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 - 2018, 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 from Common.GlobalData import *
  28 ##
  29 # Static definitions
  30 #
  31 UNICODE_WIDE_CHAR = u'\\wide'
  32 UNICODE_NARROW_CHAR = u'\\narrow'
  33 UNICODE_NON_BREAKING_CHAR = u'\\nbr'
  34 UNICODE_UNICODE_CR = '\r'
  35 UNICODE_UNICODE_LF = '\n'
  36
  37 NARROW_CHAR = u'\uFFF0'
  38 WIDE_CHAR = u'\uFFF1'
  39 NON_BREAKING_CHAR = u'\uFFF2'
  40 CR = u'\u000D'
  41 LF = u'\u000A'
  42 NULL = u'\u0000'
  43 TAB = u'\t'
  44 BACK_SLASH_PLACEHOLDER = u'\u0006'
  45
  46 gIncludePattern = re.compile("^#include +[\"<]+([^\"< >]+)[>\"]+$", re.MULTILINE | re.UNICODE)
  47
  48 ## Convert a python unicode string to a normal string
  49 #
  50 # Convert a python unicode string to a normal string
  51 # UniToStr(u'I am a string') is 'I am a string'
  52 #
  53 # @param Uni:  The python unicode string
  54 #
  55 # @retval:     The formatted normal string
  56 #
  57 def UniToStr(Uni):
  58     return repr(Uni)[2:-1]
  59
  60 ## Convert a unicode string to a Hex list
  61 #
  62 # Convert a unicode string to a Hex list
  63 # UniToHexList('ABC') is ['0x41', '0x00', '0x42', '0x00', '0x43', '0x00']
  64 #
  65 # @param Uni:    The python unicode string
  66 #
  67 # @retval List:  The formatted hex list
  68 #
  69 def UniToHexList(Uni):
  70     List = []
  71     for Item in Uni:
  72         Temp = '%04X' % ord(Item)
  73         List.append('0x' + Temp[2:4])
  74         List.append('0x' + Temp[0:2])
  75     return List
  76
  77 LangConvTable = {'eng':'en', 'fra':'fr', \
  78                  'aar':'aa', 'abk':'ab', 'ave':'ae', 'afr':'af', 'aka':'ak', 'amh':'am', \
  79                  'arg':'an', 'ara':'ar', 'asm':'as', 'ava':'av', 'aym':'ay', 'aze':'az', \
  80                  'bak':'ba', 'bel':'be', 'bul':'bg', 'bih':'bh', 'bis':'bi', 'bam':'bm', \
  81                  'ben':'bn', 'bod':'bo', 'bre':'br', 'bos':'bs', 'cat':'ca', 'che':'ce', \
  82                  'cha':'ch', 'cos':'co', 'cre':'cr', 'ces':'cs', 'chu':'cu', 'chv':'cv', \
  83                  'cym':'cy', 'dan':'da', 'deu':'de', 'div':'dv', 'dzo':'dz', 'ewe':'ee', \
  84                  'ell':'el', 'epo':'eo', 'spa':'es', 'est':'et', 'eus':'eu', 'fas':'fa', \
  85                  'ful':'ff', 'fin':'fi', 'fij':'fj', 'fao':'fo', 'fry':'fy', 'gle':'ga', \
  86                  'gla':'gd', 'glg':'gl', 'grn':'gn', 'guj':'gu', 'glv':'gv', 'hau':'ha', \
  87                  'heb':'he', 'hin':'hi', 'hmo':'ho', 'hrv':'hr', 'hat':'ht', 'hun':'hu', \
  88                  'hye':'hy', 'her':'hz', 'ina':'ia', 'ind':'id', 'ile':'ie', 'ibo':'ig', \
  89                  'iii':'ii', 'ipk':'ik', 'ido':'io', 'isl':'is', 'ita':'it', 'iku':'iu', \
  90                  'jpn':'ja', 'jav':'jv', 'kat':'ka', 'kon':'kg', 'kik':'ki', 'kua':'kj', \
  91                  'kaz':'kk', 'kal':'kl', 'khm':'km', 'kan':'kn', 'kor':'ko', 'kau':'kr', \
  92                  'kas':'ks', 'kur':'ku', 'kom':'kv', 'cor':'kw', 'kir':'ky', 'lat':'la', \
  93                  'ltz':'lb', 'lug':'lg', 'lim':'li', 'lin':'ln', 'lao':'lo', 'lit':'lt', \
  94                  'lub':'lu', 'lav':'lv', 'mlg':'mg', 'mah':'mh', 'mri':'mi', 'mkd':'mk', \
