projects / mirror_edk2.git / blame
| Commit | Line | Data |
|---|---|---|
| 421ccda3 HC |
1 | ## @file\r |
| 2 | # Collect all defined strings in multiple uni files.\r | |
| 3 | #\r | |
| b3fa393f | 4 | # Copyright (c) 2014 - 2018, Intel Corporation. All rights reserved.<BR>\r |
| 421ccda3 | 5 | #\r |
| f7496d71 LG |
6 | # This program and the accompanying materials are licensed and made available\r |
| 7 | # under the terms and conditions of the BSD License which accompanies this\r | |
| 8 | # distribution. The full text of the license may be found at\r | |
| 421ccda3 HC |
9 | # http://opensource.org/licenses/bsd-license.php\r |
| 10 | #\r | |
| 11 | # THE PROGRAM IS DISTRIBUTED UNDER THE BSD LICENSE ON AN "AS IS" BASIS,\r | |
| 12 | # WITHOUT WARRANTIES OR REPRESENTATIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED.\r | |
| 13 | #\r | |
| 14 | """\r | |
| 15 | Collect all defined strings in multiple uni files\r | |
| 16 | """\r | |
| 1ccc4d89 | 17 | from __future__ import print_function\r |
| 421ccda3 HC |
18 | \r |
| 19 | ##\r | |
| 20 | # Import Modules\r | |
| 21 | #\r | |
| 22 | import os, codecs, re\r | |
| 23 | import distutils.util\r | |
| 24 | from Logger import ToolError\r | |
| 25 | from Logger import Log as EdkLogger\r | |
| 26 | from Logger import StringTable as ST\r | |
| 64285f15 | 27 | from Library.StringUtils import GetLineNo\r |
| 421ccda3 HC |
28 | from Library.Misc import PathClass\r |
| 29 | from Library.Misc import GetCharIndexOutStr\r | |
| 30 | from Library import DataType as DT\r | |
| fe90f483 | 31 | from Library.ParserValidate import CheckUTF16FileHeader\r |
| 421ccda3 HC |
32 | \r |
| 33 | ##\r | |
| 34 | # Static definitions\r | |
| 35 | #\r | |
| 36 | UNICODE_WIDE_CHAR = u'\\wide'\r | |
| 37 | UNICODE_NARROW_CHAR = u'\\narrow'\r | |
| 38 | UNICODE_NON_BREAKING_CHAR = u'\\nbr'\r | |
| 39 | UNICODE_UNICODE_CR = '\r'\r | |
| 40 | UNICODE_UNICODE_LF = '\n'\r | |
| 41 | \r | |
| 42 | NARROW_CHAR = u'\uFFF0'\r | |
| 43 | WIDE_CHAR = u'\uFFF1'\r | |
| 44 | NON_BREAKING_CHAR = u'\uFFF2'\r | |
| 45 | CR = u'\u000D'\r | |
| 46 | LF = u'\u000A'\r | |
| 47 | NULL = u'\u0000'\r | |
| 48 | TAB = u'\t'\r | |
| 49 | BACK_SPLASH = u'\\'\r | |
| 50 | \r | |
| 421ccda3 HC |
51 | gLANG_CONV_TABLE = {'eng':'en', 'fra':'fr', \\r |
| 52 | 'aar':'aa', 'abk':'ab', 'ave':'ae', 'afr':'af', 'aka':'ak', 'amh':'am', \\r | |
| 53 | 'arg':'an', 'ara':'ar', 'asm':'as', 'ava':'av', 'aym':'ay', 'aze':'az', \\r | |
| 54 | 'bak':'ba', 'bel':'be', 'bul':'bg', 'bih':'bh', 'bis':'bi', 'bam':'bm', \\r | |
| 55 | 'ben':'bn', 'bod':'bo', 'bre':'br', 'bos':'bs', 'cat':'ca', 'che':'ce', \\r | |
| 56 | 'cha':'ch', 'cos':'co', 'cre':'cr', 'ces':'cs', 'chu':'cu', 'chv':'cv', \\r | |
| 57 | 'cym':'cy', 'dan':'da', 'deu':'de', 'div':'dv', 'dzo':'dz', 'ewe':'ee', \\r | |
| 58 | 'ell':'el', 'epo':'eo', 'spa':'es', 'est':'et', 'eus':'eu', 'fas':'fa', \\r | |
| 59 | 'ful':'ff', 'fin':'fi', 'fij':'fj', 'fao':'fo', 'fry':'fy', 'gle':'ga', \\r | |
| 60 | 'gla':'gd', 'glg':'gl', 'grn':'gn', 'guj':'gu', 'glv':'gv', 'hau':'ha', \\r | |
| 61 | 'heb':'he', 'hin':'hi', 'hmo':'ho', 'hrv':'hr', 'hat':'ht', 'hun':'hu', \\r | |
| 62 | 'hye':'hy', 'her':'hz', 'ina':'ia', 'ind':'id', 'ile':'ie', 'ibo':'ig', \\r | |
| 63 | 'iii':'ii', 'ipk':'ik', 'ido':'io', 'isl':'is', 'ita':'it', 'iku':'iu', \\r | |
| 64 | 'jpn':'ja', 'jav':'jv', 'kat':'ka', 'kon':'kg', 'kik':'ki', 'kua':'kj', \\r | |
| 65 | 'kaz':'kk', 'kal':'kl', 'khm':'km', 'kan':'kn', 'kor':'ko', 'kau':'kr', \\r | |
| 66 | 'kas':'ks', 'kur':'ku', 'kom':'kv', 'cor':'kw', 'kir':'ky', 'lat':'la', \\r | |
| 67 | 'ltz':'lb', 'lug':'lg', 'lim':'li', 'lin':'ln', 'lao':'lo', 'lit':'lt', \\r | |
| 68 | 'lub':'lu', 'lav':'lv', 'mlg':'mg', 'mah':'mh', 'mri':'mi', 'mkd':'mk', \\r | |
| 69 | 'mal':'ml', 'mon':'mn', 'mar':'mr', 'msa':'ms', 'mlt':'mt', 'mya':'my', \\r | |
| 70 | 'nau':'na', 'nob':'nb', 'nde':'nd', 'nep':'ne', 'ndo':'ng', 'nld':'nl', \\r | |
| 71 | 'nno':'nn', 'nor':'no', 'nbl':'nr', 'nav':'nv', 'nya':'ny', 'oci':'oc', \\r | |
| 72 | 'oji':'oj', 'orm':'om', 'ori':'or', 'oss':'os', 'pan':'pa', 'pli':'pi', \\r | |
| 73 | 'pol':'pl', 'pus':'ps', 'por':'pt', 'que':'qu', 'roh':'rm', 'run':'rn', \\r | |
| 74 | 'ron':'ro', 'rus':'ru', 'kin':'rw', 'san':'sa', 'srd':'sc', 'snd':'sd', \\r | |
| 75 | 'sme':'se', 'sag':'sg', 'sin':'si', 'slk':'sk', 'slv':'sl', 'smo':'sm', \\r | |
| 76 | 'sna':'sn', 'som':'so', 'sqi':'sq', 'srp':'sr', 'ssw':'ss', 'sot':'st', \\r | |
| 77 | 'sun':'su', 'swe':'sv', 'swa':'sw', 'tam':'ta', 'tel':'te', 'tgk':'tg', \\r | |
| 78 | 'tha':'th', 'tir':'ti', 'tuk':'tk', 'tgl':'tl', 'tsn':'tn', 'ton':'to', \\r | |
| 79 | 'tur':'tr', 'tso':'ts', 'tat':'tt', 'twi':'tw', 'tah':'ty', 'uig':'ug', \\r | |
| 80 | 'ukr':'uk', 'urd':'ur', 'uzb':'uz', 'ven':'ve', 'vie':'vi', 'vol':'vo', \\r | |
| 81 | 'wln':'wa', 'wol':'wo', 'xho':'xh', 'yid':'yi', 'yor':'yo', 'zha':'za', \\r | |
| 82 | 'zho':'zh', 'zul':'zu'}\r | |
| 83 | \r | |
| 84 | ## Convert a python unicode string to a normal string\r | |
| 85 | #\r | |
| 86 | # Convert a python unicode string to a normal string\r | |
| 87 | # UniToStr(u'I am a string') is 'I am a string'\r | |
| 88 | #\r | |
| 89 | # @param Uni: The python unicode string\r | |
| 90 | #\r | |
| 91 | # @retval: The formatted normal string\r | |
| 92 | #\r | |
| 93 | def UniToStr(Uni):\r | |
| 94 | return repr(Uni)[2:-1]\r | |
| 95 | \r | |
| 96 | ## Convert a unicode string to a Hex list\r | |
| 97 | #\r | |
| 98 | # Convert a unicode string to a Hex list\r | |
| 99 | # UniToHexList('ABC') is ['0x41', '0x00', '0x42', '0x00', '0x43', '0x00']\r | |
| 100 | #\r | |
| 101 | # @param Uni: The python unicode string\r | |
| 102 | #\r | |
| 103 | # @retval List: The formatted hex list\r | |
| 104 | #\r | |
| 105 | def UniToHexList(Uni):\r | |
| 106 | List = []\r | |
| 107 | for Item in Uni:\r | |
| 108 | Temp = '%04X' % ord(Item)\r | |
| 109 | List.append('0x' + Temp[2:4])\r | |
| 110 | List.append('0x' + Temp[0:2])\r | |
| 111 | return List\r | |
| 112 | \r | |
| 113 | ## Convert special unicode characters\r | |
| 114 | #\r | |
| 115 | # Convert special characters to (c), (r) and (tm).\r | |
| 116 | #\r | |
| 117 | # @param Uni: The python unicode string\r | |
| 118 | #\r | |
| 119 | # @retval NewUni: The converted unicode string\r | |
| 120 | #\r | |
| 121 | def ConvertSpecialUnicodes(Uni):\r | |
| 122 | NewUni = Uni\r | |
| 123 | NewUni = NewUni.replace(u'\u00A9', '(c)')\r | |
| 124 | NewUni = NewUni.replace(u'\u00AE', '(r)')\r | |
