lyx_mirror/lib/lyx2lyx/lyx_2_3.py
Scott Kostyshak 713fd70e8f Fix Python escaping of unicode string
When removing "r" from "ur", it is needed to add extra backslashes.
See:

  https://www.mail-archive.com/search?l=mid&q=2024193.iXIh6cq6L3%40myth

Thanks to José.

This commit amends b7983478 (and thus 586d16a4).
2017-12-26 02:10:49 -05:00

2333 lines
84 KiB
Python

# -*- coding: utf-8 -*-
# This file is part of lyx2lyx
# Copyright (C) 2016 The LyX team
#
# 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 2.3"""
import re, string
import unicodedata
import sys, os
# Uncomment only what you need to import, please.
from parser_tools import find_end_of, find_token_backwards, find_end_of_layout, \
find_token, find_end_of_inset, get_value, get_bool_value, \
get_containing_layout, get_quoted_value, del_token, find_re
# find_tokens, find_token_exact, is_in_inset, \
# check_token, get_option_value
from lyx2lyx_tools import add_to_preamble, put_cmd_in_ert, revert_font_attrs, \
insert_to_preamble
# get_ert, lyx2latex, \
# lyx2verbatim, length_in_bp, convert_info_insets
# latex_length, revert_flex_inset, hex2ratio, str2bool
####################################################################
# Private helper functions
###############################################################################
###
### Conversion and reversion routines
###
###############################################################################
def convert_microtype(document):
" Add microtype settings. "
i = find_token(document.header, "\\font_tt_scale" , 0)
if i == -1:
document.warning("Malformed LyX document: Can't find \\font_tt_scale.")
i = len(document.header) - 1
j = find_token(document.preamble, "\\usepackage{microtype}", 0)
if j == -1:
document.header.insert(i + 1, "\\use_microtype false")
else:
document.header.insert(i + 1, "\\use_microtype true")
del document.preamble[j]
def revert_microtype(document):
" Remove microtype settings. "
i = find_token(document.header, "\\use_microtype", 0)
if i == -1:
return
use_microtype = get_bool_value(document.header, "\\use_microtype" , i)
del document.header[i]
if use_microtype:
add_to_preamble(document, ["\\usepackage{microtype}"])
def convert_dateinset(document):
' Convert date external inset to ERT '
i = 0
while True:
i = find_token(document.body, "\\begin_inset External", i)
if i == -1:
return
j = find_end_of_inset(document.body, i)
if j == -1:
document.warning("Malformed lyx document: Missing '\\end_inset' in convert_dateinset.")
i += 1
continue
if get_value(document.body, 'template', i, j) == "Date":
document.body[i : j + 1] = put_cmd_in_ert("\\today ")
i += 1
continue
def convert_inputenc(document):
" Replace no longer supported input encoding settings. "
i = find_token(document.header, "\\inputenc", 0)
if i == -1:
return
if get_value(document.header, "\\inputencoding", i) == "pt254":
document.header[i] = "\\inputencoding pt154"
def convert_ibranches(document):
' Add "inverted 0" to branch insets'
i = 0
while True:
i = find_token(document.body, "\\begin_inset Branch", i)
if i == -1:
return
document.body.insert(i + 1, "inverted 0")
i += 1
def revert_ibranches(document):
' Convert inverted branches to explicit anti-branches'
# Get list of branches
ourbranches = {}
i = 0
while True:
i = find_token(document.header, "\\branch", i)
if i == -1:
break
branch = document.header[i][8:].strip()
if document.header[i+1].startswith("\\selected "):
#document.warning(document.header[i+1])
#document.warning(document.header[i+1][10])
selected = int(document.header[i+1][10])
else:
document.warning("Malformed LyX document: No selection indicator for branch " + branch)
selected = 1
# the value tells us whether the branch is selected
ourbranches[document.header[i][8:].strip()] = selected
i += 1
# Figure out what inverted branches, if any, have been used
# and convert them to "Anti-OldBranch"
ibranches = {}
i = 0
while True:
i = find_token(document.body, "\\begin_inset Branch", i)
if i == -1:
break
if not document.body[i+1].startswith("inverted "):
document.warning("Malformed LyX document: Missing 'inverted' tag!")
i += 1
continue
inverted = document.body[i+1][9]
#document.warning(document.body[i+1])
if inverted == "1":
branch = document.body[i][20:].strip()
#document.warning(branch)
if not branch in ibranches:
antibranch = "Anti-" + branch
while antibranch in ibranches:
antibranch = "x" + antibranch
ibranches[branch] = antibranch
else:
antibranch = ibranches[branch]
#document.warning(antibranch)
document.body[i] = "\\begin_inset Branch " + antibranch
# remove "inverted" key
del document.body[i+1]
i += 1
# now we need to add the new branches to the header
for old, new in ibranches.items():
i = find_token(document.header, "\\branch " + old, 0)
if i == -1:
document.warning("Can't find branch %s even though we found it before!" % (old))
continue
j = find_token(document.header, "\\end_branch", i)
if j == -1:
document.warning("Malformed LyX document! Can't find end of branch " + old)
continue
# ourbranches[old] - 1 inverts the selection status of the old branch
lines = ["\\branch " + new,
"\\selected " + str(ourbranches[old] - 1)]
# these are the old lines telling us color, etc.
lines += document.header[i+2 : j+1]
document.header[i:i] = lines
def revert_beamer_article_styles(document):
" Include (scr)article styles in beamer article "
beamer_articles = ["article-beamer", "scrarticle-beamer"]
if document.textclass not in beamer_articles:
return
inclusion = "article.layout"
if document.textclass == "scrarticle-beamer":
inclusion = "scrartcl.layout"
i = find_token(document.header, "\\begin_local_layout", 0)
if i == -1:
k = find_token(document.header, "\\language", 0)
if k == -1:
# this should not happen
document.warning("Malformed LyX document! No \\language header found!")
return
document.header[k-1 : k-1] = ["\\begin_local_layout", "\\end_local_layout"]
i = k - 1
j = find_end_of(document.header, i, "\\begin_local_layout", "\\end_local_layout")
if j == -1:
# this should not happen
document.warning("Malformed LyX document: Can't find end of local layout!")
return
document.header[i+1 : i+1] = [
"### Inserted by lyx2lyx (more [scr]article styles) ###",
"Input " + inclusion,
"Input beamer.layout",
"Provides geometry 0",
"Provides hyperref 0",
"DefaultFont",
" Family Roman",
" Series Medium",
" Shape Up",
" Size Normal",
" Color None",
"EndFont",
"Preamble",
" \\usepackage{beamerarticle,pgf}",
" % this default might be overridden by plain title style",
" \\newcommand\makebeamertitle{\\frame{\\maketitle}}%",
" \\AtBeginDocument{",
" \\let\\origtableofcontents=\\tableofcontents",
" \\def\\tableofcontents{\\@ifnextchar[{\\origtableofcontents}{\\gobbletableofcontents}}",
" \\def\\gobbletableofcontents#1{\\origtableofcontents}",
" }",
"EndPreamble",
"### End of insertion by lyx2lyx (more [scr]article styles) ###"
]
def convert_beamer_article_styles(document):
" Remove included (scr)article styles in beamer article "
beamer_articles = ["article-beamer", "scrarticle-beamer"]
if document.textclass not in beamer_articles:
return
i = find_token(document.header, "\\begin_local_layout", 0)
if i == -1:
return
j = find_end_of(document.header, i, "\\begin_local_layout", "\\end_local_layout")
if j == -1:
# this should not happen
document.warning("Malformed LyX document: Can't find end of local layout!")
return
k = find_token(document.header, "### Inserted by lyx2lyx (more [scr]article styles) ###", i, j)
if k != -1:
l = find_token(document.header, "### End of insertion by lyx2lyx (more [scr]article styles) ###", i, j)
if l == -1:
# this should not happen
document.warning("End of lyx2lyx local layout insertion not found!")
