2 # This file is used to collect all defined strings in multiple uni files
5 # Copyright (c) 2014 Hewlett-Packard Development Company, L.P.<BR>
7 # Copyright (c) 2007 - 2018, Intel Corporation. All rights reserved.<BR>
8 # SPDX-License-Identifier: BSD-2-Clause-Patent
13 from __future__
import print_function
14 import Common
.LongFilePathOs
as os
, codecs
, re
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 *
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'
32 NARROW_CHAR
= u
'\uFFF0'
34 NON_BREAKING_CHAR
= u
'\uFFF2'
39 BACK_SLASH_PLACEHOLDER
= u
'\u0006'
41 gIncludePattern
= re
.compile("^#include +[\"<]+([^\"< >]+)[>\"]+$", re
.MULTILINE | re
.UNICODE
)
43 ## Convert a unicode string to a Hex list
45 # Convert a unicode string to a Hex list
46 # UniToHexList('ABC') is ['0x41', '0x00', '0x42', '0x00', '0x43', '0x00']
48 # @param Uni: The python unicode string
50 # @retval List: The formatted hex list
52 def UniToHexList(Uni
):
55 Temp
= '%04X' % ord(Item
)
56 List
.append('0x' + Temp
[2:4])
57 List
.append('0x' + Temp
[0:2])
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'}
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
99 # @param LangName: Language codes read from .UNI file
101 # @retval LangName: Valid language code in RFC 4646 format or None
103 def GetLanguageCode(LangName
, IsCompatibleMode
, File
):
104 length
= len(LangName
)
106 if length
== 3 and LangName
.isalpha():
107 TempLangName
= LangConvTable
.get(LangName
.lower())
108 if TempLangName
is not None:
112 EdkLogger
.error("Unicode File Parser", FORMAT_INVALID
, "Invalid ISO 639-2 language code : %s" % LangName
, File
)
114 if (LangName
[0] == 'X' or LangName
[0] == 'x') and LangName
[1] == '-':
117 if LangName
.isalpha():
120 if LangName
.isalpha() and LangConvTable
.get(LangName
.lower()) is None:
123 if LangName
[0:2].isalpha() and LangName
[2] == '-':
126 if LangName
[0:2].isalpha() and LangName
[2] == '-':
128 if LangName
[0:3].isalpha() and LangConvTable
.get(LangName
.lower()) is None and LangName
[3] == '-':
131 EdkLogger
.error("Unicode File Parser", FORMAT_INVALID
, "Invalid RFC 4646 language code : %s" % LangName
, File
)
135 # This is only a partial codec implementation. It only supports
136 # encoding, and is primarily used to check that all the characters are
139 class Ucs2Codec(codecs
.Codec
):
141 self
.__utf
16 = codecs
.lookup('utf-16')
143 def encode(self
, input, errors
='strict'):
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
.__utf
16.encode(input)
153 TheUcs2Codec
= Ucs2Codec()
154 def Ucs2Search(name
):
156 return codecs
.CodecInfo(
158 encode
=TheUcs2Codec
.encode
,
159 decode
=TheUcs2Codec
.decode
)
162 codecs
.register(Ucs2Search
)
164 ## StringDefClassObject
166 # A structure for language definition
168 class StringDefClassObject(object):
169 def __init__(self
, Name
= None, Value
= None, Referenced
= False, Token
= None, UseOtherLangDef
= ''):
171 self
.StringNameByteList
= []
172 self
.StringValue
= ''
173 self
.StringValueByteList
= ''
175 self
.Referenced
= Referenced
176 self
.UseOtherLangDef
= UseOtherLangDef
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:
190 return repr(self
.StringName
) + ' ' + \
191 repr(self
.Token
) + ' ' + \
192 repr(self
.Referenced
) + ' ' + \
193 repr(self
.StringValue
) + ' ' + \
194 repr(self
.UseOtherLangDef
)
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
)
202 def StripComments(Line
):
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)
212 return Line
[:CommentPos
].strip()
215 ## UniFileClassObject
217 # A structure for .uni file definition
219 class UniFileClassObject(object):
220 def __init__(self
, FileList
= [], IsCompatibleMode
= False, IncludePathList
= []):
221 self
.FileList
= FileList
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
)
233 # Get Language definition
235 def GetLangDef(self
, File
, Line
):
236 Lang
= distutils
.util
.split_quoted((Line
.split(u
"//")[0]))
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
);
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
)
248 LangName
= GetLanguageCode(Lang
[1], self
.IsCompatibleMode
, self
.File
)
249 LangPrintName
= Lang
[2]
252 for Item
in self
.LanguageDef
:
253 if Item
[0] == LangName
:
258 self
.LanguageDef
.append([LangName
, LangPrintName
])
261 # Add language string
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)
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.