| 125 | NewUni = NewUni.replace(u'\u2122', '(tm)')\r | |
| 126 | return NewUni\r | |
| 127 | \r | |
| 128 | ## GetLanguageCode1766\r | |
| 129 | #\r | |
| 130 | # Check the language code read from .UNI file and convert RFC 4646 codes to RFC 1766 codes\r | |
| 131 | # RFC 1766 language codes supported in compatiblity mode\r | |
| 132 | # RFC 4646 language codes supported in native mode\r | |
| 133 | #\r | |
| 134 | # @param LangName: Language codes read from .UNI file\r | |
| 135 | #\r | |
| 136 | # @retval LangName: Valid lanugage code in RFC 1766 format or None\r | |
| 137 | #\r | |
| 138 | def GetLanguageCode1766(LangName, File=None):\r | |
| fe90f483 HC |
139 | return LangName\r |
| 140 | \r | |
| 421ccda3 HC |
141 | length = len(LangName)\r |
| 142 | if length == 2:\r | |
| 143 | if LangName.isalpha():\r | |
| 144 | for Key in gLANG_CONV_TABLE.keys():\r | |
| 145 | if gLANG_CONV_TABLE.get(Key) == LangName.lower():\r | |
| 146 | return Key\r | |
| 147 | elif length == 3:\r | |
| 148 | if LangName.isalpha() and gLANG_CONV_TABLE.get(LangName.lower()):\r | |
| 149 | return LangName\r | |
| 150 | else:\r | |
| f7496d71 | 151 | EdkLogger.Error("Unicode File Parser",\r |
| 421ccda3 | 152 | ToolError.FORMAT_INVALID,\r |
| f7496d71 | 153 | "Invalid RFC 1766 language code : %s" % LangName,\r |
| 421ccda3 HC |
154 | File)\r |
| 155 | elif length == 5:\r | |
| 156 | if LangName[0:2].isalpha() and LangName[2] == '-':\r | |
| 157 | for Key in gLANG_CONV_TABLE.keys():\r | |
| 158 | if gLANG_CONV_TABLE.get(Key) == LangName[0:2].lower():\r | |
| 159 | return Key\r | |
| 160 | elif length >= 6:\r | |
| 161 | if LangName[0:2].isalpha() and LangName[2] == '-':\r | |
| 162 | for Key in gLANG_CONV_TABLE.keys():\r | |
| 163 | if gLANG_CONV_TABLE.get(Key) == LangName[0:2].lower():\r | |
| 164 | return Key\r | |
| 4231a819 | 165 | if LangName[0:3].isalpha() and gLANG_CONV_TABLE.get(LangName.lower()) is None and LangName[3] == '-':\r |
| 421ccda3 HC |
166 | for Key in gLANG_CONV_TABLE.keys():\r |
| 167 | if Key == LangName[0:3].lower():\r | |
| 168 | return Key\r | |
| 169 | \r | |
| f7496d71 | 170 | EdkLogger.Error("Unicode File Parser",\r |
| 421ccda3 | 171 | ToolError.FORMAT_INVALID,\r |
| f7496d71 | 172 | "Invalid RFC 4646 language code : %s" % LangName,\r |
| 421ccda3 | 173 | File)\r |
| f7496d71 | 174 | \r |
| 421ccda3 HC |
175 | ## GetLanguageCode\r |
| 176 | #\r | |
| 177 | # Check the language code read from .UNI file and convert RFC 1766 codes to RFC 4646 codes if appropriate\r | |
| 178 | # RFC 1766 language codes supported in compatiblity mode\r | |
| 179 | # RFC 4646 language codes supported in native mode\r | |
| 180 | #\r | |
| 181 | # @param LangName: Language codes read from .UNI file\r | |
| 182 | #\r | |
| 183 | # @retval LangName: Valid lanugage code in RFC 4646 format or None\r | |
| 184 | #\r | |
| 185 | def GetLanguageCode(LangName, IsCompatibleMode, File):\r | |
| 186 | length = len(LangName)\r | |
| 187 | if IsCompatibleMode:\r | |
| 188 | if length == 3 and LangName.isalpha():\r | |
| 189 | TempLangName = gLANG_CONV_TABLE.get(LangName.lower())\r | |
| 4231a819 | 190 | if TempLangName is not None:\r |
| 421ccda3 HC |
191 | return TempLangName\r |
| 192 | return LangName\r | |
| 193 | else:\r | |
| f7496d71 | 194 | EdkLogger.Error("Unicode File Parser",\r |
| 421ccda3 | 195 | ToolError.FORMAT_INVALID,\r |
| f7496d71 | 196 | "Invalid RFC 1766 language code : %s" % LangName,\r |
| 421ccda3 HC |
197 | File)\r |
| 198 | if (LangName[0] == 'X' or LangName[0] == 'x') and LangName[1] == '-':\r | |
| 199 | return LangName\r | |
| 200 | if length == 2:\r | |
| 201 | if LangName.isalpha():\r | |
| 202 | return LangName\r | |
| 203 | elif length == 3:\r | |
| 4231a819 | 204 | if LangName.isalpha() and gLANG_CONV_TABLE.get(LangName.lower()) is None:\r |
| 421ccda3 HC |
205 | return LangName\r |
| 206 | elif length == 5:\r | |
| 207 | if LangName[0:2].isalpha() and LangName[2] == '-':\r | |
| 208 | return LangName\r | |
| 209 | elif length >= 6:\r | |
| 210 | if LangName[0:2].isalpha() and LangName[2] == '-':\r | |
| 211 | return LangName\r | |
| 4231a819 | 212 | if LangName[0:3].isalpha() and gLANG_CONV_TABLE.get(LangName.lower()) is None and LangName[3] == '-':\r |
| 421ccda3 HC |
213 | return LangName\r |
| 214 | \r | |
| f7496d71 | 215 | EdkLogger.Error("Unicode File Parser",\r |
| 421ccda3 | 216 | ToolError.FORMAT_INVALID,\r |
| f7496d71 | 217 | "Invalid RFC 4646 language code : %s" % LangName,\r |
| 421ccda3 HC |
218 | File)\r |
| 219 | \r | |
| 220 | ## FormatUniEntry\r | |
| 221 | #\r | |
| 222 | # Formated the entry in Uni file.\r | |
| 223 | #\r | |
| 224 | # @param StrTokenName StrTokenName.\r | |
| 225 | # @param TokenValueList A list need to be processed.\r | |
| 226 | # @param ContainerFile ContainerFile.\r | |
| 227 | #\r | |
| 228 | # @return formated entry\r | |
| 229 | def FormatUniEntry(StrTokenName, TokenValueList, ContainerFile):\r | |
| 230 | SubContent = ''\r | |
| 231 | PreFormatLength = 40\r | |
| 232 | if len(StrTokenName) > PreFormatLength:\r | |
| 233 | PreFormatLength = len(StrTokenName) + 1\r | |
| f7496d71 | 234 | for (Lang, Value) in TokenValueList:\r |
| 421ccda3 HC |
235 | if not Value or Lang == DT.TAB_LANGUAGE_EN_X:\r |
| 236 | continue\r | |
| 237 | if Lang == '':\r | |
| 238 | Lang = DT.TAB_LANGUAGE_EN_US\r | |
| 239 | if Lang == 'eng':\r | |
| 240 | Lang = DT.TAB_LANGUAGE_EN_US\r | |
| 241 | elif len(Lang.split('-')[0]) == 3:\r | |
| 242 | Lang = GetLanguageCode(Lang.split('-')[0], True, ContainerFile)\r | |
| 243 | else:\r | |
| 244 | Lang = GetLanguageCode(Lang, False, ContainerFile)\r | |
| 245 | ValueList = Value.split('\n')\r | |
| 246 | SubValueContent = ''\r | |
| 247 | for SubValue in ValueList:\r | |
| 248 | if SubValue.strip():\r | |
| 249 | SubValueContent += \\r | |
| 1ccc4d89 | 250 | ' ' * (PreFormatLength + len('#language en-US ')) + '\"%s\\n\"' % SubValue.strip() + '\r\n'\r |
| cf2b2bde | 251 | SubValueContent = SubValueContent[(PreFormatLength + len('#language en-US ')):SubValueContent.rfind('\\n')] \\r |
| 1ccc4d89 | 252 | + '\"' + '\r\n'\r |
| 421ccda3 HC |
253 | SubContent += ' '*PreFormatLength + '#language %-5s ' % Lang + SubValueContent\r |
| 254 | if SubContent:\r | |
| 255 | SubContent = StrTokenName + ' '*(PreFormatLength - len(StrTokenName)) + SubContent[PreFormatLength:]\r | |
| 256 | return SubContent\r | |
| 257 | \r | |
| 258 | \r | |
| 259 | ## StringDefClassObject\r | |
