTextExample(subs)] |
| 806 | top=top[:-1] |
| 807 | return StructuredTextNumbered(top[m.span()[1]:], subs, |
| 808 | indent=paragraph.indent, |
| 809 | number=top[:m.span()[1]]) |
| 810 | |
| 811 | def doc_description( |
| 812 | self, paragraph, |
| 813 | delim = re.compile(r'\s+--\s+').search, |
| 814 | nb=re.compile(r'[^\000- ]').search, |
| 815 | ): |
| 816 | |
| 817 | top=paragraph.getColorizableTexts()[0] |
| 818 | d=delim(top) |
| 819 | if not d: return None |
| 820 | start, end = d.span() |
| 821 | title=top[:start] |
| 822 | if find(title, '\n') >= 0: return None |
| 823 | if not nb(title): return None |
| 824 | d=top[start:end] |
| 825 | top=top[end:] |
| 826 | |
| 827 | subs=paragraph.getSubparagraphs() |
| 828 | if top[-2:]=='::': |
| 829 | subs=[StructuredTextExample(subs)] |
| 830 | top=top[:-1] |
| 831 | |
| 832 | return StructuredTextDescription( |
| 833 | title, top, subs, |
| 834 | indent=paragraph.indent, |
| 835 | delim=d) |
| 836 | |
| 837 | def doc_header(self, paragraph, |
| 838 | expr = re.compile(r'[ %s0-9.:/,-_*<>\?\'\"]+' % letters).match |
| 839 | ): |
| 840 | subs=paragraph.getSubparagraphs() |
| 841 | if not subs: return None |
| 842 | top=paragraph.getColorizableTexts()[0] |
| 843 | if not strip(top): return None |
| 844 | if top[-2:]=='::': |
| 845 | subs=StructuredTextExample(subs) |
| 846 | if strip(top)=='::': return subs |
| 847 | return ST.StructuredTextParagraph( |
| 848 | top[:-1], [subs], indent=paragraph.indent) |
| 849 | |
| 850 | if find(top,'\n') >= 0: return None |
| 851 | return StructuredTextSection(top, subs, indent=paragraph.indent) |
| 852 | |
| 853 | def doc_literal( |
| 854 | self, s, |
| 855 | expr=re.compile( |
| 856 | r"(?:\s|^)'" # open |
| 857 | r"([^ \t\n\r\f\v']|[^ \t\n\r\f\v'][^\n']*[^ \t\n\r\f\v'])" # contents |
| 858 | r"'(?:\s|[,.;:!?]|$)" # close |
| 859 | ).search): |
| 860 | |
| 861 | r=expr(s) |
| 862 | if r: |
| 863 | start, end = r.span(1) |
| 864 | return (StructuredTextLiteral(s[start:end]), start-1, end+1) |
| 865 | else: |
| 866 | return None |
| 867 | |
| 868 | def doc_emphasize( |
| 869 | self, s, |
| 870 | expr = re.compile(r'\s*\*([ \n%s0-9]+)\*(?!\*|-)' % lettpunc).search |
| 871 | ): |
| 872 | |
| 873 | r=expr(s) |
| 874 | if r: |
| 875 | start, end = r.span(1) |
| 876 | return (StructuredTextEmphasis(s[start:end]), start-1, end+1) |
| 877 | else: |
| 878 | return None |
| 879 | |
| 880 | def doc_inner_link(self, |
| 881 | s, |
| 882 | expr1 = re.compile(r"\.\.\s*").search, |
| 883 | expr2 = re.compile(r"\[[%s0-9]+\]" % letters ).search): |
| 884 | |
| 885 | # make sure we dont grab a named link |
| 886 | if expr2(s) and expr1(s): |
| 887 | start1,end1 = expr1(s).span() |
| 888 | start2,end2 = expr2(s).span() |
| 889 | if end1 == start2: |
| 890 | # uh-oh, looks like a named link |
| 891 | return None |
| 892 | else: |
| 893 | # the .. is somewhere else, ignore it |
| 894 | return (StructuredTextInnerLink(s[start2+1,end2-1],start2,end2)) |
| 895 | return None |
| 896 | elif expr2(s) and not expr1(s): |
| 897 | start,end = expr2(s).span() |
| 898 | return (StructuredTextInnerLink(s[start+1:end-1]),start,end) |
