projects / mirror_edk2.git / blame
| Commit | Line | Data |
|---|---|---|
| 97fa0ee9 YL |
1 | ## @file\r |
| 2 | # This file is used to collect all defined strings in multiple uni files\r | |
| 3 | #\r | |
| 71f02911 CS |
4 | #\r |
| 5 | # Copyright (c) 2014 Hewlett-Packard Development Company, L.P.<BR>\r | |
| 6 | #\r | |
| 018f7b82 | 7 | # Copyright (c) 2007 - 2018, Intel Corporation. All rights reserved.<BR>\r |
| 40d841f6 | 8 | # This program and the accompanying materials\r |
| 30fdf114 LG |
9 | # are licensed and made available under the terms and conditions of the BSD License\r |
| 10 | # which accompanies this distribution. The full text of the license may be found at\r | |
| 11 | # http://opensource.org/licenses/bsd-license.php\r | |
| 12 | #\r | |
| 13 | # THE PROGRAM IS DISTRIBUTED UNDER THE BSD LICENSE ON AN "AS IS" BASIS,\r | |
| 14 | # WITHOUT WARRANTIES OR REPRESENTATIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED.\r | |
| 15 | \r | |
| 30fdf114 LG |
16 | ##\r |
| 17 | # Import Modules\r | |
| 18 | #\r | |
| 1ccc4d89 | 19 | from __future__ import print_function\r |
| 1be2ed90 | 20 | import Common.LongFilePathOs as os, codecs, re\r |
| 40d841f6 | 21 | import distutils.util\r |
| 30fdf114 | 22 | import Common.EdkLogger as EdkLogger\r |
| 86379ac4 | 23 | from io import BytesIO\r |
| 30fdf114 | 24 | from Common.BuildToolError import *\r |
| 5a57246e | 25 | from Common.StringUtils import GetLineNo\r |
| 30fdf114 | 26 | from Common.Misc import PathClass\r |
| d943b0c3 | 27 | from Common.LongFilePathSupport import LongFilePath\r |
| 018f7b82 | 28 | from Common.GlobalData import *\r |
| 30fdf114 LG |
29 | ##\r |
| 30 | # Static definitions\r | |
| 31 | #\r | |
| 32 | UNICODE_WIDE_CHAR = u'\\wide'\r | |
| 33 | UNICODE_NARROW_CHAR = u'\\narrow'\r | |
| 34 | UNICODE_NON_BREAKING_CHAR = u'\\nbr'\r | |
| 35 | UNICODE_UNICODE_CR = '\r'\r | |
| 36 | UNICODE_UNICODE_LF = '\n'\r | |
| 37 | \r | |
| 38 | NARROW_CHAR = u'\uFFF0'\r | |
| 39 | WIDE_CHAR = u'\uFFF1'\r | |
| 40 | NON_BREAKING_CHAR = u'\uFFF2'\r | |
| 41 | CR = u'\u000D'\r | |
| 42 | LF = u'\u000A'\r | |
| 43 | NULL = u'\u0000'\r | |
| 44 | TAB = u'\t'\r | |
| 71f02911 | 45 | BACK_SLASH_PLACEHOLDER = u'\u0006'\r |
| 30fdf114 LG |
46 | \r |
| 47 | gIncludePattern = re.compile("^#include +[\"<]+([^\"< >]+)[>\"]+$", re.MULTILINE | re.UNICODE)\r | |
| 48 | \r | |
| 30fdf114 LG |
49 | ## Convert a unicode string to a Hex list\r |
| 50 | #\r | |
| 51 | # Convert a unicode string to a Hex list\r | |
| 52 | # UniToHexList('ABC') is ['0x41', '0x00', '0x42', '0x00', '0x43', '0x00']\r | |
| 53 | #\r | |
| 54 | # @param Uni: The python unicode string\r | |
| 55 | #\r | |
| 56 | # @retval List: The formatted hex list\r | |
| 57 | #\r | |
| 58 | def UniToHexList(Uni):\r | |
| 59 | List = []\r | |
| 60 | for Item in Uni:\r | |
| 61 | Temp = '%04X' % ord(Item)\r | |
| 62 | List.append('0x' + Temp[2:4])\r | |
| 63 | List.append('0x' + Temp[0:2])\r | |
| 64 | return List\r | |
| 65 | \r | |
| 66 | LangConvTable = {'eng':'en', 'fra':'fr', \\r | |
| 67 | 'aar':'aa', 'abk':'ab', 'ave':'ae', 'afr':'af', 'aka':'ak', 'amh':'am', \\r | |
| 68 | 'arg':'an', 'ara':'ar', 'asm':'as', 'ava':'av', 'aym':'ay', 'aze':'az', \\r | |
| 69 | 'bak':'ba', 'bel':'be', 'bul':'bg', 'bih':'bh', 'bis':'bi', 'bam':'bm', \\r | |
| 70 | 'ben':'bn', 'bod':'bo', 'bre':'br', 'bos':'bs', 'cat':'ca', 'che':'ce', \\r | |
| 71 | 'cha':'ch', 'cos':'co', 'cre':'cr', 'ces':'cs', 'chu':'cu', 'chv':'cv', \\r | |
| 72 | 'cym':'cy', 'dan':'da', 'deu':'de', 'div':'dv', 'dzo':'dz', 'ewe':'ee', \\r | |
| 73 | 'ell':'el', 'epo':'eo', 'spa':'es', 'est':'et', 'eus':'eu', 'fas':'fa', \\r | |
| 74 | 'ful':'ff', 'fin':'fi', 'fij':'fj', 'fao':'fo', 'fry':'fy', 'gle':'ga', \\r | |
| 75 | 'gla':'gd', 'glg':'gl', 'grn':'gn', 'guj':'gu', 'glv':'gv', 'hau':'ha', \\r | |
| 76 | 'heb':'he', 'hin':'hi', 'hmo':'ho', 'hrv':'hr', 'hat':'ht', 'hun':'hu', \\r | |
| 77 | 'hye':'hy', 'her':'hz', 'ina':'ia', 'ind':'id', 'ile':'ie', 'ibo':'ig', \\r | |
| 78 | 'iii':'ii', 'ipk':'ik', 'ido':'io', 'isl':'is', 'ita':'it', 'iku':'iu', \\r | |
| 79 | 'jpn':'ja', 'jav':'jv', 'kat':'ka', 'kon':'kg', 'kik':'ki', 'kua':'kj', \\r | |
| 80 | 'kaz':'kk', 'kal':'kl', 'khm':'km', 'kan':'kn', 'kor':'ko', 'kau':'kr', \\r | |
