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