| # Licensed to the Apache Software Foundation (ASF) under one |
| # or more contributor license agreements. See the NOTICE file |
| # distributed with this work for additional information |
| # regarding copyright ownership. The ASF licenses this file |
| # to you under the Apache License, Version 2.0 (the |
| # "License"); you may not use this file except in compliance |
| # with the License. You may obtain a copy of the License at |
| # |
| # http://www.apache.org/licenses/LICENSE-2.0 |
| # |
| # Unless required by applicable law or agreed to in writing, |
| # software distributed under the License is distributed on an |
| # "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY |
| # KIND, either express or implied. See the License for the |
| # specific language governing permissions and limitations |
| # under the License. |
| # |
| # HG changeset patch |
| # Parent d4c267a15aa0ac57d2f00ccd68eb46eb463738a7 |
| Minimal changes to integrate html parser with netbeans infrastructure |
| - create a unique version |
| - disable the HotSpot workaound, as we need the detailed transition informations |
| - track the global position of the parser |
| - make startTage and end Tag overrideable in TreeBuilder |
| |
| diff --git a/pom.xml b/pom.xml |
| --- a/pom.xml |
| +++ b/pom.xml |
| @@ -20,17 +20,17 @@ |
| * DEALINGS IN THE SOFTWARE. |
| --> |
| <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" |
| xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd"> |
| <modelVersion>4.0.0</modelVersion> |
| <groupId>nu.validator.htmlparser</groupId> |
| <artifactId>htmlparser</artifactId> |
| <packaging>bundle</packaging> |
| - <version>1.4</version> |
| + <version>1.4.20190624</version> |
| <name>htmlparser</name> |
| <url>http://about.validator.nu/htmlparser/</url> |
| <description>The Validator.nu HTML Parser is an implementation of the HTML5 parsing algorithm in Java for applications. The parser is designed to work as a drop-in replacement for the XML parser in applications that already support XHTML 1.x content with an XML parser and use SAX, DOM or XOM to interface with the parser.</description> |
| <!-- |
| Usage notes for this POM: |
| |
| To build without signing, run: |
| mvn clean source:jar javadoc:jar repository:bundle-create |
| @@ -68,16 +68,17 @@ |
| <distribution>repo</distribution> |
| </license> |
| </licenses> |
| <scm> |
| <connection>scm:hg:http://hg.mozilla.org/projects/htmlparser/</connection> |
| <url>http://hg.mozilla.org/projects/htmlparser/</url> |
| </scm> |
| <build> |
| + <!--<sourceDirectory>${basedir}/src</sourceDirectory>--> |
| <sourceDirectory>${project.build.directory}/src</sourceDirectory> |
| <testSourceDirectory>${basedir}/test-src</testSourceDirectory> |
| <plugins> |
| <plugin> |
| <groupId>org.apache.maven.plugins</groupId> |
| <artifactId>maven-compiler-plugin</artifactId> |
| <configuration> |
| <source>1.5</source> |
| @@ -108,17 +109,17 @@ |
| <delete dir="${project.build.sourceDirectory}"/> |
| <mkdir dir="${project.build.sourceDirectory}"/> |
| <copy todir="${project.build.sourceDirectory}"> |
| <fileset dir="${basedir}/src"/> |
| </copy> |
| </target> |
| </configuration> |
| </execution> |
| - <execution> |
| +<!-- <execution> |
| <id>tokenizer-hotspot-workaround</id> |
| <phase>process-sources</phase> |
| <goals> |
| <goal>run</goal> |
| </goals> |
| <configuration> |
| <target> |
| <property name="translator.sources" value="${basedir}/translator-src"/> |
| @@ -129,17 +130,17 @@ |
| <classpath> |
| <pathelement location="${translator.classes}"/> |
| </classpath> |
| <arg value="${project.build.sourceDirectory}/nu/validator/htmlparser/impl/Tokenizer.java"/> |
| <arg value="${project.build.sourceDirectory}/nu/validator/htmlparser/impl/HotSpotWorkaround.txt"/> |
| </java> |
| </target> |
| </configuration> |
| - </execution> |
| + </execution>--> |
| </executions> |
| </plugin> |
| <plugin> |
| <groupId>org.apache.maven.plugins</groupId> |
| <artifactId>maven-surefire-plugin</artifactId> |
