# This file is part of lyx2lyx
# -*- coding: utf-8 -*-
+# Copyright (C) 2002-2015 The LyX Team
# Copyright (C) 2002-2004 Dekel Tsur <dekel@lyx.org>
# Copyright (C) 2002-2006 José Matos <jamatos@lyx.org>
#
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
" The LyX module has all the rules related with different lyx file formats."
import sys
import re
import time
+import io
+import codecs
try:
import lyx2lyx_version
version__ = lyx2lyx_version.version
except: # we are running from build directory so assume the last version
- version__ = '2.0.0svn'
+ version__ = '2.3'
default_debug__ = 2
+# Provide support for both python 2 and 3
+PY2 = sys.version_info[0] == 2
+# End of code to support for both python 2 and 3
+
####################################################################
# Private helper functions
format_re = re.compile(r"(\d)[\.,]?(\d\d)")
fileformat = re.compile(r"\\lyxformat\s*(\S*)")
original_version = re.compile(r".*?LyX ([\d.]*)")
+original_tex2lyx_version = re.compile(r".*?tex2lyx ([\d.]*)")
##
# file format information:
("1_1_6_3", [218], ["1.1", "1.1.6.3","1.1.6.4"]),
("1_2", [220], minor_versions("1.2" , 4)),
("1_3", [221], minor_versions("1.3" , 7)),
- ("1_4", range(222,246), minor_versions("1.4" , 5)),
- ("1_5", range(246,277), minor_versions("1.5" , 7)),
- ("1_6", range(277,346), minor_versions("1.6" , 0)),
- ("2_0", [], minor_versions("2.0", 0))]
+ # Note that range(i,j) is up to j *excluded*.
+ ("1_4", list(range(222,246)), minor_versions("1.4" , 5)),
+ ("1_5", list(range(246,277)), minor_versions("1.5" , 7)),
+ ("1_6", list(range(277,346)), minor_versions("1.6" , 10)),
+ ("2_0", list(range(346,414)), minor_versions("2.0" , 8)),
+ ("2_1", list(range(414,475)), minor_versions("2.1" , 5)),
+ ("2_2", list(range(475,509)), minor_versions("2.2" , 0)),
+ ("2_3", (), minor_versions("2.3" , 0))
+ ]
####################################################################
# This is useful just for development versions #
def get_end_format():
" Returns the more recent file format available."
- return format_relation[-1][1][-1]
+ # this check will fail only when we have a new version
+ # and there is no format change yet.
+ if format_relation[-1][1]:
+ return format_relation[-1][1][-1]
+ return format_relation[-2][1][-1]
def get_backend(textclass):
def trim_eol(line):
" Remove end of line char(s)."
+ if line[-1] != '\n' and line[-1] != '\r':
+ # May happen for the last line of a document
+ return line
if line[-2:-1] == '\r':
return line[:-2]
else:
return line[:-1]
+def trim_eol_binary(line):
+ " Remove end of line char(s)."
+ if line[-1] != 10 and line[-1] != 13:
+ # May happen for the last line of a document
+ return line
+ if line[-2:-1] == 13:
+ return line[:-2]
+ else:
+ return line[:-1]
+
+
def get_encoding(language, inputencoding, format, cjk_encoding):
" Returns enconding of the lyx file"
if format > 248:
class LyX_base:
"""This class carries all the information of the LyX file."""
- def __init__(self, end_format = 0, input = "", output = "", error = "",
- debug = default_debug__, try_hard = 0, cjk_encoding = '',
- final_version = "", language = "english", encoding = "auto"):
+ def __init__(self, end_format = 0, input = u'', output = u'', error = u'',
+ debug = default_debug__, try_hard = 0, cjk_encoding = u'',
+ final_version = u'', systemlyxdir = u'', language = u'english',
+ encoding = u'auto'):
"""Arguments:
end_format: final format that the file should be converted. (integer)
error: the name of the error file, if empty use the standard error.
debug: debug level, O means no debug, as its value increases be more verbose.
