# 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
+from parser_tools import (del_token, del_value, del_complete_lines,
+ find_complete_lines, find_end_of, find_end_of_layout, find_end_of_inset,
+ find_re, find_substring, find_token, find_token_backwards,
+ get_containing_inset, get_containing_layout, get_bool_value, get_value,
+ get_quoted_value, is_in_inset, set_bool_value)
+# find_tokens, find_token_exact, check_token, get_option_value
+
+from lyx2lyx_tools import (add_to_preamble, put_cmd_in_ert, revert_font_attrs,
+ insert_to_preamble, latex_length, revert_language)
####################################################################
# Private helper functions
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)
+ i = find_token(document.header, "\\font_tt_scale")
+ j = find_token(document.preamble, "\\usepackage{microtype}")
if j == -1:
document.header.insert(i + 1, "\\use_microtype false")
else:
document.header.insert(i + 1, "\\use_microtype true")
del document.preamble[j]
+ if j and document.preamble[j-1] == "% Added by lyx2lyx":
+ del document.preamble[j-1]
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]
+ use_microtype = get_bool_value(document.header, "\\use_microtype", delete=True)
if use_microtype:
add_to_preamble(document, ["\\usepackage{microtype}"])
' Convert date external inset to ERT '
i = 0
while True:
- i = find_token(document.body, "\\begin_inset External", i)
+ i = find_token(document.body, "\\begin_inset External", i+1)
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
+ i = j # skip inset
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":
+ """Replace no longer supported input encoding setting."""
+ i = find_token(document.header, "\\inputencoding pt254")
+ if i != -1:
document.header[i] = "\\inputencoding pt154"
' Add "inverted 0" to branch insets'
i = 0
while True:
- i = find_token(document.body, "\\begin_inset Branch", i)
+ i = find_token(document.body, "\\begin_inset Branch", i+1)
if i == -1:
return
document.body.insert(i + 1, "inverted 0")
- i += 1
def revert_ibranches(document):
ourbranches = {}
i = 0
while True:
- i = find_token(document.header, "\\branch", i)
+ i = find_token(document.header, "\\branch", i+1)
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
-
+ selected = get_bool_value(document.header, "\\selected", i+1, i+2)
+ if selected is None:
+ document.warning("Malformed LyX document: No selection indicator "
+ "for branch %s." % branch)
+ selected = True
# the value tells us whether the branch is selected
- ourbranches[document.header[i][8:].strip()] = selected
- i += 1
+ ourbranches[branch] = selected
- # Figure out what inverted branches, if any, have been used
- # and convert them to "Anti-OldBranch"
- ibranches = {}
+ # Find branch insets, remove "inverted" tag and
+ # convert inverted insets to "Anti-OldBranch" insets
+ antibranches = {}
i = 0
while True:
- i = find_token(document.body, "\\begin_inset Branch", i)
+ i = find_token(document.body, "\\begin_inset Branch", i+1)
if i == -1:
break
- if not document.body[i+1].startswith("inverted "):
- document.warning("Malformed LyX document: Missing 'inverted' tag!")
- i += 1
+ inverted = get_bool_value(document.body, "inverted", i+1, i+2, delete=True)
+ if inverted is None:
+ document.warning("Malformed LyX document: Missing 'inverted' tag in branch inset.")
continue
- inverted = document.body[i+1][9]
- #document.warning(document.body[i+1])
-
- if inverted == "1":
+ if inverted:
branch = document.body[i][20:].strip()
- #document.warning(branch)
- if not branch in ibranches:
+ if not branch in antibranches:
antibranch = "Anti-" + branch
- while antibranch in ibranches:
+ while antibranch in antibranches:
antibranch = "x" + antibranch
- ibranches[branch] = antibranch
+ antibranches[branch] = antibranch
else:
- antibranch = ibranches[branch]
- #document.warning(antibranch)
+ antibranch = antibranches[branch]
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():
+ for old, new in antibranches.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))
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"
+def revert_new_babel_languages(document):
+ """Revert "bosnian", "friulan", "macedonian", "piedmontese", "romansh".
- 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")
+ Set the document language to English but use correct babel setting.
