1 # This file is part of lyx2lyx
2 # -*- coding: utf-8 -*-
3 # Copyright (C) 2002-2004 Dekel Tsur <dekel@lyx.org>
4 # Copyright (C) 2002-2006 José Matos <jamatos@lyx.org>
6 # This program is free software; you can redistribute it and/or
7 # modify it under the terms of the GNU General Public License
8 # as published by the Free Software Foundation; either version 2
9 # of the License, or (at your option) any later version.
11 # This program is distributed in the hope that it will be useful,
12 # but WITHOUT ANY WARRANTY; without even the implied warranty of
13 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 # GNU General Public License for more details.
16 # You should have received a copy of the GNU General Public License
17 # along with this program; if not, write to the Free Software
18 # Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
20 from parser_tools import get_value, check_token, find_token,\
21 find_tokens, find_end_of
30 import lyx2lyx_version
31 version_lyx2lyx = lyx2lyx_version.version
32 except: # we are running from build directory so assume the last version
33 version_lyx2lyx = '1.6.0svn'
35 default_debug_level = 2
37 ####################################################################
38 # Private helper functions
40 def find_end_of_inset(lines, i):
41 " Find beginning of inset, where lines[i] is included."
42 return find_end_of(lines, i, "\\begin_inset", "\\end_inset")
44 def generate_minor_versions(major, last_minor_version):
45 """ Generate minor versions, using major as prefix and minor
46 versions from 0 until last_minor_version, plus the generic version.
50 generate_minor_versions("1.2", 4) ->
51 [ "1.2", "1.2.0", "1.2.1", "1.2.2", "1.2.3"]
53 return [major] + [major + ".%d" % i for i in range(last_minor_version + 1)]
56 # End of helper functions
57 ####################################################################
60 # Regular expressions used
61 format_re = re.compile(r"(\d)[\.,]?(\d\d)")
62 fileformat = re.compile(r"\\lyxformat\s*(\S*)")
63 original_version = re.compile(r".*?LyX ([\d.]*)")
66 # file format information:
67 # file, supported formats, stable release versions
68 format_relation = [("0_06", [200], generate_minor_versions("0.6" , 4)),
69 ("0_08", [210], generate_minor_versions("0.8" , 6) + ["0.7"]),
70 ("0_10", [210], generate_minor_versions("0.10", 7) + ["0.9"]),
71 ("0_12", [215], generate_minor_versions("0.12", 1) + ["0.11"]),
72 ("1_0", [215], generate_minor_versions("1.0" , 4)),
73 ("1_1", [215], generate_minor_versions("1.1" , 4)),
74 ("1_1_5", [216], ["1.1.5","1.1.5.1","1.1.5.2","1.1"]),
75 ("1_1_6_0", [217], ["1.1.6","1.1.6.1","1.1.6.2","1.1"]),
76 ("1_1_6_3", [218], ["1.1.6.3","1.1.6.4","1.1"]),
77 ("1_2", [220], generate_minor_versions("1.2" , 4)),
78 ("1_3", [221], generate_minor_versions("1.3" , 7)),
79 ("1_4", range(222,246), generate_minor_versions("1.4" , 5)),
80 ("1_5", range(246,277), generate_minor_versions("1.5" , 1)),
81 ("1_6", range(277,286), generate_minor_versions("1.6" , 0))]
85 " Returns a list with supported file formats."
87 for version in format_relation:
88 for format in version[1]:
89 if format not in formats:
90 formats.append(format)
95 " Returns the more recent file format available."
96 return format_relation[-1][1][-1]
99 def get_backend(textclass):
100 " For _textclass_ returns its backend."
101 if textclass == "linuxdoc" or textclass == "manpage":
103 if textclass[:7] == "docbook":
109 " Remove end of line char(s)."
110 if line[-2:-1] == '\r':
116 def get_encoding(language, inputencoding, format, cjk_encoding):
119 # CJK-LyX encodes files using the current locale encoding.
120 # This means that files created by CJK-LyX can only be converted using
121 # the correct locale settings unless the encoding is given as commandline
123 if cjk_encoding == 'auto':
124 return locale.getpreferredencoding()
125 elif cjk_encoding != '':
127 from lyx2lyx_lang import lang
128 if inputencoding == "auto" or inputencoding == "default":
129 return lang[language][3]
130 if inputencoding == "":
132 # python does not know the alias latin9
133 if inputencoding == "latin9":
141 """This class carries all the information of the LyX file."""
