lib/scripts/layout2layout.py

   1 #! /usr/bin/env python
   2 # -*- coding: iso-8859-1 -*-
   3
   4 # file layout2layout.py
   5 # This file is part of LyX, the document processor.
   6 # Licence details can be found in the file COPYING.
   7
   8 # author Georg Baum
   9
  10 # Full author contact details are available in file CREDITS
  11
  12 # This script will update a .layout file to format 2
  13
  14
  15 import os, re, string, sys
  16
  17
  18 def usage(prog_name):
  19     return ("Usage: %s inputfile outputfile\n" % prog_name +
  20             "or     %s <inputfile >outputfile" % prog_name)
  21
  22
  23 def error(message):
  24     sys.stderr.write(message + '\n')
  25     sys.exit(1)
  26
  27
  28 def trim_eol(line):
  29     " Remove end of line char(s)."
  30     if line[-2:-1] == '\r':
  31         return line[:-2]
  32     elif line[-1:] == '\r' or line[-1:] == '\n':
  33         return line[:-1]
  34     else:
  35         # file with no EOL in last line
  36         return line
  37
  38
  39 def read(input):
  40     " Read input file and strip lineendings."
  41     lines = list()
  42     while 1:
  43         line = input.readline()
  44         if not line:
  45             break
  46         lines.append(trim_eol(line))
  47     return lines
  48
  49
  50 def write(output, lines):
  51     " Write output file with native lineendings."
  52     for line in lines:
  53         output.write(line + os.linesep)
  54
  55
  56 # Concatenates old and new in an intelligent way:
  57 # If old is wrapped in ", they are stripped. The result is wrapped in ".
  58 def concatenate_label(old, new):
  59     # Don't use strip as long as we support python 1.5.2
  60     if old[0] == '"':
  61         return old[0:-1] + new + '"'
  62     else:
  63         return '"' + old + new + '"'
  64
  65
  66 def convert(lines):
  67     " Convert to new format."
  68     re_Comment = re.compile(r'^(\s*)#')
  69     re_Empty = re.compile(r'^(\s*)$')
  70     re_Format = re.compile(r'^(\s*)(Format)(\s+)(\S+)', re.IGNORECASE)
  71     re_Preamble = re.compile(r'^(\s*)Preamble', re.IGNORECASE)
  72     re_EndPreamble = re.compile(r'^(\s*)EndPreamble', re.IGNORECASE)
  73     re_MaxCounter = re.compile(r'^(\s*)(MaxCounter)(\s+)(\S+)', re.IGNORECASE)
  74     re_LabelType = re.compile(r'^(\s*)(LabelType)(\s+)(\S+)', re.IGNORECASE)
  75     re_LabelString = re.compile(r'^(\s*)(LabelString)(\s+)(("[^"]+")|(\S+))', re.IGNORECASE)
  76     re_LabelStringAppendix = re.compile(r'^(\s*)(LabelStringAppendix)(\s+)(("[^"]+")|(\S+))', re.IGNORECASE)
  77     re_LatexType = re.compile(r'^(\s*)(LatexType)(\s+)(\S+)', re.IGNORECASE)
  78     re_Style = re.compile(r'^(\s*)(Style)(\s+)(\S+)', re.IGNORECASE)
  79     re_End = re.compile(r'^(\s*)(End)(\s*)$', re.IGNORECASE)
  80
  81     # counters for sectioning styles (hardcoded in 1.3)
  82     counters = {"part"          : "\\Roman{part}",
  83                 "chapter"       : "\\arabic{chapter}",
  84                 "section"       : "\\arabic{section}",
  85                 "subsection"    : "\\arabic{section}.\\arabic{subsection}",
  86                 "subsubsection" : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}",
  87                 "paragraph"     : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}.\\arabic{paragraph}",
  88                 "subparagraph"  : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}.\\arabic{paragraph}.\\arabic{subparagraph}"}
  89
  90     # counters for sectioning styles in appendix (hardcoded in 1.3)
  91     appendixcounters = {"chapter"       : "\\Alph{chapter}",
  92                         "section"       : "\\Alph{section}",
  93                         "subsection"    : "\\arabic{section}.\\arabic{subsection}",
  94                         "subsubsection" : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}",