| 81 | 'kas':'ks', 'kur':'ku', 'kom':'kv', 'cor':'kw', 'kir':'ky', 'lat':'la', \\r | |
| 82 | 'ltz':'lb', 'lug':'lg', 'lim':'li', 'lin':'ln', 'lao':'lo', 'lit':'lt', \\r | |
| 83 | 'lub':'lu', 'lav':'lv', 'mlg':'mg', 'mah':'mh', 'mri':'mi', 'mkd':'mk', \\r | |
| 84 | 'mal':'ml', 'mon':'mn', 'mar':'mr', 'msa':'ms', 'mlt':'mt', 'mya':'my', \\r | |
| 85 | 'nau':'na', 'nob':'nb', 'nde':'nd', 'nep':'ne', 'ndo':'ng', 'nld':'nl', \\r | |
| 86 | 'nno':'nn', 'nor':'no', 'nbl':'nr', 'nav':'nv', 'nya':'ny', 'oci':'oc', \\r | |
| 87 | 'oji':'oj', 'orm':'om', 'ori':'or', 'oss':'os', 'pan':'pa', 'pli':'pi', \\r | |
| 88 | 'pol':'pl', 'pus':'ps', 'por':'pt', 'que':'qu', 'roh':'rm', 'run':'rn', \\r | |
| 89 | 'ron':'ro', 'rus':'ru', 'kin':'rw', 'san':'sa', 'srd':'sc', 'snd':'sd', \\r | |
| 90 | 'sme':'se', 'sag':'sg', 'sin':'si', 'slk':'sk', 'slv':'sl', 'smo':'sm', \\r | |
| 91 | 'sna':'sn', 'som':'so', 'sqi':'sq', 'srp':'sr', 'ssw':'ss', 'sot':'st', \\r | |
| 92 | 'sun':'su', 'swe':'sv', 'swa':'sw', 'tam':'ta', 'tel':'te', 'tgk':'tg', \\r | |
| 93 | 'tha':'th', 'tir':'ti', 'tuk':'tk', 'tgl':'tl', 'tsn':'tn', 'ton':'to', \\r | |
| 94 | 'tur':'tr', 'tso':'ts', 'tat':'tt', 'twi':'tw', 'tah':'ty', 'uig':'ug', \\r | |
| 95 | 'ukr':'uk', 'urd':'ur', 'uzb':'uz', 'ven':'ve', 'vie':'vi', 'vol':'vo', \\r | |
| 96 | 'wln':'wa', 'wol':'wo', 'xho':'xh', 'yid':'yi', 'yor':'yo', 'zha':'za', \\r | |
| 97 | 'zho':'zh', 'zul':'zu'}\r | |
| 98 | \r | |
| 99 | ## GetLanguageCode\r | |
| 100 | #\r | |
| 101 | # Check the language code read from .UNI file and convert ISO 639-2 codes to RFC 4646 codes if appropriate\r | |
| fb0b35e0 | 102 | # ISO 639-2 language codes supported in compatibility mode\r |
| 30fdf114 LG |
103 | # RFC 4646 language codes supported in native mode\r |
| 104 | #\r | |
| 105 | # @param LangName: Language codes read from .UNI file\r | |
| 106 | #\r | |
| fb0b35e0 | 107 | # @retval LangName: Valid language code in RFC 4646 format or None\r |
| 30fdf114 LG |
108 | #\r |
| 109 | def GetLanguageCode(LangName, IsCompatibleMode, File):\r | |
| 30fdf114 LG |
110 | length = len(LangName)\r |
| 111 | if IsCompatibleMode:\r | |
| 112 | if length == 3 and LangName.isalpha():\r | |
| 113 | TempLangName = LangConvTable.get(LangName.lower())\r | |
| 4231a819 | 114 | if TempLangName is not None:\r |
| da92f276 | 115 | return TempLangName\r |
| 30fdf114 LG |
116 | return LangName\r |
| 117 | else:\r | |
| 118 | EdkLogger.error("Unicode File Parser", FORMAT_INVALID, "Invalid ISO 639-2 language code : %s" % LangName, File)\r | |
| 119 | \r | |
| 40d841f6 LG |
120 | if (LangName[0] == 'X' or LangName[0] == 'x') and LangName[1] == '-':\r |
| 121 | return LangName\r | |
| 30fdf114 LG |
122 | if length == 2:\r |
| 123 | if LangName.isalpha():\r | |
| 124 | return LangName\r | |
| 125 | elif length == 3:\r | |
| 4231a819 | 126 | if LangName.isalpha() and LangConvTable.get(LangName.lower()) is None:\r |
| 30fdf114 LG |
127 | return LangName\r |
| 128 | elif length == 5:\r | |
| 129 | if LangName[0:2].isalpha() and LangName[2] == '-':\r | |
| 130 | return LangName\r | |
| 131 | elif length >= 6:\r | |
| 132 | if LangName[0:2].isalpha() and LangName[2] == '-':\r | |
| 133 | return LangName\r | |
| 4231a819 | 134 | if LangName[0:3].isalpha() and LangConvTable.get(LangName.lower()) is None and LangName[3] == '-':\r |
| 30fdf114 LG |
135 | return LangName\r |
| 136 | \r | |
| 137 | EdkLogger.error("Unicode File Parser", FORMAT_INVALID, "Invalid RFC 4646 language code : %s" % LangName, File)\r | |
| 138 | \r | |
| d80e451b JJ |
139 | ## Ucs2Codec\r |
| 140 | #\r | |
| 141 | # This is only a partial codec implementation. It only supports\r | |
| 142 | # encoding, and is primarily used to check that all the characters are\r | |
| 143 | # valid for UCS-2.\r | |
| 144 | #\r | |
| 145 | class Ucs2Codec(codecs.Codec):\r | |
| 146 | def __init__(self):\r | |
| 147 | self.__utf16 = codecs.lookup('utf-16')\r | |
| 148 | \r | |
| 149 | def encode(self, input, errors='strict'):\r | |
| 150 | for Char in input:\r | |
| 151 | CodePoint = ord(Char)\r | |
| 152 | if CodePoint >= 0xd800 and CodePoint <= 0xdfff:\r | |
| 153 | raise ValueError("Code Point is in range reserved for " +\r | |
| 154 | "UTF-16 surrogate pairs")\r | |
