]> git.proxmox.com Git - mirror_edk2.git/blob - BaseTools/Source/Python/UPT/Library/UniClassObject.py
BaseTools/UPT: UPT to Support UTF-8
[mirror_edk2.git] / BaseTools / Source / Python / UPT / Library / UniClassObject.py
1 ## @file
2 # Collect all defined strings in multiple uni files.
3 #
4 # Copyright (c) 2014 - 2016, Intel Corporation. All rights reserved.<BR>
5 #
6 # This program and the accompanying materials are licensed and made available
7 # under the terms and conditions of the BSD License which accompanies this
8 # distribution. The full text of the license may be found at
9 # http://opensource.org/licenses/bsd-license.php
10 #
11 # THE PROGRAM IS DISTRIBUTED UNDER THE BSD LICENSE ON AN "AS IS" BASIS,
12 # WITHOUT WARRANTIES OR REPRESENTATIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED.
13 #
14 """
15 Collect all defined strings in multiple uni files
16 """
17
18 ##
19 # Import Modules
20 #
21 import os, codecs, re
22 import distutils.util
23 from Logger import ToolError
24 from Logger import Log as EdkLogger
25 from Logger import StringTable as ST
26 from Library.String import GetLineNo
27 from Library.Misc import PathClass
28 from Library.Misc import GetCharIndexOutStr
29 from Library import DataType as DT
30 from Library.ParserValidate import CheckUTF16FileHeader
31
32 ##
33 # Static definitions
34 #
35 UNICODE_WIDE_CHAR = u'\\wide'
36 UNICODE_NARROW_CHAR = u'\\narrow'
37 UNICODE_NON_BREAKING_CHAR = u'\\nbr'
38 UNICODE_UNICODE_CR = '\r'
39 UNICODE_UNICODE_LF = '\n'
40
41 NARROW_CHAR = u'\uFFF0'
42 WIDE_CHAR = u'\uFFF1'
43 NON_BREAKING_CHAR = u'\uFFF2'
44 CR = u'\u000D'
45 LF = u'\u000A'
46 NULL = u'\u0000'
47 TAB = u'\t'
48 BACK_SPLASH = u'\\'
49
50 gINCLUDE_PATTERN = re.compile("^!include[\s]+([\S]+)[\s]*$", re.MULTILINE | re.UNICODE)
51
52 gLANG_CONV_TABLE = {'eng':'en', 'fra':'fr', \
53 'aar':'aa', 'abk':'ab', 'ave':'ae', 'afr':'af', 'aka':'ak', 'amh':'am', \
54 'arg':'an', 'ara':'ar', 'asm':'as', 'ava':'av', 'aym':'ay', 'aze':'az', \
55 'bak':'ba', 'bel':'be', 'bul':'bg', 'bih':'bh', 'bis':'bi', 'bam':'bm', \
56 'ben':'bn', 'bod':'bo', 'bre':'br', 'bos':'bs', 'cat':'ca', 'che':'ce', \
57 'cha':'ch', 'cos':'co', 'cre':'cr', 'ces':'cs', 'chu':'cu', 'chv':'cv', \
58 'cym':'cy', 'dan':'da', 'deu':'de', 'div':'dv', 'dzo':'dz', 'ewe':'ee', \
59 'ell':'el', 'epo':'eo', 'spa':'es', 'est':'et', 'eus':'eu', 'fas':'fa', \
60 'ful':'ff', 'fin':'fi', 'fij':'fj', 'fao':'fo', 'fry':'fy', 'gle':'ga', \
61 'gla':'gd', 'glg':'gl', 'grn':'gn', 'guj':'gu', 'glv':'gv', 'hau':'ha', \
62 'heb':'he', 'hin':'hi', 'hmo':'ho', 'hrv':'hr', 'hat':'ht', 'hun':'hu', \
63 'hye':'hy', 'her':'hz', 'ina':'ia', 'ind':'id', 'ile':'ie', 'ibo':'ig', \
64 'iii':'ii', 'ipk':'ik', 'ido':'io', 'isl':'is', 'ita':'it', 'iku':'iu', \
65 'jpn':'ja', 'jav':'jv', 'kat':'ka', 'kon':'kg', 'kik':'ki', 'kua':'kj', \
66 'kaz':'kk', 'kal':'kl', 'khm':'km', 'kan':'kn', 'kor':'ko', 'kau':'kr', \
67 'kas':'ks', 'kur':'ku', 'kom':'kv', 'cor':'kw', 'kir':'ky', 'lat':'la', \
68 'ltz':'lb', 'lug':'lg', 'lim':'li', 'lin':'ln', 'lao':'lo', 'lit':'lt', \
69 'lub':'lu', 'lav':'lv', 'mlg':'mg', 'mah':'mh', 'mri':'mi', 'mkd':'mk', \
70 'mal':'ml', 'mon':'mn', 'mar':'mr', 'msa':'ms', 'mlt':'mt', 'mya':'my', \
71 'nau':'na', 'nob':'nb', 'nde':'nd', 'nep':'ne', 'ndo':'ng', 'nld':'nl', \
72 'nno':'nn', 'nor':'no', 'nbl':'nr', 'nav':'nv', 'nya':'ny', 'oci':'oc', \
73 'oji':'oj', 'orm':'om', 'ori':'or', 'oss':'os', 'pan':'pa', 'pli':'pi', \
74 'pol':'pl', 'pus':'ps', 'por':'pt', 'que':'qu', 'roh':'rm', 'run':'rn', \
75 'ron':'ro', 'rus':'ru', 'kin':'rw', 'san':'sa', 'srd':'sc', 'snd':'sd', \
76 'sme':'se', 'sag':'sg', 'sin':'si', 'slk':'sk', 'slv':'sl', 'smo':'sm', \
77 'sna':'sn', 'som':'so', 'sqi':'sq', 'srp':'sr', 'ssw':'ss', 'sot':'st', \
78 'sun':'su', 'swe':'sv', 'swa':'sw', 'tam':'ta', 'tel':'te', 'tgk':'tg', \
79 'tha':'th', 'tir':'ti', 'tuk':'tk', 'tgl':'tl', 'tsn':'tn', 'ton':'to', \
80 'tur':'tr', 'tso':'ts', 'tat':'tt', 'twi':'tw', 'tah':'ty', 'uig':'ug', \
81 'ukr':'uk', 'urd':'ur', 'uzb':'uz', 'ven':'ve', 'vie':'vi', 'vol':'vo', \
82 'wln':'wa', 'wol':'wo', 'xho':'xh', 'yid':'yi', 'yor':'yo', 'zha':'za', \
83 'zho':'zh', 'zul':'zu'}
84
85 ## Convert a python unicode string to a normal string
86 #
87 # Convert a python unicode string to a normal string
88 # UniToStr(u'I am a string') is 'I am a string'
89 #
90 # @param Uni: The python unicode string
91 #
92 # @retval: The formatted normal string
93 #
94 def UniToStr(Uni):
95 return repr(Uni)[2:-1]
96
97 ## Convert a unicode string to a Hex list
98 #
99 # Convert a unicode string to a Hex list
100 # UniToHexList('ABC') is ['0x41', '0x00', '0x42', '0x00', '0x43', '0x00']
101 #
102 # @param Uni: The python unicode string
103 #
104 # @retval List: The formatted hex list
105 #
106 def UniToHexList(Uni):
107 List = []
108 for Item in Uni:
109 Temp = '%04X' % ord(Item)
110 List.append('0x' + Temp[2:4])
111 List.append('0x' + Temp[0:2])
112 return List
113
114 ## Convert special unicode characters
115 #
116 # Convert special characters to (c), (r) and (tm).
