pegasus/src/Pegasus/Common/LanguageParser.cpp - annotate

Return to LanguageParser.cpp CVS log

Up to [Pegasus] / pegasus / src / Pegasus / Common

1 karl 1.11 //%2005////////////////////////////////////////////////////////////////////////
2 humberto 1.8 //
3 karl 1.10 // Copyright (c) 2000, 2001, 2002 BMC Software; Hewlett-Packard Development 4 // Company, L.P.; IBM Corp.; The Open Group; Tivoli Systems. 5 // Copyright (c) 2003 BMC Software; Hewlett-Packard Development Company, L.P.;
6 karl 1.9 // IBM Corp.; EMC Corporation, The Open Group.
7 karl 1.10 // Copyright (c) 2004 BMC Software; Hewlett-Packard Development Company, L.P.; 8 // IBM Corp.; EMC Corporation; VERITAS Software Corporation; The Open Group.
9 karl 1.11 // Copyright (c) 2005 Hewlett-Packard Development Company, L.P.; IBM Corp.; 10 // EMC Corporation; VERITAS Software Corporation; The Open Group.
11 humberto 1.8 // 12 // Permission is hereby granted, free of charge, to any person obtaining a copy 13 // of this software and associated documentation files (the "Software"), to 14 // deal in the Software without restriction, including without limitation the 15 // rights to use, copy, modify, merge, publish, distribute, sublicense, and/or 16 // sell copies of the Software, and to permit persons to whom the Software is 17 // furnished to do so, subject to the following conditions: 18 // 19 // THE ABOVE COPYRIGHT NOTICE AND THIS PERMISSION NOTICE SHALL BE INCLUDED IN 20 // ALL COPIES OR SUBSTANTIAL PORTIONS OF THE SOFTWARE. THE SOFTWARE IS PROVIDED 21 // "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT 22 // LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR 23 // PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT 24 // HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN 25 // ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION 26 // WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. 27 // 28 //============================================================================== 29 // 30 // Author: Humberto Rivero (hurivero@us.ibm.com) 31 //
32 aruran.ms 1.15 // Modified By: Aruran, IBM (ashanmug@in.ibm.com) for Bug# 3697, 3698, 3699, 3700
33 aruran.ms 1.19 // Aruran, IBM (ashanmug@in.ibm.com) for Bug# 3701, 3702, 3703, 3704
34 humberto 1.8 // 35 //%///////////////////////////////////////////////////////////////////////////// 36 37 #include <Pegasus/Common/LanguageParser.h> 38 #include <Pegasus/Common/InternalException.h> 39 #include <Pegasus/Common/Tracer.h> 40 #include <Pegasus/Common/MessageLoader.h> //l10n 41 #include <cstring> 42 43 //PEGASUS_USING_STD; 44 PEGASUS_NAMESPACE_BEGIN 45 46 const LanguageParser LanguageParser::EMPTY = LanguageParser(); 47
48 aruran.ms 1.12 void LanguageParser::parseHdr(Array<String> &values, String hdr){
49 humberto 1.8 // look for ',' which designates distict (Accept/Content)-Language fields 50 // the form: [languagetag, languagetag, languagetag] so whitespace removal 51 // may be necessary. 52 // then store them in the array 53 PEG_METHOD_ENTER(TRC_L10N, "LanguageParser::parseHdr"); 54 Uint32 i = 0; 55 while( i != PEG_NOT_FOUND ){ 56 i = hdr.find(","); 57 if( i != PEG_NOT_FOUND ){ 58 values.append(hdr.subString(0,i)); 59 while(hdr[i+1] == ' ') i++; // get rid of whitespace after "," 60 hdr = hdr.subString(i+1); 61 } 62 else{ // only one field, build an object with it 63 values.append(hdr); 64 } 65 } 66 PEG_METHOD_EXIT(); 67 } 68
69 aruran.ms 1.13 Real32 LanguageParser::parseAcceptLanguageValue(String &language_tag, String hdr){
