" Find end of inset, where lines[i] is included."
return find_end_of(lines, i, "\\begin_inset", "\\end_inset")
+def wrap_into_ert(string, src, dst):
+ " Wrap a something into an ERT"
+ return string.replace(src, '\n\\begin_inset ERT\nstatus collapsed\n\\begin_layout Standard\n'
+ + dst + '\n\\end_layout\n\\end_inset\n')
####################################################################
return
if document.body[i + 1] != "LatexCommand index": # Might also be index_print
return
- fullcommand = document.body[i + 2]
- document.body[i] = "\\begin_inset Index"
- document.body[i + 1] = "status collapsed"
- document.body[i + 2] = "\\begin_layout standard"
- document.body.insert(i + 3, fullcommand[6:].strip('"'))
- document.body.insert(i + 4, "\\end_layout")
+ fullcontent = document.body[i + 2][6:].strip('"')
+ document.body[i:i + 2] = ["\\begin_inset Index",
+ "status collapsed",
+ "\\begin_layout Standard"]
+ # Put here the conversions needed from LaTeX string to LyXText.
+ # Here we do a minimal conversion to prevent crashes and data loss.
+ # Manual patch-up may be needed.
+ # Umlauted characters (most common ones, can be extended):
+ fullcontent = fullcontent.replace(r'\\\"a', u'ä').replace(r'\\\"o', u'ö').replace(r'\\\"u', u'ü')
+ # Generic, \" -> ":
+ fullcontent = wrap_into_ert(fullcontent, r'\"', '"')
+ #fullcontent = fullcontent.replace(r'\"', '\n\\begin_inset ERT\nstatus collapsed\n\\begin_layout standard\n"\n\\end_layout\n\\end_inset\n')
+ # Math:
+ r = re.compile('^(.*?)(\$.*?\$)(.*)')
+ g = fullcontent
+ while r.match(g):
+ m = r.match(g)
+ s = m.group(1)
+ f = m.group(2).replace('\\\\', '\\')
+ g = m.group(3)
+ if s:
+ # this is non-math!
+ s = wrap_into_ert(s, r'\\', '\\backslash')
+ s = wrap_into_ert(s, '{', '{')
+ s = wrap_into_ert(s, '}', '}')
+ document.body.insert(i + 3, s)
+ i += 1
+ document.body.insert(i + 3, "\\begin_inset Formula " + f)
+ document.body.insert(i + 4, "\\end_inset")
+ i += 2
+ # Generic, \\ -> \backslash:
+ g = wrap_into_ert(g, r'\\', '\\backslash{}')
+ g = wrap_into_ert(g, '{', '{')
+ g = wrap_into_ert(g, '}', '}')
+ document.body.insert(i + 3, g)
+ document.body[i + 4] = "\\end_layout"
i = i + 5
def revert_latexcommand_index(document):
- "Revert from collapsable form toLatexCommand form."
+ "Revert from collapsable form to LatexCommand form."