| 260 | #\r | |
| 261 | # A structure for language definition\r | |
| 262 | #\r | |
| 263 | class StringDefClassObject(object):\r | |
| 264 | def __init__(self, Name = None, Value = None, Referenced = False, Token = None, UseOtherLangDef = ''):\r | |
| 265 | self.StringName = ''\r | |
| 266 | self.StringNameByteList = []\r | |
| 267 | self.StringValue = ''\r | |
| 268 | self.StringValueByteList = ''\r | |
| 269 | self.Token = 0\r | |
| 270 | self.Referenced = Referenced\r | |
| 271 | self.UseOtherLangDef = UseOtherLangDef\r | |
| 272 | self.Length = 0\r | |
| 273 | \r | |
| 4231a819 | 274 | if Name is not None:\r |
| 421ccda3 HC |
275 | self.StringName = Name\r |
| 276 | self.StringNameByteList = UniToHexList(Name)\r | |
| 4231a819 | 277 | if Value is not None:\r |
| 421ccda3 HC |
278 | self.StringValue = Value\r |
| 279 | self.StringValueByteList = UniToHexList(self.StringValue)\r | |
| 280 | self.Length = len(self.StringValueByteList)\r | |
| 4231a819 | 281 | if Token is not None:\r |
| 421ccda3 HC |
282 | self.Token = Token\r |
| 283 | \r | |
| 284 | def __str__(self):\r | |
| 285 | return repr(self.StringName) + ' ' + \\r | |
| 286 | repr(self.Token) + ' ' + \\r | |
| 287 | repr(self.Referenced) + ' ' + \\r | |
| 288 | repr(self.StringValue) + ' ' + \\r | |
| 289 | repr(self.UseOtherLangDef)\r | |
| 290 | \r | |
| 291 | def UpdateValue(self, Value = None):\r | |
| 4231a819 | 292 | if Value is not None:\r |
| 421ccda3 | 293 | if self.StringValue:\r |
| 1ccc4d89 | 294 | self.StringValue = self.StringValue + '\r\n' + Value\r |
| 421ccda3 HC |
295 | else:\r |
| 296 | self.StringValue = Value\r | |
| 297 | self.StringValueByteList = UniToHexList(self.StringValue)\r | |
| 298 | self.Length = len(self.StringValueByteList)\r | |
| 299 | \r | |
| 300 | ## UniFileClassObject\r | |
| 301 | #\r | |
| 302 | # A structure for .uni file definition\r | |
| 303 | #\r | |
| 304 | class UniFileClassObject(object):\r | |
| 305 | def __init__(self, FileList = None, IsCompatibleMode = False, IncludePathList = None):\r | |
| 306 | self.FileList = FileList\r | |
| 307 | self.File = None\r | |
| 308 | self.IncFileList = FileList\r | |
| 309 | self.UniFileHeader = ''\r | |
| 310 | self.Token = 2\r | |
| 311 | self.LanguageDef = [] #[ [u'LanguageIdentifier', u'PrintableName'], ... ]\r | |
| 312 | self.OrderedStringList = {} #{ u'LanguageIdentifier' : [StringDefClassObject] }\r | |
| 313 | self.OrderedStringDict = {} #{ u'LanguageIdentifier' : {StringName:(IndexInList)} }\r | |
| 314 | self.OrderedStringListByToken = {} #{ u'LanguageIdentifier' : {Token: StringDefClassObject} }\r | |
| 315 | self.IsCompatibleMode = IsCompatibleMode\r | |
| 316 | if not IncludePathList:\r | |
| 317 | self.IncludePathList = []\r | |
| 318 | else:\r | |
| 319 | self.IncludePathList = IncludePathList\r | |
| 320 | if len(self.FileList) > 0:\r | |
| 321 | self.LoadUniFiles(FileList)\r | |
| 322 | \r | |
| 323 | #\r | |
| 324 | # Get Language definition\r | |
| 325 | #\r | |
| 326 | def GetLangDef(self, File, Line):\r | |
| 327 | Lang = distutils.util.split_quoted((Line.split(u"//")[0]))\r | |
| 328 | if len(Lang) != 3:\r | |
| 329 | try:\r | |
| 645a5128 | 330 | FileIn = codecs.open(File.Path, mode='rb', encoding='utf_8').readlines()\r |
| 5b0671c1 | 331 | except UnicodeError as Xstr:\r |
| 645a5128 | 332 | FileIn = codecs.open(File.Path, mode='rb', encoding='utf_16').readlines()\r |
| 5b0671c1 | 333 | except UnicodeError as Xstr:\r |
| 645a5128 | 334 | FileIn = codecs.open(File.Path, mode='rb', encoding='utf_16_le').readlines()\r |
| 421ccda3 | 335 | except:\r |
| f7496d71 LG |
336 | EdkLogger.Error("Unicode File Parser",\r |
| 337 | ToolError.FILE_OPEN_FAILURE,\r | |
| 421ccda3 HC |
338 | "File read failure: %s" % str(Xstr),\r |
| 339 | ExtraData=File)\r | |
| 340 | LineNo = GetLineNo(FileIn, Line, False)\r | |
| f7496d71 | 341 | EdkLogger.Error("Unicode File Parser",\r |
| 421ccda3 | 342 | ToolError.PARSER_ERROR,\r |
| f7496d71 LG |
343 | "Wrong language definition",\r |
| 344 | ExtraData="""%s\n\t*Correct format is like '#langdef en-US "English"'""" % Line,\r | |
| 421ccda3 HC |
345 | File = File, Line = LineNo)\r |
| 346 | else:\r | |
| 347 | LangName = GetLanguageCode(Lang[1], self.IsCompatibleMode, self.File)\r | |
| 348 | LangPrintName = Lang[2]\r | |
| 349 | \r | |
| 350 | IsLangInDef = False\r | |
| 351 | for Item in self.LanguageDef:\r | |
| 352 | if Item[0] == LangName:\r | |
| 353 | IsLangInDef = True\r | |
| 354 | break\r | |
| 355 | \r | |
| 356 | if not IsLangInDef:\r | |
| 357 | self.LanguageDef.append([LangName, LangPrintName])\r | |
| 358 | \r | |
| 359 | #\r | |
| 360 | # Add language string\r | |
| 361 | #\r | |
| 362 | self.AddStringToList(u'$LANGUAGE_NAME', LangName, LangName, 0, True, Index=0)\r | |
| 363 | self.AddStringToList(u'$PRINTABLE_LANGUAGE_NAME', LangName, LangPrintName, 1, True, Index=1)\r | |
| 364 | \r | |
| 365 | if not IsLangInDef:\r | |
| 366 | #\r | |
| 367 | # The found STRING tokens will be added into new language string list\r | |
| f7496d71 | 368 | # so that the unique STRING identifier is reserved for all languages in the package list.\r |
| 421ccda3 HC |
369 | #\r |
| 370 | FirstLangName = self.LanguageDef[0][0]\r | |
| 371 | if LangName != FirstLangName:\r | |
| 372 | for Index in range (2, len (self.OrderedStringList[FirstLangName])):\r | |
| 373 | Item = self.OrderedStringList[FirstLangName][Index]\r | |
| 374 | if Item.UseOtherLangDef != '':\r | |
| 375 | OtherLang = Item.UseOtherLangDef\r | |
| 376 | else:\r | |
| 377 | OtherLang = FirstLangName\r | |
| f7496d71 LG |
378 | self.OrderedStringList[LangName].append (StringDefClassObject(Item.StringName,\r |
| 379 | '',\r | |
| 380 | Item.Referenced,\r | |
| 381 | Item.Token,\r | |
| 421ccda3 HC |
382 | OtherLang))\r |
| 383 | self.OrderedStringDict[LangName][Item.StringName] = len(self.OrderedStringList[LangName]) - 1\r | |
| 384 | return True\r | |
| 385 | \r | |
| 386 | #\r | |
| 387 | # Get String name and value\r | |
| 388 | #\r | |
| 389 | def GetStringObject(self, Item):\r | |
| 390 | Language = ''\r | |
| 391 | Value = ''\r | |
| 392 | \r | |
| 393 | Name = Item.split()[1]\r | |
| 394 | # Check the string name is the upper character\r | |
| 395 | if Name != '':\r | |
| 396 | MatchString = re.match('[A-Z0-9_]+', Name, re.UNICODE)\r | |
| 4231a819 | 397 | if MatchString is None or MatchString.end(0) != len(Name):\r |
| f7496d71 | 398 | EdkLogger.Error("Unicode File Parser",\r |
| 421ccda3 HC |