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
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
284 def OpenUniFile(FileName
):
289 UniFile
= open(FileName
, mode
='rb')
290 FileIn
= UniFile
.read()
293 EdkLogger
.Error("build", FILE_OPEN_FAILURE
, ExtraData
=File
)
296 # Detect Byte Order Mark at beginning of file. Default to UTF-8
299 if (FileIn
.startswith(codecs
.BOM_UTF16_BE
) or
300 FileIn
.startswith(codecs
.BOM_UTF16_LE
)):
303 UniFileClassObject
.VerifyUcs2Data(FileIn
, FileName
, Encoding
)
305 UniFile
= BytesIO(FileIn
)
306 Info
= codecs
.lookup(Encoding
)
307 (Reader
, Writer
) = (Info
.streamreader
, Info
.streamwriter
)
308 return codecs
.StreamReaderWriter(UniFile
, Reader
, Writer
)
311 def VerifyUcs2Data(FileIn
, FileName
, Encoding
):
312 Ucs2Info
= codecs
.lookup('ucs-2')
317 FileDecoded
= codecs
.decode(FileIn
, Encoding
)
318 Ucs2Info
.encode(FileDecoded
)
320 UniFile
= BytesIO(FileIn
)
321 Info
= codecs
.lookup(Encoding
)
322 (Reader
, Writer
) = (Info
.streamreader
, Info
.streamwriter
)
323 File
= codecs
.StreamReaderWriter(UniFile
, Reader
, Writer
)
325 ErrMsg
= lambda Encoding
, LineNumber
: \
326 '%s contains invalid %s characters on line %d.' % \
327 (FileName
, Encoding
, LineNumber
)
329 LineNumber
= LineNumber
+ 1
331 Line
= File
.readline()
333 EdkLogger
.error('Unicode File Parser', PARSER_ERROR
,
334 ErrMsg(Encoding
, LineNumber
))
335 Ucs2Info
.encode(Line
)
337 EdkLogger
.error('Unicode File Parser', PARSER_ERROR
,
338 ErrMsg('UCS-2', LineNumber
))
341 # Get String name and value
343 def GetStringObject(self
, Item
):
347 Name
= Item
.split()[1]
348 # Check the string 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
)):
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
)
364 # Get include file list and load them
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
)
371 # Pre-process before parse .uni file
373 def PreProcess(self
, File
):
374 if not os
.path
.exists(File
.Path
) or not os
.path
.isfile(File
.Path
):
375 EdkLogger
.error("Unicode File Parser", FILE_NOT_FOUND
, ExtraData
=File
.Path
)
378 FileIn
= UniFileClassObject
.OpenUniFile(LongFilePath(File
.Path
))
379 except UnicodeError as X
:
380 EdkLogger
.error("build", FILE_READ_FAILURE
, "File read failure: %s" % str(X
), ExtraData
=File
.Path
);
382 EdkLogger
.error("build", FILE_OPEN_FAILURE
, ExtraData
=File
.Path
);
386 # Use unique identifier
390 Line
= Line
.replace(u
'\\\\', BACK_SLASH_PLACEHOLDER
)
391 Line
= StripComments(Line
)
400 Line
= Line
.replace(u
'/langdef', u
'#langdef')
401 Line
= Line
.replace(u
'/string', u
'#string')
402 Line
= Line
.replace(u
'/language', u
'#language')
403 Line
= Line
.replace(u
'/include', u
'#include')
405 Line
= Line
.replace(UNICODE_WIDE_CHAR
, WIDE_CHAR
)
406 Line
= Line
.replace(UNICODE_NARROW_CHAR
, NARROW_CHAR
)
