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 current format
  13
  14
  15 import os, re, string, sys
  16
  17 # Incremented to format 4, 6 April 2007, lasgouttes
  18 # Introduction of generic "Provides" declaration
  19
  20 # Incremented to format 5, 22 August 2007 by vermeer
  21 # InsetLayout material
  22
  23 # Incremented to format 6, 7 January 2008 by spitz
  24 # Requires tag added to layout files
  25
  26 # Incremented to format 7, 24 March 2008 by rgh
  27 # AddToPreamble tag added to layout files
  28
  29 # Incremented to format 8, 25 July 2008 by rgh
  30 # UseModule tag added to layout files
  31 # CopyStyle added to InsetLayout
  32
  33 # Incremented to format 9, 5 October 2008 by rgh
  34 # ForcePlain and CustomPars tags added to InsetLayout
  35
  36 # Incremented to format 10, 6 October 2008 by rgh
  37 # Change format of counters
  38
  39 # Incremented to format 11, 14 October 2008 by rgh
  40 # Add ProvidesModule, ExcludesModule tags
  41
  42 # Incremented to format 12, 10 January 2009 by gb
  43 # Add I18NPreamble tag
  44
  45 # Incremented to format 13, 5 February 2009 by rgh
  46 # Add InToc tag for InsetLayout
  47
  48 # Incremented to format 14, 14 February 2009 by gb
  49 # Rename I18NPreamble to BabelPreamble and add LangPreamble
  50
  51 # Incremented to format 15, 28 May 2009 by lasgouttes
  52 # Add new tag OutputFormat; modules can be conditionned on feature
  53 # "from->to".
  54
  55 # Incremented to format 16, 5 June 2009 by rgh
  56 # Add new tags for Text Class:
  57 #   HTML Preamble
  58 # For Layout:
  59 #   HTMLTag, HTMLAttr, HTMLLabel, HTMLLabelAttr, HTMLItem, HTMLItemAttr
  60 #   HTMLStyle, and HTMLPreamble
  61 # For InsetLayout:
  62 #   HTMLTag, HTMLAttr, HTMLStyle, and HTMLPreamble
  63
  64 # Do not forget to document format change in Customization
  65 # Manual (section "Declaring a new text class").
  66
  67 currentFormat = 16
  68
  69
  70 def usage(prog_name):
  71     return ("Usage: %s inputfile outputfile\n" % prog_name +
  72             "or     %s <inputfile >outputfile" % prog_name)
  73
  74
  75 def error(message):
  76     sys.stderr.write(message + '\n')
  77     sys.exit(1)
  78
  79
  80 def trim_eol(line):
  81     " Remove end of line char(s)."
  82     if line[-2:-1] == '\r':
  83         return line[:-2]
  84     elif line[-1:] == '\r' or line[-1:] == '\n':
  85         return line[:-1]
  86     else:
  87         # file with no EOL in last line
  88         return line
  89
  90
  91 def read(input):
  92     " Read input file and strip lineendings."
  93     lines = list()
  94     while 1:
  95         line = input.readline()
  96         if not line:
  97             break
  98         lines.append(trim_eol(line))
  99     return lines
 100
 101
 102 def write(output, lines):
 103     " Write output file with native lineendings."
 104     for line in lines:
 105         output.write(line + os.linesep)
 106
 107
 108 # Concatenates old and new in an intelligent way:
 109 # If old is wrapped in ", they are stripped. The result is wrapped in ".
 110 def concatenate_label(old, new):
 111     # Don't use strip as long as we support python 1.5.2
 112     if old[0] == '"':
 113         return old[0:-1] + new + '"'
 114     else:
 115         return '"' + old + new + '"'
 116
 117 # appends a string to a list unless it's already there
 118 def addstring(s, l):
 119     if l.count(s) > 0:
 120         return
 121     l.append(s)
 122
 123
 124 def convert(lines):
 125     " Convert to new format."