+ """
+ nblanguages = ["bosnian", "friulan", "macedonian", "piedmontese", "romansh"]
-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,")
+ for lang in nblanguages:
+ if lang == "bosnian" or lang == "macedonian":
+ # These are only supported by babel
+ revert_language(document, lang, lang, "")
else:
- l = find_token(document.header, "\\use_default_options", 0)
- document.header.insert(l + 1, "\\options piedmontese")
+ # These are supported by babel and polyglossia
+ revert_language(document, lang, lang, lang)
-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")
-
+# TODO:
+# def convert_new_babel_languages(document)
+# set to native support if get_value(document.header, "\\options") in
+# ["bosnian", "friulan", "macedonian", "piedmontese", "romansh"]
+# and "\\language_package babel".
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", ""]
+ revert_language(document, "amharic", "", "amharic")
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", ""]
+ revert_language(document, "asturian", "", "asturian")
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", ""]
+ revert_language(document, "kannada", "", "kannada")
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", ""]
+ revert_language(document, "khmer", "", "khmer")
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", ""]
+ revert_language(document, "urdu", "", "urdu")
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", ""]
+ revert_language(document, "syriac", "", "syriac")
def revert_quotes(document):
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
document.warning("Malformed LyX document: Can't find end of Quote inset at line " + str(k))
i = k
continue
- replace = "\""
+ replace = '"'
if document.body[k].endswith("s"):
replace = "'"
- document.body[k:l+1] = [replace]
+ document.body[k:l+2] = [replace]
else:
i += 1
continue
replace = "\""
if document.body[k].endswith("s"):
replace = "'"
- document.body[k:l+1] = [replace]
+ document.body[k:l+2] = [replace]
else:
i += 1
continue
replace = "\""
if document.body[k].endswith("s"):
replace = "'"
- document.body[k:l+1] = [replace]
+ document.body[k:l+2] = [replace]
i = l
replace = "\""
if document.body[k].endswith("s"):
replace = "'"
- document.body[k:l+1] = [replace]
+ document.body[k:l+2] = [replace]
i = l
i = l
+def convert_crimson(document):
+ """Transform preamble code to native font setting."""
+ # Quick-check:
+ i = find_substring(document.preamble, "{cochineal}")
+ if i == -1:
+ return
+ # Find and delete user-preamble code:
+ if document.preamble[i] == "\\usepackage[proportional,osf]{cochineal}":
+ osf = True
+ elif document.preamble[i] == "\\usepackage{cochineal}":
+ osf = False
+ else:
+ return
+ del document.preamble[i]
+ if i and document.preamble[i-1] == "% Added by lyx2lyx":
+ del document.preamble[i-1]
+
+ # Convert to native font setting:
+ j = find_token(document.header, '\\font_roman')
+ if j == -1:
+ romanfont = ['\font_roman', '"cochineal"', '"default"']
+ else:
+ romanfont = document.header[j].split()
+ romanfont[1] = '"cochineal"'
+ document.header[j] = " ".join(romanfont)
+ try:
+ set_bool_value(document.header, '\\font_osf', osf)
+ except ValueError: # no \\font_osf setting in document.header
+ if osf:
+ document.header.insert(-1, "\\font_osf true")
+
+
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")
+ i = find_token(document.header, '\\font_roman "cochineal"')
+ if i == -1:
+ return
+ # replace unsupported font setting
+ document.header[i] = document.header[i].replace("cochineal", "default")
+ # no need for preamble code with system fonts
+ if get_bool_value(document.header, "\\use_non_tex_fonts"):
+ return
+ # transfer old style figures setting to package options
+ j = find_token(document.header, "\\font_osf true")
+ if j != -1:
+ options = "[proportional,osf]"
+ document.header[j] = "\\font_osf false"
+ else:
+ options = ""
+ add_to_preamble(document, ["\\usepackage%s{cochineal}"%options])
def revert_cochinealmath(document):
i += 1
continue
k = find_token(document.body, "LatexCommand labelonly", i, j)
- if k == -1:
- i = j
- continue
- noprefix = get_bool_value(document.body, "noprefix", 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
}
# 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*" ]
+ 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):
def convert_literalparam(document):
" Add param literal "
- # These already had some sort of latexify method
- latexified_insets = ["href", "index_print", "nomenclature"]
-
- 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
- if inset in latexified_insets:
- document.body.insert(i, "literal \"false\"")
- else:
- document.body.insert(i, "literal \"true\"")
-
+ pos = len("\\begin_inset CommandInset ")
+ i = 0
+ while True:
+ i = find_token(document.body, '\\begin_inset CommandInset', i)
+ if i == -1:
+ break
+ inset = document.body[i][pos:].strip()
+ if not inset in command_insets:
+ i += 1
+ continue
+ 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\"")
+ i = j + 1
def revert_literalparam(document):
del document.body[k]
-
def revert_multibib(document):
" Revert multibib support "
def convert_dashligatures(document):
- " Remove a zero-length space (U+200B) after en- and em-dashes. "
+ """Set 'use_dash_ligatures' according to content.
