1 # This file is part of lyx2lyx
2 # -*- coding: utf-8 -*-
3 # Copyright (C) 2002-2004 Dekel Tsur <dekel@lyx.org>, José Matos <jamatos@lyx.org>
5 # This program is free software; you can redistribute it and/or
6 # modify it under the terms of the GNU General Public License
7 # as published by the Free Software Foundation; either version 2
8 # of the License, or (at your option) any later version.
10 # This program is distributed in the hope that it will be useful,
11 # but WITHOUT ANY WARRANTY; without even the implied warranty of
12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 # GNU General Public License for more details.
15 # You should have received a copy of the GNU General Public License
16 # along with this program; if not, write to the Free Software
17 # Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
19 from parser_tools import get_value, check_token, find_token,\
20 find_tokens, find_end_of
28 import lyx2lyx_version
29 version_lyx2lyx = lyx2lyx_version.version
31 default_debug_level = 2
33 ####################################################################
34 # Private helper functions
36 def find_end_of_inset(lines, i):
37 " Find beginning of inset, where lines[i] is included."
38 return find_end_of(lines, i, "\\begin_inset", "\\end_inset")
40 # End of helper functions
41 ####################################################################
44 # Regular expressions used
45 format_re = re.compile(r"(\d)[\.,]?(\d\d)")
46 fileformat = re.compile(r"\\lyxformat\s*(\S*)")
47 original_version = re.compile(r"\#LyX (\S*)")
50 # file format information:
51 # file, supported formats, stable release versions
52 format_relation = [("0_08", [210], ["0.8.%d" % i for i in range(7)] + ["0.8"]),
53 ("0_10", [210], ["0.10.%d" % i for i in range(8)] + ["0.10"]),
54 ("0_12", [215], ["0.12.0","0.12.1","0.12"]),
55 ("1_0_0", [215], ["1.0.0","1.0"]),
56 ("1_0_1", [215], ["1.0.1","1.0.2","1.0.3","1.0.4", "1.1.2","1.1"]),
57 ("1_1_4", [215], ["1.1.4","1.1"]),
58 ("1_1_5", [216], ["1.1.5","1.1.5fix1","1.1.5fix2","1.1"]),
59 ("1_1_6_0", [217], ["1.1.6","1.1.6fix1","1.1.6fix2","1.1"]),
60 ("1_1_6_3", [218], ["1.1.6fix3","1.1.6fix4","1.1"]),
61 ("1_2", [220], ["1.2.%d" % i for i in range(5)] + ["1.2"]),
62 ("1_3", [221], ["1.3.%d" % i for i in range(8)] + ["1.3"]),
63 ("1_4", range(222,246), ["1.4.0", "1.4.1", "1.4.2","1.4.3svn"]),
64 ("1_5", range(246,249), ["1.5.0svn","1.5"])]
68 " Returns a list with supported file formats."
70 for version in format_relation:
71 for format in version[1]:
72 if format not in formats:
73 formats.append(format)
78 " Returns the more recent file format available."
79 return format_relation[-1][1][-1]
82 def get_backend(textclass):
83 " For _textclass_ returns its backend."
84 if textclass == "linuxdoc" or textclass == "manpage":
86 if textclass[:7] == "docbook":
92 " Remove end of line char(s)."
93 if line[-2:-1] == '\r':
103 """This class carries all the information of the LyX file."""
104 def __init__(self, end_format = 0, input = "", output = "", error = "", debug = default_debug_level, try_hard = 0):
106 end_format: final format that the file should be converted. (integer)
107 input: the name of the input source, if empty resort to standard input.
108 output: the name of the output file, if empty use the standard output.
109 error: the name of the error file, if empty use the standard error.
110 debug: debug level, O means no debug, as its value increases be more verbose.
112 self.choose_io(input, output)
115 self.err = open(error, "w")
117 self.err = sys.stderr
120 self.try_hard = try_hard
123 self.end_format = self.lyxformat(end_format)
125 self.end_format = get_end_format()
127 self.backend = "latex"
128 self.textclass = "article"
129 # This is a hack: We use '' since we don't know the default
130 # layout of the text class. LyX will parse it as default layout.
131 # FIXME: Read the layout file and use the real default layout
132 self.default_layout = ''
139 def warning(self, message, debug_level= default_debug_level):
140 " Emits warning to self.error, if the debug_level is less than the self.debug."
141 if debug_level <= self.debug:
142 self.err.write("Warning: " + message + "\n")
145 def error(self, message):
146 " Emits a warning and exits if not in try_hard mode."
147 self.warning(message)
148 if not self.try_hard:
149 self.warning("Quiting.")
156 """Reads a file into the self.header and self.body parts, from self.input."""
