/usr/share/pyshared/pyth/plugins/rtf15/reader.py is in python-pyth 0.5.6-3.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 | """
Read documents from RTF 1.5
http://www.biblioscape.com/rtf15_spec.htm
This module is potentially compatible with RTF versions up to 1.9.1,
but may not ignore all necessary control groups.
"""
import string, re, itertools, struct
from pyth import document
from pyth.format import PythReader
from pyth.encodings import symbol
_CONTROLCHARS = set(string.ascii_letters + string.digits + "-*")
_DIGITS = set(string.digits)
_CODEPAGES = {
0: "cp1252", # ANSI
1: "cp1252", # Default (this is wrong, but there is no right)
2: "symbol", # Symbol
77: "mac-roman", # Mac Roman
# Does Python have built-in support for these? What is it?
# 78: "10001", # Mac Shift Jis
# 79: "10003", # Mac Hangul
# 80: "10008", # Mac GB2312
# 81: "10002", # Mac Big5
# 83: "10005", # Mac Hebrew
84: "mac-arabic", # Mac Arabic
85: "mac-greek", # Mac Greek
86: "mac-turkish", # Mac Turkish
# 87: "10021", # Mac Thai
# 88: "10029", # Mac East Europe
# 89: "10007", # Mac Russian
128: "cp932", # Shift JIS
129: "cp949", # Hangul
130: "cp1361", # Johab
134: "cp936", # GB2312
136: "cp950", # Big5
161: "cp1253", # Greek
162: "cp1254", # Turkish
163: "cp1258", # Vietnamese
177: "cp1255", # Hebrew
178: "cp1256", # Arabic
186: "cp1257", # Baltic
204: "cp1251", # Russian
222: "cp874", # Thai
238: "cp1250", # Eastern European
254: "cp437", # PC 437
255: "cp850", # OEM
}
# All the ones named by number in my 2.6 encodings dir
_CODEPAGES_BY_NUMBER = dict(
(x, "cp%s" % x) for x in (37, 1006, 1026, 1140, 1250, 1251, 1252, 1253, 1254, 1255,
1256, 1257, 1258, 424, 437, 500, 737, 775, 850, 852, 855,
856, 857, 860, 861, 862, 863, 864, 865, 866, 869, 874,
875, 932, 949, 950))
# Miscellaneous, incomplete
_CODEPAGES_BY_NUMBER.update({
10000: "mac-roman",
10007: "mac-greek",
})
class BackslashEscape(Exception):
pass
class Rtf15Reader(PythReader):
@classmethod
def read(self, source, errors='strict'):
"""
source: A list of P objects.
"""
reader = Rtf15Reader(source, errors)
return reader.go()
def __init__(self, source, errors='strict'):
self.source = source
self.errors = errors
self.document = document.Document
def go(self):
self.source.seek(0)
if self.source.read(5) != r"{\rtf":
from pyth.errors import WrongFileType
raise WrongFileType("Doesn't look like an RTF file")
self.source.seek(0)
self.charsetTable = None
self.charset = 'cp1252'
self.group = Group(self)
self.stack = [self.group]
self.parse()
return self.build()
def parse(self):
while True:
next = self.source.read(1)
if not next:
break
if next in '\r\n':
continue
if next == '{':
subGroup = Group(self, self.group, self.charsetTable)
self.stack.append(subGroup)
subGroup.skip = self.group.skip
self.group = subGroup
elif next == '}':
subGroup = self.stack.pop()
self.group = self.stack[-1]
subGroup.finalize()
if subGroup.specialMeaning == 'FONT_TABLE':
self.charsetTable = subGroup.charsetTable
self.group.content.append(subGroup)
elif self.group.skip:
# Avoid crashing on stuff we can't handle
# inside groups we don't care about anyway
continue
elif next == '\\':
control, digits = self.getControl()
self.group.handle(control, digits)
else:
self.group.char(next)
def getControl(self):
chars = []
digits = []
current = chars
first = True
while True:
next = self.source.read(1)
if not next:
break
if first and next in '\\{}':
chars.extend("control_symbol")
digits.append(next)
break
if first and next in '\r\n':
# Special-cased in RTF, equivalent to a \par
chars.extend("par")
break
first = False
if next == "'":
# ANSI escape, takes two hex digits
chars.extend("ansi_escape")
digits.extend(self.source.read(2))
break
if next == ' ':
# Don't rewind, the space is just a delimiter
break
if next not in _CONTROLCHARS:
# Rewind, it's a meaningful character
self.source.seek(-1, 1)
break
if next in _DIGITS:
current = digits
current.append(next)
return "".join(chars), "".join(digits)
def build(self):
doc = document.Document()
ctx = DocBuilder(doc)
for bit in self.group.flatten():
typeName = type(bit).__name__
getattr(ctx, "handle_%s" % typeName)(bit)
ctx.flushParagraph()
return doc
class DocBuilder(object):
def __init__(self, doc):
self.run = []
self.propStack = [{}]
self.block = None
self.listLevel = None
self.listStack = [doc]
def flushRun(self):
if self.block is None:
self.block = document.Paragraph()
self.block.content.append(
document.Text(self.propStack[-1].copy(),
[u"".join(self.run)]))
self.run[:] = []
def cleanParagraph(self):
"""
Compress text runs, remove whitespace at start and end,
skip empty blocks, etc
"""
runs = self.block.content
if not runs:
self.block = None
return
joinedRuns = []
hasContent = False
for run in runs:
if run.content[0]:
hasContent = True
else:
continue
