[mirror_edk2.git] / BaseTools / Source / Python / AutoGen / UniClassObject.py

## @file\r
# This file is used to collect all defined strings in multiple uni files\r
#\r
#\r
# Copyright (c) 2014 Hewlett-Packard Development Company, L.P.<BR>\r
#\r
# Copyright (c) 2007 - 2015, Intel Corporation. All rights reserved.<BR>\r
# This program and the accompanying materials\r
# are licensed and made available under the terms and conditions of the BSD License\r
# which accompanies this distribution.  The full text of the license may be found at\r
# http://opensource.org/licenses/bsd-license.php\r
#\r
# THE PROGRAM IS DISTRIBUTED UNDER THE BSD LICENSE ON AN "AS IS" BASIS,\r
# WITHOUT WARRANTIES OR REPRESENTATIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED.\r
\r
##\r
# Import Modules\r
#\r
import Common.LongFilePathOs as os, codecs, re\r
import distutils.util\r
import Common.EdkLogger as EdkLogger\r
import StringIO\r
from Common.BuildToolError import *\r
from Common.String import GetLineNo\r
from Common.Misc import PathClass\r
from Common.LongFilePathSupport import LongFilePath\r
##\r
# Static definitions\r
#\r
UNICODE_WIDE_CHAR = u'\\wide'\r
UNICODE_NARROW_CHAR = u'\\narrow'\r
UNICODE_NON_BREAKING_CHAR = u'\\nbr'\r
UNICODE_UNICODE_CR = '\r'\r
UNICODE_UNICODE_LF = '\n'\r
\r
NARROW_CHAR = u'\uFFF0'\r
WIDE_CHAR = u'\uFFF1'\r
NON_BREAKING_CHAR = u'\uFFF2'\r
CR = u'\u000D'\r
LF = u'\u000A'\r
NULL = u'\u0000'\r
TAB = u'\t'\r
BACK_SLASH_PLACEHOLDER = u'\u0006'\r
\r
gIncludePattern = re.compile("^#include +[\"<]+([^\"< >]+)[>\"]+$", re.MULTILINE | re.UNICODE)\r
\r
## Convert a python unicode string to a normal string\r
#\r
# Convert a python unicode string to a normal string\r
# UniToStr(u'I am a string') is 'I am a string'\r
#\r
# @param Uni:  The python unicode string\r
#\r
# @retval:     The formatted normal string\r
#\r
def UniToStr(Uni):\r
    return repr(Uni)[2:-1]\r
\r
## Convert a unicode string to a Hex list\r
#\r
# Convert a unicode string to a Hex list\r
# UniToHexList('ABC') is ['0x41', '0x00', '0x42', '0x00', '0x43', '0x00']\r
#\r
# @param Uni:    The python unicode string\r
#\r
# @retval List:  The formatted hex list\r
#\r
def UniToHexList(Uni):\r
    List = []\r
    for Item in Uni:\r
        Temp = '%04X' % ord(Item)\r
        List.append('0x' + Temp[2:4])\r
        List.append('0x' + Temp[0:2])\r
    return List\r
\r
LangConvTable = {'eng':'en', 'fra':'fr', \\r
                 'aar':'aa', 'abk':'ab', 'ave':'ae', 'afr':'af', 'aka':'ak', 'amh':'am', \\r
                 'arg':'an', 'ara':'ar', 'asm':'as', 'ava':'av', 'aym':'ay', 'aze':'az', \\r
                 'bak':'ba', 'bel':'be', 'bul':'bg', 'bih':'bh', 'bis':'bi', 'bam':'bm', \\r
                 'ben':'bn', 'bod':'bo', 'bre':'br', 'bos':'bs', 'cat':'ca', 'che':'ce', \\r
                 'cha':'ch', 'cos':'co', 'cre':'cr', 'ces':'cs', 'chu':'cu', 'chv':'cv', \\r
                 'cym':'cy', 'dan':'da', 'deu':'de', 'div':'dv', 'dzo':'dz', 'ewe':'ee', \\r
                 'ell':'el', 'epo':'eo', 'spa':'es', 'est':'et', 'eus':'eu', 'fas':'fa', \\r
                 'ful':'ff', 'fin':'fi', 'fij':'fj', 'fao':'fo', 'fry':'fy', 'gle':'ga', \\r
                 'gla':'gd', 'glg':'gl', 'grn':'gn', 'guj':'gu', 'glv':'gv', 'hau':'ha', \\r
                 'heb':'he', 'hin':'hi', 'hmo':'ho', 'hrv':'hr', 'hat':'ht', 'hun':'hu', \\r
                 'hye':'hy', 'her':'hz', 'ina':'ia', 'ind':'id', 'ile':'ie', 'ibo':'ig', \\r
                 'iii':'ii', 'ipk':'ik', 'ido':'io', 'isl':'is', 'ita':'it', 'iku':'iu', \\r
                 'jpn':'ja', 'jav':'jv', 'kat':'ka', 'kon':'kg', 'kik':'ki', 'kua':'kj', \\r
                 'kaz':'kk', 'kal':'kl', 'khm':'km', 'kan':'kn', 'kor':'ko', 'kau':'kr', \\r
                 'kas':'ks', 'kur':'ku', 'kom':'kv', 'cor':'kw', 'kir':'ky', 'lat':'la', \\r
