Dave Jarvis' Repositories

git clone https://repo.autonoma.ca/repo/keenwrite.git
keenwrite / Commits / 2b0e847
src/main/java/com/keenwrite/ExportFormat.java
package com.keenwrite;
+import com.keenwrite.events.StatusEvent;
import com.keenwrite.io.MediaType;
import com.keenwrite.io.MediaTypeExtension;
*/
XHTML_TEX( ".xhtml" ),
+
+ /**
+ * For XHTML exports, encode TeX as SVG. Treat image links relatively.
+ */
+ XHTML_TEX_SVG( ".xhtml" ),
/**
throws IllegalArgumentException {
assert extension != null;
+ final var mediaType = MediaTypeExtension.fromExtension( extension );
- return valueFrom( MediaTypeExtension.fromExtension( extension ), modifier );
+ StatusEvent.fire( "export format: " + mediaType );
+
+ return valueFrom( mediaType, modifier );
}
public static ExportFormat valueFrom(
final MediaType type, final String modifier ) {
+
return switch( type ) {
- case TEXT_HTML, TEXT_XHTML -> "svg".equalsIgnoreCase( modifier.trim() )
+ case TEXT_HTML -> "svg".equalsIgnoreCase( modifier.trim() )
? HTML_TEX_SVG
: HTML_TEX_DELIMITED;
+ case TEXT_XML, APP_XHTML -> "svg".equalsIgnoreCase( modifier.trim() )
+ ? XHTML_TEX_SVG
+ : XHTML_TEX;
case APP_PDF -> APPLICATION_PDF;
- case TEXT_XML -> XHTML_TEX;
- default -> NONE;
+ default -> throw new IllegalArgumentException( format(
+ "Unrecognized format type and subtype: '%s' and '%s'", type, modifier
+ ) );
};
}
src/main/java/com/keenwrite/dom/DocumentParser.java
import java.nio.file.Path;
import java.util.HashMap;
-import java.util.Map;
-import java.util.function.Consumer;
-
-import static com.keenwrite.events.StatusEvent.clue;
-import static com.keenwrite.io.SysFile.toFile;
-import static java.nio.charset.StandardCharsets.UTF_16;
-import static java.nio.charset.StandardCharsets.UTF_8;
-import static java.nio.file.Files.write;
-import static javax.xml.transform.OutputKeys.*;
-import static javax.xml.xpath.XPathConstants.NODESET;
-
-/**
- * Responsible for initializing an XML parser.
- */
-public class DocumentParser {
- private static final String LOAD_EXTERNAL_DTD =
- "http://apache.org/xml/features/nonvalidating/load-external-dtd";
- private static final String INDENT_AMOUNT =
- "{http://xml.apache.org/xslt}indent-amount";
-
- private static final ByteArrayOutputStream sWriter =
- new ByteArrayOutputStream( 65536 );
- private static final OutputStreamWriter sOutput =
- new OutputStreamWriter( sWriter, UTF_8 );
-
- /**
- * Caches {@link XPathExpression}s to avoid re-compiling.
- */
- private static final Map<String, XPathExpression> sXpaths = new HashMap<>();
-
- private static final DocumentBuilderFactory sDocumentFactory;
- private static DocumentBuilder sDocumentBuilder;
- private static Transformer sTransformer;
- private static final XPath sXpath = XPathFactory.newInstance().newXPath();
-
- public static final DOMImplementation sDomImplementation;
-
- static {
- sDocumentFactory = DocumentBuilderFactory.newInstance();
-
- sDocumentFactory.setValidating( false );
- sDocumentFactory.setAttribute( LOAD_EXTERNAL_DTD, false );
- sDocumentFactory.setNamespaceAware( true );
- sDocumentFactory.setIgnoringComments( true );
- sDocumentFactory.setIgnoringElementContentWhitespace( true );
-
- DOMImplementation domImplementation;
-
- try {
- sDocumentBuilder = sDocumentFactory.newDocumentBuilder();
- domImplementation = sDocumentBuilder.getDOMImplementation();
- sTransformer = TransformerFactory.newInstance().newTransformer();
-
- // Ensure Unicode characters (emojis) are encoded correctly.
