BaseTools/Source/Python/AutoGen/UniClassObject.py

   1 ## @file
   2 # This file is used to collect all defined strings in multiple uni files
   3 #
   4 #
   5 # Copyright (c) 2014 Hewlett-Packard Development Company, L.P.<BR>
   6 #
   7 # Copyright (c) 2007 - 2015, Intel Corporation. All rights reserved.<BR>
   8 # This program and the accompanying materials
   9 # are licensed and made available under the terms and conditions of the BSD License
  10 # which accompanies this distribution.  The full text of the license may be found at
  11 # http://opensource.org/licenses/bsd-license.php
  12 #
  13 # THE PROGRAM IS DISTRIBUTED UNDER THE BSD LICENSE ON AN "AS IS" BASIS,
  14 # WITHOUT WARRANTIES OR REPRESENTATIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED.
  15
  16 ##
  17 # Import Modules
  18 #
  19 import Common.LongFilePathOs as os, codecs, re
  20 import distutils.util
  21 import Common.EdkLogger as EdkLogger
  22 import StringIO
  23 from Common.BuildToolError import *
  24 from Common.String import GetLineNo
  25 from Common.Misc import PathClass
  26 from Common.LongFilePathSupport import LongFilePath
  27 ##
  28 # Static definitions
  29 #
  30 UNICODE_WIDE_CHAR = u'\\wide'
  31 UNICODE_NARROW_CHAR = u'\\narrow'
  32 UNICODE_NON_BREAKING_CHAR = u'\\nbr'
  33 UNICODE_UNICODE_CR = '\r'
  34 UNICODE_UNICODE_LF = '\n'
  35
  36 NARROW_CHAR = u'\uFFF0'
  37 WIDE_CHAR = u'\uFFF1'
  38 NON_BREAKING_CHAR = u'\uFFF2'
  39 CR = u'\u000D'
  40 LF = u'\u000A'
  41 NULL = u'\u0000'
  42 TAB = u'\t'
  43 BACK_SLASH_PLACEHOLDER = u'\u0006'
  44
  45 gIncludePattern = re.compile("^#include +[\"<]+([^\"< >]+)[>\"]+$", re.MULTILINE | re.UNICODE)
  46
  47 ## Convert a python unicode string to a normal string
  48 #
  49 # Convert a python unicode string to a normal string
  50 # UniToStr(u'I am a string') is 'I am a string'
  51 #
  52 # @param Uni:  The python unicode string
  53 #
  54 # @retval:     The formatted normal string
  55 #
  56 def UniToStr(Uni):
  57     return repr(Uni)[2:-1]
  58
  59 ## Convert a unicode string to a Hex list
  60 #
  61 # Convert a unicode string to a Hex list
  62 # UniToHexList('ABC') is ['0x41', '0x00', '0x42', '0x00', '0x43', '0x00']
  63 #
  64 # @param Uni:    The python unicode string
  65 #
  66 # @retval List:  The formatted hex list
  67 #
  68 def UniToHexList(Uni):
  69     List = []
  70     for Item in Uni:
  71         Temp = '%04X' % ord(Item)
  72         List.append('0x' + Temp[2:4])
  73         List.append('0x' + Temp[0:2])
  74     return List
  75
  76 LangConvTable = {'eng':'en', 'fra':'fr', \
  77                  'aar':'aa', 'abk':'ab', 'ave':'ae', 'afr':'af', 'aka':'ak', 'amh':'am', \
  78                  'arg':'an', 'ara':'ar', 'asm':'as', 'ava':'av', 'aym':'ay', 'aze':'az', \
  79                  'bak':'ba', 'bel':'be', 'bul':'bg', 'bih':'bh', 'bis':'bi', 'bam':'bm', \
  80                  'ben':'bn', 'bod':'bo', 'bre':'br', 'bos':'bs', 'cat':'ca', 'che':'ce', \
  81                  'cha':'ch', 'cos':'co', 'cre':'cr', 'ces':'cs', 'chu':'cu', 'chv':'cv', \
  82                  'cym':'cy', 'dan':'da', 'deu':'de', 'div':'dv', 'dzo':'dz', 'ewe':'ee', \
  83                  'ell':'el', 'epo':'eo', 'spa':'es', 'est':'et', 'eus':'eu', 'fas':'fa', \
  84                  'ful':'ff', 'fin':'fi', 'fij':'fj', 'fao':'fo', 'fry':'fy', 'gle':'ga', \
  85                  'gla':'gd', 'glg':'gl', 'grn':'gn', 'guj':'gu', 'glv':'gv', 'hau':'ha', \
  86                  'heb':'he', 'hin':'hi', 'hmo':'ho', 'hrv':'hr', 'hat':'ht', 'hun':'hu', \
  87                  'hye':'hy', 'her':'hz', 'ina':'ia', 'ind':'id', 'ile':'ie', 'ibo':'ig', \
  88                  'iii':'ii', 'ipk':'ik', 'ido':'io', 'isl':'is', 'ita':'it', 'iku':'iu', \
  89                  'jpn':'ja', 'jav':'jv', 'kat':'ka', 'kon':'kg', 'kik':'ki', 'kua':'kj', \
  90                  'kaz':'kk', 'kal':'kl', 'khm':'km', 'kan':'kn', 'kor':'ko', 'kau':'kr', \
