# This file is part of lyx2lyx
-# -*- coding: iso-8859-1 -*-
-# Copyright (C) 2002-2004 Dekel Tsur <dekel@lyx.org>, José Matos <jamatos@lyx.org>
+# -*- coding: utf-8 -*-
+# Copyright (C) 2002-2018 The LyX Team
+# Copyright (C) 2002-2004 Dekel Tsur <dekel@lyx.org>
+# Copyright (C) 2002-2006 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
#
# 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
-from parser_tools import get_value, check_token, find_token,\
- find_tokens, find_end_of, find_end_of_inset
+" The LyX module has all the rules related with different lyx file formats."
+
+from parser_tools import (get_value, check_token, find_token, find_tokens,
+ find_end_of, find_complete_lines)
import os.path
import gzip
+import locale
import sys
import re
-import string
import time
+import io
+import codecs
+
+try:
+ import lyx2lyx_version
+ version__ = lyx2lyx_version.version
+ stable_version = True
+except: # we are running from build directory so assume the last version
+ version__ = '2.4'
+ stable_version = False
+
+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
+
+def find_end_of_inset(lines, i):
+ " Find beginning of inset, where lines[i] is included."
+ return find_end_of(lines, i, "\\begin_inset", "\\end_inset")
+
+def minor_versions(major, last_minor_version):
+ """ Generate minor versions, using major as prefix and minor
+ versions from 0 until last_minor_version, plus the generic version.
-import lyx2lyx_version
-version_lyx2lyx = lyx2lyx_version.version
+ Example:
+
+ minor_versions("1.2", 4) ->
+ [ "1.2", "1.2.0", "1.2.1", "1.2.2", "1.2.3"]
+ """
+ return [major] + [major + ".%d" % i for i in range(last_minor_version + 1)]
+
+
+# End of helper functions
+####################################################################
-default_debug_level = 2
# Regular expressions used
format_re = re.compile(r"(\d)[\.,]?(\d\d)")
fileformat = re.compile(r"\\lyxformat\s*(\S*)")
-original_version = re.compile(r"\#LyX (\S*)")
+original_version = re.compile(b".*?LyX ([\\d.]*)")
+original_tex2lyx_version = re.compile(b".*?tex2lyx ([\\d.]*)")
##
# file format information:
# file, supported formats, stable release versions
-format_relation = [("0_10", [210], ["0.10.7","0.10"]),
- ("0_12", [215], ["0.12","0.12.1","0.12"]),
- ("1_0_0", [215], ["1.0.0","1.0"]),
- ("1_0_1", [215], ["1.0.1","1.0.2","1.0.3","1.0.4", "1.1.2","1.1"]),
- ("1_1_4", [215], ["1.1.4","1.1"]),
- ("1_1_5", [216], ["1.1.5","1.1.5fix1","1.1.5fix2","1.1"]),
- ("1_1_6", [217], ["1.1.6","1.1.6fix1","1.1.6fix2","1.1"]),
- ("1_1_6fix3", [218], ["1.1.6fix3","1.1.6fix4","1.1"]),
- ("1_2", [220], ["1.2.0","1.2.1","1.2.3","1.2.4","1.2"]),
- ("1_3", [221], ["1.3.0","1.3.1","1.3.2","1.3.3","1.3.4","1.3.5","1.3.6","1.3"]),
- ("1_4", range(222,246), ["1.4.0", "1.4.1", "1.4.2svn"]),
- ("1_5", range(246,248), ["1.5.0svn"])]
-
+format_relation = [("0_06", [200], minor_versions("0.6" , 4)),
+ ("0_08", [210], minor_versions("0.8" , 6) + ["0.7"]),
+ ("0_10", [210], minor_versions("0.10", 7) + ["0.9"]),
+ ("0_12", [215], minor_versions("0.12", 1) + ["0.11"]),
+ ("1_0", [215], minor_versions("1.0" , 4)),
+ ("1_1", [215], minor_versions("1.1" , 4)),
+ ("1_1_5", [216], ["1.1", "1.1.5","1.1.5.1","1.1.5.2"]),
+ ("1_1_6_0", [217], ["1.1", "1.1.6","1.1.6.1","1.1.6.2"]),
+ ("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)),
+ # 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" , 4)),
+ ("2_3", list(range(509,545)), minor_versions("2.3" , 0)),
+ ("2_4", (), minor_versions("2.4" , 0))
+ ]
+
+####################################################################
+# This is useful just for development versions #
+# if the list of supported formats is empty get it from last step #
+if not format_relation[-1][1]:
+ step, mode = format_relation[-1][0], "convert"
+ convert = getattr(__import__("lyx_" + step), mode)
+ format_relation[-1] = (step,
+ [conv[0] for conv in convert],
+ format_relation[-1][2])
+# #
+####################################################################
def formats_list():
" Returns a list with supported file formats."
