Tim Starling has submitted this change and it was merged.
Change subject: New Grizzly version
......................................................................
New Grizzly version
* Migrate from Ant to Maven. Rearrange files per Maven standard. Add
dependencies.
* Migrate from servlet to Grizzly. The servlet class is still there but
doesn't work at the moment.
* Rename from HTML5Tidy to HTML5Depurate, so that there is less chance
of collision.
* Add CC0 license.
Change-Id: Ifb1e01191b9975a97897eb8a84d61a5b60b3dc26
---
M .gitreview
A LICENSE.TXT
R build-tomcat.xml
A pom.xml
A src/main/java/org/wikimedia/html5depurate/Config.java
A src/main/java/org/wikimedia/html5depurate/DepurateDaemon.java
A src/main/java/org/wikimedia/html5depurate/DepurateErrorPageGenerator.java
A src/main/java/org/wikimedia/html5depurate/DepurateHandler.java
A src/main/java/org/wikimedia/html5depurate/Depurator.java
A src/main/java/org/wikimedia/html5depurate/MultipartBuffer.java
R src/webapp/org/wikimedia/html5depurate/DepurateServlet.java
11 files changed, 569 insertions(+), 22 deletions(-)
Approvals:
Tim Starling: Verified; Looks good to me, approved
diff --git a/.gitreview b/.gitreview
index c2fce0c..da1e076 100644
--- a/.gitreview
+++ b/.gitreview
@@ -1,6 +1,6 @@
[gerrit]
host=gerrit.wikimedia.org
port=29418
-project=mediawiki/services/html5tidy.git
+project=mediawiki/services/html5depurate.git
defaultbranch=master
defaultrebase=0
diff --git a/LICENSE.TXT b/LICENSE.TXT
new file mode 100644
index 0000000..1373246
--- /dev/null
+++ b/LICENSE.TXT
@@ -0,0 +1,119 @@
+CC0 1.0 Universal
+
+ CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE
+ LEGAL SERVICES. DISTRIBUTION OF THIS DOCUMENT DOES NOT CREATE AN
+ ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS
+ INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES
+ REGARDING THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS
+ PROVIDED HEREUNDER, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM
+ THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS PROVIDED
+ HEREUNDER.
+
+Statement of Purpose
+
+The laws of most jurisdictions throughout the world automatically confer
+exclusive Copyright and Related Rights (defined below) upon the creator
+and subsequent owner(s) (each and all, an "owner") of an original work of
+authorship and/or a database (each, a "Work").
+
+Certain owners wish to permanently relinquish those rights to a Work for
+the purpose of contributing to a commons of creative, cultural and
+scientific works ("Commons") that the public can reliably and without fear
+of later claims of infringement build upon, modify, incorporate in other
+works, reuse and redistribute as freely as possible in any form whatsoever
+and for any purposes, including without limitation commercial purposes.
+These owners may contribute to the Commons to promote the ideal of a free
+culture and the further production of creative, cultural and scientific
+works, or to gain reputation or greater distribution for their Work in
+part through the use and efforts of others.
+
+For these and/or other purposes and motivations, and without any
+expectation of additional consideration or compensation, the person
+associating CC0 with a Work (the "Affirmer"), to the extent that he or she
+is an owner of Copyright and Related Rights in the Work, voluntarily
+elects to apply CC0 to the Work and publicly distribute the Work under its
+terms, with knowledge of his or her Copyright and Related Rights in the
+Work and the meaning and intended legal effect of CC0 on those rights.
+
+1. Copyright and Related Rights. A Work made available under CC0 may be
+protected by copyright and related or neighboring rights ("Copyright and
+Related Rights"). Copyright and Related Rights include, but are not
+limited to, the following:
+
+ i. the right to reproduce, adapt, distribute, perform, display,
+ communicate, and translate a Work;
+ ii. moral rights retained by the original author(s) and/or performer(s);
+iii. publicity and privacy rights pertaining to a person's image or
+ likeness depicted in a Work;
+ iv. rights protecting against unfair competition in regards to a Work,
+ subject to the limitations in paragraph 4(a), below;
+ v. rights protecting the extraction, dissemination, use and reuse of data
+ in a Work;
+ vi. database rights (such as those arising under Directive 96/9/EC of the
+ European Parliament and of the Council of 11 March 1996 on the legal
+ protection of databases, and under any national implementation
+ thereof, including any amended or successor version of such
+ directive); and
+vii. other similar, equivalent or corresponding rights throughout the
+ world based on applicable law or treaty, and any national
+ implementations thereof.