+ """
+ # Look for and remove dashligatures workaround from 2.3->2.2 reversion,
+ # set use_dash_ligatures to True if found, to None else.
+ use_dash_ligatures = del_complete_lines(document.preamble,
+ ['% Added by lyx2lyx',
+ r'\renewcommand{\textendash}{--}',
+ r'\renewcommand{\textemdash}{---}']) or None
+
+ 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 -- an ---.)
+ lines = document.body
+ has_literal_dashes = has_ligature_dashes = False
+ dash_pattern = re.compile(u".*[\u2013\u2014]|\\twohyphens|\\threehyphens")
+ i = j = 0
+ while True:
+ # skip lines without dashes:
+ i = find_re(lines, dash_pattern, i+1)
+ if i == -1:
+ break
+ line = lines[i]
+ # skip label width string (see bug 10243):
+ if line.startswith("\\labelwidthstring"):
+ continue
+ # do not touch hyphens in some insets (cf. lyx_2_2.convert_dashes):
+ try:
+ inset_type, start, end = get_containing_inset(lines, i)
+ except TypeError: # no containing inset
+ inset_type, start, end = "no inset", -1, -1
+ if (inset_type.split()[0] in
+ ["CommandInset", "ERT", "External", "Formula",
+ "FormulaMacro", "Graphics", "IPA", "listings"]
+ or inset_type == "Flex Code"):
+ i = end
+ continue
+ try:
+ layoutname, start, end, j = get_containing_layout(lines, i)
+ except TypeError: # no (or malformed) containing layout
+ document.warning("Malformed LyX document: "
+ "Can't find layout at line %d" % i)
+ continue
+ if not layoutname:
+ document.warning("Malformed LyX document: "
+ "Missing layout name on line %d"%start)
+ if layoutname == "LyX-Code":
+ i = end
+ continue
- i = find_token(document.header, "\\use_microtype", 0)
- if i != -1:
- if document.initial_format > 474 and document.initial_format < 509:
- # This was created by LyX 2.2
- document.header[i+1:i+1] = ["\\use_dash_ligatures false"]
- else:
- # This was created by LyX 2.1 or earlier
- document.header[i+1:i+1] = ["\\use_dash_ligatures true"]
+ # literal dash followed by a non-white-character or no-break space:
+ if re.search(u"[\u2013\u2014]([\S\u00A0\u202F\u2060]|$)",
+ line, flags=re.UNICODE):
+ has_literal_dashes = True
+ # ligature dash followed by non-white-char or no-break space on next line:
+ if (re.search(r"(\\twohyphens|\\threehyphens)", line) and
+ re.match(u"[\S\u00A0\u202F\u2060]", lines[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.')
