1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343
|
/*******************************************************************************
* Copyright (c) 2004, 2017 IBM Corporation and others.
* All rights reserved. This program and the accompanying materials
* are made available under the terms of the Eclipse Public License 2.0
* which accompanies this distribution, and is available at
* https://www.eclipse.org/legal/epl-2.0/
*
* SPDX-License-Identifier: EPL-2.0
*
* Contributors:
* IBM Corporation - initial API and implementation
*******************************************************************************/
/*nlsXXX*/
package org.eclipse.wst.html.core.internal.contenttype;
import java.io.IOException;
import java.io.Reader;
import org.eclipse.wst.xml.core.internal.contenttype.EncodingParserConstants;
import org.eclipse.wst.xml.core.internal.contenttype.XMLHeadTokenizerConstants;
%%
%{
private boolean hasMore = true;
private boolean hasCharsetAttr = false;
private final static int MAX_TO_SCAN = 8000;
StringBuffer string = new StringBuffer();
// state stack for easier state handling
private IntStack fStateStack = new IntStack();
private String valueText = null;
boolean foundContentTypeValue = false;
private boolean isXHTML;
private boolean isDocumentRootElementChecked = false;
public HTMLHeadTokenizer() {
super();
}
public void reset (Reader in) {
/* the input device */
yy_reader = in;
/* the current state of the DFA */
yy_state = 0;
/* the current lexical state */
yy_lexical_state = YYINITIAL;
/* this buffer contains the current text to be matched and is
the source of the yytext() string */
java.util.Arrays.fill(yy_buffer, (char)0);
/* the textposition at the last accepting state */
yy_markedPos = 0;
/* the textposition at the last state to be included in yytext */
yy_pushbackPos = 0;
/* the current text position in the buffer */
yy_currentPos = 0;
/* startRead marks the beginning of the yytext() string in the buffer */
yy_startRead = 0;
/**
* endRead marks the last character in the buffer, that has been read
* from input
*/
yy_endRead = 0;
/* number of newlines encountered up to the start of the matched text */
// yyline = 0;
/* the number of characters up to the start of the matched text */
yychar = 0;
/**
* the number of characters from the last newline up to the start
* of the matched text
*/
// yycolumn = 0;
/**
* yy_atBOL == true <=> the scanner is currently at the beginning
* of a line
*/
yy_atBOL = false;
/* yy_atEOF == true <=> the scanner has returned a value for EOF */
yy_atEOF = false;
/* denotes if the user-EOF-code has already been executed */
yy_eof_done = false;
fStateStack.clear();
hasMore = true;
hasCharsetAttr = false;
isXHTML = false;
isDocumentRootElementChecked = false;
// its a little wasteful to "throw away" first char array generated
// by class init (via auto generated code), but we really do want
// a small buffer for our head parsers.