+
+2. Waiver. To the greatest extent permitted by, but not in contravention
+of, applicable law, Affirmer hereby overtly, fully, permanently,
+irrevocably and unconditionally waives, abandons, and surrenders all of
+Affirmer's Copyright and Related Rights and associated claims and causes
+of action, whether now known or unknown (including existing as well as
+future claims and causes of action), in the Work (i) in all territories
+worldwide, (ii) for the maximum duration provided by applicable law or
+treaty (including future time extensions), (iii) in any current or future
+medium and for any number of copies, and (iv) for any purpose whatsoever,
+including without limitation commercial, advertising or promotional
+purposes (the "Waiver"). Affirmer makes the Waiver for the benefit of each
+member of the public at large and to the detriment of Affirmer's heirs and
+successors, fully intending that such Waiver shall not be subject to
+revocation, rescission, cancellation, termination, or any other legal or
+equitable action to disrupt the quiet enjoyment of the Work by the public
+as contemplated by Affirmer's express Statement of Purpose.
+
+3. Public License Fallback. Should any part of the Waiver for any reason
+be judged legally invalid or ineffective under applicable law, then the
+Waiver shall be preserved to the maximum extent permitted taking into
+account Affirmer's express Statement of Purpose. In addition, to the
+extent the Waiver is so judged Affirmer hereby grants to each affected
+person a royalty-free, non transferable, non sublicensable, non exclusive,
+irrevocable and unconditional license to exercise Affirmer's Copyright and
+Related Rights in the Work (i) in all territories worldwide, (ii) for the
+maximum duration provided by applicable law or treaty (including future
+time extensions), (iii) in any current or future medium and for any number
+of copies, and (iv) for any purpose whatsoever, including without
+limitation commercial, advertising or promotional purposes (the
+"License"). The License shall be deemed effective as of the date CC0 was
+applied by Affirmer to the Work. Should any part of the License for any
+reason be judged legally invalid or ineffective under applicable law, such
+partial invalidity or ineffectiveness shall not invalidate the remainder
+of the License, and in such case Affirmer hereby affirms that he or she
+will not (i) exercise any of his or her remaining Copyright and Related
+Rights in the Work or (ii) assert any associated claims and causes of
+action with respect to the Work, in either case contrary to Affirmer's
+express Statement of Purpose.
+
+4. Limitations and Disclaimers.
+
+ a. No trademark or patent rights held by Affirmer are waived, abandoned,
+ surrendered, licensed or otherwise affected by this document.
+ b. Affirmer offers the Work as-is and makes no representations or
+ warranties of any kind concerning the Work, express, implied,
+ statutory or otherwise, including without limitation warranties of
+ title, merchantability, fitness for a particular purpose, non
+ infringement, or the absence of latent or other defects, accuracy, or
+ the present or absence of errors, whether or not discoverable, all to
+ the greatest extent permissible under applicable law.
+ c. Affirmer disclaims responsibility for clearing rights of other persons
+ that may apply to the Work or any use thereof, including without
+ limitation any person's Copyright and Related Rights in the Work.
+ Further, Affirmer disclaims responsibility for obtaining any necessary
+ consents, permissions or other rights required for any use of the
+ Work.