| 155 | elif CodePoint > 0xffff:\r | |
| 156 | raise ValueError("Code Point too large to encode in UCS-2")\r | |
| 157 | return self.__utf16.encode(input)\r | |
| 158 | \r | |
| 159 | TheUcs2Codec = Ucs2Codec()\r | |
| 160 | def Ucs2Search(name):\r | |
| 161 | if name == 'ucs-2':\r | |
| 162 | return codecs.CodecInfo(\r | |
| 163 | name=name,\r | |
| 164 | encode=TheUcs2Codec.encode,\r | |
| 165 | decode=TheUcs2Codec.decode)\r | |
| 166 | else:\r | |
| 167 | return None\r | |
| 168 | codecs.register(Ucs2Search)\r | |
| 169 | \r | |
| 30fdf114 LG |
170 | ## StringDefClassObject\r |
| 171 | #\r | |
| 172 | # A structure for language definition\r | |
| 173 | #\r | |
| 174 | class StringDefClassObject(object):\r | |
| 175 | def __init__(self, Name = None, Value = None, Referenced = False, Token = None, UseOtherLangDef = ''):\r | |
| 176 | self.StringName = ''\r | |
| 177 | self.StringNameByteList = []\r | |
| 178 | self.StringValue = ''\r | |
| 179 | self.StringValueByteList = ''\r | |
| 180 | self.Token = 0\r | |
| 181 | self.Referenced = Referenced\r | |
| 182 | self.UseOtherLangDef = UseOtherLangDef\r | |
| 183 | self.Length = 0\r | |
| 184 | \r | |
| 4231a819 | 185 | if Name is not None:\r |
| 30fdf114 LG |
186 | self.StringName = Name\r |
| 187 | self.StringNameByteList = UniToHexList(Name)\r | |
| 4231a819 | 188 | if Value is not None:\r |
| 30fdf114 LG |
189 | self.StringValue = Value + u'\x00' # Add a NULL at string tail\r |
| 190 | self.StringValueByteList = UniToHexList(self.StringValue)\r | |
| 191 | self.Length = len(self.StringValueByteList)\r | |
| 4231a819 | 192 | if Token is not None:\r |
| 30fdf114 LG |
193 | self.Token = Token\r |
| 194 | \r | |
| 195 | def __str__(self):\r | |
| 196 | return repr(self.StringName) + ' ' + \\r | |
| 197 | repr(self.Token) + ' ' + \\r | |
| 198 | repr(self.Referenced) + ' ' + \\r | |
| 199 | repr(self.StringValue) + ' ' + \\r | |
| 200 | repr(self.UseOtherLangDef)\r | |
| 201 | \r | |
| 756ad8f8 | 202 | def UpdateValue(self, Value = None):\r |
| 4231a819 | 203 | if Value is not None:\r |
| 756ad8f8 LG |
204 | self.StringValue = Value + u'\x00' # Add a NULL at string tail\r |
| 205 | self.StringValueByteList = UniToHexList(self.StringValue)\r | |
| 206 | self.Length = len(self.StringValueByteList)\r | |
| 207 | \r | |
| c23ef28c CJ |
208 | def StripComments(Line):\r |
| 209 | Comment = u'//'\r | |
| 210 | CommentPos = Line.find(Comment)\r | |
| 211 | while CommentPos >= 0:\r | |
| 212 | # if there are non matched quotes before the comment header\r | |
| 213 | # then we are in the middle of a string\r | |
| 214 | # but we need to ignore the escaped quotes and backslashes.\r | |
| 215 | if ((Line.count(u'"', 0, CommentPos) - Line.count(u'\\"', 0, CommentPos)) & 1) == 1:\r | |
| 216 | CommentPos = Line.find (Comment, CommentPos + 1)\r | |
| 217 | else:\r | |
| 218 | return Line[:CommentPos].strip()\r | |
| 219 | return Line.strip()\r | |
| 220 | \r | |
| 30fdf114 LG |
221 | ## UniFileClassObject\r |
| 222 | #\r | |
| 223 | # A structure for .uni file definition\r | |
| 224 | #\r | |
| 225 | class UniFileClassObject(object):\r | |
| 756ad8f8 | 226 | def __init__(self, FileList = [], IsCompatibleMode = False, IncludePathList = []):\r |
| 30fdf114 LG |
227 | self.FileList = FileList\r |
| 228 | self.Token = 2\r | |
| 229 | self.LanguageDef = [] #[ [u'LanguageIdentifier', u'PrintableName'], ... ]\r | |
| 230 | self.OrderedStringList = {} #{ u'LanguageIdentifier' : [StringDefClassObject] }\r | |
| 79b74a03 LG |
231 | self.OrderedStringDict = {} #{ u'LanguageIdentifier' : {StringName:(IndexInList)} }\r |
| 232 | self.OrderedStringListByToken = {} #{ u'LanguageIdentifier' : {Token: StringDefClassObject} }\r | |
| 30fdf114 | 233 | self.IsCompatibleMode = IsCompatibleMode\r |
| 756ad8f8 | 234 | self.IncludePathList = IncludePathList\r |
| 30fdf114 LG |
235 | if len(self.FileList) > 0:\r |
| 236 | self.LoadUniFiles(FileList)\r | |
| 237 | \r | |
| 238 | #\r | |
| 239 | # Get Language definition\r | |
| 240 | #\r | |
| 241 | def GetLangDef(self, File, Line):\r | |
| 40d841f6 | 242 | Lang = distutils.util.split_quoted((Line.split(u"//")[0]))\r |
| 30fdf114 LG |
243 | if len(Lang) != 3:\r |
| 244 | try:\r | |
| 3b743b3b | 245 | FileIn = UniFileClassObject.OpenUniFile(LongFilePath(File.Path))\r |