  95                         "paragraph"     : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}.\\arabic{paragraph}",
  96                         "subparagraph"  : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}.\\arabic{paragraph}.\\arabic{subparagraph}"}
  97
  98     # Value of TocLevel for sectioning styles
  99     toclevels = {"part"          : 0,
 100                  "chapter"       : 0,
 101                  "section"       : 1,
 102                  "subsection"    : 2,
 103                  "subsubsection" : 3,
 104                  "paragraph"     : 4,
 105                  "subparagraph"  : 5}
 106
 107     i = 0
 108     only_comment = 1
 109     counter = ""
 110     label = ""
 111     labelstring = ""
 112     labelstringappendix = ""
 113     space1 = ""
 114     labelstring_line = -1
 115     labelstringappendix_line = -1
 116     labeltype_line = -1
 117     latextype = ""
 118     latextype_line = -1
 119     style = ""
 120     maxcounter = 0
 121     while i < len(lines):
 122
 123         # Skip comments and empty lines
 124         if re_Comment.match(lines[i]) or re_Empty.match(lines[i]):
 125             i = i + 1
 126             continue
 127
 128         # insert file format if not already there
 129         if (only_comment):
 130                 match = re_Format.match(lines[i])
 131                 if match:
 132                         format = match.group(4)
 133                         if format == '2':
 134                                 # nothing to do
 135                                 return
 136                         error('Cannot convert file format %s' % format)
 137                 else:
 138                         lines.insert(i, "Format 2")
 139                         only_comment = 0
 140                         continue
 141
 142         # Don't get confused by LaTeX code
 143         if re_Preamble.match(lines[i]):
 144             i = i + 1
 145             while i < len(lines) and not re_EndPreamble.match(lines[i]):
 146                 i = i + 1
 147             continue
 148
 149         # Delete MaxCounter and remember the value of it
 150         match = re_MaxCounter.match(lines[i])
 151         if match:
 152             level = match.group(4)
 153             if string.lower(level) == "counter_chapter":
 154                 maxcounter = 0
 155             elif string.lower(level) == "counter_section":
 156                 maxcounter = 1
 157             elif string.lower(level) == "counter_subsection":
 158                 maxcounter = 2
 159             elif string.lower(level) == "counter_subsubsection":
 160                 maxcounter = 3
 161             elif string.lower(level) == "counter_paragraph":
 162                 maxcounter = 4
 163             elif string.lower(level) == "counter_subparagraph":
 164                 maxcounter = 5
 165             elif string.lower(level) == "counter_enumi":
 166                 maxcounter = 6
 167             elif string.lower(level) == "counter_enumii":
 168                 maxcounter = 7
 169             elif string.lower(level) == "counter_enumiii":
 170                 maxcounter = 8
 171             del lines[i]
 172             continue
 173
 174         # Replace line
 175         #
 176         # LabelType Counter_EnumI
 177         #
 178         # with two lines
 179         #
 180         # LabelType Counter
 181         # LabelCounter EnumI
 182         #
 183         match = re_LabelType.match(lines[i])
 184         if match:
 185             label = match.group(4)
 186             # Remember indenting space for later reuse in added lines
 187             space1 = match.group(1)
 188             # Remember the line for adding the LabelCounter later.
 189             # We can't do it here because it could shift latextype_line etc.