- sTransformer.setOutputProperty( ENCODING, UTF_16.toString() );
- sTransformer.setOutputProperty( OMIT_XML_DECLARATION, "yes" );
- sTransformer.setOutputProperty( METHOD, "xml" );
- sTransformer.setOutputProperty( INDENT, "no" );
- sTransformer.setOutputProperty( INDENT_AMOUNT, "2" );
- } catch( final Exception ex ) {
- clue( ex );
- domImplementation = sDocumentBuilder.getDOMImplementation();
- }
-
- sDomImplementation = domImplementation;
- }
-
- public static Document newDocument() {
- return sDocumentBuilder.newDocument();
- }
-
- /**
- * Creates a new document object model based on the given XML document
- * string. This will return an empty document if the document could not
- * be parsed.
- *
- * @param xml The document text to convert into a DOM.
- * @return The DOM that represents the given XML data.
- */
- public static Document parse( final String xml ) {
- assert xml != null;
-
- final var input = new InputSource();
-
- try( final var reader = new StringReader( xml ) ) {
- input.setEncoding( UTF_8.toString() );
- input.setCharacterStream( reader );
-
- return sDocumentBuilder.parse( input );
- } catch( final Throwable t ) {
- clue( t );
-
- return sDocumentBuilder.newDocument();
- }
- }
-
- /**
- * Parses the given file contents into a document object model.
- *
- * @param doc The source XML document to parse.
- * @return The file as a document object model.
- * @throws IOException Could not open the document.
- * @throws SAXException Could not read the XML file content.
- */
- public static Document parse( final File doc )
- throws IOException, SAXException {
- assert doc != null;
-
- try( final var in = new FileInputStream( doc ) ) {
- return parse( in );
- }
- }
-
- /**
- * Parses the given file contents into a document object model. Callers
- * must close the stream.
- *
- * @param doc The source XML document to parse.
- * @return The {@link InputStream} converted to a document object model.
- * @throws IOException Could not open the document.
- * @throws SAXException Could not read the XML file content.
- */
- public static Document parse( final InputStream doc )
- throws IOException, SAXException {
- assert doc != null;
-
- return sDocumentBuilder.parse( doc );
- }
-
- /**
- * Allows an operation to be applied for every node in the document that
- * matches a given tag name pattern.
- *
- * @param document Document to traverse.
- * @param xpath Document elements to find via {@link XPath} expression.
- * @param consumer The consumer to call for each matching document node.
- */
- public static void visit(
- final Document document,
- final CharSequence xpath,
- final Consumer<Node> consumer ) {
- assert document != null;
- assert consumer != null;
-
- try {
- final var expr = compile( xpath );
- final var nodeSet = expr.evaluate( document, NODESET );
-
- if( nodeSet instanceof NodeList nodes ) {
- for( int i = 0, len = nodes.getLength(); i < len; i++ ) {
- consumer.accept( nodes.item( i ) );
- }
- }
- } catch( final Exception ex ) {
- clue( ex );
- }
- }
-
- public static Node createMeta(
- final Document document, final Map.Entry<String, String> entry ) {
- assert document != null;
- assert entry != null;
-
- final var node = document.createElement( "meta" );
-
- node.setAttribute( "name", entry.getKey() );
- node.setAttribute( "content", entry.getValue() );
-
- return node;
- }
-
- public static Node createEncoding(
- final Document document, final String encoding
- ) {
- assert document != null;
- assert encoding != null;
-
- final var node = document.createElement( "meta" );
-
- node.setAttribute( "charset", encoding );
-
- return node;
- }
-
- public static Node createElement(
- final Document doc, final String nodeName, final String nodeValue ) {
- assert doc != null;
- assert nodeName != null;
- assert !nodeName.isBlank();
-
- final var node = doc.createElement( nodeName );
-
- if( nodeValue != null ) {
- node.setTextContent( nodeValue );
- }
-
- return node;
- }
-
- public static String toString( final Document xhtml ) {
- assert xhtml != null;
-
- try( final var writer = new StringWriter() ) {
- final var result = new StreamResult( writer );
-
- transform( xhtml, result );
-
- return writer.toString();
- } catch( final Exception ex ) {
- clue( ex );
- return "";
- }
- }
-
- public static String transform( final Element root )
- throws IOException, TransformerException {
- assert root != null;
-
- try( final var writer = new StringWriter() ) {
- transform( root.getOwnerDocument(), new StreamResult( writer ) );
-
- return writer.toString();
- }
- }
-
- /**
- * Remove whitespace, comments, and XML/DOCTYPE declarations to make
- * processing work with ConTeXt.
- *
- * @param path The SVG file to process.
- * @throws Exception The file could not be processed.
