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     re_Provides = re.compile(r'^(\s*)Provides(\S+)(\s+)(\S+)', re.IGNORECASE)
  83     re_CharStyle = re.compile(r'^(\s*)CharStyle(\s+)(\S+)$', re.IGNORECASE)
  84
  85     # counters for sectioning styles (hardcoded in 1.3)
  86     counters = {"part"          : "\\Roman{part}",
  87                 "chapter"       : "\\arabic{chapter}",
  88                 "section"       : "\\arabic{section}",
  89                 "subsection"    : "\\arabic{section}.\\arabic{subsection}",
  90                 "subsubsection" : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}",
  91                 "paragraph"     : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}.\\arabic{paragraph}",
  92                 "subparagraph"  : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}.\\arabic{paragraph}.\\arabic{subparagraph}"}
  93
  94     # counters for sectioning styles in appendix (hardcoded in 1.3)
  95     appendixcounters = {"chapter"       : "\\Alph{chapter}",
  96                         "section"       : "\\Alph{section}",
  97                         "subsection"    : "\\arabic{section}.\\arabic{subsection}",
  98                         "subsubsection" : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}",
  99                         "paragraph"     : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}.\\arabic{paragraph}",
 100                         "subparagraph"  : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}.\\arabic{paragraph}.\\arabic{subparagraph}"}
 101
 102     # Value of TocLevel for sectioning styles
 103     toclevels = {"part"          : 0,
 104                  "chapter"       : 0,
 105                  "section"       : 1,
 106                  "subsection"    : 2,
 107                  "subsubsection" : 3,
 108                  "paragraph"     : 4,
 109                  "subparagraph"  : 5}
 110
 111     i = 0
 112     only_comment = 1
 113     counter = ""
 114     label = ""
 115     labelstring = ""
 116     labelstringappendix = ""
 117     space1 = ""
 118     labelstring_line = -1
 119     labelstringappendix_line = -1
 120     labeltype_line = -1
 121     latextype = ""
 122     latextype_line = -1
 123     style = ""
 124     maxcounter = 0
 125     format = 1
 126     while i < len(lines):
 127
 128         # Skip comments and empty lines
 129         if re_Comment.match(lines[i]) or re_Empty.match(lines[i]):
 130             i += 1
 131             continue
 132
 133         # insert file format if not already there
 134         if (only_comment):
 135                 match = re_Format.match(lines[i])
 136                 if match:
 137                         format = int(match.group(4))
 138                         if format > 1 and format < 5:
 139                             lines[i] = "Format %d" % (format + 1)
 140                             only_comment = 0
 141                         elif format == 5:
 142                                 # nothing to do
 143                                 return format
 144                         else:
 145                             error('Cannot convert file format %s' % format)
 146                 else:
 147                         lines.insert(i, "Format 2")
 148                         only_comment = 0
 149                         continue
 150
 151         # Don't get confused by LaTeX code
 152         if re_Preamble.match(lines[i]):
 153             i += 1
 154             while i < len(lines) and not re_EndPreamble.match(lines[i]):
 155                 i += 1
 156             continue
 157
 158         if format == 4:
 159             # Handle conversion to long CharStyle names
 160             match = re_CharStyle.match(lines[i])
 161             if match:
 162                 lines[i] = "InsetLayout CharStyle:%s" % (match.group(3))
 163                 i += 1
 164                 lines.insert(i, "\tLyXType charstyle")
 165                 i += 1
 166                 lines.insert(i, "")
 167                 lines[i] = "\tLabelString %s" % (match.group(3))
 168             i += 1
 169             continue
 170
 171         if format == 3:
 172             # convert 'providesamsmath x',  'providesmakeidx x',  'providesnatbib x',  'providesurl x' to
 173             #         'provides amsmath x', 'provides makeidx x', 'provides natbib x', 'provides url x'
 174             # x is either 0 or 1
 175             match = re_Provides.match(lines[i])
 176             if match:
 177                 lines[i] = "%sProvides %s%s%s" % (match.group(1), match.group(2).lower(),
 178                                                   match.group(3), match.group(4))
 179             i += 1
 180             continue
 181
 182         if format == 2:
 183             caption = []
 184
 185             # delete caption styles
 186             match = re_Style.match(lines[i])
 187             if match:
 188                 style = string.lower(match.group(4))
 189                 if style == "caption":
 190                     del lines[i]
 191                     while i < len(lines) and not re_End.match(lines[i]):
 192                         caption.append(lines[i])
 193                         del lines[i]
 194                     if i == len(lines):
 195                         error('Incomplete caption style.')