| 899 | return None |
| 900 | |
| 901 | def doc_named_link(self, |
| 902 | s, |
| 903 | expr=re.compile(r"(\.\.\s)(\[[%s0-9]+\])" % letters).search): |
| 904 | |
| 905 | result = expr(s) |
| 906 | if result: |
| 907 | start,end = result.span(2) |
| 908 | a,b = result.span(1) |
| 909 | str = strip(s[a:b]) + s[start:end] |
| 910 | st,en = result.span() |
| 911 | return (StructuredTextNamedLink(str),st,en) |
| 912 | #return (StructuredTextNamedLink(s[st:en]),st,en) |
| 913 | return None |
| 914 | |
| 915 | def doc_underline(self, |
| 916 | s, |
| 917 | expr=re.compile(r"\s+\_([%s0-9\s]+)\_" % lettpunc).search): |
| 918 | |
| 919 | result = expr(s) |
| 920 | if result: |
| 921 | start,end = result.span(1) |
| 922 | st,e = result.span() |
| 923 | return (StructuredTextUnderline(s[start:end]),st,e) |
| 924 | else: |
| 925 | return None |
| 926 | |
| 927 | def doc_strong(self, |
| 928 | s, |
| 929 | expr = re.compile(r'\s*\*\*([ \n%s0-9]+)\*\*' % lettpunc).search |
| 930 | ): |
| 931 | |
| 932 | r=expr(s) |
| 933 | if r: |
| 934 | start, end = r.span(1) |
| 935 | return (StructuredTextStrong(s[start:end]), start-2, end+2) |
| 936 | else: |
| 937 | return None |
| 938 | |
| 939 | ## Some constants to make the doc_href() regex easier to read. |
| 940 | _DQUOTEDTEXT = r'("[%s0-9\n\-\.\,\;\(\)\/\:\/\*\']+")' % letters ## double quoted text |
| 941 | _URL_AND_PUNC = r'([%s0-9\@\.\,\?\!\/\:\;\-\#\~]+)' % letters |
| 942 | _SPACES = r'(\s*)' |
| 943 | |
| 944 | def doc_href(self, s, |
| 945 | expr1 = re.compile(_DQUOTEDTEXT + "(:)" + _URL_AND_PUNC + _SPACES).search, |
| 946 | expr2 = re.compile(_DQUOTEDTEXT + r'(\,\s+)' + _URL_AND_PUNC + _SPACES).search): |
| 947 | |
| 948 | punctuation = re.compile(r"[\,\.\?\!\;]+").match |
| 949 | r=expr1(s) or expr2(s) |
| 950 | |
| 951 | if r: |
| 952 | # need to grab the href part and the |
| 953 | # beginning part |
| 954 | |
| 955 | start,e = r.span(1) |
| 956 | name = s[start:e] |
| 957 | name = replace(name,'"','',2) |
| 958 | #start = start + 1 |
| 959 | st,end = r.span(3) |
| 960 | if punctuation(s[end-1:end]): |
| 961 | end = end -1 |
| 962 | link = s[st:end] |
| 963 | #end = end - 1 |
| 964 | |
| 965 | # name is the href title, link is the target |
| 966 | # of the href |
| 967 | return (StructuredTextLink(name, href=link), |
| 968 | start, end) |
| 969 | |
| 970 | #return (StructuredTextLink(s[start:end], href=s[start:end]), |
| 971 | # start, end) |
| 972 | else: |
| 973 | return None |
| 974 | |
| 975 | def doc_sgml(self,s,expr=re.compile(r"\<[%s0-9\.\=\'\"\:\/\-\#\+\s\*]+\>" % letters).search): |
| 976 | """ |
| 977 | SGML text is ignored and outputed as-is |
| 978 | """ |
| 979 | r = expr(s) |
| 980 | if r: |
| 981 | start,end = r.span() |
| 982 | text = s[start:end] |
| 983 | return (StructuredTextSGML(text),start,end) |
| 984 | |
| 985 | |
| 986 | def doc_xref(self, s, |
| 987 | expr = re.compile('\[([%s0-9\-.:/;,\n\~]+)\]' % letters).search |
| 988 | ): |
| 989 | r = expr(s) |
| 990 | if r: |
| 991 | start, end = r.span(1) |
| 992 | return (StructuredTextXref(s[start:end]), start-1, end+1) |
| 993 | else: |
| 994 | return None |
| 995 | |
| 996 | |
| 997 | |
| 998 | |