 126     re_Comment = re.compile(r'^(\s*)#')
 127     re_Counter = re.compile(r'\s*Counter\s*', re.IGNORECASE)
 128     re_Name = re.compile(r'\s*Name\s+(\S+)\s*', re.IGNORECASE)
 129     re_UseMod = re.compile(r'^\s*UseModule\s+(.*)', re.IGNORECASE)
 130     re_Empty = re.compile(r'^(\s*)$')
 131     re_Format = re.compile(r'^(\s*)(Format)(\s+)(\S+)', re.IGNORECASE)
 132     re_Preamble = re.compile(r'^(\s*)Preamble', re.IGNORECASE)
 133     re_EndPreamble = re.compile(r'^(\s*)EndPreamble', re.IGNORECASE)
 134     re_LangPreamble = re.compile(r'^(\s*)LangPreamble', re.IGNORECASE)
 135     re_EndLangPreamble = re.compile(r'^(\s*)EndLangPreamble', re.IGNORECASE)
 136     re_BabelPreamble = re.compile(r'^(\s*)BabelPreamble', re.IGNORECASE)
 137     re_EndBabelPreamble = re.compile(r'^(\s*)EndBabelPreamble', re.IGNORECASE)
 138     re_MaxCounter = re.compile(r'^(\s*)(MaxCounter)(\s+)(\S+)', re.IGNORECASE)
 139     re_LabelType = re.compile(r'^(\s*)(LabelType)(\s+)(\S+)', re.IGNORECASE)
 140     re_LabelString = re.compile(r'^(\s*)(LabelString)(\s+)(("[^"]+")|(\S+))', re.IGNORECASE)
 141     re_LabelStringAppendix = re.compile(r'^(\s*)(LabelStringAppendix)(\s+)(("[^"]+")|(\S+))', re.IGNORECASE)
 142     re_LatexType = re.compile(r'^(\s*)(LatexType)(\s+)(\S+)', re.IGNORECASE)
 143     re_Style = re.compile(r'^(\s*)(Style)(\s+)(\S+)', re.IGNORECASE)
 144     re_CopyStyle = re.compile(r'^(\s*)(CopyStyle)(\s+)(\S+)', re.IGNORECASE)
 145     re_NoStyle = re.compile(r'^(\s*)(NoStyle)(\s+)(\S+)', re.IGNORECASE)
 146     re_End = re.compile(r'^(\s*)(End)(\s*)$', re.IGNORECASE)
 147     re_Provides = re.compile(r'^(\s*)Provides(\S+)(\s+)(\S+)', re.IGNORECASE)
 148     re_CharStyle = re.compile(r'^(\s*)CharStyle(\s+)(\S+)$', re.IGNORECASE)
 149     re_AMSMaths = re.compile(r'^\s*Input amsmaths.inc\s*')
 150     re_AMSMathsPlain = re.compile(r'^\s*Input amsmaths-plain.inc\s*')
 151     re_AMSMathsSeq = re.compile(r'^\s*Input amsmaths-seq.inc\s*')
 152     re_TocLevel = re.compile(r'^(\s*)(TocLevel)(\s+)(\S+)', re.IGNORECASE)
 153     re_I18nPreamble = re.compile(r'^(\s*)I18nPreamble', re.IGNORECASE)
 154     re_EndI18nPreamble = re.compile(r'^(\s*)EndI18nPreamble', re.IGNORECASE)
 155
 156     # counters for sectioning styles (hardcoded in 1.3)
 157     counters = {"part"          : "\\Roman{part}",
 158                 "chapter"       : "\\arabic{chapter}",
 159                 "section"       : "\\arabic{section}",
 160                 "subsection"    : "\\arabic{section}.\\arabic{subsection}",
 161                 "subsubsection" : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}",
 162                 "paragraph"     : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}.\\arabic{paragraph}",
 163                 "subparagraph"  : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}.\\arabic{paragraph}.\\arabic{subparagraph}"}
 164
 165     # counters for sectioning styles in appendix (hardcoded in 1.3)
 166     appendixcounters = {"chapter"       : "\\Alph{chapter}",
 167                         "section"       : "\\Alph{section}",
 168                         "subsection"    : "\\arabic{section}.\\arabic{subsection}",
 169                         "subsubsection" : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}",
 170                         "paragraph"     : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}.\\arabic{paragraph}",
 171                         "subparagraph"  : "\\arabic{section}.\\arabic{subsection}.\\arabic{subsubsection}.\\arabic{paragraph}.\\arabic{subparagraph}"}
 172
 173     # Value of TocLevel for sectioning styles
 174     toclevels = {"part"          : 0,
 175                  "chapter"       : 0,
 176                  "section"       : 1,
 177                  "subsection"    : 2,
 178                  "subsubsection" : 3,
 179                  "paragraph"     : 4,
 180                  "subparagraph"  : 5}
 181
 182     i = 0
 183     only_comment = 1
 184     counter = ""
 185     toclevel = ""
 186     label = ""
 187     labelstring = ""
 188     labelstringappendix = ""
 189     space1 = ""
 190     labelstring_line = -1