117 #
118 # @param Uni: The python unicode string
119 #
120 # @retval NewUni: The converted unicode string
121 #
122 def ConvertSpecialUnicodes(Uni):
123 NewUni = Uni
124 NewUni = NewUni.replace(u'\u00A9', '(c)')
125 NewUni = NewUni.replace(u'\u00AE', '(r)')
126 NewUni = NewUni.replace(u'\u2122', '(tm)')
127 return NewUni
128
129 ## GetLanguageCode1766
130 #
131 # Check the language code read from .UNI file and convert RFC 4646 codes to RFC 1766 codes
132 # RFC 1766 language codes supported in compatiblity mode
133 # RFC 4646 language codes supported in native mode
134 #
135 # @param LangName: Language codes read from .UNI file
136 #
137 # @retval LangName: Valid lanugage code in RFC 1766 format or None
138 #
139 def GetLanguageCode1766(LangName, File=None):
140 return LangName
141
142 length = len(LangName)
143 if length == 2:
144 if LangName.isalpha():
145 for Key in gLANG_CONV_TABLE.keys():
146 if gLANG_CONV_TABLE.get(Key) == LangName.lower():
147 return Key
148 elif length == 3:
149 if LangName.isalpha() and gLANG_CONV_TABLE.get(LangName.lower()):
150 return LangName
151 else:
152 EdkLogger.Error("Unicode File Parser",
153 ToolError.FORMAT_INVALID,
154 "Invalid RFC 1766 language code : %s" % LangName,
155 File)
156 elif length == 5:
157 if LangName[0:2].isalpha() and LangName[2] == '-':
158 for Key in gLANG_CONV_TABLE.keys():
159 if gLANG_CONV_TABLE.get(Key) == LangName[0:2].lower():
160 return Key
161 elif length >= 6:
162 if LangName[0:2].isalpha() and LangName[2] == '-':
163 for Key in gLANG_CONV_TABLE.keys():
164 if gLANG_CONV_TABLE.get(Key) == LangName[0:2].lower():
165 return Key
166 if LangName[0:3].isalpha() and gLANG_CONV_TABLE.get(LangName.lower()) == None and LangName[3] == '-':
167 for Key in gLANG_CONV_TABLE.keys():
168 if Key == LangName[0:3].lower():
169 return Key
170
171 EdkLogger.Error("Unicode File Parser",
172 ToolError.FORMAT_INVALID,
173 "Invalid RFC 4646 language code : %s" % LangName,
174 File)
175
176 ## GetLanguageCode
177 #
178 # Check the language code read from .UNI file and convert RFC 1766 codes to RFC 4646 codes if appropriate
179 # RFC 1766 language codes supported in compatiblity mode
180 # RFC 4646 language codes supported in native mode
181 #
182 # @param LangName: Language codes read from .UNI file
183 #
184 # @retval LangName: Valid lanugage code in RFC 4646 format or None
185 #
186 def GetLanguageCode(LangName, IsCompatibleMode, File):
187 length = len(LangName)
188 if IsCompatibleMode:
189 if length == 3 and LangName.isalpha():
190 TempLangName = gLANG_CONV_TABLE.get(LangName.lower())
191 if TempLangName != None:
192 return TempLangName
193 return LangName
194 else:
195 EdkLogger.Error("Unicode File Parser",
196 ToolError.FORMAT_INVALID,
197 "Invalid RFC 1766 language code : %s" % LangName,
198 File)
199 if (LangName[0] == 'X' or LangName[0] == 'x') and LangName[1] == '-':
200 return LangName
201 if length == 2:
202 if LangName.isalpha():
203 return LangName
204 elif length == 3:
205 if LangName.isalpha() and gLANG_CONV_TABLE.get(LangName.lower()) == None:
206 return LangName
207 elif length == 5:
208 if LangName[0:2].isalpha() and LangName[2] == '-':
209 return LangName
210 elif length >= 6:
211 if LangName[0:2].isalpha() and LangName[2] == '-':
212 return LangName
213 if LangName[0:3].isalpha() and gLANG_CONV_TABLE.get(LangName.lower()) == None and LangName[3] == '-':
214 return LangName
215
216 EdkLogger.Error("Unicode File Parser",
217 ToolError.FORMAT_INVALID,
218 "Invalid RFC 4646 language code : %s" % LangName,
219 File)
220
221 ## FormatUniEntry
222 #
223 # Formated the entry in Uni file.