+ break
- i = 0
- while i < len(document.body):
- words = document.body[i].split()
- # Skip some document parts where dashes are not converted
- 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))
- i += 1
- else:
- i = j
- continue
- if len(words) > 0 and words[0] in ["\\leftindent", \
- "\\paragraph_spacing", "\\align", "\\labelwidthstring"]:
- i += 1
- continue
+ if has_literal_dashes and not has_ligature_dashes:
+ use_dash_ligatures = False
+ elif has_ligature_dashes and not has_literal_dashes:
+ use_dash_ligatures = True
- start = 0
- while True:
- j = document.body[i].find(u"\u2013", start) # en-dash
- k = document.body[i].find(u"\u2014", start) # em-dash
- if j == -1 and k == -1:
- break
- if j == -1 or (k != -1 and k < j):
- j = k
- after = document.body[i][j+1:]
- if after.startswith(u"\u200B"):
- document.body[i] = document.body[i][:j+1] + after[1:]
- else:
- if len(after) == 0 and document.body[i+1].startswith(u"\u200B"):
- document.body[i+1] = document.body[i+1][1:]
- break
- start = j+1
- i += 1
+ # insert the setting if there is a preferred value
+ if use_dash_ligatures is True:
+ document.header.insert(-1, "\\use_dash_ligatures true")
+ elif use_dash_ligatures is False:
+ document.header.insert(-1, "\\use_dash_ligatures false")
def revert_dashligatures(document):
- " Remove font ligature settings for en- and em-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 use_non_tex_fonts:
+ """Remove font ligature settings for en- and em-dashes.
+ Revert conversion of \twodashes or \threedashes to literal dashes.
+ """
+ use_dash_ligatures = del_value(document.header, "\\use_dash_ligatures")
+ if use_dash_ligatures != "true" or document.backend != "latex":
return
-
- # Add a zero-length space (U+200B) after en- and em-dashes
i = 0
- while i < len(document.body):
- words = document.body[i].split()
- # Skip some document parts where dashes are not converted
- 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))
- i += 1
- else:
- i = j
+ dash_pattern = re.compile(u".*[\u2013\u2014]")
+ while True:
+ # skip lines without dashes:
+ i = find_re(document.body, dash_pattern, i+1)
+ if i == -1:
+ break
+ line = document.body[i]
+ # skip label width string (see bug 10243):
+ if line.startswith("\\labelwidthstring"):
continue
- if len(words) > 0 and words[0] in ["\\leftindent", \
- "\\paragraph_spacing", "\\align", "\\labelwidthstring"]:
- i += 1
+ # do not touch hyphens in some insets (cf. lyx_2_2.convert_dashes):
+ try:
+ inset_type, start, end = get_containing_inset(document.body, i)
+ except TypeError: # no containing inset
+ inset_type, start, end = "no inset", -1, -1
+ if (inset_type.split()[0] in
+ ["CommandInset", "ERT", "External", "Formula",
+ "FormulaMacro", "Graphics", "IPA", "listings"]
+ or inset_type == "Flex Code"):
+ i = end
continue
-
- start = 0
- while True:
- j = document.body[i].find(u"\u2013", start) # en-dash
- k = document.body[i].find(u"\u2014", start) # em-dash
- if j == -1 and k == -1:
- break
- if j == -1 or (k != -1 and k < j):
- j = k
- after = document.body[i][j+1:]
- document.body[i] = document.body[i][:j+1] + u"\u200B" + after
- start = j+1
- i += 1
+ try:
+ layoutname, start, end, j = get_containing_layout(document.body, i)
+ except TypeError: # no (or malformed) containing layout
+ document.warning("Malformed LyX document: "
+ "Can't find layout at body line %d" % i)
+ continue
+ if layoutname == "LyX-Code":
+ i = end
+ continue
+ # TODO: skip replacement in typewriter fonts
+ line = line.replace(u'\u2013', '\\twohyphens\n')
+ line = line.replace(u'\u2014', '\\threehyphens\n')
+ document.body[i:i+1] = line.split('\n')
+ # redefine the dash LICRs to use ligature dashes:
+ add_to_preamble(document, [r'\renewcommand{\textendash}{--}',
+ r'\renewcommand{\textemdash}{---}'])
def revert_noto(document):
def convert_mathindent(document):
- " add the \\is_math_indent tag "
+ """Add the \\is_math_indent tag.