# For whitespace-only groups, remove any property stuff,
# to avoid extra markup in output
if not run.content[0].strip():
run.properties = {}
# Join runs only if their properties match
if joinedRuns and (run.properties == joinedRuns[-1].properties):
joinedRuns[-1].content[0] += run.content[0]
else:
joinedRuns.append(run)
if hasContent:
# Strip beginning of paragraph
joinedRuns[0].content[0] = joinedRuns[0].content[0].lstrip()
# And then strip the end
joinedRuns[-1].content[0] = joinedRuns[-1].content[0].rstrip()
self.block.content = joinedRuns
else:
self.block = None
def flushParagraph(self):
self.flushRun()
if self.block.content:
self.cleanParagraph()
if self.block is not None:
self.listStack[-1].append(self.block)
def handle_unicode(self, bit):
self.run.append(bit)
def handle_Push(self, _):
self.propStack.append(self.propStack[-1].copy())
def handle_Pop(self, _):
self.flushRun()
self.propStack.pop()
def handle_Para(self, para):
self.flushParagraph()
prevListLevel = self.listLevel
self.listLevel = para.listLevel
if self.listLevel > prevListLevel:
l = document.List()
self.listStack.append(l)
elif self.listLevel < prevListLevel:
l = self.listStack.pop()
self.listStack[-1].append(l)
self.block = None
def handle_Reset(self, _):
self.flushRun()
self.propStack[-1].clear()
def handle_ReadableMarker(self, marker):
self.flushRun()
if marker.val:
# RTF needs underline markers for hyperlinks,
# but nothing else does. If we're in a hyperlink,
# ignore underlines.
if 'url' in self.propStack[-1] and marker.name == 'underline':
return
self.propStack[-1][marker.name] = marker.val
else:
if marker.name in self.propStack[-1]:
del self.propStack[-1][marker.name]
class Group(object):
def __init__(self, reader, parent=None, charsetTable=None):
self.reader = reader
self.parent = parent
if parent:
self.props = parent.props.copy()
self.charset = self.parent.charset
else:
self.props = {}
self.charset = self.reader.charset
self.specialMeaning = None
self.skip = False
self.url = None
self.currentParaTag = None
self.destination = False
self.charsetTable = charsetTable
self.content = []
def handle(self, control, digits):
if control == '*':
self.destination = True
return
handler = getattr(self, 'handle_%s' % control, None)
if handler is None:
return
if digits:
handler(digits)
else:
handler()
def char(self, char):
self.content.append(char.decode(self.charset, self.reader.errors))
def _finalize(self):
if self.destination:
self.skip = True
if self.specialMeaning is not None:
self.skip = True
if self.skip:
return
stuff = []
i = 0
while i < len(self.content):
thing = self.content[i]
if isinstance(thing, Skip):
i += thing.count
else:
stuff.append(thing)
i += 1
self.content = stuff
# This is only the default,
# and is overridden by some controls
finalize = _finalize
def flatten(self):
if self.skip:
return []
stuff = [Push]
for thing in self.content:
if isinstance(thing, Group):
stuff.extend(thing.flatten())
else:
stuff.append(thing)
stuff.append(Pop)
return stuff
# Header stuff
def handle_ansi(self): self.charset = self.reader.charset = 'cp1252'
def handle_mac(self): self.charset = self.reader.charset = 'mac-roman'
def handle_pc(self): self.charset = self.reader.charset = 'cp437'
def handle_pca(self): self.charset = self.reader.charset = 'cp850'
def handle_ansicpg(self, codepage):
codepage = int(codepage)
if codepage in _CODEPAGES_BY_NUMBER:
self.charset = self.reader.charset = _CODEPAGES_BY_NUMBER[codepage]
else:
raise ValueError("Unknown codepage %s" % codepage)
def handle_fonttbl(self):
self.specialMeaning = 'FONT_TABLE'
self.charsetTable = {}
def _setFontCharset(self, charset=None):
if charset is None:
charset = self.reader.charset
# XXX Todo: Figure out a more graceful way to handle the fact that
# RTF font declarations can be in their own groups or not
if self.parent.charsetTable is not None:
self.parent.charsetTable[self.fontNum] = charset
else:
self.charsetTable[self.fontNum] = charset
def handle_f(self, fontNum):
if 'FONT_TABLE' in (self.parent.specialMeaning, self.specialMeaning):
self.fontNum = int(fontNum)
self._setFontCharset()
elif self.charsetTable is not None:
self.charset = self.charsetTable[int(fontNum)]
def handle_fcharset(self, charsetNum):
if 'FONT_TABLE' in (self.parent.specialMeaning, self.specialMeaning):
# Theoretically, \fN should always be before \fcharsetN
# I don't really expect that will always be true, but let's crash
# if it's not, and see if it happens in the real world.
charset = _CODEPAGES.get(int(charsetNum))
if charset is None:
raise ValueError("Unsupported charset %s" % charsetNum)
self._setFontCharset(charset)
def handle_ansi_escape(self, code):
code = int(code, 16)
if isinstance(self.charset, dict):
uni_code = self.charset.get(code)
if uni_code is None:
char = u'?'