- */
- public static void sanitize( final Path path ) throws Exception {
- assert path != null;
-
- // Preprocessing the SVG image is a single-threaded operation, no matter
- // how many SVG images are in the document to typeset.
- sWriter.reset();
-
- final var target = new StreamResult( sOutput );
- final var source = sDocumentBuilder.parse( toFile( path ) );
-
- transform( source, target );
- write( path, sWriter.toByteArray() );
- }
-
- /**
- * Converts a string into an {@link XPathExpression}, which may be used to
- * extract elements from a {@link Document} object model.
- *
- * @param cs The string to convert to an {@link XPathExpression}.
- * @return {@code null} if there was an error compiling the xpath.
- */
- public static XPathExpression compile( final CharSequence cs ) {
- assert cs != null;
-
- final var xpath = cs.toString();
-
- return sXpaths.computeIfAbsent( xpath, k -> {
- try {
- return sXpath.compile( xpath );
- } catch( final XPathExpressionException ex ) {
- clue( ex );
- return null;
- }
- } );
- }
-
- /**
- * Streams an instance of {@link Document} as a plain text XML document.
- *
- * @param src The source document to transform.
- * @param dst The destination location to write the transformed version.
- * @throws TransformerException Could not transform the document.
- */
- private static void transform( final Document src, final StreamResult dst )
- throws TransformerException {
- sTransformer.transform( new DOMSource( src ), dst );
- }
-
- /**
- * Use the {@code static} constants and methods, not an instance, at least
- * until an iterable sub-interface is written.
- */
- private DocumentParser() {}
+import java.util.Locale;
+import java.util.Map;
+import java.util.function.Consumer;
+
+import static com.keenwrite.events.StatusEvent.clue;
+import static com.keenwrite.io.SysFile.toFile;
+import static java.nio.charset.StandardCharsets.UTF_16;
+import static java.nio.charset.StandardCharsets.UTF_8;
+import static java.nio.file.Files.write;
+import static javax.xml.transform.OutputKeys.*;
+import static javax.xml.xpath.XPathConstants.NODESET;
+
+/**
+ * Responsible for initializing an XML parser.
+ */
+public class DocumentParser {
+ private static final String LOAD_EXTERNAL_DTD =
+ "http://apache.org/xml/features/nonvalidating/load-external-dtd";
+ private static final String INDENT_AMOUNT =
+ "{http://xml.apache.org/xslt}indent-amount";
+
+ private static final ByteArrayOutputStream sWriter =
+ new ByteArrayOutputStream( 65536 );
+ private static final OutputStreamWriter sOutput =
+ new OutputStreamWriter( sWriter, UTF_8 );
+
+ /**
+ * Caches {@link XPathExpression}s to avoid re-compiling.
+ */
+ private static final Map<String, XPathExpression> sXpaths = new HashMap<>();
+
+ private static final DocumentBuilderFactory sDocumentFactory;
+ private static DocumentBuilder sDocumentBuilder;
+ private static Transformer sTransformer;
+ private static final XPath sXpath = XPathFactory.newInstance().newXPath();
+
+ public static final DOMImplementation sDomImplementation;
+
+ static {
+ sDocumentFactory = DocumentBuilderFactory.newInstance();
+
+ sDocumentFactory.setValidating( false );
+ sDocumentFactory.setAttribute( LOAD_EXTERNAL_DTD, false );
+ sDocumentFactory.setNamespaceAware( true );
+ sDocumentFactory.setIgnoringComments( true );
+ sDocumentFactory.setIgnoringElementContentWhitespace( true );
+
+ DOMImplementation domImplementation;
+
+ try {
+ sDocumentBuilder = sDocumentFactory.newDocumentBuilder();
+ domImplementation = sDocumentBuilder.getDOMImplementation();
+ sTransformer = TransformerFactory.newInstance().newTransformer();
+
+ // Ensure Unicode characters (emojis) are encoded correctly.
+ sTransformer.setOutputProperty( ENCODING, UTF_16.toString() );
+ sTransformer.setOutputProperty( OMIT_XML_DECLARATION, "yes" );
+ sTransformer.setOutputProperty( METHOD, "xml" );
+ sTransformer.setOutputProperty( INDENT, "no" );
+ sTransformer.setOutputProperty( INDENT_AMOUNT, "2" );
+ } catch( final Exception ex ) {
+ clue( ex );
+ domImplementation = sDocumentBuilder.getDOMImplementation();
+ }
+
+ sDomImplementation = domImplementation;
+ }
+
+ public static Document newDocument() {
+ return sDocumentBuilder.newDocument();
+ }
+
+ /**
+ * Creates a new document object model based on the given XML document
+ * string. This will return an empty document if the document could not
+ * be parsed.