return
if k == i + 1 and l == j - 1:
# that was all the local layout there was
document.header[i : j + 1] = []
else:
document.header[k : l + 1] = []
def revert_bosnian(document):
"Set the document language to English but assure Bosnian output"
if document.language == "bosnian":
document.language = "english"
i = find_token(document.header, "\\language bosnian", 0)
if i != -1:
document.header[i] = "\\language english"
j = find_token(document.header, "\\language_package default", 0)
if j != -1:
document.header[j] = "\\language_package babel"
k = find_token(document.header, "\\options", 0)
if k != -1:
document.header[k] = document.header[k].replace("\\options", "\\options bosnian,")
else:
l = find_token(document.header, "\\use_default_options", 0)
document.header.insert(l + 1, "\\options bosnian")
def revert_friulan(document):
"Set the document language to English but assure Friulan output"
if document.language == "friulan":
document.language = "english"
i = find_token(document.header, "\\language friulan", 0)
if i != -1:
document.header[i] = "\\language english"
j = find_token(document.header, "\\language_package default", 0)
if j != -1:
document.header[j] = "\\language_package babel"
k = find_token(document.header, "\\options", 0)
if k != -1:
document.header[k] = document.header[k].replace("\\options", "\\options friulan,")
else:
l = find_token(document.header, "\\use_default_options", 0)
document.header.insert(l + 1, "\\options friulan")
def revert_macedonian(document):
"Set the document language to English but assure Macedonian output"
if document.language == "macedonian":
document.language = "english"
i = find_token(document.header, "\\language macedonian", 0)
if i != -1:
document.header[i] = "\\language english"
j = find_token(document.header, "\\language_package default", 0)
if j != -1:
document.header[j] = "\\language_package babel"
k = find_token(document.header, "\\options", 0)
if k != -1:
document.header[k] = document.header[k].replace("\\options", "\\options macedonian,")
else:
l = find_token(document.header, "\\use_default_options", 0)
document.header.insert(l + 1, "\\options macedonian")
def revert_piedmontese(document):
"Set the document language to English but assure Piedmontese output"
if document.language == "piedmontese":
document.language = "english"
i = find_token(document.header, "\\language piedmontese", 0)
if i != -1:
document.header[i] = "\\language english"
j = find_token(document.header, "\\language_package default", 0)
if j != -1:
document.header[j] = "\\language_package babel"
k = find_token(document.header, "\\options", 0)
if k != -1:
document.header[k] = document.header[k].replace("\\options", "\\options piedmontese,")
else:
l = find_token(document.header, "\\use_default_options", 0)
document.header.insert(l + 1, "\\options piedmontese")
def revert_romansh(document):
"Set the document language to English but assure Romansh output"
if document.language == "romansh":
document.language = "english"
i = find_token(document.header, "\\language romansh", 0)
if i != -1:
document.header[i] = "\\language english"
j = find_token(document.header, "\\language_package default", 0)
if j != -1:
document.header[j] = "\\language_package babel"
k = find_token(document.header, "\\options", 0)
if k != -1:
document.header[k] = document.header[k].replace("\\options", "\\options romansh,")
else:
l = find_token(document.header, "\\use_default_options", 0)
document.header.insert(l + 1, "\\options romansh")
def revert_amharic(document):
"Set the document language to English but assure Amharic output"
if document.language == "amharic":
document.language = "english"
i = find_token(document.header, "\\language amharic", 0)
if i != -1:
document.header[i] = "\\language english"
j = find_token(document.header, "\\language_package default", 0)
if j != -1:
document.header[j] = "\\language_package default"
add_to_preamble(document, ["\\AtBeginDocument{\setotherlanguage{amharic}}"])
document.body[2 : 2] = ["\\begin_layout Standard",
"\\begin_inset ERT", "status open", "",
"\\begin_layout Plain Layout", "", "",
"\\backslash",
"resetdefaultlanguage{amharic}",
"\\end_layout", "", "\\end_inset", "", "",
"\\end_layout", ""]
def revert_asturian(document):
"Set the document language to English but assure Asturian output"
if document.language == "asturian":
document.language = "english"
i = find_token(document.header, "\\language asturian", 0)
if i != -1:
document.header[i] = "\\language english"
j = find_token(document.header, "\\language_package default", 0)
if j != -1:
document.header[j] = "\\language_package default"
add_to_preamble(document, ["\\AtBeginDocument{\setotherlanguage{asturian}}"])
document.body[2 : 2] = ["\\begin_layout Standard",
"\\begin_inset ERT", "status open", "",
"\\begin_layout Plain Layout", "", "",
"\\backslash",
"resetdefaultlanguage{asturian}",
"\\end_layout", "", "\\end_inset", "", "",
"\\end_layout", ""]
def revert_kannada(document):
"Set the document language to English but assure Kannada output"
if document.language == "kannada":
document.language = "english"
i = find_token(document.header, "\\language kannada", 0)
if i != -1:
document.header[i] = "\\language english"
j = find_token(document.header, "\\language_package default", 0)
if j != -1:
document.header[j] = "\\language_package default"
add_to_preamble(document, ["\\AtBeginDocument{\setotherlanguage{kannada}}"])
document.body[2 : 2] = ["\\begin_layout Standard",
"\\begin_inset ERT", "status open", "",
"\\begin_layout Plain Layout", "", "",
"\\backslash",
"resetdefaultlanguage{kannada}",
"\\end_layout", "", "\\end_inset", "", "",
"\\end_layout", ""]
def revert_khmer(document):
"Set the document language to English but assure Khmer output"
if document.language == "khmer":
document.language = "english"
i = find_token(document.header, "\\language khmer", 0)
if i != -1:
document.header[i] = "\\language english"
j = find_token(document.header, "\\language_package default", 0)
if j != -1:
document.header[j] = "\\language_package default"
add_to_preamble(document, ["\\AtBeginDocument{\setotherlanguage{khmer}}"])
document.body[2 : 2] = ["\\begin_layout Standard",
"\\begin_inset ERT", "status open", "",
"\\begin_layout Plain Layout", "", "",
"\\backslash",
"resetdefaultlanguage{khmer}",
"\\end_layout", "", "\\end_inset", "", "",
"\\end_layout", ""]
def revert_urdu(document):
"Set the document language to English but assure Urdu output"
if document.language == "urdu":
document.language = "english"
i = find_token(document.header, "\\language urdu", 0)
if i != -1:
document.header[i] = "\\language english"
j = find_token(document.header, "\\language_package default", 0)
if j != -1:
document.header[j] = "\\language_package default"
add_to_preamble(document, ["\\AtBeginDocument{\setotherlanguage{urdu}}"])
document.body[2 : 2] = ["\\begin_layout Standard",
"\\begin_inset ERT", "status open", "",
"\\begin_layout Plain Layout", "", "",
"\\backslash",
"resetdefaultlanguage{urdu}",
"\\end_layout", "", "\\end_inset", "", "",
"\\end_layout", ""]
def revert_syriac(document):
"Set the document language to English but assure Syriac output"
if document.language == "syriac":
document.language = "english"
i = find_token(document.header, "\\language syriac", 0)
if i != -1:
document.header[i] = "\\language english"
j = find_token(document.header, "\\language_package default", 0)
if j != -1:
document.header[j] = "\\language_package default"
add_to_preamble(document, ["\\AtBeginDocument{\setotherlanguage{syriac}}"])
document.body[2 : 2] = ["\\begin_layout Standard",
"\\begin_inset ERT", "status open", "",
"\\begin_layout Plain Layout", "", "",
"\\backslash",
"resetdefaultlanguage{syriac}",
"\\end_layout", "", "\\end_inset", "", "",
"\\end_layout", ""]
def revert_quotes(document):
" Revert Quote Insets in verbatim or Hebrew context to plain quotes "
# First handle verbatim insets
i = 0
j = 0
while i < len(document.body):
words = document.body[i].split()
if len(words) > 1 and words[0] == "\\begin_inset" and \
( words[1] in ["ERT", "listings"] or ( len(words) > 2 and words[2] in ["URL", "Chunk", "Sweave", "S/R"]) ):
j = find_end_of_inset(document.body, i)
if j == -1:
document.warning("Malformed LyX document: Can't find end of " + words[1] + " inset at line " + str(i))
i += 1
continue
while True:
k = find_token(document.body, '\\begin_inset Quotes', i, j)
if k == -1:
i += 1
break
l = find_end_of_inset(document.body, k)
if l == -1:
document.warning("Malformed LyX document: Can't find end of Quote inset at line " + str(k))
i = k
continue
replace = "\""
if document.body[k].endswith("s"):
replace = "'"
document.body[k:l+1] = [replace]
else:
i += 1
continue
# Now verbatim layouts
i = 0
j = 0
while i < len(document.body):
words = document.body[i].split()
if len(words) > 1 and words[0] == "\\begin_layout" and \
words[1] in ["Verbatim", "Verbatim*", "Code", "Author_Email", "Author_URL"]:
j = find_end_of_layout(document.body, i)
if j == -1:
document.warning("Malformed LyX document: Can't find end of " + words[1] + " layout at line " + str(i))
i += 1
continue
while True:
k = find_token(document.body, '\\begin_inset Quotes', i, j)
if k == -1:
i += 1
break
l = find_end_of_inset(document.body, k)
if l == -1:
document.warning("Malformed LyX document: Can't find end of Quote inset at line " + str(k))
i = k
continue
replace = "\""
if document.body[k].endswith("s"):
replace = "'"
document.body[k:l+1] = [replace]
else:
i += 1
continue
# Now handle Hebrew
if not document.language == "hebrew" and find_token(document.body, '\\lang hebrew', 0) == -1:
return
i = 0
j = 0
while True:
k = find_token(document.body, '\\begin_inset Quotes', i)
if k == -1:
return
l = find_end_of_inset(document.body, k)
if l == -1:
document.warning("Malformed LyX document: Can't find end of Quote inset at line " + str(k))
i = k
continue
hebrew = False
parent = get_containing_layout(document.body, k)
ql = find_token_backwards(document.body, "\\lang", k)
if ql == -1 or ql < parent[1]:
hebrew = document.language == "hebrew"
elif document.body[ql] == "\\lang hebrew":
hebrew = True
if hebrew:
replace = "\""
if document.body[k].endswith("s"):
replace = "'"
document.body[k:l+1] = [replace]
i = l
def revert_iopart(document):
" Input new styles via local layout "
if document.textclass != "iopart":
return
i = find_token(document.header, "\\begin_local_layout", 0)
if i == -1:
k = find_token(document.header, "\\language", 0)
if k == -1:
# this should not happen
document.warning("Malformed LyX document! No \\language header found!")
