BaseTools/Source/Python/AutoGen/UniClassObject.py

   1 ## @file
   2 # This file is used to collect all defined strings in multiple uni files
   3 #
   4 #
   5 # Copyright (c) 2014 Hewlett-Packard Development Company, L.P.<BR>
   6 #
   7 # Copyright (c) 2007 - 2015, Intel Corporation. All rights reserved.<BR>
   8 # This program and the accompanying materials
   9 # are licensed and made available under the terms and conditions of the BSD License
  10 # which accompanies this distribution.  The full text of the license may be found at
  11 # http://opensource.org/licenses/bsd-license.php
  12 #
  13 # THE PROGRAM IS DISTRIBUTED UNDER THE BSD LICENSE ON AN "AS IS" BASIS,
  14 # WITHOUT WARRANTIES OR REPRESENTATIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED.
  15
  16 ##
  17 # Import Modules
  18 #
  19 import Common.LongFilePathOs as os, codecs, re
  20 import distutils.util
  21 import Common.EdkLogger as EdkLogger
  22 import StringIO
  23 from Common.BuildToolError import *
  24 from Common.String import GetLineNo
  25 from Common.Misc import PathClass
  26 from Common.LongFilePathSupport import LongFilePath
  27 ##
  28 # Static definitions
  29 #
  30 UNICODE_WIDE_CHAR = u'\\wide'
  31 UNICODE_NARROW_CHAR = u'\\narrow'
  32 UNICODE_NON_BREAKING_CHAR = u'\\nbr'
  33 UNICODE_UNICODE_CR = '\r'
  34 UNICODE_UNICODE_LF = '\n'
  35
  36 NARROW_CHAR = u'\uFFF0'
  37 WIDE_CHAR = u'\uFFF1'
  38 NON_BREAKING_CHAR = u'\uFFF2'
  39 CR = u'\u000D'
  40 LF = u'\u000A'
  41 NULL = u'\u0000'
  42 TAB = u'\t'
  43 BACK_SLASH_PLACEHOLDER = u'\u0006'
  44
  45 gIncludePattern = re.compile("^#include +[\"<]+([^\"< >]+)[>\"]+$", re.MULTILINE | re.UNICODE)
  46
  47 ## Convert a python unicode string to a normal string
  48 #
  49 # Convert a python unicode string to a normal string
  50 # UniToStr(u'I am a string') is 'I am a string'
  51 #
  52 # @param Uni:  The python unicode string
  53 #
  54 # @retval:     The formatted normal string
  55 #
  56 def UniToStr(Uni):
  57     return repr(Uni)[2:-1]
  58
  59 ## Convert a unicode string to a Hex list
  60 #
  61 # Convert a unicode string to a Hex list
  62 # UniToHexList('ABC') is ['0x41', '0x00', '0x42', '0x00', '0x43', '0x00']
  63 #
  64 # @param Uni:    The python unicode string
  65 #
  66 # @retval List:  The formatted hex list
  67 #
  68 def UniToHexList(Uni):
  69     List = []
  70     for Item in Uni:
  71         Temp = '%04X' % ord(Item)
  72         List.append('0x' + Temp[2:4])
  73         List.append('0x' + Temp[0:2])
  74     return List
  75
  76 LangConvTable = {'eng':'en', 'fra':'fr', \
  77                  'aar':'aa', 'abk':'ab', 'ave':'ae', 'afr':'af', 'aka':'ak', 'amh':'am', \
  78                  'arg':'an', 'ara':'ar', 'asm':'as', 'ava':'av', 'aym':'ay', 'aze':'az', \
  79                  'bak':'ba', 'bel':'be', 'bul':'bg', 'bih':'bh', 'bis':'bi', 'bam':'bm', \
  80                  'ben':'bn', 'bod':'bo', 'bre':'br', 'bos':'bs', 'cat':'ca', 'che':'ce', \
  81                  'cha':'ch', 'cos':'co', 'cre':'cr', 'ces':'cs', 'chu':'cu', 'chv':'cv', \
  82                  'cym':'cy', 'dan':'da', 'deu':'de', 'div':'dv', 'dzo':'dz', 'ewe':'ee', \
  83                  'ell':'el', 'epo':'eo', 'spa':'es', 'est':'et', 'eus':'eu', 'fas':'fa', \
  84                  'ful':'ff', 'fin':'fi', 'fij':'fj', 'fao':'fo', 'fry':'fy', 'gle':'ga', \
  85                  'gla':'gd', 'glg':'gl', 'grn':'gn', 'guj':'gu', 'glv':'gv', 'hau':'ha', \
  86                  'heb':'he', 'hin':'hi', 'hmo':'ho', 'hrv':'hr', 'hat':'ht', 'hun':'hu', \
  87                  'hye':'hy', 'her':'hz', 'ina':'ia', 'ind':'id', 'ile':'ie', 'ibo':'ig', \
  88                  'iii':'ii', 'ipk':'ik', 'ido':'io', 'isl':'is', 'ita':'it', 'iku':'iu', \