 191     labelstringappendix_line = -1
 192     labeltype_line = -1
 193     latextype = ""
 194     latextype_line = -1
 195     style = ""
 196     maxcounter = 0
 197     format = 1
 198     formatline = 0
 199     usemodules = []
 200
 201     while i < len(lines):
 202         # Skip comments and empty lines
 203         if re_Comment.match(lines[i]) or re_Empty.match(lines[i]):
 204             i += 1
 205             continue
 206
 207         # insert file format if not already there
 208         if (only_comment):
 209             match = re_Format.match(lines[i])
 210             if match:
 211                 formatline = i
 212                 format = int(match.group(4))
 213                 if format > 1 and format < currentFormat:
 214                     lines[i] = "Format %d" % (format + 1)
 215                     only_comment = 0
 216                 elif format == currentFormat:
 217                     # nothing to do
 218                     return format
 219                 else:
 220                     error('Cannot convert file format %s' % format)
 221             else:
 222                 lines.insert(i, "Format 2")
 223                 only_comment = 0
 224                 continue
 225
 226         # Don't get confused by LaTeX code
 227         if re_Preamble.match(lines[i]):
 228             i += 1
 229             while i < len(lines) and not re_EndPreamble.match(lines[i]):
 230                 i += 1
 231             continue
 232         if re_LangPreamble.match(lines[i]):
 233             i += 1
 234             while i < len(lines) and not re_EndLangPreamble.match(lines[i]):
 235                 i += 1
 236             continue
 237         if re_BabelPreamble.match(lines[i]):
 238             i += 1
 239             while i < len(lines) and not re_EndBabelPreamble.match(lines[i]):
 240                 i += 1
 241             continue
 242
 243         # This just involved new features, not any changes to old ones
 244         if format == 14 or format == 15:
 245           i += 1
 246           continue
 247
 248         # Rename I18NPreamble to BabelPreamble
 249         if format == 13:
 250             match = re_I18nPreamble.match(lines[i])
 251             if match:
 252                 lines[i] = match.group(1) + "BabelPreamble"
 253                 i += 1
 254                 match = re_EndI18nPreamble.match(lines[i])
 255                 while i < len(lines) and not match:
 256                     i += 1
 257                     match = re_EndI18nPreamble.match(lines[i])
 258                 lines[i] = match.group(1) + "EndBabelPreamble"
 259                 i += 1
 260                 continue
 261
 262         # These just involved new features, not any changes to old ones
 263         if format == 11 or format == 12:
 264           i += 1
 265           continue
 266
 267         if format == 10:
 268             match = re_UseMod.match(lines[i])
 269             if match:
 270                 module = match.group(1)
 271                 lines[i] = "DefaultModule " + module
 272             i += 1
 273             continue
 274
 275         if format == 9:
 276             match = re_Counter.match(lines[i])
 277             if match:
 278                 counterline = i
 279                 i += 1
 280                 while i < len(lines):
 281                     namem = re_Name.match(lines[i])
 282                     if namem:
 283                         name = namem.group(1)
 284                         lines.pop(i)
 285                         lines[counterline] = "Counter %s" % name
 286                         # we don't need to increment i
 287                         continue
 288                     endem = re_End.match(lines[i])
 289                     if endem:
 290                         i += 1
 291                         break
 292                     i += 1
 293             i += 1
 294             continue
 295
 296         if format == 8:
 297             # We want to scan for ams-type includes and, if we find them,
 298             # add corresponding UseModule tags to the layout.