return
document.header[k-1 : k-1] = ["\\begin_local_layout", "\\end_local_layout"]
i = k-1
j = find_end_of(document.header, i, "\\begin_local_layout", "\\end_local_layout")
if j == -1:
# this should not happen
document.warning("Malformed LyX document! Can't find end of local layout!")
return
document.header[i+1 : i+1] = [
"### Inserted by lyx2lyx (stdlayouts) ###",
"Input stdlayouts.inc",
"### End of insertion by lyx2lyx (stdlayouts) ###"
]
def convert_iopart(document):
" Remove local layout we added, if it is there "
if document.textclass != "iopart":
return
i = find_token(document.header, "\\begin_local_layout", 0)
if i == -1:
return
j = find_end_of(document.header, i, "\\begin_local_layout", "\\end_local_layout")
if j == -1:
# this should not happen
document.warning("Malformed LyX document! Can't find end of local layout!")
return
k = find_token(document.header, "### Inserted by lyx2lyx (stdlayouts) ###", i, j)
if k != -1:
l = find_token(document.header, "### End of insertion by lyx2lyx (stdlayouts) ###", i, j)
if l == -1:
# this should not happen
document.warning("End of lyx2lyx local layout insertion not found!")
return
if k == i + 1 and l == j - 1:
# that was all the local layout there was
document.header[i : j + 1] = []
else:
document.header[k : l + 1] = []
def convert_quotestyle(document):
" Convert \\quotes_language to \\quotes_style "
i = find_token(document.header, "\\quotes_language", 0)
if i == -1:
document.warning("Malformed LyX document! Can't find \\quotes_language!")
return
val = get_value(document.header, "\\quotes_language", i)
document.header[i] = "\\quotes_style " + val
def revert_quotestyle(document):
" Revert \\quotes_style to \\quotes_language "
i = find_token(document.header, "\\quotes_style", 0)
if i == -1:
document.warning("Malformed LyX document! Can't find \\quotes_style!")
return
val = get_value(document.header, "\\quotes_style", i)
document.header[i] = "\\quotes_language " + val
def revert_plainquote(document):
" Revert plain quote insets "
# First, revert style setting
i = find_token(document.header, "\\quotes_style plain", 0)
if i != -1:
document.header[i] = "\\quotes_style english"
# now the insets
i = 0
j = 0
while True:
k = find_token(document.body, '\\begin_inset Quotes q', i)
if k == -1:
return
l = find_end_of_inset(document.body, k)
if l == -1:
document.warning("Malformed LyX document: Can't find end of Quote inset at line " + str(k))
i = k
continue
replace = "\""
if document.body[k].endswith("s"):
replace = "'"
document.body[k:l+1] = [replace]
i = l
def convert_frenchquotes(document):
" Convert french quote insets to swiss "
# First, revert style setting
i = find_token(document.header, "\\quotes_style french", 0)
if i != -1:
document.header[i] = "\\quotes_style swiss"
# now the insets
i = 0
while True:
i = find_token(document.body, '\\begin_inset Quotes f', i)
if i == -1:
return
val = get_value(document.body, "\\begin_inset Quotes", i)[7:]
newval = val.replace("f", "c", 1)
document.body[i] = document.body[i].replace(val, newval)
i += 1
def revert_swissquotes(document):
" Revert swiss quote insets to french "
# First, revert style setting
i = find_token(document.header, "\\quotes_style swiss", 0)
if i != -1:
document.header[i] = "\\quotes_style french"
# now the insets
i = 0
while True:
i = find_token(document.body, '\\begin_inset Quotes c', i)
if i == -1:
return
val = get_value(document.body, "\\begin_inset Quotes", i)[7:]
newval = val.replace("c", "f", 1)
document.body[i] = document.body[i].replace(val, newval)
i += 1
def revert_britishquotes(document):
" Revert british quote insets to english "
# First, revert style setting
i = find_token(document.header, "\\quotes_style british", 0)
if i != -1:
document.header[i] = "\\quotes_style english"
# now the insets
i = 0
while True:
i = find_token(document.body, '\\begin_inset Quotes b', i)
if i == -1:
return
val = get_value(document.body, "\\begin_inset Quotes", i)[7:]
newval = val.replace("b", "e", 1)
if val[2] == "d":
# opening mark
newval = newval.replace("d", "s")
else:
# closing mark
newval = newval.replace("s", "d")
document.body[i] = document.body[i].replace(val, newval)
i += 1
def revert_swedishgquotes(document):
" Revert swedish quote insets "
# First, revert style setting
i = find_token(document.header, "\\quotes_style swedishg", 0)
if i != -1:
document.header[i] = "\\quotes_style danish"
# now the insets
i = 0
while True:
i = find_token(document.body, '\\begin_inset Quotes w', i)
if i == -1:
return
val = get_value(document.body, "\\begin_inset Quotes", i)[7:]
if val[2] == "d":
# outer marks
newval = val.replace("w", "a", 1).replace("r", "l")
else:
# inner marks
newval = val.replace("w", "s", 1)
document.body[i] = document.body[i].replace(val, newval)
i += 1
def revert_frenchquotes(document):
" Revert french inner quote insets "
i = 0
while True:
i = find_token(document.body, '\\begin_inset Quotes f', i)
if i == -1:
return
val = get_value(document.body, "\\begin_inset Quotes", i)[7:]
if val[2] == "s":
# inner marks
newval = val.replace("f", "e", 1).replace("s", "d")
document.body[i] = document.body[i].replace(val, newval)
i += 1
def revert_frenchinquotes(document):
" Revert inner frenchin quote insets "
# First, revert style setting
i = find_token(document.header, "\\quotes_style frenchin", 0)
if i != -1:
document.header[i] = "\\quotes_style french"
# now the insets
i = 0
while True:
i = find_token(document.body, '\\begin_inset Quotes i', i)
if i == -1:
return
val = get_value(document.body, "\\begin_inset Quotes", i)[7:]
newval = val.replace("i", "f", 1)
if val[2] == "s":
# inner marks
newval = newval.replace("s", "d")
document.body[i] = document.body[i].replace(val, newval)
i += 1
def revert_russianquotes(document):
" Revert russian quote insets "
# First, revert style setting
i = find_token(document.header, "\\quotes_style russian", 0)
if i != -1:
document.header[i] = "\\quotes_style french"
# now the insets
i = 0
while True:
i = find_token(document.body, '\\begin_inset Quotes r', i)
if i == -1:
return
val = get_value(document.body, "\\begin_inset Quotes", i)[7:]
newval = val
if val[2] == "s":
# inner marks
newval = val.replace("r", "g", 1).replace("s", "d")
else:
# outer marks
newval = val.replace("r", "f", 1)
document.body[i] = document.body[i].replace(val, newval)
i += 1
def revert_dynamicquotes(document):
" Revert dynamic quote insets "
# First, revert header
i = find_token(document.header, "\\dynamic_quotes", 0)
if i != -1:
del document.header[i]
# Get global style
style = "english"
i = find_token(document.header, "\\quotes_style", 0)
if i == -1:
document.warning("Malformed document! Missing \\quotes_style")
else:
style = get_value(document.header, "\\quotes_style", i)
s = "e"
if style == "english":
s = "e"
elif style == "swedish":
s = "s"
elif style == "german":
s = "g"
elif style == "polish":
s = "p"
elif style == "swiss":
s = "c"
elif style == "danish":
s = "a"
elif style == "plain":
s = "q"
elif style == "british":
s = "b"
elif style == "swedishg":
s = "w"
elif style == "french":
s = "f"
elif style == "frenchin":
s = "i"
elif style == "russian":
s = "r"
# now transform the insets
i = 0
while True:
i = find_token(document.body, '\\begin_inset Quotes x', i)
if i == -1:
return
document.body[i] = document.body[i].replace("x", s)
i += 1
def revert_cjkquotes(document):
" Revert cjk quote insets "
# Get global style
style = "english"
i = find_token(document.header, "\\quotes_style", 0)
if i == -1:
document.warning("Malformed document! Missing \\quotes_style")
else:
style = get_value(document.header, "\\quotes_style", i)
global_cjk = style.find("cjk") != -1
if global_cjk:
document.header[i] = "\\quotes_style english"
# transform dynamic insets
s = "j"
if style == "cjkangle":
s = "k"
i = 0
while True:
i = find_token(document.body, '\\begin_inset Quotes x', i)
if i == -1:
break
document.body[i] = document.body[i].replace("x", s)
i += 1
cjk_langs = ["chinese-simplified", "chinese-traditional", "japanese", "japanese-cjk", "korean"]
i = 0
j = 0
while True:
k = find_token(document.body, '\\begin_inset Quotes j', i)
if k == -1:
break
l = find_end_of_inset(document.body, k)
if l == -1:
document.warning("Malformed LyX document: Can't find end of Quote inset at line " + str(k))
i = k
continue
cjk = False
parent = get_containing_layout(document.body, k)
ql = find_token_backwards(document.body, "\\lang", k)
if ql == -1 or ql < parent[1]:
cjk = document.language in cjk_langs
elif document.body[ql].split()[1] in cjk_langs:
cjk = True
val = get_value(document.body, "\\begin_inset Quotes", i)[7:]
replace = []
if val[2] == "s":
# inner marks
if val[1] == "l":
# inner opening mark
if cjk:
replace = [u"\u300E"]
else:
replace = ["\\begin_inset Formula $\\llceil$", "\\end_inset"]
else:
# inner closing mark
if cjk:
replace = [u"\u300F"]
else:
replace = ["\\begin_inset Formula $\\rrfloor$", "\\end_inset"]
else:
# outer marks
if val[1] == "l":