399 | ToolError.FORMAT_INVALID,\r |
| 400 | 'The string token name %s in UNI file %s must be upper case character.' %(Name, self.File))\r | |
| 401 | LanguageList = Item.split(u'#language ')\r | |
| 402 | for IndexI in range(len(LanguageList)):\r | |
| 403 | if IndexI == 0:\r | |
| 404 | continue\r | |
| 405 | else:\r | |
| 406 | Language = LanguageList[IndexI].split()[0]\r | |
| 407 | #.replace(u'\r\n', u'')\r | |
| 408 | Value = \\r | |
| f7496d71 | 409 | LanguageList[IndexI][LanguageList[IndexI].find(u'\"') + len(u'\"') : LanguageList[IndexI].rfind(u'\"')]\r |
| 421ccda3 HC |
410 | Language = GetLanguageCode(Language, self.IsCompatibleMode, self.File)\r |
| 411 | self.AddStringToList(Name, Language, Value)\r | |
| 412 | \r | |
| 413 | #\r | |
| 414 | # Get include file list and load them\r | |
| 415 | #\r | |
| 416 | def GetIncludeFile(self, Item, Dir = None):\r | |
| 417 | if Dir:\r | |
| 418 | pass\r | |
| 419 | FileName = Item[Item.find(u'!include ') + len(u'!include ') :Item.find(u' ', len(u'!include '))][1:-1]\r | |
| 420 | self.LoadUniFile(FileName)\r | |
| 421 | \r | |
| 422 | #\r | |
| 423 | # Pre-process before parse .uni file\r | |
| 424 | #\r | |
| 425 | def PreProcess(self, File, IsIncludeFile=False):\r | |
| 426 | if not os.path.exists(File.Path) or not os.path.isfile(File.Path):\r | |
| f7496d71 | 427 | EdkLogger.Error("Unicode File Parser",\r |
| 421ccda3 HC |
428 | ToolError.FILE_NOT_FOUND,\r |
| 429 | ExtraData=File.Path)\r | |
| 430 | \r | |
| fe90f483 HC |
431 | #\r |
| 432 | # Check file header of the Uni file\r | |
| 433 | #\r | |
| 4a21fb3b HC |
434 | # if not CheckUTF16FileHeader(File.Path):\r |
| 435 | # EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID,\r | |
| 436 | # ExtraData='The file %s is either invalid UTF-16LE or it is missing the BOM.' % File.Path)\r | |
| fe90f483 | 437 | \r |
| 421ccda3 | 438 | try:\r |
| 645a5128 | 439 | FileIn = codecs.open(File.Path, mode='rb', encoding='utf_8').readlines()\r |
| 5b0671c1 | 440 | except UnicodeError as Xstr:\r |
| 421ccda3 HC |
441 | FileIn = codecs.open(File.Path, mode='rb', encoding='utf_16').readlines()\r |
| 442 | except UnicodeError:\r | |
| 443 | FileIn = codecs.open(File.Path, mode='rb', encoding='utf_16_le').readlines()\r | |
| 444 | except:\r | |
| 445 | EdkLogger.Error("Unicode File Parser", ToolError.FILE_OPEN_FAILURE, ExtraData=File.Path)\r | |
| f7496d71 LG |
446 | \r |
| 447 | \r | |
| 421ccda3 HC |
448 | #\r |
| 449 | # get the file header\r | |
| 450 | #\r | |
| 451 | Lines = []\r | |
| 452 | HeaderStart = False\r | |
| 453 | HeaderEnd = False\r | |
| 454 | if not self.UniFileHeader:\r | |
| 455 | FirstGenHeader = True\r | |
| 456 | else:\r | |
| 457 | FirstGenHeader = False\r | |
| 458 | for Line in FileIn:\r | |
| 459 | Line = Line.strip()\r | |
| 460 | if Line == u'':\r | |
| 461 | continue\r | |
| 462 | if Line.startswith(DT.TAB_COMMENT_EDK1_SPLIT) and (Line.find(DT.TAB_HEADER_COMMENT) > -1) \\r | |
| 463 | and not HeaderEnd and not HeaderStart:\r | |
| 464 | HeaderStart = True\r | |
| 465 | if not Line.startswith(DT.TAB_COMMENT_EDK1_SPLIT) and HeaderStart and not HeaderEnd:\r | |
| 466 | HeaderEnd = True\r | |
| 467 | if Line.startswith(DT.TAB_COMMENT_EDK1_SPLIT) and HeaderStart and not HeaderEnd and FirstGenHeader:\r | |
| 1ccc4d89 | 468 | self.UniFileHeader += Line + '\r\n'\r |
| 421ccda3 | 469 | continue\r |
| f7496d71 | 470 | \r |
| 421ccda3 HC |
471 | #\r |
| 472 | # Use unique identifier\r | |
| 473 | #\r | |
| 474 | FindFlag = -1\r | |
| 475 | LineCount = 0\r | |
| 476 | MultiLineFeedExits = False\r | |
| 477 | #\r | |
| 478 | # 0: initial value\r | |
| 479 | # 1: signle String entry exist\r | |
| 480 | # 2: line feed exist under the some signle String entry\r | |
| 481 | #\r | |
| 482 | StringEntryExistsFlag = 0\r | |
| 483 | for Line in FileIn:\r | |
| 484 | Line = FileIn[LineCount]\r | |
| 485 | LineCount += 1\r | |
| 486 | Line = Line.strip()\r | |
| 487 | #\r | |
| 488 | # Ignore comment line and empty line\r | |
| f7496d71 | 489 | #\r |
| 421ccda3 HC |
490 | if Line == u'' or Line.startswith(u'//'):\r |
| 491 | #\r | |
| 492 | # Change the single line String entry flag status\r | |
| 493 | #\r | |
| 494 | if StringEntryExistsFlag == 1:\r | |
| 495 | StringEntryExistsFlag = 2\r | |
| 496 | #\r | |
| 497 | # If the '#string' line and the '#language' line are not in the same line,\r | |
| 498 | # there should be only one line feed character betwwen them\r | |
| 499 | #\r | |
| 500 | if MultiLineFeedExits:\r | |
| 501 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)\r | |
| 502 | continue\r | |
| 503 | \r | |
| 504 | MultiLineFeedExits = False\r | |
| 505 | #\r | |
| 506 | # Process comment embeded in string define lines\r | |
| 507 | #\r | |
| 508 | FindFlag = Line.find(u'//')\r | |
| 509 | if FindFlag != -1 and Line.find(u'//') < Line.find(u'"'):\r | |
| 510 | Line = Line.replace(Line[FindFlag:], u' ')\r | |
| 511 | if FileIn[LineCount].strip().startswith('#language'):\r | |
| 512 | Line = Line + FileIn[LineCount]\r | |
| 513 | FileIn[LineCount-1] = Line\r | |
| 1ccc4d89 | 514 | FileIn[LineCount] = '\r\n'\r |
| 421ccda3 | 515 | LineCount -= 1\r |
| 1ccc4d89 | 516 | for Index in xrange (LineCount + 1, len (FileIn) - 1):\r |
| 421ccda3 | 517 | if (Index == len(FileIn) -1):\r |
| 1ccc4d89 | 518 | FileIn[Index] = '\r\n'\r |
| 421ccda3 HC |
519 | else:\r |
| 520 | FileIn[Index] = FileIn[Index + 1]\r | |
| 521 | continue\r | |
| 522 | CommIndex = GetCharIndexOutStr(u'/', Line)\r | |
| 523 | if CommIndex > -1:\r | |
| 524 | if (len(Line) - 1) > CommIndex:\r | |
| 525 | if Line[CommIndex+1] == u'/':\r | |
| 526 | Line = Line[:CommIndex].strip()\r | |
| 527 | else:\r | |
| 528 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)\r | |
| 529 | else:\r | |
| 530 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)\r | |
| f7496d71 | 531 | \r |
| 421ccda3 HC |
532 | Line = Line.replace(UNICODE_WIDE_CHAR, WIDE_CHAR)\r |
| 533 | Line = Line.replace(UNICODE_NARROW_CHAR, NARROW_CHAR)\r | |
| 534 | Line = Line.replace(UNICODE_NON_BREAKING_CHAR, NON_BREAKING_CHAR)\r | |
| 535 | \r | |
| 536 | Line = Line.replace(u'\\\\', u'\u0006')\r | |
| 537 | Line = Line.replace(u'\\r\\n', CR + LF)\r | |
| 538 | Line = Line.replace(u'\\n', CR + LF)\r | |
| 539 | Line = Line.replace(u'\\r', CR)\r | |
| 540 | Line = Line.replace(u'\\t', u'\t')\r | |
| 541 | Line = Line.replace(u'''\"''', u'''"''')\r | |
| 542 | Line = Line.replace(u'\t', u' ')\r | |