  95                  'mal':'ml', 'mon':'mn', 'mar':'mr', 'msa':'ms', 'mlt':'mt', 'mya':'my', \
  96                  'nau':'na', 'nob':'nb', 'nde':'nd', 'nep':'ne', 'ndo':'ng', 'nld':'nl', \
  97                  'nno':'nn', 'nor':'no', 'nbl':'nr', 'nav':'nv', 'nya':'ny', 'oci':'oc', \
  98                  'oji':'oj', 'orm':'om', 'ori':'or', 'oss':'os', 'pan':'pa', 'pli':'pi', \
  99                  'pol':'pl', 'pus':'ps', 'por':'pt', 'que':'qu', 'roh':'rm', 'run':'rn', \
 100                  'ron':'ro', 'rus':'ru', 'kin':'rw', 'san':'sa', 'srd':'sc', 'snd':'sd', \
 101                  'sme':'se', 'sag':'sg', 'sin':'si', 'slk':'sk', 'slv':'sl', 'smo':'sm', \
 102                  'sna':'sn', 'som':'so', 'sqi':'sq', 'srp':'sr', 'ssw':'ss', 'sot':'st', \
 103                  'sun':'su', 'swe':'sv', 'swa':'sw', 'tam':'ta', 'tel':'te', 'tgk':'tg', \
 104                  'tha':'th', 'tir':'ti', 'tuk':'tk', 'tgl':'tl', 'tsn':'tn', 'ton':'to', \
 105                  'tur':'tr', 'tso':'ts', 'tat':'tt', 'twi':'tw', 'tah':'ty', 'uig':'ug', \
 106                  'ukr':'uk', 'urd':'ur', 'uzb':'uz', 'ven':'ve', 'vie':'vi', 'vol':'vo', \
 107                  'wln':'wa', 'wol':'wo', 'xho':'xh', 'yid':'yi', 'yor':'yo', 'zha':'za', \
 108                  'zho':'zh', 'zul':'zu'}
 109
 110 ## GetLanguageCode
 111 #
 112 # Check the language code read from .UNI file and convert ISO 639-2 codes to RFC 4646 codes if appropriate
 113 # ISO 639-2 language codes supported in compatiblity mode
 114 # RFC 4646 language codes supported in native mode
 115 #
 116 # @param LangName:   Language codes read from .UNI file
 117 #
 118 # @retval LangName:  Valid lanugage code in RFC 4646 format or None
 119 #
 120 def GetLanguageCode(LangName, IsCompatibleMode, File):
 121     length = len(LangName)
 122     if IsCompatibleMode:
 123         if length == 3 and LangName.isalpha():
 124             TempLangName = LangConvTable.get(LangName.lower())
 125             if TempLangName is not None:
 126                 return TempLangName
 127             return LangName
 128         else:
 129             EdkLogger.error("Unicode File Parser", FORMAT_INVALID, "Invalid ISO 639-2 language code : %s" % LangName, File)
 130
 131     if (LangName[0] == 'X' or LangName[0] == 'x') and LangName[1] == '-':
 132         return LangName
 133     if length == 2:
 134         if LangName.isalpha():
 135             return LangName
 136     elif length == 3:
 137         if LangName.isalpha() and LangConvTable.get(LangName.lower()) is None:
 138             return LangName
 139     elif length == 5:
 140         if LangName[0:2].isalpha() and LangName[2] == '-':
 141             return LangName
 142     elif length >= 6:
 143         if LangName[0:2].isalpha() and LangName[2] == '-':
 144             return LangName
 145         if LangName[0:3].isalpha() and LangConvTable.get(LangName.lower()) is None and LangName[3] == '-':
 146             return LangName
 147
 148     EdkLogger.error("Unicode File Parser", FORMAT_INVALID, "Invalid RFC 4646 language code : %s" % LangName, File)
 149
 150 ## Ucs2Codec
 151 #
 152 # This is only a partial codec implementation. It only supports
 153 # encoding, and is primarily used to check that all the characters are
 154 # valid for UCS-2.