i = 0
while True:
i = find_token(document.body, "\\begin_inset Index", i)
if i == -1:
- return
- j = find_end_of_inset(document.body, i)
+ return
+ j = find_end_of_inset(document.body, i + 1)
+ if j == -1:
+ return
del document.body[j - 1]
del document.body[j - 2] # \end_layout
document.body[i] = "\\begin_inset CommandInset index"
document.body[i + 1] = "LatexCommand index"
- document.body[i + 3] = "name " + '"' + document.body[i + 3] + '"'
+ # clean up multiline stuff
+ content = ""
+ for k in range(i + 3, j - 2):
+ line = document.body[k]
+ if line.startswith("\\begin_inset ERT"):
+ line = line[16:]
+ if line.startswith("\\begin_inset Formula"):
+ line = line[20:]
+ if line.startswith("\\begin_layout Standard"):
+ line = line[22:]
+ if line.startswith("\\end_layout"):
+ line = line[11:]
+ if line.startswith("\\end_inset"):
+ line = line[10:]
+ if line.startswith("status collapsed"):
+ line = line[16:]
+ line = line.replace(u'ä', r'\\\"a').replace(u'ö', r'\\\"o').replace(u'ü', r'\\\"u')
+ content = content + line;
+ document.body[i + 3] = "name " + '"' + content + '"'
+ for k in range(i + 4, j - 2):
+ del document.body[i + 4]
document.body.insert(i + 4, "")
del document.body[i + 2] # \begin_layout standard
i = i + 5
document.body[i + 1] = "LatexCommand href"
i = i + 1
+
def convert_url(document):
'Convert url insets to url charstyles'
if document.backend == "docbook":
return
- r = re.compile(r'target\s+"(.*)"')
- didone = False
i = 0
while True:
i = find_token(document.body, "\\begin_inset CommandInset url", i)
if i == -1:
break
+ n = find_token(document.body, "name", i)
+ if n == i + 2:
+ # place the URL name in typewriter before the new URL insert
+ # grab the name 'bla' from the e.g. the line 'name "bla"',
+ # therefore start with the 6th character
+ name = document.body[n][6:-1]
+ newname = [name + " "]
+ document.body[i:i] = newname
+ i = i + 1
j = find_token(document.body, "target", i)
if j == -1:
document.warning("Malformed LyX document: Can't find target for url inset")
i = j
continue
- m = r.match(document.body[j])
- target = m.group(1)
+ target = document.body[j][8:-1]
k = find_token(document.body, "\\end_inset", j)
if k == -1:
document.warning("Malformed LyX document: Can't find end of url inset")
newstuff = ["\\begin_inset Flex URL",
"status collapsed", "",
"\\begin_layout Standard",
+ "",
target,
"\\end_layout",
""]
document.body[i:k] = newstuff
- didone = True
i = k
- #If we did one, we need to add URL to the modules
- if didone:
- i = find_token(document.header, "\\begin_modules", 0)
- if i == -1:
- #No modules yet included
- i = find_token(document.header, "\\textclass", 0)
- if i == -1:
- document.warning("Malformed LyX document: No \\textclass!!")
- return
- modinfo = ["\\begin_modules", "URL", "\\end_modules"]
- document.header[i + 1: i + 1] = modinfo
- return
- j = find_token(document.header, "\\end_modules", i)
- if j == -1:
- document.warning("Malformed LyX document: No \\end_modules.")
- return
- k = find_token(document.header, "URL", i)
- if k != -1 and k < j:
- return
- document.header.insert(i + 1, "URL")
+def convert_ams_classes(document):
+ tc = document.textclass
+ if (tc != "amsart" and tc != "amsart-plain" and
+ tc != "amsart-seq" and tc != "amsbook"):
+ return
+ if tc == "amsart-plain":
+ document.textclass = "amsart"
+ document.set_textclass()
+ document.add_module("Theorems (Starred)")
+ return
+ if tc == "amsart-seq":
+ document.textclass = "amsart"
+ document.set_textclass()
+ document.add_module("Theorems (AMS)")
+
+ #Now we want to see if any of the environments in the extended theorems
+ #module were used in this document. If so, we'll add that module, too.
+ layouts = ["Criterion", "Algorithm", "Axiom", "Condition", "Note", \
+ "Notation", "Summary", "Acknowledgement", "Conclusion", "Fact", \
+ "Assumption"]
+
+ r = re.compile(r'^\\begin_layout (.*?)\*?\s*$')
+ i = 0
+ while True:
+ i = find_token(document.body, "\\begin_layout", i)
+ if i == -1:
+ return
+ m = r.match(document.body[i])
+ if m == None:
+ document.warning("Weirdly formed \\begin_layout at line " + i + " of body!")
+ i += 1
+ continue
+ m = m.group(1)
+ if layouts.count(m) != 0:
+ document.add_module("Theorems (AMS-Extended)")
+ return
+ i += 1
def revert_href(document):
'Reverts hyperlink insets (href) to url insets (url)'
i = i + 2
+def convert_include(document):
+ 'Converts include insets to new format.'
+ i = 0
+ r = re.compile(r'\\begin_inset Include\s+\\([^{]+){([^}]*)}(?:\[(.*)\])?')
+ while True:
+ i = find_token(document.body, "\\begin_inset Include", i)
+ if i == -1:
+ return
+ line = document.body[i]
+ previewline = document.body[i + 1]
+ m = r.match(line)
+ if m == None:
+ document.warning("Unable to match line " + str(i) + " of body!")