| 5b0671c1 | 246 | except UnicodeError as X:\r |
| 30fdf114 LG |
247 | EdkLogger.error("build", FILE_READ_FAILURE, "File read failure: %s" % str(X), ExtraData=File);\r |
| 248 | except:\r | |
| 249 | EdkLogger.error("build", FILE_OPEN_FAILURE, ExtraData=File);\r | |
| 250 | LineNo = GetLineNo(FileIn, Line, False)\r | |
| 251 | EdkLogger.error("Unicode File Parser", PARSER_ERROR, "Wrong language definition",\r | |
| 47fea6af | 252 | ExtraData="""%s\n\t*Correct format is like '#langdef en-US "English"'""" % Line, File=File, Line=LineNo)\r |
| 30fdf114 LG |
253 | else:\r |
| 254 | LangName = GetLanguageCode(Lang[1], self.IsCompatibleMode, self.File)\r | |
| 40d841f6 | 255 | LangPrintName = Lang[2]\r |
| 30fdf114 LG |
256 | \r |
| 257 | IsLangInDef = False\r | |
| 258 | for Item in self.LanguageDef:\r | |
| 259 | if Item[0] == LangName:\r | |
| 260 | IsLangInDef = True\r | |
| 261 | break;\r | |
| 262 | \r | |
| 263 | if not IsLangInDef:\r | |
| 264 | self.LanguageDef.append([LangName, LangPrintName])\r | |
| 265 | \r | |
| 266 | #\r | |
| 267 | # Add language string\r | |
| 268 | #\r | |
| 269 | self.AddStringToList(u'$LANGUAGE_NAME', LangName, LangName, 0, True, Index=0)\r | |
| 270 | self.AddStringToList(u'$PRINTABLE_LANGUAGE_NAME', LangName, LangPrintName, 1, True, Index=1)\r | |
| 271 | \r | |
| 756ad8f8 LG |
272 | if not IsLangInDef:\r |
| 273 | #\r | |
| 274 | # The found STRING tokens will be added into new language string list\r | |
| f7496d71 | 275 | # so that the unique STRING identifier is reserved for all languages in the package list.\r |
| 756ad8f8 LG |
276 | #\r |
| 277 | FirstLangName = self.LanguageDef[0][0]\r | |
| 278 | if LangName != FirstLangName:\r | |
| 279 | for Index in range (2, len (self.OrderedStringList[FirstLangName])):\r | |
| 280 | Item = self.OrderedStringList[FirstLangName][Index]\r | |
| 281 | if Item.UseOtherLangDef != '':\r | |
| 282 | OtherLang = Item.UseOtherLangDef\r | |
| 283 | else:\r | |
| 284 | OtherLang = FirstLangName\r | |
| 285 | self.OrderedStringList[LangName].append (StringDefClassObject(Item.StringName, '', Item.Referenced, Item.Token, OtherLang))\r | |
| 79b74a03 | 286 | self.OrderedStringDict[LangName][Item.StringName] = len(self.OrderedStringList[LangName]) - 1\r |
| 30fdf114 LG |
287 | return True\r |
| 288 | \r | |
| 3b743b3b CJ |
289 | @staticmethod\r |
| 290 | def OpenUniFile(FileName):\r | |
| d80e451b JJ |
291 | #\r |
| 292 | # Read file\r | |
| 293 | #\r | |
| 294 | try:\r | |
| 295 | UniFile = open(FileName, mode='rb')\r | |
| 296 | FileIn = UniFile.read()\r | |
| 297 | UniFile.close()\r | |
| 298 | except:\r | |
| 299 | EdkLogger.Error("build", FILE_OPEN_FAILURE, ExtraData=File)\r | |
| 300 | \r | |
| 301 | #\r | |
| be264422 | 302 | # Detect Byte Order Mark at beginning of file. Default to UTF-8\r |
| d80e451b | 303 | #\r |
| be264422 JJ |
304 | Encoding = 'utf-8'\r |
| 305 | if (FileIn.startswith(codecs.BOM_UTF16_BE) or\r | |
| 306 | FileIn.startswith(codecs.BOM_UTF16_LE)):\r | |
| 307 | Encoding = 'utf-16'\r | |
| d80e451b | 308 | \r |
| 3b743b3b | 309 | UniFileClassObject.VerifyUcs2Data(FileIn, FileName, Encoding)\r |
| d80e451b | 310 | \r |
| 86379ac4 | 311 | UniFile = BytesIO(FileIn)\r |
| d80e451b JJ |
312 | Info = codecs.lookup(Encoding)\r |
| 313 | (Reader, Writer) = (Info.streamreader, Info.streamwriter)\r | |
| 314 | return codecs.StreamReaderWriter(UniFile, Reader, Writer)\r | |
| 315 | \r | |
| 3b743b3b CJ |
316 | @staticmethod\r |
| 317 | def VerifyUcs2Data(FileIn, FileName, Encoding):\r | |
| d80e451b JJ |
318 | Ucs2Info = codecs.lookup('ucs-2')\r |
| 319 | #\r | |
| 320 | # Convert to unicode\r | |
| 321 | #\r | |
| 322 | try:\r | |
| 323 | FileDecoded = codecs.decode(FileIn, Encoding)\r | |
| 324 | Ucs2Info.encode(FileDecoded)\r | |
| 325 | except:\r | |
| 86379ac4 | 326 | UniFile = BytesIO(FileIn)\r |
| d80e451b JJ |
327 | Info = codecs.lookup(Encoding)\r |
| 328 | (Reader, Writer) = (Info.streamreader, Info.streamwriter)\r | |
| 329 | File = codecs.StreamReaderWriter(UniFile, Reader, Writer)\r | |
| 330 | LineNumber = 0\r | |
| 331 | ErrMsg = lambda Encoding, LineNumber: \\r | |
| 332 | '%s contains invalid %s characters on line %d.' % \\r | |
| 333 | (FileName, Encoding, LineNumber)\r | |