 155 #
 156 class Ucs2Codec(codecs.Codec):
 157     def __init__(self):
 158         self.__utf16 = codecs.lookup('utf-16')
 159
 160     def encode(self, input, errors='strict'):
 161         for Char in input:
 162             CodePoint = ord(Char)
 163             if CodePoint >= 0xd800 and CodePoint <= 0xdfff:
 164                 raise ValueError("Code Point is in range reserved for " +
 165                                  "UTF-16 surrogate pairs")
 166             elif CodePoint > 0xffff:
 167                 raise ValueError("Code Point too large to encode in UCS-2")
 168         return self.__utf16.encode(input)
 169
 170 TheUcs2Codec = Ucs2Codec()
 171 def Ucs2Search(name):
 172     if name == 'ucs-2':
 173         return codecs.CodecInfo(
 174             name=name,
 175             encode=TheUcs2Codec.encode,
 176             decode=TheUcs2Codec.decode)
 177     else:
 178         return None
 179 codecs.register(Ucs2Search)
 180
 181 ## StringDefClassObject
 182 #
 183 # A structure for language definition
 184 #
 185 class StringDefClassObject(object):
 186     def __init__(self, Name = None, Value = None, Referenced = False, Token = None, UseOtherLangDef = ''):
 187         self.StringName = ''
 188         self.StringNameByteList = []
 189         self.StringValue = ''
 190         self.StringValueByteList = ''
 191         self.Token = 0
 192         self.Referenced = Referenced
 193         self.UseOtherLangDef = UseOtherLangDef
 194         self.Length = 0
 195
 196         if Name is not None:
 197             self.StringName = Name
 198             self.StringNameByteList = UniToHexList(Name)
 199         if Value is not None:
 200             self.StringValue = Value + u'\x00'        # Add a NULL at string tail
 201             self.StringValueByteList = UniToHexList(self.StringValue)
 202             self.Length = len(self.StringValueByteList)
 203         if Token is not None:
 204             self.Token = Token
 205
 206     def __str__(self):
 207         return repr(self.StringName) + ' ' + \
 208                repr(self.Token) + ' ' + \
 209                repr(self.Referenced) + ' ' + \
 210                repr(self.StringValue) + ' ' + \
 211                repr(self.UseOtherLangDef)
 212
 213     def UpdateValue(self, Value = None):
 214         if Value is not None:
 215             self.StringValue = Value + u'\x00'        # Add a NULL at string tail
 216             self.StringValueByteList = UniToHexList(self.StringValue)
 217             self.Length = len(self.StringValueByteList)
 218
 219 def StripComments(Line):
 220     Comment = u'//'
 221     CommentPos = Line.find(Comment)
 222     while CommentPos >= 0:
 223     # if there are non matched quotes before the comment header
 224     # then we are in the middle of a string
 225     # but we need to ignore the escaped quotes and backslashes.