  89                  'jpn':'ja', 'jav':'jv', 'kat':'ka', 'kon':'kg', 'kik':'ki', 'kua':'kj', \
  90                  'kaz':'kk', 'kal':'kl', 'khm':'km', 'kan':'kn', 'kor':'ko', 'kau':'kr', \
  91                  'kas':'ks', 'kur':'ku', 'kom':'kv', 'cor':'kw', 'kir':'ky', 'lat':'la', \
  92                  'ltz':'lb', 'lug':'lg', 'lim':'li', 'lin':'ln', 'lao':'lo', 'lit':'lt', \
  93                  'lub':'lu', 'lav':'lv', 'mlg':'mg', 'mah':'mh', 'mri':'mi', 'mkd':'mk', \
  94                  'mal':'ml', 'mon':'mn', 'mar':'mr', 'msa':'ms', 'mlt':'mt', 'mya':'my', \
  95                  'nau':'na', 'nob':'nb', 'nde':'nd', 'nep':'ne', 'ndo':'ng', 'nld':'nl', \
  96                  'nno':'nn', 'nor':'no', 'nbl':'nr', 'nav':'nv', 'nya':'ny', 'oci':'oc', \
  97                  'oji':'oj', 'orm':'om', 'ori':'or', 'oss':'os', 'pan':'pa', 'pli':'pi', \
  98                  'pol':'pl', 'pus':'ps', 'por':'pt', 'que':'qu', 'roh':'rm', 'run':'rn', \
  99                  'ron':'ro', 'rus':'ru', 'kin':'rw', 'san':'sa', 'srd':'sc', 'snd':'sd', \
 100                  'sme':'se', 'sag':'sg', 'sin':'si', 'slk':'sk', 'slv':'sl', 'smo':'sm', \
 101                  'sna':'sn', 'som':'so', 'sqi':'sq', 'srp':'sr', 'ssw':'ss', 'sot':'st', \
 102                  'sun':'su', 'swe':'sv', 'swa':'sw', 'tam':'ta', 'tel':'te', 'tgk':'tg', \
 103                  'tha':'th', 'tir':'ti', 'tuk':'tk', 'tgl':'tl', 'tsn':'tn', 'ton':'to', \
 104                  'tur':'tr', 'tso':'ts', 'tat':'tt', 'twi':'tw', 'tah':'ty', 'uig':'ug', \
 105                  'ukr':'uk', 'urd':'ur', 'uzb':'uz', 'ven':'ve', 'vie':'vi', 'vol':'vo', \
 106                  'wln':'wa', 'wol':'wo', 'xho':'xh', 'yid':'yi', 'yor':'yo', 'zha':'za', \
 107                  'zho':'zh', 'zul':'zu'}
 108
 109 ## GetLanguageCode
 110 #
 111 # Check the language code read from .UNI file and convert ISO 639-2 codes to RFC 4646 codes if appropriate
 112 # ISO 639-2 language codes supported in compatiblity mode
 113 # RFC 4646 language codes supported in native mode
 114 #
 115 # @param LangName:   Language codes read from .UNI file
 116 #
 117 # @retval LangName:  Valid lanugage code in RFC 4646 format or None
 118 #
 119 def GetLanguageCode(LangName, IsCompatibleMode, File):
 120     global LangConvTable
 121
 122     length = len(LangName)
 123     if IsCompatibleMode:
 124         if length == 3 and LangName.isalpha():
 125             TempLangName = LangConvTable.get(LangName.lower())
 126             if TempLangName != None:
 127                 return TempLangName
 128             return LangName
 129         else:
 130             EdkLogger.error("Unicode File Parser", FORMAT_INVALID, "Invalid ISO 639-2 language code : %s" % LangName, File)
 131
 132     if (LangName[0] == 'X' or LangName[0] == 'x') and LangName[1] == '-':
 133         return LangName
 134     if length == 2:
 135         if LangName.isalpha():
 136             return LangName
 137     elif length == 3:
 138         if LangName.isalpha() and LangConvTable.get(LangName.lower()) == None:
 139             return LangName
 140     elif length == 5:
 141         if LangName[0:2].isalpha() and LangName[2] == '-':
 142             return LangName
 143     elif length >= 6:
 144         if LangName[0:2].isalpha() and LangName[2] == '-':
 145             return LangName
 146         if LangName[0:3].isalpha() and LangConvTable.get(LangName.lower()) == None and LangName[3] == '-':
 147             return LangName
 148
 149     EdkLogger.error("Unicode File Parser", FORMAT_INVALID, "Invalid RFC 4646 language code : %s" % LangName, File)
 150
 151 ## Ucs2Codec
 152 #
 153 # This is only a partial codec implementation. It only supports
 154 # encoding, and is primarily used to check that all the characters are
 155 # valid for UCS-2.
