lib/scripts/layout2layout.py

   1 #! /usr/bin/env python
   2 # -*- coding: utf-8 -*-
   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 3
  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*)$')
  70     re_Format = re.compile(r'^(\s*)(Format)(\s+)(\S+)', re.IGNORECASE)
  71     re_Preamble = re.compile(r'^(\s*)Preamble', re.IGNORECASE)
  72     re_EndPreamble = re.compile(r'^(\s*)EndPreamble', re.IGNORECASE)
  73     re_MaxCounter = re.compile(r'^(\s*)(MaxCounter)(\s+)(\S+)', re.IGNORECASE)
  74     re_LabelType = re.compile(r'^(\s*)(LabelType)(\s+)(\S+)', re.IGNORECASE)
  75     re_LabelString = re.compile(r'^(\s*)(LabelString)(\s+)(("[^"]+")|(\S+))', re.IGNORECASE)
  76     re_LabelStringAppendix = re.compile(r'^(\s*)(LabelStringAppendix)(\s+)(("[^"]+")|(\S+))', re.IGNORECASE)
  77     re_LatexType = re.compile(r'^(\s*)(LatexType)(\s+)(\S+)', re.IGNORECASE)
  78     re_Style = re.compile(r'^(\s*)(Style)(\s+)(\S+)', re.IGNORECASE)
  79     re_CopyStyle = re.compile(r'^(\s*)(CopyStyle)(\s+)(\S+)', re.IGNORECASE)
  80     re_NoStyle = re.compile(r'^(\s*)(NoStyle)(\s+)(\S+)', re.IGNORECASE)
  81     re_End = re.compile(r'^(\s*)(End)(\s*)$', re.IGNORECASE)
  82
  83     # counters for sectioning styles (hardcoded in 1.3)
  84     counters = {"part"          : "\\Roman{part}",
  85                 "chapter"       : "\\arabic{chapter}",
  86                 "section"       : "\\arabic{section}",
  87                 "subsection"    : "\\arabic{section}.\\arabic{subsection}",
  88                 "subsubsection" : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}",
  89                 "paragraph"     : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}.\\arabic{paragraph}",
  90                 "subparagraph"  : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}.\\arabic{paragraph}.\\arabic{subparagraph}"}
  91
  92     # counters for sectioning styles in appendix (hardcoded in 1.3)
  93     appendixcounters = {"chapter"       : "\\Alph{chapter}",
  94                         "section"       : "\\Alph{section}",
  95                         "subsection"    : "\\arabic{section}.\\arabic{subsection}",
  96                         "subsubsection" : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}",
  97                         "paragraph"     : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}.\\arabic{paragraph}",
  98                         "subparagraph"  : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}.\\arabic{paragraph}.\\arabic{subparagraph}"}
  99
 100     # Value of TocLevel for sectioning styles
 101     toclevels = {"part"          : 0,
 102                  "chapter"       : 0,
 103                  "section"       : 1,
 104                  "subsection"    : 2,
 105                  "subsubsection" : 3,
 106                  "paragraph"     : 4,
 107                  "subparagraph"  : 5}
 108
 109     i = 0
 110     only_comment = 1
 111     counter = ""
 112     label = ""
 113     labelstring = ""
 114     labelstringappendix = ""
 115     space1 = ""
 116     labelstring_line = -1
 117     labelstringappendix_line = -1
 118     labeltype_line = -1
 119     latextype = ""
 120     latextype_line = -1
 121     style = ""
 122     maxcounter = 0
 123     format = 1
 124     while i < len(lines):
 125
 126         # Skip comments and empty lines
 127         if re_Comment.match(lines[i]) or re_Empty.match(lines[i]):
 128             i = i + 1
 129             continue
 130
 131         # insert file format if not already there
 132         if (only_comment):
 133                 match = re_Format.match(lines[i])
 134                 if match:
 135                         format = int(match.group(4))
 136                         if format == 2:
 137                             lines[i] = "Format 3"
 138                             only_comment = 0
 139                         elif format == 3:
 140                                 # nothing to do
 141                                 return
 142                         else:
 143                             error('Cannot convert file format %s' % format)
 144                 else:
 145                         lines.insert(i, "Format 3")
 146                         only_comment = 0
 147                         continue
 148
 149         # Don't get confused by LaTeX code
 150         if re_Preamble.match(lines[i]):
 151             i = i + 1
 152             while i < len(lines) and not re_EndPreamble.match(lines[i]):
 153                 i = i + 1
 154             continue
 155
 156         if format == 2:
 157             caption = []
 158
 159             # delete caption styles
 160             match = re_Style.match(lines[i])
 161             if match:
 162                 style = string.lower(match.group(4))
 163                 if style == "caption":
 164                     del lines[i]
 165                     while i < len(lines) and not re_End.match(lines[i]):
 166                         caption.append(lines[i])
 167                         del lines[i]
 168                     if i == len(lines):
 169                         error('Incomplete caption style.')