if (yy_buffer.length != MAX_TO_SCAN) {
yy_buffer = new char[MAX_TO_SCAN];
}
}
public final HeadParserToken getNextToken() throws IOException {
String context = null;
HeadParserToken result = null;
try {
context = primGetNextToken();
}
catch (IllegalStateException e) {
hasMore = false;
result = createToken(HTMLHeadTokenizerConstants.UNDEFINED, yychar, yytext());
while(yy_advance() != YYEOF) {}
return result;
}
if (valueText != null) {
result = createToken(context, yychar, valueText);
valueText = null;
} else {
result = createToken(context, yychar, yytext());
}
return result;
}
public final boolean hasMoreTokens() {
return hasMore && yychar < MAX_TO_SCAN;
}
private void pushCurrentState() {
fStateStack.push(yystate());
}
public final boolean hasCharsetAttr() {
return hasCharsetAttr;
}
private void popState() {
yybegin(fStateStack.pop());
}
private HeadParserToken createToken(String context, int start, String text) {
return new HeadParserToken(context, start, text);
}
/* Is this file XHTML, for the purposes of its description (encoding, etc.) */
public boolean isXHTML() {
return isXHTML;
}
public boolean isDocumentRootElementChecked(){
return isDocumentRootElementChecked;
}
%}
%eof{
hasMore=false;
%eof}
%public
%class HTMLHeadTokenizer
%function primGetNextToken
%type String
%char
%unicode
%ignorecase
//%debug
%switch
UTF16BE = \xFE\xFF
UTF16LE = \xFF\xFE
UTF83ByteBOM = \xEF\xBB\xBF
SpaceChar = [\x20\x09]
// [3] S ::= (0x20 | 0x9 | 0xD | 0xA)+
S = [\x20\x09\x0D\x0A]
// BeginAttribeValue = {S}* \= {S}*
BaseChar = [\u0041-\u005A\u0061-\u007A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u0131\u0134-\u013E\u0141-\u0148\u014A-\u017E\u0180-\u01C3\u01CD-\u01F0\u01F4-\u01F5\u01FA-\u0217\u0250-\u02A8\u02BB-\u02C1\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03CE\u03D0-\u03D6\u03DA\u03DC\u03DE\u03E0\u03E2-\u03F3\u0401-\u040C\u040E-\u044F\u0451-\u045C\u045E-\u0481\u0490-\u04C4\u04C7-\u04C8\u04CB-\u04CC\u04D0-\u04EB\u04EE-\u04F5\u04F8-\u04F9\u0531-\u0556\u0559\u0561-\u0586\u05D0-\u05EA\u05F0-\u05F2\u0621-\u063A\u0641-\u064A\u0671-\u06B7\u06BA-\u06BE\u06C0-\u06CE\u06D0-\u06D3\u06D5\u06E5-\u06E6\u0905-\u0939\u093D\u0958-\u0961\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09DC-\u09DD\u09DF-\u09E1\u09F0-\u09F1\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A59-\u0A5C\u0A5E\u0A72-\u0A74\u0A85-\u0A8B\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABD\u0AE0\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B36-\u0B39\u0B3D\u0B5C-\u0B5D\u0B5F-\u0B61\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C60-\u0C61\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CDE\u0CE0-\u0CE1\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D60-\u0D61\u0E01-\u0E2E\u0E30\u0E32-\u0E33\u0E40-\u0E45\u0E81-\u0E82\u0E84\u0E87-\u0E88\u0E8A\u0E8D\u0E94-\u0E97\u0E99-\u0E9F\u0EA1-\u0EA3\u0EA5\u0EA7\u0EAA-\u0EAB\u0EAD-\u0EAE\u0EB0\u0EB2-\u0EB3\u0EBD\u0EC0-\u0EC4\u0F40-\u0F47\u0F49-\u0F69\u10A0-\u10C5\u10D0-\u10F6\u1100\u1102-\u1103\u1105-\u1107\u1109\u110B-\u110C\u110E-\u1112\u113C\u113E\u1140\u114C\u114E\u1150\u1154-\u1155\u1159\u115F-\u1161\u1163\u1165\u1167\u1169\u116D-\u116E\u1172-\u1173\u1175\u119E\u11A8\u11AB\u11AE-\u11AF\u11B7-\u11B8\u11BA\u11BC-\u11C2\u11EB\u11F0\u11F9\u1E00-\u1E9B\u1EA0-\u1EF9\u1F00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2126\u212A-\u212B\u212E\u2180-\u2182\u3041-\u3094\u30A1-\u30FA\u3105-\u312C\uAC00-\uD7A3]
