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 # SPDX-License-Identifier: BSD-2-Clause-Patent
   9
  10 ##
  11 # Import Modules
  12 #
  13 from __future__ import print_function
  14 import Common.LongFilePathOs as os, codecs, re
  15 import shlex
  16 import Common.EdkLogger as EdkLogger
  17 from io import BytesIO
  18 from Common.BuildToolError import *
  19 from Common.StringUtils import GetLineNo
  20 from Common.Misc import PathClass
  21 from Common.LongFilePathSupport import LongFilePath
  22 from Common.GlobalData import *
  23 ##
  24 # Static definitions
  25 #
  26 UNICODE_WIDE_CHAR = u'\\wide'
  27 UNICODE_NARROW_CHAR = u'\\narrow'
  28 UNICODE_NON_BREAKING_CHAR = u'\\nbr'
  29 UNICODE_UNICODE_CR = '\r'
  30 UNICODE_UNICODE_LF = '\n'
  31
  32 NARROW_CHAR = u'\uFFF0'
  33 WIDE_CHAR = u'\uFFF1'
  34 NON_BREAKING_CHAR = u'\uFFF2'
  35 CR = u'\u000D'
  36 LF = u'\u000A'
  37 NULL = u'\u0000'
  38 TAB = u'\t'
  39 BACK_SLASH_PLACEHOLDER = u'\u0006'
  40
  41 gIncludePattern = re.compile("^#include +[\"<]+([^\"< >]+)[>\"]+$", re.MULTILINE | re.UNICODE)
  42
  43 ## Convert a unicode string to a Hex list
  44 #
  45 # Convert a unicode string to a Hex list
  46 # UniToHexList('ABC') is ['0x41', '0x00', '0x42', '0x00', '0x43', '0x00']
  47 #
  48 # @param Uni:    The python unicode string
  49 #
  50 # @retval List:  The formatted hex list
  51 #
  52 def UniToHexList(Uni):
  53     List = []
  54     for Item in Uni:
  55         Temp = '%04X' % ord(Item)
  56         List.append('0x' + Temp[2:4])
  57         List.append('0x' + Temp[0:2])
  58     return List
  59
  60 LangConvTable = {'eng':'en', 'fra':'fr', \
  61                  'aar':'aa', 'abk':'ab', 'ave':'ae', 'afr':'af', 'aka':'ak', 'amh':'am', \
  62                  'arg':'an', 'ara':'ar', 'asm':'as', 'ava':'av', 'aym':'ay', 'aze':'az', \
  63                  'bak':'ba', 'bel':'be', 'bul':'bg', 'bih':'bh', 'bis':'bi', 'bam':'bm', \
  64                  'ben':'bn', 'bod':'bo', 'bre':'br', 'bos':'bs', 'cat':'ca', 'che':'ce', \
  65                  'cha':'ch', 'cos':'co', 'cre':'cr', 'ces':'cs', 'chu':'cu', 'chv':'cv', \
  66                  'cym':'cy', 'dan':'da', 'deu':'de', 'div':'dv', 'dzo':'dz', 'ewe':'ee', \
  67                  'ell':'el', 'epo':'eo', 'spa':'es', 'est':'et', 'eus':'eu', 'fas':'fa', \
  68                  'ful':'ff', 'fin':'fi', 'fij':'fj', 'fao':'fo', 'fry':'fy', 'gle':'ga', \
  69                  'gla':'gd', 'glg':'gl', 'grn':'gn', 'guj':'gu', 'glv':'gv', 'hau':'ha', \
  70                  'heb':'he', 'hin':'hi', 'hmo':'ho', 'hrv':'hr', 'hat':'ht', 'hun':'hu', \
  71                  'hye':'hy', 'her':'hz', 'ina':'ia', 'ind':'id', 'ile':'ie', 'ibo':'ig', \
  72                  'iii':'ii', 'ipk':'ik', 'ido':'io', 'isl':'is', 'ita':'it', 'iku':'iu', \
  73                  'jpn':'ja', 'jav':'jv', 'kat':'ka', 'kon':'kg', 'kik':'ki', 'kua':'kj', \
  74                  'kaz':'kk', 'kal':'kl', 'khm':'km', 'kan':'kn', 'kor':'ko', 'kau':'kr', \
  75                  'kas':'ks', 'kur':'ku', 'kom':'kv', 'cor':'kw', 'kir':'ky', 'lat':'la', \
  76                  'ltz':'lb', 'lug':'lg', 'lim':'li', 'lin':'ln', 'lao':'lo', 'lit':'lt', \
  77                  'lub':'lu', 'lav':'lv', 'mlg':'mg', 'mah':'mh', 'mri':'mi', 'mkd':'mk', \