407 Line
= Line
.replace(UNICODE_NON_BREAKING_CHAR
, NON_BREAKING_CHAR
)
409 Line
= Line
.replace(u
'\\r\\n', CR
+ LF
)
410 Line
= Line
.replace(u
'\\n', CR
+ LF
)
411 Line
= Line
.replace(u
'\\r', CR
)
412 Line
= Line
.replace(u
'\\t', u
' ')
413 Line
= Line
.replace(u
'\t', u
' ')
414 Line
= Line
.replace(u
'\\"', u
'"')
415 Line
= Line
.replace(u
"\\'", u
"'")
416 Line
= Line
.replace(BACK_SLASH_PLACEHOLDER
, u
'\\')
418 StartPos
= Line
.find(u
'\\x')
419 while (StartPos
!= -1):
420 EndPos
= Line
.find(u
'\\', StartPos
+ 1, StartPos
+ 7)
421 if EndPos
!= -1 and EndPos
- StartPos
== 6 :
422 if g4HexChar
.match(Line
[StartPos
+ 2 : EndPos
], re
.UNICODE
):
423 EndStr
= Line
[EndPos
: ]
424 UniStr
= Line
[StartPos
+ 2: EndPos
]
425 if EndStr
.startswith(u
'\\x') and len(EndStr
) >= 7:
426 if EndStr
[6] == u
'\\' and g4HexChar
.match(EndStr
[2 : 6], re
.UNICODE
):
427 Line
= Line
[0 : StartPos
] + UniStr
+ EndStr
429 Line
= Line
[0 : StartPos
] + UniStr
+ EndStr
[1:]
430 StartPos
= Line
.find(u
'\\x', StartPos
+ 1)
432 IncList
= gIncludePattern
.findall(Line
)
433 if len(IncList
) == 1:
434 for Dir
in [File
.Dir
] + self
.IncludePathList
:
435 IncFile
= PathClass(str(IncList
[0]), Dir
)
436 if os
.path
.isfile(IncFile
.Path
):
437 Lines
.extend(self
.PreProcess(IncFile
))
440 EdkLogger
.error("Unicode File Parser", FILE_NOT_FOUND
, Message
="Cannot find include file", ExtraData
=str(IncList
[0]))
450 def LoadUniFile(self
, File
= None):
452 EdkLogger
.error("Unicode File Parser", PARSER_ERROR
, 'No unicode file is given')
455 # Process special char in file
457 Lines
= self
.PreProcess(File
)
460 # Get Unicode Information
462 for IndexI
in range(len(Lines
)):
464 if (IndexI
+ 1) < len(Lines
):
465 SecondLine
= Lines
[IndexI
+ 1]
466 if (IndexI
+ 2) < len(Lines
):
467 ThirdLine
= Lines
[IndexI
+ 2]
470 # Get Language def information
472 if Line
.find(u
'#langdef ') >= 0:
473 self
.GetLangDef(File
, Line
)
480 # Get string def information format 1 as below
482 # #string MY_STRING_1
484 # My first English string line 1
485 # My first English string line 2
486 # #string MY_STRING_1
488 # Mi segunda secuencia 1
489 # Mi segunda secuencia 2
491 if Line
.find(u
'#string ') >= 0 and Line
.find(u
'#language ') < 0 and \
492 SecondLine
.find(u
'#string ') < 0 and SecondLine
.find(u
'#language ') >= 0 and \
493 ThirdLine
.find(u
'#string ') < 0 and ThirdLine
.find(u
'#language ') < 0:
494 Name
= Line
[Line
.find(u
'#string ') + len(u
'#string ') : ].strip(' ')
495 Language
= SecondLine
[SecondLine
.find(u
'#language ') + len(u
'#language ') : ].strip(' ')
496 for IndexJ
in range(IndexI
+ 2, len(Lines
)):
497 if Lines
[IndexJ
].find(u
'#string ') < 0 and Lines
[IndexJ
].find(u
'#language ') < 0:
498 Value
= Value
+ Lines
[IndexJ
]
502 # Value = Value.replace(u'\r\n', u'')
503 Language
= GetLanguageCode(Language