 299             match = re_AMSMaths.match(lines[i])
 300             if match:
 301                 addstring("theorems-ams", usemodules)
 302                 addstring("theorems-ams-extended", usemodules)
 303                 addstring("theorems-sec", usemodules)
 304                 lines.pop(i)
 305                 continue
 306             match = re_AMSMathsPlain.match(lines[i])
 307             if match:
 308                 addstring("theorems-starred", usemodules)
 309                 lines.pop(i)
 310                 continue
 311             match = re_AMSMathsSeq.match(lines[i])
 312             if match:
 313                 addstring("theorems-ams", usemodules)
 314                 addstring("theorems-ams-extended", usemodules)
 315                 lines.pop(i)
 316                 continue
 317             i += 1
 318             continue
 319
 320         # These just involved new features, not any changes to old ones
 321         if format >= 5 and format <= 7:
 322           i += 1
 323           continue
 324
 325         if format == 4:
 326             # Handle conversion to long CharStyle names
 327             match = re_CharStyle.match(lines[i])
 328             if match:
 329                 lines[i] = "InsetLayout CharStyle:%s" % (match.group(3))
 330                 i += 1
 331                 lines.insert(i, "\tLyXType charstyle")
 332                 i += 1
 333                 lines.insert(i, "")
 334                 lines[i] = "\tLabelString %s" % (match.group(3))
 335             i += 1
 336             continue
 337
 338         if format == 3:
 339             # convert 'providesamsmath x',  'providesmakeidx x',  'providesnatbib x',  'providesurl x' to
 340             #         'provides amsmath x', 'provides makeidx x', 'provides natbib x', 'provides url x'
 341             # x is either 0 or 1
 342             match = re_Provides.match(lines[i])
 343             if match:
 344                 lines[i] = "%sProvides %s%s%s" % (match.group(1), match.group(2).lower(),
 345                                                   match.group(3), match.group(4))
 346             i += 1
 347             continue
 348
 349         if format == 2:
 350             caption = []
 351
 352             # delete caption styles
 353             match = re_Style.match(lines[i])
 354             if match:
 355                 style = string.lower(match.group(4))
 356                 if style == "caption":
 357                     del lines[i]
 358                     while i < len(lines) and not re_End.match(lines[i]):
 359                         caption.append(lines[i])
 360                         del lines[i]
 361                     if i == len(lines):
 362                         error('Incomplete caption style.')
 363                     else:
 364                         del lines[i]
 365                         continue
 366
 367             # delete undefinition of caption styles
 368             match = re_NoStyle.match(lines[i])
 369             if match:
 370                 style = string.lower(match.group(4))
 371                 if style == "caption":
 372                     del lines[i]
 373                     continue
 374
 375             # replace the CopyStyle statement with the definition of the real
 376             # style. This may result in duplicate statements, but that is OK
 377             # since the second one will overwrite the first one.
 378             match = re_CopyStyle.match(lines[i])
 379             if match:
 380                 style = string.lower(match.group(4))
 381                 if style == "caption":
 382                     if len(caption) > 0:
 383                         lines[i:i+1] = caption
 384                     else:
 385                         # FIXME: This style comes from an include file, we
 386                         # should replace the real style and not this default.