  91                  'kas':'ks', 'kur':'ku', 'kom':'kv', 'cor':'kw', 'kir':'ky', 'lat':'la', \
  92                  'ltz':'lb', 'lug':'lg', 'lim':'li', 'lin':'ln', 'lao':'lo', 'lit':'lt', \
  93                  'lub':'lu', 'lav':'lv', 'mlg':'mg', 'mah':'mh', 'mri':'mi', 'mkd':'mk', \
  94                  'mal':'ml', 'mon':'mn', 'mar':'mr', 'msa':'ms', 'mlt':'mt', 'mya':'my', \
  95                  'nau':'na', 'nob':'nb', 'nde':'nd', 'nep':'ne', 'ndo':'ng', 'nld':'nl', \
  96                  'nno':'nn', 'nor':'no', 'nbl':'nr', 'nav':'nv', 'nya':'ny', 'oci':'oc', \
  97                  'oji':'oj', 'orm':'om', 'ori':'or', 'oss':'os', 'pan':'pa', 'pli':'pi', \
  98                  'pol':'pl', 'pus':'ps', 'por':'pt', 'que':'qu', 'roh':'rm', 'run':'rn', \
  99                  'ron':'ro', 'rus':'ru', 'kin':'rw', 'san':'sa', 'srd':'sc', 'snd':'sd', \
 100                  'sme':'se', 'sag':'sg', 'sin':'si', 'slk':'sk', 'slv':'sl', 'smo':'sm', \
 101                  'sna':'sn', 'som':'so', 'sqi':'sq', 'srp':'sr', 'ssw':'ss', 'sot':'st', \
 102                  'sun':'su', 'swe':'sv', 'swa':'sw', 'tam':'ta', 'tel':'te', 'tgk':'tg', \
 103                  'tha':'th', 'tir':'ti', 'tuk':'tk', 'tgl':'tl', 'tsn':'tn', 'ton':'to', \
 104                  'tur':'tr', 'tso':'ts', 'tat':'tt', 'twi':'tw', 'tah':'ty', 'uig':'ug', \
 105                  'ukr':'uk', 'urd':'ur', 'uzb':'uz', 'ven':'ve', 'vie':'vi', 'vol':'vo', \
 106                  'wln':'wa', 'wol':'wo', 'xho':'xh', 'yid':'yi', 'yor':'yo', 'zha':'za', \
 107                  'zho':'zh', 'zul':'zu'}
 108
 109 ## GetLanguageCode
 110 #
 111 # Check the language code read from .UNI file and convert ISO 639-2 codes to RFC 4646 codes if appropriate
 112 # ISO 639-2 language codes supported in compatiblity mode
 113 # RFC 4646 language codes supported in native mode
 114 #
 115 # @param LangName:   Language codes read from .UNI file
 116 #
 117 # @retval LangName:  Valid lanugage code in RFC 4646 format or None
 118 #
 119 def GetLanguageCode(LangName, IsCompatibleMode, File):
 120     global LangConvTable
 121
 122     length = len(LangName)
 123     if IsCompatibleMode:
 124         if length == 3 and LangName.isalpha():
 125             TempLangName = LangConvTable.get(LangName.lower())
 126             if TempLangName != None:
 127                 return TempLangName
 128             return LangName
 129         else:
 130             EdkLogger.error("Unicode File Parser", FORMAT_INVALID, "Invalid ISO 639-2 language code : %s" % LangName, File)
 131
 132     if (LangName[0] == 'X' or LangName[0] == 'x') and LangName[1] == '-':
 133         return LangName
 134     if length == 2:
 135         if LangName.isalpha():
 136             return LangName
 137     elif length == 3:
 138         if LangName.isalpha() and LangConvTable.get(LangName.lower()) == None:
 139             return LangName
 140     elif length == 5:
 141         if LangName[0:2].isalpha() and LangName[2] == '-':
 142             return LangName
 143     elif length >= 6:
 144         if LangName[0:2].isalpha() and LangName[2] == '-':
 145             return LangName
 146         if LangName[0:3].isalpha() and LangConvTable.get(LangName.lower()) == None and LangName[3] == '-':
 147             return LangName
 148
 149     EdkLogger.error("Unicode File Parser", FORMAT_INVALID, "Invalid RFC 4646 language code : %s" % LangName, File)
 150
 151 ## Ucs2Codec
 152 #
 153 # This is only a partial codec implementation. It only supports
 154 # encoding, and is primarily used to check that all the characters are
 155 # valid for UCS-2.
 156 #
 157 class Ucs2Codec(codecs.Codec):
 158     def __init__(self):
 159         self.__utf16 = codecs.lookup('utf-16')
 160
 161     def encode(self, input, errors='strict'):
 162         for Char in input:
 163             CodePoint = ord(Char)
 164             if CodePoint >= 0xd800 and CodePoint <= 0xdfff:
 165                 raise ValueError("Code Point is in range reserved for " +
 166                                  "UTF-16 surrogate pairs")
 167             elif CodePoint > 0xffff:
 168                 raise ValueError("Code Point too large to encode in UCS-2")
 169         return self.__utf16.encode(input)
 170
 171 TheUcs2Codec = Ucs2Codec()
 172 def Ucs2Search(name):
 173     if name == 'ucs-2':
 174         return codecs.CodecInfo(
 175             name=name,
 176             encode=TheUcs2Codec.encode,
 177             decode=TheUcs2Codec.decode)
 178     else:
 179         return None
 180 codecs.register(Ucs2Search)
 181
 182 ## StringDefClassObject
 183 #
 184 # A structure for language definition
 185 #
 186 class StringDefClassObject(object):
 187     def __init__(self, Name = None, Value = None, Referenced = False, Token = None, UseOtherLangDef = ''):
 188         self.StringName = ''
 189         self.StringNameByteList = []
 190         self.StringValue = ''
 191         self.StringValueByteList = ''
 192         self.Token = 0
 193         self.Referenced = Referenced
 194         self.UseOtherLangDef = UseOtherLangDef
 195         self.Length = 0
 196
 197         if Name != None:
 198             self.StringName = Name
 199             self.StringNameByteList = UniToHexList(Name)
 200         if Value != None:
 201             self.StringValue = Value + u'\x00'        # Add a NULL at string tail
 202             self.StringValueByteList = UniToHexList(self.StringValue)
 203             self.Length = len(self.StringValueByteList)
 204         if Token != None:
 205             self.Token = Token
 206
 207     def __str__(self):
 208         return repr(self.StringName) + ' ' + \
 209                repr(self.Token) + ' ' + \
 210                repr(self.Referenced) + ' ' + \
 211                repr(self.StringValue) + ' ' + \
 212                repr(self.UseOtherLangDef)
 213
 214     def UpdateValue(self, Value = None):
 215         if Value != None:
 216             self.StringValue = Value + u'\x00'        # Add a NULL at string tail
 217             self.StringValueByteList = UniToHexList(self.StringValue)
 218             self.Length = len(self.StringValueByteList)
 219
 220 ## UniFileClassObject
 221 #
 222 # A structure for .uni file definition
 223 #
 224 class UniFileClassObject(object):
 225     def __init__(self, FileList = [], IsCompatibleMode = False, IncludePathList = []):
 226         self.FileList = FileList
 227         self.Token = 2
 228         self.LanguageDef = []                   #[ [u'LanguageIdentifier', u'PrintableName'], ... ]
 229         self.OrderedStringList = {}             #{ u'LanguageIdentifier' : [StringDefClassObject]  }
 230         self.OrderedStringDict = {}             #{ u'LanguageIdentifier' : {StringName:(IndexInList)}  }
 231         self.OrderedStringListByToken = {}      #{ u'LanguageIdentifier' : {Token: StringDefClassObject} }
 232         self.IsCompatibleMode = IsCompatibleMode
 233         self.IncludePathList = IncludePathList
 234         if len(self.FileList) > 0:
 235             self.LoadUniFiles(FileList)
 236
 237     #
 238     # Get Language definition
 239     #
 240     def GetLangDef(self, File, Line):
 241         Lang = distutils.util.split_quoted((Line.split(u"//")[0]))
 242         if len(Lang) != 3:
 243             try:
 244                 FileIn = self.OpenUniFile(LongFilePath(File.Path))
 245             except UnicodeError, X:
 246                 EdkLogger.error("build", FILE_READ_FAILURE, "File read failure: %s" % str(X), ExtraData=File);
 247             except:
 248                 EdkLogger.error("build", FILE_OPEN_FAILURE, ExtraData=File);
 249             LineNo = GetLineNo(FileIn, Line, False)
 250             EdkLogger.error("Unicode File Parser", PARSER_ERROR, "Wrong language definition",