+ i += 1
+ continue
+ cmd = m.group(1)
+ fn = m.group(2)
+ opt = m.group(3)
+ insertion = ["\\begin_inset CommandInset include",
+ "LatexCommand " + cmd, previewline,
+ "filename \"" + fn + "\""]
+ newlines = 2
+ if opt:
+ insertion.append("lstparams " + '"' + opt + '"')
+ newlines += 1
+ document.body[i : i + 2] = insertion
+ i += newlines
+
+
+def revert_include(document):
+ 'Reverts include insets to old format.'
+ i = 0
+ r1 = re.compile('LatexCommand (.+)')
+ r2 = re.compile('filename (.+)')
+ r3 = re.compile('options (.*)')
+ while True:
+ i = find_token(document.body, "\\begin_inset CommandInset include", i)
+ if i == -1:
+ return
+ previewline = document.body[i + 1]
+ m = r1.match(document.body[i + 2])
+ if m == None:
+ document.warning("Malformed LyX document: No LatexCommand line for `" +
+ document.body[i] + "' on line " + str(i) + ".")
+ i += 1
+ continue
+ cmd = m.group(1)
+ m = r2.match(document.body[i + 3])
+ if m == None:
+ document.warning("Malformed LyX document: No filename line for `" + \
+ document.body[i] + "' on line " + str(i) + ".")
+ i += 2
+ continue
+ fn = m.group(1)
+ options = ""
+ numlines = 4
+ if (cmd == "lstinputlisting"):
+ m = r3.match(document.body[i + 4])
+ if m != None:
+ options = m.group(1)
+ numlines = 5
+ newline = "\\begin_inset Include \\" + cmd + "{" + fn + "}"
+ if options:
+ newline += ("[" + options + "]")
+ insertion = [newline, previewline]
+ document.body[i : i + numlines] = insertion
+ i += 2
+
+
+def revert_albanian(document):
+ "Set language Albanian to English"
+ i = 0
+ if document.language == "albanian":
+ document.language = "english"
+ i = find_token(document.header, "\\language", 0)
+ if i != -1:
+ document.header[i] = "\\language english"
+ j = 0
+ while True:
+ j = find_token(document.body, "\\lang albanian", j)
+ if j == -1:
+ return
+ document.body[j] = document.body[j].replace("\\lang albanian", "\\lang english")
+ j = j + 1
+
+
+def revert_lowersorbian(document):
+ "Set language lower Sorbian to English"
+ i = 0
+ if document.language == "lowersorbian":
+ document.language = "english"
+ i = find_token(document.header, "\\language", 0)
+ if i != -1:
+ document.header[i] = "\\language english"
+ j = 0
+ while True:
+ j = find_token(document.body, "\\lang lowersorbian", j)
+ if j == -1:
+ return
+ document.body[j] = document.body[j].replace("\\lang lowersorbian", "\\lang english")
+ j = j + 1
+
+
+def revert_uppersorbian(document):
+ "Set language uppersorbian to usorbian as this was used in LyX 1.5"
+ i = 0
+ if document.language == "uppersorbian":
+ document.language = "usorbian"
+ i = find_token(document.header, "\\language", 0)
+ if i != -1:
+ document.header[i] = "\\language usorbian"
+ j = 0
+ while True:
+ j = find_token(document.body, "\\lang uppersorbian", j)
+ if j == -1:
+ return
+ document.body[j] = document.body[j].replace("\\lang uppersorbian", "\\lang usorbian")
+ j = j + 1
+
+
+def convert_usorbian(document):
+ "Set language usorbian to uppersorbian"
+ i = 0
+ if document.language == "usorbian":
+ document.language = "uppersorbian"
+ i = find_token(document.header, "\\language", 0)
+ if i != -1:
+ document.header[i] = "\\language uppersorbian"
+ j = 0
+ while True:
+ j = find_token(document.body, "\\lang usorbian", j)
+ if j == -1:
+ return
+ document.body[j] = document.body[j].replace("\\lang usorbian", "\\lang uppersorbian")
+ j = j + 1
+
+
+def revert_macro_optional_params(document):
+ "Convert macro definitions with optional parameters into ERTs"
+ # Stub to convert macro definitions with one or more optional parameters
+ # into uninterpreted ERT insets
+
+
+def revert_hyperlinktype(document):
+ 'Reverts hyperlink type'
+ i = 0
+ j = 0
+ while True:
+ i = find_token(document.body, "target", i)
+ if i == -1:
+ return
+ j = find_token(document.body, "type", i)
+ if j == -1:
+ return
+ if j == i + 1:
+ del document.body[j]
+ i = i + 1
+
+
+def revert_pagebreak(document):
+ 'Reverts pagebreak to ERT'
+ i = 0
+ while True:
+ i = find_token(document.body, "\\pagebreak", i)
+ if i == -1:
+ return
+ document.body[i] = '\\begin_inset ERT\nstatus collapsed\n\n' \
+ '\\begin_layout Standard\n\n\n\\backslash\n' \
+ 'pagebreak{}\n\\end_layout\n\n\\end_inset\n\n'
+ i = i + 1
+
+
+def revert_linebreak(document):
+ 'Reverts linebreak to ERT'
+ i = 0
+ while True:
+ i = find_token(document.body, "\\linebreak", i)
+ if i == -1:
+ return
+ document.body[i] = '\\begin_inset ERT\nstatus collapsed\n\n' \
+ '\\begin_layout Standard\n\n\n\\backslash\n' \
+ 'linebreak{}\n\\end_layout\n\n\\end_inset\n\n'
+ i = i + 1
+
+
+def revert_latin(document):
+ "Set language Latin to English"
+ i = 0
+ if document.language == "latin":
+ document.language = "english"
+ i = find_token(document.header, "\\language", 0)
+ if i != -1:
+ document.header[i] = "\\language english"
+ j = 0
+ while True:
+ j = find_token(document.body, "\\lang latin", j)
+ if j == -1:
+ return
+ document.body[j] = document.body[j].replace("\\lang latin", "\\lang english")
+ j = j + 1
+
+
+def revert_samin(document):
+ "Set language North Sami to English"
+ i = 0
+ if document.language == "samin":
+ document.language = "english"
+ i = find_token(document.header, "\\language", 0)
+ if i != -1:
+ document.header[i] = "\\language english"
+ j = 0
+ while True:
+ j = find_token(document.body, "\\lang samin", j)
+ if j == -1:
+ return
+ document.body[j] = document.body[j].replace("\\lang samin", "\\lang english")
+ j = j + 1
+
+
+def convert_serbocroatian(document):
+ "Set language Serbocroatian to Croatian as this was really Croatian in LyX 1.5"
+ i = 0
+ if document.language == "serbocroatian":
+ document.language = "croatian"
+ i = find_token(document.header, "\\language", 0)
+ if i != -1:
+ document.header[i] = "\\language croatian"
+ j = 0
+ while True:
+ j = find_token(document.body, "\\lang serbocroatian", j)
+ if j == -1:
+ return
+ document.body[j] = document.body[j].replace("\\lang serbocroatian", "\\lang croatian")
+ j = j + 1
+
+
+def convert_framed_notes(document):
+ "Convert framed notes to boxes. "
+ i = 0
+ while 1:
+ i = find_tokens(document.body, ["\\begin_inset Note Framed", "\\begin_inset Note Shaded"], i)
+
+ if i == -1:
+ return
+ document.body[i] = document.body[i].replace("\\begin_inset Note", "\\begin_inset Box")
+ document.body.insert(i + 1, 'position "t"\nhor_pos "c"\nhas_inner_box 0\ninner_pos "t"\n' \
+ 'use_parbox 0\nwidth "100col%"\nspecial "none"\nheight "1in"\n' \
+ 'height_special "totalheight"')
+ i = i + 1
+
+
+def revert_framed_notes(document):
+ "Revert framed boxes to notes. "
+ i = 0
+ while 1:
+ i = find_tokens(document.body, ["\\begin_inset Box Framed", "\\begin_inset Box Shaded"], i)
+
+ if i == -1:
+ return
+ j = find_end_of_inset(document.body, i + 1)
+ if j == -1:
+ # should not happen
+ document.warning("Malformed LyX document: Could not find end of Box inset.")