+ d. Affirmer understands and acknowledges that Creative Commons is not a
+ party to this document and has no duty or obligation with respect to
+ this CC0 or use of the Work.
diff --git a/build.xml b/build-tomcat.xml
similarity index 100%
rename from build.xml
rename to build-tomcat.xml
diff --git a/pom.xml b/pom.xml
new file mode 100644
index 0000000..e726baa
--- /dev/null
+++ b/pom.xml
@@ -0,0 +1,42 @@
+<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>org.wikimedia</groupId>
+ <artifactId>html5depurate</artifactId>
+ <packaging>jar</packaging>
+ <version>1.0-SNAPSHOT</version>
+ <name>html5depurate</name>
+ <url>http://maven.apache.org</url>
+ <dependencies>
+ <dependency>
+ <groupId>nu.validator</groupId>
+ <artifactId>htmlparser</artifactId>
+ <version>1.4.1</version>
+ </dependency>
+ <dependency>
+ <groupId>commons-daemon</groupId>
+ <artifactId>commons-daemon</artifactId>
+ <version>1.0.15</version>
+ </dependency>
+ <dependency>
+ <groupId>commons-cli</groupId>
+ <artifactId>commons-cli</artifactId>
+ <version>1.3.1</version>
+ </dependency>
+ <dependency>
+ <groupId>org.glassfish.grizzly</groupId>
+ <artifactId>grizzly-framework</artifactId>
+ <version>2.3.22</version>
+ </dependency>
+ <dependency>
+ <groupId>org.glassfish.grizzly</groupId>
+ <artifactId>grizzly-http-server</artifactId>
+ <version>2.3.22</version>
+ </dependency>
+ <dependency>
+ <groupId>org.glassfish.grizzly</groupId>
+ <artifactId>grizzly-http-server-multipart</artifactId>
+ <version>2.3.22</version>
+ </dependency>
+ </dependencies>
+</project>
diff --git a/src/main/java/org/wikimedia/html5depurate/Config.java
b/src/main/java/org/wikimedia/html5depurate/Config.java
new file mode 100644
index 0000000..bb9b34e
--- /dev/null
+++ b/src/main/java/org/wikimedia/html5depurate/Config.java
@@ -0,0 +1,9 @@
+package org.wikimedia.html5depurate;
+
+class Config {
+ public Config() {}
+
+ int maxPostSize;
+ String host;
+ int port;
+}
diff --git a/src/main/java/org/wikimedia/html5depurate/DepurateDaemon.java
b/src/main/java/org/wikimedia/html5depurate/DepurateDaemon.java
new file mode 100644
index 0000000..a171c7b
--- /dev/null
+++ b/src/main/java/org/wikimedia/html5depurate/DepurateDaemon.java
@@ -0,0 +1,114 @@
+package org.wikimedia.html5depurate;
+
+import org.wikimedia.html5depurate.Config;
+import org.wikimedia.html5depurate.DepurateErrorPageGenerator;
+
+import org.apache.commons.cli.CommandLine;
+import org.apache.commons.cli.DefaultParser;
+import org.apache.commons.cli.Options;
+import org.apache.commons.cli.ParseException;
+import org.apache.commons.daemon.Daemon;
+import org.apache.commons.daemon.DaemonContext;
+import org.apache.commons.daemon.DaemonInitException;
+
+import org.glassfish.grizzly.http.server.HttpServer;
+import org.glassfish.grizzly.http.server.NetworkListener;
+import org.glassfish.grizzly.http.server.ServerConfiguration;
+
+import java.io.FileNotFoundException;
+import java.io.FileInputStream;
+import java.io.IOException;
+import java.util.Properties;
+import java.util.logging.Logger;
+import java.util.logging.Level;
+
+/**
+ * Daemon for execution via jsvc
+ */
+public class DepurateDaemon implements Daemon {
+ HttpServer m_server;
+ String[] m_args;
+ Logger m_logger = Logger.getLogger(this.getClass().getName());
+
+ public static void main(String[] args) throws Exception {
+ DepurateDaemon daemon = new DepurateDaemon();
+ daemon.m_args = args;
+ daemon.start();
+ Thread.currentThread().join();
+ }
+
+ public void init(DaemonContext context)