return formats
+def format_info():
+ " Returns a list with the supported file formats."
+ template = """
+%s\tstable format: %s
+ \tstable versions: %s
+ \tdevelopment formats: %s
+"""
+
+ out = "version: formats and versions"
+ for version in format_relation:
+ major = str(version[2][0])
+ versions = str(version[2][1:])
+ if len(version[1]) == 1:
+ formats = str(version[1][0])
+ stable_format = str(version[1][0])
+ elif not stable_version and major == version__:
+ stable_format = "-- not yet --"
+ versions = "-- not yet --"
+ formats = "%s - %s" % (version[1][0], version[1][-1])
+ else:
+ formats = "%s - %s" % (version[1][0], version[1][-2])
+ stable_format = str(version[1][-1])
+
+ out += template % (major, stable_format, versions, formats)
+ return out + '\n'
+
+
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):
" For _textclass_ returns its backend."
if textclass == "linuxdoc" or textclass == "manpage":
return "linuxdoc"
- if textclass[:7] == "docbook":
+ if textclass.startswith("docbook") or textclass.startswith("agu-"):
return "docbook"
return "latex"
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:
+ return "utf8"
+ # CJK-LyX encodes files using the current locale encoding.
+ # This means that files created by CJK-LyX can only be converted using
+ # the correct locale settings unless the encoding is given as commandline
+ # argument.
+ if cjk_encoding == 'auto':
+ return locale.getpreferredencoding()
+ elif cjk_encoding:
+ return cjk_encoding
+ from lyx2lyx_lang import lang
+ if inputencoding == "auto" or inputencoding == "default":
+ return lang[language][3]
+ if inputencoding == "":
+ return "latin1"
+ if inputencoding == "utf8x":
+ return "utf8"
+ # python does not know the alias latin9
+ if inputencoding == "latin9":
+ return "iso-8859-15"
+ return inputencoding
+
##
# Class
#
-class LyX_Base:
+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_level, try_hard = 0):
+
+ 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)
input: the name of the input source, if empty resort to standard input.
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.debug = debug
self.try_hard = try_hard
+ self.cjk_encoding = cjk_encoding
if end_format:
self.end_format = self.lyxformat(end_format)
+
+ # In case the target version and format are both specified
+ # verify that they are compatible. If not send a warning
+ # and ignore the version.
+ if final_version:
+ message = "Incompatible version %s for specified format %d" % (
+ final_version, self.end_format)
+ for version in format_relation:
+ if self.end_format in version[1]:
+ if final_version not in version[2]:
+ self.warning(message)
+ final_version = ""
+ elif final_version:
+ for version in format_relation:
+ if final_version in version[2]:
+ # set the last format for that version
+ self.end_format = version[1][-1]
+ break
+ else:
+ final_version = ""
else:
self.end_format = get_end_format()
+ if not final_version:
+ for step in format_relation:
+ if self.end_format in step[1]:
+ final_version = step[2][1]
+ self.final_version = final_version
+ self.warning("Final version: %s" % self.final_version, 10)
+ self.warning("Final format: %d" % self.end_format, 10)
+
self.backend = "latex"
self.textclass = "article"
# This is a hack: We use '' since we don't know the default
self.preamble = []
self.body = []
self.status = 0
+ self.encoding = encoding
+ self.language = language
+ self.systemlyxdir = systemlyxdir
- def warning(self, message, debug_level= default_debug_level):
- " Emits warning to self.error, if the debug_level is less than the self.debug."
