/usr/share/pyshared/rest2web/restindex.py is in rest2web 0.5.2~alpha+svn-r248-2.
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 | # restindex.py
# Subversion Details
# $LastChangedDate: 2007-06-10 00:06:55 +0200 (Sun, 10 Jun 2007) $
# $LastChangedBy: fuzzyman $
# $HeadURL: https://svn.rest2web.python-hosting.com/trunk/rest2web/restindex.py $
# $LastChangedRevision: 246 $
# The function that parses the restindex, and associated data.
# http://www.voidspace.org.uk/python/rest2web
# Copyright Michael Foord, 2004 - 2006.
# Released subject to the BSD License
# Please see http://www.voidspace.org.uk/python/license.shtml
# For information about bugfixes, updates and support, please join the
# rest2web mailing list.
# http://lists.sourceforge.net/lists/listinfo/rest2web-develop
# Comments, suggestions and bug reports welcome.
# Scripts maintained at http://www.voidspace.org.uk/python/index.shtml
# E-mail fuzzyman@voidspace.org.uk
import os
from rest2web.embedded_code import align_multiline_code
class restindexError(SyntaxError):
""" """
# acceptable values for keywords that must be on or off
true_false_list = ['yes', 'no', 'true', 'false', 'on', 'off', '1', '0']
# keywords that are on or off
true_false_keywords = ['include', 'build']
# any keywords that take normal text values
text_keywords = [
'file-extension', 'template', 'index-file', 'section',
'link-title', 'page-title', 'crumb', 'target', 'encoding',
'output-encoding', 'template-encoding', 'file', 'initialheaderlevel'
]
# keywords in this dictionary can only have values from a list of options
limited_keywords = {
# FIXME: add sextile and textile
'format': ['html', 'rest']
}
# keywords in this dictionary have multiple values
# the entry is either the number of values expected
# or 0, meaning unspecified
# or a minus number meaning a *minimum* number
multiple_keywords = {'sectionlist': 0, 'section-title': 2,
'tags': 0, 'plugins': 0, 'section-pages': -1}
# keywords in this dictionary are descriptions
# they may also have a value assciated with them
# their entry is True or False - whether they have a value or not
# if they do, there may be multiple - and the value becomes part of the key
# (as a tuple)
description_keywords = {'section-description': 1, 'page-description': 0}
# keywords that can appear more than once
repeat_keywords = [
'section-title', 'section-description', 'file',
'section-pages', # 'nofile', 'filemask',
]
def remove_comment(inlines):
restindex = inlines[1:]
indent = 0
i = -1
while i < len(restindex):
i += 1
line = restindex.pop(0)
stripped = line.strip()
if not stripped:
continue
this_indent = len(line) - len(stripped)
if indent and this_indent < indent:
return inlines
indent = min(this_indent, indent or this_indent)
if stripped == 'restindex':
restindex.insert(0, line)
break
else:
return inlines
#
return restindex
def find_start(inlines):
while inlines:
line = inlines.pop(0)
if not line.strip():
continue
if line.strip().startswith('..') and line.find('::') == -1:
inlines.insert(0, line)
inlines = remove_comment(inlines)
break
inlines.insert(0, line)
break
return inlines
def read_restindex(infile):
"""
Interpret the restindex and divide it from the contents.
Given a file as a list of lines (or file object, or bounded iterable),
read the restindex from the start. (if any)
Returns restindex, remainder of file (which will have trailing whitespace
removed from each line).
restindex will be None if there isn't one.