 196                     else:
 197                         del lines[i]
 198                         continue
 199
 200             # delete undefinition of caption styles
 201             match = re_NoStyle.match(lines[i])
 202             if match:
 203                 style = string.lower(match.group(4))
 204                 if style == "caption":
 205                     del lines[i]
 206                     continue
 207
 208             # replace the CopyStyle statement with the definition of the real
 209             # style. This may result in duplicate statements, but that is OK
 210             # since the second one will overwrite the first one.
 211             match = re_CopyStyle.match(lines[i])
 212             if match:
 213                 style = string.lower(match.group(4))
 214                 if style == "caption":
 215                     if len(caption) > 0:
 216                         lines[i:i+1] = caption
 217                     else:
 218                         # FIXME: This style comes from an include file, we
 219                         # should replace the real style and not this default.
 220                         lines[i:i+1] = ['       Margin                First_Dynamic',
 221                                         '       LatexType             Command',
 222                                         '       LatexName             caption',
 223                                         '       NeedProtect           1',
 224                                         '       LabelSep              xx',
 225                                         '       ParSkip               0.4',
 226                                         '       TopSep                0.5',
 227                                         '       Align                 Center',
 228                                         '       AlignPossible         Center',
 229                                         '       LabelType             Sensitive',
 230                                         '       LabelString           "Senseless!"',
 231                                         '       OptionalArgs          1',
 232                                         '       LabelFont',
 233                                         '         Series              Bold',
 234                                         '       EndFont']
 235
 236             i += 1
 237             continue
 238
 239         # Delete MaxCounter and remember the value of it
 240         match = re_MaxCounter.match(lines[i])
 241         if match:
 242             level = match.group(4)
 243             if string.lower(level) == "counter_chapter":
 244                 maxcounter = 0
 245             elif string.lower(level) == "counter_section":
 246                 maxcounter = 1
 247             elif string.lower(level) == "counter_subsection":
 248                 maxcounter = 2
 249             elif string.lower(level) == "counter_subsubsection":
 250                 maxcounter = 3
 251             elif string.lower(level) == "counter_paragraph":
 252                 maxcounter = 4
 253             elif string.lower(level) == "counter_subparagraph":
 254                 maxcounter = 5
 255             elif string.lower(level) == "counter_enumi":
 256                 maxcounter = 6
 257             elif string.lower(level) == "counter_enumii":
 258                 maxcounter = 7
 259             elif string.lower(level) == "counter_enumiii":
 260                 maxcounter = 8
 261             del lines[i]
 262             continue
 263
 264         # Replace line
 265         #
 266         # LabelType Counter_EnumI
 267         #
 268         # with two lines
 269         #
 270         # LabelType Counter
 271         # LabelCounter EnumI
 272         #
 273         match = re_LabelType.match(lines[i])
 274         if match:
 275             label = match.group(4)
 276             # Remember indenting space for later reuse in added lines
 277             space1 = match.group(1)
 278             # Remember the line for adding the LabelCounter later.
 279             # We can't do it here because it could shift latextype_line etc.