 251                             ExtraData="""%s\n\t*Correct format is like '#langdef en-US "English"'""" % Line, File = File, Line = LineNo)
 252         else:
 253             LangName = GetLanguageCode(Lang[1], self.IsCompatibleMode, self.File)
 254             LangPrintName = Lang[2]
 255
 256         IsLangInDef = False
 257         for Item in self.LanguageDef:
 258             if Item[0] == LangName:
 259                 IsLangInDef = True
 260                 break;
 261
 262         if not IsLangInDef:
 263             self.LanguageDef.append([LangName, LangPrintName])
 264
 265         #
 266         # Add language string
 267         #
 268         self.AddStringToList(u'$LANGUAGE_NAME', LangName, LangName, 0, True, Index=0)
 269         self.AddStringToList(u'$PRINTABLE_LANGUAGE_NAME', LangName, LangPrintName, 1, True, Index=1)
 270
 271         if not IsLangInDef:
 272             #
 273             # The found STRING tokens will be added into new language string list
 274             # so that the unique STRING identifier is reserved for all languages in the package list.
 275             #
 276             FirstLangName = self.LanguageDef[0][0]
 277             if LangName != FirstLangName:
 278                 for Index in range (2, len (self.OrderedStringList[FirstLangName])):
 279                     Item = self.OrderedStringList[FirstLangName][Index]
 280                     if Item.UseOtherLangDef != '':
 281                         OtherLang = Item.UseOtherLangDef
 282                     else:
 283                         OtherLang = FirstLangName
 284                     self.OrderedStringList[LangName].append (StringDefClassObject(Item.StringName, '', Item.Referenced, Item.Token, OtherLang))
 285                     self.OrderedStringDict[LangName][Item.StringName] = len(self.OrderedStringList[LangName]) - 1
 286         return True
 287
 288     def OpenUniFile(self, FileName):
 289         #
 290         # Read file
 291         #
 292         try:
 293             UniFile = open(FileName, mode='rb')
 294             FileIn = UniFile.read()
 295             UniFile.close()
 296         except:
 297             EdkLogger.Error("build", FILE_OPEN_FAILURE, ExtraData=File)
 298
 299         #
 300         # We currently only support UTF-16
 301         #
 302         Encoding = 'utf-16'
 303
 304         self.VerifyUcs2Data(FileIn, FileName, Encoding)
 305
 306         UniFile = StringIO.StringIO(FileIn)
 307         Info = codecs.lookup(Encoding)
 308         (Reader, Writer) = (Info.streamreader, Info.streamwriter)
 309         return codecs.StreamReaderWriter(UniFile, Reader, Writer)
 310
 311     def VerifyUcs2Data(self, FileIn, FileName, Encoding):
 312         Ucs2Info = codecs.lookup('ucs-2')
 313         #
 314         # Convert to unicode
 315         #
 316         try:
 317             FileDecoded = codecs.decode(FileIn, Encoding)
 318             Ucs2Info.encode(FileDecoded)
 319         except:
 320             UniFile = StringIO.StringIO(FileIn)
 321             Info = codecs.lookup(Encoding)
 322             (Reader, Writer) = (Info.streamreader, Info.streamwriter)
 323             File = codecs.StreamReaderWriter(UniFile, Reader, Writer)
 324             LineNumber = 0
 325             ErrMsg = lambda Encoding, LineNumber: \
 326                      '%s contains invalid %s characters on line %d.' % \
 327                      (FileName, Encoding, LineNumber)
 328             while True:
 329                 LineNumber = LineNumber + 1
 330                 try:
 331                     Line = File.readline()
 332                     if Line == '':
 333                         EdkLogger.error('Unicode File Parser', PARSER_ERROR,
 334                                         ErrMsg(Encoding, LineNumber))
 335                     Ucs2Info.encode(Line)
 336                 except:
 337                     EdkLogger.error('Unicode File Parser', PARSER_ERROR,