 156 #
 157 class Ucs2Codec(codecs.Codec):
 158     def __init__(self):
 159         self.__utf16 = codecs.lookup('utf-16')
 160
 161     def encode(self, input, errors='strict'):
 162         for Char in input:
 163             CodePoint = ord(Char)
 164             if CodePoint >= 0xd800 and CodePoint <= 0xdfff:
 165                 raise ValueError("Code Point is in range reserved for " +
 166                                  "UTF-16 surrogate pairs")
 167             elif CodePoint > 0xffff:
 168                 raise ValueError("Code Point too large to encode in UCS-2")
 169         return self.__utf16.encode(input)
 170
 171 TheUcs2Codec = Ucs2Codec()
 172 def Ucs2Search(name):
 173     if name == 'ucs-2':
 174         return codecs.CodecInfo(
 175             name=name,
 176             encode=TheUcs2Codec.encode,
 177             decode=TheUcs2Codec.decode)
 178     else:
 179         return None
 180 codecs.register(Ucs2Search)
 181
 182 ## StringDefClassObject
 183 #
 184 # A structure for language definition
 185 #
 186 class StringDefClassObject(object):
 187     def __init__(self, Name = None, Value = None, Referenced = False, Token = None, UseOtherLangDef = ''):
 188         self.StringName = ''
 189         self.StringNameByteList = []
 190         self.StringValue = ''
 191         self.StringValueByteList = ''
 192         self.Token = 0
 193         self.Referenced = Referenced
 194         self.UseOtherLangDef = UseOtherLangDef
 195         self.Length = 0
 196
 197         if Name != None:
 198             self.StringName = Name
 199             self.StringNameByteList = UniToHexList(Name)
 200         if Value != None:
 201             self.StringValue = Value + u'\x00'        # Add a NULL at string tail
 202             self.StringValueByteList = UniToHexList(self.StringValue)
 203             self.Length = len(self.StringValueByteList)
 204         if Token != None:
 205             self.Token = Token
 206
 207     def __str__(self):
 208         return repr(self.StringName) + ' ' + \
 209                repr(self.Token) + ' ' + \
 210                repr(self.Referenced) + ' ' + \
 211                repr(self.StringValue) + ' ' + \
 212                repr(self.UseOtherLangDef)
 213
 214     def UpdateValue(self, Value = None):
 215         if Value != None:
 216             self.StringValue = Value + u'\x00'        # Add a NULL at string tail
 217             self.StringValueByteList = UniToHexList(self.StringValue)
 218             self.Length = len(self.StringValueByteList)
 219
 220 ## UniFileClassObject
 221 #
 222 # A structure for .uni file definition
 223 #
 224 class UniFileClassObject(object):
 225     def __init__(self, FileList = [], IsCompatibleMode = False, IncludePathList = []):
 226         self.FileList = FileList
 227         self.Token = 2
 228         self.LanguageDef = []                   #[ [u'LanguageIdentifier', u'PrintableName'], ... ]
 229         self.OrderedStringList = {}             #{ u'LanguageIdentifier' : [StringDefClassObject]  }
 230         self.OrderedStringDict = {}             #{ u'LanguageIdentifier' : {StringName:(IndexInList)}  }
 231         self.OrderedStringListByToken = {}      #{ u'LanguageIdentifier' : {Token: StringDefClassObject} }
 232         self.IsCompatibleMode = IsCompatibleMode
 233         self.IncludePathList = IncludePathList
 234         if len(self.FileList) > 0:
 235             self.LoadUniFiles(FileList)
 236
 237     #
 238     # Get Language definition
 239     #
 240     def GetLangDef(self, File, Line):
 241         Lang = distutils.util.split_quoted((Line.split(u"//")[0]))
 242         if len(Lang) != 3:
 243             try:
 244                 FileIn = self.OpenUniFile(LongFilePath(File.Path))
 245             except UnicodeError, X:
 246                 EdkLogger.error("build", FILE_READ_FAILURE, "File read failure: %s" % str(X), ExtraData=File);
 247             except:
 248                 EdkLogger.error("build", FILE_OPEN_FAILURE, ExtraData=File);