, self
.IsCompatibleMode
, self
.File
)
504 # Check the string name
505 if not self
.IsCompatibleMode
and Name
!= '':
506 MatchString
= gIdentifierPattern
.match(Name
)
507 if MatchString
is None:
508 EdkLogger
.error('Unicode File Parser', FORMAT_INVALID
, 'The string token name %s defined in UNI file %s contains the invalid character.' % (Name
, self
.File
))
509 self
.AddStringToList(Name
, Language
, Value
)
513 # Get string def information format 2 as below
515 # #string MY_STRING_1 #language eng "My first English string line 1"
516 # "My first English string line 2"
517 # #language spa "Mi segunda secuencia 1"
518 # "Mi segunda secuencia 2"
519 # #string MY_STRING_2 #language eng "My first English string line 1"
520 # "My first English string line 2"
521 # #string MY_STRING_2 #language spa "Mi segunda secuencia 1"
522 # "Mi segunda secuencia 2"
524 if Line
.find(u
'#string ') >= 0 and Line
.find(u
'#language ') >= 0:
526 for IndexJ
in range(IndexI
+ 1, len(Lines
)):
527 if Lines
[IndexJ
].find(u
'#string ') >= 0 and Lines
[IndexJ
].find(u
'#language ') >= 0:
530 elif Lines
[IndexJ
].find(u
'#string ') < 0 and Lines
[IndexJ
].find(u
'#language ') >= 0:
531 StringItem
= StringItem
+ Lines
[IndexJ
]
532 elif Lines
[IndexJ
].count(u
'\"') >= 2:
533 StringItem
= StringItem
[ : StringItem
.rfind(u
'\"')] + Lines
[IndexJ
][Lines
[IndexJ
].find(u
'\"') + len(u
'\"') : ]
534 self
.GetStringObject(StringItem
)
538 # Load multiple .uni files
540 def LoadUniFiles(self
, FileList
):
541 if len(FileList
) > 0:
542 for File
in FileList
:
543 self
.LoadUniFile(File
)
546 # Add a string to list
548 def AddStringToList(self
, Name
, Language
, Value
, Token
= None, Referenced
= False, UseOtherLangDef
= '', Index
= -1):
549 for LangNameItem
in self
.LanguageDef
:
550 if Language
== LangNameItem
[0]:
553 EdkLogger
.error('Unicode File Parser', FORMAT_NOT_SUPPORTED
, "The language '%s' for %s is not defined in Unicode file %s." \
554 % (Language
, Name
, self
.File
))
556 if Language
not in self
.OrderedStringList
:
557 self
.OrderedStringList
[Language
] = []
558 self
.OrderedStringDict
[Language
] = {}
561 if Name
in self
.OrderedStringDict
[Language
]:
563 if Value
is not None:
564 ItemIndexInList
= self
.OrderedStringDict
[Language
][Name
]
565 Item
= self
.OrderedStringList
[Language
][ItemIndexInList
]
566 Item
.UpdateValue(Value
)
567 Item
.UseOtherLangDef
= ''
570 Token
= len(self
.OrderedStringList
[Language
])
572 self
.OrderedStringList
[Language
].append(StringDefClassObject(Name
, Value
, Referenced
, Token
, UseOtherLangDef
))
573 self
.OrderedStringDict
[Language
][Name
] = Token
574 for LangName
in self
.LanguageDef
:
576 # New STRING token will be added into all language string lists.
577 # so that the unique STRING identifier is reserved for all languages in the package list.