+ *
+ * @param xml The document text to convert into a DOM.
+ * @return The DOM that represents the given XML data.
+ */
+ public static Document parse( final String xml ) {
+ assert xml != null;
+
+ final var input = new InputSource();
+
+ try( final var reader = new StringReader( xml ) ) {
+ input.setEncoding( UTF_8.toString() );
+ input.setCharacterStream( reader );
+
+ return sDocumentBuilder.parse( input );
+ } catch( final Throwable t ) {
+ clue( t );
+
+ return sDocumentBuilder.newDocument();
+ }
+ }
+
+ public static Document create(
+ final Document source,
+ final Map<String, String> metadata,
+ final Locale locale
+ ) throws IOException, SAXException {
+ final var NAMESPACE = "http://www.w3.org/1999/xhtml";
+
+ final var root = source.getDocumentElement();
+ root.setAttribute( "xmlns", NAMESPACE );
+
+ final var doc = newXhtmlDocument( NAMESPACE );
+ final var html = doc.getDocumentElement();
+ final var head = createElement( doc, "head", null );
+
+ html.setAttribute( "lang", locale.getLanguage() );
+
+ final var encoding = createEncoding( doc, "UTF-8" );
+ head.appendChild( encoding );
+
+ for( final var entry : metadata.entrySet() ) {
+ final var node = createMeta( doc, entry );
+ head.appendChild( node );
+ }
+
+ final var title = createElement( doc, "title", "Generated Page" );
+ head.appendChild( title );
+ html.appendChild( head );
+
+ final var body = createElement( doc, "body", null );
+ final var sourceBody = source.getElementsByTagName( "body" ).item( 0 );
+ final var children = sourceBody.getChildNodes();
+ final var count = children.getLength();
+
+ for( var i = 0; i < count; i++ ) {
+ final var imported = importNode( doc, children.item( i ), NAMESPACE );
+ body.appendChild( imported );
+ }
+
+ html.appendChild( body );
+
+ return doc;
+ }
+
+ private static Node importNode(
+ final Document targetDoc,
+ final Node sourceNode,
+ final String namespace ) {
+
+ if( sourceNode.getNodeType() == Node.ELEMENT_NODE ) {
+ // Create element in target namespace
+ final var element = targetDoc.createElementNS(
+ namespace,
+ sourceNode.getNodeName()
+ );
+
+ // Copy attributes
+ final var attrs = sourceNode.getAttributes();
+ if( attrs != null ) {
+ for( int i = 0; i < attrs.getLength(); i++ ) {
+ final var attr = attrs.item( i );
+ element.setAttribute( attr.getNodeName(), attr.getNodeValue() );
+ }
+ }
+
+ // Recursively copy children
+ final var children = sourceNode.getChildNodes();
+ for( int i = 0; i < children.getLength(); i++ ) {
+ final var child = importNode(
+ targetDoc,
+ children.item( i ), namespace
+ );
+ element.appendChild( child );
+ }
+
+ return element;
+ }
+ else if( sourceNode.getNodeType() == Node.TEXT_NODE ) {
+ return targetDoc.createTextNode( sourceNode.getNodeValue() );
+ }
+ else {
+ // For other node types, fall back to regular import
+ return targetDoc.importNode( sourceNode, true );
+ }
+ }
+
+ public static Document newXhtmlDocument( final String namespace ) {
+ return sDomImplementation.createDocument(
+ namespace,
+ "html",
+ sDomImplementation.createDocumentType(
+ "html", "-//W3C//DTD XHTML 1.0 Strict//EN",
+ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"
+ )
+ );
+ }
+
+ /**
+ * Parses the given file contents into a document object model.
+ *
+ * @param doc The source XML document to parse.
+ * @return The file as a document object model.
+ * @throws IOException Could not open the document.
+ * @throws SAXException Could not read the XML file content.
+ */
+ public static Document parse( final File doc )
+ throws IOException, SAXException {
+ assert doc != null;
+
+ try( final var in = new FileInputStream( doc ) ) {
+ return parse( in );
+ }
+ }
+
+ /**
+ * Parses the given file contents into a document object model. Callers
+ * must close the stream.