                 'ltz':'lb', 'lug':'lg', 'lim':'li', 'lin':'ln', 'lao':'lo', 'lit':'lt', \\r
                 'lub':'lu', 'lav':'lv', 'mlg':'mg', 'mah':'mh', 'mri':'mi', 'mkd':'mk', \\r
                 'mal':'ml', 'mon':'mn', 'mar':'mr', 'msa':'ms', 'mlt':'mt', 'mya':'my', \\r
                 'nau':'na', 'nob':'nb', 'nde':'nd', 'nep':'ne', 'ndo':'ng', 'nld':'nl', \\r
                 'nno':'nn', 'nor':'no', 'nbl':'nr', 'nav':'nv', 'nya':'ny', 'oci':'oc', \\r
                 'oji':'oj', 'orm':'om', 'ori':'or', 'oss':'os', 'pan':'pa', 'pli':'pi', \\r
                 'pol':'pl', 'pus':'ps', 'por':'pt', 'que':'qu', 'roh':'rm', 'run':'rn', \\r
                 'ron':'ro', 'rus':'ru', 'kin':'rw', 'san':'sa', 'srd':'sc', 'snd':'sd', \\r
                 'sme':'se', 'sag':'sg', 'sin':'si', 'slk':'sk', 'slv':'sl', 'smo':'sm', \\r
                 'sna':'sn', 'som':'so', 'sqi':'sq', 'srp':'sr', 'ssw':'ss', 'sot':'st', \\r
                 'sun':'su', 'swe':'sv', 'swa':'sw', 'tam':'ta', 'tel':'te', 'tgk':'tg', \\r
                 'tha':'th', 'tir':'ti', 'tuk':'tk', 'tgl':'tl', 'tsn':'tn', 'ton':'to', \\r
                 'tur':'tr', 'tso':'ts', 'tat':'tt', 'twi':'tw', 'tah':'ty', 'uig':'ug', \\r
                 'ukr':'uk', 'urd':'ur', 'uzb':'uz', 'ven':'ve', 'vie':'vi', 'vol':'vo', \\r
                 'wln':'wa', 'wol':'wo', 'xho':'xh', 'yid':'yi', 'yor':'yo', 'zha':'za', \\r
                 'zho':'zh', 'zul':'zu'}\r
\r
## GetLanguageCode\r
#\r
# Check the language code read from .UNI file and convert ISO 639-2 codes to RFC 4646 codes if appropriate\r
# ISO 639-2 language codes supported in compatiblity mode\r
# RFC 4646 language codes supported in native mode\r
#\r
# @param LangName:   Language codes read from .UNI file\r
#\r
# @retval LangName:  Valid lanugage code in RFC 4646 format or None\r
#\r
def GetLanguageCode(LangName, IsCompatibleMode, File):\r
    global LangConvTable\r
\r
    length = len(LangName)\r
    if IsCompatibleMode:\r
        if length == 3 and LangName.isalpha():\r
            TempLangName = LangConvTable.get(LangName.lower())\r
            if TempLangName != None:\r
                return TempLangName\r
            return LangName\r
        else:\r
            EdkLogger.error("Unicode File Parser", FORMAT_INVALID, "Invalid ISO 639-2 language code : %s" % LangName, File)\r
\r
    if (LangName[0] == 'X' or LangName[0] == 'x') and LangName[1] == '-':\r
        return LangName\r
    if length == 2:\r
        if LangName.isalpha():\r
            return LangName\r
    elif length == 3:\r
        if LangName.isalpha() and LangConvTable.get(LangName.lower()) == None:\r
            return LangName\r
    elif length == 5:\r
        if LangName[0:2].isalpha() and LangName[2] == '-':\r
            return LangName\r
    elif length >= 6:\r
        if LangName[0:2].isalpha() and LangName[2] == '-':\r
            return LangName\r
        if LangName[0:3].isalpha() and LangConvTable.get(LangName.lower()) == None and LangName[3] == '-':\r
            return LangName\r
\r
    EdkLogger.error("Unicode File Parser", FORMAT_INVALID, "Invalid RFC 4646 language code : %s" % LangName, File)\r
\r
## Ucs2Codec\r
#\r
# This is only a partial codec implementation. It only supports\r
# encoding, and is primarily used to check that all the characters are\r
# valid for UCS-2.\r
#\r
class Ucs2Codec(codecs.Codec):\r
    def __init__(self):\r
        self.__utf16 = codecs.lookup('utf-16')\r
\r
    def encode(self, input, errors='strict'):\r
        for Char in input:\r
            CodePoint = ord(Char)\r
            if CodePoint >= 0xd800 and CodePoint <= 0xdfff:\r
                raise ValueError("Code Point is in range reserved for " +\r
                                 "UTF-16 surrogate pairs")\r
            elif CodePoint > 0xffff:\r