"""
- self.choose_io(input, output)
+ self.choose_input(input)
+ self.output = output
if error:
self.err = open(error, "w")
self.status = 0
self.encoding = encoding
self.language = language
+ self.systemlyxdir = systemlyxdir
def warning(self, message, debug_level= default_debug__):
"""Reads a file into the self.header and
self.body parts, from self.input."""
+ # First pass: Read header to determine file encoding
+ # If we are running under python3 then all strings are binary in this
+ # pass. In some cases we need to convert binary to unicode in order to
+ # use our parser tools. Since we do not know the true encoding yet we
+ # use latin1. This works since a) the parts we are interested in are
+ # pure ASCII (subset of latin1) and b) in contrast to pure ascii or
+ # utf8, one can decode any 8byte string using latin1.
+ first_line = True
while True:
line = self.input.readline()
if not line:
- self.error("Invalid LyX file.")
+ # eof found before end of header
+ self.error("Invalid LyX file: Missing body.")
+
+ if first_line:
+ # Remove UTF8 BOM marker if present
+ if line.startswith(codecs.BOM_UTF8):
+ line = line[len(codecs.BOM_UTF8):]
+
+ first_line = False
- line = trim_eol(line)
- if check_token(line, '\\begin_preamble'):
- while 1:
+ if PY2:
+ line = trim_eol(line)
+ decoded = line
+ else:
+ line = trim_eol_binary(line)
+ decoded = line.decode('latin1')
+ if check_token(decoded, '\\begin_preamble'):
+ while True:
line = self.input.readline()
if not line:
- self.error("Invalid LyX file.")
+ # eof found before end of header
+ self.error("Invalid LyX file: Missing body.")
- line = trim_eol(line)
- if check_token(line, '\\end_preamble'):
+ if PY2:
+ line = trim_eol(line)
+ decoded = line
+ else:
+ line = trim_eol_binary(line)
+ decoded = line.decode('latin1')
+ if check_token(decoded, '\\end_preamble'):
break
- if line.split()[:0] in ("\\layout",
+ if decoded.split()[:0] in ("\\layout",
"\\begin_layout", "\\begin_body"):
self.warning("Malformed LyX file:"
self.preamble.append(line)
- if check_token(line, '\\end_preamble'):
+ if check_token(decoded, '\\end_preamble'):
continue
- line = line.strip()
+ line = line.rstrip()
if not line:
continue
- if line.split()[0] in ("\\layout", "\\begin_layout",
+ if decoded.split()[0] in ("\\layout", "\\begin_layout",
"\\begin_body", "\\begin_deeper"):
self.body.append(line)
break
self.header.append(line)
- i = find_token(self.header, '\\textclass', 0)
+ if PY2:
+ i = find_token(self.header, '\\textclass', 0)
+ else:
+ i = find_token(self.header, b'\\textclass', 0)
if i == -1:
self.warning("Malformed LyX file: Missing '\\textclass'.")
- i = find_token(self.header, '\\lyxformat', 0) + 1
- self.header[i:i] = ['\\textclass article']
-
- self.textclass = get_value(self.header, "\\textclass", 0)
- self.backend = get_backend(self.textclass)
- self.format = self.read_format()
- self.language = get_value(self.header, "\\language", 0,
- default = "english")
- self.inputencoding = get_value(self.header, "\\inputencoding",
- 0, default = "auto")
+ if PY2:
+ i = find_token(self.header, '\\lyxformat', 0) + 1
+ self.header[i:i] = ['\\textclass article']
+ else:
+ i = find_token(self.header, b'\\lyxformat', 0) + 1
+ self.header[i:i] = [b'\\textclass article']
+
+ if PY2:
+ self.textclass = get_value(self.header, "\\textclass", 0,
+ default = "")
+ self.language = get_value(self.header, "\\language", 0,
+ default = "english")
+ self.inputencoding = get_value(self.header, "\\inputencoding", 0,
+ default = "auto")
+ else:
+ self.textclass = get_value(self.header, b"\\textclass", 0,
+ default = b"")
+ self.language = get_value(self.header, b"\\language", 0,
+ default = b"english").decode('ascii')
+ self.inputencoding = get_value(self.header, b"\\inputencoding", 0,
+ default = b"auto").decode('ascii')
+ self.format = self.read_format()
+ self.initial_format = self.format
self.encoding = get_encoding(self.language,
self.inputencoding, self.format,
self.cjk_encoding)
self.initial_version = self.read_version()
# Second pass over header and preamble, now we know the file encoding
+ # Do not forget the textclass (Debian bug #700828)
+ self.textclass = self.textclass.decode(self.encoding)
+ self.backend = get_backend(self.textclass)
for i in range(len(self.header)):
self.header[i] = self.header[i].decode(self.encoding)
for i in range(len(self.preamble)):
self.preamble[i] = self.preamble[i].decode(self.encoding)
+ for i in range(len(self.body)):
+ self.body[i] = self.body[i].decode(self.encoding)
# Read document body
- while 1:
+ while True:
line = self.input.readline().decode(self.encoding)
if not line:
break
def write(self):
" Writes the LyX file to self.output."
+ self.choose_output(self.output)
self.set_version()
self.set_format()
self.set_textclass()
header = self.header
for line in header + [''] + self.body:
- self.output.write(line.encode(self.encoding)+"\n")
+ self.output.write(line+u"\n")
- def choose_io(self, input, output):
- """Choose input and output streams, dealing transparently with
+ def choose_output(self, output):
+ """Choose output streams dealing transparently with
compressed files."""
- if output:
- self.output = open(output, "wb")
+ # This is a bit complicated, because we need to be compatible both with
+ # python 2 and python 3. Therefore we handle the encoding here and not
+ # when writing individual lines and may need up to 3 layered file like
+ # interfaces.
+ if self.compressed:
+ if output:
+ outputfileobj = open(output, 'wb')
+ else:
+ # We cannot not use stdout directly since it needs text, not bytes in python 3
+ outputfileobj = os.fdopen(sys.stdout.fileno(), 'wb')
+ # We cannot not use gzip.open() since it is not supported by python 2
+ zipbuffer = gzip.GzipFile(mode='wb', fileobj=outputfileobj)
+ # We do not want to use different newlines on different OSes inside zipped files
+ self.output = io.TextIOWrapper(zipbuffer, encoding=self.encoding, newline='\n')
else:
- self.output = sys.stdout
+ if output:
+ self.output = io.open(output, 'w', encoding=self.encoding)
+ else:
+ self.output = io.open(sys.stdout.fileno(), 'w', encoding=self.encoding)
+
+
+ def choose_input(self, input):
+ """Choose input stream, dealing transparently with
+ compressed files."""
- if input and input != '-':
+ # Since we do not know the encoding yet we need to read the input as
+ # bytes in binary mode, and convert later to unicode.
+ if input and input != u'-':
self.dir = os.path.dirname(os.path.abspath(input))
try:
gzip.open(input).readline()
self.input = gzip.open(input)
- self.output = gzip.GzipFile(mode="wb", fileobj=self.output)
+ self.compressed = True
except:
- self.input = open(input)
+ self.input = open(input, 'rb')
+ self.compressed = False
else:
- self.dir = ''
- self.input = sys.stdin
+ self.dir = u''
+ self.input = os.fdopen(sys.stdin.fileno(), 'rb')
+ self.compressed = False
def lyxformat(self, format):
return None
line = line.replace("fix",".")
- result = original_version.match(line)
+ # need to test original_tex2lyx_version first because tex2lyx
+ # writes "#LyX file created by tex2lyx 2.2"
+ result = original_tex2lyx_version.match(line)
+ if not result:
+ result = original_version.match(line)
+ if result:
+ # Special know cases: reLyX and KLyX
+ if line.find("reLyX") != -1 or line.find("KLyX") != -1:
+ return "0.12"
if result:
- # Special know cases: reLyX and KLyX
- if line.find("reLyX") != -1 or line.find("KLyX") != -1:
- return "0.12"
-
res = result.group(1)
if not res:
self.warning(line)
def set_version(self):
" Set the header with the version used."