# outer opening mark
if cjk:
replace = [u"\u300C"]
else:
replace = ["\\begin_inset Formula $\\lceil$", "\\end_inset"]
else:
# outer closing mark
if cjk:
replace = [u"\u300D"]
else:
replace = ["\\begin_inset Formula $\\rfloor$", "\\end_inset"]
document.body[k:l+1] = replace
i = l
i = 0
j = 0
while True:
k = find_token(document.body, '\\begin_inset Quotes k', i)
if k == -1:
return
l = find_end_of_inset(document.body, k)
if l == -1:
document.warning("Malformed LyX document: Can't find end of Quote inset at line " + str(k))
i = k
continue
cjk = False
parent = get_containing_layout(document.body, k)
ql = find_token_backwards(document.body, "\\lang", k)
if ql == -1 or ql < parent[1]:
cjk = document.language in cjk_langs
elif document.body[ql].split()[1] in cjk_langs:
cjk = True
val = get_value(document.body, "\\begin_inset Quotes", i)[7:]
replace = []
if val[2] == "s":
# inner marks
if val[1] == "l":
# inner opening mark
if cjk:
replace = [u"\u3008"]
else:
replace = ["\\begin_inset Formula $\\langle$", "\\end_inset"]
else:
# inner closing mark
if cjk:
replace = [u"\u3009"]
else:
replace = ["\\begin_inset Formula $\\rangle$", "\\end_inset"]
else:
# outer marks
if val[1] == "l":
# outer opening mark
if cjk:
replace = [u"\u300A"]
else:
replace = ["\\begin_inset Formula $\\langle\\kern -2.5pt\\langle$", "\\end_inset"]
else:
# outer closing mark
if cjk:
replace = [u"\u300B"]
else:
replace = ["\\begin_inset Formula $\\rangle\\kern -2.5pt\\rangle$", "\\end_inset"]
document.body[k:l+1] = replace
i = l
def revert_crimson(document):
" Revert native Cochineal/Crimson font definition to LaTeX "
if find_token(document.header, "\\use_non_tex_fonts false", 0) != -1:
preamble = ""
i = find_token(document.header, "\\font_roman \"cochineal\"", 0)
if i != -1:
osf = False
j = find_token(document.header, "\\font_osf true", 0)
if j != -1:
osf = True
preamble = "\\usepackage"
if osf:
document.header[j] = "\\font_osf false"
preamble += "[proportional,osf]"
preamble += "{cochineal}"
add_to_preamble(document, [preamble])
document.header[i] = document.header[i].replace("cochineal", "default")
def revert_cochinealmath(document):
" Revert cochineal newtxmath definitions to LaTeX "
if find_token(document.header, "\\use_non_tex_fonts false", 0) != -1:
i = find_token(document.header, "\\font_math \"cochineal-ntxm\"", 0)
if i != -1:
add_to_preamble(document, "\\usepackage[cochineal]{newtxmath}")
document.header[i] = document.header[i].replace("cochineal-ntxm", "auto")
def revert_labelonly(document):
" Revert labelonly tag for InsetRef "
i = 0
while (True):
i = find_token(document.body, "\\begin_inset CommandInset ref", i)
if i == -1:
return
j = find_end_of_inset(document.body, i)
if j == -1:
document.warning("Can't find end of reference inset at line %d!!" %(i))
i += 1
continue
k = find_token(document.body, "LatexCommand labelonly", i, j)
if k == -1:
i = j
continue
label = get_quoted_value(document.body, "reference", i, j)
if not label:
document.warning("Can't find label for reference at line %d!" %(i))
i = j + 1
continue
document.body[i:j+1] = put_cmd_in_ert([label])
i += 1
def revert_plural_refs(document):
" Revert plural and capitalized references "
i = find_token(document.header, "\\use_refstyle 1", 0)
use_refstyle = (i != 0)
i = 0
while (True):
i = find_token(document.body, "\\begin_inset CommandInset ref", i)
if i == -1:
return
j = find_end_of_inset(document.body, i)
if j == -1:
document.warning("Can't find end of reference inset at line %d!!" %(i))
i += 1
continue
plural = caps = suffix = False
k = find_token(document.body, "LaTeXCommand formatted", i, j)
if k != -1 and use_refstyle:
plural = get_bool_value(document.body, "plural", i, j, False)
caps = get_bool_value(document.body, "caps", i, j, False)
label = get_quoted_value(document.body, "reference", i, j)
if label:
try:
(prefix, suffix) = label.split(":", 1)
except:
document.warning("No `:' separator in formatted reference at line %d!" % (i))
else:
document.warning("Can't find label for reference at line %d!" % (i))
# this effectively tests also for use_refstyle and a formatted reference
# we do this complicated test because we would otherwise do this erasure
# over and over and over
if not ((plural or caps) and suffix):
del_token(document.body, "plural", i, j)
del_token(document.body, "caps", i, j - 1) # since we deleted a line
i = j - 1
continue
if caps:
prefix = prefix[0].title() + prefix[1:]
cmd = "\\" + prefix + "ref"
if plural:
cmd += "[s]"
cmd += "{" + suffix + "}"
document.body[i:j+1] = put_cmd_in_ert([cmd])
i += 1
def revert_noprefix(document):
" Revert labelonly tags with 'noprefix' set "
i = 0
while (True):
i = find_token(document.body, "\\begin_inset CommandInset ref", i)
if i == -1:
return
j = find_end_of_inset(document.body, i)
if j == -1:
document.warning("Can't find end of reference inset at line %d!!" %(i))
i += 1
continue
k = find_token(document.body, "LatexCommand labelonly", i, j)
noprefix = False
if k != -1:
noprefix = get_bool_value(document.body, "noprefix", i, j)
if not noprefix:
# either it was not a labelonly command, or else noprefix was not set.
# in that case, we just delete the option.
del_token(document.body, "noprefix", i, j)
i = j
continue
label = get_quoted_value(document.body, "reference", i, j)
if not label:
document.warning("Can't find label for reference at line %d!" %(i))
i = j + 1
continue
try:
(prefix, suffix) = label.split(":", 1)
except:
document.warning("No `:' separator in formatted reference at line %d!" % (i))
# we'll leave this as an ordinary labelonly reference
del_token(document.body, "noprefix", i, j)
i = j
continue
document.body[i:j+1] = put_cmd_in_ert([suffix])
i += 1
def revert_biblatex(document):
" Revert biblatex support "
#
# Header
#
# 1. Get cite engine
engine = "basic"
i = find_token(document.header, "\\cite_engine", 0)
if i == -1:
document.warning("Malformed document! Missing \\cite_engine")
else:
engine = get_value(document.header, "\\cite_engine", i)
# 2. Store biblatex state and revert to natbib
biblatex = False
if engine in ["biblatex", "biblatex-natbib"]:
biblatex = True
document.header[i] = "\\cite_engine natbib"
# 3. Store and remove new document headers
bibstyle = ""
i = find_token(document.header, "\\biblatex_bibstyle", 0)
if i != -1:
bibstyle = get_value(document.header, "\\biblatex_bibstyle", i)
del document.header[i]
citestyle = ""
i = find_token(document.header, "\\biblatex_citestyle", 0)
if i != -1:
citestyle = get_value(document.header, "\\biblatex_citestyle", i)
del document.header[i]
biblio_options = ""
i = find_token(document.header, "\\biblio_options", 0)
if i != -1:
biblio_options = get_value(document.header, "\\biblio_options", i)
del document.header[i]
if biblatex:
bbxopts = "[natbib=true"
if bibstyle != "":
bbxopts += ",bibstyle=" + bibstyle
if citestyle != "":
bbxopts += ",citestyle=" + citestyle
if biblio_options != "":
bbxopts += "," + biblio_options
bbxopts += "]"
add_to_preamble(document, "\\usepackage" + bbxopts + "{biblatex}")
#
# Body
#
# 1. Bibtex insets
i = 0
bibresources = []
while (True):
i = find_token(document.body, "\\begin_inset CommandInset bibtex", i)
if i == -1:
break
j = find_end_of_inset(document.body, i)
if j == -1:
document.warning("Can't find end of bibtex inset at line %d!!" %(i))
i += 1
continue
bibs = get_quoted_value(document.body, "bibfiles", i, j)
opts = get_quoted_value(document.body, "biblatexopts", i, j)
# store resources
if bibs:
bibresources += bibs.split(",")
else:
document.warning("Can't find bibfiles for bibtex inset at line %d!" %(i))
# remove biblatexopts line
k = find_token(document.body, "biblatexopts", i, j)
if k != -1:
del document.body[k]
# Re-find inset end line
j = find_end_of_inset(document.body, i)
# Insert ERT \\printbibliography and wrap bibtex inset to a Note
if biblatex:
pcmd = "printbibliography"
if opts:
pcmd += "[" + opts + "]"
repl = ["\\begin_inset ERT", "status open", "", "\\begin_layout Plain Layout",\
"", "", "\\backslash", pcmd, "\\end_layout", "", "\\end_inset", "", "",\
"\\end_layout", "", "\\begin_layout Standard", "\\begin_inset Note Note",\
"status open", "", "\\begin_layout Plain Layout" ]
repl += document.body[i:j+1]
repl += ["", "\\end_layout", "", "\\end_inset", "", ""]
document.body[i:j+1] = repl
j += 27
i = j + 1
if biblatex:
for b in bibresources:
add_to_preamble(document, "\\addbibresource{" + b + ".bib}")
# 2. Citation insets
# Specific citation insets used in biblatex that need to be reverted to ERT
new_citations = {
"Cite" : "Cite",
"citebyear" : "citeyear",
"citeyear" : "cite*",
"Footcite" : "Smartcite",
"footcite" : "smartcite",
"Autocite" : "Autocite",
"autocite" : "autocite",
"citetitle" : "citetitle",
"citetitle*" : "citetitle*",
"fullcite" : "fullcite",
"footfullcite" : "footfullcite",
"supercite" : "supercite",
"citeauthor" : "citeauthor",
"citeauthor*" : "citeauthor*",
"Citeauthor" : "Citeauthor",
"Citeauthor*" : "Citeauthor*"