 226         if ((Line.count(u'"', 0, CommentPos) - Line.count(u'\\"', 0, CommentPos)) & 1) == 1:
 227             CommentPos = Line.find (Comment, CommentPos + 1)
 228         else:
 229             return Line[:CommentPos].strip()
 230     return Line.strip()
 231
 232 ## UniFileClassObject
 233 #
 234 # A structure for .uni file definition
 235 #
 236 class UniFileClassObject(object):
 237     def __init__(self, FileList = [], IsCompatibleMode = False, IncludePathList = []):
 238         self.FileList = FileList
 239         self.Token = 2
 240         self.LanguageDef = []                   #[ [u'LanguageIdentifier', u'PrintableName'], ... ]
 241         self.OrderedStringList = {}             #{ u'LanguageIdentifier' : [StringDefClassObject]  }
 242         self.OrderedStringDict = {}             #{ u'LanguageIdentifier' : {StringName:(IndexInList)}  }
 243         self.OrderedStringListByToken = {}      #{ u'LanguageIdentifier' : {Token: StringDefClassObject} }
 244         self.IsCompatibleMode = IsCompatibleMode
 245         self.IncludePathList = IncludePathList
 246         if len(self.FileList) > 0:
 247             self.LoadUniFiles(FileList)
 248
 249     #
 250     # Get Language definition
 251     #
 252     def GetLangDef(self, File, Line):
 253         Lang = distutils.util.split_quoted((Line.split(u"//")[0]))
 254         if len(Lang) != 3:
 255             try:
 256                 FileIn = self.OpenUniFile(LongFilePath(File.Path))
 257             except UnicodeError, X:
 258                 EdkLogger.error("build", FILE_READ_FAILURE, "File read failure: %s" % str(X), ExtraData=File);
 259             except:
 260                 EdkLogger.error("build", FILE_OPEN_FAILURE, ExtraData=File);
 261             LineNo = GetLineNo(FileIn, Line, False)
 262             EdkLogger.error("Unicode File Parser", PARSER_ERROR, "Wrong language definition",
 263                             ExtraData="""%s\n\t*Correct format is like '#langdef en-US "English"'""" % Line, File=File, Line=LineNo)
 264         else:
 265             LangName = GetLanguageCode(Lang[1], self.IsCompatibleMode, self.File)
 266             LangPrintName = Lang[2]
 267
 268         IsLangInDef = False
 269         for Item in self.LanguageDef:
 270             if Item[0] == LangName:
 271                 IsLangInDef = True
 272                 break;
 273
 274         if not IsLangInDef:
 275             self.LanguageDef.append([LangName, LangPrintName])
 276
 277         #
 278         # Add language string
 279         #
 280         self.AddStringToList(u'$LANGUAGE_NAME', LangName, LangName, 0, True, Index=0)
 281         self.AddStringToList(u'$PRINTABLE_LANGUAGE_NAME', LangName, LangPrintName, 1, True, Index=1)
 282
 283         if not IsLangInDef:
 284             #
 285             # The found STRING tokens will be added into new language string list
 286             # so that the unique STRING identifier is reserved for all languages in the package list.
 287             #
 288             FirstLangName = self.LanguageDef[0][0]
 289             if LangName != FirstLangName:
 290                 for Index in range (2, len (self.OrderedStringList[FirstLangName])):
 291                     Item = self.OrderedStringList[FirstLangName][Index]
 292                     if Item.UseOtherLangDef != '':
 293                         OtherLang = Item.UseOtherLangDef
 294                     else:
 295                         OtherLang = FirstLangName
 296                     self.OrderedStringList[LangName].append (StringDefClassObject(Item.StringName, '', Item.Referenced, Item.Token, OtherLang))
 297                     self.OrderedStringDict[LangName][Item.StringName] = len(self.OrderedStringList[LangName]) - 1
 298         return True
 299
 300     def OpenUniFile(self, FileName):
 301         #
 302         # Read file
 303         #
 304         try:
 305             UniFile = open(FileName, mode='rb')
 306             FileIn = UniFile.read()
 307             UniFile.close()
 308         except:
 309             EdkLogger.Error("build", FILE_OPEN_FAILURE, ExtraData=File)
 310
 311         #
 312         # Detect Byte Order Mark at beginning of file.  Default to UTF-8
 313         #
 314         Encoding = 'utf-8'
 315         if (FileIn.startswith(codecs.BOM_UTF16_BE) or
 316             FileIn.startswith(codecs.BOM_UTF16_LE)):
 317             Encoding = 'utf-16'
 318