143 def __init__(self, end_format = 0, input = "", output = "", error
144 = "", debug = default_debug_level, try_hard = 0, cjk_encoding = '',
145 language = "english", encoding = "auto"):
148 end_format: final format that the file should be converted. (integer)
149 input: the name of the input source, if empty resort to standard input.
150 output: the name of the output file, if empty use the standard output.
151 error: the name of the error file, if empty use the standard error.
152 debug: debug level, O means no debug, as its value increases be more verbose.
154 self.choose_io(input, output)
157 self.err = open(error, "w")
159 self.err = sys.stderr
162 self.try_hard = try_hard
163 self.cjk_encoding = cjk_encoding
166 self.end_format = self.lyxformat(end_format)
168 self.end_format = get_end_format()
170 self.backend = "latex"
171 self.textclass = "article"
172 # This is a hack: We use '' since we don't know the default
173 # layout of the text class. LyX will parse it as default layout.
174 # FIXME: Read the layout file and use the real default layout
175 self.default_layout = ''
181 self.encoding = encoding
182 self.language = language
185 def warning(self, message, debug_level= default_debug_level):
186 " Emits warning to self.error, if the debug_level is less than the self.debug."
187 if debug_level <= self.debug:
188 self.err.write("Warning: " + message + "\n")
191 def error(self, message):
192 " Emits a warning and exits if not in try_hard mode."
193 self.warning(message)
194 if not self.try_hard:
195 self.warning("Quiting.")
202 """Reads a file into the self.header, self.manifest and self.body parts, from self.input."""
205 line = self.input.readline()
207 self.error("Invalid LyX file.")
209 line = trim_eol(line)
210 if check_token(line, '\\begin_preamble'):
212 line = self.input.readline()
214 self.error("Invalid LyX file.")
216 line = trim_eol(line)
217 if check_token(line, '\\end_preamble'):
220 if line.split()[:0] in ("\\layout", "\\begin_layout", "\\begin_body"):
221 self.warning("Malformed LyX file: Missing '\\end_preamble'.")
222 self.warning("Adding it now and hoping for the best.")
224 self.preamble.append(line)
226 if check_token(line, '\\end_preamble'):
229 if check_token(line, '\\begin_manifest'):
231 line = self.input.readline()
233 self.error("Invalid LyX file.")
235 line = trim_eol(line)
236 if check_token(line, "\\end_manifest"):
239 if not line.startswith('\\filename') and not line.startswith('\\inzipName') \
240 and not line.startswith('\\embed'):
241 self.warning("Malformed LyX file: Missing '\\end_manifest'.")
243 self.manifest.append(line)
245 if check_token(line, '\\end_manifest'):
252 if line.split()[0] in ("\\layout", "\\begin_layout", "\\begin_body", "\\begin_deeper"):
253 self.body.append(line)
256 self.header.append(line)
258 self.textclass = get_value(self.header, "\\textclass", 0)
259 self.backend = get_backend(self.textclass)
260 self.format = self.read_format()
261 self.language = get_value(self.header, "\\language", 0, default = "english")
262 self.inputencoding = get_value(self.header, "\\inputencoding", 0, default = "auto")
263 self.encoding = get_encoding(self.language, self.inputencoding, self.format, self.cjk_encoding)
264 self.initial_version = self.read_version()
266 # Second pass over header and preamble, now we know the file encoding
267 for i in range(len(self.header)):
268 self.header[i] = self.header[i].decode(self.encoding)
269 for i in range(len(self.preamble)):
270 self.preamble[i] = self.preamble[i].decode(self.encoding)
274 line = self.input.readline().decode(self.encoding)
277 self.body.append(trim_eol(line))
281 " Writes the LyX file to self.output."
285 if self.encoding == "auto":
286 self.encoding = get_encoding(self.language, self.encoding, self.format, self.cjk_encoding)
289 i = find_token(self.header, '\\textclass', 0) + 1
290 preamble = ['\\begin_preamble'] + self.preamble + ['\\end_preamble']
292 self.error("Malformed LyX file: Missing '\\textclass'.")