+ def warning(self, message, debug_level= default_debug__):
+ """ Emits warning to self.error, if the debug_level is less
+ than the self.debug."""
if debug_level <= self.debug:
self.err.write("Warning: " + message + "\n")
" Emits a warning and exits if not in try_hard mode."
self.warning(message)
if not self.try_hard:
- self.warning("Quiting.")
+ self.warning("Quitting.")
sys.exit(1)
self.status = 2
def read(self):
- """Reads a file into the self.header and self.body parts, from self.input."""
-
- while 1:
+ """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.")
- line = trim_eol(line)
- if check_token(line, '\\begin_preamble'):
- while 1:
+ if first_line:
+ # Remove UTF8 BOM marker if present
+ if line.startswith(codecs.BOM_UTF8):
+ line = line[len(codecs.BOM_UTF8):]
+
+ first_line = False
+
+ 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 string.split(line)[:0] in ("\\layout", "\\begin_layout", "\\begin_body"):
- self.warning("Malformed LyX file: Missing '\\end_preamble'.")
- self.warning("Adding it now and hoping for the best.")
+
+ if decoded.split()[:0] in ("\\layout",
+ "\\begin_layout", "\\begin_body"):
+
+ self.warning("Malformed LyX file:"
+ "Missing '\\end_preamble'."
+ "\nAdding it now and hoping"
+ "for the best.")
self.preamble.append(line)
- if check_token(line, '\\end_preamble'):
+ if check_token(decoded, '\\end_preamble'):
continue
- line = string.strip(line)
+ line = line.rstrip()
if not line:
continue
- if string.split(line)[0] in ("\\layout", "\\begin_layout", "\\begin_body"):
+ if decoded.split()[0] in ("\\layout", "\\begin_layout",
+ "\\begin_body", "\\begin_deeper"):
self.body.append(line)
break
self.header.append(line)
- while 1:
- line = self.input.readline()
+ 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'.")
+ 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 True:
+ line = self.input.readline().decode(self.encoding)
if not line:
break
self.body.append(trim_eol(line))
- 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)
- if self.language == "":
- self.language = "english"
- self.initial_version = self.read_version()
-
def write(self):
" Writes the LyX file to self.output."
+ self.choose_output(self.output)
self.set_version()
self.set_format()
-
+ self.set_textclass()
+ if self.encoding == "auto":
+ self.encoding = get_encoding(self.language, self.encoding,
+ self.format, self.cjk_encoding)
if self.preamble:
i = find_token(self.header, '\\textclass', 0) + 1
preamble = ['\\begin_preamble'] + self.preamble + ['\\end_preamble']
- if i == 0:
- self.error("Malformed LyX file: Missing '\\textclass'.")
- else:
- header = self.header[:i] + preamble + self.header[i:]
+ header = self.header[:i] + preamble + self.header[i:]
else:
header = self.header
- for line in header + [''] + self.body:
- self.output.write(line+"\n")
+ for line in header + [u''] + self.body:
+ 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)
+
- if input and input != '-':
+ def choose_input(self, input):
+ """Choose input stream, dealing transparently with
+ compressed files."""
+
+ # 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.input = sys.stdin
+ self.dir = u''
+ self.input = os.fdopen(sys.stdin.fileno(), 'rb')
+ self.compressed = False
def lyxformat(self, format):
result = format_re.match(format)
if result:
format = int(result.group(1) + result.group(2))
+ elif format == '2':
+ format = 200
else:
self.error(str(format) + ": " + "Invalid LyX file.")
def read_version(self):
- """ Searchs for clues of the LyX version used to write the file, returns the
- most likely value, or None otherwise."""
+ """ Searchs for clues of the LyX version used to write the
+ file, returns the most likely value, or None otherwise."""
+
for line in self.header:
- if line[0] != "#":
+ if line[0:1] != b"#":
return None
- result = original_version.match(line)
+ line = line.replace(b"fix",b".")