 387                         lines[i:i+1] = ['       Margin                First_Dynamic',
 388                                         '       LatexType             Command',
 389                                         '       LatexName             caption',
 390                                         '       NeedProtect           1',
 391                                         '       LabelSep              xx',
 392                                         '       ParSkip               0.4',
 393                                         '       TopSep                0.5',
 394                                         '       Align                 Center',
 395                                         '       AlignPossible         Center',
 396                                         '       LabelType             Sensitive',
 397                                         '       LabelString           "Senseless!"',
 398                                         '       OptionalArgs          1',
 399                                         '       LabelFont',
 400                                         '         Series              Bold',
 401                                         '       EndFont']
 402
 403             i += 1
 404             continue
 405
 406         # Delete MaxCounter and remember the value of it
 407         match = re_MaxCounter.match(lines[i])
 408         if match:
 409             level = match.group(4)
 410             if string.lower(level) == "counter_chapter":
 411                 maxcounter = 0
 412             elif string.lower(level) == "counter_section":
 413                 maxcounter = 1
 414             elif string.lower(level) == "counter_subsection":
 415                 maxcounter = 2
 416             elif string.lower(level) == "counter_subsubsection":
 417                 maxcounter = 3
 418             elif string.lower(level) == "counter_paragraph":
 419                 maxcounter = 4
 420             elif string.lower(level) == "counter_subparagraph":
 421                 maxcounter = 5
 422             elif string.lower(level) == "counter_enumi":
 423                 maxcounter = 6
 424             elif string.lower(level) == "counter_enumii":
 425                 maxcounter = 7
 426             elif string.lower(level) == "counter_enumiii":
 427                 maxcounter = 8
 428             del lines[i]
 429             continue
 430
 431         # Replace line
 432         #
 433         # LabelType Counter_EnumI
 434         #
 435         # with two lines
 436         #
 437         # LabelType Counter
 438         # LabelCounter EnumI
 439         #
 440         match = re_LabelType.match(lines[i])
 441         if match:
 442             label = match.group(4)
 443             # Remember indenting space for later reuse in added lines
 444             space1 = match.group(1)
 445             # Remember the line for adding the LabelCounter later.
 446             # We can't do it here because it could shift latextype_line etc.
 447             labeltype_line = i
 448             if string.lower(label[:8]) == "counter_":
 449                 counter = string.lower(label[8:])
 450                 lines[i] = re_LabelType.sub(r'\1\2\3Counter', lines[i])
 451
 452         # Remember the LabelString line
 453         match = re_LabelString.match(lines[i])
 454         if match:
 455             labelstring = match.group(4)
 456             labelstring_line = i
 457
 458         # Remember the LabelStringAppendix line
 459         match = re_LabelStringAppendix.match(lines[i])
 460         if match:
 461             labelstringappendix = match.group(4)
 462             labelstringappendix_line = i
 463
 464         # Remember the LatexType line
 465         match = re_LatexType.match(lines[i])
 466         if match:
 467             latextype = string.lower(match.group(4))
 468             latextype_line = i
 469
 470         # Remember the TocLevel line
 471         match = re_TocLevel.match(lines[i])
 472         if match:
 473             toclevel = string.lower(match.group(4))
 474
 475         # Reset variables at the beginning of a style definition
 476         match = re_Style.match(lines[i])
 477         if match:
 478             style = string.lower(match.group(4))
 479             counter = ""
 480             toclevel = ""
 481             label = ""
 482             space1 = ""
 483             labelstring = ""
 484             labelstringappendix = ""
