lyx_mirror/lib/lyx2lyx/lyx_2_3.py

# -*- coding: utf-8 -*-
# This file is part of lyx2lyx
# -*- coding: utf-8 -*-
# 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_tokens, \
#  find_token_exact, find_end_of_inset, \
#  is_in_inset, get_value, get_quoted_value, \
#  del_token, check_token, get_option_value, get_bool_value

from parser_tools import find_token, find_end_of_inset, get_value, \
     get_bool_value, get_containing_layout

from lyx2lyx_tools import add_to_preamble, put_cmd_in_ert
#  get_ert, lyx2latex, \
#  lyx2verbatim, length_in_bp, convert_info_insets
#  insert_to_preamble, latex_length, revert_flex_inset, \
#  revert_font_attrs, hex2ratio, str2bool

from lyx2lyx_tools import add_to_preamble, put_cmd_in_ert

####################################################################
# 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.iteritems():
        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"

    while True:
        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!")
                break
            document.header[k-1 : k-1] = ["\\begin_local_layout", "\\end_local_layout"]
            i = find_token(document.header, "\\begin_local_layout", 0)
        if i != -1:
            j = find_end_of(document.header, i, "\\begin_local_layout", "\\end_local_layout")
            if j == -1:
                # this should not happen
                break

            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) ###"]
        return


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

    while True:
        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
            break

        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!")
                break

            document.header[k : l + 1] = []

        return


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 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
    i = 0
    j = 0
    while True:
        k = find_token(document.body, '\\begin_inset Quotes', i, j)
        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 += 1
    


##
# 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, []]  
          ]

revert =  [
           [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