 249             LineNo = GetLineNo(FileIn, Line, False)
 250             EdkLogger.error("Unicode File Parser", PARSER_ERROR, "Wrong language definition",
 251                             ExtraData="""%s\n\t*Correct format is like '#langdef en-US "English"'""" % Line, File = File, Line = LineNo)
 252         else:
 253             LangName = GetLanguageCode(Lang[1], self.IsCompatibleMode, self.File)
 254             LangPrintName = Lang[2]
 255
 256         IsLangInDef = False
 257         for Item in self.LanguageDef:
 258             if Item[0] == LangName:
 259                 IsLangInDef = True
 260                 break;
 261
 262         if not IsLangInDef:
 263             self.LanguageDef.append([LangName, LangPrintName])
 264
 265         #
 266         # Add language string
 267         #
 268         self.AddStringToList(u'$LANGUAGE_NAME', LangName, LangName, 0, True, Index=0)
 269         self.AddStringToList(u'$PRINTABLE_LANGUAGE_NAME', LangName, LangPrintName, 1, True, Index=1)
 270
 271         if not IsLangInDef:
 272             #
 273             # The found STRING tokens will be added into new language string list
 274             # so that the unique STRING identifier is reserved for all languages in the package list.
 275             #
 276             FirstLangName = self.LanguageDef[0][0]
 277             if LangName != FirstLangName:
 278                 for Index in range (2, len (self.OrderedStringList[FirstLangName])):
 279                     Item = self.OrderedStringList[FirstLangName][Index]
 280                     if Item.UseOtherLangDef != '':
 281                         OtherLang = Item.UseOtherLangDef
 282                     else:
 283                         OtherLang = FirstLangName
 284                     self.OrderedStringList[LangName].append (StringDefClassObject(Item.StringName, '', Item.Referenced, Item.Token, OtherLang))
 285                     self.OrderedStringDict[LangName][Item.StringName] = len(self.OrderedStringList[LangName]) - 1
 286         return True
 287
 288     def OpenUniFile(self, FileName):
 289         #
 290         # Read file
 291         #
 292         try:
 293             UniFile = open(FileName, mode='rb')
 294             FileIn = UniFile.read()
 295             UniFile.close()
 296         except:
 297             EdkLogger.Error("build", FILE_OPEN_FAILURE, ExtraData=File)
 298
 299         #
 300         # Detect Byte Order Mark at beginning of file.  Default to UTF-8
 301         #
 302         Encoding = 'utf-8'
 303         if (FileIn.startswith(codecs.BOM_UTF16_BE) or
 304             FileIn.startswith(codecs.BOM_UTF16_LE)):
 305             Encoding = 'utf-16'
 306
 307         self.VerifyUcs2Data(FileIn, FileName, Encoding)
 308
 309         UniFile = StringIO.StringIO(FileIn)
 310         Info = codecs.lookup(Encoding)
 311         (Reader, Writer) = (Info.streamreader, Info.streamwriter)
 312         return codecs.StreamReaderWriter(UniFile, Reader, Writer)
 313
 314     def VerifyUcs2Data(self, FileIn, FileName, Encoding):
 315         Ucs2Info = codecs.lookup('ucs-2')
 316         #
 317         # Convert to unicode
 318         #
 319         try:
 320             FileDecoded = codecs.decode(FileIn, Encoding)
 321             Ucs2Info.encode(FileDecoded)
 322         except:
 323             UniFile = StringIO.StringIO(FileIn)
 324             Info = codecs.lookup(Encoding)
 325             (Reader, Writer) = (Info.streamreader, Info.streamwriter)
 326             File = codecs.StreamReaderWriter(UniFile, Reader, Writer)
 327             LineNumber = 0
 328             ErrMsg = lambda Encoding, LineNumber: \
 329                      '%s contains invalid %s characters on line %d.' % \
 330                      (FileName, Encoding, LineNumber)
 331             while True:
 332                 LineNumber = LineNumber + 1
 333                 try:
 334                     Line = File.readline()
 335                     if Line == '':