  78                  'mal':'ml', 'mon':'mn', 'mar':'mr', 'msa':'ms', 'mlt':'mt', 'mya':'my', \
  79                  'nau':'na', 'nob':'nb', 'nde':'nd', 'nep':'ne', 'ndo':'ng', 'nld':'nl', \
  80                  'nno':'nn', 'nor':'no', 'nbl':'nr', 'nav':'nv', 'nya':'ny', 'oci':'oc', \
  81                  'oji':'oj', 'orm':'om', 'ori':'or', 'oss':'os', 'pan':'pa', 'pli':'pi', \
  82                  'pol':'pl', 'pus':'ps', 'por':'pt', 'que':'qu', 'roh':'rm', 'run':'rn', \
  83                  'ron':'ro', 'rus':'ru', 'kin':'rw', 'san':'sa', 'srd':'sc', 'snd':'sd', \
  84                  'sme':'se', 'sag':'sg', 'sin':'si', 'slk':'sk', 'slv':'sl', 'smo':'sm', \
  85                  'sna':'sn', 'som':'so', 'sqi':'sq', 'srp':'sr', 'ssw':'ss', 'sot':'st', \
  86                  'sun':'su', 'swe':'sv', 'swa':'sw', 'tam':'ta', 'tel':'te', 'tgk':'tg', \
  87                  'tha':'th', 'tir':'ti', 'tuk':'tk', 'tgl':'tl', 'tsn':'tn', 'ton':'to', \
  88                  'tur':'tr', 'tso':'ts', 'tat':'tt', 'twi':'tw', 'tah':'ty', 'uig':'ug', \
  89                  'ukr':'uk', 'urd':'ur', 'uzb':'uz', 'ven':'ve', 'vie':'vi', 'vol':'vo', \
  90                  'wln':'wa', 'wol':'wo', 'xho':'xh', 'yid':'yi', 'yor':'yo', 'zha':'za', \
  91                  'zho':'zh', 'zul':'zu'}
  92
  93 ## GetLanguageCode
  94 #
  95 # Check the language code read from .UNI file and convert ISO 639-2 codes to RFC 4646 codes if appropriate
  96 # ISO 639-2 language codes supported in compatibility mode
  97 # RFC 4646 language codes supported in native mode
  98 #
  99 # @param LangName:   Language codes read from .UNI file
 100 #
 101 # @retval LangName:  Valid language code in RFC 4646 format or None
 102 #
 103 def GetLanguageCode(LangName, IsCompatibleMode, File):
 104     length = len(LangName)
 105     if IsCompatibleMode:
 106         if length == 3 and LangName.isalpha():
 107             TempLangName = LangConvTable.get(LangName.lower())
 108             if TempLangName is not None:
 109                 return TempLangName
 110             return LangName
 111         else:
 112             EdkLogger.error("Unicode File Parser", FORMAT_INVALID, "Invalid ISO 639-2 language code : %s" % LangName, File)
 113
 114     if (LangName[0] == 'X' or LangName[0] == 'x') and LangName[1] == '-':
 115         return LangName
 116     if length == 2:
 117         if LangName.isalpha():
 118             return LangName
 119     elif length == 3:
 120         if LangName.isalpha() and LangConvTable.get(LangName.lower()) is None:
 121             return LangName
 122     elif length == 5:
 123         if LangName[0:2].isalpha() and LangName[2] == '-':
 124             return LangName
 125     elif length >= 6:
 126         if LangName[0:2].isalpha() and LangName[2] == '-':
 127             return LangName
 128         if LangName[0:3].isalpha() and LangConvTable.get(LangName.lower()) is None and LangName[3] == '-':
 129             return LangName
 130
 131     EdkLogger.error("Unicode File Parser", FORMAT_INVALID, "Invalid RFC 4646 language code : %s" % LangName, File)
 132
 133 ## Ucs2Codec
 134 #
 135 # This is only a partial codec implementation. It only supports
 136 # encoding, and is primarily used to check that all the characters are
 137 # valid for UCS-2.