                raise ValueError("Code Point too large to encode in UCS-2")\r
        return self.__utf16.encode(input)\r
\r
TheUcs2Codec = Ucs2Codec()\r
def Ucs2Search(name):\r
    if name == 'ucs-2':\r
        return codecs.CodecInfo(\r
            name=name,\r
            encode=TheUcs2Codec.encode,\r
            decode=TheUcs2Codec.decode)\r
    else:\r
        return None\r
codecs.register(Ucs2Search)\r
\r
## StringDefClassObject\r
#\r
# A structure for language definition\r
#\r
class StringDefClassObject(object):\r
    def __init__(self, Name = None, Value = None, Referenced = False, Token = None, UseOtherLangDef = ''):\r
        self.StringName = ''\r
        self.StringNameByteList = []\r
        self.StringValue = ''\r
        self.StringValueByteList = ''\r
        self.Token = 0\r
        self.Referenced = Referenced\r
        self.UseOtherLangDef = UseOtherLangDef\r
        self.Length = 0\r
\r
        if Name != None:\r
            self.StringName = Name\r
            self.StringNameByteList = UniToHexList(Name)\r
        if Value != None:\r
            self.StringValue = Value + u'\x00'        # Add a NULL at string tail\r
            self.StringValueByteList = UniToHexList(self.StringValue)\r
            self.Length = len(self.StringValueByteList)\r
        if Token != None:\r
            self.Token = Token\r
\r
    def __str__(self):\r
        return repr(self.StringName) + ' ' + \\r
               repr(self.Token) + ' ' + \\r
               repr(self.Referenced) + ' ' + \\r
               repr(self.StringValue) + ' ' + \\r
               repr(self.UseOtherLangDef)\r
\r
    def UpdateValue(self, Value = None):\r
        if Value != None:\r
            self.StringValue = Value + u'\x00'        # Add a NULL at string tail\r
            self.StringValueByteList = UniToHexList(self.StringValue)\r
            self.Length = len(self.StringValueByteList)\r
\r
## UniFileClassObject\r
#\r
# A structure for .uni file definition\r
#\r
class UniFileClassObject(object):\r
    def __init__(self, FileList = [], IsCompatibleMode = False, IncludePathList = []):\r
        self.FileList = FileList\r
        self.Token = 2\r
        self.LanguageDef = []                   #[ [u'LanguageIdentifier', u'PrintableName'], ... ]\r
        self.OrderedStringList = {}             #{ u'LanguageIdentifier' : [StringDefClassObject]  }\r
        self.OrderedStringDict = {}             #{ u'LanguageIdentifier' : {StringName:(IndexInList)}  }\r
        self.OrderedStringListByToken = {}      #{ u'LanguageIdentifier' : {Token: StringDefClassObject} }\r
        self.IsCompatibleMode = IsCompatibleMode\r
        self.IncludePathList = IncludePathList\r
        if len(self.FileList) > 0:\r
            self.LoadUniFiles(FileList)\r
\r
    #\r
    # Get Language definition\r
    #\r
    def GetLangDef(self, File, Line):\r
        Lang = distutils.util.split_quoted((Line.split(u"//")[0]))\r
        if len(Lang) != 3:\r
            try:\r
                FileIn = self.OpenUniFile(LongFilePath(File.Path))\r
            except UnicodeError, X:\r
                EdkLogger.error("build", FILE_READ_FAILURE, "File read failure: %s" % str(X), ExtraData=File);\r
            except:\r
                EdkLogger.error("build", FILE_OPEN_FAILURE, ExtraData=File);\r
            LineNo = GetLineNo(FileIn, Line, False)\r
            EdkLogger.error("Unicode File Parser", PARSER_ERROR, "Wrong language definition",\r
                            ExtraData="""%s\n\t*Correct format is like '#langdef en-US "English"'""" % Line, File=File, Line=LineNo)\r
        else:\r
            LangName = GetLanguageCode(Lang[1], self.IsCompatibleMode, self.File)\r
            LangPrintName = Lang[2]\r
\r
        IsLangInDef = False\r
        for Item in self.LanguageDef:\r