+ throws DaemonInitException,Exception
+ {
+ m_args = context.getArguments();
+ }
+
+ protected CommandLine loadCommandLine()
+ throws IOException, ParseException
+ {
+ Options options = new Options();
+ options.addOption("c", true, "The configuration file name");
+ DefaultParser parser = new DefaultParser();
+ return parser.parse(options, m_args);
+ }
+
+ protected Config loadConfig(String path) {
+ Config config = new Config();
+ Properties properties = new Properties();
+ try {
+ properties.load(new FileInputStream(path));
+ } catch (FileNotFoundException e) {
+ m_logger.warning("Config file not found: " + path);
+ } catch (IOException e) {
+ m_logger.warning("Error loading config file: " +
e.toString());
+ }
+
+ double maxPostSize = Double.parseDouble(
+ properties.getProperty("maxPostSize", "100e6"));
+ if (maxPostSize > Integer.MAX_VALUE) {
+ config.maxPostSize = Integer.MAX_VALUE;
+ } else if (maxPostSize > 0) {
+ config.maxPostSize = (int)maxPostSize;
+ } else {
+ config.maxPostSize = 100000000;
+ }
+ m_logger.info("Max post size: " + config.maxPostSize);
+
+ config.host = properties.getProperty("host", "localhost");
+ config.port = Integer.parseInt(properties.getProperty("port",
"4339"));
+ m_logger.info("Binding to " + config.host + ":" +
Integer.toString(config.port));
+
+ return config;
+ }
+
+ public void start() throws Exception {
+ m_logger.info("Starting");
+
+ CommandLine cl = loadCommandLine();
+ String configPath = "/etc/html5depurate/html5depurate.conf";
+ if (cl.hasOption("c")) {
+ configPath = cl.getOptionValue("c");
+ }
+ Config config = loadConfig(configPath);
+
+ m_server = new HttpServer();
+ m_server.addListener(
+ new NetworkListener("depurate", config.host,
config.port));
+
+ ServerConfiguration serverConf =
m_server.getServerConfiguration();
+ serverConf.addHttpHandler(new DepurateHandler(config),
"/depurate");
+ serverConf.setDefaultErrorPageGenerator(new
DepurateErrorPageGenerator());
+ serverConf.setName("depurate");
+ m_server.start();
+ }
+
+ public void stop() throws Exception {
+ m_logger.info("Stopping");
+ if (m_server != null) {
+ m_server.shutdownNow();
+ }
+ }
+
+ public void destroy() {
+ }
+}
diff --git
a/src/main/java/org/wikimedia/html5depurate/DepurateErrorPageGenerator.java
b/src/main/java/org/wikimedia/html5depurate/DepurateErrorPageGenerator.java
new file mode 100644
index 0000000..280cbf5
--- /dev/null
+++ b/src/main/java/org/wikimedia/html5depurate/DepurateErrorPageGenerator.java
@@ -0,0 +1,27 @@
+package org.wikimedia.html5depurate;
+
+import org.glassfish.grizzly.http.server.ErrorPageGenerator;
+import org.glassfish.grizzly.http.server.DefaultErrorPageGenerator;
+import org.glassfish.grizzly.http.server.Request;
+import org.glassfish.grizzly.http.util.HttpStatus;
+
+public class DepurateErrorPageGenerator implements ErrorPageGenerator {
+ DefaultErrorPageGenerator def = new DefaultErrorPageGenerator();
+
+ @Override
+ public String generate(final Request request,
+ final int status, final String reasonPhrase,
+ final String description, final Throwable exception)
+ {
+ String realReasonPhrase;
+ if (reasonPhrase.equals(description)) {
+ realReasonPhrase =
HttpStatus.getHttpStatus(status).getReasonPhrase();
+ } else {
+ realReasonPhrase = reasonPhrase;
+ }
+ return def.generate(request, status,
+ "\n" + realReasonPhrase + "\n",
+ "\n" + description + "\n",
+ exception);
+ }
+}
diff --git a/src/main/java/org/wikimedia/html5depurate/DepurateHandler.java