+ """
+ k = find_token(document.header, "\\quotes_style") # where to insert
# 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:
+ options = get_value(document.header, "\\options")
+ if 'fleqn' in options:
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
+ # delete the fleqn option
+ i = find_token(document.header, "\\options")
+ options = [option for option in options.split(",")
+ if option.strip() != "fleqn"]
+ if options:
+ document.header[i] = "\\options " + ",".join(options)
+ else:
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)
+ # emulate and delete \math_indentation
+ value = get_value(document.header, "\\math_indentation",
+ default="default", delete=True)
+ if value != "default":
+ add_to_preamble(document, [r"\setlength{\mathindent}{%s}"%value])
+ # delete \is_math_indent and emulate via document class option
+ if not get_bool_value(document.header, "\\is_math_indent", delete=True):
+ return
+ i = find_token(document.header, "\\options")
if i != -1:
- value = get_value(document.header, "\\math_indentation" , i).split()[0]
- 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]
+ document.header[i] = document.header[i].replace("\\options ",
+ "\\options fleqn,")
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]
+ l = find_token(document.header, "\\use_default_options")
+ document.header.insert(l, "\\options fleqn")
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
+ " Revert baselineskips to TeX code "
+ i = 0
+ while True:
+ i = find_substring(document.body, "baselineskip%", i+1)
+ if i == -1:
+ return
+ if document.body[i].startswith("\\begin_inset VSpace"):
+ # output VSpace inset as TeX code
+ end = find_end_of_inset(document.body, i)
+ if end == -1:
+ document.warning("Malformed LyX document: "
+ "Can't find end of VSpace inset at line %d." % i)
+ continue
+ # read out the value
+ baselineskip = document.body[i].split()[-1]
+ # check if it is the starred version
+ star = '*' if '*' in document.body[i] else ''
+ # now output TeX code
+ cmd = "\\vspace%s{%s}" %(star, latex_length(baselineskip)[1])
+ document.body[i:end+1] = put_cmd_in_ert(cmd)
+ i += 8
+ continue
+ begin, end = is_in_inset(document.body, i, "\\begin_inset space \\hspace")
+ if begin != - 1:
+ # output space inset as TeX code
+ baselineskip = document.body[i].split()[-1]
+ star = '*' if '*' in document.body[i-1] else ''
+ cmd = "\\hspace%s{%s}" %(star, latex_length(baselineskip)[1])
+ document.body[begin:end+1] = put_cmd_in_ert(cmd)
def revert_rotfloat(document):
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:
+ if i == -1:
return
+ if not document.body[i-2].startswith('placement '):
+ i = i + 1
+ continue
# we found a sideways float with placement options
# at first store the placement
beg = document.body[i-2].rfind(" ");
i = i + 1
+allowbreak_emulation = [r"\begin_inset space \hspace{}",
+ r"\length 0dd",
+ r"\end_inset",
+ r""]
+
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")
+ lines = document.body
+ i = find_complete_lines(lines, allowbreak_emulation, 2)
+ while i != -1:
+ lines[i-1:i+4] = [lines[i-1] + r"\SpecialChar allowbreak"]
+ i = find_complete_lines(lines, allowbreak_emulation, i+3)
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")
+ i = 1
+ lines = document.body
+ while i < len(lines):
+ if lines[i].endswith(r"\SpecialChar allowbreak"):
+ lines[i:i+1] = [lines[i].replace(r"\SpecialChar allowbreak", "")
+ ] + allowbreak_emulation
+ i += 5
+ else:
+ i += 1
def convert_mathnumberpos(document):
- " add the \math_number_before tag "
+ " add the \\math_number_before tag "
# check if the document uses the class option "leqno"
- k = find_token(document.header, "\\quotes_style", 0)
- regexp = re.compile(r'^.*leqno.*')
- i = find_re(document.header, regexp, 0)
- if i != -1:
+ i = find_token(document.header, "\\options")
+ k = find_token(document.header, "\\quotes_style")
+ if 'leqno' in document.header[i]:
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 fleqn as the only option
+ if 'leqno' in document.header[i]:
+ # 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]
+ """Remove \\math_number_before tag,
+ add the document class option leqno if required.