CombiningChar = [\u0300-\u0345\u0360-\u0361\u0483-\u0486\u0591-\u05A1\u05A3-\u05B9\u05BB-\u05BD\u05BF\u05C1-\u05C2\u05C4\u064B-\u0652\u0670\u06D6-\u06DC\u06DD-\u06DF\u06E0-\u06E4\u06E7-\u06E8\u06EA-\u06ED\u0901-\u0903\u093C\u093E-\u094C\u094D\u0951-\u0954\u0962-\u0963\u0981-\u0983\u09BC\u09BE\u09BF\u09C0-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09E2-\u09E3\u0A02\u0A3C\u0A3E\u0A3F\u0A40-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A70-\u0A71\u0A81-\u0A83\u0ABC\u0ABE-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0B01-\u0B03\u0B3C\u0B3E-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B82-\u0B83\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0C01-\u0C03\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56\u0C82-\u0C83\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0D02-\u0D03\u0D3E-\u0D43\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0E31\u0E34-\u0E3A\u0E47-\u0E4E\u0EB1\u0EB4-\u0EB9\u0EBB-\u0EBC\u0EC8-\u0ECD\u0F18-\u0F19\u0F35\u0F37\u0F39\u0F3E\u0F3F\u0F71-\u0F84\u0F86-\u0F8B\u0F90-\u0F95\u0F97\u0F99-\u0FAD\u0FB1-\u0FB7\u0FB9\u20D0-\u20DC\u20E1\u302A-\u302F\u3099\u309A]
Digit = [\u0030-\u0039\u0660-\u0669\u06F0-\u06F9\u0966-\u096F\u09E6-\u09EF\u0A66-\u0A6F\u0AE6-\u0AEF\u0B66-\u0B6F\u0BE7-\u0BEF\u0C66-\u0C6F\u0CE6-\u0CEF\u0D66-\u0D6F\u0E50-\u0E59\u0ED0-\u0ED9\u0F20-\u0F29]
Extender = [\u00B7\u02D0\u02D1\u0387\u0640\u0E46\u0EC6\u3005\u3031-\u3035\u309D-\u309E\u30FC-\u30FE]
Ideographic = [\u4E00-\u9FA5\u3007\u3021-\u3029]
Letter = ({BaseChar} | {Ideographic})
NameChar = ({Letter} | {Digit} | "." | "-" | "_" | ":" | {CombiningChar} | {Extender})
Name = ({Letter} | "_" | ":" ) ({NameChar})*
LineTerminator = \r|\n
Z = (\x00)?
S_UTF = {Z}{S}{Z}
BeginAttributeValueUTF = {S_UTF}* \= {S_UTF}*
%state ST_XMLDecl
%state ST_META_TAG
%state ST_XMLNameSpace
%state QuotedAttributeValue
%state DQ_STRING
%state SQ_STRING
%state UnDelimitedString
%state UnDelimitedCharset
%%
<YYINITIAL>
{
{UTF16BE} {hasMore = false; return EncodingParserConstants.UTF16BE;}
{UTF16LE} {hasMore = false; return EncodingParserConstants.UTF16LE;}
{UTF83ByteBOM} {hasMore = false; return EncodingParserConstants.UTF83ByteBOM;}
// force to be started on first line, but we do allow preceeding spaces
^ {S_UTF}* ({Z}<{Z}\?{Z}x{Z}m{Z}l{Z}){S_UTF}+ {if (yychar == 0 ) {yybegin(ST_XMLDecl); return XMLHeadTokenizerConstants.XMLDeclStart;}}
({Z}<{Z}M{Z}E{Z}T{Z}A{Z}) {yybegin(ST_META_TAG); return HTMLHeadTokenizerConstants.MetaTagStart;}
// To determine if content is XHTML
{Z}<{Name} { if (!isDocumentRootElementChecked()){yybegin(ST_XMLNameSpace); return HTMLHeadTokenizerConstants.DocumentRootNameSpace;}}
}
<ST_XMLNameSpace>{