b/src/main/java/org/wikimedia/html5depurate/DepurateHandler.java
new file mode 100644
index 0000000..ea5262b
--- /dev/null
+++ b/src/main/java/org/wikimedia/html5depurate/DepurateHandler.java
@@ -0,0 +1,116 @@
+package org.wikimedia.html5depurate;
+
+import org.wikimedia.html5depurate.Config;
+import org.wikimedia.html5depurate.MultipartBuffer;
+import org.wikimedia.html5depurate.Depurator;
+
+import org.glassfish.grizzly.http.multipart.MultipartScanner;
+import org.glassfish.grizzly.http.server.HttpHandler;
+import org.glassfish.grizzly.http.server.Request;
+import org.glassfish.grizzly.http.server.Response;
+import org.glassfish.grizzly.http.util.HttpStatus;
+import org.glassfish.grizzly.EmptyCompletionHandler;
+
+import java.io.InputStream;
+import java.io.IOException;
+import java.io.ByteArrayInputStream;
+import java.io.StringReader;
+import java.util.logging.Logger;
+import java.util.logging.Level;
+import org.xml.sax.InputSource;
+import org.xml.sax.SAXException;
+
+class DepurateHandler extends HttpHandler {
+ final private Config m_config;
+ Logger m_logger = Logger.getLogger(this.getClass().getName());
+
+ DepurateHandler(Config config) {
+ super("depurate");
+ m_config = config;
+ }
+
+ @Override
+ public void service(final Request request, final Response response)
+ throws Exception
+ {
+ response.suspend();
+ request.setCharacterEncoding("UTF-8");
+ final MultipartBuffer buf = new
MultipartBuffer(m_config.maxPostSize);
+
+ MultipartScanner.scan(request,
+ buf,
+ new EmptyCompletionHandler<Request>() {
+ @Override
+ public void completed(final Request request) {
+ depurate(request, response, buf);
+ response.resume();
+ }
+
+ @Override
+ public void failed(Throwable throwable) {
+ depurate(request, response, buf);
+ response.resume();
+ }
+ }
+ );
+ }
+
+ private void depurate(
+ final Request request, Response response,
MultipartBuffer multi)
+ {
+ try {
+ if (multi.isTooBig()) {
+ sendError(response, 400, "The POST size was too
large");
+ return;
+ }
+ String text = request.getParameter("text");
+ InputSource source = null;
+ if (text != null) {
+ StringReader sr = new StringReader(text);
+ source = new InputSource(sr);
+ m_logger.log(Level.INFO, "Depurating {0} chars
of URL input",
+ text.length());
+ } else {
+ byte[] textBytes = multi.getParameter("text");
+ if (textBytes != null) {
+ m_logger.log(Level.INFO,
+ "Depurating {0} bytes
of multipart input",
+ textBytes.length);
+ InputStream stream = new
ByteArrayInputStream(textBytes);
+ source = new InputSource(stream);
+ source.setEncoding("UTF-8");
+ }
+ }
+ if (source == null) {
+ sendError(response, 400, "The text parameter
must be given");
+ return;
+ }
+
+ byte[] outputBytes;
+ try {
+ outputBytes = Depurator.depurate(source);
+ } catch (SAXException e) {
+ m_logger.info("Error running depurator");
+ sendError(response, 500, "Error parsing HTML: "
+ e.toString());
+ return;
+ }
+
+ response.setContentType("text/html;charset=UTF-8");
+ response.setContentLength(outputBytes.length);
+ response.setBufferSize(outputBytes.length);
+ response.getOutputStream().write(outputBytes);
+ } catch (IOException e) {
+ m_logger.warning("Got IOException: " + e.toString());
+ sendError(response, 500, "Got IOException: " +
e.toString());
+ }
+ }
+
+ private void sendError(Response response, int code, String message) {
+ response.getResponse().setAllowCustomReasonPhrase(false);
+ try {
+ response.sendError(code, message);
+ } catch (IOException e) {
+ m_logger.warning("Got IOException while sending error:
" + e.toString());
+ }
+ }
+}
diff --git a/src/main/java/org/wikimedia/html5depurate/Depurator.java
b/src/main/java/org/wikimedia/html5depurate/Depurator.java
new file mode 100644
index 0000000..644d242
--- /dev/null
+++ b/src/main/java/org/wikimedia/html5depurate/Depurator.java
@@ -0,0 +1,27 @@
+package org.wikimedia.html5depurate;
+
+import nu.validator.htmlparser.common.XmlViolationPolicy;
+import nu.validator.htmlparser.sax.HtmlParser;
+import nu.validator.htmlparser.sax.HtmlSerializer;
+
+import java.io.ByteArrayOutputStream;
+import java.io.IOException;
+import org.xml.sax.InputSource;
+import org.xml.sax.SAXException;
+import org.xml.sax.ContentHandler;
+
+
+class Depurator {
+ public static byte[] depurate(InputSource source)
+ throws SAXException, IOException
+ {
+ ByteArrayOutputStream sink = new ByteArrayOutputStream();
+ ContentHandler serializer = new HtmlSerializer(sink);
+ HtmlParser parser = new HtmlParser(XmlViolationPolicy.ALLOW);
+ parser.setContentHandler(serializer);
+
parser.setProperty("http://xml.org/sax/properties/lexical-handler";,
+ serializer);
+ parser.parse(source);
+ return sink.toByteArray();
+ }
+}
diff --git a/src/main/java/org/wikimedia/html5depurate/MultipartBuffer.java
b/src/main/java/org/wikimedia/html5depurate/MultipartBuffer.java
new file mode 100644
index 0000000..4fadc53
--- /dev/null
+++ b/src/main/java/org/wikimedia/html5depurate/MultipartBuffer.java
@@ -0,0 +1,106 @@
+package org.wikimedia.html5depurate;
+
+import org.glassfish.grizzly.Buffer;
+import org.glassfish.grizzly.ReadHandler;
+import org.glassfish.grizzly.http.io.NIOInputStream;
+import org.glassfish.grizzly.http.multipart.MultipartEntryHandler;
+import org.glassfish.grizzly.http.multipart.MultipartEntry;
+import org.glassfish.grizzly.http.multipart.ContentDisposition;
+import org.glassfish.grizzly.http.multipart.MultipartEntry;
+
+import java.io.ByteArrayOutputStream;
+import java.util.HashMap;
+
+class MultipartBuffer implements MultipartEntryHandler {
+ private HashMap<String, byte[]> m_params;
+ private int m_size;
+ private int m_maxSize;
+ private NIOInputStream m_stream;
+ private boolean m_tooBig;
+
+ private class MultipartBufferReadHandler implements ReadHandler {
+ private String m_name;
+ private ByteArrayOutputStream m_largeBuffer = new
ByteArrayOutputStream();
+ private byte[] m_smallBuffer = new byte[8192];
+
+ private MultipartBufferReadHandler(NIOInputStream stream,
String name) {
+ m_stream = stream;
+ m_name = name;
+ }
+
+ @Override
+ public void onDataAvailable() throws Exception {
+ readAndSaveAvail();
+ m_stream.notifyAvailable(this);
+ }
+
+ @Override
+ public void onAllDataRead() throws Exception {
+ readAndSaveAvail();
+ finish();
+ }
+
+ @Override
+ public void onError(Throwable t) {
+ finish();
+ }
+
+ private void readAndSaveAvail() throws Exception {
+ while (m_stream.isReady()) {
+ int bytesRead = m_stream.read(m_smallBuffer);
+ if (incrementSize(bytesRead)) {
+ m_largeBuffer.write(m_smallBuffer, 0,
bytesRead);
+ }
+ }
+ }
+
+ private void finish() {
+ m_params.put(m_name, m_largeBuffer.toByteArray());
+ }
+ }
+
+ public MultipartBuffer(int maxSize) {
+ m_params = new HashMap<String, byte[]>();
+ m_size = 0;
+ m_maxSize = maxSize;
+ }
+
+ @Override
+ public void handle(MultipartEntry entry) throws Exception {
+ ContentDisposition disposition = entry.getContentDisposition();
+ String name = disposition.getDispositionParamUnquoted("name");
+ if (isTooBig()) {
+ entry.skip();
+ } else if (name != null) {