If it finds any errors it raises ``restindexError`` - which is a subclass
of ``SyntaxError``
"""
# FIXME: consumes the whole file immediately
thefile = [line.rstrip() for line in infile]
thefile.append('')
#
# UTF8 BOM
if thefile[0].startswith('\xef\xbb\xbf'):
# get rid of it
thefile[0] = thefile[0][3:]
#
thefile = find_start(thefile)
#
started = False
indesc = False
thisdesc = []
restindex = {}
#
index = -1
length = len(thefile) - 1
# indexing like this is more versatile, we can manually
# wind forwards or back
while index < length:
index += 1
origline = thefile[index]
line = origline.strip()
#
if (line and
not line.startswith('#') and
not line == 'restindex' and
not line.strip() == '..' and
not started
):
return None, '\n'.join(thefile)
#
# if we are in a multiline value
if indesc:
# end of a description
if not line == '/description':
thisdesc.append(origline)
else:
# join, remove indentation, and save
value = align_multiline_code('\n'.join(thisdesc))
# FIXME: special case for 'section-description' -
# where indesc is a tuple
if isinstance(indesc, tuple):
keyword, name = indesc
if restindex.has_key(keyword):
if restindex[keyword].has_key(name):
# section description twice
raise restindexError(('"%s" repeated for "%s"'
' - line %s') % (keyword, name, index + 1))
restindex[keyword][name] = value
else:
restindex[keyword] = {name: value}
else:
restindex[indesc] = value
indesc = None
thisdesc = []
continue
#
if line.startswith('#') or not line:
# comments and empty lines are skipped
continue
#
if not started and line.strip() == '..':
continue
#
if line == 'restindex':
if started:
raise restindexError(('restindex found in the wrong place'
' - line %s') % (index + 1))
started = True
continue
#
if line == '/restindex':
# the end
body = thefile[index+1:]
return restindex, '\n'.join(body)
#
if line.find(':') == -1:
raise restindexError('No keyword on line - line %s' % (index + 1))
keyword, value = line.split(':', 1)
keyword = keyword.strip().lower()
value = value.strip()
#
if restindex.has_key(keyword) and keyword not in repeat_keywords:
raise restindexError('Keyword "%s" repeated - line %s' % (
keyword, index + 1))
#
if keyword in true_false_keywords:
# this keyword should be on or off
value = value.lower()
if value not in true_false_list:
raise restindexError('Strange value - line %s' % (index + 1))
restindex[keyword] = value
continue
#
if keyword in text_keywords:
if keyword in repeat_keywords:
try:
restindex[keyword].append(value)
except KeyError:
restindex[keyword] = [value]
else:
# this keyword takes a straight text value
restindex[keyword] = value
continue
#
if keyword in limited_keywords:
# value must be one from a list of options
value = value.lower()
if value not in limited_keywords[keyword]:
raise restindexError, 'Strange value - line %s' % (index + 1)
restindex[keyword] = value
continue
#
if keyword in multiple_keywords:
# NOTE we can have multiple section titles
numsplits = multiple_keywords[keyword]
if numsplits < 1:
if not value:
values = []
else:
values = [entry.strip() or None
for entry in value.split(',')]
if numsplits < 0:
numsplits = int(numsplits)
if len(values) < numsplits:
raise restindexError(('Multiple keyword with too '
'few values - line %s') % (index + 1))
if keyword in repeat_keywords:
# keyword is a repeat
# first value is a name
name = values[0]
values = values[1:]
if restindex.has_key(keyword):
if restindex[keyword].has_key(name):
raise restindexError(('"%s" repeated for "%s"'
' - line %s') % (keyword, name, index + 1))
restindex[keyword][name] = values
else:
restindex[keyword] = {name: values}
#
else:
restindex[keyword] = values
else:
values = [entry.strip() or None
for entry in value.split(',', numsplits-1)]
name = values[0] or None
# this allows UP TO numsplit values - XXXX *doesn't* choke
# on less; NOTE: returns a list, even though will usually
# be 0 or 1 items
value = values[1:]
if numsplits == 2:
# special case - should only have a single value
if value:
value = value[0]
else:
value = ''
if restindex.has_key(keyword):
# section description twice
if restindex[keyword].has_key(name):
raise restindexError(('"%s" repeated for "%s"'
' - line %s') % (keyword, name, index + 1))
restindex[keyword][name] = value
#
else:
restindex[keyword] = {name: value}
continue
#
if keyword in description_keywords:
if description_keywords[keyword]:
indesc = (keyword, value or None)
else:
indesc = keyword
continue
#
# if we get this far, we haven't recognised the keyword
# FIXME: show the offending line?
raise restindexError('Unrecognised keyword - line %s' % (index + 1))
# if we get this far, we reached the end of the file
# without finding '/restindex'
if not started:
return None, '\n'.join(thefile)
raise restindexError, "No '/restindex' found."