 336                         EdkLogger.error('Unicode File Parser', PARSER_ERROR,
 337                                         ErrMsg(Encoding, LineNumber))
 338                     Ucs2Info.encode(Line)
 339                 except:
 340                     EdkLogger.error('Unicode File Parser', PARSER_ERROR,
 341                                     ErrMsg('UCS-2', LineNumber))
 342
 343     #
 344     # Get String name and value
 345     #
 346     def GetStringObject(self, Item):
 347         Language = ''
 348         Value = ''
 349
 350         Name = Item.split()[1]
 351         # Check the string name is the upper character
 352         if Name != '':
 353             MatchString = re.match('[A-Z0-9_]+', Name, re.UNICODE)
 354             if MatchString == None or MatchString.end(0) != len(Name):
 355                 EdkLogger.error('Unicode File Parser', FORMAT_INVALID, 'The string token name %s defined in UNI file %s contains the invalid lower case character.' %(Name, self.File))
 356         LanguageList = Item.split(u'#language ')
 357         for IndexI in range(len(LanguageList)):
 358             if IndexI == 0:
 359                 continue
 360             else:
 361                 Language = LanguageList[IndexI].split()[0]
 362                 Value = LanguageList[IndexI][LanguageList[IndexI].find(u'\"') + len(u'\"') : LanguageList[IndexI].rfind(u'\"')] #.replace(u'\r\n', u'')
 363                 Language = GetLanguageCode(Language, self.IsCompatibleMode, self.File)
 364                 self.AddStringToList(Name, Language, Value)
 365
 366     #
 367     # Get include file list and load them
 368     #
 369     def GetIncludeFile(self, Item, Dir):
 370         FileName = Item[Item.find(u'#include ') + len(u'#include ') :Item.find(u' ', len(u'#include '))][1:-1]
 371         self.LoadUniFile(FileName)
 372
 373     def StripComments(self, Line):
 374         Comment = u'//'
 375         CommentPos = Line.find(Comment)
 376         while CommentPos >= 0:
 377         # if there are non matched quotes before the comment header
 378         # then we are in the middle of a string
 379         # but we need to ignore the escaped quotes and backslashes.
 380             if ((Line.count(u'"', 0, CommentPos) - Line.count(u'\\"', 0, CommentPos)) & 1) == 1:
 381                 CommentPos = Line.find (Comment, CommentPos + 1)
 382             else:
 383                 return Line[:CommentPos].strip()
 384         return Line.strip()
 385
 386
 387     #
 388     # Pre-process before parse .uni file
 389     #
 390     def PreProcess(self, File):
 391         if not os.path.exists(File.Path) or not os.path.isfile(File.Path):
 392             EdkLogger.error("Unicode File Parser", FILE_NOT_FOUND, ExtraData=File.Path)
 393
 394         try:
 395             FileIn = self.OpenUniFile(LongFilePath(File.Path))
 396         except UnicodeError, X:
 397             EdkLogger.error("build", FILE_READ_FAILURE, "File read failure: %s" % str(X), ExtraData=File.Path);
 398         except:
 399             EdkLogger.error("build", FILE_OPEN_FAILURE, ExtraData=File.Path);
 400
 401         Lines = []
 402         #
 403         # Use unique identifier
 404         #
 405         for Line in FileIn:
 406             Line = Line.strip()
 407             Line = Line.replace(u'\\\\', BACK_SLASH_PLACEHOLDER)
 408             Line = self.StripComments(Line)
 409
 410             #
 411             # Ignore empty line
 412             #
 413             if len(Line) == 0:
 414                 continue
 415
 416
 417             Line = Line.replace(u'/langdef', u'#langdef')
 418             Line = Line.replace(u'/string', u'#string')
 419             Line = Line.replace(u'/language', u'#language')
 420             Line = Line.replace(u'/include', u'#include')
 421
 422             Line = Line.replace(UNICODE_WIDE_CHAR, WIDE_CHAR)
 423             Line = Line.replace(UNICODE_NARROW_CHAR, NARROW_CHAR)
 424             Line = Line.replace(UNICODE_NON_BREAKING_CHAR, NON_BREAKING_CHAR)