+ NIOInputStream stream = entry.getNIOInputStream();
+ MultipartBufferReadHandler rh = new
MultipartBufferReadHandler(
+ stream, name);
+ stream.notifyAvailable(rh);
+ } else {
+ entry.skip();
+ }
+ }
+
+ private boolean incrementSize(int size) throws Exception {
+ if (m_tooBig) {
+ return false;
+ } else if (m_size >= m_maxSize - size) {
+ m_tooBig = true;
+ return false;
+ } else {
+ m_size += size;
+ return true;
+ }
+ }
+
+ public byte[] getParameter(String key) throws RuntimeException {
+ if (m_tooBig) {
+ throw new RuntimeException("Maximum POST size
exceeded");
+ }
+ return m_params.get(key);
+ }
+
+ public boolean isTooBig() {
+ return m_tooBig;
+ }
+}
diff --git a/src/org/wikimedia/html5tidy/HTML5Tidy.java
b/src/webapp/org/wikimedia/html5depurate/DepurateServlet.java
similarity index 66%
rename from src/org/wikimedia/html5tidy/HTML5Tidy.java
rename to src/webapp/org/wikimedia/html5depurate/DepurateServlet.java
index 93b8efe..92b3bb7 100644
--- a/src/org/wikimedia/html5tidy/HTML5Tidy.java
+++ b/src/webapp/org/wikimedia/html5depurate/DepurateServlet.java
@@ -1,8 +1,7 @@
/*
* License: http://creativecommons.org/publicdomain/zero/1.0/
*/
-
-package org.wikimedia.html5tidy;
+package org.wikimedia.html5depurate;
import javax.servlet.http.HttpServlet;
import javax.servlet.http.HttpServletRequest;
@@ -18,21 +17,15 @@
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
-import java.util.Enumeration;
-
import java.nio.charset.Charset;
-import org.xml.sax.ContentHandler;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import nu.validator.encoding.Encoding;
-import nu.validator.htmlparser.common.XmlViolationPolicy;
-import nu.validator.htmlparser.sax.HtmlParser;
-import nu.validator.htmlparser.sax.HtmlSerializer;
@MultipartConfig()
-public class HTML5Tidy extends HttpServlet {
+public class DepurateServlet extends HttpServlet {
public void doPost(HttpServletRequest req, HttpServletResponse res)
throws ServletException, IOException
{
@@ -63,24 +56,18 @@
return;
}
- // Set up the parser and run it
- ByteArrayOutputStream sink = new ByteArrayOutputStream();
- ContentHandler serializer = new HtmlSerializer(sink);
- HtmlParser parser = new HtmlParser(XmlViolationPolicy.ALLOW);
- parser.setContentHandler(serializer);
+ InputSource source = new InputSource(stream);
+ source.setEncoding("UTF-8");
+ byte[] outputBytes;
try {
-
parser.setProperty("http://xml.org/sax/properties/lexical-handler";,
- serializer);
- InputSource source = new InputSource(stream);
- source.setEncoding("UTF-8");
- parser.parse(source);
+ outputBytes = Depurator.depurate(source);
} catch (SAXException e) {
throw new ServletException("Error parsing HTML", e);
}
// HtmlSerializer writes UTF-8 by default
res.setContentType("text/html;charset=UTF-8");
-
- res.getOutputStream().write(sink.toByteArray());
+ res.setContentLength(outputBytes.length);
+ res.getOutputStream().write(outputBytes);
}
};
--
To view, visit https://gerrit.wikimedia.org/r/232444
To unsubscribe, visit https://gerrit.wikimedia.org/r/settings
Gerrit-MessageType: merged
Gerrit-Change-Id: Ifb1e01191b9975a97897eb8a84d61a5b60b3dc26
Gerrit-PatchSet: 1
Gerrit-Project: mediawiki/services/html5depurate
Gerrit-Branch: master
Gerrit-Owner: Tim Starling <tstarl...@wikimedia.org>
Gerrit-Reviewer: Tim Starling <tstarl...@wikimedia.org>
_______________________________________________
MediaWiki-commits mailing list
MediaWiki-commits@lists.wikimedia.org
https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits
