lyx_mirror/lib/lyx2lyx/lyx_0_10.py
José Matox 6785e442cf Add support for input encoding handling by lyx2lyx.
Support all lyx files (support goes to lyx-0.6 the first public available lyx version).

Fine tune the guessing of the lyx version used to produce the document (only useful for 2.10 and 2.15 documents).

Support to convertion to utf-8 encoding was added but it is not (yet) active.

git-svn-id: svn://svn.lyx.org/lyx/lyx-devel/trunk@14558 a592a061-630c-0410-9148-cb99ea01b6c8
2006-08-07 14:10:41 +00:00

139 lines
4.1 KiB
Python

# This file is part of lyx2lyx
# -*- coding: utf-8 -*-
# Copyright (C) 2006 José Matos <jamatos@lyx.org>
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# 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.
""" Convert files to the file format generated by lyx 0.10"""
def regularise_header(document):
" Put each entry in header into a separate line. "
i = 0
while i < len(document.header):
line = document.header[i]
if len(line.split('\\')) > 1:
tmp = [ '\\'+ token.strip() for token in line.split('\\')][1:]
document.header[i: i+1] = tmp
i += len(tmp)
i += 1
def find_next_space(line, j):
""" Return position of next space or backslash, which one comes
first, starting from position k, if not existing return last
position in line."""
l = line.find(' ', j)
if l == -1:
l = len(line)
k = line.find('\\', j)
if k == -1:
k = len(line)
if k < l:
return k
return l
def regularise_body(document):
""" Place tokens starting with a backslash into a separate line. """
getline_tokens = ["added_space_bottom", "added_space_top",
"align", "layout", "fill_bottom", "fill_top",
"labelwidthstring", "pagebreak_top",
"pagebreak_bottom", "noindent"]
noargs_tokens = ["backslash", "begin_deeper", "end_deeper",
"end_float", "end_inset", "hfill", "newline",
"protected_separator"]
onearg_tokens = ["bar", "begin_float", "family", "latex", "shape",
"size", "series", "cursor"]
i = 0
while i < len(document.body):
line = document.body[i]
j = 0
tmp = []
while j < len(line):
k = line.find('\\', j)
if k == -1:
tmp += [line[j:]]
break
if k != j:
tmp += [line[j: k]]
j = k
k = find_next_space(line, j+1)
# These tokens take the rest of the line
token = line[j+1:k]
if token in getline_tokens:
tmp += [line[j:]]
break
# These tokens take no arguments
if token in noargs_tokens:
tmp += [line[j:k]]
j = k
continue
# These tokens take one argument
if token in onearg_tokens:
k = find_next_space(line, k + 1)
tmp += [line[j:k]]
j = k
continue
# Special treatment for insets
if token in ["begin_inset"]:
l = find_next_space(line, k + 1)
inset = line[k+1: l]
if inset == "Latex":
tmp += [line[j:l]]
j = l
continue
if inset in ["LatexCommand", "LatexDel"]:
tmp += [line[j:]]
break
if inset == "Quotes":
l = find_next_space(line, l + 1)
tmp += [line[j:l]]
j = l
continue
document.warning("unkown inset %s" % line)
assert(False)
# We are inside a latex inset, pass the text verbatim
tmp += [line[j:]]
break
document.body[i: i+1] = tmp
i += len(tmp)
supported_versions = ["0.10.%d" % i for i in range(8)] + ["0.10"]
convert = [[210, [regularise_header, regularise_body]]]
revert = []
if __name__ == "__main__":
pass