159 line = self.input.readline()
161 self.error("Invalid LyX file.")
163 line = trim_eol(line)
164 if check_token(line, '\\begin_preamble'):
166 line = self.input.readline()
168 self.error("Invalid LyX file.")
170 line = trim_eol(line)
171 if check_token(line, '\\end_preamble'):
174 if string.split(line)[:0] in ("\\layout", "\\begin_layout", "\\begin_body"):
175 self.warning("Malformed LyX file: Missing '\\end_preamble'.")
176 self.warning("Adding it now and hoping for the best.")
178 self.preamble.append(line)
180 if check_token(line, '\\end_preamble'):
183 line = string.strip(line)
187 if string.split(line)[0] in ("\\layout", "\\begin_layout", "\\begin_body"):
188 self.body.append(line)
191 self.header.append(line)
194 line = self.input.readline()
197 self.body.append(trim_eol(line))
199 self.textclass = get_value(self.header, "\\textclass", 0)
200 self.backend = get_backend(self.textclass)
201 self.format = self.read_format()
202 self.language = get_value(self.header, "\\language", 0)
203 if self.language == "":
204 self.language = "english"
205 self.initial_version = self.read_version()
209 " Writes the LyX file to self.output."
214 i = find_token(self.header, '\\textclass', 0) + 1
215 preamble = ['\\begin_preamble'] + self.preamble + ['\\end_preamble']
217 self.error("Malformed LyX file: Missing '\\textclass'.")
219 header = self.header[:i] + preamble + self.header[i:]
223 for line in header + [''] + self.body:
224 self.output.write(line+"\n")
227 def choose_io(self, input, output):
228 """Choose input and output streams, dealing transparently with
232 self.output = open(output, "wb")
234 self.output = sys.stdout
236 if input and input != '-':
237 self.dir = os.path.dirname(os.path.abspath(input))
239 gzip.open(input).readline()
240 self.input = gzip.open(input)
241 self.output = gzip.GzipFile(mode="wb", fileobj=self.output)
243 self.input = open(input)
246 self.input = sys.stdin
249 def lyxformat(self, format):
250 " Returns the file format representation, an integer."
251 result = format_re.match(format)
253 format = int(result.group(1) + result.group(2))
255 self.error(str(format) + ": " + "Invalid LyX file.")
257 if format in formats_list():
260 self.error(str(format) + ": " + "Format not supported.")
264 def read_version(self):
265 """ Searchs for clues of the LyX version used to write the file, returns the
266 most likely value, or None otherwise."""
267 for line in self.header:
271 result = original_version.match(line)
273 return result.group(1)
277 def set_version(self):
278 " Set the header with the version used."
279 self.header[0] = "#LyX %s created this file. For more info see http://www.lyx.org/" % version_lyx2lyx
280 if self.header[1][0] == '#':
284 def read_format(self):
285 " Read from the header the fileformat of the present LyX file."
286 for line in self.header:
287 result = fileformat.match(line)
289 return self.lyxformat(result.group(1))
291 self.error("Invalid LyX File.")
295 def set_format(self):
296 " Set the file format of the file, in the header."
297 if self.format <= 217:
298 format = str(float(self.format)/100)
300 format = str(self.format)
301 i = find_token(self.header, "\\lyxformat", 0)
302 self.header[i] = "\\lyxformat %s" % format
305 def set_parameter(self, param, value):
306 " Set the value of the header parameter."
307 i = find_token(self.header, '\\' + param, 0)
309 self.warning('Parameter not found in the header: %s' % param, 3)
311 self.header[i] = '\\%s %s' % (param, str(value))
314 def is_default_layout(self, layout):
315 " Check whether a layout is the default layout of this class."
316 # FIXME: Check against the real text class default layout
317 if layout == 'Standard' or layout == self.default_layout:
323 "Convert from current (self.format) to self.end_format."
324 mode, convertion_chain = self.chain()
325 self.warning("convertion chain: " + str(convertion_chain), 3)
327 for step in convertion_chain:
328 steps = getattr(__import__("lyx_" + step), mode)
330 self.warning("Convertion step: %s - %s" % (step, mode), default_debug_level + 1)
332 self.error("The convertion to an older format (%s) is not implemented." % self.format)
334 multi_conv = len(steps) != 1
335 for version, table in steps:
337 (self.format >= version and mode == "convert") or\
338 (self.format <= version and mode == "revert"):
346 self.warning("An error ocurred in %s, %s" % (version, str(conv)),
348 if not self.try_hard:
352 self.warning("%lf: Elapsed time on %s" % (time.time() - init_t, str(conv)),
353 default_debug_level + 1)
355 self.format = version
356 if self.end_format == self.format:
361 """ This is where all the decisions related with the convertion are taken.