| 334 | while True:\r | |
| 335 | LineNumber = LineNumber + 1\r | |
| 336 | try:\r | |
| 337 | Line = File.readline()\r | |
| 338 | if Line == '':\r | |
| 339 | EdkLogger.error('Unicode File Parser', PARSER_ERROR,\r | |
| 340 | ErrMsg(Encoding, LineNumber))\r | |
| 341 | Ucs2Info.encode(Line)\r | |
| 342 | except:\r | |
| 343 | EdkLogger.error('Unicode File Parser', PARSER_ERROR,\r | |
| 344 | ErrMsg('UCS-2', LineNumber))\r | |
| 345 | \r | |
| 30fdf114 LG |
346 | #\r |
| 347 | # Get String name and value\r | |
| 348 | #\r | |
| 349 | def GetStringObject(self, Item):\r | |
| 30fdf114 LG |
350 | Language = ''\r |
| 351 | Value = ''\r | |
| 352 | \r | |
| 353 | Name = Item.split()[1]\r | |
| c3915fa5 | 354 | # Check the string name\r |
| 2bcc713e | 355 | if Name != '':\r |
| 1f26f5fd | 356 | MatchString = gIdentifierPattern.match(Name)\r |
| bfc8f566 | 357 | if MatchString is None:\r |
| c3915fa5 | 358 | EdkLogger.error('Unicode File Parser', FORMAT_INVALID, 'The string token name %s defined in UNI file %s contains the invalid character.' % (Name, self.File))\r |
| 30fdf114 LG |
359 | LanguageList = Item.split(u'#language ')\r |
| 360 | for IndexI in range(len(LanguageList)):\r | |
| 361 | if IndexI == 0:\r | |
| 362 | continue\r | |
| 363 | else:\r | |
| 364 | Language = LanguageList[IndexI].split()[0]\r | |
| 365 | Value = LanguageList[IndexI][LanguageList[IndexI].find(u'\"') + len(u'\"') : LanguageList[IndexI].rfind(u'\"')] #.replace(u'\r\n', u'')\r | |
| 366 | Language = GetLanguageCode(Language, self.IsCompatibleMode, self.File)\r | |
| 367 | self.AddStringToList(Name, Language, Value)\r | |
| 368 | \r | |
| 369 | #\r | |
| 370 | # Get include file list and load them\r | |
| 371 | #\r | |
| 372 | def GetIncludeFile(self, Item, Dir):\r | |
| 373 | FileName = Item[Item.find(u'#include ') + len(u'#include ') :Item.find(u' ', len(u'#include '))][1:-1]\r | |
| 374 | self.LoadUniFile(FileName)\r | |
| 375 | \r | |
| 376 | #\r | |
| 377 | # Pre-process before parse .uni file\r | |
| 378 | #\r | |
| 379 | def PreProcess(self, File):\r | |
| 380 | if not os.path.exists(File.Path) or not os.path.isfile(File.Path):\r | |
| 381 | EdkLogger.error("Unicode File Parser", FILE_NOT_FOUND, ExtraData=File.Path)\r | |
| 382 | \r | |
| 30fdf114 | 383 | try:\r |
| 3b743b3b | 384 | FileIn = UniFileClassObject.OpenUniFile(LongFilePath(File.Path))\r |
| 5b0671c1 | 385 | except UnicodeError as X:\r |
| 30fdf114 LG |
386 | EdkLogger.error("build", FILE_READ_FAILURE, "File read failure: %s" % str(X), ExtraData=File.Path);\r |
| 387 | except:\r | |
| 388 | EdkLogger.error("build", FILE_OPEN_FAILURE, ExtraData=File.Path);\r | |
| 389 | \r | |
| 390 | Lines = []\r | |
| 391 | #\r | |
| 392 | # Use unique identifier\r | |
| 393 | #\r | |
| 394 | for Line in FileIn:\r | |
| 395 | Line = Line.strip()\r | |
| 71f02911 | 396 | Line = Line.replace(u'\\\\', BACK_SLASH_PLACEHOLDER)\r |
| c23ef28c | 397 | Line = StripComments(Line)\r |
| 71f02911 | 398 | \r |
| 30fdf114 | 399 | #\r |
| 71f02911 | 400 | # Ignore empty line\r |
| 30fdf114 | 401 | #\r |
| f7496d71 LG |
402 | if len(Line) == 0:\r |
| 403 | continue\r | |
| 404 | \r | |
| 405 | \r | |
| 30fdf114 LG |
406 | Line = Line.replace(u'/langdef', u'#langdef')\r |
| 407 | Line = Line.replace(u'/string', u'#string')\r | |
| 408 | Line = Line.replace(u'/language', u'#language')\r | |
| 409 | Line = Line.replace(u'/include', u'#include')\r | |
| 410 | \r | |
| 411 | Line = Line.replace(UNICODE_WIDE_CHAR, WIDE_CHAR)\r | |
| 412 | Line = Line.replace(UNICODE_NARROW_CHAR, NARROW_CHAR)\r | |
| 413 | Line = Line.replace(UNICODE_NON_BREAKING_CHAR, NON_BREAKING_CHAR)\r | |
| 414 | \r | |
| 30fdf114 LG |
415 | Line = Line.replace(u'\\r\\n', CR + LF)\r |
| 416 | Line = Line.replace(u'\\n', CR + LF)\r | |
| 417 | Line = Line.replace(u'\\r', CR)\r | |
| 71f02911 | 418 | Line = Line.replace(u'\\t', u' ')\r |
| 8546dfea | 419 | Line = Line.replace(u'\t', u' ')\r |
| f7496d71 LG |
420 | Line = Line.replace(u'\\"', u'"')\r |
| 421 | Line = Line.replace(u"\\'", u"'")\r | |
| 71f02911 | 422 | Line = Line.replace(BACK_SLASH_PLACEHOLDER, u'\\')\r |
| 4afd3d04 | 423 | \r |
| 314e2fb1 YZ |
424 | StartPos = Line.find(u'\\x')\r |
| 425 | while (StartPos != -1):\r | |