| 543 | Line = Line.replace(u'\u0006', u'\\')\r | |
| 544 | \r | |
| 85ea493f HC |
545 | #\r |
| 546 | # Check if single line has correct '"'\r | |
| 547 | #\r | |
| 548 | if Line.startswith(u'#string') and Line.find(u'#language') > -1 and Line.find('"') > Line.find(u'#language'):\r | |
| 549 | if not Line.endswith('"'):\r | |
| 550 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID,\r | |
| 551 | ExtraData='''The line %s misses '"' at the end of it in file %s'''\r | |
| 552 | % (LineCount, File.Path))\r | |
| 553 | \r | |
| 421ccda3 HC |
554 | #\r |
| 555 | # Between Name entry and Language entry can not contain line feed\r | |
| 556 | #\r | |
| 557 | if Line.startswith(u'#string') and Line.find(u'#language') == -1:\r | |
| 558 | MultiLineFeedExits = True\r | |
| f7496d71 | 559 | \r |
| 421ccda3 HC |
560 | if Line.startswith(u'#string') and Line.find(u'#language') > 0 and Line.find(u'"') < 0:\r |
| 561 | MultiLineFeedExits = True\r | |
| f7496d71 | 562 | \r |
| 421ccda3 HC |
563 | #\r |
| 564 | # Between Language entry and String entry can not contain line feed\r | |
| 565 | #\r | |
| 566 | if Line.startswith(u'#language') and len(Line.split()) == 2:\r | |
| 567 | MultiLineFeedExits = True\r | |
| f7496d71 | 568 | \r |
| 90c64aad HC |
569 | #\r |
| 570 | # Check the situation that there only has one '"' for the language entry\r | |
| 571 | #\r | |
| 572 | if Line.startswith(u'#string') and Line.find(u'#language') > 0 and Line.count(u'"') == 1:\r | |
| 573 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID,\r | |
| 574 | ExtraData='''The line %s misses '"' at the end of it in file %s'''\r | |
| 575 | % (LineCount, File.Path))\r | |
| 576 | \r | |
| 577 | #\r | |
| 578 | # Check the situation that there has more than 2 '"' for the language entry\r | |
| 579 | #\r | |
| 580 | if Line.startswith(u'#string') and Line.find(u'#language') > 0 and Line.replace(u'\\"', '').count(u'"') > 2:\r | |
| 581 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID,\r | |
| 582 | ExtraData='''The line %s has more than 2 '"' for language entry in file %s'''\r | |
| 583 | % (LineCount, File.Path))\r | |
| 584 | \r | |
| 421ccda3 HC |
585 | #\r |
| 586 | # Between two String entry, can not contain line feed\r | |
| 587 | #\r | |
| 588 | if Line.startswith(u'"'):\r | |
| 589 | if StringEntryExistsFlag == 2:\r | |
| 645a5128 | 590 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID,\r |
| 421ccda3 | 591 | Message=ST.ERR_UNIPARSE_LINEFEED_UP_EXIST % Line, ExtraData=File.Path)\r |
| 645a5128 | 592 | \r |
| 421ccda3 HC |
593 | StringEntryExistsFlag = 1\r |
| 594 | if not Line.endswith('"'):\r | |
| fe90f483 HC |
595 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID,\r |
| 596 | ExtraData='''The line %s misses '"' at the end of it in file %s'''\r | |
| 597 | % (LineCount, File.Path))\r | |
| 421ccda3 HC |
598 | elif Line.startswith(u'#language'):\r |
| 599 | if StringEntryExistsFlag == 2:\r | |
| 645a5128 | 600 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID,\r |
| fe90f483 | 601 | Message=ST.ERR_UNI_MISS_STRING_ENTRY % Line, ExtraData=File.Path)\r |
| 421ccda3 HC |
602 | StringEntryExistsFlag = 0\r |
| 603 | else:\r | |
| 604 | StringEntryExistsFlag = 0\r | |
| 605 | \r | |
| 606 | Lines.append(Line)\r | |
| f7496d71 | 607 | \r |
| 421ccda3 HC |
608 | #\r |
| 609 | # Convert string def format as below\r | |
| 610 | #\r | |
| 611 | # #string MY_STRING_1\r | |
| 612 | # #language eng\r | |
| 613 | # "My first English string line 1"\r | |
| 614 | # "My first English string line 2"\r | |
| 615 | # #string MY_STRING_1\r | |
| 616 | # #language spa\r | |
| 617 | # "Mi segunda secuencia 1"\r | |
| 618 | # "Mi segunda secuencia 2"\r | |
| 619 | #\r | |
| f7496d71 | 620 | \r |
| 421ccda3 HC |
621 | if not IsIncludeFile and not Lines:\r |
| 622 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \\r | |
| 623 | Message=ST.ERR_UNIPARSE_NO_SECTION_EXIST, \\r | |
| f7496d71 | 624 | ExtraData=File.Path)\r |
| 421ccda3 HC |
625 | \r |
| 626 | NewLines = []\r | |
| 627 | StrName = u''\r | |
| 628 | ExistStrNameList = []\r | |
| 629 | for Line in Lines:\r | |
| 630 | if StrName and not StrName.split()[1].startswith(DT.TAB_STR_TOKENCNAME + DT.TAB_UNDERLINE_SPLIT):\r | |
| 631 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \\r | |
| 632 | Message=ST.ERR_UNIPARSE_STRNAME_FORMAT_ERROR % StrName.split()[1], \\r | |
| 633 | ExtraData=File.Path)\r | |
| f7496d71 | 634 | \r |
| 421ccda3 HC |
635 | if StrName and len(StrName.split()[1].split(DT.TAB_UNDERLINE_SPLIT)) == 4:\r |
| 636 | StringTokenList = StrName.split()[1].split(DT.TAB_UNDERLINE_SPLIT)\r | |
| 637 | if (StringTokenList[3].upper() in [DT.TAB_STR_TOKENPROMPT, DT.TAB_STR_TOKENHELP] and \\r | |
| 638 | StringTokenList[3] not in [DT.TAB_STR_TOKENPROMPT, DT.TAB_STR_TOKENHELP]) or \\r | |
| 639 | (StringTokenList[2].upper() == DT.TAB_STR_TOKENERR and StringTokenList[2] != DT.TAB_STR_TOKENERR):\r | |
| 640 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \\r | |
| 641 | Message=ST.ERR_UNIPARSE_STRTOKEN_FORMAT_ERROR % StrName.split()[1], \\r | |
| 642 | ExtraData=File.Path)\r | |
| f7496d71 | 643 | \r |
| 421ccda3 HC |
644 | if Line.count(u'#language') > 1:\r |
| 645 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \\r | |
| 646 | Message=ST.ERR_UNIPARSE_SEP_LANGENTRY_LINE % Line, \\r | |
| f7496d71 LG |
647 | ExtraData=File.Path)\r |
| 648 | \r | |
| 421ccda3 HC |
649 | if Line.startswith(u'//'):\r |
| 650 | continue\r | |
| 651 | elif Line.startswith(u'#langdef'):\r | |
| 652 | if len(Line.split()) == 2:\r | |
| 653 | NewLines.append(Line)\r | |
| 654 | continue\r | |
| f7496d71 | 655 | elif len(Line.split()) > 2 and Line.find(u'"') > 0:\r |
| 421ccda3 HC |
656 | NewLines.append(Line[:Line.find(u'"')].strip())\r |
| 657 | NewLines.append(Line[Line.find(u'"'):])\r | |
| 658 | else:\r | |
| 659 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)\r | |
| 660 | elif Line.startswith(u'#string'):\r | |
| 661 | if len(Line.split()) == 2:\r | |
| 662 | StrName = Line\r | |
| 663 | if StrName:\r | |
| 664 | if StrName.split()[1] not in ExistStrNameList:\r | |
| 665 | ExistStrNameList.append(StrName.split()[1].strip())\r | |
| 666 | elif StrName.split()[1] in [DT.TAB_INF_ABSTRACT, DT.TAB_INF_DESCRIPTION, \\r | |
| 667 | DT.TAB_INF_BINARY_ABSTRACT, DT.TAB_INF_BINARY_DESCRIPTION, \\r | |
| 668 | DT.TAB_DEC_PACKAGE_ABSTRACT, DT.TAB_DEC_PACKAGE_DESCRIPTION, \\r | |
| 669 | DT.TAB_DEC_BINARY_ABSTRACT, DT.TAB_DEC_BINARY_DESCRIPTION]:\r | |