224 #
225 # @param StrTokenName StrTokenName.
226 # @param TokenValueList A list need to be processed.
227 # @param ContainerFile ContainerFile.
228 #
229 # @return formated entry
230 def FormatUniEntry(StrTokenName, TokenValueList, ContainerFile):
231 SubContent = ''
232 PreFormatLength = 40
233 if len(StrTokenName) > PreFormatLength:
234 PreFormatLength = len(StrTokenName) + 1
235 for (Lang, Value) in TokenValueList:
236 if not Value or Lang == DT.TAB_LANGUAGE_EN_X:
237 continue
238 if Lang == '':
239 Lang = DT.TAB_LANGUAGE_EN_US
240 if Lang == 'eng':
241 Lang = DT.TAB_LANGUAGE_EN_US
242 elif len(Lang.split('-')[0]) == 3:
243 Lang = GetLanguageCode(Lang.split('-')[0], True, ContainerFile)
244 else:
245 Lang = GetLanguageCode(Lang, False, ContainerFile)
246 ValueList = Value.split('\n')
247 SubValueContent = ''
248 for SubValue in ValueList:
249 if SubValue.strip():
250 SubValueContent += \
251 ' ' * (PreFormatLength + len('#language en-US ')) + '\"%s\\n\"' % SubValue.strip() + '\r\n'
252 SubValueContent = SubValueContent[(PreFormatLength + len('#language en-US ')):SubValueContent.rfind('\\n')] \
253 + '\"' + '\r\n'
254 SubContent += ' '*PreFormatLength + '#language %-5s ' % Lang + SubValueContent
255 if SubContent:
256 SubContent = StrTokenName + ' '*(PreFormatLength - len(StrTokenName)) + SubContent[PreFormatLength:]
257 return SubContent
258
259
260 ## StringDefClassObject
261 #
262 # A structure for language definition
263 #
264 class StringDefClassObject(object):
265 def __init__(self, Name = None, Value = None, Referenced = False, Token = None, UseOtherLangDef = ''):
266 self.StringName = ''
267 self.StringNameByteList = []
268 self.StringValue = ''
269 self.StringValueByteList = ''
270 self.Token = 0
271 self.Referenced = Referenced
272 self.UseOtherLangDef = UseOtherLangDef
273 self.Length = 0
274
275 if Name != None:
276 self.StringName = Name
277 self.StringNameByteList = UniToHexList(Name)
278 if Value != None:
279 self.StringValue = Value
280 self.StringValueByteList = UniToHexList(self.StringValue)
281 self.Length = len(self.StringValueByteList)
282 if Token != None:
283 self.Token = Token
284
285 def __str__(self):
286 return repr(self.StringName) + ' ' + \
287 repr(self.Token) + ' ' + \
288 repr(self.Referenced) + ' ' + \
289 repr(self.StringValue) + ' ' + \
290 repr(self.UseOtherLangDef)
291
292 def UpdateValue(self, Value = None):
293 if Value != None:
294 if self.StringValue:
295 self.StringValue = self.StringValue + '\r\n' + Value
296 else:
297 self.StringValue = Value
298 self.StringValueByteList = UniToHexList(self.StringValue)
299 self.Length = len(self.StringValueByteList)
300
301 ## UniFileClassObject
302 #
303 # A structure for .uni file definition
304 #
305 class UniFileClassObject(object):
306 def __init__(self, FileList = None, IsCompatibleMode = False, IncludePathList = None):
307 self.FileList = FileList
308 self.File = None
309 self.IncFileList = FileList
310 self.UniFileHeader = ''
311 self.Token = 2
312 self.LanguageDef = [] #[ [u'LanguageIdentifier', u'PrintableName'], ... ]
313 self.OrderedStringList = {} #{ u'LanguageIdentifier' : [StringDefClassObject] }
314 self.OrderedStringDict = {} #{ u'LanguageIdentifier' : {StringName:(IndexInList)} }
315 self.OrderedStringListByToken = {} #{ u'LanguageIdentifier' : {Token: StringDefClassObject} }
316 self.IsCompatibleMode = IsCompatibleMode
317 if not IncludePathList:
318 self.IncludePathList = []
319 else:
320 self.IncludePathList = IncludePathList
321 if len(self.FileList) > 0:
322 self.LoadUniFiles(FileList)
323
324 #
325 # Get Language definition
326 #
327 def GetLangDef(self, File, Line):
328 Lang = distutils.util.split_quoted((Line.split(u"//")[0]))
329 if len(Lang) != 3:
330 try:
331 FileIn = codecs.open(File.Path, mode='rb', encoding='utf_8').read()
332 except UnicodeError, Xstr:
333 FileIn = codecs.open(File.Path, mode='rb', encoding='utf_16').read()
334 except UnicodeError, Xstr:
335 FileIn = codecs.open(File.Path, mode='rb', encoding='utf_16_le').read()
336 except:
337 EdkLogger.Error("Unicode File Parser",
338 ToolError.FILE_OPEN_FAILURE,
339 "File read failure: %s" % str(Xstr),
340 ExtraData=File)
341 LineNo = GetLineNo(FileIn, Line, False)
342 EdkLogger.Error("Unicode File Parser",
343 ToolError.PARSER_ERROR,
344 "Wrong language definition",
345 ExtraData="""%s\n\t*Correct format is like '#langdef en-US "English"'""" % Line,
346 File = File, Line = LineNo)
347 else:
348 LangName = GetLanguageCode(Lang[1], self.IsCompatibleMode, self.File)
349 LangPrintName = Lang[2]
350
351 IsLangInDef = False
352 for Item in self.LanguageDef:
353 if Item[0] == LangName:
354 IsLangInDef = True
355 break
356
357 if not IsLangInDef:
358 self.LanguageDef.append([LangName, LangPrintName])
359
360 #
361 # Add language string
362 #
363 self.AddStringToList(u'$LANGUAGE_NAME', LangName, LangName, 0, True, Index=0)
364 self.AddStringToList(u'$PRINTABLE_LANGUAGE_NAME', LangName, LangPrintName, 1, True, Index=1)
365
366 if not IsLangInDef:
367 #
368 # The found STRING tokens will be added into new language string list
369 # so that the unique STRING identifier is reserved for all languages in the package list.