 425
 426             Line = Line.replace(u'\\r\\n', CR + LF)
 427             Line = Line.replace(u'\\n', CR + LF)
 428             Line = Line.replace(u'\\r', CR)
 429             Line = Line.replace(u'\\t', u' ')
 430             Line = Line.replace(u'\t', u' ')
 431             Line = Line.replace(u'\\"', u'"')
 432             Line = Line.replace(u"\\'", u"'")
 433             Line = Line.replace(BACK_SLASH_PLACEHOLDER, u'\\')
 434
 435 #           if Line.find(u'\\x'):
 436 #               hex = Line[Line.find(u'\\x') + 2 : Line.find(u'\\x') + 6]
 437 #               hex = "u'\\u" + hex + "'"
 438
 439             IncList = gIncludePattern.findall(Line)
 440             if len(IncList) == 1:
 441                 for Dir in [File.Dir] + self.IncludePathList:
 442                     IncFile = PathClass(str(IncList[0]), Dir)
 443                     if os.path.isfile(IncFile.Path):
 444                         Lines.extend(self.PreProcess(IncFile))
 445                         break
 446                 else:
 447                     EdkLogger.error("Unicode File Parser", FILE_NOT_FOUND, Message="Cannot find include file", ExtraData=str(IncList[0]))
 448                 continue
 449
 450             Lines.append(Line)
 451
 452         return Lines
 453
 454     #
 455     # Load a .uni file
 456     #
 457     def LoadUniFile(self, File = None):
 458         if File == None:
 459             EdkLogger.error("Unicode File Parser", PARSER_ERROR, 'No unicode file is given')
 460         self.File = File
 461         #
 462         # Process special char in file
 463         #
 464         Lines = self.PreProcess(File)
 465
 466         #
 467         # Get Unicode Information
 468         #
 469         for IndexI in range(len(Lines)):
 470             Line = Lines[IndexI]
 471             if (IndexI + 1) < len(Lines):
 472                 SecondLine = Lines[IndexI + 1]
 473             if (IndexI + 2) < len(Lines):
 474                 ThirdLine = Lines[IndexI + 2]
 475
 476             #
 477             # Get Language def information
 478             #
 479             if Line.find(u'#langdef ') >= 0:
 480                 self.GetLangDef(File, Line)
 481                 continue
 482
 483             Name = ''
 484             Language = ''
 485             Value = ''
 486             #
 487             # Get string def information format 1 as below
 488             #
 489             #     #string MY_STRING_1
 490             #     #language eng
 491             #     My first English string line 1
 492             #     My first English string line 2
 493             #     #string MY_STRING_1
 494             #     #language spa
 495             #     Mi segunda secuencia 1
 496             #     Mi segunda secuencia 2
 497             #
 498             if Line.find(u'#string ') >= 0 and Line.find(u'#language ') < 0 and \
 499                 SecondLine.find(u'#string ') < 0 and SecondLine.find(u'#language ') >= 0 and \
 500                 ThirdLine.find(u'#string ') < 0 and ThirdLine.find(u'#language ') < 0:
 501                 Name = Line[Line.find(u'#string ') + len(u'#string ') : ].strip(' ')
 502                 Language = SecondLine[SecondLine.find(u'#language ') + len(u'#language ') : ].strip(' ')
 503                 for IndexJ in range(IndexI + 2, len(Lines)):
 504                     if Lines[IndexJ].find(u'#string ') < 0 and Lines[IndexJ].find(u'#language ') < 0:
 505                         Value = Value + Lines[IndexJ]
 506                     else:
 507                         IndexI = IndexJ
 508                         break
 509                 # Value = Value.replace(u'\r\n', u'')
 510                 Language = GetLanguageCode(Language, self.IsCompatibleMode, self.File)
 511                 # Check the string name is the upper character
 512                 if not self.IsCompatibleMode and Name != '':
 513                     MatchString = re.match('[A-Z0-9_]+', Name, re.UNICODE)
