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