| 670 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \\r | |
| 671 | Message=ST.ERR_UNIPARSE_MULTI_ENTRY_EXIST % StrName.split()[1], \\r | |
| 672 | ExtraData=File.Path)\r | |
| 673 | continue\r | |
| 674 | elif len(Line.split()) == 4 and Line.find(u'#language') > 0:\r | |
| 675 | if Line[Line.find(u'#language')-1] != ' ' or \\r | |
| 676 | Line[Line.find(u'#language')+len(u'#language')] != u' ':\r | |
| 677 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)\r | |
| f7496d71 | 678 | \r |
| 421ccda3 HC |
679 | if Line.find(u'"') > 0:\r |
| 680 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)\r | |
| f7496d71 | 681 | \r |
| 421ccda3 HC |
682 | StrName = Line.split()[0] + u' ' + Line.split()[1]\r |
| 683 | if StrName:\r | |
| 684 | if StrName.split()[1] not in ExistStrNameList:\r | |
| 685 | ExistStrNameList.append(StrName.split()[1].strip())\r | |
| 686 | elif StrName.split()[1] in [DT.TAB_INF_ABSTRACT, DT.TAB_INF_DESCRIPTION, \\r | |
| 687 | DT.TAB_INF_BINARY_ABSTRACT, DT.TAB_INF_BINARY_DESCRIPTION, \\r | |
| 688 | DT.TAB_DEC_PACKAGE_ABSTRACT, DT.TAB_DEC_PACKAGE_DESCRIPTION, \\r | |
| 689 | DT.TAB_DEC_BINARY_ABSTRACT, DT.TAB_DEC_BINARY_DESCRIPTION]:\r | |
| 690 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \\r | |
| 691 | Message=ST.ERR_UNIPARSE_MULTI_ENTRY_EXIST % StrName.split()[1], \\r | |
| 692 | ExtraData=File.Path)\r | |
| 693 | if IsIncludeFile:\r | |
| 694 | if StrName not in NewLines:\r | |
| 695 | NewLines.append((Line[:Line.find(u'#language')]).strip())\r | |
| 696 | else:\r | |
| 697 | NewLines.append((Line[:Line.find(u'#language')]).strip())\r | |
| 698 | NewLines.append((Line[Line.find(u'#language'):]).strip())\r | |
| 699 | elif len(Line.split()) > 4 and Line.find(u'#language') > 0 and Line.find(u'"') > 0:\r | |
| 700 | if Line[Line.find(u'#language')-1] != u' ' or \\r | |
| 701 | Line[Line.find(u'#language')+len(u'#language')] != u' ':\r | |
| 702 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)\r | |
| f7496d71 | 703 | \r |
| 421ccda3 | 704 | if Line[Line.find(u'"')-1] != u' ':\r |
| f7496d71 LG |
705 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)\r |
| 706 | \r | |
| 707 | StrName = Line.split()[0] + u' ' + Line.split()[1]\r | |
| 421ccda3 HC |
708 | if StrName:\r |
| 709 | if StrName.split()[1] not in ExistStrNameList:\r | |
| 710 | ExistStrNameList.append(StrName.split()[1].strip())\r | |
| 711 | elif StrName.split()[1] in [DT.TAB_INF_ABSTRACT, DT.TAB_INF_DESCRIPTION, \\r | |
| 712 | DT.TAB_INF_BINARY_ABSTRACT, DT.TAB_INF_BINARY_DESCRIPTION, \\r | |
| 713 | DT.TAB_DEC_PACKAGE_ABSTRACT, DT.TAB_DEC_PACKAGE_DESCRIPTION, \\r | |
| 714 | DT.TAB_DEC_BINARY_ABSTRACT, DT.TAB_DEC_BINARY_DESCRIPTION]:\r | |
| 715 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \\r | |
| 716 | Message=ST.ERR_UNIPARSE_MULTI_ENTRY_EXIST % StrName.split()[1], \\r | |
| f7496d71 | 717 | ExtraData=File.Path)\r |
| 421ccda3 HC |
718 | if IsIncludeFile:\r |
| 719 | if StrName not in NewLines:\r | |
| 720 | NewLines.append((Line[:Line.find(u'#language')]).strip())\r | |
| f7496d71 | 721 | else:\r |
| 421ccda3 HC |
722 | NewLines.append((Line[:Line.find(u'#language')]).strip())\r |
| 723 | NewLines.append((Line[Line.find(u'#language'):Line.find(u'"')]).strip())\r | |
| 724 | NewLines.append((Line[Line.find(u'"'):]).strip())\r | |
| 725 | else:\r | |
| 726 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)\r | |
| 727 | elif Line.startswith(u'#language'):\r | |
| 728 | if len(Line.split()) == 2:\r | |
| 729 | if IsIncludeFile:\r | |
| 730 | if StrName not in NewLines:\r | |
| 731 | NewLines.append(StrName)\r | |
| 732 | else:\r | |
| 733 | NewLines.append(StrName)\r | |
| 734 | NewLines.append(Line)\r | |
| 735 | elif len(Line.split()) > 2 and Line.find(u'"') > 0:\r | |
| 736 | if IsIncludeFile:\r | |
| 737 | if StrName not in NewLines:\r | |
| 738 | NewLines.append(StrName)\r | |
| 739 | else:\r | |
| 740 | NewLines.append(StrName)\r | |
| 741 | NewLines.append((Line[:Line.find(u'"')]).strip())\r | |
| 742 | NewLines.append((Line[Line.find(u'"'):]).strip())\r | |
| 743 | else:\r | |
| 744 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)\r | |
| 745 | elif Line.startswith(u'"'):\r | |
| 90c64aad HC |
746 | #\r |
| 747 | # Check the situation that there has more than 2 '"' for the language entry\r | |
| 748 | #\r | |
| 749 | if Line.replace(u'\\"', '').count(u'"') > 2:\r | |
| 750 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID,\r | |
| 751 | ExtraData='''The line %s has more than 2 '"' for language entry in file %s'''\r | |
| 752 | % (LineCount, File.Path))\r | |
| 421ccda3 HC |
753 | if u'#string' in Line or u'#language' in Line:\r |
| 754 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)\r | |
| 755 | NewLines.append(Line)\r | |
| 756 | else:\r | |
| 72443dd2 | 757 | print(Line)\r |
| 421ccda3 | 758 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, ExtraData=File.Path)\r |
| f7496d71 | 759 | \r |
| 421ccda3 HC |
760 | if StrName and not StrName.split()[1].startswith(u'STR_'):\r |
| 761 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \\r | |
| 762 | Message=ST.ERR_UNIPARSE_STRNAME_FORMAT_ERROR % StrName.split()[1], \\r | |
| f7496d71 LG |
763 | ExtraData=File.Path)\r |
| 764 | \r | |
| 421ccda3 HC |
765 | if StrName and not NewLines:\r |
| 766 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \\r | |
| 767 | Message=ST.ERR_UNI_MISS_LANGENTRY % StrName, \\r | |
| 768 | ExtraData=File.Path)\r | |
| f7496d71 | 769 | \r |
| 421ccda3 HC |
770 | #\r |
| 771 | # Check Abstract, Description, BinaryAbstract and BinaryDescription order,\r | |
| 772 | # should be Abstract, Description, BinaryAbstract, BinaryDesctiption\r | |
| 773 | AbstractPosition = -1\r | |
| 774 | DescriptionPosition = -1\r | |
| 775 | BinaryAbstractPosition = -1\r | |
| 776 | BinaryDescriptionPosition = -1\r | |
| 777 | for StrName in ExistStrNameList:\r | |
| 778 | if DT.TAB_HEADER_ABSTRACT.upper() in StrName:\r | |
| 779 | if 'BINARY' in StrName:\r | |
| 780 | BinaryAbstractPosition = ExistStrNameList.index(StrName)\r | |
| 781 | else:\r | |
| 782 | AbstractPosition = ExistStrNameList.index(StrName)\r | |
| 783 | if DT.TAB_HEADER_DESCRIPTION.upper() in StrName:\r | |
| 784 | if 'BINARY' in StrName:\r | |
| 785 | BinaryDescriptionPosition = ExistStrNameList.index(StrName)\r | |
| 786 | else:\r | |
| 787 | DescriptionPosition = ExistStrNameList.index(StrName)\r | |
| f7496d71 | 788 | \r |
| 421ccda3 HC |