            if Item[0] == LangName:\r
                IsLangInDef = True\r
                break;\r
\r
        if not IsLangInDef:\r
            self.LanguageDef.append([LangName, LangPrintName])\r
\r
        #\r
        # Add language string\r
        #\r
        self.AddStringToList(u'$LANGUAGE_NAME', LangName, LangName, 0, True, Index=0)\r
        self.AddStringToList(u'$PRINTABLE_LANGUAGE_NAME', LangName, LangPrintName, 1, True, Index=1)\r
\r
        if not IsLangInDef:\r
            #\r
            # The found STRING tokens will be added into new language string list\r
            # so that the unique STRING identifier is reserved for all languages in the package list. \r
            #\r
            FirstLangName = self.LanguageDef[0][0]\r
            if LangName != FirstLangName:\r
                for Index in range (2, len (self.OrderedStringList[FirstLangName])):\r
                    Item = self.OrderedStringList[FirstLangName][Index]\r
                    if Item.UseOtherLangDef != '':\r
                        OtherLang = Item.UseOtherLangDef\r
                    else:\r
                        OtherLang = FirstLangName\r
                    self.OrderedStringList[LangName].append (StringDefClassObject(Item.StringName, '', Item.Referenced, Item.Token, OtherLang))\r
                    self.OrderedStringDict[LangName][Item.StringName] = len(self.OrderedStringList[LangName]) - 1\r
        return True\r
\r
    def OpenUniFile(self, FileName):\r
        #\r
        # Read file\r
        #\r
        try:\r
            UniFile = open(FileName, mode='rb')\r
            FileIn = UniFile.read()\r
            UniFile.close()\r
        except:\r
            EdkLogger.Error("build", FILE_OPEN_FAILURE, ExtraData=File)\r
\r
        #\r
        # Detect Byte Order Mark at beginning of file.  Default to UTF-8\r
        #\r
        Encoding = 'utf-8'\r
        if (FileIn.startswith(codecs.BOM_UTF16_BE) or\r
            FileIn.startswith(codecs.BOM_UTF16_LE)):\r
            Encoding = 'utf-16'\r
\r
        self.VerifyUcs2Data(FileIn, FileName, Encoding)\r
\r
        UniFile = StringIO.StringIO(FileIn)\r
        Info = codecs.lookup(Encoding)\r
        (Reader, Writer) = (Info.streamreader, Info.streamwriter)\r
        return codecs.StreamReaderWriter(UniFile, Reader, Writer)\r
\r
    def VerifyUcs2Data(self, FileIn, FileName, Encoding):\r
        Ucs2Info = codecs.lookup('ucs-2')\r
        #\r
        # Convert to unicode\r
        #\r
        try:\r
            FileDecoded = codecs.decode(FileIn, Encoding)\r
            Ucs2Info.encode(FileDecoded)\r
        except:\r
            UniFile = StringIO.StringIO(FileIn)\r
            Info = codecs.lookup(Encoding)\r
            (Reader, Writer) = (Info.streamreader, Info.streamwriter)\r
            File = codecs.StreamReaderWriter(UniFile, Reader, Writer)\r
            LineNumber = 0\r
            ErrMsg = lambda Encoding, LineNumber: \\r
                     '%s contains invalid %s characters on line %d.' % \\r
                     (FileName, Encoding, LineNumber)\r
            while True:\r
                LineNumber = LineNumber + 1\r
                try:\r
                    Line = File.readline()\r
                    if Line == '':\r
                        EdkLogger.error('Unicode File Parser', PARSER_ERROR,\r
                                        ErrMsg(Encoding, LineNumber))\r
                    Ucs2Info.encode(Line)\r
                except:\r
                    EdkLogger.error('Unicode File Parser', PARSER_ERROR,\r
                                    ErrMsg('UCS-2', LineNumber))\r
\r
    #\r
    # Get String name and value\r
    #\r
    def GetStringObject(self, Item):\r
        Language = ''\r
        Value = ''\r
\r
        Name = Item.split()[1]\r
