public void addCharacterHandler(CharacterHandler characterHandler) { this.characterHandlers.add(characterHandler); if (driver != null) { driver.addCharacterHandler(characterHandler); } }
public void setEncoding(Encoding encoding, Confidence confidence) { this.characterEncoding = encoding; if (confidence == Confidence.CERTAIN) { becomeConfident(); } }
/** * Returns the <code>Locator</code> during parse. * @return the <code>Locator</code> */ public Locator getDocumentLocator() { return driver.getDocumentLocator(); }
/** * This class wraps different tree builders depending on configuration. This * method does the work of hiding this from the user of the class. */ private void lazyInit() { if (driver == null) { this.driver = new Driver(newTokenizer(treeBuilder, false)); this.driver.setErrorHandler(errorHandler); this.driver.setTransitionHandler(transitionHandler); this.treeBuilder.setErrorHandler(treeBuilderErrorHandler); this.driver.setCheckingNormalization(checkingNormalization); this.driver.setCommentPolicy(commentPolicy); this.driver.setContentNonXmlCharPolicy(contentNonXmlCharPolicy); this.driver.setContentSpacePolicy(contentSpacePolicy); this.driver.setMappingLangToXmlLang(mappingLangToXmlLang); this.driver.setXmlnsPolicy(xmlnsPolicy); this.driver.setHeuristics(heuristics); for (CharacterHandler characterHandler : characterHandlers) { this.driver.addCharacterHandler(characterHandler); } this.treeBuilder.setDocumentModeHandler(documentModeHandler); this.treeBuilder.setScriptingEnabled(scriptingEnabled); this.treeBuilder.setReportingDoctype(reportingDoctype); this.treeBuilder.setNamePolicy(namePolicy); } }
tokenizer.initLocation(is.getPublicId(), is.getSystemId()); this.reader = is.getCharacterStream(); this.characterEncoding = encodingFromExternalDeclaration(is.getEncoding()); if (this.reader == null) { InputStream inputStream = is.getByteStream(); } else { if (this.characterEncoding != Encoding.UTF8) { errorWithoutLocation("Legacy encoding \u201C" + this.characterEncoding.getCanonName() + "\u201D used. Documents must use UTF-8."); becomeConfident(); this.reader = new HtmlInputStreamReader(inputStream, tokenizer.getErrorHandler(), tokenizer, this, this.characterEncoding); becomeConfident(); runStates(); break; } catch (ReparseException e) { } else { rewindableInputStream.rewind(); becomeConfident(); this.reader = new HtmlInputStreamReader( rewindableInputStream, tokenizer.getErrorHandler(), tokenizer,
tokenizer.initLocation(is.getPublicId(), is.getSystemId()); this.reader = is.getCharacterStream(); this.characterEncoding = encodingFromExternalDeclaration(is.getEncoding()); if (this.reader == null) { InputStream inputStream = is.getByteStream(); tokenizer.getErrorHandler(), tokenizer, this, heuristics); } else { becomeConfident(); this.reader = new HtmlInputStreamReader(inputStream, tokenizer.getErrorHandler(), tokenizer, this, this.characterEncoding); becomeConfident(); ch.start(); runStates(); if (confidence == Confidence.TENTATIVE && !tokenizer.isAlreadyComplainedAboutNonAscii()) { warnWithoutLocation("The character encoding of the document was not declared."); } else { rewindableInputStream.rewind(); becomeConfident(); this.reader = new HtmlInputStreamReader( rewindableInputStream, tokenizer.getErrorHandler(), tokenizer,
becomeConfident(); return true; + characterEncoding.getCanonName() + "\u201D)."); } else { Encoding newEnc = whineAboutEncodingAndReturnActual( internalCharset, cs); tokenizer.errTreeBuilder("Changing character encoding \u201C"
if (isCheckingNormalization()) { return; } else { if (isCheckingNormalization()) { CharacterHandler[] newHandlers = new CharacterHandler[characterHandlers.length - 1]; boolean skipped = false;
if (needToNotifyTokenizer) { if (driver != null) { driver.notifyAboutMetaBoundary();