370 #
371 FirstLangName = self.LanguageDef[0][0]
372 if LangName != FirstLangName:
373 for Index in range (2, len (self.OrderedStringList[FirstLangName])):
374 Item = self.OrderedStringList[FirstLangName][Index]
375 if Item.UseOtherLangDef != '':
376 OtherLang = Item.UseOtherLangDef
377 else:
378 OtherLang = FirstLangName
379 self.OrderedStringList[LangName].append (StringDefClassObject(Item.StringName,
380 '',
381 Item.Referenced,
382 Item.Token,
383 OtherLang))
384 self.OrderedStringDict[LangName][Item.StringName] = len(self.OrderedStringList[LangName]) - 1
385 return True
386
387 #
388 # Get String name and value
389 #
390 def GetStringObject(self, Item):
391 Language = ''
392 Value = ''
393
394 Name = Item.split()[1]
395 # Check the string name is the upper character
396 if Name != '':
397 MatchString = re.match('[A-Z0-9_]+', Name, re.UNICODE)
398 if MatchString == None or MatchString.end(0) != len(Name):
399 EdkLogger.Error("Unicode File Parser",
400 ToolError.FORMAT_INVALID,
401 'The string token name %s in UNI file %s must be upper case character.' %(Name, self.File))
402 LanguageList = Item.split(u'#language ')
403 for IndexI in range(len(LanguageList)):
404 if IndexI == 0:
405 continue
406 else:
407 Language = LanguageList[IndexI].split()[0]
408 #.replace(u'\r\n', u'')
409 Value = \
410 LanguageList[IndexI][LanguageList[IndexI].find(u'\"') + len(u'\"') : LanguageList[IndexI].rfind(u'\"')]
411 Language = GetLanguageCode(Language, self.IsCompatibleMode, self.File)
412 self.AddStringToList(Name, Language, Value)
413
414 #
415 # Get include file list and load them
416 #
417 def GetIncludeFile(self, Item, Dir = None):
418 if Dir:
419 pass
420 FileName = Item[Item.find(u'!include ') + len(u'!include ') :Item.find(u' ', len(u'!include '))][1:-1]
421 self.LoadUniFile(FileName)
422
423 #
424 # Pre-process before parse .uni file
425 #
426 def PreProcess(self, File, IsIncludeFile=False):
427 if not os.path.exists(File.Path) or not os.path.isfile(File.Path):
428 EdkLogger.Error("Unicode File Parser",
429 ToolError.FILE_NOT_FOUND,
430 ExtraData=File.Path)
431
432 #
433 # Check file header of the Uni file
434 #
435 # if not CheckUTF16FileHeader(File.Path):
436 # EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID,
437 # ExtraData='The file %s is either invalid UTF-16LE or it is missing the BOM.' % File.Path)
438
439 try:
440 FileIn = codecs.open(File.Path, mode='rb', encoding='utf_8').read()
441 except UnicodeError, Xstr:
442 FileIn = codecs.open(File.Path, mode='rb', encoding='utf_16').readlines()
443 except UnicodeError:
444 FileIn = codecs.open(File.Path, mode='rb', encoding='utf_16_le').readlines()
445 except:
446 EdkLogger.Error("Unicode File Parser", ToolError.FILE_OPEN_FAILURE, ExtraData=File.Path)
447
448
449 #
450 # get the file header
451 #
452 Lines = []
453 HeaderStart = False
454 HeaderEnd = False
455 if not self.UniFileHeader:
456 FirstGenHeader = True
457 else:
458 FirstGenHeader = False
459 for Line in FileIn:
460 Line = Line.strip()
461 if Line == u'':
462 continue
463 if Line.startswith(DT.TAB_COMMENT_EDK1_SPLIT) and (Line.find(DT.TAB_HEADER_COMMENT) > -1) \
464 and not HeaderEnd and not HeaderStart:
465 HeaderStart = True
466 if not Line.startswith(DT.TAB_COMMENT_EDK1_SPLIT) and HeaderStart and not HeaderEnd:
467 HeaderEnd = True
468 if Line.startswith(DT.TAB_COMMENT_EDK1_SPLIT) and HeaderStart and not HeaderEnd and FirstGenHeader:
469 self.UniFileHeader += Line + '\r\n'
470 continue
471
472 #
473 # Use unique identifier
474 #
475 FindFlag = -1
476 LineCount = 0
477 MultiLineFeedExits = False
478 #
479 # 0: initial value
480 # 1: signle String entry exist
481 # 2: line feed exist under the some signle String entry
482 #
483 StringEntryExistsFlag = 0
484 for Line in FileIn:
485 Line = FileIn[LineCount]
486 LineCount += 1
487 Line = Line.strip()
488 #
489 # Ignore comment line and empty line
490 #
491 if Line == u'' or Line.startswith(u'//'):
492 #
493 # Change the single line String entry flag status
494 #
495 if StringEntryExistsFlag == 1:
496 StringEntryExistsFlag = 2
497 #
498 # If the '#string' line and the '#language' line are not in the same line,
499 # there should be only one line feed character betwwen them
500 #
501 if MultiLineFeedExits:
502 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)
503 continue
504
505 MultiLineFeedExits = False
506 #
507 # Process comment embeded in string define lines
508 #
509 FindFlag = Line.find(u'//')
510 if FindFlag != -1 and Line.find(u'//') < Line.find(u'"'):
511 Line = Line.replace(Line[FindFlag:], u' ')
512 if FileIn[LineCount].strip().startswith('#language'):
513 Line = Line + FileIn[LineCount]
514 FileIn[LineCount-1] = Line
515 FileIn[LineCount] = '\r\n'
516 LineCount -= 1
517 for Index in xrange (LineCount + 1, len (FileIn) - 1):
518 if (Index == len(FileIn) -1):
519 FileIn[Index] = '\r\n'
520 else:
521 FileIn[Index] = FileIn[Index + 1]
522 continue
523 CommIndex = GetCharIndexOutStr(u'/', Line)