 514                     if MatchString == None or MatchString.end(0) != len(Name):
 515                         EdkLogger.error('Unicode File Parser', FORMAT_INVALID, 'The string token name %s defined in UNI file %s contains the invalid lower case character.' %(Name, self.File))
 516                 self.AddStringToList(Name, Language, Value)
 517                 continue
 518
 519             #
 520             # Get string def information format 2 as below
 521             #
 522             #     #string MY_STRING_1     #language eng     "My first English string line 1"
 523             #                                               "My first English string line 2"
 524             #                             #language spa     "Mi segunda secuencia 1"
 525             #                                               "Mi segunda secuencia 2"
 526             #     #string MY_STRING_2     #language eng     "My first English string line 1"
 527             #                                               "My first English string line 2"
 528             #     #string MY_STRING_2     #language spa     "Mi segunda secuencia 1"
 529             #                                               "Mi segunda secuencia 2"
 530             #
 531             if Line.find(u'#string ') >= 0 and Line.find(u'#language ') >= 0:
 532                 StringItem = Line
 533                 for IndexJ in range(IndexI + 1, len(Lines)):
 534                     if Lines[IndexJ].find(u'#string ') >= 0 and Lines[IndexJ].find(u'#language ') >= 0:
 535                         IndexI = IndexJ
 536                         break
 537                     elif Lines[IndexJ].find(u'#string ') < 0 and Lines[IndexJ].find(u'#language ') >= 0:
 538                         StringItem = StringItem + Lines[IndexJ]
 539                     elif Lines[IndexJ].count(u'\"') >= 2:
 540                         StringItem = StringItem[ : StringItem.rfind(u'\"')] + Lines[IndexJ][Lines[IndexJ].find(u'\"') + len(u'\"') : ]
 541                 self.GetStringObject(StringItem)
 542                 continue
 543
 544     #
 545     # Load multiple .uni files
 546     #
 547     def LoadUniFiles(self, FileList):
 548         if len(FileList) > 0:
 549             for File in FileList:
 550                 self.LoadUniFile(File)
 551
 552     #
 553     # Add a string to list
 554     #
 555     def AddStringToList(self, Name, Language, Value, Token = None, Referenced = False, UseOtherLangDef = '', Index = -1):
 556         for LangNameItem in self.LanguageDef:
 557             if Language == LangNameItem[0]:
 558                 break
 559         else:
 560             EdkLogger.error('Unicode File Parser', FORMAT_NOT_SUPPORTED, "The language '%s' for %s is not defined in Unicode file %s." \
 561                             % (Language, Name, self.File))
 562
 563         if Language not in self.OrderedStringList:
 564             self.OrderedStringList[Language] = []
 565             self.OrderedStringDict[Language] = {}
 566
 567         IsAdded = True
 568         if Name in self.OrderedStringDict[Language]:
 569             IsAdded = False
 570             if Value != None:
 571                 ItemIndexInList = self.OrderedStringDict[Language][Name]
 572                 Item = self.OrderedStringList[Language][ItemIndexInList]
 573                 Item.UpdateValue(Value)
 574                 Item.UseOtherLangDef = ''
 575
 576         if IsAdded:
 577             Token = len(self.OrderedStringList[Language])
 578             if Index == -1:
 579                 self.OrderedStringList[Language].append(StringDefClassObject(Name, Value, Referenced, Token, UseOtherLangDef))
 580                 self.OrderedStringDict[Language][Name] = Token
 581                 for LangName in self.LanguageDef:
 582                     #
 583                     # New STRING token will be added into all language string lists.
 584                     # so that the unique STRING identifier is reserved for all languages in the package list.