| 426 | EndPos = Line.find(u'\\', StartPos + 1, StartPos + 7)\r | |
| 427 | if EndPos != -1 and EndPos - StartPos == 6 :\r | |
| 018f7b82 | 428 | if g4HexChar.match(Line[StartPos + 2 : EndPos], re.UNICODE):\r |
| 314e2fb1 | 429 | EndStr = Line[EndPos: ]\r |
| d943b0c3 | 430 | UniStr = Line[StartPos + 2: EndPos]\r |
| 314e2fb1 | 431 | if EndStr.startswith(u'\\x') and len(EndStr) >= 7:\r |
| 018f7b82 | 432 | if EndStr[6] == u'\\' and g4HexChar.match(EndStr[2 : 6], re.UNICODE):\r |
| 314e2fb1 YZ |
433 | Line = Line[0 : StartPos] + UniStr + EndStr\r |
| 434 | else:\r | |
| 435 | Line = Line[0 : StartPos] + UniStr + EndStr[1:]\r | |
| ad319b93 | 436 | StartPos = Line.find(u'\\x', StartPos + 1)\r |
| 30fdf114 LG |
437 | \r |
| 438 | IncList = gIncludePattern.findall(Line)\r | |
| 439 | if len(IncList) == 1:\r | |
| 756ad8f8 LG |
440 | for Dir in [File.Dir] + self.IncludePathList:\r |
| 441 | IncFile = PathClass(str(IncList[0]), Dir)\r | |
| 442 | if os.path.isfile(IncFile.Path):\r | |
| 443 | Lines.extend(self.PreProcess(IncFile))\r | |
| 444 | break\r | |
| 445 | else:\r | |
| 446 | EdkLogger.error("Unicode File Parser", FILE_NOT_FOUND, Message="Cannot find include file", ExtraData=str(IncList[0]))\r | |
| 30fdf114 LG |
447 | continue\r |
| 448 | \r | |
| 449 | Lines.append(Line)\r | |
| 450 | \r | |
| 451 | return Lines\r | |
| 452 | \r | |
| 453 | #\r | |
| 454 | # Load a .uni file\r | |
| 455 | #\r | |
| 456 | def LoadUniFile(self, File = None):\r | |
| 4231a819 | 457 | if File is None:\r |
| 30fdf114 LG |
458 | EdkLogger.error("Unicode File Parser", PARSER_ERROR, 'No unicode file is given')\r |
| 459 | self.File = File\r | |
| 460 | #\r | |
| 461 | # Process special char in file\r | |
| 462 | #\r | |
| 463 | Lines = self.PreProcess(File)\r | |
| 464 | \r | |
| 465 | #\r | |
| 466 | # Get Unicode Information\r | |
| 467 | #\r | |
| 468 | for IndexI in range(len(Lines)):\r | |
| 469 | Line = Lines[IndexI]\r | |
| 470 | if (IndexI + 1) < len(Lines):\r | |
| 471 | SecondLine = Lines[IndexI + 1]\r | |
| 472 | if (IndexI + 2) < len(Lines):\r | |
| 473 | ThirdLine = Lines[IndexI + 2]\r | |
| 474 | \r | |
| 475 | #\r | |
| 476 | # Get Language def information\r | |
| 477 | #\r | |
| 478 | if Line.find(u'#langdef ') >= 0:\r | |
| 479 | self.GetLangDef(File, Line)\r | |
| 480 | continue\r | |
| 481 | \r | |
| 482 | Name = ''\r | |
| 483 | Language = ''\r | |
| 484 | Value = ''\r | |
| 485 | #\r | |
| 486 | # Get string def information format 1 as below\r | |
| 487 | #\r | |
| 488 | # #string MY_STRING_1\r | |
| 489 | # #language eng\r | |
| 490 | # My first English string line 1\r | |
| 491 | # My first English string line 2\r | |
| 492 | # #string MY_STRING_1\r | |
| 493 | # #language spa\r | |
| 494 | # Mi segunda secuencia 1\r | |
| 495 | # Mi segunda secuencia 2\r | |
| 496 | #\r | |
| 497 | if Line.find(u'#string ') >= 0 and Line.find(u'#language ') < 0 and \\r | |
| 498 | SecondLine.find(u'#string ') < 0 and SecondLine.find(u'#language ') >= 0 and \\r | |
| 499 | ThirdLine.find(u'#string ') < 0 and ThirdLine.find(u'#language ') < 0:\r | |
| 500 | Name = Line[Line.find(u'#string ') + len(u'#string ') : ].strip(' ')\r | |
| 501 | Language = SecondLine[SecondLine.find(u'#language ') + len(u'#language ') : ].strip(' ')\r | |
| 502 | for IndexJ in range(IndexI + 2, len(Lines)):\r | |
| 503 | if Lines[IndexJ].find(u'#string ') < 0 and Lines[IndexJ].find(u'#language ') < 0:\r | |
| 504 | Value = Value + Lines[IndexJ]\r | |
| 505 | else:\r | |
| 506 | IndexI = IndexJ\r | |
| 507 | break\r | |
| 508 | # Value = Value.replace(u'\r\n', u'')\r | |
| 509 | Language = GetLanguageCode(Language, self.IsCompatibleMode, self.File)\r | |
| c3915fa5 | 510 | # Check the string name\r |
| b303ea72 | 511 | if not self.IsCompatibleMode and Name != '':\r |
| 1f26f5fd | 512 | MatchString = gIdentifierPattern.match(Name)\r |
| bfc8f566 | 513 | if MatchString is None:\r |
| c3915fa5 | 514 | EdkLogger.error('Unicode File Parser', FORMAT_INVALID, 'The string token name %s defined in UNI file %s contains the invalid character.' % (Name, self.File))\r |
| 30fdf114 LG |
515 | self.AddStringToList(Name, Language, Value)\r |
| 516 | continue\r | |
| 517 | \r | |
| 518 | #\r | |
| 519 | # Get string def information format 2 as below\r | |