 190             labeltype_line = i
 191             if string.lower(label[:8]) == "counter_":
 192                 counter = string.lower(label[8:])
 193                 lines[i] = re_LabelType.sub(r'\1\2\3Counter', lines[i])
 194
 195         # Remember the LabelString line
 196         match = re_LabelString.match(lines[i])
 197         if match:
 198             labelstring = match.group(4)
 199             labelstring_line = i
 200
 201         # Remember the LabelStringAppendix line
 202         match = re_LabelStringAppendix.match(lines[i])
 203         if match:
 204             labelstringappendix = match.group(4)
 205             labelstringappendix_line = i
 206
 207         # Remember the LatexType line
 208         match = re_LatexType.match(lines[i])
 209         if match:
 210             latextype = string.lower(match.group(4))
 211             latextype_line = i
 212
 213         # Reset variables at the beginning of a style definition
 214         match = re_Style.match(lines[i])
 215         if match:
 216             style = string.lower(match.group(4))
 217             counter = ""
 218             label = ""
 219             space1 = ""
 220             labelstring = ""
 221             labelstringappendix = ""
 222             labelstring_line = -1
 223             labelstringappendix_line = -1
 224             labeltype_line = -1
 225             latextype = ""
 226             latextype_line = -1
 227
 228         if re_End.match(lines[i]):
 229
 230             # Add a line "LatexType Bib_Environment" if LabelType is Bibliography
 231             # (or change the existing LatexType)
 232             if string.lower(label) == "bibliography":
 233                 if (latextype_line < 0):
 234                     lines.insert(i, "%sLatexType Bib_Environment" % space1)
 235                     i = i + 1
 236                 else:
 237                     lines[latextype_line] = re_LatexType.sub(r'\1\2\3Bib_Environment', lines[latextype_line])
 238
 239             # Change "LabelType Static" to "LabelType Itemize" for itemize environments
 240             if latextype == "item_environment" and string.lower(label) == "static":
 241                 lines[labeltype_line] = re_LabelType.sub(r'\1\2\3Itemize', lines[labeltype_line])
 242
 243             # Change "LabelType Counter_EnumI" to "LabelType Enumerate" for enumerate environments
 244             if latextype == "item_environment" and string.lower(label) == "counter_enumi":
 245                 lines[labeltype_line] = re_LabelType.sub(r'\1\2\3Enumerate', lines[labeltype_line])
 246                 # Don't add the LabelCounter line later
 247                 counter = ""
 248
 249             # Replace
 250             #
 251             # LabelString "Chapter"
 252             #
 253             # with
 254             #
 255             # LabelString "Chapter \arabic{chapter}"
 256             #
 257             # if this style has a counter. Ditto for LabelStringAppendix.
 258             # This emulates the hardcoded article style numbering of 1.3
 259             #
 260             if counter != "":
 261                 if counters.has_key(style):
 262                     if labelstring_line < 0:
 263                         lines.insert(i, '%sLabelString "%s"' % (space1, counters[style]))
 264                         i = i + 1
 265                     else:
 266                         new_labelstring = concatenate_label(labelstring, counters[style])
 267                         lines[labelstring_line] = re_LabelString.sub(
 268                                 r'\1\2\3%s' % new_labelstring.replace("\\", "\\\\"),
 269                                 lines[labelstring_line])
 270                 if appendixcounters.has_key(style):
 271                     if labelstringappendix_line < 0:
 272                         lines.insert(i, '%sLabelStringAppendix "%s"' % (space1, appendixcounters[style]))
 273                         i = i + 1
 274                     else:
 275                         new_labelstring = concatenate_label(labelstring, appendixcounters[style])
 276                         lines[labelstringappendix_line] = re_LabelStringAppendix.sub(
 277                                 r'\1\2\3%s' % new_labelstring.replace("\\", "\\\\"),
 278                                 lines[labelstringappendix_line])
 279
 280                 # Now we can safely add the LabelCounter line
 281                 lines.insert(labeltype_line + 1, "%sLabelCounter %s" % (space1, counter))
 282                 i = i + 1
 283
 284             # Add the TocLevel setting for sectioning styles
 285             if toclevels.has_key(style) and maxcounter <= toclevels[style]:
 286                 lines.insert(i, '%sTocLevel %d' % (space1, toclevels[style]))
 287                 i = i + 1
 288
 289         i = i + 1
 290
 291
 292 def main(argv):
 293
 294     # Open files
 295     if len(argv) == 1:
 296         input = sys.stdin
 297         output = sys.stdout
 298     elif len(argv) == 3:
 299         input = open(argv[1], 'rb')
 300         output = open(argv[2], 'wb')
 301     else:
 302         error(usage(argv[0]))
 303
 304     # Do the real work
 305     lines = read(input)
 306     convert(lines)
 307     write(output, lines)
 308
 309     # Close files
 310     if len(argv) == 3:
 311         input.close()
 312         output.close()
 313
 314     return 0
 315
 316
 317 if __name__ == "__main__":
 318     main(sys.argv)