+ """
+ math_number_before = get_bool_value(document.header,
+ '\\math_number_before', delete=True)
+ if math_number_before:
+ i = find_token(document.header, "\\options")
+ if i != -1 and 'leqno' not in document.header[i]:
+ document.header[i] = document.header[i].replace("\\options", "\\options leqno,")
+ else:
+ i = find_token(document.header, "\\use_default_options")
+ document.header.insert(i, "\\options leqno")
+
+
+def convert_mathnumberingname(document):
+ " rename the \\math_number_before tag to \\math_numbering_side "
+ i = find_token(document.header, "\\math_number_before")
+ math_number_before = get_bool_value(document.header, '\\math_number_before', i)
+ if math_number_before:
+ document.header[i] = "\\math_numbering_side left"
+ return
+ # check if the document uses the class option "reqno"
+ k = find_token(document.header, "\\options")
+ if 'reqno' in document.header[k]:
+ document.header[i] = "\\math_numbering_side right"
+ # delete the found option
+ document.header[k] = document.header[k].replace(",reqno", "")
+ document.header[k] = document.header[k].replace(", reqno", "")
+ document.header[k] = document.header[k].replace("reqno,", "")
+ if 'reqno' in document.header[k]:
+ # then we have reqno as the only option
+ del document.header[k]
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]
+ document.header[i] = "\\math_numbering_side default"
+
+
+def revert_mathnumberingname(document):
+ " rename the \\math_numbering_side tag back to \\math_number_before "
+ i = find_token(document.header, "\\math_numbering_side")
+ math_numbering_side = get_value(document.header, '\\math_numbering_side', i)
+ # rename tag and set boolean value:
+ if math_numbering_side == "left":
+ document.header[i] = "\\math_number_before 1"
+ elif math_numbering_side == "right":
+ # also add the option reqno:
+ document.header[i] = "\\math_number_before 0"
+ k = find_token(document.header, "\\options")
+ if k != -1 and 'reqno' not in document.header[k]:
+ 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 leqno")
- del document.header[i + 1]
+ document.header.insert(l, "\\options reqno")
+ else:
+ document.header[i] = "\\math_number_before 0"
+
+
+def convert_minted(document):
+ " add the \\use_minted tag "
+ i = find_token(document.header, "\\index ")
+ document.header.insert(i, "\\use_minted 0")
+
+
+def revert_minted(document):
+ " remove the \\use_minted tag "
+ del_token(document.header, "\\use_minted")
+
+
+def revert_longtable_lscape(document):
+ " revert the longtable landcape mode to ERT "
+ i = 0
+ regexp = re.compile(r'^<features rotate=\"90\"\s.*islongtable=\"true\"\s.*$', re.IGNORECASE)
+ while True:
+ i = find_re(document.body, regexp, i)
+ if i == -1:
+ return
+
+ document.body[i] = document.body[i].replace(" rotate=\"90\"", "")
+ lay = get_containing_layout(document.body, i)
+ if lay == False:
+ document.warning("Longtable has not layout!")
+ i += 1
+ continue
+ begcmd = put_cmd_in_ert("\\begin{landscape}")
+ endcmd = put_cmd_in_ert("\\end{landscape}")
+ document.body[lay[2] : lay[2]] = endcmd + ["\\end_layout"]
+ document.body[lay[1] : lay[1]] = ["\\begin_layout " + lay[0], ""] + begcmd
+
+ add_to_preamble(document, ["\\usepackage{pdflscape}"])
+ i = lay[2]
##
[521, [convert_frenchquotes]],
[522, []],
[523, []],
- [524, []],
+ [524, [convert_crimson]],
[525, []],
[526, []],
[527, []],
[539, []],
[540, []],
[541, [convert_allowbreak]],
- [542, [convert_mathnumberpos]]
+ [542, [convert_mathnumberpos]],
+ [543, [convert_mathnumberingname]],
+ [544, [convert_minted]]
]
revert = [
+ [543, [revert_minted, revert_longtable_lscape]],
+ [542, [revert_mathnumberingname]],
[541, [revert_mathnumberpos]],
[540, [revert_allowbreak]],
[539, [revert_rotfloat]],
[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]],
+ [512, [revert_new_babel_languages]],
[511, [revert_beamer_article_styles]],
[510, [revert_ibranches]],
[509, []],
projects / lyx.git / blobdiff