| 520 | #\r | |
| 521 | # #string MY_STRING_1 #language eng "My first English string line 1"\r | |
| 522 | # "My first English string line 2"\r | |
| 523 | # #language spa "Mi segunda secuencia 1"\r | |
| 524 | # "Mi segunda secuencia 2"\r | |
| 525 | # #string MY_STRING_2 #language eng "My first English string line 1"\r | |
| 526 | # "My first English string line 2"\r | |
| 527 | # #string MY_STRING_2 #language spa "Mi segunda secuencia 1"\r | |
| 528 | # "Mi segunda secuencia 2"\r | |
| 529 | #\r | |
| 530 | if Line.find(u'#string ') >= 0 and Line.find(u'#language ') >= 0:\r | |
| 531 | StringItem = Line\r | |
| 532 | for IndexJ in range(IndexI + 1, len(Lines)):\r | |
| 533 | if Lines[IndexJ].find(u'#string ') >= 0 and Lines[IndexJ].find(u'#language ') >= 0:\r | |
| 534 | IndexI = IndexJ\r | |
| 535 | break\r | |
| 536 | elif Lines[IndexJ].find(u'#string ') < 0 and Lines[IndexJ].find(u'#language ') >= 0:\r | |
| 537 | StringItem = StringItem + Lines[IndexJ]\r | |
| 538 | elif Lines[IndexJ].count(u'\"') >= 2:\r | |
| 539 | StringItem = StringItem[ : StringItem.rfind(u'\"')] + Lines[IndexJ][Lines[IndexJ].find(u'\"') + len(u'\"') : ]\r | |
| 540 | self.GetStringObject(StringItem)\r | |
| 541 | continue\r | |
| 542 | \r | |
| 543 | #\r | |
| 544 | # Load multiple .uni files\r | |
| 545 | #\r | |
| 52302d4d | 546 | def LoadUniFiles(self, FileList):\r |
| 30fdf114 | 547 | if len(FileList) > 0:\r |
| 52302d4d LG |
548 | for File in FileList:\r |
| 549 | self.LoadUniFile(File)\r | |
| 30fdf114 LG |
550 | \r |
| 551 | #\r | |
| 552 | # Add a string to list\r | |
| 553 | #\r | |
| 554 | def AddStringToList(self, Name, Language, Value, Token = None, Referenced = False, UseOtherLangDef = '', Index = -1):\r | |
| 08dd311f LG |
555 | for LangNameItem in self.LanguageDef:\r |
| 556 | if Language == LangNameItem[0]:\r | |
| 557 | break\r | |
| 558 | else:\r | |
| 559 | EdkLogger.error('Unicode File Parser', FORMAT_NOT_SUPPORTED, "The language '%s' for %s is not defined in Unicode file %s." \\r | |
| 560 | % (Language, Name, self.File))\r | |
| f7496d71 | 561 | \r |
| 30fdf114 LG |
562 | if Language not in self.OrderedStringList:\r |
| 563 | self.OrderedStringList[Language] = []\r | |
| 79b74a03 | 564 | self.OrderedStringDict[Language] = {}\r |
| 30fdf114 | 565 | \r |
| 756ad8f8 | 566 | IsAdded = True\r |
| 79b74a03 LG |
567 | if Name in self.OrderedStringDict[Language]:\r |
| 568 | IsAdded = False\r | |
| 4231a819 | 569 | if Value is not None:\r |
| 79b74a03 LG |
570 | ItemIndexInList = self.OrderedStringDict[Language][Name]\r |
| 571 | Item = self.OrderedStringList[Language][ItemIndexInList]\r | |
| 572 | Item.UpdateValue(Value)\r | |
| 47fea6af | 573 | Item.UseOtherLangDef = ''\r |
| 756ad8f8 LG |
574 | \r |
| 575 | if IsAdded:\r | |
| 30fdf114 LG |
576 | Token = len(self.OrderedStringList[Language])\r |
| 577 | if Index == -1:\r | |
| 578 | self.OrderedStringList[Language].append(StringDefClassObject(Name, Value, Referenced, Token, UseOtherLangDef))\r | |
| 79b74a03 | 579 | self.OrderedStringDict[Language][Name] = Token\r |
| 756ad8f8 LG |
580 | for LangName in self.LanguageDef:\r |
| 581 | #\r | |
| 582 | # New STRING token will be added into all language string lists.\r | |
| f7496d71 | 583 | # so that the unique STRING identifier is reserved for all languages in the package list.\r |
| 756ad8f8 LG |
584 | #\r |
| 585 | if LangName[0] != Language:\r | |
| 586 | if UseOtherLangDef != '':\r | |
| 587 | OtherLangDef = UseOtherLangDef\r | |
| 588 | else:\r | |
| 589 | OtherLangDef = Language\r | |
| 590 | self.OrderedStringList[LangName[0]].append(StringDefClassObject(Name, '', Referenced, Token, OtherLangDef))\r | |
| 79b74a03 | 591 | self.OrderedStringDict[LangName[0]][Name] = len(self.OrderedStringList[LangName[0]]) - 1\r |
| 30fdf114 LG |
592 | else:\r |
| 593 | self.OrderedStringList[Language].insert(Index, StringDefClassObject(Name, Value, Referenced, Token, UseOtherLangDef))\r | |
| 79b74a03 | 594 | self.OrderedStringDict[Language][Name] = Index\r |
| 30fdf114 LG |
595 | \r |
| 596 | #\r | |
| 597 | # Set the string as referenced\r | |
| 598 | #\r | |
| 599 | def SetStringReferenced(self, Name):\r | |
| 756ad8f8 LG |
600 | #\r |
| 601 | # String stoken are added in the same order in all language string lists.\r | |