}
# All commands accepted by LyX < 2.3. Everything else throws an error.
old_citations = [ "cite", "nocite", "citet", "citep", "citealt", "citealp",\
"citeauthor", "citeyear", "citeyearpar", "citet*", "citep*",\
"citealt*", "citealp*", "citeauthor*", "Citet", "Citep",\
"Citealt", "Citealp", "Citeauthor", "Citet*", "Citep*",\
"Citealt*", "Citealp*", "Citeauthor*", "fullcite", "footcite",\
"footcitet", "footcitep", "footcitealt", "footcitealp",\
"footciteauthor", "footciteyear", "footciteyearpar",\
"citefield", "citetitle", "cite*" ]
i = 0
while (True):
i = find_token(document.body, "\\begin_inset CommandInset citation", i)
if i == -1:
break
j = find_end_of_inset(document.body, i)
if j == -1:
document.warning("Can't find end of citation inset at line %d!!" %(i))
i += 1
continue
k = find_token(document.body, "LatexCommand", i, j)
if k == -1:
document.warning("Can't find LatexCommand for citation inset at line %d!" %(i))
i = j + 1
continue
cmd = get_value(document.body, "LatexCommand", k)
if biblatex and cmd in list(new_citations.keys()):
pre = get_quoted_value(document.body, "before", i, j)
post = get_quoted_value(document.body, "after", i, j)
key = get_quoted_value(document.body, "key", i, j)
if not key:
document.warning("Citation inset at line %d does not have a key!" %(i))
key = "???"
# Replace known new commands with ERT
res = "\\" + new_citations[cmd]
if pre:
res += "[" + pre + "]"
if post:
res += "[" + post + "]"
elif pre:
res += "[]"
res += "{" + key + "}"
document.body[i:j+1] = put_cmd_in_ert([res])
elif cmd not in old_citations:
# Reset unknown commands to cite. This is what LyX does as well
# (but LyX 2.2 would break on unknown commands)
document.body[k] = "LatexCommand cite"
document.warning("Reset unknown cite command '%s' with cite" % cmd)
i = j + 1
# Emulate the old biblatex-workaround (pretend natbib in order to use the styles)
if biblatex:
i = find_token(document.header, "\\begin_local_layout", 0)
if i == -1:
k = find_token(document.header, "\\language", 0)
if k == -1:
# this should not happen
document.warning("Malformed LyX document! No \\language header found!")
return
document.header[k-1 : k-1] = ["\\begin_local_layout", "\\end_local_layout"]
i = k-1
j = find_end_of(document.header, i, "\\begin_local_layout", "\\end_local_layout")
if j == -1:
# this should not happen
document.warning("Malformed LyX document! Can't find end of local layout!")
return
document.header[i+1 : i+1] = [
"### Inserted by lyx2lyx (biblatex emulation) ###",
"Provides natbib 1",
"### End of insertion by lyx2lyx (biblatex emulation) ###"
]
def revert_citekeyonly(document):
" Revert keyonly cite command to ERT "
i = 0
while (True):
i = find_token(document.body, "\\begin_inset CommandInset citation", i)
if i == -1:
break
j = find_end_of_inset(document.body, i)
if j == -1:
document.warning("Can't find end of citation inset at line %d!!" %(i))
i += 1
continue
k = find_token(document.body, "LatexCommand", i, j)
if k == -1:
document.warning("Can't find LatexCommand for citation inset at line %d!" %(i))
i = j + 1
continue
cmd = get_value(document.body, "LatexCommand", k)
if cmd != "keyonly":
i = j + 1
continue
key = get_quoted_value(document.body, "key", i, j)
if not key:
document.warning("Citation inset at line %d does not have a key!" %(i))
# Replace known new commands with ERT
document.body[i:j+1] = put_cmd_in_ert([key])
i = j + 1
def revert_bibpackopts(document):
" Revert support for natbib/jurabib package options "
engine = "basic"
i = find_token(document.header, "\\cite_engine", 0)
if i == -1:
document.warning("Malformed document! Missing \\cite_engine")
else:
engine = get_value(document.header, "\\cite_engine", i)
biblatex = False
if engine not in ["natbib", "jurabib"]:
return
i = find_token(document.header, "\\biblio_options", 0)
if i == -1:
# Nothing to do if we have no options
return
biblio_options = get_value(document.header, "\\biblio_options", i)
del document.header[i]
if not biblio_options:
# Nothing to do for empty options
return
i = find_token(document.header, "\\begin_local_layout", 0)
if i == -1:
k = find_token(document.header, "\\language", 0)
if k == -1:
# this should not happen
document.warning("Malformed LyX document! No \\language header found!")
return
document.header[k-1 : k-1] = ["\\begin_local_layout", "\\end_local_layout"]
i = k - 1
j = find_end_of(document.header, i, "\\begin_local_layout", "\\end_local_layout")
if j == -1:
# this should not happen
document.warning("Malformed LyX document! Can't find end of local layout!")
return
document.header[i+1 : i+1] = [
"### Inserted by lyx2lyx (bibliography package options) ###",
"PackageOptions " + engine + " " + biblio_options,
"### End of insertion by lyx2lyx (bibliography package options) ###"
]
def revert_qualicites(document):
" Revert qualified citation list commands to ERT "
# Citation insets that support qualified lists, with their LaTeX code
ql_citations = {
"cite" : "cites",
"Cite" : "Cites",
"citet" : "textcites",
"Citet" : "Textcites",
"citep" : "parencites",
"Citep" : "Parencites",
"Footcite" : "Smartcites",
"footcite" : "smartcites",
"Autocite" : "Autocites",
"autocite" : "autocites",
}
# Get cite engine
engine = "basic"
i = find_token(document.header, "\\cite_engine", 0)
if i == -1:
document.warning("Malformed document! Missing \\cite_engine")
else:
engine = get_value(document.header, "\\cite_engine", i)
biblatex = engine in ["biblatex", "biblatex-natbib"]
i = 0
while (True):
i = find_token(document.body, "\\begin_inset CommandInset citation", i)
if i == -1:
break
j = find_end_of_inset(document.body, i)
if j == -1:
document.warning("Can't find end of citation inset at line %d!!" %(i))
i += 1
continue
pres = find_token(document.body, "pretextlist", i, j)
posts = find_token(document.body, "posttextlist", i, j)
if pres == -1 and posts == -1:
# nothing to do.
i = j + 1
continue
pretexts = get_quoted_value(document.body, "pretextlist", pres)
posttexts = get_quoted_value(document.body, "posttextlist", posts)
k = find_token(document.body, "LatexCommand", i, j)
if k == -1:
document.warning("Can't find LatexCommand for citation inset at line %d!" %(i))
i = j + 1
continue
cmd = get_value(document.body, "LatexCommand", k)
if biblatex and cmd in list(ql_citations.keys()):
pre = get_quoted_value(document.body, "before", i, j)
post = get_quoted_value(document.body, "after", i, j)
key = get_quoted_value(document.body, "key", i, j)
if not key:
document.warning("Citation inset at line %d does not have a key!" %(i))
key = "???"