+ k = find_token(document.body, "status", i + 1, j)
+ if k == -1:
+ document.warning("Malformed LyX document: Missing `status' tag in Box inset.")
+ return
+ status = document.body[k]
+ l = find_token(document.body, "\\begin_layout Standard", i + 1, j)
+ if l == -1:
+ document.warning("Malformed LyX document: Missing `\\begin_layout Standard' in Box inset.")
+ return
+ m = find_token(document.body, "\\end_layout", i + 1, j)
+ if m == -1:
+ document.warning("Malformed LyX document: Missing `\\end_layout' in Box inset.")
+ return
+ ibox = find_token(document.body, "has_inner_box 1", i + 1, k)
+ pbox = find_token(document.body, "use_parbox 1", i + 1, k)
+ if ibox == -1 and pbox == -1:
+ document.body[i] = document.body[i].replace("\\begin_inset Box", "\\begin_inset Note")
+ del document.body[i+1:k]
+ else:
+ document.body[i] = document.body[i].replace("\\begin_inset Box Shaded", "\\begin_inset Box Frameless")
+ document.body.insert(l + 1, "\\begin_inset Note Shaded\n" + status + "\n\\begin_layout Standard\n")
+ document.body.insert(m + 1, "\\end_layout\n\\end_inset")
+ i = i + 1
+
+
+def revert_slash(document):
+ 'Revert \\SpecialChar \\slash{} to ERT'
+ for i in range(len(document.body)):
+ document.body[i] = document.body[i].replace('\\SpecialChar \\slash{}', \
+ '\\begin_inset ERT\nstatus collapsed\n\n' \
+ '\\begin_layout Standard\n\n\n\\backslash\n' \
+ 'slash{}\n\\end_layout\n\n\\end_inset\n\n')
+
+
+def revert_nobreakdash(document):
+ 'Revert \\SpecialChar \\nobreakdash- to ERT'
+ found = 0
+ for i in range(len(document.body)):
+ line = document.body[i]
+ r = re.compile(r'\\SpecialChar \\nobreakdash-')
+ m = r.match(line)
+ if m:
+ found = 1
+ document.body[i] = document.body[i].replace('\\SpecialChar \\nobreakdash-', \
+ '\\begin_inset ERT\nstatus collapsed\n\n' \
+ '\\begin_layout Standard\n\n\n\\backslash\n' \
+ 'nobreakdash-\n\\end_layout\n\n\\end_inset\n\n')
+ if not found:
+ return
+ j = find_token(document.header, "\\use_amsmath", 0)
+ if j == -1:
+ document.warning("Malformed LyX document: Missing '\\use_amsmath'.")
+ return
+ document.header[j] = "\\use_amsmath 2"
+
+
+def revert_nocite_key(body, start, end):
+ 'key "..." -> \nocite{...}'
+ for i in range(start, end):
+ if (body[i][0:5] == 'key "'):
+ body[i] = body[i].replace('key "', "\\backslash\nnocite{")
+ body[i] = body[i].replace('"', "}")
+ else:
+ body[i] = ""
+
+
+def revert_nocite(document):
+ "Revert LatexCommand nocite to ERT"
+ i = 0
+ while 1:
+ i = find_token(document.body, "\\begin_inset CommandInset citation", i)
+ if i == -1:
+ return
+ i = i + 1
+ if (document.body[i] == "LatexCommand nocite"):
+ j = find_end_of_inset(document.body, i + 1)
+ if j == -1:
+ #this should not happen
+ document.warning("End of CommandInset citation not found in revert_nocite!")
+ revert_nocite_key(document.body, i + 1, len(document.body))
+ return
+ revert_nocite_key(document.body, i + 1, j)
+ document.body[i-1] = "\\begin_inset ERT"
+ document.body[i] = "status collapsed\n\n" \
+ "\\begin_layout Standard"
+ document.body.insert(j, "\\end_layout\n");
+ i = j
+
+
+def revert_btprintall(document):
+ "Revert (non-bibtopic) btPrintAll option to ERT \nocite{*}"
+ i = find_token(document.header, '\\use_bibtopic', 0)
+ if i == -1:
+ document.warning("Malformed lyx document: Missing '\\use_bibtopic'.")