 138 #
 139 class Ucs2Codec(codecs.Codec):
 140     def __init__(self):
 141         self.__utf16 = codecs.lookup('utf-16')
 142
 143     def encode(self, input, errors='strict'):
 144         for Char in input:
 145             CodePoint = ord(Char)
 146             if CodePoint >= 0xd800 and CodePoint <= 0xdfff:
 147                 raise ValueError("Code Point is in range reserved for " +
 148                                  "UTF-16 surrogate pairs")
 149             elif CodePoint > 0xffff:
 150                 raise ValueError("Code Point too large to encode in UCS-2")
 151         return self.__utf16.encode(input)
 152
 153 TheUcs2Codec = Ucs2Codec()
 154 def Ucs2Search(name):
 155     if name in ['ucs-2', 'ucs_2']:
 156         return codecs.CodecInfo(
 157             name=name,
 158             encode=TheUcs2Codec.encode,
 159             decode=TheUcs2Codec.decode)
 160     else:
 161         return None
 162 codecs.register(Ucs2Search)
 163
 164 ## StringDefClassObject
 165 #
 166 # A structure for language definition
 167 #
 168 class StringDefClassObject(object):
 169     def __init__(self, Name = None, Value = None, Referenced = False, Token = None, UseOtherLangDef = ''):
 170         self.StringName = ''
 171         self.StringNameByteList = []
 172         self.StringValue = ''
 173         self.StringValueByteList = ''
 174         self.Token = 0
 175         self.Referenced = Referenced
 176         self.UseOtherLangDef = UseOtherLangDef
 177         self.Length = 0
 178
 179         if Name is not None:
 180             self.StringName = Name
 181             self.StringNameByteList = UniToHexList(Name)
 182         if Value is not None:
 183             self.StringValue = Value + u'\x00'        # Add a NULL at string tail
 184             self.StringValueByteList = UniToHexList(self.StringValue)
 185             self.Length = len(self.StringValueByteList)
 186         if Token is not None:
 187             self.Token = Token
 188
 189     def __str__(self):
 190         return repr(self.StringName) + ' ' + \
 191                repr(self.Token) + ' ' + \
 192                repr(self.Referenced) + ' ' + \
 193                repr(self.StringValue) + ' ' + \
 194                repr(self.UseOtherLangDef)
 195
 196     def UpdateValue(self, Value = None):
 197         if Value is not None:
 198             self.StringValue = Value + u'\x00'        # Add a NULL at string tail
 199             self.StringValueByteList = UniToHexList(self.StringValue)
 200             self.Length = len(self.StringValueByteList)
 201
 202 def StripComments(Line):
 203     Comment = u'//'
 204     CommentPos = Line.find(Comment)
 205     while CommentPos >= 0:
 206     # if there are non matched quotes before the comment header
 207     # then we are in the middle of a string
 208     # but we need to ignore the escaped quotes and backslashes.
