#\r
# Copyright (c) 2014 Hewlett-Packard Development Company, L.P.<BR>\r
#\r
-# Copyright (c) 2007 - 2015, Intel Corporation. All rights reserved.<BR>\r
+# Copyright (c) 2007 - 2018, 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
##\r
# Import Modules\r
#\r
+from __future__ import print_function\r
import Common.LongFilePathOs as os, codecs, re\r
import distutils.util\r
import Common.EdkLogger as EdkLogger\r
-import StringIO\r
+from io import BytesIO\r
from Common.BuildToolError import *\r
-from Common.String import GetLineNo\r
+from Common.StringUtils import GetLineNo\r
from Common.Misc import PathClass\r
from Common.LongFilePathSupport import LongFilePath\r
+from Common.GlobalData import *\r
##\r
# Static definitions\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
+ if TempLangName is not None:\r
return TempLangName\r
return LangName\r
else:\r
if LangName.isalpha():\r
return LangName\r
elif length == 3:\r
- if LangName.isalpha() and LangConvTable.get(LangName.lower()) == None:\r
+ if LangName.isalpha() and LangConvTable.get(LangName.lower()) is None:\r
return LangName\r
elif length == 5:\r
if LangName[0:2].isalpha() and LangName[2] == '-':\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
+ if LangName[0:3].isalpha() and LangConvTable.get(LangName.lower()) is 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
self.UseOtherLangDef = UseOtherLangDef\r
self.Length = 0\r
\r
- if Name != None:\r
+ if Name is not None:\r
self.StringName = Name\r
self.StringNameByteList = UniToHexList(Name)\r
- if Value != None:\r
+ if Value is not 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
+ if Token is not None:\r
self.Token = Token\r
\r
def __str__(self):\r
repr(self.UseOtherLangDef)\r
\r
def UpdateValue(self, Value = None):\r
- if Value != None:\r
+ if Value is not 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
+def StripComments(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
## UniFileClassObject\r
#\r
# A structure for .uni file definition\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
+ FileIn = UniFileClassObject.OpenUniFile(LongFilePath(File.Path))\r
+ except UnicodeError as 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
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
+ # 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
self.OrderedStringDict[LangName][Item.StringName] = len(self.OrderedStringList[LangName]) - 1\r
return True\r
\r
- def OpenUniFile(self, FileName):\r
+ @staticmethod\r
+ def OpenUniFile(FileName):\r
#\r
# Read file\r
#\r
FileIn.startswith(codecs.BOM_UTF16_LE)):\r
Encoding = 'utf-16'\r
\r
- self.VerifyUcs2Data(FileIn, FileName, Encoding)\r
+ UniFileClassObject.VerifyUcs2Data(FileIn, FileName, Encoding)\r
\r
- UniFile = StringIO.StringIO(FileIn)\r
+ UniFile = BytesIO(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
+ @staticmethod\r
+ def VerifyUcs2Data(FileIn, FileName, Encoding):\r
Ucs2Info = codecs.lookup('ucs-2')\r
#\r
# Convert to unicode\r
FileDecoded = codecs.decode(FileIn, Encoding)\r
Ucs2Info.encode(FileDecoded)\r
except:\r
- UniFile = StringIO.StringIO(FileIn)\r
+ UniFile = BytesIO(FileIn)\r
Info = codecs.lookup(Encoding)\r
(Reader, Writer) = (Info.streamreader, Info.streamwriter)\r
File = codecs.StreamReaderWriter(UniFile, Reader, Writer)\r
Value = ''\r
\r
Name = Item.split()[1]\r
- # Check the string name is the upper character\r
+ # Check the string name\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
+ MatchString = gIdentifierPattern.match(Name)\r
+ if MatchString is None:\r
+ EdkLogger.error('Unicode File Parser', FORMAT_INVALID, 'The string token name %s defined in UNI file %s contains the invalid character.' % (Name, self.File))\r
LanguageList = Item.split(u'#language ')\r
for IndexI in range(len(LanguageList)):\r
if IndexI == 0:\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
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
+ FileIn = UniFileClassObject.OpenUniFile(LongFilePath(File.Path))\r
+ except UnicodeError as 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
for Line in FileIn:\r
Line = Line.strip()\r
Line = Line.replace(u'\\\\', BACK_SLASH_PLACEHOLDER)\r
- Line = self.StripComments(Line)\r
+ Line = StripComments(Line)\r
\r
#\r
# Ignore empty line\r
#\r
- if len(Line) == 0: \r
- continue \r
- \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'\\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(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
+ StartPos = Line.find(u'\\x')\r
+ while (StartPos != -1):\r
+ EndPos = Line.find(u'\\', StartPos + 1, StartPos + 7)\r
+ if EndPos != -1 and EndPos - StartPos == 6 :\r
+ if g4HexChar.match(Line[StartPos + 2 : EndPos], re.UNICODE):\r
+ EndStr = Line[EndPos: ]\r
+ UniStr = ('\u' + (Line[StartPos + 2 : EndPos])).decode('unicode_escape')\r
+ if EndStr.startswith(u'\\x') and len(EndStr) >= 7:\r
+ if EndStr[6] == u'\\' and g4HexChar.match(EndStr[2 : 6], re.UNICODE):\r
+ Line = Line[0 : StartPos] + UniStr + EndStr\r
+ else:\r
+ Line = Line[0 : StartPos] + UniStr + EndStr[1:]\r
+ StartPos = Line.find(u'\\x', StartPos + 1)\r
\r
IncList = gIncludePattern.findall(Line)\r
if len(IncList) == 1:\r
# Load a .uni file\r
#\r
def LoadUniFile(self, File = None):\r
- if File == None:\r
+ if File is None:\r
EdkLogger.error("Unicode File Parser", PARSER_ERROR, 'No unicode file is given')\r
self.File = File\r
#\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
+ # Check the string name\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
+ MatchString = gIdentifierPattern.match(Name)\r
+ if MatchString is None:\r
+ EdkLogger.error('Unicode File Parser', FORMAT_INVALID, 'The string token name %s defined in UNI file %s contains the invalid character.' % (Name, self.File))\r
self.AddStringToList(Name, Language, Value)\r
continue\r
\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
+\r
if Language not in self.OrderedStringList:\r
self.OrderedStringList[Language] = []\r
self.OrderedStringDict[Language] = {}\r
IsAdded = True\r
if Name in self.OrderedStringDict[Language]:\r
IsAdded = False\r
- if Value != None:\r
+ if Value is not None:\r
ItemIndexInList = self.OrderedStringDict[Language][Name]\r
Item = self.OrderedStringList[Language][ItemIndexInList]\r
Item.UpdateValue(Value)\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
+ # 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
# Show the instance itself\r
#\r
def ShowMe(self):\r
- print self.LanguageDef\r
+ print(self.LanguageDef)\r
#print self.OrderedStringList\r
for Item in self.OrderedStringList:\r
- print Item\r
+ print(Item)\r
for Member in self.OrderedStringList[Item]:\r
- print str(Member)\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