789 | OrderList = sorted([AbstractPosition, DescriptionPosition])\r |
| 790 | BinaryOrderList = sorted([BinaryAbstractPosition, BinaryDescriptionPosition])\r | |
| 791 | Min = OrderList[0]\r | |
| 792 | Max = OrderList[1]\r | |
| 793 | BinaryMin = BinaryOrderList[0]\r | |
| 794 | BinaryMax = BinaryOrderList[1]\r | |
| 795 | if BinaryDescriptionPosition > -1:\r | |
| 796 | if not(BinaryDescriptionPosition == BinaryMax and BinaryAbstractPosition == BinaryMin and \\r | |
| 797 | BinaryMax > Max):\r | |
| 798 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \\r | |
| 799 | Message=ST.ERR_UNIPARSE_ENTRY_ORDER_WRONG, \\r | |
| f7496d71 | 800 | ExtraData=File.Path)\r |
| 421ccda3 HC |
801 | elif BinaryAbstractPosition > -1:\r |
| 802 | if not(BinaryAbstractPosition > Max):\r | |
| 803 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \\r | |
| 804 | Message=ST.ERR_UNIPARSE_ENTRY_ORDER_WRONG, \\r | |
| f7496d71 LG |
805 | ExtraData=File.Path)\r |
| 806 | \r | |
| 421ccda3 HC |
807 | if DescriptionPosition > -1:\r |
| 808 | if not(DescriptionPosition == Max and AbstractPosition == Min and \\r | |
| 809 | DescriptionPosition > AbstractPosition):\r | |
| 810 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID, \\r | |
| 811 | Message=ST.ERR_UNIPARSE_ENTRY_ORDER_WRONG, \\r | |
| f7496d71 LG |
812 | ExtraData=File.Path)\r |
| 813 | \r | |
| 421ccda3 | 814 | if not self.UniFileHeader:\r |
| f7496d71 | 815 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID,\r |
| 421ccda3 HC |
816 | Message = ST.ERR_NO_SOURCE_HEADER,\r |
| 817 | ExtraData=File.Path)\r | |
| f7496d71 | 818 | \r |
| 421ccda3 HC |
819 | return NewLines\r |
| 820 | \r | |
| 821 | #\r | |
| 822 | # Load a .uni file\r | |
| 823 | #\r | |
| 824 | def LoadUniFile(self, File = None):\r | |
| 4231a819 | 825 | if File is None:\r |
| f7496d71 LG |
826 | EdkLogger.Error("Unicode File Parser",\r |
| 827 | ToolError.PARSER_ERROR,\r | |
| 828 | Message='No unicode file is given',\r | |
| 421ccda3 | 829 | ExtraData=File.Path)\r |
| f7496d71 | 830 | \r |
| 421ccda3 | 831 | self.File = File\r |
| f7496d71 | 832 | \r |
| 421ccda3 HC |
833 | #\r |
| 834 | # Process special char in file\r | |
| 835 | #\r | |
| 836 | Lines = self.PreProcess(File)\r | |
| 837 | \r | |
| 838 | #\r | |
| 839 | # Get Unicode Information\r | |
| 840 | #\r | |
| 841 | for IndexI in range(len(Lines)):\r | |
| 842 | Line = Lines[IndexI]\r | |
| 843 | if (IndexI + 1) < len(Lines):\r | |
| 844 | SecondLine = Lines[IndexI + 1]\r | |
| 845 | if (IndexI + 2) < len(Lines):\r | |
| 846 | ThirdLine = Lines[IndexI + 2]\r | |
| 847 | \r | |
| 848 | #\r | |
| 849 | # Get Language def information\r | |
| 850 | #\r | |
| 851 | if Line.find(u'#langdef ') >= 0:\r | |
| 852 | self.GetLangDef(File, Line + u' ' + SecondLine)\r | |
| 853 | continue\r | |
| 854 | \r | |
| 855 | Name = ''\r | |
| 856 | Language = ''\r | |
| 857 | Value = ''\r | |
| 858 | CombineToken = False\r | |
| 859 | #\r | |
| 860 | # Get string def information format as below\r | |
| 861 | #\r | |
| 862 | # #string MY_STRING_1\r | |
| 863 | # #language eng\r | |
| 864 | # "My first English string line 1"\r | |
| 865 | # "My first English string line 2"\r | |
| 866 | # #string MY_STRING_1\r | |
| 867 | # #language spa\r | |
| 868 | # "Mi segunda secuencia 1"\r | |
| 869 | # "Mi segunda secuencia 2"\r | |
| 870 | #\r | |
| 871 | if Line.find(u'#string ') >= 0 and Line.find(u'#language ') < 0 and \\r | |
| 872 | SecondLine.find(u'#string ') < 0 and SecondLine.find(u'#language ') >= 0 and \\r | |
| 873 | ThirdLine.find(u'#string ') < 0 and ThirdLine.find(u'#language ') < 0:\r | |
| 874 | if Line.find('"') > 0 or SecondLine.find('"') > 0:\r | |
| f7496d71 | 875 | EdkLogger.Error("Unicode File Parser", ToolError.FORMAT_INVALID,\r |
| 421ccda3 HC |
876 | Message=ST.ERR_UNIPARSE_DBLQUOTE_UNMATCHED,\r |
| 877 | ExtraData=File.Path)\r | |
| f7496d71 | 878 | \r |
| 421ccda3 HC |
879 | Name = Line[Line.find(u'#string ') + len(u'#string ') : ].strip(' ')\r |
| 880 | Language = SecondLine[SecondLine.find(u'#language ') + len(u'#language ') : ].strip(' ')\r | |
| 881 | for IndexJ in range(IndexI + 2, len(Lines)):\r | |
| 882 | if Lines[IndexJ].find(u'#string ') < 0 and Lines[IndexJ].find(u'#language ') < 0 and \\r | |
| 883 | Lines[IndexJ].strip().startswith(u'"') and Lines[IndexJ].strip().endswith(u'"'):\r | |
| 884 | if Lines[IndexJ][-2] == ' ':\r | |
| 885 | CombineToken = True\r | |
| 886 | if CombineToken:\r | |
| 887 | if Lines[IndexJ].strip()[1:-1].strip():\r | |
| 888 | Value = Value + Lines[IndexJ].strip()[1:-1].rstrip() + ' '\r | |
| 889 | else:\r | |
| 890 | Value = Value + Lines[IndexJ].strip()[1:-1]\r | |
| 891 | CombineToken = False\r | |
| 892 | else:\r | |
| 1ccc4d89 | 893 | Value = Value + Lines[IndexJ].strip()[1:-1] + '\r\n'\r |
| 421ccda3 HC |
894 | else:\r |
| 895 | IndexI = IndexJ\r | |
| 896 | break\r | |
| 1ccc4d89 LG |
897 | if Value.endswith('\r\n'):\r |
| 898 | Value = Value[: Value.rfind('\r\n')]\r | |
| 421ccda3 HC |
899 | Language = GetLanguageCode(Language, self.IsCompatibleMode, self.File)\r |
| 900 | self.AddStringToList(Name, Language, Value)\r | |
| 901 | continue\r | |
| 902 | \r | |
| 903 | #\r | |
| 904 | # Load multiple .uni files\r | |
| 905 | #\r | |
| 906 | def LoadUniFiles(self, FileList):\r | |
| 907 | if len(FileList) > 0:\r | |
| 908 | for File in FileList:\r | |
| 909 | FilePath = File.Path.strip()\r | |
| 910 | if FilePath.endswith('.uni') or FilePath.endswith('.UNI') or FilePath.endswith('.Uni'):\r | |
| 911 | self.LoadUniFile(File)\r | |
| 912 | \r | |
| 913 | #\r | |
| 914 | # Add a string to list\r | |
| 915 | #\r | |
| 916 | def AddStringToList(self, Name, Language, Value, Token = 0, Referenced = False, UseOtherLangDef = '', Index = -1):\r | |
| 917 | for LangNameItem in self.LanguageDef:\r | |
| 918 | if Language == LangNameItem[0]:\r | |
| 919 | break\r | |
| f7496d71 | 920 | \r |
| 421ccda3 HC |
921 | if Language not in self.OrderedStringList:\r |
| 922 | self.OrderedStringList[Language] = []\r | |
| 923 | self.OrderedStringDict[Language] = {}\r | |
| f7496d71 | 924 | \r |
| 421ccda3 HC |
925 | IsAdded = True\r |
| 926 | if Name in self.OrderedStringDict[Language]:\r | |
| 927 | IsAdded = False\r | |
| 4231a819 | 928 | if Value is not None:\r |
| 421ccda3 HC |
929 | ItemIndexInList = self.OrderedStringDict[Language][Name]\r |
| 930 | Item = self.OrderedStringList[Language][ItemIndexInList]\r | |
| 931 | Item.UpdateValue(Value)\r | |
| f7496d71 | 932 | Item.UseOtherLangDef = ''\r |