+ return
+ if get_value(document.header, '\\use_bibtopic', 0) == "false":
+ i = 0
+ while i < len(document.body):
+ i = find_token(document.body, "\\begin_inset CommandInset bibtex", i)
+ if i == -1:
+ return
+ j = find_end_of_inset(document.body, i + 1)
+ if j == -1:
+ #this should not happen
+ document.warning("End of CommandInset bibtex not found in revert_btprintall!")
+ j = len(document.body)
+ for k in range(i, j):
+ if (document.body[k] == 'btprint "btPrintAll"'):
+ del document.body[k]
+ document.body.insert(i, "\\begin_inset ERT\n" \
+ "status collapsed\n\n\\begin_layout Standard\n\n" \
+ "\\backslash\nnocite{*}\n" \
+ "\\end_layout\n\\end_inset\n")
+ i = j
+
+
+def revert_bahasam(document):
+ "Set language Bahasa Malaysia to Bahasa Indonesia"
+ i = 0
+ if document.language == "bahasam":
+ document.language = "bahasa"
+ i = find_token(document.header, "\\language", 0)
+ if i != -1:
+ document.header[i] = "\\language bahasa"
+ j = 0
+ while True:
+ j = find_token(document.body, "\\lang bahasam", j)
+ if j == -1:
+ return
+ document.body[j] = document.body[j].replace("\\lang bahasam", "\\lang bahasa")
+ j = j + 1
+
+
+def revert_interlingua(document):
+ "Set language Interlingua to English"
+ i = 0
+ if document.language == "interlingua":
+ document.language = "english"
+ i = find_token(document.header, "\\language", 0)
+ if i != -1:
+ document.header[i] = "\\language english"
+ j = 0
+ while True:
+ j = find_token(document.body, "\\lang interlingua", j)
+ if j == -1:
+ return
+ document.body[j] = document.body[j].replace("\\lang interlingua", "\\lang english")
+ j = j + 1
+
+
+def revert_serbianlatin(document):
+ "Set language Serbian-Latin to Croatian"
+ i = 0
+ if document.language == "serbian-latin":
+ document.language = "croatian"
+ i = find_token(document.header, "\\language", 0)
+ if i != -1:
+ document.header[i] = "\\language croatian"
+ j = 0
+ while True:
+ j = find_token(document.body, "\\lang serbian-latin", j)
+ if j == -1:
+ return
+ document.body[j] = document.body[j].replace("\\lang serbian-latin", "\\lang croatian")
+ j = j + 1
+
+
##
# Conversion hub
#
[292, []],
[293, []],
[294, [convert_pdf_options]],
- [295, [convert_htmlurl, convert_url]]
+ [295, [convert_htmlurl, convert_url]],
+ [296, [convert_include]],
+ [297, [convert_usorbian]],
+ [298, []],
+ [299, []],
+ [300, []],
+ [301, []],
+ [302, []],
+ [303, [convert_serbocroatian]],
+ [304, [convert_framed_notes]],
+ [305, []],
+ [306, []],
+ [307, []],
+ [308, []],
+ [309, []],
+ [310, []],
+ [311, [convert_ams_classes]]
]
-revert = [[294, [revert_href]],
+revert = [[310, []],
+ [309, [revert_btprintall]],
+ [308, [revert_nocite]],
+ [307, [revert_serbianlatin]],
+ [306, [revert_slash, revert_nobreakdash]],
+ [305, [revert_interlingua]],
+ [304, [revert_bahasam]],
+ [303, [revert_framed_notes]],
+ [302, []],
+ [301, [revert_latin, revert_samin]],
+ [300, [revert_linebreak]],
+ [299, [revert_pagebreak]],
+ [298, [revert_hyperlinktype]],
+ [297, [revert_macro_optional_params]],
+ [296, [revert_albanian, revert_lowersorbian, revert_uppersorbian]],
+ [295, [revert_include]],
+ [294, [revert_href]],
[293, [revert_pdf_options_2]],
[292, [revert_inset_info]],
[291, [revert_japanese, revert_japanese_encoding]],