+ *
+ * @param doc The source XML document to parse.
+ * @return The {@link InputStream} converted to a document object model.
+ * @throws IOException Could not open the document.
+ * @throws SAXException Could not read the XML file content.
+ */
+ public static Document parse( final InputStream doc )
+ throws IOException, SAXException {
+ assert doc != null;
+
+ return sDocumentBuilder.parse( doc );
+ }
+
+ /**
+ * Allows an operation to be applied for every node in the document that
+ * matches a given tag name pattern.
+ *
+ * @param document Document to traverse.
+ * @param xpath Document elements to find via {@link XPath} expression.
+ * @param consumer The consumer to call for each matching document node.
+ */
+ public static void visit(
+ final Document document,
+ final CharSequence xpath,
+ final Consumer<Node> consumer ) {
+ assert document != null;
+ assert consumer != null;
+
+ try {
+ final var expr = compile( xpath );
+ final var nodeSet = expr.evaluate( document, NODESET );
+
+ if( nodeSet instanceof NodeList nodes ) {
+ for( int i = 0, len = nodes.getLength(); i < len; i++ ) {
+ consumer.accept( nodes.item( i ) );
+ }
+ }
+ } catch( final Exception ex ) {
+ clue( ex );
+ }
+ }
+
+ public static Node createMeta(
+ final Document document, final Map.Entry<String, String> entry ) {
+ assert document != null;
+ assert entry != null;
+
+ final var node = document.createElement( "meta" );
+
+ node.setAttribute( "name", entry.getKey() );
+ node.setAttribute( "content", entry.getValue() );
+
+ return node;
+ }
+
+ public static Node createEncoding(
+ final Document document, final String encoding
+ ) {
+ assert document != null;
+ assert encoding != null;
+
+ final var node = document.createElement( "meta" );
+
+ node.setAttribute( "http-equiv", "Content-Type" );
+ node.setAttribute( "content", "text/html; charset=" + encoding );
+
+ return node;
+ }
+
+ public static Element createElement(
+ final Document doc, final String nodeName, final String nodeValue ) {
+ assert doc != null;
+ assert nodeName != null;
+ assert !nodeName.isBlank();
+
+ final var node = doc.createElement( nodeName );
+
+ if( nodeValue != null ) {
+ node.setTextContent( nodeValue );
+ }
+
+ return node;
+ }
+
+ public static String toString( final Document xhtml ) {
+ assert xhtml != null;
+
+ try( final var writer = new StringWriter() ) {
+ final var result = new StreamResult( writer );
+
+ transform( xhtml, result );
+
+ return writer.toString();
+ } catch( final Exception ex ) {
+ clue( ex );
+ return "";
+ }
+ }
+
+ public static String transform( final Element root )
+ throws IOException, TransformerException {
+ assert root != null;
+
+ try( final var writer = new StringWriter() ) {
+ transform( root.getOwnerDocument(), new StreamResult( writer ) );
+
+ return writer.toString();
+ }
+ }
+
+ /**
+ * Remove whitespace, comments, and XML/DOCTYPE declarations to make
+ * processing work with ConTeXt.
+ *
+ * @param path The SVG file to process.
+ * @throws Exception The file could not be processed.
+ */
+ public static void sanitize( final Path path ) throws Exception {
+ assert path != null;
+
+ // Preprocessing the SVG image is a single-threaded operation, no matter
+ // how many SVG images are in the document to typeset.
+ sWriter.reset();
+
+ final var target = new StreamResult( sOutput );
+ final var source = sDocumentBuilder.parse( toFile( path ) );
+
+ transform( source, target );
+ write( path, sWriter.toByteArray() );
+ }
+
+ /**
+ * Converts a string into an {@link XPathExpression}, which may be used to
+ * extract elements from a {@link Document} object model.
+ *
+ * @param cs The string to convert to an {@link XPathExpression}.
+ * @return {@code null} if there was an error compiling the xpath.
+ */
+ public static XPathExpression compile( final CharSequence cs ) {
+ assert cs != null;
+
+ final var xpath = cs.toString();
+
+ return sXpaths.computeIfAbsent(
+ xpath, k -> {
+ try {
+ return sXpath.compile( xpath );
+ } catch( final XPathExpressionException ex ) {
+ clue( ex );
+ return null;
+ }
+ }
+ );
+ }
+
+ /**
+ * Streams an instance of {@link Document} as a plain text XML document.