else:
char = unichr(uni_code)
else:
char = chr(code).decode(self.charset, self.reader.errors)
self.content.append(char)
def handle_control_symbol(self, symbol):
# Ignore ~, -, and _, since they are optional crap.
if symbol in '\\{}':
self.content.append(unicode(symbol))
def handle_u(self, codepoint):
codepoint = int(codepoint)
try:
char = unichr(codepoint)
except ValueError:
if self.reader.errors == 'replace':
char = '?'
else:
raise
self.content.append(char)
self.content.append(Skip(self.props.get('unicode_skip', 1)))
def handle_par(self):
p = Para()
self.content.append(p)
self.currentParaTag = p
def handle_pard(self):
self.content.append(Reset)
def handle_plain(self):
self.content.append(Reset)
def handle_line(self):
self.content.append(u"\n")
def handle_b(self, onOff=None):
val = onOff in (None, "", "1")
self.content.append(ReadableMarker("bold", val))
def handle_i(self, onOff=None):
val = onOff in (None, "", "1")
self.content.append(ReadableMarker("italic", val))
def handle_ul(self, onOff=None):
val = onOff in (None, "", "1")
self.content.append(ReadableMarker("underline", val))
def handle_ilvl(self, level):
if self.currentParaTag is not None:
self.currentParaTag.listLevel = level
else:
# Well, now we're in trouble. But I'm pretty sure this
# isn't supposed to happen anyway.
pass
def handle_up(self, amount):
self.content.append(ReadableMarker("super", True))
def handle_super(self):
self.content.append(ReadableMarker("super", True))
def handle_dn(self, amount):
self.content.append(ReadableMarker("sub", True))
def handle_sub(self):
self.content.append(ReadableMarker("sub", True))
def handle_emdash(self):
self.content.append(u'\u2014')
def handle_endash(self):
self.content.append(u'\u2013')
def handle_lquote(self):
self.content.append(u'\u2018')
def handle_rquote(self):
self.content.append(u'\u2019')
def handle_ldblquote(self):
self.content.append(u'\u201C')
def handle_rdblquote(self):
self.content.append(u'\u201D')
def handle_field(self):
def finalize():
if len(self.content) != 2:
return u""
destination, content = self.content
# The destination isn't allowed to contain any controls,
# so this should be safe.
# Except when it isn't, like this:
# {\field{\*\fldinst {\rtlch\fcs1 \af0 \ltrch\fcs0 \insrsid15420660 PAGE \\* MERGEFORMAT }}
try:
destination = u"".join(destination.content)
except:
return u""
match = re.match(ur'HYPERLINK "(.*)"', destination)
if match:
content.skip = False
self.content = [ReadableMarker("url", match.group(1)),
content]
else:
return u""
self.finalize = finalize
def __repr__(self):
return "G(%s)" % repr(self.content)
def ignore(self, _=None):
self.skip = True
# Header
handle_filetbl = ignore
handle_colortbl = ignore
handle_stylesheet = ignore
handle_listtable = ignore
handle_listoverridetable = ignore
handle_revtbl = ignore
handle_mmath = ignore
handle_header = ignore
handle_footer = ignore
handle_headerl = ignore
handle_headerr = ignore
handle_headerf = ignore
handle_footerl = ignore
handle_footerr = ignore
handle_footerf = ignore
# Document
handle_info = ignore
handle_docfmt = ignore
handle_pgdsctbl = ignore
handle_listtext = ignore
# Revision hacks
handle_revauthdel = ignore
class Skip(object):
def __init__(self, count):
self.count = count
class ReadableMarker(object):
def __init__(self, name=None, val=None):
if name is not None:
self.name = name
self.val = val
def __repr__(self):
if self.val is None:
return "!%s!" % self.name
else:
return "!%s::%s!" % (self.name, self.val)
class Para(ReadableMarker):
listLevel = None
def __init__(self):
ReadableMarker.__init__(self, "Para")
def __repr__(self):
return "!Para:%s!" % self.listLevel
class Reset(ReadableMarker):
name = "Reset"
class Push(ReadableMarker):
name = "Push"
class Pop(ReadableMarker):
name = "Pop"
# Yes, yes, I know, I'll clean it up later.
Reset = Reset()
Push = Push()
Pop = Pop()
|