/** * This class wraps different tree builders depending on configuration. This * method does the work of hiding this from the user of the class. */ private void lazyInit() { if (driver == null) { this.driver = new Driver(newTokenizer(treeBuilder, false)); this.driver.setErrorHandler(errorHandler); this.driver.setTransitionHandler(transitionHandler); this.treeBuilder.setErrorHandler(treeBuilderErrorHandler); this.driver.setCheckingNormalization(checkingNormalization); this.driver.setCommentPolicy(commentPolicy); this.driver.setContentNonXmlCharPolicy(contentNonXmlCharPolicy); this.driver.setContentSpacePolicy(contentSpacePolicy); this.driver.setHtml4ModeCompatibleWithXhtml1Schemata(html4ModeCompatibleWithXhtml1Schemata); this.driver.setMappingLangToXmlLang(mappingLangToXmlLang); this.driver.setXmlnsPolicy(xmlnsPolicy); this.driver.setHeuristics(heuristics); for (CharacterHandler characterHandler : characterHandlers) { this.driver.addCharacterHandler(characterHandler); } this.treeBuilder.setDoctypeExpectation(doctypeExpectation); this.treeBuilder.setDocumentModeHandler(documentModeHandler); this.treeBuilder.setScriptingEnabled(scriptingEnabled); this.treeBuilder.setReportingDoctype(reportingDoctype); this.treeBuilder.setNamePolicy(namePolicy); } }
tokenizer.initLocation(is.getPublicId(), is.getSystemId()); this.reader = is.getCharacterStream(); this.characterEncoding = encodingFromExternalDeclaration(is.getEncoding()); if (this.reader == null) { InputStream inputStream = is.getByteStream(); } else { if (this.characterEncoding != Encoding.UTF8) { errorWithoutLocation("Legacy encoding \u201C" + this.characterEncoding.getCanonName() + "\u201D used. Documents must use UTF-8."); becomeConfident(); this.reader = new HtmlInputStreamReader(inputStream, tokenizer.getErrorHandler(), tokenizer, this, this.characterEncoding); becomeConfident(); runStates(); break; } catch (ReparseException e) { } else { rewindableInputStream.rewind(); becomeConfident(); this.reader = new HtmlInputStreamReader( rewindableInputStream, tokenizer.getErrorHandler(), tokenizer,
becomeConfident(); return true; + characterEncoding.getCanonName() + "\u201D)."); } else { Encoding newEnc = whineAboutEncodingAndReturnActual( internalCharset, cs); tokenizer.errTreeBuilder("Changing character encoding \u201C"
if (isCheckingNormalization()) { return; } else { if (isCheckingNormalization()) { CharacterHandler[] newHandlers = new CharacterHandler[characterHandlers.length - 1]; boolean skipped = false;
if (needToNotifyTokenizer) { if (driver != null) { driver.notifyAboutMetaBoundary();
/** * This class wraps different tree builders depending on configuration. This * method does the work of hiding this from the user of the class. */ private void lazyInit() { if (driver == null) { this.driver = new Driver(newTokenizer(treeBuilder, false)); this.driver.setErrorHandler(errorHandler); this.driver.setTransitionHandler(transitionHandler); this.treeBuilder.setErrorHandler(treeBuilderErrorHandler); this.driver.setCheckingNormalization(checkingNormalization); this.driver.setCommentPolicy(commentPolicy); this.driver.setContentNonXmlCharPolicy(contentNonXmlCharPolicy); this.driver.setContentSpacePolicy(contentSpacePolicy); this.driver.setMappingLangToXmlLang(mappingLangToXmlLang); this.driver.setXmlnsPolicy(xmlnsPolicy); this.driver.setHeuristics(heuristics); for (CharacterHandler characterHandler : characterHandlers) { this.driver.addCharacterHandler(characterHandler); } this.treeBuilder.setDocumentModeHandler(documentModeHandler); this.treeBuilder.setScriptingEnabled(scriptingEnabled); this.treeBuilder.setReportingDoctype(reportingDoctype); this.treeBuilder.setNamePolicy(namePolicy); } }
becomeConfident(); return true; + characterEncoding.getCanonName() + "\u201D)."); } else { Encoding newEnc = whineAboutEncodingAndReturnActual( internalCharset, cs); tokenizer.errTreeBuilder("Changing character encoding \u201C"
/** * Returns the <code>Locator</code> during parse. * @return the <code>Locator</code> */ public Locator getDocumentLocator() { return driver.getDocumentLocator(); }
public void addCharacterHandler(CharacterHandler characterHandler) { this.characterHandlers.add(characterHandler); if (driver != null) { driver.addCharacterHandler(characterHandler); } }
public void setEncoding(Encoding encoding, Confidence confidence) { this.characterEncoding = encoding; if (confidence == Confidence.CERTAIN) { becomeConfident(); } }
if (isCheckingNormalization()) { return; } else { if (isCheckingNormalization()) { CharacterHandler[] newHandlers = new CharacterHandler[characterHandlers.length - 1]; boolean skipped = false;