 209         if ((Line.count(u'"', 0, CommentPos) - Line.count(u'\\"', 0, CommentPos)) & 1) == 1:
 210             CommentPos = Line.find (Comment, CommentPos + 1)
 211         else:
 212             return Line[:CommentPos].strip()
 213     return Line.strip()
 214
 215 ## UniFileClassObject
 216 #
 217 # A structure for .uni file definition
 218 #
 219 class UniFileClassObject(object):
 220     def __init__(self, FileList = [], IsCompatibleMode = False, IncludePathList = []):
 221         self.FileList = FileList
 222         self.Token = 2
 223         self.LanguageDef = []                   #[ [u'LanguageIdentifier', u'PrintableName'], ... ]
 224         self.OrderedStringList = {}             #{ u'LanguageIdentifier' : [StringDefClassObject]  }
 225         self.OrderedStringDict = {}             #{ u'LanguageIdentifier' : {StringName:(IndexInList)}  }
 226         self.OrderedStringListByToken = {}      #{ u'LanguageIdentifier' : {Token: StringDefClassObject} }
 227         self.IsCompatibleMode = IsCompatibleMode
 228         self.IncludePathList = IncludePathList
 229         if len(self.FileList) > 0:
 230             self.LoadUniFiles(FileList)
 231
 232     #
 233     # Get Language definition
 234     #
 235     def GetLangDef(self, File, Line):
 236         Lang = shlex.split(Line.split(u"//")[0])
 237         if len(Lang) != 3:
 238             try:
 239                 FileIn = UniFileClassObject.OpenUniFile(LongFilePath(File.Path))
 240             except UnicodeError as X:
 241                 EdkLogger.error("build", FILE_READ_FAILURE, "File read failure: %s" % str(X), ExtraData=File);
 242             except:
 243                 EdkLogger.error("build", FILE_OPEN_FAILURE, ExtraData=File);
 244             LineNo = GetLineNo(FileIn, Line, False)
 245             EdkLogger.error("Unicode File Parser", PARSER_ERROR, "Wrong language definition",
 246                             ExtraData="""%s\n\t*Correct format is like '#langdef en-US "English"'""" % Line, File=File, Line=LineNo)
 247         else:
 248             LangName = GetLanguageCode(Lang[1], self.IsCompatibleMode, self.File)
 249             LangPrintName = Lang[2]
 250
 251         IsLangInDef = False
 252         for Item in self.LanguageDef:
 253             if Item[0] == LangName:
 254                 IsLangInDef = True
 255                 break;
 256
 257         if not IsLangInDef:
 258             self.LanguageDef.append([LangName, LangPrintName])
 259
 260         #
 261         # Add language string
 262         #
 263         self.AddStringToList(u'$LANGUAGE_NAME', LangName, LangName, 0, True, Index=0)
 264         self.AddStringToList(u'$PRINTABLE_LANGUAGE_NAME', LangName, LangPrintName, 1, True, Index=1)
 265
 266         if not IsLangInDef:
 267             #
 268             # The found STRING tokens will be added into new language string list
 269             # so that the unique STRING identifier is reserved for all languages in the package list.
 270             #
 271             FirstLangName = self.LanguageDef[0][0]
 272             if LangName != FirstLangName:
 273                 for Index in range (2, len (self.OrderedStringList[FirstLangName])):
 274                     Item = self.OrderedStringList[FirstLangName][Index]
 275                     if Item.UseOtherLangDef != '':
 276                         OtherLang = Item.UseOtherLangDef
 277                     else:
 278                         OtherLang = FirstLangName
 279                     self.OrderedStringList[LangName].append (StringDefClassObject(Item.StringName, '', Item.Referenced, Item.Token, OtherLang))
 280                     self.OrderedStringDict[LangName][Item.StringName] = len(self.OrderedStringList[LangName]) - 1
 281         return True
 282
 283     @staticmethod
 284     def OpenUniFile(FileName):
 285         #
 286         # Read file
 287         #
 288         try:
 289             UniFile = open(FileName, mode='rb')
 290             FileIn = UniFile.read()
 291             UniFile.close()
 292         except:
 293             EdkLogger.Error("build", FILE_OPEN_FAILURE, ExtraData=File)
 294
 295         #
 296         # Detect Byte Order Mark at beginning of file.  Default to UTF-8
 297         #
 298         Encoding = 'utf-8'
 299         if (FileIn.startswith(codecs.BOM_UTF16_BE) or
 300             FileIn.startswith(codecs.BOM_UTF16_LE)):
 301             Encoding = 'utf-16'
 302
 303         UniFileClassObject.VerifyUcs2Data(FileIn, FileName, Encoding)
 304
 305         UniFile = BytesIO(FileIn)
 306         Info = codecs.lookup(Encoding)
 307         (Reader, Writer) = (Info.streamreader, Info.streamwriter)
 308         return codecs.StreamReaderWriter(UniFile, Reader, Writer)
 309
 310     @staticmethod
 311     def VerifyUcs2Data(FileIn, FileName, Encoding):
 312         Ucs2Info = codecs.lookup('ucs-2')
 313         #
 314         # Convert to unicode
 315         #
 316         try:
 317             FileDecoded = codecs.decode(FileIn, Encoding)
 318             Ucs2Info.encode(FileDecoded)
 319         except:
 320             UniFile = BytesIO(FileIn)
 321             Info = codecs.lookup(Encoding)
 322             (Reader, Writer) = (Info.streamreader, Info.streamwriter)
 323             File = codecs.StreamReaderWriter(UniFile, Reader, Writer)
 324             LineNumber = 0
 325             ErrMsg = lambda Encoding, LineNumber: \
 326                      '%s contains invalid %s characters on line %d.' % \
 327                      (FileName, Encoding, LineNumber)
 328             while True:
 329                 LineNumber = LineNumber + 1
 330                 try:
 331                     Line = File.readline()
 332                     if Line == '':
 333                         EdkLogger.error('Unicode File Parser', PARSER_ERROR,
 334                                         ErrMsg(Encoding, LineNumber))
 335                     Ucs2Info.encode(Line)
 336                 except:
 337                     EdkLogger.error('Unicode File Parser', PARSER_ERROR,
 338                                     ErrMsg('UCS-2', LineNumber))
 339
 340     #
 341     # Get String name and value
 342     #
 343     def GetStringObject(self, Item):
 344         Language = ''
 345         Value = ''
 346
 347         Name = Item.split()[1]
 348         # Check the string name
 349         if Name != '':
 350             MatchString = gIdentifierPattern.match(Name)
 351             if MatchString is None:
 352                 EdkLogger.error('Unicode File Parser', FORMAT_INVALID, 'The string token name %s defined in UNI file %s contains the invalid character.' % (Name, self.File))
 353         LanguageList = Item.split(u'#language ')
 354         for IndexI in range(len(LanguageList)):
 355             if IndexI == 0:
 356                 continue
 357             else:
 358                 Language = LanguageList[IndexI].split()[0]
 359                 Value = LanguageList[IndexI][LanguageList[IndexI].find(u'\"') + len(u'\"') : LanguageList[IndexI].rfind(u'\"')] #.replace(u'\r\n', u'')
 360                 Language = GetLanguageCode(Language, self.IsCompatibleMode, self.File)
 361                 self.AddStringToList(Name, Language, Value)
 362
 363     #
 364     # Get include file list and load them
 365     #
 366     def GetIncludeFile(self, Item, Dir):
 367         FileName = Item[Item.find(u'#include ') + len(u'#include ') :Item.find(u' ', len(u'#include '))][1:-1]
 368         self.LoadUniFile(FileName)
 369
 370     #
 371     # Pre-process before parse .uni file
 372     #
 373     def PreProcess(self, File):
 374         try:
 375             FileIn = UniFileClassObject.OpenUniFile(LongFilePath(File.Path))
 376         except UnicodeError as X:
 377             EdkLogger.error("build", FILE_READ_FAILURE, "File read failure: %s" % str(X), ExtraData=File.Path);
 378         except OSError:
 379             EdkLogger.error("Unicode File Parser", FILE_NOT_FOUND, ExtraData=File.Path)
 380         except:
 381             EdkLogger.error("build", FILE_OPEN_FAILURE, ExtraData=File.Path);
 382
 383         Lines = []
 384         #
 385         # Use unique identifier
 386         #
 387         for Line in FileIn:
 388             Line = Line.strip()
 389             Line = Line.replace(u'\\\\', BACK_SLASH_PLACEHOLDER)
 390             Line = StripComments(Line)
 391
 392             #
 393             # Ignore empty line
 394             #
 395             if len(Line) == 0:
 396                 continue
 397
 398
 399             Line = Line.replace(u'/langdef', u'#langdef')
 400             Line = Line.replace(u'/string', u'#string')
 401             Line = Line.replace(u'/language', u'#language')
 402             Line = Line.replace(u'/include', u'#include')
 403
 404             Line = Line.replace(UNICODE_WIDE_CHAR, WIDE_CHAR)