keys = key.split(",")
prelist = pretexts.split("\t")
premap = dict()
for pp in prelist:
ppp = pp.split(" ", 1)
premap[ppp[0]] = ppp[1]
postlist = posttexts.split("\t")
postmap = dict()
for pp in postlist:
ppp = pp.split(" ", 1)
postmap[ppp[0]] = ppp[1]
# Replace known new commands with ERT
if "(" in pre or ")" in pre:
pre = "{" + pre + "}"
if "(" in post or ")" in post:
post = "{" + post + "}"
res = "\\" + ql_citations[cmd]
if pre:
res += "(" + pre + ")"
if post:
res += "(" + post + ")"
elif pre:
res += "()"
for kk in keys:
if premap.get(kk, "") != "":
res += "[" + premap[kk] + "]"
if postmap.get(kk, "") != "":
res += "[" + postmap[kk] + "]"
elif premap.get(kk, "") != "":
res += "[]"
res += "{" + kk + "}"
document.body[i:j+1] = put_cmd_in_ert([res])
else:
# just remove the params
del document.body[posttexts]
del document.body[pretexts]
i += 1
command_insets = ["bibitem", "citation", "href", "index_print", "nomenclature"]
def convert_literalparam(document):
" Add param literal "
for inset in command_insets:
i = 0
while True:
i = find_token(document.body, '\\begin_inset CommandInset %s' % inset, i)
if i == -1:
break
j = find_end_of_inset(document.body, i)
if j == -1:
document.warning("Malformed LyX document: Can't find end of %s inset at line %d" % (inset, i))
i += 1
continue
while i < j and document.body[i].strip() != '':
i += 1
# href is already fully latexified. Here we can switch off literal.
if inset == "href":
document.body.insert(i, "literal \"false\"")
else:
document.body.insert(i, "literal \"true\"")
def revert_literalparam(document):
" Remove param literal "
for inset in command_insets:
i = 0
while True:
i = find_token(document.body, '\\begin_inset CommandInset %s' % inset, i)
if i == -1:
break
j = find_end_of_inset(document.body, i)
if j == -1:
document.warning("Malformed LyX document: Can't find end of %s inset at line %d" % (inset, i))
i += 1
continue
k = find_token(document.body, 'literal', i, j)
if k == -1:
i += 1
continue
del document.body[k]
def revert_multibib(document):
" Revert multibib support "
# 1. Get cite engine
engine = "basic"
i = find_token(document.header, "\\cite_engine", 0)
if i == -1:
document.warning("Malformed document! Missing \\cite_engine")
else:
engine = get_value(document.header, "\\cite_engine", i)
# 2. Do we use biblatex?
biblatex = False
if engine in ["biblatex", "biblatex-natbib"]:
biblatex = True
# 3. Store and remove multibib document header
multibib = ""
i = find_token(document.header, "\\multibib", 0)
if i != -1:
multibib = get_value(document.header, "\\multibib", i)
del document.header[i]
if not multibib:
return
# 4. The easy part: Biblatex
if biblatex:
i = find_token(document.header, "\\biblio_options", 0)
if i == -1:
k = find_token(document.header, "\\use_bibtopic", 0)
if k == -1:
# this should not happen
document.warning("Malformed LyX document! No \\use_bibtopic header found!")
return
document.header[k-1 : k-1] = ["\\biblio_options " + "refsection=" + multibib]
else:
biblio_options = get_value(document.header, "\\biblio_options", i)
if biblio_options:
biblio_options += ","
biblio_options += "refsection=" + multibib
document.header[i] = "\\biblio_options " + biblio_options
# Bibtex insets
i = 0
while (True):
i = find_token(document.body, "\\begin_inset CommandInset bibtex", i)
if i == -1:
break
j = find_end_of_inset(document.body, i)
if j == -1:
document.warning("Can't find end of bibtex inset at line %d!!" %(i))
i += 1
continue
btprint = get_quoted_value(document.body, "btprint", i, j)
if btprint != "bibbysection":
i += 1
continue
opts = get_quoted_value(document.body, "biblatexopts", i, j)
# change btprint line
k = find_token(document.body, "btprint", i, j)
if k != -1:
document.body[k] = "btprint \"btPrintCited\""
# Insert ERT \\bibbysection and wrap bibtex inset to a Note
pcmd = "bibbysection"
if opts:
pcmd += "[" + opts + "]"
repl = ["\\begin_inset ERT", "status open", "", "\\begin_layout Plain Layout",\
"", "", "\\backslash", pcmd, "\\end_layout", "", "\\end_inset", "", "",\
"\\end_layout", "", "\\begin_layout Standard", "\\begin_inset Note Note",\
"status open", "", "\\begin_layout Plain Layout" ]
repl += document.body[i:j+1]
repl += ["", "\\end_layout", "", "\\end_inset", "", ""]
document.body[i:j+1] = repl
j += 27
i = j + 1
return
# 5. More tricky: Bibtex/Bibtopic
k = find_token(document.header, "\\use_bibtopic", 0)
if k == -1:
# this should not happen
document.warning("Malformed LyX document! No \\use_bibtopic header found!")
return
document.header[k] = "\\use_bibtopic true"
# Possible units. This assumes that the LyX name follows the std,
# which might not always be the case. But it's as good as we can get.
units = {
"part" : "Part",
"chapter" : "Chapter",
"section" : "Section",
"subsection" : "Subsection",
}
if multibib not in units.keys():
document.warning("Unknown multibib value `%s'!" % nultibib)
return
unit = units[multibib]
btunit = False
i = 0
while (True):
i = find_token(document.body, "\\begin_layout " + unit, i)
if i == -1:
break
if btunit:
document.body[i-1 : i-1] = ["\\begin_layout Standard",
"\\begin_inset ERT", "status open", "",
"\\begin_layout Plain Layout", "", "",
"\\backslash",
"end{btUnit}", "\\end_layout",
"\\begin_layout Plain Layout", "",
"\\backslash",
"begin{btUnit}"
"\\end_layout", "", "\\end_inset", "", "",
"\\end_layout", ""]
i += 21
else:
document.body[i-1 : i-1] = ["\\begin_layout Standard",
"\\begin_inset ERT", "status open", "",
"\\begin_layout Plain Layout", "", "",
"\\backslash",
"begin{btUnit}"
"\\end_layout", "", "\\end_inset", "", "",
"\\end_layout", ""]
i += 16
btunit = True
i += 1
if btunit:
i = find_token(document.body, "\\end_body", i)
document.body[i-1 : i-1] = ["\\begin_layout Standard",
"\\begin_inset ERT", "status open", "",
"\\begin_layout Plain Layout", "", "",
"\\backslash",
"end{btUnit}"
"\\end_layout", "", "\\end_inset", "", "",
"\\end_layout", ""]
def revert_chapterbib(document):
" Revert chapterbib support "
# 1. Get cite engine
engine = "basic"
i = find_token(document.header, "\\cite_engine", 0)
if i == -1:
document.warning("Malformed document! Missing \\cite_engine")
else:
engine = get_value(document.header, "\\cite_engine", i)
# 2. Do we use biblatex?
biblatex = False
if engine in ["biblatex", "biblatex-natbib"]:
biblatex = True
# 3. Store multibib document header value
multibib = ""
i = find_token(document.header, "\\multibib", 0)
if i != -1:
multibib = get_value(document.header, "\\multibib", i)
if not multibib or multibib != "child":
# nothing to do
return
# 4. remove multibib header
del document.header[i]
# 5. Biblatex
if biblatex:
# find include insets
i = 0
while (True):
i = find_token(document.body, "\\begin_inset CommandInset include", i)
if i == -1:
break
j = find_end_of_inset(document.body, i)
if j == -1:
document.warning("Can't find end of bibtex inset at line %d!!" %(i))
i += 1
continue
parent = get_containing_layout(document.body, i)
parbeg = parent[1]
# Insert ERT \\newrefsection before inset
beg = ["\\begin_layout Standard",
"\\begin_inset ERT", "status open", "",
"\\begin_layout Plain Layout", "", "",
"\\backslash",
"newrefsection"
"\\end_layout", "", "\\end_inset", "", "",
"\\end_layout", ""]
document.body[parbeg-1:parbeg-1] = beg
j += len(beg)
i = j + 1
return
# 6. Bibtex/Bibtopic
i = find_token(document.header, "\\use_bibtopic", 0)
if i == -1:
# this should not happen
document.warning("Malformed LyX document! No \\use_bibtopic header found!")