{S_UTF}+{Z}x{Z}m{Z}l{Z}n{Z}s{Z} {S_UTF}* {Z}\={Z} {S_UTF}* (({Z}\"{Z}) | ({Z}\'{Z})) {Z}h{Z}t{Z}t{Z}p{Z}:{Z}\/{Z}\/{Z}w{Z}w{Z}w{Z}\.{Z}w{Z}3{Z}\.{Z}o{Z}r{Z}g{Z}\/{Z}1{Z}9{Z}9{Z}9{Z}\/{Z}x{Z}h{Z}t{Z}m{Z}l{Z} {isXHTML = true;}
{Z}>{Z} { yybegin(YYINITIAL); isDocumentRootElementChecked = true; return HTMLHeadTokenizerConstants.RootElementTagEnd;}
{Z}\/{Z}>{Z} { yybegin(YYINITIAL); isDocumentRootElementChecked = true; return HTMLHeadTokenizerConstants.RootElementTagEnd;}
}
<ST_XMLDecl>
{
//"version" {BeginAttribeValue} {pushCurrentState(); yybegin(QuotedAttributeValue); return XMLHeadTokenizerConstants.XMLDeclVersion;}
({Z}e{Z}n{Z}c{Z}o{Z}d{Z}i{Z}n{Z}g{Z}) {BeginAttributeValueUTF} {pushCurrentState(); yybegin(QuotedAttributeValue); this.isXHTML = true; return XMLHeadTokenizerConstants.XMLDelEncoding;}
// note this "forced end" once end of XML Declaration found
({Z}\?{Z}>{Z}) {yybegin(YYINITIAL); return XMLHeadTokenizerConstants.XMLDeclEnd;}
}
<ST_META_TAG>
{
// "http-equiv" {S}* \= {S}* \"? "Content-Type" \"? {S}+ "content" {BeginAttribeValue} {pushCurrentState(); yybegin(QuotedAttributeValue); foundContentTypeValue=true; return HTMLHeadTokenizerConstants.MetaTagContentType;}
{Z}h{Z}t{Z}t{Z}p{Z}-{Z}e{Z}q{Z}u{Z}i{Z}v{Z} {S_UTF}* \= {S_UTF}* {Z}\"?{Z} ({Z}C{Z}o{Z}n{Z}t{Z}e{Z}n{Z}t{Z}-{Z}T{Z}y{Z}p{Z}e{Z}) \"?{Z} ({S_UTF})+ ({Z}c{Z}o{Z}n{Z}t{Z}e{Z}n{Z}t{Z}) {BeginAttributeValueUTF} {pushCurrentState(); yybegin(QuotedAttributeValue); foundContentTypeValue=true; return HTMLHeadTokenizerConstants.MetaTagContentType;}
{Z}c{Z}h{Z}a{Z}r{Z}s{Z}e{Z}t{Z} {BeginAttributeValueUTF} {pushCurrentState(); yybegin(QuotedAttributeValue); foundContentTypeValue=true; hasCharsetAttr=true; return HTMLHeadTokenizerConstants.MetaTagContentType;}
{Z}>{Z} { yybegin(YYINITIAL); if (foundContentTypeValue) hasMore = false; return HTMLHeadTokenizerConstants.MetaTagEnd;}
{Z}\/{Z}>{Z} { yybegin(YYINITIAL); if (foundContentTypeValue) hasMore = false; return HTMLHeadTokenizerConstants.MetaTagEnd;}
}
<QuotedAttributeValue>
{
{Z}\"{Z} { yybegin(DQ_STRING); string.setLength(0); }
{Z}\'{Z} { yybegin(SQ_STRING); string.setLength(0); }
// in this state, anything other than a space character can start an undelimited string
{S_UTF}*. { yypushback(1); yybegin(UnDelimitedString); string.setLength(0);}
}
<DQ_STRING>
{
{Z}\"{Z} { popState(); valueText = string.toString(); return EncodingParserConstants.StringValue; }
{Z}{LineTerminator}{Z} { yypushback(yylength());popState(); valueText = string.toString(); return EncodingParserConstants.InvalidTerminatedStringValue;}
{Z}\?{Z}>{Z} { yypushback(yylength()); popState(); valueText = string.toString(); return EncodingParserConstants.InvalidTerminatedStringValue;}
{Z}<{Z} { yypushback(yylength());popState(); valueText = string.toString(); return EncodingParserConstants.InvalidTerminatedStringValue;}
{Z}>{Z} { yypushback(yylength());popState(); valueText = string.toString(); return EncodingParserConstants.InvalidTerminatedStringValue;}
{Z}\/{Z}>{Z} { yypushback(yylength()); popState(); valueText = string.toString(); return EncodingParserConstants.InvalidTerminatedStringValue;}
[^\x00] { string.append( yytext() ); }