 280             labeltype_line = i
 281             if string.lower(label[:8]) == "counter_":
 282                 counter = string.lower(label[8:])
 283                 lines[i] = re_LabelType.sub(r'\1\2\3Counter', lines[i])
 284
 285         # Remember the LabelString line
 286         match = re_LabelString.match(lines[i])
 287         if match:
 288             labelstring = match.group(4)
 289             labelstring_line = i
 290
 291         # Remember the LabelStringAppendix line
 292         match = re_LabelStringAppendix.match(lines[i])
 293         if match:
 294             labelstringappendix = match.group(4)
 295             labelstringappendix_line = i
 296
 297         # Remember the LatexType line
 298         match = re_LatexType.match(lines[i])
 299         if match:
 300             latextype = string.lower(match.group(4))
 301             latextype_line = i
 302
 303         # Reset variables at the beginning of a style definition
 304         match = re_Style.match(lines[i])
 305         if match:
 306             style = string.lower(match.group(4))
 307             counter = ""
 308             label = ""
 309             space1 = ""
 310             labelstring = ""
 311             labelstringappendix = ""
 312             labelstring_line = -1
 313             labelstringappendix_line = -1
 314             labeltype_line = -1
 315             latextype = ""
 316             latextype_line = -1
 317
 318         if re_End.match(lines[i]):
 319
 320             # Add a line "LatexType Bib_Environment" if LabelType is Bibliography
 321             # (or change the existing LatexType)
 322             if string.lower(label) == "bibliography":
 323                 if (latextype_line < 0):
 324                     lines.insert(i, "%sLatexType Bib_Environment" % space1)
 325                     i += 1
 326                 else:
 327                     lines[latextype_line] = re_LatexType.sub(r'\1\2\3Bib_Environment', lines[latextype_line])
 328
 329             # Change "LabelType Static" to "LabelType Itemize" for itemize environments
 330             if latextype == "item_environment" and string.lower(label) == "static":
 331                 lines[labeltype_line] = re_LabelType.sub(r'\1\2\3Itemize', lines[labeltype_line])
 332
 333             # Change "LabelType Counter_EnumI" to "LabelType Enumerate" for enumerate environments
 334             if latextype == "item_environment" and string.lower(label) == "counter_enumi":
 335                 lines[labeltype_line] = re_LabelType.sub(r'\1\2\3Enumerate', lines[labeltype_line])
 336                 # Don't add the LabelCounter line later
 337                 counter = ""
 338
 339             # Replace
 340             #
 341             # LabelString "Chapter"
 342             #
 343             # with
 344             #
 345             # LabelString "Chapter \arabic{chapter}"
 346             #
 347             # if this style has a counter. Ditto for LabelStringAppendix.
 348             # This emulates the hardcoded article style numbering of 1.3
 349             #
 350             if counter != "":
 351                 if counters.has_key(style):
 352                     if labelstring_line < 0:
 353                         lines.insert(i, '%sLabelString "%s"' % (space1, counters[style]))
 354                         i += 1
 355                     else:
 356                         new_labelstring = concatenate_label(labelstring, counters[style])
 357                         lines[labelstring_line] = re_LabelString.sub(
 358                                 r'\1\2\3%s' % new_labelstring.replace("\\", "\\\\"),
 359                                 lines[labelstring_line])
 360                 if appendixcounters.has_key(style):
 361                     if labelstringappendix_line < 0:
 362                         lines.insert(i, '%sLabelStringAppendix "%s"' % (space1, appendixcounters[style]))
 363                         i += 1
 364                     else:
 365                         new_labelstring = concatenate_label(labelstring, appendixcounters[style])
 366                         lines[labelstringappendix_line] = re_LabelStringAppendix.sub(
 367                                 r'\1\2\3%s' % new_labelstring.replace("\\", "\\\\"),
 368                                 lines[labelstringappendix_line])
 369
 370                 # Now we can safely add the LabelCounter line
 371                 lines.insert(labeltype_line + 1, "%sLabelCounter %s" % (space1, counter))
 372                 i += 1
 373
 374             # Add the TocLevel setting for sectioning styles
 375             if toclevels.has_key(style) and maxcounter <= toclevels[style]:
 376                 lines.insert(i, '%sTocLevel %d' % (space1, toclevels[style]))
 377                 i += 1
 378
 379         i += 1
 380
 381     return format + 1
 382
 383
 384 def main(argv):
 385
 386     # Open files
 387     if len(argv) == 1:
 388         input = sys.stdin
 389         output = sys.stdout
 390     elif len(argv) == 3:
 391         input = open(argv[1], 'rb')
 392         output = open(argv[2], 'wb')
 393     else:
 394         error(usage(argv[0]))
 395
 396     # Do the real work
 397     lines = read(input)
 398     format = 1
 399     while (format < 4):
 400         format = convert(lines)
 401     write(output, lines)
 402
 403     # Close files
 404     if len(argv) == 3:
 405         input.close()
 406         output.close()
 407
 408     return 0
 409
 410
 411 if __name__ == "__main__":
 412     main(sys.argv)