- self.header[0] = " ".join(["#LyX %s created this file." % version__,
- "For more info see http://www.lyx.org/"])
+
+ initial_comment = " ".join(["#LyX %s created this file." % version__,
+ "For more info see http://www.lyx.org/"])
+
+ # Simple heuristic to determine the comment that always starts
+ # a lyx file
+ if self.header[0].startswith("#"):
+ self.header[0] = initial_comment
+ else:
+ self.header.insert(0, initial_comment)
+
+ # Old lyx files had a two lines comment header:
+ # 1) the first line had the user who had created it
+ # 2) the second line had the lyx version used
+ # later we decided that 1) was a privacy risk for no gain
+ # here we remove the second line effectively erasing 1)
if self.header[1][0] == '#':
del self.header[1]
def read_format(self):
" Read from the header the fileformat of the present LyX file."
for line in self.header:
- result = fileformat.match(line)
+ if PY2:
+ result = fileformat.match(line)
+ else:
+ result = fileformat.match(line.decode('ascii'))
if result:
return self.lyxformat(result.group(1))
else:
- self.error("Invalid LyX File.")
+ self.error("Invalid LyX File: Missing format.")
return None
def convert(self):
"Convert from current (self.format) to self.end_format."
- mode, convertion_chain = self.chain()
- self.warning("convertion chain: " + str(convertion_chain), 3)
+ if self.format == self.end_format:
+ self.warning("No conversion needed: Target format %s "
+ "same as current format!" % self.format, default_debug__)
+ return
+
+ mode, conversion_chain = self.chain()
+ self.warning("conversion chain: " + str(conversion_chain), 3)
- for step in convertion_chain:
+ for step in conversion_chain:
steps = getattr(__import__("lyx_" + step), mode)
self.warning("Convertion step: %s - %s" % (step, mode),
default_debug__ + 1)
if not steps:
- self.error("The convertion to an older "
+ self.error("The conversion to an older "
"format (%s) is not implemented." % self.format)
multi_conv = len(steps) != 1
def chain(self):
""" This is where all the decisions related with the
- convertion are taken. It returns a list of modules needed to
+ conversion are taken. It returns a list of modules needed to
convert the LyX file from self.format to self.end_format"""
- self.start = self.format
format = self.format
correct_version = 0
# Convertion mode, back or forth
steps = []
- if (initial_step, self.start) < (final_step, self.end_format):
+ if (initial_step, self.initial_format) < (final_step, self.end_format):
mode = "convert"
full_steps = []
for step in format_relation:
return mode, steps
- def get_toc(self, depth = 4):
- " Returns the TOC of this LyX document."
- paragraphs_filter = {'Title' : 0,'Chapter' : 1, 'Section' : 2,
- 'Subsection' : 3, 'Subsubsection': 4}
- allowed_insets = ['Quotes']
- allowed_parameters = ('\\paragraph_spacing', '\\noindent',
- '\\align', '\\labelwidthstring',
- "\\start_of_appendix", "\\leftindent")
- sections = []
- for section in paragraphs_filter.keys():
- sections.append('\\begin_layout %s' % section)
-
- toc_par = []
- i = 0
- while 1:
- i = find_tokens(self.body, sections, i)
- if i == -1:
- break
-
- j = find_end_of(self.body, i + 1, '\\begin_layout', '\\end_layout')
- if j == -1:
- self.warning('Incomplete file.', 0)
- break
-
- section = self.body[i].split()[1]
- if section[-1] == '*':
- section = section[:-1]
-
- par = []
-
- k = i + 1
- # skip paragraph parameters
- while not self.body[k].strip() or self.body[k].split()[0] \
- in allowed_parameters:
- k += 1
-
- while k < j:
- if check_token(self.body[k], '\\begin_inset'):
- inset = self.body[k].split()[1]
- end = find_end_of_inset(self.body, k)
- if end == -1 or end > j:
- self.warning('Malformed file.', 0)
-
- if inset in allowed_insets:
- par.extend(self.body[k: end+1])
- k = end + 1
- else:
- par.append(self.body[k])
- k += 1
-
- # trim empty lines in the end.