        # Check the string name is the upper character\r
        if Name != '':\r
            MatchString = re.match('[A-Z0-9_]+', Name, re.UNICODE)\r
            if MatchString == None or MatchString.end(0) != len(Name):\r
                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))\r
        LanguageList = Item.split(u'#language ')\r
        for IndexI in range(len(LanguageList)):\r
            if IndexI == 0:\r
                continue\r
            else:\r
                Language = LanguageList[IndexI].split()[0]\r
                Value = LanguageList[IndexI][LanguageList[IndexI].find(u'\"') + len(u'\"') : LanguageList[IndexI].rfind(u'\"')] #.replace(u'\r\n', u'')\r
                Language = GetLanguageCode(Language, self.IsCompatibleMode, self.File)\r
                self.AddStringToList(Name, Language, Value)\r
\r
    #\r
    # Get include file list and load them\r
    #\r
    def GetIncludeFile(self, Item, Dir):\r
        FileName = Item[Item.find(u'#include ') + len(u'#include ') :Item.find(u' ', len(u'#include '))][1:-1]\r
        self.LoadUniFile(FileName)\r
\r
    def StripComments(self, Line):\r
        Comment = u'//'\r
        CommentPos = Line.find(Comment)\r
        while CommentPos >= 0:\r
        # if there are non matched quotes before the comment header\r
        # then we are in the middle of a string\r
        # but we need to ignore the escaped quotes and backslashes.\r
            if ((Line.count(u'"', 0, CommentPos) - Line.count(u'\\"', 0, CommentPos)) & 1) == 1:\r
                CommentPos = Line.find (Comment, CommentPos + 1)\r
            else:\r
                return Line[:CommentPos].strip()\r
        return Line.strip()\r
                \r
\r
    #\r
    # Pre-process before parse .uni file\r
    #\r
    def PreProcess(self, File):\r
        if not os.path.exists(File.Path) or not os.path.isfile(File.Path):\r
            EdkLogger.error("Unicode File Parser", FILE_NOT_FOUND, ExtraData=File.Path)\r
\r
        try:\r
            FileIn = self.OpenUniFile(LongFilePath(File.Path))\r
        except UnicodeError, X:\r
            EdkLogger.error("build", FILE_READ_FAILURE, "File read failure: %s" % str(X), ExtraData=File.Path);\r
        except:\r
            EdkLogger.error("build", FILE_OPEN_FAILURE, ExtraData=File.Path);\r
\r
        Lines = []\r
        #\r
        # Use unique identifier\r
        #\r
        for Line in FileIn:\r
            Line = Line.strip()\r
            Line = Line.replace(u'\\\\', BACK_SLASH_PLACEHOLDER)\r
            Line = self.StripComments(Line)\r
\r
            #\r
            # Ignore empty line\r
            #\r
            if len(Line) == 0: \r
                continue \r
            \r
                             \r
            Line = Line.replace(u'/langdef', u'#langdef')\r
            Line = Line.replace(u'/string', u'#string')\r
            Line = Line.replace(u'/language', u'#language')\r
            Line = Line.replace(u'/include', u'#include')\r
\r
            Line = Line.replace(UNICODE_WIDE_CHAR, WIDE_CHAR)\r
            Line = Line.replace(UNICODE_NARROW_CHAR, NARROW_CHAR)\r
            Line = Line.replace(UNICODE_NON_BREAKING_CHAR, NON_BREAKING_CHAR)\r
\r
            Line = Line.replace(u'\\r\\n', CR + LF)\r
            Line = Line.replace(u'\\n', CR + LF)\r
            Line = Line.replace(u'\\r', CR)\r
            Line = Line.replace(u'\\t', u' ')\r
            Line = Line.replace(u'\t', u' ')\r
            Line = Line.replace(u'\\"', u'"') \r
            Line = Line.replace(u"\\'", u"'") \r
            Line = Line.replace(BACK_SLASH_PLACEHOLDER, u'\\')\r
\r
#           if Line.find(u'\\x'):\r
#               hex = Line[Line.find(u'\\x') + 2 : Line.find(u'\\x') + 6]\r
#               hex = "u'\\u" + hex + "'"\r
\r
            IncList = gIncludePattern.findall(Line)\r