return
if get_value(document.header, "\\use_bibtopic", i) == "true":
# find include insets
i = 0
while (True):
i = find_token(document.body, "\\begin_inset CommandInset include", i)
if i == -1:
break
j = find_end_of_inset(document.body, i)
if j == -1:
document.warning("Can't find end of bibtex inset at line %d!!" %(i))
i += 1
continue
parent = get_containing_layout(document.body, i)
parbeg = parent[1]
parend = parent[2]
# Insert wrap inset into \\begin{btUnit}...\\end{btUnit}
beg = ["\\begin_layout Standard",
"\\begin_inset ERT", "status open", "",
"\\begin_layout Plain Layout", "", "",
"\\backslash",
"begin{btUnit}"
"\\end_layout", "", "\\end_inset", "", "",
"\\end_layout", ""]
end = ["\\begin_layout Standard",
"\\begin_inset ERT", "status open", "",
"\\begin_layout Plain Layout", "", "",
"\\backslash",
"end{btUnit}"
"\\end_layout", "", "\\end_inset", "", "",
"\\end_layout", ""]
document.body[parend+1:parend+1] = end
document.body[parbeg-1:parbeg-1] = beg
j += len(beg) + len(end)
i = j + 1
return
# 7. Chapterbib proper
add_to_preamble(document, ["\\usepackage{chapterbib}"])
def convert_dashligatures(document):
"Set 'use_dash_ligatures' according to content."
use_dash_ligatures = None
# eventually remove preamble code from 2.3->2.2 conversion:
for i, line in enumerate(document.preamble):
if i > 1 and line == r'\renewcommand{\textemdash}{---}':
if (document.preamble[i-1] == r'\renewcommand{\textendash}{--}'
and document.preamble[i-2] == '% Added by lyx2lyx'):
del document.preamble[i-2:i+1]
use_dash_ligatures = True
if use_dash_ligatures is None:
# Look for dashes:
# (Documents by LyX 2.1 or older have "\twohyphens\n" or "\threehyphens\n"
# as interim representation for dash ligatures in 2.2.)
has_literal_dashes = False
has_ligature_dashes = False
j = 0
for i, line in enumerate(document.body):
# Skip some document parts where dashes are not converted
if (i < j) or line.startswith("\\labelwidthstring"):
continue
words = line.split()
if len(words) > 1 and words[0] == "\\begin_inset" and \
words[1] in ["CommandInset", "ERT", "External", "Formula",
"FormulaMacro", "Graphics", "IPA", "listings"]:
j = find_end_of_inset(document.body, i)
if j == -1:
document.warning("Malformed LyX document: "
"Can't find end of %s inset at line %d" % (words[1],i))
continue
# literal dash followed by a word or no-break space:
if re.search(u"[\u2013\u2014]([\w\u00A0]|$)", line,
flags=re.UNICODE):
has_literal_dashes = True
# ligature dash followed by word or no-break space on next line:
if re.search(u"(\\\\twohyphens|\\\\threehyphens)", line,
flags=re.UNICODE) and re.match(u"[\w\u00A0]",
document.body[i+1], flags=re.UNICODE):
has_ligature_dashes = True
if has_literal_dashes and has_ligature_dashes:
# TODO: insert a warning note in the document?
document.warning('This document contained both literal and '
'"ligature" dashes.\n Line breaks may have changed. '
'See UserGuide chapter 3.9.1 for details.')
elif has_literal_dashes:
use_dash_ligatures = False
elif has_ligature_dashes:
use_dash_ligatures = True
# insert the setting if there is a preferred value
if use_dash_ligatures is not None:
i = find_token(document.header, "\\use_microtype", 0)
if i != -1:
document.header.insert(i+1, "\\use_dash_ligatures %s"
% str(use_dash_ligatures).lower())
def revert_dashligatures(document):
"""Remove font ligature settings for en- and em-dashes.
Revert conversion of \twodashes or \threedashes to literal dashes."""
i = find_token(document.header, "\\use_dash_ligatures", 0)
if i == -1:
return
use_dash_ligatures = get_bool_value(document.header, "\\use_dash_ligatures", i)
del document.header[i]
use_non_tex_fonts = False
i = find_token(document.header, "\\use_non_tex_fonts", 0)
if i != -1:
use_non_tex_fonts = get_bool_value(document.header, "\\use_non_tex_fonts", i)
if not use_dash_ligatures or document.backend != "latex":
return
j = 0
new_body = []
for i, line in enumerate(document.body):
# Skip some document parts where dashes are not converted
if (i < j) or line.startswith("\\labelwidthstring"):
new_body.append(line)
continue
words = line.split()
if len(words) > 1 and words[0] == "\\begin_inset" and \
words[1] in ["CommandInset", "ERT", "External", "Formula",
"FormulaMacro", "Graphics", "IPA", "listings"]:
j = find_end_of_inset(document.body, i)
if j == -1:
document.warning("Malformed LyX document: Can't find end of "
+ words[1] + " inset at line " + str(i))
new_body.append(line)
continue
line = line.replace(u'\u2013', '\\twohyphens\n')
line = line.replace(u'\u2014', '\\threehyphens\n')
lines = line.split('\n')
new_body.extend(line.split('\n'))
document.body = new_body
# redefine the dash LICRs to use ligature dashes:
add_to_preamble(document, [r'\renewcommand{\textendash}{--}',
r'\renewcommand{\textemdash}{---}'])
def revert_noto(document):
" Revert Noto font definitions to LaTeX "
if find_token(document.header, "\\use_non_tex_fonts false", 0) != -1:
preamble = ""
i = find_token(document.header, "\\font_roman \"NotoSerif-TLF\"", 0)
if i != -1:
add_to_preamble(document, ["\\renewcommand{\\rmdefault}{NotoSerif-TLF}"])
document.header[i] = document.header[i].replace("NotoSerif-TLF", "default")
i = find_token(document.header, "\\font_sans \"NotoSans-TLF\"", 0)
if i != -1:
add_to_preamble(document, ["\\renewcommand{\\sfdefault}{NotoSans-TLF}"])
document.header[i] = document.header[i].replace("NotoSans-TLF", "default")
i = find_token(document.header, "\\font_typewriter \"NotoMono-TLF\"", 0)
if i != -1:
add_to_preamble(document, ["\\renewcommand{\\ttdefault}{NotoMono-TLF}"])
document.header[i] = document.header[i].replace("NotoMono-TLF", "default")
def revert_xout(document):
" Reverts \\xout font attribute "
changed = revert_font_attrs(document.body, "\\xout", "\\xout")
if changed == True:
insert_to_preamble(document, \
['% for proper cross-out',
'\\PassOptionsToPackage{normalem}{ulem}',
'\\usepackage{ulem}'])
def convert_mathindent(document):
" add the \\is_math_indent tag "
# check if the document uses the class option "fleqn"
k = find_token(document.header, "\\quotes_style", 0)
regexp = re.compile(r'^.*fleqn.*')
i = find_re(document.header, regexp, 0)
if i != -1:
document.header.insert(k, "\\is_math_indent 1")
# delete the found option
document.header[i] = document.header[i].replace(",fleqn", "")
document.header[i] = document.header[i].replace(", fleqn", "")
document.header[i] = document.header[i].replace("fleqn,", "")
j = find_re(document.header, regexp, 0)
if i == j:
# then we have fleqn as the only option
del document.header[i]
else:
document.header.insert(k, "\\is_math_indent 0")
def revert_mathindent(document):
" Define mathindent if set in the document "
# first output the length
regexp = re.compile(r'(\\math_indentation)')
i = find_re(document.header, regexp, 0)
if i != -1:
value = get_value(document.header, "\\math_indentation" , i).split()[0]
if value != "default":
add_to_preamble(document, ["\\setlength{\\mathindent}{" + value + '}'])
del document.header[i]
# now set the document class option
regexp = re.compile(r'(\\is_math_indent 1)')
i = find_re(document.header, regexp, 0)
if i == -1:
regexp = re.compile(r'(\\is_math_indent)')
j = find_re(document.header, regexp, 0)
del document.header[j]
else:
k = find_token(document.header, "\\options", 0)
if k != -1:
document.header[k] = document.header[k].replace("\\options", "\\options fleqn,")
del document.header[i]
else:
l = find_token(document.header, "\\use_default_options", 0)
document.header.insert(l, "\\options fleqn")
del document.header[i + 1]
def revert_baselineskip(document):
" Revert baselineskips to TeX code "
i = 0
vspaceLine = 0
hspaceLine = 0
while True:
regexp = re.compile(r'^.*baselineskip%.*$')
i = find_re(document.body, regexp, i)
if i == -1:
return
vspaceLine = find_token(document.body, "\\begin_inset VSpace", i)
if vspaceLine == i:
# output VSpace inset as TeX code
# first read out the values
beg = document.body[i].rfind("VSpace ");
end = document.body[i].rfind("baselineskip%");
baselineskip = float(document.body[i][beg + 7:end]);
# we store the value in percent, thus divide by 100
baselineskip = baselineskip/100;
baselineskip = str(baselineskip);
# check if it is the starred version
if document.body[i].find('*') != -1:
star = '*'
else:
star = ''
# now output TeX code
endInset = find_end_of_inset(document.body, i)
if endInset == -1:
document.warning("Malformed LyX document: Missing '\\end_inset' of VSpace inset.")