default_restindex = {
'include': 'yes',
'format': 'rest',
'file-extension': 'html',
'template': None,
'index-file': 'index.txt',
'template-encoding': None,
'section': None,
'link-title': '',
'page-title': None,
'page-description': '',
'crumb': None,
'target': None,
'build': 'yes',
'sectionlist': [],
'section-title': {},
'section-description': {},
'encoding': None,
'output-encoding': None,
'tags': [],
'section-pages': {},
'plugins': [],
'file': [],
# 'filemask': [],
# 'nofile': [],
'initialheaderlevel': '1'
}
# these keyword(s) set the default value for the whole directory
default_keywords = ['file-extension', 'initialheaderlevel']
if __name__ == '__main__':
ri = """
restindex
# this is a comment
include: yes
file: file1
file: file2
file: file3
plugins:
format: html
tags: tag1, tag2, tag3
file-extension: shtml
template: template.txt
template-encoding: utf8
index-file: index.txt
section: section name
link-title: This is the text to use in the link
page-title: We *usually* only need a title for HTML
page-description:
this is a description
It can go across several line
And even be indented a bit.
It will be interpreted as *reST*.
/description
crumb: Short Name
build: yes
target: thisfile.html
encoding: utf8
output-encoding: utf8
sectionlist: , section-name, section-name2, section-name3
section-title: section-name, title
section-description: section-name
This is also a description.
/description
section-title: , default-section-title
section-description:
This is the default-section description.
/description
section-pages: , page1, page2, page3
section-pages: section-name, page1, page2, page3
/restindex
"""
rest_index = read_restindex(ri.split('\n'))[0]
for entry in rest_index:
print entry, ' : ', rest_index[entry]
#
ri2 = """
..
restindex
# this is a comment
include: yes
file: file1
file: file2
file: file3
plugins:
format: html
tags: tag1, tag2, tag3
file-extension: shtml
template: template.txt
template-encoding: utf8
index-file: index.txt
section: section name
link-title: This is the text to use in the link
page-title: We *usually* only need a title for HTML
page-description:
this is a description
It can go across several line
And even be indented a bit.
It will be interpreted as *reST*.
/description
crumb: Short Name
build: yes
target: thisfile.html
encoding: utf8
output-encoding: utf8
sectionlist: , section-name, section-name2, section-name3
section-title: section-name, title
section-description: section-name
This is also a description.
/description
section-title: , default-section-title
section-description:
This is the default-section description.
/description
section-pages: , page1, page2, page3
section-pages: section-name, page1, page2, page3
/restindex
"""
print
print
print 'Attempting restindex in a comment:'
print
rest_index2 = read_restindex(ri2.split('\n'))[0]
for entry in rest_index2:
print entry, ' : ', rest_index[entry]
assert rest_index == rest_index2
# multiline parser
# for uservalues
import re
valid_line = re.compile(r'\s*([a-zA-Z_]\w*)\s*(?:=|:)(.*)')
# the reserved_names are all the names used in the namespace other than 'body'
reserved_names = [
'title', 'breadcrumbs', 'sections', 'pagename', 'pagepath',
'encoding', 'output_encoding', 'final_encoding', 'path_to_root',
'sectionlist', 'rest_dict', 'doc', 'stdout', 'modified', 'modtime',
'template_file', 'template_encoding', 'indexpage', 'indextree',
'thispage', 'sidebar', 'minibar', 'print_crumbs', 'Processor', 'tags',
'default_section', 'modtime', 'modtimeiso'
]
def parse_user_values(content, directory):
"""
Read the content of a page, as a list of lines (after the restindex
has been read). Parse and extracts any 'uservalues'
Return (uservalues, content) - (dict, string)
uservalues will be ``None`` if there is no uservalues section.