+ # 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(b"reLyX") != -1 or line.find(b"KLyX") != -1:
+ return "0.12"
if result:
- return result.group(1)
+ res = result.group(1)
+ if not res:
+ self.warning(line)
+ #self.warning("Version %s" % result.group(1))
+ return res.decode('ascii') if not PY2 else res
+ self.warning(str(self.header[:2]))
return None
def set_version(self):
" Set the header with the version used."
- self.header[0] = "#LyX %s created this file. For more info see http://www.lyx.org/" % version_lyx2lyx
+
+ initial_comment = " ".join(["#LyX %s created this file." % version__,
+ "For more info see https://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
self.header[i] = "\\lyxformat %s" % format
+ def set_textclass(self):
+ i = find_token(self.header, "\\textclass", 0)
+ self.header[i] = "\\textclass %s" % self.textclass
+
+
+ #Note that the module will be added at the END of the extant ones
+ def add_module(self, module):
+ " Append module to the modules list."
+ i = find_token(self.header, "\\begin_modules", 0)
+ if i == -1:
+ #No modules yet included
+ i = find_token(self.header, "\\textclass", 0)
+ if i == -1:
+ self.warning("Malformed LyX document: No \\textclass!!")
+ return
+ modinfo = ["\\begin_modules", module, "\\end_modules"]
+ self.header[i + 1: i + 1] = modinfo
+ return
+ j = find_token(self.header, "\\end_modules", i)
+ if j == -1:
+ self.warning("(add_module)Malformed LyX document: No \\end_modules.")
+ return
+ k = find_token(self.header, module, i)
+ if k != -1 and k < j:
+ return
+ self.header.insert(j, module)
+
+
+ def del_module(self, module):
+ " Delete `module` from module list, return success."
+ modlist = self.get_module_list()
+ if module not in modlist:
+ return False
+ self.set_module_list([line for line in modlist if line != module])
+ return True
+
+ def get_module_list(self):
+ " Return list of modules."
+ i = find_token(self.header, "\\begin_modules", 0)
+ if (i == -1):
+ return []
+ j = find_token(self.header, "\\end_modules", i)
+ return self.header[i + 1 : j]
+
+
+ def set_module_list(self, mlist):
+ i = find_token(self.header, "\\begin_modules", 0)
+ if (i == -1):
+ #No modules yet included
+ tclass = find_token(self.header, "\\textclass", 0)
+ if tclass == -1:
+ self.warning("Malformed LyX document: No \\textclass!!")
+ return
+ i = j = tclass + 1
+ else:
+ j = find_token(self.header, "\\end_modules", i)
+ if j == -1:
+ self.warning("(set_module_list) Malformed LyX document: No \\end_modules.")
+ return
+ j += 1
+ if mlist:
+ mlist = ['\\begin_modules'] + mlist + ['\\end_modules']
+ self.header[i:j] = mlist
+
+
def set_parameter(self, param, value):
" Set the value of the header parameter."
i = find_token(self.header, '\\' + param, 0)
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
- for step in convertion_chain:
+ mode, conversion_chain = self.chain()
+ self.warning("conversion chain: " + str(conversion_chain), 3)
+
+ for step in conversion_chain:
steps = getattr(__import__("lyx_" + step), mode)
- self.warning("Convertion step: %s - %s" % (step, mode), default_debug_level + 1)
+ self.warning("Convertion step: %s - %s" % (step, mode),
+ default_debug__ + 1)
if not steps:
- self.error("The convertion to an older format (%s) is not implemented." % self.format)
+ self.error("The conversion to an older "
+ "format (%s) is not implemented." % self.format)
multi_conv = len(steps) != 1
for version, table in steps:
try:
conv(self)
except:
- self.warning("An error ocurred in %s, %s" % (version, str(conv)),
- default_debug_level)
+ self.warning("An error ocurred in %s, %s" %
+ (version, str(conv)),
+ default_debug__)
if not self.try_hard:
raise
self.status = 2
else:
- self.warning("%lf: Elapsed time on %s" % (time.time() - init_t, str(conv)),
- default_debug_level + 1)
-
+ self.warning("%lf: Elapsed time on %s" %
+ (time.time() - init_t,
+ str(conv)), default_debug__ +
+ 1)
self.format = version
if self.end_format == self.format:
return
def chain(self):
- """ This is where all the decisions related with the convertion are taken.