70 humberto 1.8 // look for ';' in hdr, that means we have a quality value to capture 71 // if not, we only have a language 72 73 // if hdr begins with "x-" then we have a non-IANA (private) language tag 74 PEG_METHOD_ENTER(TRC_L10N, "LanguageParser::parseAcceptLanguageValue"); 75 Uint32 i; 76 Boolean validate_length = true; 77 if((( i = hdr.find("x-")) != PEG_NOT_FOUND ) && (i == 0)){ 78 hdr = convertPrivateLanguageTag(hdr); 79 validate_length = false; 80 } 81 82 // get rid of any beginning or trailing whitespaces 83 Uint32 j; 84 while( (j = hdr.find(" ")) != PEG_NOT_FOUND ){ 85 hdr.remove(j,1); 86 } 87 88 Real32 quality = 1; 89 i = hdr.find(";"); 90 if(i != PEG_NOT_FOUND){ // extract and store language and quality 91 humberto 1.8 if(isValid(hdr.subString(0,i), validate_length)){ 92 language_tag = hdr.subString(0,i); 93 if(hdr.size() > i + 3) 94 hdr.remove(0,i+3); // remove everything but the quality value 95 else{ 96 MessageLoaderParms parms("Common.LanguageParser.INVALID_QUALITY_VALUE", 97 "AcceptLanguage contains an invalid quality value"); 98 throw InvalidAcceptLanguageHeader(MessageLoader::getMessage(parms)); 99 } 100 } 101 else{ 102 //l10n 103 //throw InvalidAcceptLanguageHeader( 104 //"AcceptLanguage contains too many characters or non-alpha characters"); 105 MessageLoaderParms parms("Common.LanguageParser.TOO_MANY_OR_NON_ALPHA_CHARACTERS_AL", 106 "AcceptLanguage contains too many characters or non-alpha characters"); 107 throw InvalidAcceptLanguageHeader(MessageLoader::getMessage(parms)); 108 } 109 //validate quality 110 quality = atof(hdr.getCString()); 111 if(quality > 1.0 \|\| quality < 0.0){ 112 humberto 1.8 //l10n 113 //throw InvalidAcceptLanguageHeader( 114 //"AcceptLanguage contains an invalid quality value"); 115 MessageLoaderParms parms("Common.LanguageParser.INVALID_QUALITY_VALUE", 116 "AcceptLanguage contains an invalid quality value"); 117 throw InvalidAcceptLanguageHeader(MessageLoader::getMessage(parms)); 118 } 119 } 120 else{ // extract and store language, quality defaults to 1.0 121 if(isValid(hdr, validate_length)) language_tag = hdr; 122 else{ 123 //l10n 124 //throw InvalidAcceptLanguageHeader( 125 //"AcceptLanguage contains too many characters or non-alpha characters"); 126 MessageLoaderParms parms("Common.LanguageParser.TOO_MANY_OR_NON_ALPHA_CHARACTERS_AL", 127 "AcceptLanguage contains too many characters or non-alpha characters"); 128 throw InvalidAcceptLanguageHeader(MessageLoader::getMessage(parms)); 129 } 130 } 131 132 PEG_METHOD_EXIT(); 133 humberto 1.8 return quality; 134 } 135
136 aruran.ms 1.14 String LanguageParser::parseContentLanguageValue(const String& hdr){
137 humberto 1.8 // we are looking for the language part of the hdr only, 138 // according to the RFC, there may be parenthesized strings 139 // that describe the purpose of the language, we need to ignore those 140 PEG_METHOD_ENTER(TRC_L10N, "LanguageParser::parseContentLanguageValue"); 141 String value = hdr; 142 Uint32 i,j; 143 while((i = value.find("(")) != PEG_NOT_FOUND){ // get rid of anything in parenthesis in hdr if found 144 if((j = value.find(")")) != PEG_NOT_FOUND) 145 value.remove(i, (j-i)+1); 146 else{ 147 //l10n 148 //throw InvalidContentLanguageHeader( 149 //"ContentLanguage does not contain terminating ) character"); 150 MessageLoaderParms parms("Common.LanguageParser.DOES_NOT_CONTAIN_TERMINATING", 151 "ContentLanguage does not contain terminating ) character"); 152 throw InvalidContentLanguageHeader(MessageLoader::getMessage(parms)); 153 } 154 } 155 // get rid of any beginning or trailing whitespaces 156 while( (i = value.find(" ")) != PEG_NOT_FOUND ){ 157 value.remove(i,1); 158 humberto 1.8 } 159 if(!isValid(value)){ 160 //l10n 161 //throw InvalidContentLanguageHeader( 162 //"ContentLanguage contains too many characters or non-alpha characters"); 163 MessageLoaderParms parms("Common.LanguageParser.TOO_MANY_OR_NON_ALPHA_CHARACTERS_CL", 164 "ContentLanguage contains too many characters or non-alpha characters"); 165 throw InvalidContentLanguageHeader(MessageLoader::getMessage(parms)); 166 167 } 168 PEG_METHOD_EXIT(); 169 return value; 170 } 171
172 aruran.ms 1.15 String LanguageParser::getLanguage(const String & language_tag){
173 humberto 1.8 // given a language_tag: en-US-mn we want to return "en" 174 Uint32 i; 175 if((i = language_tag.find(findSeparator(language_tag.getCString()))) != PEG_NOT_FOUND) 176 return language_tag.subString(0,i); 177 return String(language_tag); 178 } 179