 319         self.VerifyUcs2Data(FileIn, FileName, Encoding)
 320
 321         UniFile = StringIO.StringIO(FileIn)
 322         Info = codecs.lookup(Encoding)
 323         (Reader, Writer) = (Info.streamreader, Info.streamwriter)
 324         return codecs.StreamReaderWriter(UniFile, Reader, Writer)
 325
 326     def VerifyUcs2Data(self, FileIn, FileName, Encoding):
 327         Ucs2Info = codecs.lookup('ucs-2')
 328         #
 329         # Convert to unicode
 330         #
 331         try:
 332             FileDecoded = codecs.decode(FileIn, Encoding)
 333             Ucs2Info.encode(FileDecoded)
 334         except:
 335             UniFile = StringIO.StringIO(FileIn)
 336             Info = codecs.lookup(Encoding)
 337             (Reader, Writer) = (Info.streamreader, Info.streamwriter)
 338             File = codecs.StreamReaderWriter(UniFile, Reader, Writer)
 339             LineNumber = 0
 340             ErrMsg = lambda Encoding, LineNumber: \
 341                      '%s contains invalid %s characters on line %d.' % \
 342                      (FileName, Encoding, LineNumber)
 343             while True:
 344                 LineNumber = LineNumber + 1
 345                 try:
 346                     Line = File.readline()
 347                     if Line == '':
 348                         EdkLogger.error('Unicode File Parser', PARSER_ERROR,
 349                                         ErrMsg(Encoding, LineNumber))
 350                     Ucs2Info.encode(Line)
 351                 except:
 352                     EdkLogger.error('Unicode File Parser', PARSER_ERROR,
 353                                     ErrMsg('UCS-2', LineNumber))
 354
 355     #
 356     # Get String name and value
 357     #
 358     def GetStringObject(self, Item):
 359         Language = ''
 360         Value = ''
 361
 362         Name = Item.split()[1]
 363         # Check the string name
 364         if Name != '':
 365             MatchString = gIdentifierPattern.match(Name)
 366             if MatchString is None:
 367                 EdkLogger.error('Unicode File Parser', FORMAT_INVALID, 'The string token name %s defined in UNI file %s contains the invalid character.' % (Name, self.File))
 368         LanguageList = Item.split(u'#language ')
 369         for IndexI in range(len(LanguageList)):
 370             if IndexI == 0:
 371                 continue
 372             else:
 373                 Language = LanguageList[IndexI].split()[0]
 374                 Value = LanguageList[IndexI][LanguageList[IndexI].find(u'\"') + len(u'\"') : LanguageList[IndexI].rfind(u'\"')] #.replace(u'\r\n', u'')
 375                 Language = GetLanguageCode(Language, self.IsCompatibleMode, self.File)
 376                 self.AddStringToList(Name, Language, Value)
 377
 378     #
 379     # Get include file list and load them
 380     #
 381     def GetIncludeFile(self, Item, Dir):
 382         FileName = Item[Item.find(u'#include ') + len(u'#include ') :Item.find(u' ', len(u'#include '))][1:-1]
 383         self.LoadUniFile(FileName)
 384
 385     #
 386     # Pre-process before parse .uni file
 387     #
 388     def PreProcess(self, File):
 389         if not os.path.exists(File.Path) or not os.path.isfile(File.Path):
 390             EdkLogger.error("Unicode File Parser", FILE_NOT_FOUND, ExtraData=File.Path)
 391
 392         try:
 393             FileIn = self.OpenUniFile(LongFilePath(File.Path))
 394         except UnicodeError, X:
 395             EdkLogger.error("build", FILE_READ_FAILURE, "File read failure: %s" % str(X), ExtraData=File.Path);
 396         except:
 397             EdkLogger.error("build", FILE_OPEN_FAILURE, ExtraData=File.Path);
 398
 399         Lines = []
 400         #
 401         # Use unique identifier
 402         #
 403         for Line in FileIn:
 404             Line = Line.strip()
 405             Line = Line.replace(u'\\\\', BACK_SLASH_PLACEHOLDER)
 406             Line = StripComments(Line)
 407
 408             #
 409             # Ignore empty line
 410             #
 411             if len(Line) == 0:
 412                 continue
 413
 414
 415             Line = Line.replace(u'/langdef', u'#langdef')
 416             Line = Line.replace(u'/string', u'#string')
 417             Line = Line.replace(u'/language', u'#language')
 418             Line = Line.replace(u'/include', u'#include')
 419
 420             Line = Line.replace(UNICODE_WIDE_CHAR, WIDE_CHAR)