| <configuration> |
| <skip>true</skip> |
| </configuration> |
| diff --git a/src/nu/validator/htmlparser/impl/Tokenizer.java b/src/nu/validator/htmlparser/impl/Tokenizer.java |
| --- a/src/nu/validator/htmlparser/impl/Tokenizer.java |
| +++ b/src/nu/validator/htmlparser/impl/Tokenizer.java |
| @@ -504,16 +504,19 @@ public class Tokenizer implements Locato |
| private final boolean newAttributesEachTime; |
| |
| private boolean shouldSuspend; |
| |
| protected boolean confident; |
| |
| private int line; |
| |
| + //holds the offset of the current buffer relative to the beginning of the input source |
| + protected int currentBufferGlobalOffset; |
| + |
| /* |
| * The line number of the current attribute. First set to the line of the |
| * attribute name and if there is a value, set to the line the value |
| * started on. |
| */ |
| // CPPONLY: private int attributeLine; |
| |
| private Interner interner; |
| @@ -1371,16 +1374,18 @@ public class Tokenizer implements Locato |
| initializeWithoutStarting(); |
| tokenHandler.startTokenization(this); |
| // [NOCPP[ |
| startErrorReporting(); |
| // ]NOCPP] |
| } |
| |
| public boolean tokenizeBuffer(UTF16Buffer buffer) throws SAXException { |
| + setTransitionBaseOffset(currentBufferGlobalOffset); |
| + |
| int state = stateSave; |
| int returnState = returnStateSave; |
| char c = '\u0000'; |
| shouldSuspend = false; |
| lastCR = false; |
| |
| int start = buffer.getStart(); |
| int end = buffer.getEnd(); |
| @@ -1443,16 +1448,21 @@ public class Tokenizer implements Locato |
| end); |
| // ]NOCPP] |
| if (pos == end) { |
| // exiting due to end of buffer |
| buffer.setStart(pos); |
| } else { |
| buffer.setStart(pos + 1); |
| } |
| + |
| + if(! buffer.hasMore()) { |
| + currentBufferGlobalOffset += buffer.getEnd(); |
| + } |
| + |
| return lastCR; |
| } |
| |
| // [NOCPP[ |
| private void ensureBufferSpace(int inputLength) throws SAXException { |
| // Add 2 to account for emissions of LT_GT, LT_SOLIDUS and RSQB_RSQB. |
| // Adding to the general worst case instead of only the |
| // TreeBuilder-exposed worst case to avoid re-introducing a bug when |
| @@ -6924,16 +6934,17 @@ public class Tokenizer implements Locato |
| html4 = false; |
| metaBoundaryPassed = false; |
| wantsComments = tokenHandler.wantsComments(); |
| if (!newAttributesEachTime) { |
| attributes = new HtmlAttributes(mappingLangToXmlLang); |
| } |
| // ]NOCPP] |
| resetToDataState(); |
| + currentBufferGlobalOffset = 0; |
| } |
| |
| protected void errGarbageAfterLtSlash() throws SAXException { |
| } |
| |
| protected void errLtSlashGt() throws SAXException { |
| } |
| |
| diff --git a/src/nu/validator/htmlparser/impl/TreeBuilder.java b/src/nu/validator/htmlparser/impl/TreeBuilder.java |
| --- a/src/nu/validator/htmlparser/impl/TreeBuilder.java |
| +++ b/src/nu/validator/htmlparser/impl/TreeBuilder.java |
| @@ -1666,17 +1666,17 @@ public abstract class TreeBuilder<T> imp |
| } |
| // [NOCPP[ |
| idLocations.clear(); |
| // ]NOCPP] |
| charBuffer = null; |
| end(); |
| } |
| |
| - public final void startTag(ElementName elementName, |
| + public void startTag(ElementName elementName, |
| HtmlAttributes attributes, boolean selfClosing) throws SAXException { |
| flushCharacters(); |
| |
| // [NOCPP[ |
| if (errorHandler != null) { |
| // ID uniqueness |
| @IdType String id = attributes.getId(); |
| if (id != null) { |
| @@ -3330,17 +3330,17 @@ public abstract class TreeBuilder<T> imp |
| if (tokenizer.internalEncodingDeclaration(extract)) { |
| requestSuspension(); |
| } |
| } |
| Portability.releaseString(extract); |
| } |
| } |
| |
| - public final void endTag(ElementName elementName) throws SAXException { |
| + public void endTag(ElementName elementName) throws SAXException { |
| flushCharacters(); |
| needToDropLF = false; |
| int eltPos; |
| int group = elementName.getGroup(); |
| @Local String name = elementName.getName(); |
| endtagloop: for (;;) { |
| if (isInForeign()) { |
| if (stack[currentPtr].name != name) { |