| 421ccda3 HC |
933 | \r |
| 934 | if IsAdded:\r | |
| 935 | Token = len(self.OrderedStringList[Language])\r | |
| 936 | if Index == -1:\r | |
| f7496d71 LG |
937 | self.OrderedStringList[Language].append(StringDefClassObject(Name,\r |
| 938 | Value,\r | |
| 939 | Referenced,\r | |
| 940 | Token,\r | |
| 421ccda3 HC |
941 | UseOtherLangDef))\r |
| 942 | self.OrderedStringDict[Language][Name] = Token\r | |
| 943 | for LangName in self.LanguageDef:\r | |
| 944 | #\r | |
| 945 | # New STRING token will be added into all language string lists.\r | |
| f7496d71 | 946 | # so that the unique STRING identifier is reserved for all languages in the package list.\r |
| 421ccda3 HC |
947 | #\r |
| 948 | if LangName[0] != Language:\r | |
| 949 | if UseOtherLangDef != '':\r | |
| 950 | OtherLangDef = UseOtherLangDef\r | |
| 951 | else:\r | |
| 952 | OtherLangDef = Language\r | |
| f7496d71 LG |
953 | self.OrderedStringList[LangName[0]].append(StringDefClassObject(Name,\r |
| 954 | '',\r | |
| 955 | Referenced,\r | |
| 956 | Token,\r | |
| 421ccda3 HC |
957 | OtherLangDef))\r |
| 958 | self.OrderedStringDict[LangName[0]][Name] = len(self.OrderedStringList[LangName[0]]) - 1\r | |
| 959 | else:\r | |
| f7496d71 LG |
960 | self.OrderedStringList[Language].insert(Index, StringDefClassObject(Name,\r |
| 961 | Value,\r | |
| 962 | Referenced,\r | |
| 963 | Token,\r | |
| 421ccda3 HC |
964 | UseOtherLangDef))\r |
| 965 | self.OrderedStringDict[Language][Name] = Index\r | |
| 966 | \r | |
| 967 | #\r | |
| 968 | # Set the string as referenced\r | |
| 969 | #\r | |
| 970 | def SetStringReferenced(self, Name):\r | |
| 971 | #\r | |
| 972 | # String stoken are added in the same order in all language string lists.\r | |
| 973 | # So, only update the status of string stoken in first language string list.\r | |
| 974 | #\r | |
| 975 | Lang = self.LanguageDef[0][0]\r | |
| 976 | if Name in self.OrderedStringDict[Lang]:\r | |
| 977 | ItemIndexInList = self.OrderedStringDict[Lang][Name]\r | |
| 978 | Item = self.OrderedStringList[Lang][ItemIndexInList]\r | |
| 979 | Item.Referenced = True\r | |
| 980 | \r | |
| 981 | #\r | |
| 982 | # Search the string in language definition by Name\r | |
| 983 | #\r | |
| 984 | def FindStringValue(self, Name, Lang):\r | |
| 985 | if Name in self.OrderedStringDict[Lang]:\r | |
| 986 | ItemIndexInList = self.OrderedStringDict[Lang][Name]\r | |
| 987 | return self.OrderedStringList[Lang][ItemIndexInList]\r | |
| 988 | \r | |
| 989 | return None\r | |
| 990 | \r | |
| 991 | #\r | |
| 992 | # Search the string in language definition by Token\r | |
| 993 | #\r | |
| 994 | def FindByToken(self, Token, Lang):\r | |
| 995 | for Item in self.OrderedStringList[Lang]:\r | |
| 996 | if Item.Token == Token:\r | |
| 997 | return Item\r | |
| 998 | \r | |
| 999 | return None\r | |
| 1000 | \r | |
| 1001 | #\r | |
| 1002 | # Re-order strings and re-generate tokens\r | |
| 1003 | #\r | |
| 1004 | def ReToken(self):\r | |
| 1005 | if len(self.LanguageDef) == 0:\r | |
| 1006 | return None\r | |
| 1007 | #\r | |
| 1008 | # Retoken all language strings according to the status of string stoken in the first language string.\r | |
| 1009 | #\r | |
| 1010 | FirstLangName = self.LanguageDef[0][0]\r | |
| 1011 | \r | |
| 1012 | # Convert the OrderedStringList to be OrderedStringListByToken in order to faciliate future search by token\r | |
| 1013 | for LangNameItem in self.LanguageDef:\r | |
| 1014 | self.OrderedStringListByToken[LangNameItem[0]] = {}\r | |
| 1015 | \r | |
| 1016 | #\r | |
| 1017 | # Use small token for all referred string stoken.\r | |
| 1018 | #\r | |
| 1019 | RefToken = 0\r | |
| 1020 | for Index in range (0, len (self.OrderedStringList[FirstLangName])):\r | |
| 1021 | FirstLangItem = self.OrderedStringList[FirstLangName][Index]\r | |
| 1022 | if FirstLangItem.Referenced == True:\r | |
| 1023 | for LangNameItem in self.LanguageDef:\r | |
| 1024 | LangName = LangNameItem[0]\r | |
| 1025 | OtherLangItem = self.OrderedStringList[LangName][Index]\r | |
| 1026 | OtherLangItem.Referenced = True\r | |
| 1027 | OtherLangItem.Token = RefToken\r | |
| 1028 | self.OrderedStringListByToken[LangName][OtherLangItem.Token] = OtherLangItem\r | |
| 1029 | RefToken = RefToken + 1\r | |
| 1030 | \r | |
| 1031 | #\r | |
| 1032 | # Use big token for all unreferred string stoken.\r | |
| 1033 | #\r | |
| 1034 | UnRefToken = 0\r | |
| 1035 | for Index in range (0, len (self.OrderedStringList[FirstLangName])):\r | |
| 1036 | FirstLangItem = self.OrderedStringList[FirstLangName][Index]\r | |
| 1037 | if FirstLangItem.Referenced == False:\r | |
| 1038 | for LangNameItem in self.LanguageDef:\r | |
| 1039 | LangName = LangNameItem[0]\r | |
| 1040 | OtherLangItem = self.OrderedStringList[LangName][Index]\r | |
| 1041 | OtherLangItem.Token = RefToken + UnRefToken\r | |
| 1042 | self.OrderedStringListByToken[LangName][OtherLangItem.Token] = OtherLangItem\r | |
| 1043 | UnRefToken = UnRefToken + 1\r | |
| 1044 | \r | |
| 1045 | #\r | |
| 1046 | # Show the instance itself\r | |
| 1047 | #\r | |
| 1048 | def ShowMe(self):\r | |
| 72443dd2 | 1049 | print(self.LanguageDef)\r |
| 421ccda3 HC |
1050 | #print self.OrderedStringList\r |
| 1051 | for Item in self.OrderedStringList:\r | |
| 72443dd2 | 1052 | print(Item)\r |
| 421ccda3 | 1053 | for Member in self.OrderedStringList[Item]:\r |
| 72443dd2 | 1054 | print(str(Member))\r |
| f7496d71 | 1055 | \r |
| 421ccda3 | 1056 | #\r |
| f7496d71 | 1057 | # Read content from '!include' UNI file\r |
| 421ccda3 HC |
1058 | #\r |
| 1059 | def ReadIncludeUNIfile(self, FilaPath):\r | |
| 1060 | if self.File:\r | |
| 1061 | pass\r | |
| f7496d71 | 1062 | \r |
| 421ccda3 | 1063 | if not os.path.exists(FilaPath) or not os.path.isfile(FilaPath):\r |
| f7496d71 | 1064 | EdkLogger.Error("Unicode File Parser",\r |
| 421ccda3 HC |
1065 | ToolError.FILE_NOT_FOUND,\r |
| 1066 | ExtraData=FilaPath)\r | |
| 1067 | try:\r | |
| 645a5128 | 1068 | FileIn = codecs.open(FilaPath, mode='rb', encoding='utf_8').readlines()\r |
| 5b0671c1 | 1069 | except UnicodeError as Xstr:\r |
| 421ccda3 HC |
1070 | FileIn = codecs.open(FilaPath, mode='rb', encoding='utf_16').readlines()\r |
| 1071 | except UnicodeError:\r | |
| 1072 | FileIn = codecs.open(FilaPath, mode='rb', encoding='utf_16_le').readlines()\r | |
| 1073 | except:\r | |
| 1074 | EdkLogger.Error("Unicode File Parser", ToolError.FILE_OPEN_FAILURE, ExtraData=FilaPath)\r | |
| 1075 | return FileIn\r | |
| 1076 | \r |