return
else:
document.body[vspaceLine: endInset + 1] = put_cmd_in_ert("\\vspace" + star + '{' + baselineskip + "\\baselineskip}")
hspaceLine = find_token(document.body, "\\begin_inset space \\hspace", i - 1)
document.warning("hspaceLine: " + str(hspaceLine))
document.warning("i: " + str(i))
if hspaceLine == i - 1:
# output space inset as TeX code
# first read out the values
beg = document.body[i].rfind("\\length ");
end = document.body[i].rfind("baselineskip%");
baselineskip = float(document.body[i][beg + 7:end]);
document.warning("baselineskip: " + str(baselineskip))
# we store the value in percent, thus divide by 100
baselineskip = baselineskip/100;
baselineskip = str(baselineskip);
# check if it is the starred version
if document.body[i-1].find('*') != -1:
star = '*'
else:
star = ''
# now output TeX code
endInset = find_end_of_inset(document.body, i)
if endInset == -1:
document.warning("Malformed LyX document: Missing '\\end_inset' of space inset.")
return
else:
document.body[hspaceLine: endInset + 1] = put_cmd_in_ert("\\hspace" + star + '{' + baselineskip + "\\baselineskip}")
i = i + 1
def revert_rotfloat(document):
" Revert placement options for rotated floats "
i = 0
j = 0
k = 0
while True:
i = find_token(document.body, "sideways true", i)
if i != -1:
regexp = re.compile(r'^.*placement.*$')
j = find_re(document.body, regexp, i-2)
if j == -1:
return
if j != i-2:
i = i + 1
continue
else:
return
# we found a sideways float with placement options
# at first store the placement
beg = document.body[i-2].rfind(" ");
placement = document.body[i-2][beg+1:]
# check if the option'H' is used
if placement.find("H") != -1:
add_to_preamble(document, ["\\usepackage{float}"])
# now check if it is a starred type
if document.body[i-1].find("wide true") != -1:
star = '*'
else:
star = ''
# store the float type
beg = document.body[i-3].rfind(" ");
fType = document.body[i-3][beg+1:]
# now output TeX code
endInset = find_end_of_inset(document.body, i-3)
if endInset == -1:
document.warning("Malformed LyX document: Missing '\\end_inset' of Float inset.")
return
else:
document.body[endInset-2: endInset+1] = put_cmd_in_ert("\\end{sideways" + fType + star + '}')
document.body[i-3: i+2] = put_cmd_in_ert("\\begin{sideways" + fType + star + "}[" + placement + ']')
add_to_preamble(document, ["\\usepackage{rotfloat}"])
i = i + 1
def convert_allowbreak(document):
" Zero widths Space-inset -> \SpecialChar allowbreak. "
body = "\n".join(document.body)
body = body.replace("\\begin_inset space \hspace{}\n"
"\\length 0dd\n"
"\\end_inset\n\n",
"\\SpecialChar allowbreak\n")
document.body = body.split("\n")
def revert_allowbreak(document):
" \SpecialChar allowbreak -> Zero widths Space-inset. "
body = "\n".join(document.body)
body = body.replace("\\SpecialChar allowbreak\n",
"\\begin_inset space \hspace{}\n"
"\\length 0dd\n"
"\\end_inset\n\n")
document.body = body.split("\n")
def convert_mathnumberpos(document):
" add the \\math_number_before tag "
# check if the document uses the class option "leqno"
k = find_token(document.header, "\\quotes_style", 0)
m = find_token(document.header, "\\options", 0)
regexp = re.compile(r'^.*leqno.*')
i = find_re(document.header, regexp, 0)
if i != -1 and i == m:
document.header.insert(k, "\\math_number_before 1")
# delete the found option
document.header[i] = document.header[i].replace(",leqno", "")
document.header[i] = document.header[i].replace(", leqno", "")
document.header[i] = document.header[i].replace("leqno,", "")
j = find_re(document.header, regexp, 0)
if i == j:
# then we have leqno as the only option
del document.header[i]
else:
document.header.insert(k, "\\math_number_before 0")
def revert_mathnumberpos(document):
" add the document class option leqno"
regexp = re.compile(r'(\\math_number_before 1)')
i = find_re(document.header, regexp, 0)
if i == -1:
regexp = re.compile(r'(\\math_number_before)')
j = find_re(document.header, regexp, 0)
del document.header[j]
else:
k = find_token(document.header, "\\options", 0)
if k != -1:
document.header[k] = document.header[k].replace("\\options", "\\options leqno,")
del document.header[i]
else:
l = find_token(document.header, "\\use_default_options", 0)
document.header.insert(l, "\\options leqno")
del document.header[i + 1]
def convert_mathnumberingname(document):
" rename the \\math_number_before tag to \\math_numbering_side "
regexp = re.compile(r'(\\math_number_before 1)')
i = find_re(document.header, regexp, 0)
if i != -1:
document.header[i] = "\\math_numbering_side left"
regexp = re.compile(r'(\\math_number_before 0)')
i = find_re(document.header, regexp, 0)
if i != -1:
document.header[i] = "\\math_numbering_side default"
# check if the document uses the class option "reqno"
k = find_token(document.header, "\\math_numbering_side", 0)
m = find_token(document.header, "\\options", 0)
regexp = re.compile(r'^.*reqno.*')
i = find_re(document.header, regexp, 0)
if i != -1 and i == m:
document.header[k] = "\\math_numbering_side right"
# delete the found option
document.header[i] = document.header[i].replace(",reqno", "")
document.header[i] = document.header[i].replace(", reqno", "")
document.header[i] = document.header[i].replace("reqno,", "")
j = find_re(document.header, regexp, 0)
if i == j:
# then we have reqno as the only option
del document.header[i]
def revert_mathnumberingname(document):
" rename the \\math_numbering_side tag back to \\math_number_before "
# just rename
regexp = re.compile(r'(\\math_numbering_side left)')
i = find_re(document.header, regexp, 0)
if i != -1:
document.header[i] = "\\math_number_before 1"
# add the option reqno and delete the tag
regexp = re.compile(r'(\\math_numbering_side right)')
i = find_re(document.header, regexp, 0)
if i != -1:
document.header[i] = "\\math_number_before 0"
k = find_token(document.header, "\\options", 0)
if k != -1:
document.header[k] = document.header[k].replace("\\options", "\\options reqno,")
else:
l = find_token(document.header, "\\use_default_options", 0)
document.header.insert(l, "\\options reqno")
# add the math_number_before tag
regexp = re.compile(r'(\\math_numbering_side default)')
i = find_re(document.header, regexp, 0)
if i != -1:
document.header[i] = "\\math_number_before 0"
def convert_minted(document):
" add the \\use_minted tag "
document.header.insert(-1, "\\use_minted 0")
def revert_minted(document):
" remove the \\use_minted tag "
i = find_token(document.header, "\\use_minted", 0)
if i != -1:
document.header.pop(i)
##
# Conversion hub
#
supported_versions = ["2.3.0", "2.3"]
convert = [
[509, [convert_microtype]],
[510, [convert_dateinset]],
[511, [convert_ibranches]],
[512, [convert_beamer_article_styles]],
[513, []],
[514, []],
[515, []],
[516, [convert_inputenc]],
[517, []],
[518, [convert_iopart]],
[519, [convert_quotestyle]],
[520, []],
[521, [convert_frenchquotes]],
[522, []],
[523, []],
[524, []],
[525, []],
[526, []],
[527, []],
[528, []],
[529, []],
[530, []],
[531, []],
[532, [convert_literalparam]],
[533, []],
[534, []],
[535, [convert_dashligatures]],
[536, []],
[537, []],
[538, [convert_mathindent]],
[539, []],
[540, []],
[541, [convert_allowbreak]],
[542, [convert_mathnumberpos]],
[543, [convert_mathnumberingname]],
[544, [convert_minted]]
]
revert = [
[543, [revert_minted]],
[542, [revert_mathnumberingname]],
[541, [revert_mathnumberpos]],
[540, [revert_allowbreak]],
[539, [revert_rotfloat]],
[538, [revert_baselineskip]],
[537, [revert_mathindent]],
[536, [revert_xout]],
[535, [revert_noto]],
[534, [revert_dashligatures]],
[533, [revert_chapterbib]],
[532, [revert_multibib]],
[531, [revert_literalparam]],
[530, [revert_qualicites]],
[529, [revert_bibpackopts]],
[528, [revert_citekeyonly]],
[527, [revert_biblatex]],
[526, [revert_noprefix]],
[525, [revert_plural_refs]],
[524, [revert_labelonly]],
[523, [revert_crimson, revert_cochinealmath]],
[522, [revert_cjkquotes]],
[521, [revert_dynamicquotes]],
[520, [revert_britishquotes, revert_swedishgquotes, revert_frenchquotes, revert_frenchinquotes, revert_russianquotes, revert_swissquotes]],
[519, [revert_plainquote]],
[518, [revert_quotestyle]],
[517, [revert_iopart]],
[516, [revert_quotes]],
[515, []],
[514, [revert_urdu, revert_syriac]],
[513, [revert_amharic, revert_asturian, revert_kannada, revert_khmer]],
[512, [revert_bosnian, revert_friulan, revert_macedonian, revert_piedmontese, revert_romansh]],
[511, [revert_beamer_article_styles]],
[510, [revert_ibranches]],
[509, []],
[508, [revert_microtype]]
]
if __name__ == "__main__":
pass