294 header = self.header[:i] + preamble + self.header[i:]
298 # LyX file format <= 284 does not have a manifest section
299 # so this section is set to None
300 if self.manifest is None:
303 manifest = ['\\begin_manifest'] + self.manifest + ['\\end_manifest', '']
305 for line in header + [''] + manifest + self.body:
306 self.output.write(line.encode(self.encoding)+"\n")
309 def choose_io(self, input, output):
310 """Choose input and output streams, dealing transparently with
314 self.output = open(output, "wb")
316 self.output = sys.stdout
318 if input and input != '-':
319 self.dir = os.path.dirname(os.path.abspath(input))
321 gzip.open(input).readline()
322 self.input = gzip.open(input)
323 self.output = gzip.GzipFile(mode="wb", fileobj=self.output)
325 self.input = open(input)
328 self.input = sys.stdin
331 def lyxformat(self, format):
332 " Returns the file format representation, an integer."
333 result = format_re.match(format)
335 format = int(result.group(1) + result.group(2))
339 self.error(str(format) + ": " + "Invalid LyX file.")
341 if format in formats_list():
344 self.error(str(format) + ": " + "Format not supported.")
348 def read_version(self):
349 """ Searchs for clues of the LyX version used to write the file, returns the
350 most likely value, or None otherwise."""
351 for line in self.header:
355 line = line.replace("fix",".")
356 result = original_version.match(line)
358 # Special know cases: reLyX and KLyX
359 if line.find("reLyX") != -1 or line.find("KLyX") != -1:
362 res = result.group(1)
365 #self.warning("Version %s" % result.group(1))
367 self.warning(str(self.header[:2]))
371 def set_version(self):
372 " Set the header with the version used."
373 self.header[0] = "#LyX %s created this file. For more info see http://www.lyx.org/" % version_lyx2lyx
374 if self.header[1][0] == '#':
378 def read_format(self):
379 " Read from the header the fileformat of the present LyX file."
380 for line in self.header:
381 result = fileformat.match(line)
383 return self.lyxformat(result.group(1))
385 self.error("Invalid LyX File.")
389 def set_format(self):
390 " Set the file format of the file, in the header."
391 if self.format <= 217:
392 format = str(float(self.format)/100)
394 format = str(self.format)
395 i = find_token(self.header, "\\lyxformat", 0)
396 self.header[i] = "\\lyxformat %s" % format
399 def set_textclass(self):
400 i = find_token(self.header, "\\textclass", 0)
401 self.header[i] = "\\textclass %s" % self.textclass
404 def set_parameter(self, param, value):
405 " Set the value of the header parameter."
406 i = find_token(self.header, '\\' + param, 0)
408 self.warning('Parameter not found in the header: %s' % param, 3)
410 self.header[i] = '\\%s %s' % (param, str(value))
413 def is_default_layout(self, layout):
414 " Check whether a layout is the default layout of this class."
415 # FIXME: Check against the real text class default layout
416 if layout == 'Standard' or layout == self.default_layout:
422 "Convert from current (self.format) to self.end_format."
423 mode, convertion_chain = self.chain()
424 self.warning("convertion chain: " + str(convertion_chain), 3)
426 for step in convertion_chain:
427 steps = getattr(__import__("lyx_" + step), mode)
429 self.warning("Convertion step: %s - %s" % (step, mode), default_debug_level + 1)
431 self.error("The convertion to an older format (%s) is not implemented." % self.format)
433 multi_conv = len(steps) != 1
434 for version, table in steps:
436 (self.format >= version and mode == "convert") or\
437 (self.format <= version and mode == "revert"):
445 self.warning("An error ocurred in %s, %s" % (version, str(conv)),
447 if not self.try_hard:
451 self.warning("%lf: Elapsed time on %s" % (time.time() - init_t, str(conv)),
452 default_debug_level + 1)
454 self.format = version
455 if self.end_format == self.format:
460 """ This is where all the decisions related with the convertion are taken.
461 It returns a list of modules needed to convert the LyX file from
462 self.format to self.end_format"""
464 self.start = self.format
468 for rel in format_relation:
469 if self.initial_version in rel[2]:
471 initial_step = rel[0]
475 if not correct_version:
477 self.warning("Version does not match file format, discarding it. (Version %s, format %d)" %(self.initial_version, self.format))
478 for rel in format_relation:
480 initial_step = rel[0]
483 # This should not happen, really.
484 self.error("Format not supported.")