362 It returns a list of modules needed to convert the LyX file from
363 self.format to self.end_format"""
365 self.start = self.format
369 for rel in format_relation:
370 if self.initial_version in rel[2]:
372 initial_step = rel[0]
376 if not correct_version:
378 self.warning("Version does not match file format, discarding it.")
379 for rel in format_relation:
381 initial_step = rel[0]
384 # This should not happen, really.
385 self.error("Format not supported.")
387 # Find the final step
388 for rel in format_relation:
389 if self.end_format in rel[1]:
393 self.error("Format not supported.")
395 # Convertion mode, back or forth
397 if (initial_step, self.start) < (final_step, self.end_format):
400 for step in format_relation:
401 if initial_step <= step[0] <= final_step:
402 if first_step and len(step[1]) == 1:
405 steps.append(step[0])
408 relation_format = format_relation[:]
409 relation_format.reverse()
412 for step in relation_format:
413 if final_step <= step[0] <= initial_step:
414 steps.append(step[0])
417 if last_step[1][-1] == self.end_format:
423 def get_toc(self, depth = 4):
424 " Returns the TOC of this LyX document."
425 paragraphs_filter = {'Title' : 0,'Chapter' : 1, 'Section' : 2, 'Subsection' : 3, 'Subsubsection': 4}
426 allowed_insets = ['Quotes']
427 allowed_parameters = '\\paragraph_spacing', '\\noindent', '\\align', '\\labelwidthstring', "\\start_of_appendix", "\\leftindent"
430 for section in paragraphs_filter.keys():
431 sections.append('\\begin_layout %s' % section)
436 i = find_tokens(self.body, sections, i)
440 j = find_end_of(self.body, i + 1, '\\begin_layout', '\\end_layout')
442 self.warning('Incomplete file.', 0)
445 section = string.split(self.body[i])[1]
446 if section[-1] == '*':
447 section = section[:-1]
452 # skip paragraph parameters
453 while not string.strip(self.body[k]) or string.split(self.body[k])[0] in allowed_parameters:
457 if check_token(self.body[k], '\\begin_inset'):
458 inset = string.split(self.body[k])[1]
459 end = find_end_of_inset(self.body, k)
460 if end == -1 or end > j:
461 self.warning('Malformed file.', 0)
463 if inset in allowed_insets:
464 par.extend(self.body[k: end+1])
467 par.append(self.body[k])
470 # trim empty lines in the end.
471 while string.strip(par[-1]) == '' and par:
474 toc_par.append(Paragraph(section, par))
481 class File(LyX_Base):
482 " This class reads existing LyX files."
483 def __init__(self, end_format = 0, input = "", output = "", error = "", debug = default_debug_level, try_hard = 0):
484 LyX_Base.__init__(self, end_format, input, output, error, debug, try_hard)
488 class NewFile(LyX_Base):
489 " This class is to create new LyX files."
490 def set_header(self, **params):
493 "#LyX xxxx created this file. For more info see http://www.lyx.org/",
497 "\\textclass article",
498 "\\language english",
499 "\\inputencoding auto",
500 "\\font_roman default",
501 "\\font_sans default",
502 "\\font_typewriter default",
503 "\\font_default_family default",
506 "\\font_sf_scale 100",
507 "\\font_tt_scale 100",
508 "\\graphics default",
509 "\\paperfontsize default",
510 "\\papersize default",
511 "\\use_geometry false",
513 "\\cite_engine basic",
514 "\\use_bibtopic false",
515 "\\paperorientation portrait",
518 "\\paragraph_separation indent",
520 "\\quotes_language english",
523 "\\paperpagestyle default",
524 "\\tracking_changes false",
527 self.format = get_end_format()
529 self.set_parameter(param, params[param])
532 def set_body(self, paragraphs):
533 self.body.extend(['\\begin_body',''])
535 for par in paragraphs:
536 self.body.extend(par.asLines())
538 self.body.extend(['','\\end_body', '\\end_document'])
542 # unfinished implementation, it is missing the Text and Insets representation.
543 " This class represents the LyX paragraphs."
544 def __init__(self, name, body=[], settings = [], child = []):
546 name: paragraph name.
547 body: list of lines of body text.
548 child: list of paragraphs that descend from this paragraph.
552 self.settings = settings
556 " Converts the paragraph to a list of strings, representing it in the LyX file."
557 result = ['','\\begin_layout %s' % self.name]
558 result.extend(self.settings)
560 result.extend(self.body)
561 result.append('\\end_layout')
566 result.append('\\begin_deeper')
567 for node in self.child:
568 result.extend(node.asLines())
569 result.append('\\end_deeper')
575 " This class represents the LyX insets."
580 " This class represents simple chuncks of text."