}
<SQ_STRING>
{
{Z}\'{Z} { popState(); valueText = string.toString(); return EncodingParserConstants.StringValue;}
{Z}{LineTerminator}{Z} { yypushback(yylength());popState(); valueText = string.toString(); return EncodingParserConstants.InvalidTerminatedStringValue;}
{Z}%{Z}>{Z} { yypushback(yylength());popState(); valueText = string.toString(); return EncodingParserConstants.InvalidTerminatedStringValue;}
{Z}<{Z} { yypushback(yylength());popState(); valueText = string.toString(); return EncodingParserConstants.InvalidTerminatedStringValue;}
{Z}>{Z} { yypushback(yylength());popState(); valueText = string.toString(); return EncodingParserConstants.InvalidTerminatedStringValue;}
{Z}\/{Z}>{Z} { yypushback(yylength()); popState(); valueText = string.toString(); return EncodingParserConstants.InvalidTerminatedStringValue;}
[^\x00] { string.append( yytext() ); }
}
<UnDelimitedString>
{
// note this initial special case for HTTP contenttype values
// Look ahead and see if there are spaces, but don't append the spaces as they may be double-byte
// Let the next state handle removal of the \x00 and properly append spaces
";"/{S_UTF}* { pushCurrentState(); yybegin(UnDelimitedCharset); string.append( yytext() ); }
{S_UTF} { yypushback(yylength());popState(); valueText = string.toString(); return EncodingParserConstants.UnDelimitedStringValue; }
{Z}{LineTerminator}{Z} { yypushback(yylength());popState(); valueText = string.toString(); return EncodingParserConstants.InvalidTerminatedStringValue;}
{Z}\?{Z}>{Z} { yypushback(yylength());popState(); valueText = string.toString(); return EncodingParserConstants.InvalidTerminatedStringValue;}
{Z}<{Z} { yypushback(yylength());popState(); valueText = string.toString(); return EncodingParserConstants.InvalidTerminatedStringValue;}
// these are a bit special, since we started an undelimit string, but found a quote ... probably indicates a missing beginning quote
{Z}\'{Z} { yypushback(yylength());popState(); valueText = string.toString(); return EncodingParserConstants.InvalidTermintatedUnDelimitedStringValue;}
{Z}\"{Z} { yypushback(yylength());popState(); valueText = string.toString(); return EncodingParserConstants.InvalidTermintatedUnDelimitedStringValue;}
{Z}>{Z} { yypushback(yylength());popState(); valueText = string.toString(); return EncodingParserConstants.InvalidTerminatedStringValue;}
{Z}\/{Z}>{Z} { yypushback(yylength()); popState(); valueText = string.toString(); return EncodingParserConstants.InvalidTerminatedStringValue;}
[^\x00] { string.append( yytext() ); }
}
<UnDelimitedCharset>
{
{S} { string.append( yytext() ); }
// For non \x00 characters, let the previous state handle it
[^\x00] {yypushback(1); popState(); }
}
// The "match anything" rule should always be in effect except for when looking for end of string
// (That is, remember to update state list if/when new states added)
.|\n {if(yychar > MAX_TO_SCAN) {hasMore=false; return EncodingParserConstants.MAX_CHARS_REACHED;}}
// this rule always in effect
<<EOF>> {hasMore = false; return EncodingParserConstants.EOF;}
|