| 602 | # So, only update the status of string stoken in first language string list.\r | |
| 603 | #\r | |
| 604 | Lang = self.LanguageDef[0][0]\r | |
| 79b74a03 LG |
605 | if Name in self.OrderedStringDict[Lang]:\r |
| 606 | ItemIndexInList = self.OrderedStringDict[Lang][Name]\r | |
| 607 | Item = self.OrderedStringList[Lang][ItemIndexInList]\r | |
| 608 | Item.Referenced = True\r | |
| 609 | \r | |
| 30fdf114 LG |
610 | #\r |
| 611 | # Search the string in language definition by Name\r | |
| 612 | #\r | |
| 613 | def FindStringValue(self, Name, Lang):\r | |
| 79b74a03 LG |
614 | if Name in self.OrderedStringDict[Lang]:\r |
| 615 | ItemIndexInList = self.OrderedStringDict[Lang][Name]\r | |
| 616 | return self.OrderedStringList[Lang][ItemIndexInList]\r | |
| 30fdf114 LG |
617 | \r |
| 618 | return None\r | |
| 619 | \r | |
| 620 | #\r | |
| 621 | # Search the string in language definition by Token\r | |
| 622 | #\r | |
| 623 | def FindByToken(self, Token, Lang):\r | |
| 624 | for Item in self.OrderedStringList[Lang]:\r | |
| 625 | if Item.Token == Token:\r | |
| 626 | return Item\r | |
| 627 | \r | |
| 628 | return None\r | |
| 629 | \r | |
| 630 | #\r | |
| 631 | # Re-order strings and re-generate tokens\r | |
| 632 | #\r | |
| 633 | def ReToken(self):\r | |
| 634 | #\r | |
| 756ad8f8 | 635 | # Retoken all language strings according to the status of string stoken in the first language string.\r |
| 30fdf114 | 636 | #\r |
| 756ad8f8 | 637 | FirstLangName = self.LanguageDef[0][0]\r |
| 52302d4d | 638 | \r |
| 79b74a03 LG |
639 | # Convert the OrderedStringList to be OrderedStringListByToken in order to faciliate future search by token\r |
| 640 | for LangNameItem in self.LanguageDef:\r | |
| 641 | self.OrderedStringListByToken[LangNameItem[0]] = {}\r | |
| 642 | \r | |
| 52302d4d | 643 | #\r |
| 756ad8f8 | 644 | # Use small token for all referred string stoken.\r |
| 52302d4d | 645 | #\r |
| 756ad8f8 LG |
646 | RefToken = 0\r |
| 647 | for Index in range (0, len (self.OrderedStringList[FirstLangName])):\r | |
| 648 | FirstLangItem = self.OrderedStringList[FirstLangName][Index]\r | |
| 649 | if FirstLangItem.Referenced == True:\r | |
| 650 | for LangNameItem in self.LanguageDef:\r | |
| 651 | LangName = LangNameItem[0]\r | |
| 652 | OtherLangItem = self.OrderedStringList[LangName][Index]\r | |
| 653 | OtherLangItem.Referenced = True\r | |
| 654 | OtherLangItem.Token = RefToken\r | |
| 79b74a03 | 655 | self.OrderedStringListByToken[LangName][OtherLangItem.Token] = OtherLangItem\r |
| 756ad8f8 | 656 | RefToken = RefToken + 1\r |
| 30fdf114 LG |
657 | \r |
| 658 | #\r | |
| 756ad8f8 | 659 | # Use big token for all unreferred string stoken.\r |
| 30fdf114 | 660 | #\r |
| 756ad8f8 LG |
661 | UnRefToken = 0\r |
| 662 | for Index in range (0, len (self.OrderedStringList[FirstLangName])):\r | |
| 663 | FirstLangItem = self.OrderedStringList[FirstLangName][Index]\r | |
| 664 | if FirstLangItem.Referenced == False:\r | |
| 665 | for LangNameItem in self.LanguageDef:\r | |
| 666 | LangName = LangNameItem[0]\r | |
| 667 | OtherLangItem = self.OrderedStringList[LangName][Index]\r | |
| 668 | OtherLangItem.Token = RefToken + UnRefToken\r | |
| 79b74a03 | 669 | self.OrderedStringListByToken[LangName][OtherLangItem.Token] = OtherLangItem\r |
| 756ad8f8 | 670 | UnRefToken = UnRefToken + 1\r |
| 30fdf114 LG |
671 | \r |
| 672 | #\r | |
| 673 | # Show the instance itself\r | |
| 674 | #\r | |
| 675 | def ShowMe(self):\r | |
| 72443dd2 | 676 | print(self.LanguageDef)\r |
| 30fdf114 LG |
677 | #print self.OrderedStringList\r |
| 678 | for Item in self.OrderedStringList:\r | |
| 72443dd2 | 679 | print(Item)\r |
| 30fdf114 | 680 | for Member in self.OrderedStringList[Item]:\r |
| 72443dd2 | 681 | print(str(Member))\r |
| 30fdf114 LG |
682 | \r |
| 683 | # This acts like the main() function for the script, unless it is 'import'ed into another\r | |
| 684 | # script.\r | |
| 685 | if __name__ == '__main__':\r | |
| 686 | EdkLogger.Initialize()\r | |
| 687 | EdkLogger.SetLevel(EdkLogger.DEBUG_0)\r | |
| da92f276 | 688 | a = UniFileClassObject([PathClass("C:\\Edk\\Strings.uni"), PathClass("C:\\Edk\\Strings2.uni")])\r |
| 30fdf114 LG |
689 | a.ReToken()\r |
| 690 | a.ShowMe()\r |