            if len(IncList) == 1:\r
                for Dir in [File.Dir] + self.IncludePathList:\r
                    IncFile = PathClass(str(IncList[0]), Dir)\r
                    if os.path.isfile(IncFile.Path):\r
                        Lines.extend(self.PreProcess(IncFile))\r
                        break\r
                else:\r
                    EdkLogger.error("Unicode File Parser", FILE_NOT_FOUND, Message="Cannot find include file", ExtraData=str(IncList[0]))\r
                continue\r
\r
            Lines.append(Line)\r
\r
        return Lines\r
\r
    #\r
    # Load a .uni file\r
    #\r
    def LoadUniFile(self, File = None):\r
        if File == None:\r
            EdkLogger.error("Unicode File Parser", PARSER_ERROR, 'No unicode file is given')\r
        self.File = File\r
        #\r
        # Process special char in file\r
        #\r
        Lines = self.PreProcess(File)\r
\r
        #\r
        # Get Unicode Information\r
        #\r
        for IndexI in range(len(Lines)):\r
            Line = Lines[IndexI]\r
            if (IndexI + 1) < len(Lines):\r
                SecondLine = Lines[IndexI + 1]\r
            if (IndexI + 2) < len(Lines):\r
                ThirdLine = Lines[IndexI + 2]\r
\r
            #\r
            # Get Language def information\r
            #\r
            if Line.find(u'#langdef ') >= 0:\r
                self.GetLangDef(File, Line)\r
                continue\r
\r
            Name = ''\r
            Language = ''\r
            Value = ''\r
            #\r
            # Get string def information format 1 as below\r
            #\r
            #     #string MY_STRING_1\r
            #     #language eng\r
            #     My first English string line 1\r
            #     My first English string line 2\r
            #     #string MY_STRING_1\r
            #     #language spa\r
            #     Mi segunda secuencia 1\r
            #     Mi segunda secuencia 2\r
            #\r
            if Line.find(u'#string ') >= 0 and Line.find(u'#language ') < 0 and \\r
                SecondLine.find(u'#string ') < 0 and SecondLine.find(u'#language ') >= 0 and \\r
                ThirdLine.find(u'#string ') < 0 and ThirdLine.find(u'#language ') < 0:\r
                Name = Line[Line.find(u'#string ') + len(u'#string ') : ].strip(' ')\r
                Language = SecondLine[SecondLine.find(u'#language ') + len(u'#language ') : ].strip(' ')\r
                for IndexJ in range(IndexI + 2, len(Lines)):\r
                    if Lines[IndexJ].find(u'#string ') < 0 and Lines[IndexJ].find(u'#language ') < 0:\r
                        Value = Value + Lines[IndexJ]\r
                    else:\r
                        IndexI = IndexJ\r
                        break\r
                # Value = Value.replace(u'\r\n', u'')\r
                Language = GetLanguageCode(Language, self.IsCompatibleMode, self.File)\r
                # Check the string name is the upper character\r
                if not self.IsCompatibleMode and Name != '':\r
                    MatchString = re.match('[A-Z0-9_]+', Name, re.UNICODE)\r
                    if MatchString == None or MatchString.end(0) != len(Name):\r
                        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))\r
                self.AddStringToList(Name, Language, Value)\r
                continue\r
\r
            #\r
            # Get string def information format 2 as below\r
            #\r
            #     #string MY_STRING_1     #language eng     "My first English string line 1"\r
            #                                               "My first English string line 2"\r
            #                             #language spa     "Mi segunda secuencia 1"\r
            #                                               "Mi segunda secuencia 2"\r