486 # Find the final step
487 for rel in format_relation:
488 if self.end_format in rel[1]:
492 self.error("Format not supported.")
494 # Convertion mode, back or forth
496 if (initial_step, self.start) < (final_step, self.end_format):
499 for step in format_relation:
500 if initial_step <= step[0] <= final_step:
501 if first_step and len(step[1]) == 1:
504 steps.append(step[0])
507 relation_format = format_relation[:]
508 relation_format.reverse()
511 for step in relation_format:
512 if final_step <= step[0] <= initial_step:
513 steps.append(step[0])
516 if last_step[1][-1] == self.end_format:
519 self.warning("Convertion mode: %s\tsteps%s" %(mode, steps), 10)
523 def get_toc(self, depth = 4):
524 " Returns the TOC of this LyX document."
525 paragraphs_filter = {'Title' : 0,'Chapter' : 1, 'Section' : 2, 'Subsection' : 3, 'Subsubsection': 4}
526 allowed_insets = ['Quotes']
527 allowed_parameters = '\\paragraph_spacing', '\\noindent', '\\align', '\\labelwidthstring', "\\start_of_appendix", "\\leftindent"
530 for section in paragraphs_filter.keys():
531 sections.append('\\begin_layout %s' % section)
536 i = find_tokens(self.body, sections, i)
540 j = find_end_of(self.body, i + 1, '\\begin_layout', '\\end_layout')
542 self.warning('Incomplete file.', 0)
545 section = self.body[i].split()[1]
546 if section[-1] == '*':
547 section = section[:-1]
552 # skip paragraph parameters
553 while not self.body[k].strip() or self.body[k].split()[0] in allowed_parameters:
557 if check_token(self.body[k], '\\begin_inset'):
558 inset = self.body[k].split()[1]
559 end = find_end_of_inset(self.body, k)
560 if end == -1 or end > j:
561 self.warning('Malformed file.', 0)
563 if inset in allowed_insets:
564 par.extend(self.body[k: end+1])
567 par.append(self.body[k])
570 # trim empty lines in the end.
571 while par and par[-1].strip() == '':
574 toc_par.append(Paragraph(section, par))
581 class File(LyX_Base):
582 " This class reads existing LyX files."
583 def __init__(self, end_format = 0, input = "", output = "", error = "", debug = default_debug_level, try_hard = 0, cjk_encoding = ''):
584 LyX_Base.__init__(self, end_format, input, output, error, debug, try_hard, cjk_encoding)
588 class NewFile(LyX_Base):
589 " This class is to create new LyX files."
590 def set_header(self, **params):
593 "#LyX xxxx created this file. For more info see http://www.lyx.org/",
597 "\\textclass article",
598 "\\language english",
599 "\\inputencoding auto",
600 "\\font_roman default",
601 "\\font_sans default",
602 "\\font_typewriter default",
603 "\\font_default_family default",
606 "\\font_sf_scale 100",
607 "\\font_tt_scale 100",
608 "\\graphics default",
609 "\\paperfontsize default",
610 "\\papersize default",
611 "\\use_geometry false",
613 "\\cite_engine basic",
614 "\\use_bibtopic false",
615 "\\paperorientation portrait",
618 "\\paragraph_separation indent",
620 "\\quotes_language english",
623 "\\paperpagestyle default",
624 "\\tracking_changes false",
627 self.format = get_end_format()
629 self.set_parameter(param, params[param])
632 def set_body(self, paragraphs):
633 self.body.extend(['\\begin_body',''])
635 for par in paragraphs:
636 self.body.extend(par.asLines())
638 self.body.extend(['','\\end_body', '\\end_document'])
642 # unfinished implementation, it is missing the Text and Insets representation.
643 " This class represents the LyX paragraphs."
644 def __init__(self, name, body=[], settings = [], child = []):
646 name: paragraph name.
647 body: list of lines of body text.
648 child: list of paragraphs that descend from this paragraph.
652 self.settings = settings
656 " Converts the paragraph to a list of strings, representing it in the LyX file."
657 result = ['','\\begin_layout %s' % self.name]
658 result.extend(self.settings)
660 result.extend(self.body)
661 result.append('\\end_layout')
666 result.append('\\begin_deeper')
667 for node in self.child:
668 result.extend(node.asLines())
669 result.append('\\end_deeper')
675 " This class represents the LyX insets."
680 " This class represents simple chuncks of text."