579 if LangName
[0] != Language
:
580 if UseOtherLangDef
!= '':
581 OtherLangDef
= UseOtherLangDef
583 OtherLangDef
= Language
584 self
.OrderedStringList
[LangName
[0]].append(StringDefClassObject(Name
, '', Referenced
, Token
, OtherLangDef
))
585 self
.OrderedStringDict
[LangName
[0]][Name
] = len(self
.OrderedStringList
[LangName
[0]]) - 1
587 self
.OrderedStringList
[Language
].insert(Index
, StringDefClassObject(Name
, Value
, Referenced
, Token
, UseOtherLangDef
))
588 self
.OrderedStringDict
[Language
][Name
] = Index
591 # Set the string as referenced
593 def SetStringReferenced(self
, Name
):
595 # String stoken are added in the same order in all language string lists.
596 # So, only update the status of string stoken in first language string list.
598 Lang
= self
.LanguageDef
[0][0]
599 if Name
in self
.OrderedStringDict
[Lang
]:
600 ItemIndexInList
= self
.OrderedStringDict
[Lang
][Name
]
601 Item
= self
.OrderedStringList
[Lang
][ItemIndexInList
]
602 Item
.Referenced
= True
605 # Search the string in language definition by Name
607 def FindStringValue(self
, Name
, Lang
):
608 if Name
in self
.OrderedStringDict
[Lang
]:
609 ItemIndexInList
= self
.OrderedStringDict
[Lang
][Name
]
610 return self
.OrderedStringList
[Lang
][ItemIndexInList
]
615 # Search the string in language definition by Token
617 def FindByToken(self
, Token
, Lang
):
618 for Item
in self
.OrderedStringList
[Lang
]:
619 if Item
.Token
== Token
:
625 # Re-order strings and re-generate tokens
629 # Retoken all language strings according to the status of string stoken in the first language string.
631 FirstLangName
= self
.LanguageDef
[0][0]
633 # Convert the OrderedStringList to be OrderedStringListByToken in order to faciliate future search by token
634 for LangNameItem
in self
.LanguageDef
:
635 self
.OrderedStringListByToken
[LangNameItem
[0]] = {}
638 # Use small token for all referred string stoken.
641 for Index
in range (0, len (self
.OrderedStringList
[FirstLangName
])):
642 FirstLangItem
= self
.OrderedStringList
[FirstLangName
][Index
]
643 if FirstLangItem
.Referenced
== True:
644 for LangNameItem
in self
.LanguageDef
:
645 LangName
= LangNameItem
[0]
646 OtherLangItem
= self
.OrderedStringList
[LangName
][Index
]
647 OtherLangItem
.Referenced
= True
648 OtherLangItem
.Token
= RefToken
649 self
.OrderedStringListByToken
[LangName
][OtherLangItem
.Token
] = OtherLangItem
650 RefToken
= RefToken
+ 1
653 # Use big token for all unreferred string stoken.
656 for Index
in range (0, len (self
.OrderedStringList
[FirstLangName
])):
657 FirstLangItem
= self
.OrderedStringList
[FirstLangName
][Index
]
658 if FirstLangItem
.Referenced
== False:
659 for LangNameItem
in self
.LanguageDef
:
660 LangName
= LangNameItem
[0]
661 OtherLangItem
= self
.OrderedStringList
[LangName
][Index
]
662 OtherLangItem
.Token
= RefToken
+ UnRefToken
663 self
.OrderedStringListByToken
[LangName
][OtherLangItem
.Token
] = OtherLangItem
664 UnRefToken
= UnRefToken
+ 1
667 # Show the instance itself
670 print(self
.LanguageDef
)
671 #print self.OrderedStringList
672 for Item
in self
.OrderedStringList
:
674 for Member
in self
.OrderedStringList
[Item
]:
677 # This acts like the main() function for the script, unless it is 'import'ed into another
679 if __name__
== '__main__':
680 EdkLogger
.Initialize()
681 EdkLogger
.SetLevel(EdkLogger
.DEBUG_0
)
682 a
= UniFileClassObject([PathClass("C:\\Edk\\Strings.uni"), PathClass("C:\\Edk\\Strings2.uni")])