 338                                     ErrMsg('UCS-2', LineNumber))
 339
 340     #
 341     # Get String name and value
 342     #
 343     def GetStringObject(self, Item):
 344         Language = ''
 345         Value = ''
 346
 347         Name = Item.split()[1]
 348         # Check the string name is the upper character
 349         if Name != '':
 350             MatchString = re.match('[A-Z0-9_]+', Name, re.UNICODE)
 351             if MatchString == None or MatchString.end(0) != len(Name):
 352                 EdkLogger.error('Unicode File Parser', FORMAT_INVALID, 'The string token name %s defined in UNI file %s contains the invalid lower case character.' %(Name, self.File))
 353         LanguageList = Item.split(u'#language ')
 354         for IndexI in range(len(LanguageList)):
 355             if IndexI == 0:
 356                 continue
 357             else:
 358                 Language = LanguageList[IndexI].split()[0]
 359                 Value = LanguageList[IndexI][LanguageList[IndexI].find(u'\"') + len(u'\"') : LanguageList[IndexI].rfind(u'\"')] #.replace(u'\r\n', u'')
 360                 Language = GetLanguageCode(Language, self.IsCompatibleMode, self.File)
 361                 self.AddStringToList(Name, Language, Value)
 362
 363     #
 364     # Get include file list and load them
 365     #
 366     def GetIncludeFile(self, Item, Dir):
 367         FileName = Item[Item.find(u'#include ') + len(u'#include ') :Item.find(u' ', len(u'#include '))][1:-1]
 368         self.LoadUniFile(FileName)
 369
 370     def StripComments(self, Line):
 371         Comment = u'//'
 372         CommentPos = Line.find(Comment)
 373         while CommentPos >= 0:
 374         # if there are non matched quotes before the comment header
 375         # then we are in the middle of a string
 376         # but we need to ignore the escaped quotes and backslashes.
 377             if ((Line.count(u'"', 0, CommentPos) - Line.count(u'\\"', 0, CommentPos)) & 1) == 1:
 378                 CommentPos = Line.find (Comment, CommentPos + 1)
 379             else:
 380                 return Line[:CommentPos].strip()
 381         return Line.strip()
 382
 383
 384     #
 385     # Pre-process before parse .uni file
 386     #
 387     def PreProcess(self, File):
 388         if not os.path.exists(File.Path) or not os.path.isfile(File.Path):
 389             EdkLogger.error("Unicode File Parser", FILE_NOT_FOUND, ExtraData=File.Path)
 390
 391         try:
 392             FileIn = self.OpenUniFile(LongFilePath(File.Path))
 393         except UnicodeError, X:
 394             EdkLogger.error("build", FILE_READ_FAILURE, "File read failure: %s" % str(X), ExtraData=File.Path);
 395         except:
 396             EdkLogger.error("build", FILE_OPEN_FAILURE, ExtraData=File.Path);
 397
 398         Lines = []
 399         #
 400         # Use unique identifier
 401         #
 402         for Line in FileIn:
 403             Line = Line.strip()
 404             Line = Line.replace(u'\\\\', BACK_SLASH_PLACEHOLDER)
 405             Line = self.StripComments(Line)
 406
 407             #
 408             # Ignore empty line
 409             #
 410             if len(Line) == 0:
 411                 continue
 412
 413
 414             Line = Line.replace(u'/langdef', u'#langdef')
 415             Line = Line.replace(u'/string', u'#string')
 416             Line = Line.replace(u'/language', u'#language')
 417             Line = Line.replace(u'/include', u'#include')
 418
 419             Line = Line.replace(UNICODE_WIDE_CHAR, WIDE_CHAR)
 420             Line = Line.replace(UNICODE_NARROW_CHAR, NARROW_CHAR)
 421             Line = Line.replace(UNICODE_NON_BREAKING_CHAR, NON_BREAKING_CHAR)
 422
 423             Line = Line.replace(u'\\r\\n', CR + LF)
 424             Line = Line.replace(u'\\n', CR + LF)
 425             Line = Line.replace(u'\\r', CR)