 421             Line = Line.replace(UNICODE_NARROW_CHAR, NARROW_CHAR)
 422             Line = Line.replace(UNICODE_NON_BREAKING_CHAR, NON_BREAKING_CHAR)
 423
 424             Line = Line.replace(u'\\r\\n', CR + LF)
 425             Line = Line.replace(u'\\n', CR + LF)
 426             Line = Line.replace(u'\\r', CR)
 427             Line = Line.replace(u'\\t', u' ')
 428             Line = Line.replace(u'\t', u' ')
 429             Line = Line.replace(u'\\"', u'"')
 430             Line = Line.replace(u"\\'", u"'")
 431             Line = Line.replace(BACK_SLASH_PLACEHOLDER, u'\\')
 432
 433             StartPos = Line.find(u'\\x')
 434             while (StartPos != -1):
 435                 EndPos = Line.find(u'\\', StartPos + 1, StartPos + 7)
 436                 if EndPos != -1 and EndPos - StartPos == 6 :
 437                     if g4HexChar.match(Line[StartPos + 2 : EndPos], re.UNICODE):
 438                         EndStr = Line[EndPos: ]
 439                         UniStr = ('\u' + (Line[StartPos + 2 : EndPos])).decode('unicode_escape')
 440                         if EndStr.startswith(u'\\x') and len(EndStr) >= 7:
 441                             if EndStr[6] == u'\\' and g4HexChar.match(EndStr[2 : 6], re.UNICODE):
 442                                 Line = Line[0 : StartPos] + UniStr + EndStr
 443                         else:
 444                             Line = Line[0 : StartPos] + UniStr + EndStr[1:]
 445                 StartPos = Line.find(u'\\x', StartPos + 1)
 446
 447             IncList = gIncludePattern.findall(Line)
 448             if len(IncList) == 1:
 449                 for Dir in [File.Dir] + self.IncludePathList:
 450                     IncFile = PathClass(str(IncList[0]), Dir)
 451                     if os.path.isfile(IncFile.Path):
 452                         Lines.extend(self.PreProcess(IncFile))
 453                         break
 454                 else:
 455                     EdkLogger.error("Unicode File Parser", FILE_NOT_FOUND, Message="Cannot find include file", ExtraData=str(IncList[0]))
 456                 continue
 457
 458             Lines.append(Line)
 459
 460         return Lines
 461
 462     #
 463     # Load a .uni file
 464     #
 465     def LoadUniFile(self, File = None):
 466         if File is None:
 467             EdkLogger.error("Unicode File Parser", PARSER_ERROR, 'No unicode file is given')
 468         self.File = File
 469         #
 470         # Process special char in file
 471         #
 472         Lines = self.PreProcess(File)
 473
 474         #
 475         # Get Unicode Information
 476         #
 477         for IndexI in range(len(Lines)):
 478             Line = Lines[IndexI]
 479             if (IndexI + 1) < len(Lines):
 480                 SecondLine = Lines[IndexI + 1]
 481             if (IndexI + 2) < len(Lines):
 482                 ThirdLine = Lines[IndexI + 2]
 483
 484             #
 485             # Get Language def information
 486             #
 487             if Line.find(u'#langdef ') >= 0:
 488                 self.GetLangDef(File, Line)
 489                 continue
 490
 491             Name = ''
 492             Language = ''
 493             Value = ''
 494             #
 495             # Get string def information format 1 as below
 496             #
 497             #     #string MY_STRING_1
 498             #     #language eng
 499             #     My first English string line 1
 500             #     My first English string line 2
 501             #     #string MY_STRING_1
 502             #     #language spa
 503             #     Mi segunda secuencia 1
 504             #     Mi segunda secuencia 2
 505             #
 506             if Line.find(u'#string ') >= 0 and Line.find(u'#language ') < 0 and \
 507                 SecondLine.find(u'#string ') < 0 and SecondLine.find(u'#language ') >= 0 and \
 508                 ThirdLine.find(u'#string ') < 0 and ThirdLine.find(u'#language ') < 0:
 509                 Name = Line[Line.find(u'#string ') + len(u'#string ') : ].strip(' ')
 510                 Language = SecondLine[SecondLine.find(u'#language ') + len(u'#language ') : ].strip(' ')
 511                 for IndexJ in range(IndexI + 2, len(Lines)):
 512                     if Lines[IndexJ].find(u'#string ') < 0 and Lines[IndexJ].find(u'#language ') < 0:
 513                         Value = Value + Lines[IndexJ]