 170                     else:
 171                         del lines[i]
 172                         continue
 173
 174             # delete undefinition of caption styles
 175             match = re_NoStyle.match(lines[i])
 176             if match:
 177                 style = string.lower(match.group(4))
 178                 if style == "caption":
 179                     del lines[i]
 180                     continue
 181
 182             # replace the CopyStyle statement with the definition of the real
 183             # style. This may result in duplicate statements, but that is OK
 184             # since the second one will overwrite the first one.
 185             match = re_CopyStyle.match(lines[i])
 186             if match:
 187                 style = string.lower(match.group(4))
 188                 if style == "caption":
 189                     if len(caption) > 0:
 190                         lines[i:i+1] = caption
 191                     else:
 192                         # FIXME: This style comes from an include file, we
 193                         # should replace the real style and not this default.
 194                         lines[i:i+1] = ['       Margin                First_Dynamic',
 195                                         '       LatexType             Command',
 196                                         '       LatexName             caption',
 197                                         '       NeedProtect           1',
 198                                         '       LabelSep              xx',
 199                                         '       ParSkip               0.4',
 200                                         '       TopSep                0.5',
 201                                         '       Align                 Center',
 202                                         '       AlignPossible         Center',
 203                                         '       LabelType             Sensitive',
 204                                         '       LabelString           "Senseless!"',
 205                                         '       OptionalArgs          1',
 206                                         '       LabelFont',
 207                                         '         Series              Bold',
 208                                         '       EndFont']
 209
 210             i = i + 1
 211             continue
 212
 213         # Delete MaxCounter and remember the value of it
 214         match = re_MaxCounter.match(lines[i])
 215         if match:
 216             level = match.group(4)
 217             if string.lower(level) == "counter_chapter":
 218                 maxcounter = 0
 219             elif string.lower(level) == "counter_section":
 220                 maxcounter = 1
 221             elif string.lower(level) == "counter_subsection":
 222                 maxcounter = 2
 223             elif string.lower(level) == "counter_subsubsection":
 224                 maxcounter = 3
 225             elif string.lower(level) == "counter_paragraph":
 226                 maxcounter = 4
 227             elif string.lower(level) == "counter_subparagraph":
 228                 maxcounter = 5
 229             elif string.lower(level) == "counter_enumi":
 230                 maxcounter = 6
 231             elif string.lower(level) == "counter_enumii":
 232                 maxcounter = 7
 233             elif string.lower(level) == "counter_enumiii":
 234                 maxcounter = 8
 235             del lines[i]
 236             continue
 237
 238         # Replace line
 239         #
 240         # LabelType Counter_EnumI
 241         #
 242         # with two lines
 243         #
 244         # LabelType Counter
 245         # LabelCounter EnumI
 246         #
 247         match = re_LabelType.match(lines[i])
 248         if match:
 249             label = match.group(4)
 250             # Remember indenting space for later reuse in added lines
 251             space1 = match.group(1)
 252             # Remember the line for adding the LabelCounter later.
 253             # We can't do it here because it could shift latextype_line etc.
 254             labeltype_line = i
 255             if string.lower(label[:8]) == "counter_":
 256                 counter = string.lower(label[8:])
 257                 lines[i] = re_LabelType.sub(r'\1\2\3Counter', lines[i])
 258
 259         # Remember the LabelString line
 260         match = re_LabelString.match(lines[i])
 261         if match:
 262             labelstring = match.group(4)
 263             labelstring_line = i
 264
 265         # Remember the LabelStringAppendix line
 266         match = re_LabelStringAppendix.match(lines[i])
 267         if match:
 268             labelstringappendix = match.group(4)
 269             labelstringappendix_line = i
 270
 271         # Remember the LatexType line
 272         match = re_LatexType.match(lines[i])
 273         if match:
 274             latextype = string.lower(match.group(4))
 275             latextype_line = i
 276
 277         # Reset variables at the beginning of a style definition
 278         match = re_Style.match(lines[i])
 279         if match:
 280             style = string.lower(match.group(4))
 281             counter = ""
 282             label = ""
 283             space1 = ""
 284             labelstring = ""
 285             labelstringappendix = ""
 286             labelstring_line = -1
 287             labelstringappendix_line = -1
 288             labeltype_line = -1
 289             latextype = ""
 290             latextype_line = -1
 291
 292         if re_End.match(lines[i]):
 293
 294             # Add a line "LatexType Bib_Environment" if LabelType is Bibliography
 295             # (or change the existing LatexType)
 296             if string.lower(label) == "bibliography":
 297                 if (latextype_line < 0):
 298                     lines.insert(i, "%sLatexType Bib_Environment" % space1)
 299                     i = i + 1
 300                 else:
 301                     lines[latextype_line] = re_LatexType.sub(r'\1\2\3Bib_Environment', lines[latextype_line])
 302
 303             # Change "LabelType Static" to "LabelType Itemize" for itemize environments
 304             if latextype == "item_environment" and string.lower(label) == "static":
 305                 lines[labeltype_line] = re_LabelType.sub(r'\1\2\3Itemize', lines[labeltype_line])
 306
 307             # Change "LabelType Counter_EnumI" to "LabelType Enumerate" for enumerate environments
 308             if latextype == "item_environment" and string.lower(label) == "counter_enumi":
 309                 lines[labeltype_line] = re_LabelType.sub(r'\1\2\3Enumerate', lines[labeltype_line])
 310                 # Don't add the LabelCounter line later
 311                 counter = ""
 312
 313             # Replace
 314             #
 315             # LabelString "Chapter"
 316             #
 317             # with
 318             #
 319             # LabelString "Chapter \arabic{chapter}"
 320             #
 321             # if this style has a counter. Ditto for LabelStringAppendix.
 322             # This emulates the hardcoded article style numbering of 1.3
 323             #
 324             if counter != "":
 325                 if counters.has_key(style):
 326                     if labelstring_line < 0:
 327                         lines.insert(i, '%sLabelString "%s"' % (space1, counters[style]))
 328                         i = i + 1
 329                     else:
 330                         new_labelstring = concatenate_label(labelstring, counters[style])
 331                         lines[labelstring_line] = re_LabelString.sub(
 332                                 r'\1\2\3%s' % new_labelstring.replace("\\", "\\\\"),
 333                                 lines[labelstring_line])
 334                 if appendixcounters.has_key(style):
 335                     if labelstringappendix_line < 0:
 336                         lines.insert(i, '%sLabelStringAppendix "%s"' % (space1, appendixcounters[style]))
 337                         i = i + 1
 338                     else:
 339                         new_labelstring = concatenate_label(labelstring, appendixcounters[style])
 340                         lines[labelstringappendix_line] = re_LabelStringAppendix.sub(
 341                                 r'\1\2\3%s' % new_labelstring.replace("\\", "\\\\"),
 342                                 lines[labelstringappendix_line])
 343
 344                 # Now we can safely add the LabelCounter line
 345                 lines.insert(labeltype_line + 1, "%sLabelCounter %s" % (space1, counter))
 346                 i = i + 1
 347
 348             # Add the TocLevel setting for sectioning styles
 349             if toclevels.has_key(style) and maxcounter <= toclevels[style]:
 350                 lines.insert(i, '%sTocLevel %d' % (space1, toclevels[style]))
 351                 i = i + 1
 352
 353         i = i + 1
 354
 355
 356 def main(argv):
 357
 358     # Open files
 359     if len(argv) == 1:
 360         input = sys.stdin
 361         output = sys.stdout
 362     elif len(argv) == 3:
 363         input = open(argv[1], 'rb')
 364         output = open(argv[2], 'wb')
 365     else:
 366         error(usage(argv[0]))
 367
 368     # Do the real work
 369     lines = read(input)
 370     convert(lines)
 371     write(output, lines)
 372
 373     # Close files
 374     if len(argv) == 3:
 375         input.close()
 376         output.close()
 377
 378     return 0
 379
 380
 381 if __name__ == "__main__":
 382     main(sys.argv)