524 if CommIndex > -1:
525 if (len(Line) - 1) > CommIndex:
526 if Line[CommIndex+1] == u'/':
527 Line = Line[:CommIndex].strip()
528 else:
529 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)
530 else:
531 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)
532
533 Line = Line.replace(UNICODE_WIDE_CHAR, WIDE_CHAR)
534 Line = Line.replace(UNICODE_NARROW_CHAR, NARROW_CHAR)
535 Line = Line.replace(UNICODE_NON_BREAKING_CHAR, NON_BREAKING_CHAR)
536
537 Line = Line.replace(u'\\\\', u'\u0006')
538 Line = Line.replace(u'\\r\\n', CR + LF)
539 Line = Line.replace(u'\\n', CR + LF)
540 Line = Line.replace(u'\\r', CR)
541 Line = Line.replace(u'\\t', u'\t')
542 Line = Line.replace(u'''\"''', u'''"''')
543 Line = Line.replace(u'\t', u' ')
544 Line = Line.replace(u'\u0006', u'\\')
545
546 # IncList = gINCLUDE_PATTERN.findall(Line)
547 IncList = []
548 if len(IncList) == 1:
549 for Dir in [File.Dir] + self.IncludePathList:
550 IncFile = PathClass(str(IncList[0]), Dir)
551 self.IncFileList.append(IncFile)
552 if os.path.isfile(IncFile.Path):
553 Lines.extend(self.PreProcess(IncFile, True))
554 break
555 else:
556 EdkLogger.Error("Unicode File Parser",
557 ToolError.FILE_NOT_FOUND,
558 Message="Cannot find include file",
559 ExtraData=str(IncList[0]))
560 continue
561
562 #
563 # Between Name entry and Language entry can not contain line feed
564 #
565 if Line.startswith(u'#string') and Line.find(u'#language') == -1:
566 MultiLineFeedExits = True
567
568 if Line.startswith(u'#string') and Line.find(u'#language') > 0 and Line.find(u'"') < 0:
569 MultiLineFeedExits = True
570
571 #
572 # Between Language entry and String entry can not contain line feed
573 #
574 if Line.startswith(u'#language') and len(Line.split()) == 2:
575 MultiLineFeedExits = True
576
577 #
578 # Between two String entry, can not contain line feed
579 #
580 if Line.startswith(u'"'):
581 if StringEntryExistsFlag == 2:
582 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID,
583 Message=ST.ERR_UNIPARSE_LINEFEED_UP_EXIST % Line, ExtraData=File.Path)
584
585 StringEntryExistsFlag = 1
586 if not Line.endswith('"'):
587 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID,
588 ExtraData='''The line %s misses '"' at the end of it in file %s'''
589 % (LineCount, File.Path))
590 elif Line.startswith(u'#language'):
591 if StringEntryExistsFlag == 2:
592 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID,
593 Message=ST.ERR_UNI_MISS_STRING_ENTRY % Line, ExtraData=File.Path)
594 StringEntryExistsFlag = 0
595 else:
596 StringEntryExistsFlag = 0
597
598 Lines.append(Line)
599
600 #
601 # Convert string def format as below
602 #
603 # #string MY_STRING_1
604 # #language eng
605 # "My first English string line 1"
606 # "My first English string line 2"
607 # #string MY_STRING_1
608 # #language spa
609 # "Mi segunda secuencia 1"
610 # "Mi segunda secuencia 2"
611 #
612
613 if not IsIncludeFile and not Lines:
614 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \
615 Message=ST.ERR_UNIPARSE_NO_SECTION_EXIST, \
616 ExtraData=File.Path)
617
618 NewLines = []
619 StrName = u''
620 ExistStrNameList = []
621 for Line in Lines:
622 if StrName and not StrName.split()[1].startswith(DT.TAB_STR_TOKENCNAME + DT.TAB_UNDERLINE_SPLIT):
623 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \
624 Message=ST.ERR_UNIPARSE_STRNAME_FORMAT_ERROR % StrName.split()[1], \
625 ExtraData=File.Path)
626
627 if StrName and len(StrName.split()[1].split(DT.TAB_UNDERLINE_SPLIT)) == 4:
628 StringTokenList = StrName.split()[1].split(DT.TAB_UNDERLINE_SPLIT)
629 if (StringTokenList[3].upper() in [DT.TAB_STR_TOKENPROMPT, DT.TAB_STR_TOKENHELP] and \
630 StringTokenList[3] not in [DT.TAB_STR_TOKENPROMPT, DT.TAB_STR_TOKENHELP]) or \
631 (StringTokenList[2].upper() == DT.TAB_STR_TOKENERR and StringTokenList[2] != DT.TAB_STR_TOKENERR):
632 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \
633 Message=ST.ERR_UNIPARSE_STRTOKEN_FORMAT_ERROR % StrName.split()[1], \
634 ExtraData=File.Path)
635
636 if Line.count(u'#language') > 1:
637 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \
638 Message=ST.ERR_UNIPARSE_SEP_LANGENTRY_LINE % Line, \
639 ExtraData=File.Path)
640
641 if Line.startswith(u'//'):
642 continue
643 elif Line.startswith(u'#langdef'):
644 if len(Line.split()) == 2:
645 NewLines.append(Line)
646 continue
647 elif len(Line.split()) > 2 and Line.find(u'"') > 0:
648 NewLines.append(Line[:Line.find(u'"')].strip())
649 NewLines.append(Line[Line.find(u'"'):])
650 else:
651 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)
652 elif Line.startswith(u'#string'):
653 if len(Line.split()) == 2:
654 StrName = Line
655 if StrName:
656 if StrName.split()[1] not in ExistStrNameList:
657 ExistStrNameList.append(StrName.split()[1].strip())
658 elif StrName.split()[1] in [DT.TAB_INF_ABSTRACT, DT.TAB_INF_DESCRIPTION, \
659 DT.TAB_INF_BINARY_ABSTRACT, DT.TAB_INF_BINARY_DESCRIPTION, \
660 DT.TAB_DEC_PACKAGE_ABSTRACT, DT.TAB_DEC_PACKAGE_DESCRIPTION, \
661 DT.TAB_DEC_BINARY_ABSTRACT, DT.TAB_DEC_BINARY_DESCRIPTION]:
662 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \
663 Message=ST.ERR_UNIPARSE_MULTI_ENTRY_EXIST % StrName.split()[1], \
664 ExtraData=File.Path)
665 continue
666 elif len(Line.split()) == 4 and Line.find(u'#language') > 0:
667 if Line[Line.find(u'#language')-1] != ' ' or \
668 Line[Line.find(u'#language')+len(u'#language')] != u' ':
669 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)
670
671 if Line.find(u'"') > 0:
672 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)
673
674 StrName = Line.split()[0] + u' ' + Line.split()[1]
675 if StrName:
676 if StrName.split()[1] not in ExistStrNameList:
677 ExistStrNameList.append(StrName.split()[1].strip())
678 elif StrName.split()[1] in [DT.TAB_INF_ABSTRACT, DT.TAB_INF_DESCRIPTION, \
679 DT.TAB_INF_BINARY_ABSTRACT, DT.TAB_INF_BINARY_DESCRIPTION, \
680 DT.TAB_DEC_PACKAGE_ABSTRACT, DT.TAB_DEC_PACKAGE_DESCRIPTION, \
681 DT.TAB_DEC_BINARY_ABSTRACT, DT.TAB_DEC_BINARY_DESCRIPTION]:
682 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \
683 Message=ST.ERR_UNIPARSE_MULTI_ENTRY_EXIST % StrName.split()[1], \
684 ExtraData=File.Path)
685 if IsIncludeFile:
686 if StrName not in NewLines:
687 NewLines.append((Line[:Line.find(u'#language')]).strip())
688 else:
689 NewLines.append((Line[:Line.find(u'#language')]).strip())
690 NewLines.append((Line[Line.find(u'#language'):]).strip())
691 elif len(Line.split()) > 4 and Line.find(u'#language') > 0 and Line.find(u'"') > 0:
692 if Line[Line.find(u'#language')-1] != u' ' or \
693 Line[Line.find(u'#language')+len(u'#language')] != u' ':
694 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)
695
696 if Line[Line.find(u'"')-1] != u' ':
697 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)
698
699 StrName = Line.split()[0] + u' ' + Line.split()[1]
700 if StrName:
701 if StrName.split()[1] not in ExistStrNameList:
702 ExistStrNameList.append(StrName.split()[1].strip())
703 elif StrName.split()[1] in [DT.TAB_INF_ABSTRACT, DT.TAB_INF_DESCRIPTION, \
704 DT.TAB_INF_BINARY_ABSTRACT, DT.TAB_INF_BINARY_DESCRIPTION, \
705 DT.TAB_DEC_PACKAGE_ABSTRACT, DT.TAB_DEC_PACKAGE_DESCRIPTION, \
706 DT.TAB_DEC_BINARY_ABSTRACT, DT.TAB_DEC_BINARY_DESCRIPTION]:
707 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \
708 Message=ST.ERR_UNIPARSE_MULTI_ENTRY_EXIST % StrName.split()[1], \
709 ExtraData=File.Path)
710 if IsIncludeFile:
711 if StrName not in NewLines:
712 NewLines.append((Line[:Line.find(u'#language')]).strip())
713 else:
714 NewLines.append((Line[:Line.find(u'#language')]).strip())
715 NewLines.append((Line[Line.find(u'#language'):Line.find(u'"')]).strip())
716 NewLines.append((Line[Line.find(u'"'):]).strip())
717 else:
718 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)
719 elif Line.startswith(u'#language'):
720 if len(Line.split()) == 2:
721 if IsIncludeFile:
722 if StrName not in NewLines:
723 NewLines.append(StrName)
724 else:
725 NewLines.append(StrName)
726 NewLines.append(Line)
727 elif len(Line.split()) > 2 and Line.find(u'"') > 0:
728 if IsIncludeFile:
729 if StrName not in NewLines:
730 NewLines.append(StrName)
731 else:
732 NewLines.append(StrName)
733 NewLines.append((Line[:Line.find(u'"')]).strip())
734 NewLines.append((Line[Line.find(u'"'):]).strip())
735 else:
736 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)
737 elif Line.startswith(u'"'):
738 if u'#string' in Line or u'#language' in Line:
739 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)
740 NewLines.append(Line)
741 else:
742 print Line
743 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)
744
745 if StrName and not StrName.split()[1].startswith(u'STR_'):
746 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \
747 Message=ST.ERR_UNIPARSE_STRNAME_FORMAT_ERROR % StrName.split()[1], \
748 ExtraData=File.Path)
749
750 if StrName and not NewLines:
751 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \
752 Message=ST.ERR_UNI_MISS_LANGENTRY % StrName, \
753 ExtraData=File.Path)
754
755 #
756 # Check Abstract, Description, BinaryAbstract and BinaryDescription order,
757 # should be Abstract, Description, BinaryAbstract, BinaryDesctiption
758 AbstractPosition = -1
759 DescriptionPosition = -1
760 BinaryAbstractPosition = -1
761 BinaryDescriptionPosition = -1
762 for StrName in ExistStrNameList:
763 if DT.TAB_HEADER_ABSTRACT.upper() in StrName:
764 if 'BINARY' in StrName:
765 BinaryAbstractPosition = ExistStrNameList.index(StrName)
766 else:
767 AbstractPosition = ExistStrNameList.index(StrName)
768 if DT.TAB_HEADER_DESCRIPTION.upper() in StrName:
769 if 'BINARY' in StrName:
770 BinaryDescriptionPosition = ExistStrNameList.index(StrName)
771 else:
772 DescriptionPosition = ExistStrNameList.index(StrName)
773
774 OrderList = sorted([AbstractPosition, DescriptionPosition])
775 BinaryOrderList = sorted([BinaryAbstractPosition, BinaryDescriptionPosition])
776 Min = OrderList[0]