 405             Line = Line.replace(UNICODE_NARROW_CHAR, NARROW_CHAR)
 406             Line = Line.replace(UNICODE_NON_BREAKING_CHAR, NON_BREAKING_CHAR)
 407
 408             Line = Line.replace(u'\\r\\n', CR + LF)
 409             Line = Line.replace(u'\\n', CR + LF)
 410             Line = Line.replace(u'\\r', CR)
 411             Line = Line.replace(u'\\t', u' ')
 412             Line = Line.replace(u'\t', u' ')
 413             Line = Line.replace(u'\\"', u'"')
 414             Line = Line.replace(u"\\'", u"'")
 415             Line = Line.replace(BACK_SLASH_PLACEHOLDER, u'\\')
 416
 417             StartPos = Line.find(u'\\x')
 418             while (StartPos != -1):
 419                 EndPos = Line.find(u'\\', StartPos + 1, StartPos + 7)
 420                 if EndPos != -1 and EndPos - StartPos == 6 :
 421                     if g4HexChar.match(Line[StartPos + 2 : EndPos], re.UNICODE):
 422                         EndStr = Line[EndPos: ]
 423                         UniStr = Line[StartPos + 2: EndPos]
 424                         if EndStr.startswith(u'\\x') and len(EndStr) >= 7:
 425                             if EndStr[6] == u'\\' and g4HexChar.match(EndStr[2 : 6], re.UNICODE):
 426                                 Line = Line[0 : StartPos] + UniStr + EndStr
 427                         else:
 428                             Line = Line[0 : StartPos] + UniStr + EndStr[1:]
 429                 StartPos = Line.find(u'\\x', StartPos + 1)
 430
 431             IncList = gIncludePattern.findall(Line)
 432             if len(IncList) == 1:
 433                 for Dir in [File.Dir] + self.IncludePathList:
 434                     IncFile = PathClass(str(IncList[0]), Dir)
 435                     if os.path.isfile(IncFile.Path):
 436                         Lines.extend(self.PreProcess(IncFile))
 437                         break
 438                 else:
 439                     EdkLogger.error("Unicode File Parser", FILE_NOT_FOUND, Message="Cannot find include file", ExtraData=str(IncList[0]))
 440                 continue
 441
 442             Lines.append(Line)
 443
 444         return Lines
 445
 446     #
 447     # Load a .uni file
 448     #
 449     def LoadUniFile(self, File = None):
 450         if File is None:
 451             EdkLogger.error("Unicode File Parser", PARSER_ERROR, 'No unicode file is given')
 452         self.File = File
 453         #
 454         # Process special char in file
 455         #
 456         Lines = self.PreProcess(File)
 457
 458         #
 459         # Get Unicode Information
 460         #
 461         for IndexI in range(len(Lines)):
 462             Line = Lines[IndexI]
 463             if (IndexI + 1) < len(Lines):
 464                 SecondLine = Lines[IndexI + 1]
 465             if (IndexI + 2) < len(Lines):
 466                 ThirdLine = Lines[IndexI + 2]
 467
 468             #
 469             # Get Language def information
 470             #
 471             if Line.find(u'#langdef ') >= 0:
 472                 self.GetLangDef(File, Line)
 473                 continue
 474
 475             Name = ''
 476             Language = ''
 477             Value = ''
 478             #
 479             # Get string def information format 1 as below
 480             #
 481             #     #string MY_STRING_1
 482             #     #language eng
 483             #     My first English string line 1
 484             #     My first English string line 2
 485             #     #string MY_STRING_1
 486             #     #language spa
 487             #     Mi segunda secuencia 1
 488             #     Mi segunda secuencia 2
 489             #
 490             if Line.find(u'#string ') >= 0 and Line.find(u'#language ') < 0 and \
 491                 SecondLine.find(u'#string ') < 0 and SecondLine.find(u'#language ') >= 0 and \
 492                 ThirdLine.find(u'#string ') < 0 and ThirdLine.find(u'#language ') < 0:
 493                 Name = Line[Line.find(u'#string ') + len(u'#string ') : ].strip(' ')
 494                 Language = SecondLine[SecondLine.find(u'#language ') + len(u'#language ') : ].strip(' ')
 495                 for IndexJ in range(IndexI + 2, len(Lines)):
 496                     if Lines[IndexJ].find(u'#string ') < 0 and Lines[IndexJ].find(u'#language ') < 0:
 497                         Value = Value + Lines[IndexJ]
 498                     else:
 499                         IndexI = IndexJ
 500                         break
 501                 # Value = Value.replace(u'\r\n', u'')
 502                 Language = GetLanguageCode(Language, self.IsCompatibleMode, self.File)
 503                 # Check the string name
 504                 if not self.IsCompatibleMode and Name != '':
 505                     MatchString = gIdentifierPattern.match(Name)
 506                     if MatchString is None:
 507                         EdkLogger.error('Unicode File Parser', FORMAT_INVALID, 'The string token name %s defined in UNI file %s contains the invalid character.' % (Name, self.File))
 508                 self.AddStringToList(Name, Language, Value)
 509                 continue
 510
 511             #
 512             # Get string def information format 2 as below
 513             #
 514             #     #string MY_STRING_1     #language eng     "My first English string line 1"
 515             #                                               "My first English string line 2"
 516             #                             #language spa     "Mi segunda secuencia 1"
 517             #                                               "Mi segunda secuencia 2"
 518             #     #string MY_STRING_2     #language eng     "My first English string line 1"
 519             #                                               "My first English string line 2"
 520             #     #string MY_STRING_2     #language spa     "Mi segunda secuencia 1"
 521             #                                               "Mi segunda secuencia 2"
 522             #
 523             if Line.find(u'#string ') >= 0 and Line.find(u'#language ') >= 0:
 524                 StringItem = Line
 525                 for IndexJ in range(IndexI + 1, len(Lines)):
 526                     if Lines[IndexJ].find(u'#string ') >= 0 and Lines[IndexJ].find(u'#language ') >= 0:
 527                         IndexI = IndexJ
 528                         break
 529                     elif Lines[IndexJ].find(u'#string ') < 0 and Lines[IndexJ].find(u'#language ') >= 0:
 530                         StringItem = StringItem + Lines[IndexJ]
 531                     elif Lines[IndexJ].count(u'\"') >= 2:
 532                         StringItem = StringItem[ : StringItem.rfind(u'\"')] + Lines[IndexJ][Lines[IndexJ].find(u'\"') + len(u'\"') : ]
 533                 self.GetStringObject(StringItem)
 534                 continue
 535
 536     #
 537     # Load multiple .uni files
 538     #
 539     def LoadUniFiles(self, FileList):
 540         if len(FileList) > 0:
 541             for File in FileList:
 542                 self.LoadUniFile(File)
 543
 544     #
 545     # Add a string to list
 546     #
 547     def AddStringToList(self, Name, Language, Value, Token = None, Referenced = False, UseOtherLangDef = '', Index = -1):
 548         for LangNameItem in self.LanguageDef:
 549             if Language == LangNameItem[0]:
 550                 break
 551         else:
 552             EdkLogger.error('Unicode File Parser', FORMAT_NOT_SUPPORTED, "The language '%s' for %s is not defined in Unicode file %s." \
 553                             % (Language, Name, self.File))
 554
 555         if Language not in self.OrderedStringList:
 556             self.OrderedStringList[Language] = []
 557             self.OrderedStringDict[Language] = {}
 558
 559         IsAdded = True
 560         if Name in self.OrderedStringDict[Language]:
 561             IsAdded = False
 562             if Value is not None:
 563                 ItemIndexInList = self.OrderedStringDict[Language][Name]
 564                 Item = self.OrderedStringList[Language][ItemIndexInList]
 565                 Item.UpdateValue(Value)
 566                 Item.UseOtherLangDef = ''
 567
 568         if IsAdded:
 569             Token = len(self.OrderedStringList[Language])
 570             if Index == -1:
 571                 self.OrderedStringList[Language].append(StringDefClassObject(Name, Value, Referenced, Token, UseOtherLangDef))
 572                 self.OrderedStringDict[Language][Name] = Token
 573                 for LangName in self.LanguageDef:
 574                     #
 575                     # New STRING token will be added into all language string lists.
 576                     # so that the unique STRING identifier is reserved for all languages in the package list.