- It returns a list of modules needed to convert the LyX file from
- self.format to self.end_format"""
+ """ This is where all the decisions related with the
+ 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
if not correct_version:
if format <= 215:
- self.warning("Version does not match file format, discarding it.")
+ self.warning("Version does not match file format, "
+ "discarding it. (Version %s, format %d)" %
+ (self.initial_version, self.format))
for rel in format_relation:
if format in rel[1]:
initial_step = rel[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"
- first_step = 1
+ full_steps = []
for step in format_relation:
- if initial_step <= step[0] <= final_step:
- if first_step and len(step[1]) == 1:
- first_step = 0
- continue
- steps.append(step[0])
+ if initial_step <= step[0] <= final_step and step[2][0] <= self.final_version:
+ full_steps.append(step)
+ if full_steps[0][1][-1] == self.format:
+ full_steps = full_steps[1:]
+ for step in full_steps:
+ steps.append(step[0])
else:
mode = "revert"
relation_format = format_relation[:]
if last_step[1][-1] == self.end_format:
steps.pop()
+ self.warning("Convertion mode: %s\tsteps%s" %(mode, steps), 10)
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 = string.split(self.body[i])[1]
- if section[-1] == '*':
- section = section[:-1]
-
- par = []
-
- k = i + 1
- # skip paragraph parameters
- while not string.strip(self.body[k]) or string.split(self.body[k])[0] in allowed_parameters:
- k = k +1
-
- while k < j:
- if check_token(self.body[k], '\\begin_inset'):
- inset = string.split(self.body[k])[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 = k + 1
-
- # trim empty lines in the end.
- while string.strip(par[-1]) == '' and par:
- par.pop()
-
- toc_par.append(Paragraph(section, par))
-
- i = j + 1
-
- return toc_par
+ def append_local_layout(self, new_layout):
+ " Append `new_layout` to the local layouts."
+ # new_layout may be a string or a list of strings (lines)
+ try:
+ new_layout = new_layout.splitlines()
+ except AttributeError:
+ pass
+ i = find_token(self.header, "\\begin_local_layout", 0)
+ if i == -1:
+ k = find_token(self.header, "\\language", 0)
+ if k == -1:
+ # this should not happen
+ self.warning("Malformed LyX document! No \\language header found!")
+ return
+ self.header[k : k] = ["\\begin_local_layout", "\\end_local_layout"]
+ i = k
+
+ j = find_end_of(self.header, i, "\\begin_local_layout", "\\end_local_layout")
+ if j == -1:
+ # this should not happen
+ self.warning("Malformed LyX document: Can't find end of local layout!")
+ return
+ self.header[i+1 : i+1] = new_layout
-class File(LyX_Base):
+ def del_local_layout(self, layout_def):
+ " Delete `layout_def` from local layouts, return success."
+ i = find_complete_lines(self.header, layout_def)
+ if i == -1:
+ return False
+ j = i+len(layout_def)
+ if (self.header[i-1] == "\\begin_local_layout" and
+ self.header[j] == "\\end_local_layout"):
+ i -=1
+ j +=1
+ self.header[i:j] = []
+ return True
+
+ def del_from_header(self, lines):
+ " Delete `lines` from the document header, return success."
+ i = find_complete_lines(self.header, lines)
+ if i == -1:
+ return False
+ j = i + len(lines)
+ self.header[i:j] = []
+ return True
+
+# 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_level, try_hard = 0):
- LyX_Base.__init__(self, end_format, input, output, error, debug, try_hard)
- 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
-
-
-class Inset:
- " This class represents the LyX insets."
- pass
+ 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,
+ systemlyxdir)
+ self.read()
-class Text:
- " This class represents simple chuncks of text."
- pass
+# 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