 426             Line = Line.replace(u'\\t', u' ')
 427             Line = Line.replace(u'\t', u' ')
 428             Line = Line.replace(u'\\"', u'"')
 429             Line = Line.replace(u"\\'", u"'")
 430             Line = Line.replace(BACK_SLASH_PLACEHOLDER, u'\\')
 431
 432 #           if Line.find(u'\\x'):
 433 #               hex = Line[Line.find(u'\\x') + 2 : Line.find(u'\\x') + 6]
 434 #               hex = "u'\\u" + hex + "'"
 435
 436             IncList = gIncludePattern.findall(Line)
 437             if len(IncList) == 1:
 438                 for Dir in [File.Dir] + self.IncludePathList:
 439                     IncFile = PathClass(str(IncList[0]), Dir)
 440                     if os.path.isfile(IncFile.Path):
 441                         Lines.extend(self.PreProcess(IncFile))
 442                         break
 443                 else:
 444                     EdkLogger.error("Unicode File Parser", FILE_NOT_FOUND, Message="Cannot find include file", ExtraData=str(IncList[0]))
 445                 continue
 446
 447             Lines.append(Line)
 448
 449         return Lines
 450
 451     #
 452     # Load a .uni file
 453     #
 454     def LoadUniFile(self, File = None):
 455         if File == None:
 456             EdkLogger.error("Unicode File Parser", PARSER_ERROR, 'No unicode file is given')
 457         self.File = File
 458         #
 459         # Process special char in file
 460         #
 461         Lines = self.PreProcess(File)
 462
 463         #
 464         # Get Unicode Information
 465         #
 466         for IndexI in range(len(Lines)):
 467             Line = Lines[IndexI]
 468             if (IndexI + 1) < len(Lines):
 469                 SecondLine = Lines[IndexI + 1]
 470             if (IndexI + 2) < len(Lines):
 471                 ThirdLine = Lines[IndexI + 2]
 472
 473             #
 474             # Get Language def information
 475             #
 476             if Line.find(u'#langdef ') >= 0:
 477                 self.GetLangDef(File, Line)
 478                 continue
 479
 480             Name = ''
 481             Language = ''
 482             Value = ''
 483             #
 484             # Get string def information format 1 as below
 485             #
 486             #     #string MY_STRING_1
 487             #     #language eng
 488             #     My first English string line 1
 489             #     My first English string line 2
 490             #     #string MY_STRING_1
 491             #     #language spa
 492             #     Mi segunda secuencia 1
 493             #     Mi segunda secuencia 2
 494             #
 495             if Line.find(u'#string ') >= 0 and Line.find(u'#language ') < 0 and \
 496                 SecondLine.find(u'#string ') < 0 and SecondLine.find(u'#language ') >= 0 and \
 497                 ThirdLine.find(u'#string ') < 0 and ThirdLine.find(u'#language ') < 0:
 498                 Name = Line[Line.find(u'#string ') + len(u'#string ') : ].strip(' ')
 499                 Language = SecondLine[SecondLine.find(u'#language ') + len(u'#language ') : ].strip(' ')
 500                 for IndexJ in range(IndexI + 2, len(Lines)):
 501                     if Lines[IndexJ].find(u'#string ') < 0 and Lines[IndexJ].find(u'#language ') < 0:
 502                         Value = Value + Lines[IndexJ]
 503                     else:
 504                         IndexI = IndexJ
 505                         break
 506                 # Value = Value.replace(u'\r\n', u'')
 507                 Language = GetLanguageCode(Language, self.IsCompatibleMode, self.File)
 508                 # Check the string name is the upper character
 509                 if not self.IsCompatibleMode and Name != '':
 510                     MatchString = re.match('[A-Z0-9_]+', Name, re.UNICODE)
 511                     if MatchString == None or MatchString.end(0) != len(Name):