- while par and par[-1].strip() == '':
- par.pop()
-
- toc_par.append(Paragraph(section, par))
-
- i = j + 1
-
- return toc_par
+# Part of an unfinished attempt to make lyx2lyx gave a more
+# structured view of the document.
+# def get_toc(self, depth = 4):
+# " Returns the TOC of this LyX document."
+# paragraphs_filter = {'Title' : 0,'Chapter' : 1, 'Section' : 2,
+# 'Subsection' : 3, 'Subsubsection': 4}
+# allowed_insets = ['Quotes']
+# allowed_parameters = ('\\paragraph_spacing', '\\noindent',
+# '\\align', '\\labelwidthstring',
+# "\\start_of_appendix", "\\leftindent")
+# sections = []
+# for section in paragraphs_filter.keys():
+# sections.append('\\begin_layout %s' % section)
+
+# toc_par = []
+# i = 0
+# while True:
+# i = find_tokens(self.body, sections, i)
+# if i == -1:
+# break
+
+# j = find_end_of(self.body, i + 1, '\\begin_layout', '\\end_layout')
+# if j == -1:
+# self.warning('Incomplete file.', 0)
+# break
+
+# section = self.body[i].split()[1]
+# if section[-1] == '*':
+# section = section[:-1]
+
+# par = []
+
+# k = i + 1
+# # skip paragraph parameters
+# while not self.body[k].strip() or self.body[k].split()[0] \
+# in allowed_parameters:
+# k += 1
+
+# while k < j:
+# if check_token(self.body[k], '\\begin_inset'):
+# inset = self.body[k].split()[1]
+# end = find_end_of_inset(self.body, k)
+# if end == -1 or end > j:
+# self.warning('Malformed file.', 0)
+
+# if inset in allowed_insets:
+# par.extend(self.body[k: end+1])
+# k = end + 1
+# else:
+# par.append(self.body[k])
+# k += 1
+
+# # trim empty lines in the end.
+# while par and par[-1].strip() == '':
+# par.pop()
+
+# toc_par.append(Paragraph(section, par))
+
+# i = j + 1
+
+# return toc_par
class File(LyX_base):
" This class reads existing LyX files."
- def __init__(self, end_format = 0, input = "", output = "", error = "",
- debug = default_debug__, try_hard = 0, cjk_encoding = '',
- final_version = ''):
+ def __init__(self, end_format = 0, input = u'', output = u'', error = u'',
+ debug = default_debug__, try_hard = 0, cjk_encoding = u'',
+ final_version = u'', systemlyxdir = u''):
LyX_base.__init__(self, end_format, input, output, error,
- debug, try_hard, cjk_encoding, final_version)
+ debug, try_hard, cjk_encoding, final_version,
+ systemlyxdir)
self.read()
-class NewFile(LyX_base):
- " This class is to create new LyX files."
- def set_header(self, **params):
- # set default values
- self.header.extend([
- "#LyX xxxx created this file."
- "For more info see http://www.lyx.org/",
- "\\lyxformat xxx",
- "\\begin_document",
- "\\begin_header",
- "\\textclass article",
- "\\language english",
- "\\inputencoding auto",
- "\\font_roman default",
- "\\font_sans default",
- "\\font_typewriter default",
- "\\font_default_family default",
- "\\font_sc false",
- "\\font_osf false",
- "\\font_sf_scale 100",
- "\\font_tt_scale 100",
- "\\graphics default",
- "\\paperfontsize default",
- "\\papersize default",
- "\\use_geometry false",
- "\\use_amsmath 1",
- "\\cite_engine basic",
- "\\use_bibtopic false",
- "\\paperorientation portrait",
- "\\secnumdepth 3",
- "\\tocdepth 3",
- "\\paragraph_separation indent",
- "\\defskip medskip",
- "\\quotes_language english",
- "\\papercolumns 1",
- "\\papersides 1",
- "\\paperpagestyle default",
- "\\tracking_changes false",
- "\\end_header"])
-
- self.format = get_end_format()
- for param in params:
- self.set_parameter(param, params[param])
-
-
- def set_body(self, paragraphs):
- self.body.extend(['\\begin_body',''])
-
- for par in paragraphs:
- self.body.extend(par.asLines())
-
- self.body.extend(['','\\end_body', '\\end_document'])
-
-
-class Paragraph:
- # unfinished implementation, it is missing the Text and Insets
- # representation.