 514                     else:
 515                         IndexI = IndexJ
 516                         break
 517                 # Value = Value.replace(u'\r\n', u'')
 518                 Language = GetLanguageCode(Language, self.IsCompatibleMode, self.File)
 519                 # Check the string name
 520                 if not self.IsCompatibleMode and Name != '':
 521                     MatchString = gIdentifierPattern.match(Name)
 522                     if MatchString is None:
 523                         EdkLogger.error('Unicode File Parser', FORMAT_INVALID, 'The string token name %s defined in UNI file %s contains the invalid character.' % (Name, self.File))
 524                 self.AddStringToList(Name, Language, Value)
 525                 continue
 526
 527             #
 528             # Get string def information format 2 as below
 529             #
 530             #     #string MY_STRING_1     #language eng     "My first English string line 1"
 531             #                                               "My first English string line 2"
 532             #                             #language spa     "Mi segunda secuencia 1"
 533             #                                               "Mi segunda secuencia 2"
 534             #     #string MY_STRING_2     #language eng     "My first English string line 1"
 535             #                                               "My first English string line 2"
 536             #     #string MY_STRING_2     #language spa     "Mi segunda secuencia 1"
 537             #                                               "Mi segunda secuencia 2"
 538             #
 539             if Line.find(u'#string ') >= 0 and Line.find(u'#language ') >= 0:
 540                 StringItem = Line
 541                 for IndexJ in range(IndexI + 1, len(Lines)):
 542                     if Lines[IndexJ].find(u'#string ') >= 0 and Lines[IndexJ].find(u'#language ') >= 0:
 543                         IndexI = IndexJ
 544                         break
 545                     elif Lines[IndexJ].find(u'#string ') < 0 and Lines[IndexJ].find(u'#language ') >= 0:
 546                         StringItem = StringItem + Lines[IndexJ]
 547                     elif Lines[IndexJ].count(u'\"') >= 2:
 548                         StringItem = StringItem[ : StringItem.rfind(u'\"')] + Lines[IndexJ][Lines[IndexJ].find(u'\"') + len(u'\"') : ]
 549                 self.GetStringObject(StringItem)
 550                 continue
 551
 552     #
 553     # Load multiple .uni files
 554     #
 555     def LoadUniFiles(self, FileList):
 556         if len(FileList) > 0:
 557             for File in FileList:
 558                 self.LoadUniFile(File)
 559
 560     #
 561     # Add a string to list
 562     #
 563     def AddStringToList(self, Name, Language, Value, Token = None, Referenced = False, UseOtherLangDef = '', Index = -1):
 564         for LangNameItem in self.LanguageDef:
 565             if Language == LangNameItem[0]:
 566                 break
 567         else:
 568             EdkLogger.error('Unicode File Parser', FORMAT_NOT_SUPPORTED, "The language '%s' for %s is not defined in Unicode file %s." \
 569                             % (Language, Name, self.File))
 570
 571         if Language not in self.OrderedStringList:
 572             self.OrderedStringList[Language] = []
 573             self.OrderedStringDict[Language] = {}
 574
 575         IsAdded = True
 576         if Name in self.OrderedStringDict[Language]:
 577             IsAdded = False
 578             if Value is not None:
 579                 ItemIndexInList = self.OrderedStringDict[Language][Name]
 580                 Item = self.OrderedStringList[Language][ItemIndexInList]
 581                 Item.UpdateValue(Value)
 582                 Item.UseOtherLangDef = ''
 583
 584         if IsAdded:
 585             Token = len(self.OrderedStringList[Language])
 586             if Index == -1:
 587                 self.OrderedStringList[Language].append(StringDefClassObject(Name, Value, Referenced, Token, UseOtherLangDef))
 588                 self.OrderedStringDict[Language][Name] = Token
 589                 for LangName in self.LanguageDef:
 590                     #
 591                     # New STRING token will be added into all language string lists.
 592                     # so that the unique STRING identifier is reserved for all languages in the package list.