 512                         EdkLogger.error('Unicode File Parser', FORMAT_INVALID, 'The string token name %s defined in UNI file %s contains the invalid lower case character.' %(Name, self.File))
 513                 self.AddStringToList(Name, Language, Value)
 514                 continue
 515
 516             #
 517             # Get string def information format 2 as below
 518             #
 519             #     #string MY_STRING_1     #language eng     "My first English string line 1"
 520             #                                               "My first English string line 2"
 521             #                             #language spa     "Mi segunda secuencia 1"
 522             #                                               "Mi segunda secuencia 2"
 523             #     #string MY_STRING_2     #language eng     "My first English string line 1"
 524             #                                               "My first English string line 2"
 525             #     #string MY_STRING_2     #language spa     "Mi segunda secuencia 1"
 526             #                                               "Mi segunda secuencia 2"
 527             #
 528             if Line.find(u'#string ') >= 0 and Line.find(u'#language ') >= 0:
 529                 StringItem = Line
 530                 for IndexJ in range(IndexI + 1, len(Lines)):
 531                     if Lines[IndexJ].find(u'#string ') >= 0 and Lines[IndexJ].find(u'#language ') >= 0:
 532                         IndexI = IndexJ
 533                         break
 534                     elif Lines[IndexJ].find(u'#string ') < 0 and Lines[IndexJ].find(u'#language ') >= 0:
 535                         StringItem = StringItem + Lines[IndexJ]
 536                     elif Lines[IndexJ].count(u'\"') >= 2:
 537                         StringItem = StringItem[ : StringItem.rfind(u'\"')] + Lines[IndexJ][Lines[IndexJ].find(u'\"') + len(u'\"') : ]
 538                 self.GetStringObject(StringItem)
 539                 continue
 540
 541     #
 542     # Load multiple .uni files
 543     #
 544     def LoadUniFiles(self, FileList):
 545         if len(FileList) > 0:
 546             for File in FileList:
 547                 self.LoadUniFile(File)
 548
 549     #
 550     # Add a string to list
 551     #
 552     def AddStringToList(self, Name, Language, Value, Token = None, Referenced = False, UseOtherLangDef = '', Index = -1):
 553         for LangNameItem in self.LanguageDef:
 554             if Language == LangNameItem[0]:
 555                 break
 556         else:
 557             EdkLogger.error('Unicode File Parser', FORMAT_NOT_SUPPORTED, "The language '%s' for %s is not defined in Unicode file %s." \
 558                             % (Language, Name, self.File))
 559
 560         if Language not in self.OrderedStringList:
 561             self.OrderedStringList[Language] = []
 562             self.OrderedStringDict[Language] = {}
 563
 564         IsAdded = True
 565         if Name in self.OrderedStringDict[Language]:
 566             IsAdded = False
 567             if Value != None:
 568                 ItemIndexInList = self.OrderedStringDict[Language][Name]
 569                 Item = self.OrderedStringList[Language][ItemIndexInList]
 570                 Item.UpdateValue(Value)
 571                 Item.UseOtherLangDef = ''
 572
 573         if IsAdded:
 574             Token = len(self.OrderedStringList[Language])
 575             if Index == -1:
 576                 self.OrderedStringList[Language].append(StringDefClassObject(Name, Value, Referenced, Token, UseOtherLangDef))
 577                 self.OrderedStringDict[Language][Name] = Token
 578                 for LangName in self.LanguageDef:
 579                     #
 580                     # New STRING token will be added into all language string lists.
 581                     # so that the unique STRING identifier is reserved for all languages in the package list.