            #     #string MY_STRING_2     #language eng     "My first English string line 1"\r
            #                                               "My first English string line 2"\r
            #     #string MY_STRING_2     #language spa     "Mi segunda secuencia 1"\r
            #                                               "Mi segunda secuencia 2"\r
            #\r
            if Line.find(u'#string ') >= 0 and Line.find(u'#language ') >= 0:\r
                StringItem = Line\r
                for IndexJ in range(IndexI + 1, len(Lines)):\r
                    if Lines[IndexJ].find(u'#string ') >= 0 and Lines[IndexJ].find(u'#language ') >= 0:\r
                        IndexI = IndexJ\r
                        break\r
                    elif Lines[IndexJ].find(u'#string ') < 0 and Lines[IndexJ].find(u'#language ') >= 0:\r
                        StringItem = StringItem + Lines[IndexJ]\r
                    elif Lines[IndexJ].count(u'\"') >= 2:\r
                        StringItem = StringItem[ : StringItem.rfind(u'\"')] + Lines[IndexJ][Lines[IndexJ].find(u'\"') + len(u'\"') : ]\r
                self.GetStringObject(StringItem)\r
                continue\r
\r
    #\r
    # Load multiple .uni files\r
    #\r
    def LoadUniFiles(self, FileList):\r
        if len(FileList) > 0:\r
            for File in FileList:\r
                self.LoadUniFile(File)\r
\r
    #\r
    # Add a string to list\r
    #\r
    def AddStringToList(self, Name, Language, Value, Token = None, Referenced = False, UseOtherLangDef = '', Index = -1):\r
        for LangNameItem in self.LanguageDef:\r
            if Language == LangNameItem[0]:\r
                break\r
        else:\r
            EdkLogger.error('Unicode File Parser', FORMAT_NOT_SUPPORTED, "The language '%s' for %s is not defined in Unicode file %s." \\r
                            % (Language, Name, self.File))\r
            \r
        if Language not in self.OrderedStringList:\r
            self.OrderedStringList[Language] = []\r
            self.OrderedStringDict[Language] = {}\r
\r
        IsAdded = True\r
        if Name in self.OrderedStringDict[Language]:\r
            IsAdded = False\r
            if Value != None:\r
                ItemIndexInList = self.OrderedStringDict[Language][Name]\r
                Item = self.OrderedStringList[Language][ItemIndexInList]\r
                Item.UpdateValue(Value)\r
                Item.UseOtherLangDef = ''\r
\r
        if IsAdded:\r
            Token = len(self.OrderedStringList[Language])\r
            if Index == -1:\r
                self.OrderedStringList[Language].append(StringDefClassObject(Name, Value, Referenced, Token, UseOtherLangDef))\r
                self.OrderedStringDict[Language][Name] = Token\r
                for LangName in self.LanguageDef:\r
                    #\r
                    # New STRING token will be added into all language string lists.\r
                    # so that the unique STRING identifier is reserved for all languages in the package list. \r
                    #\r
                    if LangName[0] != Language:\r
                        if UseOtherLangDef != '':\r
                            OtherLangDef = UseOtherLangDef\r
                        else:\r
                            OtherLangDef = Language\r
                        self.OrderedStringList[LangName[0]].append(StringDefClassObject(Name, '', Referenced, Token, OtherLangDef))\r
                        self.OrderedStringDict[LangName[0]][Name] = len(self.OrderedStringList[LangName[0]]) - 1\r
            else:\r
                self.OrderedStringList[Language].insert(Index, StringDefClassObject(Name, Value, Referenced, Token, UseOtherLangDef))\r
                self.OrderedStringDict[Language][Name] = Index\r