 485             labelstring_line = -1
 486             labelstringappendix_line = -1
 487             labeltype_line = -1
 488             latextype = ""
 489             latextype_line = -1
 490
 491         if re_End.match(lines[i]):
 492
 493             # Add a line "LatexType Bib_Environment" if LabelType is Bibliography
 494             # (or change the existing LatexType)
 495             if string.lower(label) == "bibliography":
 496                 if (latextype_line < 0):
 497                     lines.insert(i, "%sLatexType Bib_Environment" % space1)
 498                     i += 1
 499                 else:
 500                     lines[latextype_line] = re_LatexType.sub(r'\1\2\3Bib_Environment', lines[latextype_line])
 501
 502             # Change "LabelType Static" to "LabelType Itemize" for itemize environments
 503             if latextype == "item_environment" and string.lower(label) == "static":
 504                 lines[labeltype_line] = re_LabelType.sub(r'\1\2\3Itemize', lines[labeltype_line])
 505
 506             # Change "LabelType Counter_EnumI" to "LabelType Enumerate" for enumerate environments
 507             if latextype == "item_environment" and string.lower(label) == "counter_enumi":
 508                 lines[labeltype_line] = re_LabelType.sub(r'\1\2\3Enumerate', lines[labeltype_line])
 509                 # Don't add the LabelCounter line later
 510                 counter = ""
 511
 512             # Replace
 513             #
 514             # LabelString "Chapter"
 515             #
 516             # with
 517             #
 518             # LabelString "Chapter \arabic{chapter}"
 519             #
 520             # if this style has a counter. Ditto for LabelStringAppendix.
 521             # This emulates the hardcoded article style numbering of 1.3
 522             #
 523             if counter != "":
 524                 if counters.has_key(style):
 525                     if labelstring_line < 0:
 526                         lines.insert(i, '%sLabelString "%s"' % (space1, counters[style]))
 527                         i += 1
 528                     else:
 529                         new_labelstring = concatenate_label(labelstring, counters[style])
 530                         lines[labelstring_line] = re_LabelString.sub(
 531                                 r'\1\2\3%s' % new_labelstring.replace("\\", "\\\\"),
 532                                 lines[labelstring_line])
 533                 if appendixcounters.has_key(style):
 534                     if labelstringappendix_line < 0:
 535                         lines.insert(i, '%sLabelStringAppendix "%s"' % (space1, appendixcounters[style]))
 536                         i += 1
 537                     else:
 538                         new_labelstring = concatenate_label(labelstring, appendixcounters[style])
 539                         lines[labelstringappendix_line] = re_LabelStringAppendix.sub(
 540                                 r'\1\2\3%s' % new_labelstring.replace("\\", "\\\\"),
 541                                 lines[labelstringappendix_line])
 542
 543                 # Now we can safely add the LabelCounter line
 544                 lines.insert(labeltype_line + 1, "%sLabelCounter %s" % (space1, counter))
 545                 i += 1
 546
 547             # Add the TocLevel setting for sectioning styles
 548             if toclevel == "" and toclevels.has_key(style) and maxcounter <= toclevels[style]:
 549                 lines.insert(i, '%sTocLevel %d' % (space1, toclevels[style]))
 550                 i += 1
 551
 552         i += 1
 553
 554     if usemodules:
 555         i = formatline + 1
 556         for mod in usemodules:
 557             lines.insert(i, "UseModule " + mod)
 558             i += 1
 559
 560     return format + 1
 561
 562
 563 def main(argv):
 564
 565     # Open files
 566     if len(argv) == 1:
 567         input = sys.stdin
 568         output = sys.stdout
 569     elif len(argv) == 3:
 570         input = open(argv[1], 'rb')
 571         output = open(argv[2], 'wb')
 572     else:
 573         error(usage(argv[0]))
 574
 575     # Do the real work
 576     lines = read(input)
 577     format = 1
 578     while (format < currentFormat):
 579         format = convert(lines)
 580     write(output, lines)
 581
 582     # Close files
 583     if len(argv) == 3:
 584         input.close()
 585         output.close()
 586
 587     return 0
 588
 589
 590 if __name__ == "__main__":
 591     main(sys.argv)