 582                     #
 583                     if LangName[0] != Language:
 584                         if UseOtherLangDef != '':
 585                             OtherLangDef = UseOtherLangDef
 586                         else:
 587                             OtherLangDef = Language
 588                         self.OrderedStringList[LangName[0]].append(StringDefClassObject(Name, '', Referenced, Token, OtherLangDef))
 589                         self.OrderedStringDict[LangName[0]][Name] = len(self.OrderedStringList[LangName[0]]) - 1
 590             else:
 591                 self.OrderedStringList[Language].insert(Index, StringDefClassObject(Name, Value, Referenced, Token, UseOtherLangDef))
 592                 self.OrderedStringDict[Language][Name] = Index
 593
 594     #
 595     # Set the string as referenced
 596     #
 597     def SetStringReferenced(self, Name):
 598         #
 599         # String stoken are added in the same order in all language string lists.
 600         # So, only update the status of string stoken in first language string list.
 601         #
 602         Lang = self.LanguageDef[0][0]
 603         if Name in self.OrderedStringDict[Lang]:
 604             ItemIndexInList = self.OrderedStringDict[Lang][Name]
 605             Item = self.OrderedStringList[Lang][ItemIndexInList]
 606             Item.Referenced = True
 607
 608     #
 609     # Search the string in language definition by Name
 610     #
 611     def FindStringValue(self, Name, Lang):
 612         if Name in self.OrderedStringDict[Lang]:
 613             ItemIndexInList = self.OrderedStringDict[Lang][Name]
 614             return self.OrderedStringList[Lang][ItemIndexInList]
 615
 616         return None
 617
 618     #
 619     # Search the string in language definition by Token
 620     #
 621     def FindByToken(self, Token, Lang):
 622         for Item in self.OrderedStringList[Lang]:
 623             if Item.Token == Token:
 624                 return Item
 625
 626         return None
 627
 628     #
 629     # Re-order strings and re-generate tokens
 630     #
 631     def ReToken(self):
 632         #
 633         # Retoken all language strings according to the status of string stoken in the first language string.
 634         #
 635         FirstLangName = self.LanguageDef[0][0]
 636
 637         # Convert the OrderedStringList to be OrderedStringListByToken in order to faciliate future search by token
 638         for LangNameItem in self.LanguageDef:
 639             self.OrderedStringListByToken[LangNameItem[0]] = {}
 640
 641         #
 642         # Use small token for all referred string stoken.
 643         #
 644         RefToken = 0
 645         for Index in range (0, len (self.OrderedStringList[FirstLangName])):
 646             FirstLangItem = self.OrderedStringList[FirstLangName][Index]
 647             if FirstLangItem.Referenced == True:
 648                 for LangNameItem in self.LanguageDef:
 649                     LangName = LangNameItem[0]
 650                     OtherLangItem = self.OrderedStringList[LangName][Index]
 651                     OtherLangItem.Referenced = True
 652                     OtherLangItem.Token = RefToken
 653                     self.OrderedStringListByToken[LangName][OtherLangItem.Token] = OtherLangItem
 654                 RefToken = RefToken + 1
 655
 656         #
 657         # Use big token for all unreferred string stoken.
 658         #
 659         UnRefToken = 0
 660         for Index in range (0, len (self.OrderedStringList[FirstLangName])):
 661             FirstLangItem = self.OrderedStringList[FirstLangName][Index]
 662             if FirstLangItem.Referenced == False:
 663                 for LangNameItem in self.LanguageDef:
 664                     LangName = LangNameItem[0]
 665                     OtherLangItem = self.OrderedStringList[LangName][Index]
 666                     OtherLangItem.Token = RefToken + UnRefToken
 667                     self.OrderedStringListByToken[LangName][OtherLangItem.Token] = OtherLangItem
 668                 UnRefToken = UnRefToken + 1
 669
 670     #
 671     # Show the instance itself
 672     #
 673     def ShowMe(self):
 674         print self.LanguageDef
 675         #print self.OrderedStringList
 676         for Item in self.OrderedStringList:
 677             print Item
 678             for Member in self.OrderedStringList[Item]:
 679                 print str(Member)
 680
 681 # This acts like the main() function for the script, unless it is 'import'ed into another
 682 # script.
 683 if __name__ == '__main__':
 684     EdkLogger.Initialize()
 685     EdkLogger.SetLevel(EdkLogger.DEBUG_0)
 686     a = UniFileClassObject([PathClass("C:\\Edk\\Strings.uni"), PathClass("C:\\Edk\\Strings2.uni")])
 687     a.ReToken()
 688     a.ShowMe()