777 Max = OrderList[1]
778 BinaryMin = BinaryOrderList[0]
779 BinaryMax = BinaryOrderList[1]
780 if BinaryDescriptionPosition > -1:
781 if not(BinaryDescriptionPosition == BinaryMax and BinaryAbstractPosition == BinaryMin and \
782 BinaryMax > Max):
783 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \
784 Message=ST.ERR_UNIPARSE_ENTRY_ORDER_WRONG, \
785 ExtraData=File.Path)
786 elif BinaryAbstractPosition > -1:
787 if not(BinaryAbstractPosition > Max):
788 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \
789 Message=ST.ERR_UNIPARSE_ENTRY_ORDER_WRONG, \
790 ExtraData=File.Path)
791
792 if DescriptionPosition > -1:
793 if not(DescriptionPosition == Max and AbstractPosition == Min and \
794 DescriptionPosition > AbstractPosition):
795 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \
796 Message=ST.ERR_UNIPARSE_ENTRY_ORDER_WRONG, \
797 ExtraData=File.Path)
798
799 if not self.UniFileHeader:
800 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID,
801 Message = ST.ERR_NO_SOURCE_HEADER,
802 ExtraData=File.Path)
803
804 return NewLines
805
806 #
807 # Load a .uni file
808 #
809 def LoadUniFile(self, File = None):
810 if File == None:
811 EdkLogger.Error("Unicode File Parser",
812 ToolError.PARSER_ERROR,
813 Message='No unicode file is given',
814 ExtraData=File.Path)
815
816 self.File = File
817
818 #
819 # Process special char in file
820 #
821 Lines = self.PreProcess(File)
822
823 #
824 # Get Unicode Information
825 #
826 for IndexI in range(len(Lines)):
827 Line = Lines[IndexI]
828 if (IndexI + 1) < len(Lines):
829 SecondLine = Lines[IndexI + 1]
830 if (IndexI + 2) < len(Lines):
831 ThirdLine = Lines[IndexI + 2]
832
833 #
834 # Get Language def information
835 #
836 if Line.find(u'#langdef ') >= 0:
837 self.GetLangDef(File, Line + u' ' + SecondLine)
838 continue
839
840 Name = ''
841 Language = ''
842 Value = ''
843 CombineToken = False
844 #
845 # Get string def information format as below
846 #
847 # #string MY_STRING_1
848 # #language eng
849 # "My first English string line 1"
850 # "My first English string line 2"
851 # #string MY_STRING_1
852 # #language spa
853 # "Mi segunda secuencia 1"
854 # "Mi segunda secuencia 2"
855 #
856 if Line.find(u'#string ') >= 0 and Line.find(u'#language ') < 0 and \
857 SecondLine.find(u'#string ') < 0 and SecondLine.find(u'#language ') >= 0 and \
858 ThirdLine.find(u'#string ') < 0 and ThirdLine.find(u'#language ') < 0:
859 if Line.find('"') > 0 or SecondLine.find('"') > 0:
860 EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID,
861 Message=ST.ERR_UNIPARSE_DBLQUOTE_UNMATCHED,
862 ExtraData=File.Path)
863
864 Name = Line[Line.find(u'#string ') + len(u'#string ') : ].strip(' ')
865 Language = SecondLine[SecondLine.find(u'#language ') + len(u'#language ') : ].strip(' ')
866 for IndexJ in range(IndexI + 2, len(Lines)):
867 if Lines[IndexJ].find(u'#string ') < 0 and Lines[IndexJ].find(u'#language ') < 0 and \
868 Lines[IndexJ].strip().startswith(u'"') and Lines[IndexJ].strip().endswith(u'"'):
869 if Lines[IndexJ][-2] == ' ':
870 CombineToken = True
871 if CombineToken:
872 if Lines[IndexJ].strip()[1:-1].strip():
873 Value = Value + Lines[IndexJ].strip()[1:-1].rstrip() + ' '
874 else:
875 Value = Value + Lines[IndexJ].strip()[1:-1]
876 CombineToken = False
877 else:
878 Value = Value + Lines[IndexJ].strip()[1:-1] + '\r\n'
879 else:
880 IndexI = IndexJ
881 break
882 if Value.endswith('\r\n'):
883 Value = Value[: Value.rfind('\r\n')]
884 Language = GetLanguageCode(Language, self.IsCompatibleMode, self.File)
885 self.AddStringToList(Name, Language, Value)
886 continue
887
888 #
889 # Load multiple .uni files
890 #
891 def LoadUniFiles(self, FileList):
892 if len(FileList) > 0:
893 for File in FileList:
894 FilePath = File.Path.strip()
895 if FilePath.endswith('.uni') or FilePath.endswith('.UNI') or FilePath.endswith('.Uni'):
896 self.LoadUniFile(File)
897
898 #
899 # Add a string to list
900 #
901 def AddStringToList(self, Name, Language, Value, Token = 0, Referenced = False, UseOtherLangDef = '', Index = -1):
902 for LangNameItem in self.LanguageDef:
903 if Language == LangNameItem[0]:
904 break
905
906 if Language not in self.OrderedStringList:
907 self.OrderedStringList[Language] = []
908 self.OrderedStringDict[Language] = {}
909
910 IsAdded = True
911 if Name in self.OrderedStringDict[Language]:
912 IsAdded = False
913 if Value != None:
914 ItemIndexInList = self.OrderedStringDict[Language][Name]
915 Item = self.OrderedStringList[Language][ItemIndexInList]
916 Item.UpdateValue(Value)
917 Item.UseOtherLangDef = ''
918
919 if IsAdded:
920 Token = len(self.OrderedStringList[Language])
921 if Index == -1:
922 self.OrderedStringList[Language].append(StringDefClassObject(Name,
923 Value,
924 Referenced,
925 Token,
926 UseOtherLangDef))
927 self.OrderedStringDict[Language][Name] = Token
928 for LangName in self.LanguageDef:
929 #
930 # New STRING token will be added into all language string lists.