- " This class represents the LyX paragraphs."
- def __init__(self, name, body=[], settings = [], child = []):
- """ Parameters:
- name: paragraph name.
- body: list of lines of body text.
- child: list of paragraphs that descend from this paragraph.
- """
- self.name = name
- self.body = body
- self.settings = settings
- self.child = child
-
- def asLines(self):
- """ Converts the paragraph to a list of strings, representing
- it in the LyX file."""
-
- result = ['','\\begin_layout %s' % self.name]
- result.extend(self.settings)
- result.append('')
- result.extend(self.body)
- result.append('\\end_layout')
-
- if not self.child:
- return result
-
- result.append('\\begin_deeper')
- for node in self.child:
- result.extend(node.asLines())
- result.append('\\end_deeper')
-
- return result
+# FIXME: header settings are completely outdated, don't use like this
+#class NewFile(LyX_base):
+# " This class is to create new LyX files."
+# def set_header(self, **params):
+# # set default values
+# self.header.extend([
+# "#LyX xxxx created this file."
+# "For more info see http://www.lyx.org/",
+# "\\lyxformat xxx",
+# "\\begin_document",
+# "\\begin_header",
+# "\\textclass article",
+# "\\language english",
+# "\\inputencoding auto",
+# "\\font_roman default",
+# "\\font_sans default",
+# "\\font_typewriter default",
+# "\\font_default_family default",
+# "\\font_sc false",
+# "\\font_osf false",
+# "\\font_sf_scale 100",
+# "\\font_tt_scale 100",
+# "\\graphics default",
+# "\\paperfontsize default",
+# "\\papersize default",
+# "\\use_geometry false",
+# "\\use_amsmath 1",
+# "\\cite_engine basic",
+# "\\use_bibtopic false",
+# "\\use_indices false",
+# "\\paperorientation portrait",
+# "\\secnumdepth 3",
+# "\\tocdepth 3",
+# "\\paragraph_separation indent",
+# "\\defskip medskip",
+# "\\quotes_language english",
+# "\\papercolumns 1",
+# "\\papersides 1",
+# "\\paperpagestyle default",
+# "\\tracking_changes false",
+# "\\end_header"])
+
+# self.format = get_end_format()
+# for param in params:
+# self.set_parameter(param, params[param])
+
+
+# def set_body(self, paragraphs):
+# self.body.extend(['\\begin_body',''])
+
+# for par in paragraphs:
+# self.body.extend(par.asLines())
+
+# self.body.extend(['','\\end_body', '\\end_document'])
+
+
+# Part of an unfinished attempt to make lyx2lyx gave a more
+# structured view of the document.
+#class Paragraph:
+# # unfinished implementation, it is missing the Text and Insets
+# # representation.
+# " This class represents the LyX paragraphs."
+# def __init__(self, name, body=[], settings = [], child = []):
+# """ Parameters:
+# name: paragraph name.
+# body: list of lines of body text.
+# child: list of paragraphs that descend from this paragraph.
+# """
+# self.name = name
+# self.body = body
+# self.settings = settings
+# self.child = child
+
+# def asLines(self):
+# """ Converts the paragraph to a list of strings, representing
+# it in the LyX file."""
+
+# result = ['','\\begin_layout %s' % self.name]
+# result.extend(self.settings)
+# result.append('')
+# result.extend(self.body)
+# result.append('\\end_layout')
+
+# if not self.child:
+# return result
+
+# result.append('\\begin_deeper')
+# for node in self.child:
+# result.extend(node.asLines())
+# result.append('\\end_deeper')
+
+# return result
projects / lyx.git / blobdiff