180 aruran.ms 1.15 String LanguageParser::getCountry(const String & language_tag){
181 humberto 1.8 // given a language_tag: en-US-mn we want to return "US" 182 Uint32 i,j; 183 if( (i = language_tag.find(findSeparator(language_tag.getCString()))) != PEG_NOT_FOUND ) 184 if( (j = language_tag.find(i+1, findSeparator(language_tag.getCString()))) != PEG_NOT_FOUND ) 185 return language_tag.subString(i+1, j-(i+1)); 186 else 187 return language_tag.subString(i+1); 188 return String::EMPTY; 189 } 190
191 aruran.ms 1.15 String LanguageParser::getVariant(const String & language_tag){
192 humberto 1.8 // given a language_tag: en-US-mn we want to return "mn" 193 Uint32 i; 194 if( (i = language_tag.find(findSeparator(language_tag.getCString()))) != PEG_NOT_FOUND ) 195 if( (i = language_tag.find(i+1, findSeparator(language_tag.getCString()))) != PEG_NOT_FOUND ) 196 return language_tag.subString(i+1); 197 return String::EMPTY; 198 } 199 200 void LanguageParser::parseLanguageSubtags(Array<String> &subtags, String language_tag){ 201 PEG_METHOD_ENTER(TRC_L10N, "LanguageParser::parseLanguageSubtags"); 202 Uint32 i; 203 char separator = findSeparator(language_tag.getCString()); 204 while( (i = language_tag.find(Char16(separator))) != PEG_NOT_FOUND ){ 205 subtags.append(language_tag.subString(0,i)); 206 language_tag.remove(0,i + 1); 207 } 208 if(language_tag.size() > 0) 209 subtags.append(language_tag); 210 PEG_METHOD_EXIT(); 211 } 212
213 aruran.ms 1.16 Boolean LanguageParser::isValid(const String& language_tag, Boolean validate_length){
214 humberto 1.8 //break the String down into parts(subtags), then validate each part 215 216 if(language_tag == "*") return true; 217 218 Array<String> subtags; 219 parseLanguageSubtags(subtags, language_tag); 220 if(subtags.size() > 0){ 221 for(Uint32 i = 0; i < subtags.size(); i++){ 222 //length should be 8 or less AND all characters should be A-Z or a-z 223 if((validate_length && subtags[i].size() > 8) \|\| !checkAlpha(subtags[i].getCString())) 224 return false; 225 } 226 } 227 else{ //nothing back from parseLanguageSubtags 228 return false; 229 } 230 return true; 231 } 232
233 aruran.ms 1.17 String LanguageParser::convertPrivateLanguageTag(const String & language_tag){
234 humberto 1.8 // figure out if its a unix style locale or windows locale 235 Uint32 i; 236 if(( i = language_tag.find("pegasus-")) != PEG_NOT_FOUND ){
237 aruran.ms 1.17 String str; 238 str = language_tag.subString(i+5); 239 //language_tag = language_tag.subString(i+5); // capture the remainder of the string 240 return String(replaceSeparator(str.getCString(), '-'));
241 humberto 1.8 } 242 //else if( (i = language_tag.find("win-")) != PEG_NOT_FOUND ){ 243 // return language_tag.subString(i+4); // capture the remainder of the string 244 // call windows ID to ICU convert routine or locmap.c function here 245 //} 246 else{ 247 return language_tag; 248 } 249 } 250
251 aruran.ms 1.18 Boolean LanguageParser::checkAlpha(const CString & _str){
252 humberto 1.7 Uint32 length = (Uint32) strlen(_str);
253 humberto 1.8 for(Uint32 i = 0; i < length; i++) 254 if( !isalpha(_str[i]) ) 255 return false; 256 return true; 257 } 258
259 aruran.ms 1.18 char LanguageParser::findSeparator(const CString & _str){
260 kumpf 1.4 Uint32 length = (Uint32) strlen(_str);
261 humberto 1.8 for(Uint32 i = 0; i < length; i++) 262 if(!isalnum(_str[i])) 263 return _str[i]; 264 return '\0'; 265 } 266
267 aruran.ms 1.18 CString LanguageParser::replaceSeparator(const CString & _s, char new_sep){
268 aruran.ms 1.20 const Uint32 length = (Uint32) strlen(_s); 269 AutoArrayPtr<char> _str(new char[length + 1]); 270 strcpy(_str.get(),_s); 271 for(Uint32 i = 0; i < length; i++) 272 { 273 if (!isalnum(_str.get()[i])) 274 { 275 _str.get()[i] = new_sep; 276 } 277 } 278 const String retval(_str.get()); 279 _str.release(); 280 return(retval.getCString());
281 humberto 1.8 } 282 283 284 PEGASUS_NAMESPACE_END

No CVS admin address has been configured