 593                     #
 594                     if LangName[0] != Language:
 595                         if UseOtherLangDef != '':
 596                             OtherLangDef = UseOtherLangDef
 597                         else:
 598                             OtherLangDef = Language
 599                         self.OrderedStringList[LangName[0]].append(StringDefClassObject(Name, '', Referenced, Token, OtherLangDef))
 600                         self.OrderedStringDict[LangName[0]][Name] = len(self.OrderedStringList[LangName[0]]) - 1
 601             else:
 602                 self.OrderedStringList[Language].insert(Index, StringDefClassObject(Name, Value, Referenced, Token, UseOtherLangDef))
 603                 self.OrderedStringDict[Language][Name] = Index
 604
 605     #
 606     # Set the string as referenced
 607     #
 608     def SetStringReferenced(self, Name):
 609         #
 610         # String stoken are added in the same order in all language string lists.
 611         # So, only update the status of string stoken in first language string list.
 612         #
 613         Lang = self.LanguageDef[0][0]
 614         if Name in self.OrderedStringDict[Lang]:
 615             ItemIndexInList = self.OrderedStringDict[Lang][Name]
 616             Item = self.OrderedStringList[Lang][ItemIndexInList]
 617             Item.Referenced = True
 618
 619     #
 620     # Search the string in language definition by Name
 621     #
 622     def FindStringValue(self, Name, Lang):
 623         if Name in self.OrderedStringDict[Lang]:
 624             ItemIndexInList = self.OrderedStringDict[Lang][Name]
 625             return self.OrderedStringList[Lang][ItemIndexInList]
 626
 627         return None
 628
 629     #
 630     # Search the string in language definition by Token
 631     #
 632     def FindByToken(self, Token, Lang):
 633         for Item in self.OrderedStringList[Lang]:
 634             if Item.Token == Token:
 635                 return Item
 636
 637         return None
 638
 639     #
 640     # Re-order strings and re-generate tokens
 641     #
 642     def ReToken(self):
 643         #
 644         # Retoken all language strings according to the status of string stoken in the first language string.
 645         #
 646         FirstLangName = self.LanguageDef[0][0]
 647
 648         # Convert the OrderedStringList to be OrderedStringListByToken in order to faciliate future search by token
 649         for LangNameItem in self.LanguageDef:
 650             self.OrderedStringListByToken[LangNameItem[0]] = {}
 651
 652         #
 653         # Use small token for all referred string stoken.
 654         #
 655         RefToken = 0
 656         for Index in range (0, len (self.OrderedStringList[FirstLangName])):
 657             FirstLangItem = self.OrderedStringList[FirstLangName][Index]
 658             if FirstLangItem.Referenced == True:
 659                 for LangNameItem in self.LanguageDef:
 660                     LangName = LangNameItem[0]
 661                     OtherLangItem = self.OrderedStringList[LangName][Index]
 662                     OtherLangItem.Referenced = True
 663                     OtherLangItem.Token = RefToken
 664                     self.OrderedStringListByToken[LangName][OtherLangItem.Token] = OtherLangItem
 665                 RefToken = RefToken + 1
 666
 667         #
 668         # Use big token for all unreferred string stoken.
 669         #
 670         UnRefToken = 0
 671         for Index in range (0, len (self.OrderedStringList[FirstLangName])):
 672             FirstLangItem = self.OrderedStringList[FirstLangName][Index]
 673             if FirstLangItem.Referenced == False:
 674                 for LangNameItem in self.LanguageDef:
 675                     LangName = LangNameItem[0]
 676                     OtherLangItem = self.OrderedStringList[LangName][Index]
 677                     OtherLangItem.Token = RefToken + UnRefToken
 678                     self.OrderedStringListByToken[LangName][OtherLangItem.Token] = OtherLangItem
 679                 UnRefToken = UnRefToken + 1
 680
 681     #
 682     # Show the instance itself
 683     #
 684     def ShowMe(self):
 685         print self.LanguageDef
 686         #print self.OrderedStringList
 687         for Item in self.OrderedStringList:
 688             print Item
 689             for Member in self.OrderedStringList[Item]:
 690                 print str(Member)
 691
 692 # This acts like the main() function for the script, unless it is 'import'ed into another
 693 # script.
 694 if __name__ == '__main__':
 695     EdkLogger.Initialize()
 696     EdkLogger.SetLevel(EdkLogger.DEBUG_0)
 697     a = UniFileClassObject([PathClass("C:\\Edk\\Strings.uni"), PathClass("C:\\Edk\\Strings2.uni")])
 698     a.ReToken()
 699     a.ShowMe()