 585                     #
 586                     if LangName[0] != Language:
 587                         if UseOtherLangDef != '':
 588                             OtherLangDef = UseOtherLangDef
 589                         else:
 590                             OtherLangDef = Language
 591                         self.OrderedStringList[LangName[0]].append(StringDefClassObject(Name, '', Referenced, Token, OtherLangDef))
 592                         self.OrderedStringDict[LangName[0]][Name] = len(self.OrderedStringList[LangName[0]]) - 1
 593             else:
 594                 self.OrderedStringList[Language].insert(Index, StringDefClassObject(Name, Value, Referenced, Token, UseOtherLangDef))
 595                 self.OrderedStringDict[Language][Name] = Index
 596
 597     #
 598     # Set the string as referenced
 599     #
 600     def SetStringReferenced(self, Name):
 601         #
 602         # String stoken are added in the same order in all language string lists.
 603         # So, only update the status of string stoken in first language string list.
 604         #
 605         Lang = self.LanguageDef[0][0]
 606         if Name in self.OrderedStringDict[Lang]:
 607             ItemIndexInList = self.OrderedStringDict[Lang][Name]
 608             Item = self.OrderedStringList[Lang][ItemIndexInList]
 609             Item.Referenced = True
 610
 611     #
 612     # Search the string in language definition by Name
 613     #
 614     def FindStringValue(self, Name, Lang):
 615         if Name in self.OrderedStringDict[Lang]:
 616             ItemIndexInList = self.OrderedStringDict[Lang][Name]
 617             return self.OrderedStringList[Lang][ItemIndexInList]
 618
 619         return None
 620
 621     #
 622     # Search the string in language definition by Token
 623     #
 624     def FindByToken(self, Token, Lang):
 625         for Item in self.OrderedStringList[Lang]:
 626             if Item.Token == Token:
 627                 return Item
 628
 629         return None
 630
 631     #
 632     # Re-order strings and re-generate tokens
 633     #
 634     def ReToken(self):
 635         #
 636         # Retoken all language strings according to the status of string stoken in the first language string.
 637         #
 638         FirstLangName = self.LanguageDef[0][0]
 639
 640         # Convert the OrderedStringList to be OrderedStringListByToken in order to faciliate future search by token
 641         for LangNameItem in self.LanguageDef:
 642             self.OrderedStringListByToken[LangNameItem[0]] = {}
 643
 644         #
 645         # Use small token for all referred string stoken.
 646         #
 647         RefToken = 0
 648         for Index in range (0, len (self.OrderedStringList[FirstLangName])):
 649             FirstLangItem = self.OrderedStringList[FirstLangName][Index]
 650             if FirstLangItem.Referenced == True:
 651                 for LangNameItem in self.LanguageDef:
 652                     LangName = LangNameItem[0]
 653                     OtherLangItem = self.OrderedStringList[LangName][Index]
 654                     OtherLangItem.Referenced = True
 655                     OtherLangItem.Token = RefToken
 656                     self.OrderedStringListByToken[LangName][OtherLangItem.Token] = OtherLangItem
 657                 RefToken = RefToken + 1
 658
 659         #
 660         # Use big token for all unreferred string stoken.
 661         #
 662         UnRefToken = 0
 663         for Index in range (0, len (self.OrderedStringList[FirstLangName])):
 664             FirstLangItem = self.OrderedStringList[FirstLangName][Index]
 665             if FirstLangItem.Referenced == False:
 666                 for LangNameItem in self.LanguageDef:
 667                     LangName = LangNameItem[0]
 668                     OtherLangItem = self.OrderedStringList[LangName][Index]
 669                     OtherLangItem.Token = RefToken + UnRefToken
 670                     self.OrderedStringListByToken[LangName][OtherLangItem.Token] = OtherLangItem
 671                 UnRefToken = UnRefToken + 1
 672
 673     #
 674     # Show the instance itself
 675     #
 676     def ShowMe(self):
 677         print self.LanguageDef
 678         #print self.OrderedStringList
 679         for Item in self.OrderedStringList:
 680             print Item
 681             for Member in self.OrderedStringList[Item]:
 682                 print str(Member)
 683
 684 # This acts like the main() function for the script, unless it is 'import'ed into another
 685 # script.
 686 if __name__ == '__main__':
 687     EdkLogger.Initialize()
 688     EdkLogger.SetLevel(EdkLogger.DEBUG_0)
 689     a = UniFileClassObject([PathClass("C:\\Edk\\Strings.uni"), PathClass("C:\\Edk\\Strings2.uni")])
 690     a.ReToken()
 691     a.ShowMe()