+ *
+ * @param src The source document to transform.
+ * @param dst The destination location to write the transformed version.
+ * @throws TransformerException Could not transform the document.
+ */
+ private static void transform( final Document src, final StreamResult dst )
+ throws TransformerException {
+ sTransformer.transform( new DOMSource( src ), dst );
+ }
+
+ /**
+ * Use the {@code static} constants and methods, not an instance, at least
+ * until an iterable sub-interface is written.
+ */
+ private DocumentParser() {
+ }
}
src/main/java/com/keenwrite/io/MediaType.java
APP_PDF( APPLICATION, "pdf" ),
APP_ZIP( APPLICATION, "zip" ),
+ APP_XHTML( APPLICATION, "xhtml+xml" ),
/*
TEXT_PROPERTIES( TEXT, "x-java-properties" ),
TEXT_HTML( TEXT, "html" ),
- TEXT_XHTML( TEXT, "xhtml+xml" ),
TEXT_XML( TEXT, "xml" ),
src/main/java/com/keenwrite/io/MediaTypeExtension.java
MEDIA_IMAGE_GIF( IMAGE_GIF ),
MEDIA_IMAGE_JPEG( IMAGE_JPEG,
- of( "jpg", "jpe", "jpeg", "jfif", "pjpeg", "pjp" ) ),
+ of( "jpg", "jpe", "jpeg", "jfif", "pjpeg", "pjp" ) ),
MEDIA_IMAGE_PNG( IMAGE_PNG ),
MEDIA_IMAGE_PSD( IMAGE_PHOTOSHOP, of( "psd" ) ),
MEDIA_TEXT_R_MARKDOWN( TEXT_R_MARKDOWN, of( "Rmd" ) ),
MEDIA_TEXT_PROPERTIES( TEXT_PROPERTIES, of( "properties" ) ),
- MEDIA_TEXT_XHTML( TEXT_XHTML, of( "htm", "html", "xhtml" ) ),
+ MEDIA_TEXT_HTML( TEXT_HTML, of( "htm", "html" ) ),
+ MEDIA_APP_XHTML( APP_XHTML, of( "xhtml" ) ),
MEDIA_TEXT_XML( TEXT_XML ),
MEDIA_TEXT_YAML( TEXT_YAML, of( "yaml", "yml" ) ),
*/
public String getExtension() {
- return mExtensions.get( 0 );
+ return mExtensions.getFirst();
}
src/main/java/com/keenwrite/processors/ProcessorFactory.java
final var successor = switch( outputType ) {
case NONE -> preview;
- case HTML_TEX_DELIMITED -> createHtmlProcessor( context );
- case XHTML_TEX -> createXhtmlProcessor( context );
+ case HTML_TEX_DELIMITED, HTML_TEX_SVG -> createHtmlProcessor( context );
+ case XHTML_TEX, XHTML_TEX_SVG -> createXhtmlProcessor( context );
case TEXT_TEX -> createTextProcessor( context );
case APPLICATION_PDF -> createPdfProcessor( context );
default -> createIdentityProcessor( context );
};
-
final var inputType = context.getSourceFileType();
final Processor<String> processor;
src/main/java/com/keenwrite/processors/html/XhtmlProcessor.java
private static final Curler CURLER = createCurler( FILTER_XML, CONVERT_APOS );
private static final String DTD =
- "<!DOCTYPE html PUBLIC " +
- "\"-//W3C//DTD XHTML 1.0 Transitional//EN\" " +
- "\"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">";
+ "<!DOCTYPE html PUBLIC " +
+ "\"-//W3C//DTD XHTML 1.0 Transitional//EN\" " +
+ "\"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">";
private final ProcessorContext mContext;
try {
final var doc = parse( html );
- setMetaData( doc );
visit( doc, "//img", node -> {
} );
- final var document = DTD + DocumentParser.toString( doc );
+ final var locale = mContext.getLocale();
+ final var metadata = createMetaDataMap( doc );
+ final var xhtml = DocumentParser.create( doc, metadata, locale );
+ final var document = DTD + DocumentParser.toString( xhtml );
final var curl = mContext.getCurlQuotes();

Exports as XHTML from command-line for .xhtml files

Author DaveJarvis <email>
Date 2025-08-20 19:42:15 GMT-0700
Commit 2b0e847697646ba5c9943d516de4cd634b9973e1
Parent ec26a8e
Delta 418 lines added, 301 lines removed, 117-line increase