\r
    #\r
    # Set the string as referenced\r
    #\r
    def SetStringReferenced(self, Name):\r
        #\r
        # String stoken are added in the same order in all language string lists.\r
        # So, only update the status of string stoken in first language string list.\r
        #\r
        Lang = self.LanguageDef[0][0]\r
        if Name in self.OrderedStringDict[Lang]:\r
            ItemIndexInList = self.OrderedStringDict[Lang][Name]\r
            Item = self.OrderedStringList[Lang][ItemIndexInList]\r
            Item.Referenced = True\r
\r
    #\r
    # Search the string in language definition by Name\r
    #\r
    def FindStringValue(self, Name, Lang):\r
        if Name in self.OrderedStringDict[Lang]:\r
            ItemIndexInList = self.OrderedStringDict[Lang][Name]\r
            return self.OrderedStringList[Lang][ItemIndexInList]\r
\r
        return None\r
\r
    #\r
    # Search the string in language definition by Token\r
    #\r
    def FindByToken(self, Token, Lang):\r
        for Item in self.OrderedStringList[Lang]:\r
            if Item.Token == Token:\r
                return Item\r
\r
        return None\r
\r
    #\r
    # Re-order strings and re-generate tokens\r
    #\r
    def ReToken(self):\r
        #\r
        # Retoken all language strings according to the status of string stoken in the first language string.\r
        #\r
        FirstLangName = self.LanguageDef[0][0]\r
\r
        # Convert the OrderedStringList to be OrderedStringListByToken in order to faciliate future search by token\r
        for LangNameItem in self.LanguageDef:\r
            self.OrderedStringListByToken[LangNameItem[0]] = {}\r
\r
        #\r
        # Use small token for all referred string stoken.\r
        #\r
        RefToken = 0\r
        for Index in range (0, len (self.OrderedStringList[FirstLangName])):\r
            FirstLangItem = self.OrderedStringList[FirstLangName][Index]\r
            if FirstLangItem.Referenced == True:\r
                for LangNameItem in self.LanguageDef:\r
                    LangName = LangNameItem[0]\r
                    OtherLangItem = self.OrderedStringList[LangName][Index]\r
                    OtherLangItem.Referenced = True\r
                    OtherLangItem.Token = RefToken\r
                    self.OrderedStringListByToken[LangName][OtherLangItem.Token] = OtherLangItem\r
                RefToken = RefToken + 1\r
\r
        #\r
        # Use big token for all unreferred string stoken.\r
        #\r
        UnRefToken = 0\r
        for Index in range (0, len (self.OrderedStringList[FirstLangName])):\r
            FirstLangItem = self.OrderedStringList[FirstLangName][Index]\r
            if FirstLangItem.Referenced == False:\r
                for LangNameItem in self.LanguageDef:\r
                    LangName = LangNameItem[0]\r
                    OtherLangItem = self.OrderedStringList[LangName][Index]\r
                    OtherLangItem.Token = RefToken + UnRefToken\r
                    self.OrderedStringListByToken[LangName][OtherLangItem.Token] = OtherLangItem\r
                UnRefToken = UnRefToken + 1\r
\r
    #\r
    # Show the instance itself\r
    #\r
    def ShowMe(self):\r
        print self.LanguageDef\r
        #print self.OrderedStringList\r
        for Item in self.OrderedStringList:\r
            print Item\r
            for Member in self.OrderedStringList[Item]:\r
                print str(Member)\r
\r
# This acts like the main() function for the script, unless it is 'import'ed into another\r
# script.\r
if __name__ == '__main__':\r
    EdkLogger.Initialize()\r
    EdkLogger.SetLevel(EdkLogger.DEBUG_0)\r
    a = UniFileClassObject([PathClass("C:\\Edk\\Strings.uni"), PathClass("C:\\Edk\\Strings2.uni")])\r
    a.ReToken()\r
    a.ShowMe()\r