"""
quot = ''
user_values = {}
found_end = False
started = False
index = -1
length = len(content) - 1
while index < length:
index += 1
line = content[index]
#
if quot:
val = val + '\n'
if line.rstrip().endswith(quot):
val += line.rstrip()[:-3]
quot = False
user_values[name] = val
else:
val += line
continue
#
if line.lstrip().startswith('#') or not line.strip():
continue
elif not started and line.strip() == 'uservalues':
started = True
continue
elif not started:
return None, '\n'.join(content)
#
# XXXX if we find a '/uservalues' without a start
# XXXX should we raise an error ?
elif line.strip() ==('/uservalues'):
found_end = True
break
#
mat = valid_line.match(line)
if not mat:
raise SyntaxError, 'Invalid line in uservalues:\n "%s"' % line
name, val = mat.groups()
if name in reserved_names:
raise SyntaxError, ('Use of reserved name in uservalues:\n'
' "%s"') % line
if val.lstrip()[:3] in ['"""', "'''"]:
quot = val.lstrip()[:3]
val = val.lstrip()[3:]
if val.rstrip().endswith(quot):
quot = ''
val = val.rstrip()[:-3]
else:
continue
user_values[name] = val.strip()
#
if not started:
# only blank lines or comments
return None, '\n'.join(content)
if quot:
raise SyntaxError, 'No end to a triple quoted section.'
if not found_end:
raise SyntaxError, 'No end to "uservalues" section.'
#
content = content[index+1:]
if user_values.has_key('body'):
loc = os.path.normpath(os.path.join(directory, user_values['body']))
# XXXX os.path.join ? technically this value will be in URL form
# - not native
#
content = open(loc).readlines()
del user_values['body']
#
return user_values, '\n'.join(content)
#######################################################################
if __name__ == '__main__':
print
print '#'*30
print
#
content1 = '''
#comment
uservalues
test: 3
# a comment
test2: a value
test3 = \''' a multiline
""" value"""
\'''
test4 = """ A test """
test5 = """
A long
line.
"""
/uservalues
The content...
'''
content2 = '''
uservalues
test = """
/uservalues
'''
directory = ''
(user_values, content) = parse_user_values(
content1.split('\n'), directory)
print 'Content: ', content
for entry in user_values:
print entry, ' : ', user_values[entry]
#
try:
(user_values, content) = parse_user_values(
content2.split('\n'), directory)
except SyntaxError:
print 'Picked up the error in content2.'
else:
print '***FAIL** failed to pick up the error in content2.'
raise SyntaxError
"""
CHANGELOG
=========
2006/08/13
----------
Allow the restindex and uservalues to be in a ReST comment.
2005/10/12
----------
Added the 'section-pages' keyword. Only valid for indexes.
2005/07/26
Added 'file' and 'plugins' keywords
Added 'tags' to reserved name
An empty multiple value now returns '[]' rather than '[None]'
2005/07/23
Added the tags keyword.
2005/06/18
Changes by Nicola Larosa
Code cleanup
lines shortened
comments on line above code
empty comments in empty lines
2005/06/12
Added the parser for "uservalues"
2005/05/20
Added the 'template-encoding' keyword.
Allowed for default section in sectionlist.
2005/05/16
restindex['section-title'] is now a dictionary of single values, rather than a
dictionary of lists !
2005/05/15
``read_restindex`` removes UTF8 BOM at start of files
Added ``output-encoding`` keyword.
If no name is given with a section-description, then we use ``None`` (the default section)
A ``section-title`` with no name (``section-title: , Title Line``) is a title for the default section.
Added test.
"""
|