 577                     #
 578                     if LangName[0] != Language:
 579                         if UseOtherLangDef != '':
 580                             OtherLangDef = UseOtherLangDef
 581                         else:
 582                             OtherLangDef = Language
 583                         self.OrderedStringList[LangName[0]].append(StringDefClassObject(Name, '', Referenced, Token, OtherLangDef))
 584                         self.OrderedStringDict[LangName[0]][Name] = len(self.OrderedStringList[LangName[0]]) - 1
 585             else:
 586                 self.OrderedStringList[Language].insert(Index, StringDefClassObject(Name, Value, Referenced, Token, UseOtherLangDef))
 587                 self.OrderedStringDict[Language][Name] = Index
 588
 589     #
 590     # Set the string as referenced
 591     #
 592     def SetStringReferenced(self, Name):
 593         #
 594         # String stoken are added in the same order in all language string lists.
 595         # So, only update the status of string stoken in first language string list.
 596         #
 597         Lang = self.LanguageDef[0][0]
 598         if Name in self.OrderedStringDict[Lang]:
 599             ItemIndexInList = self.OrderedStringDict[Lang][Name]
 600             Item = self.OrderedStringList[Lang][ItemIndexInList]
 601             Item.Referenced = True
 602
 603     #
 604     # Search the string in language definition by Name
 605     #
 606     def FindStringValue(self, Name, Lang):
 607         if Name in self.OrderedStringDict[Lang]:
 608             ItemIndexInList = self.OrderedStringDict[Lang][Name]
 609             return self.OrderedStringList[Lang][ItemIndexInList]
 610
 611         return None
 612
 613     #
 614     # Search the string in language definition by Token
 615     #
 616     def FindByToken(self, Token, Lang):
 617         for Item in self.OrderedStringList[Lang]:
 618             if Item.Token == Token:
 619                 return Item
 620
 621         return None
 622
 623     #
 624     # Re-order strings and re-generate tokens
 625     #
 626     def ReToken(self):
 627         #
 628         # Retoken all language strings according to the status of string stoken in the first language string.
 629         #
 630         FirstLangName = self.LanguageDef[0][0]
 631
 632         # Convert the OrderedStringList to be OrderedStringListByToken in order to faciliate future search by token
 633         for LangNameItem in self.LanguageDef:
 634             self.OrderedStringListByToken[LangNameItem[0]] = {}
 635
 636         #
 637         # Use small token for all referred string stoken.
 638         #
 639         RefToken = 0
 640         for Index in range (0, len (self.OrderedStringList[FirstLangName])):
 641             FirstLangItem = self.OrderedStringList[FirstLangName][Index]
 642             if FirstLangItem.Referenced == True:
 643                 for LangNameItem in self.LanguageDef:
 644                     LangName = LangNameItem[0]
 645                     OtherLangItem = self.OrderedStringList[LangName][Index]
 646                     OtherLangItem.Referenced = True
 647                     OtherLangItem.Token = RefToken
 648                     self.OrderedStringListByToken[LangName][OtherLangItem.Token] = OtherLangItem
 649                 RefToken = RefToken + 1
 650
 651         #
 652         # Use big token for all unreferred string stoken.
 653         #
 654         UnRefToken = 0
 655         for Index in range (0, len (self.OrderedStringList[FirstLangName])):
 656             FirstLangItem = self.OrderedStringList[FirstLangName][Index]
 657             if FirstLangItem.Referenced == False:
 658                 for LangNameItem in self.LanguageDef:
 659                     LangName = LangNameItem[0]
 660                     OtherLangItem = self.OrderedStringList[LangName][Index]
 661                     OtherLangItem.Token = RefToken + UnRefToken
 662                     self.OrderedStringListByToken[LangName][OtherLangItem.Token] = OtherLangItem
 663                 UnRefToken = UnRefToken + 1
 664
 665     #
 666     # Show the instance itself
 667     #
 668     def ShowMe(self):
 669         print(self.LanguageDef)
 670         #print self.OrderedStringList
 671         for Item in self.OrderedStringList:
 672             print(Item)
 673             for Member in self.OrderedStringList[Item]:
 674                 print(str(Member))
 675
 676 # This acts like the main() function for the script, unless it is 'import'ed into another
 677 # script.
 678 if __name__ == '__main__':
 679     EdkLogger.Initialize()
 680     EdkLogger.SetLevel(EdkLogger.DEBUG_0)
 681     a = UniFileClassObject([PathClass("C:\\Edk\\Strings.uni"), PathClass("C:\\Edk\\Strings2.uni")])
 682     a.ReToken()
 683     a.ShowMe()