931 # so that the unique STRING identifier is reserved for all languages in the package list.
932 #
933 if LangName[0] != Language:
934 if UseOtherLangDef != '':
935 OtherLangDef = UseOtherLangDef
936 else:
937 OtherLangDef = Language
938 self.OrderedStringList[LangName[0]].append(StringDefClassObject(Name,
939 '',
940 Referenced,
941 Token,
942 OtherLangDef))
943 self.OrderedStringDict[LangName[0]][Name] = len(self.OrderedStringList[LangName[0]]) - 1
944 else:
945 self.OrderedStringList[Language].insert(Index, StringDefClassObject(Name,
946 Value,
947 Referenced,
948 Token,
949 UseOtherLangDef))
950 self.OrderedStringDict[Language][Name] = Index
951
952 #
953 # Set the string as referenced
954 #
955 def SetStringReferenced(self, Name):
956 #
957 # String stoken are added in the same order in all language string lists.
958 # So, only update the status of string stoken in first language string list.
959 #
960 Lang = self.LanguageDef[0][0]
961 if Name in self.OrderedStringDict[Lang]:
962 ItemIndexInList = self.OrderedStringDict[Lang][Name]
963 Item = self.OrderedStringList[Lang][ItemIndexInList]
964 Item.Referenced = True
965
966 #
967 # Search the string in language definition by Name
968 #
969 def FindStringValue(self, Name, Lang):
970 if Name in self.OrderedStringDict[Lang]:
971 ItemIndexInList = self.OrderedStringDict[Lang][Name]
972 return self.OrderedStringList[Lang][ItemIndexInList]
973
974 return None
975
976 #
977 # Search the string in language definition by Token
978 #
979 def FindByToken(self, Token, Lang):
980 for Item in self.OrderedStringList[Lang]:
981 if Item.Token == Token:
982 return Item
983
984 return None
985
986 #
987 # Re-order strings and re-generate tokens
988 #
989 def ReToken(self):
990 if len(self.LanguageDef) == 0:
991 return None
992 #
993 # Retoken all language strings according to the status of string stoken in the first language string.
994 #
995 FirstLangName = self.LanguageDef[0][0]
996
997 # Convert the OrderedStringList to be OrderedStringListByToken in order to faciliate future search by token
998 for LangNameItem in self.LanguageDef:
999 self.OrderedStringListByToken[LangNameItem[0]] = {}
1000
1001 #
1002 # Use small token for all referred string stoken.
1003 #
1004 RefToken = 0
1005 for Index in range (0, len (self.OrderedStringList[FirstLangName])):
1006 FirstLangItem = self.OrderedStringList[FirstLangName][Index]
1007 if FirstLangItem.Referenced == True:
1008 for LangNameItem in self.LanguageDef:
1009 LangName = LangNameItem[0]
1010 OtherLangItem = self.OrderedStringList[LangName][Index]
1011 OtherLangItem.Referenced = True
1012 OtherLangItem.Token = RefToken
1013 self.OrderedStringListByToken[LangName][OtherLangItem.Token] = OtherLangItem
1014 RefToken = RefToken + 1
1015
1016 #
1017 # Use big token for all unreferred string stoken.
1018 #
1019 UnRefToken = 0
1020 for Index in range (0, len (self.OrderedStringList[FirstLangName])):
1021 FirstLangItem = self.OrderedStringList[FirstLangName][Index]
1022 if FirstLangItem.Referenced == False:
1023 for LangNameItem in self.LanguageDef:
1024 LangName = LangNameItem[0]
1025 OtherLangItem = self.OrderedStringList[LangName][Index]
1026 OtherLangItem.Token = RefToken + UnRefToken
1027 self.OrderedStringListByToken[LangName][OtherLangItem.Token] = OtherLangItem
1028 UnRefToken = UnRefToken + 1
1029
1030 #
1031 # Show the instance itself
1032 #
1033 def ShowMe(self):
1034 print self.LanguageDef
1035 #print self.OrderedStringList
1036 for Item in self.OrderedStringList:
1037 print Item
1038 for Member in self.OrderedStringList[Item]:
1039 print str(Member)
1040
1041 #
1042 # Read content from '!include' UNI file
1043 #
1044 def ReadIncludeUNIfile(self, FilaPath):
1045 if self.File:
1046 pass
1047
1048 if not os.path.exists(FilaPath) or not os.path.isfile(FilaPath):
1049 EdkLogger.Error("Unicode File Parser",
1050 ToolError.FILE_NOT_FOUND,
1051 ExtraData=FilaPath)
1052 try:
1053 FileIn = codecs.open(FilaPath, mode='rb', encoding='utf_8').read()
1054 except UnicodeError, Xstr:
1055 FileIn = codecs.open(FilaPath, mode='rb', encoding='utf_16').readlines()
1056 except UnicodeError:
1057 FileIn = codecs.open(FilaPath, mode='rb', encoding='utf_16_le').readlines()
1058 except:
1059 EdkLogger.Error("Unicode File Parser", ToolError.FILE_OPEN_FAILURE, ExtraData=FilaPath)
1060 return FileIn
1061