First checkin (56bd6d72) · Commits · REDMIC Project / Third party / Sitemapgen4j

TODO.txt

0 → 100644

+18 −0

Original line number	Diff line number	Diff line

		Ping search engines

		Text file reader
		Sitemap reader

		Improve validator for basic sitemap case (gzip, 10MB, urls, encoding)
		validate Mobile/Geo/Video/Code/News sitemaps


		JS api
		addUrl({url:"http://www.example.com",lastMod:"2007-08-01");
		new WebSitemapGenerator({});
		new SitemapIndexGenerator({});

		Google KML generation
		GeoRSS generation
		Google Code packagemap http://www.google.com/help/codesearch_packagemap.html

pom.xml

0 → 100644

+34 −0

Original line number	Diff line number	Diff line
		<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>com.redfin</groupId>
		<artifactId>sitemapgen4j</artifactId>
		<packaging>jar</packaging>
		<version>1.0-SNAPSHOT</version>
		<name>SitemapGen4J</name>
		<build>
		<defaultGoal>install</defaultGoal>
		<plugins>
		<plugin>
		<artifactId>maven-compiler-plugin</artifactId>
		<configuration>
		<source>1.5</source>
		<target>1.5</target>
		</configuration>
		</plugin>
		<plugin>
		<groupId>org.apache.maven.plugins</groupId>
		<artifactId>maven-eclipse-plugin</artifactId>
		<version>2.5.1</version>
		</plugin>
		</plugins>
		</build>
		<dependencies>
		<dependency>
		<groupId>junit</groupId>
		<artifactId>junit</artifactId>
		<version>3.8.1</version>
		<scope>test</scope>
		</dependency>
		</dependencies>
		</project>

src/main/java/com/redfin/sitemapgenerator/AbstractSitemapGeneratorOptions.java

0 → 100644

+69 −0

Original line number	Diff line number	Diff line
		package com.redfin.sitemapgenerator;

		import java.io.File;
		import java.net.URL;

		// that weird thing with generics is so sub-classed objects will return themselves
		// It makes sense, I swear! http://madbean.com/2004/mb2004-3/
		abstract class AbstractSitemapGeneratorOptions<THIS extends AbstractSitemapGeneratorOptions<THIS>> {
		File baseDir;
		String baseUrl;
		String fileNamePrefix = "sitemap";
		boolean allowMultipleSitemaps = true;
		W3CDateFormat dateFormat;
		int maxUrls = SitemapGenerator.MAX_URLS_PER_SITEMAP;
		boolean autoValidate = false;
		boolean gzip = false;

		public AbstractSitemapGeneratorOptions(URL baseUrl, File baseDir) {
		if (baseDir == null) throw new NullPointerException("baseDir may not be null");
		if (baseUrl == null) throw new NullPointerException("baseUrl may not be null");
		this.baseDir = baseDir;
		this.baseUrl = baseUrl.toString();
		}

		/** The prefix of the name of the sitemaps we'll create; by default this is "sitemap" */
		public THIS fileNamePrefix(String fileNamePrefix) {
		if (fileNamePrefix == null) throw new NullPointerException("fileNamePrefix may not be null");
		this.fileNamePrefix = fileNamePrefix;
		return getThis();
		}
		/** When more than the maximum number of URLs are passed in, should we split into multiple sitemaps automatically, or just throw an exception? */
		public THIS allowMultipleSitemaps(boolean allowMultipleSitemaps) {
		this.allowMultipleSitemaps = allowMultipleSitemaps;
		return getThis();
		}
		/** The date formatter, typically configured with a {@link W3CDateFormat.Pattern} and/or a time zone */
		public THIS dateFormat(W3CDateFormat dateFormat) {
		this.dateFormat = dateFormat;
		return getThis();
		}
		/**
		* The maximum number of URLs to allow per sitemap; the default is the
		* maximum allowed (50,000), but you can decrease it if you wish (to make
		* your auto-generated sitemaps smaller)
		*/
		public THIS maxUrls(int maxUrls) {
		if (maxUrls > SitemapGenerator.MAX_URLS_PER_SITEMAP) {
		throw new RuntimeException("You can only have 50,000 URLs per sitemap; to use more, allowMultipleSitemaps and generate a sitemap index. You asked for " + maxUrls);
		}
		this.maxUrls = maxUrls;
		return getThis();
		}
		/**
		* Validate the sitemaps automatically after writing them; this takes time (and may fail for Google-specific sitemaps)
		*/
		public THIS autoValidate(boolean autoValidate) {
		this.autoValidate = autoValidate;
		return getThis();
		}
		/** Gzip the sitemaps after they are written to disk */
		THIS gzip(boolean gzip) {
		this.gzip = gzip;
		return getThis();
		}
		@SuppressWarnings("unchecked")
		public THIS getThis() {
		return (THIS)this;
		}
		}
		No newline at end of file

src/main/java/com/redfin/sitemapgenerator/AbstractSitemapUrlOptions.java

0 → 100644

+112 −0

Original line number	Diff line number	Diff line
		package com.redfin.sitemapgenerator;

		import java.net.MalformedURLException;
		import java.net.URL;
		import java.text.ParseException;
		import java.util.Date;

		/** Container for optional URL parameters */
		//that weird thing with generics is so sub-classed objects will return themselves
		//It makes sense, I swear! http://madbean.com/2004/mb2004-3/
		abstract class AbstractSitemapUrlOptions<U extends WebSitemapUrl, THIS extends AbstractSitemapUrlOptions<U,THIS>> {
		Date lastMod;
		ChangeFreq changeFreq;
		Double priority;
		URL url;
		Class<U> clazz;

		public AbstractSitemapUrlOptions(String url, Class<U> clazz) throws MalformedURLException {
		this(new URL(url), clazz);
		}

		public AbstractSitemapUrlOptions(URL url, Class<U> clazz) {
		if (url == null) throw new NullPointerException("URL may not be null");
		this.url = url;
		this.clazz = clazz;
		}

		/**
		* The date of last modification of the file. Note that this tag is
		* separate from the If-Modified-Since (304) header the server can
		* return, and search engines may use the information from both sources
		* differently.
		*/
		public THIS lastMod(Date lastMod) {
		this.lastMod = lastMod;
		return getThis();
		}

		/**
		* The date of last modification of the file. Note that this tag is
		* separate from the If-Modified-Since (304) header the server can
		* return, and search engines may use the information from both sources
		* differently.
		* @throws ParseException if the string isn't a valid W3C date time
		* @see W3CDateFormat
		*/
		public THIS lastMod(String lastMod) throws ParseException {
		this.lastMod = new W3CDateFormat().parse(lastMod);
		return getThis();
		}

		/**
		* How frequently the page is likely to change. This value provides
		* general information to search engines and may not correlate exactly
		* to how often they crawl the page. The value {@link ChangeFreq#ALWAYS} should be used to
		* describe documents that change each time they are accessed. The value
		* {@link ChangeFreq#NEVER} should be used to describe archived URLs.
		*
		* <p>Please note that the
		* value of this tag is considered a <em>hint</em> and not a command. Even though
		* search engine crawlers may consider this information when making
		* decisions, they may crawl pages marked {@link ChangeFreq#HOURLY} less frequently than
		* that, and they may crawl pages marked {@link ChangeFreq#YEARLY} more frequently than
		* that. Crawlers may periodically crawl pages marked {@link ChangeFreq#NEVER} so that
		* they can handle unexpected changes to those pages.</p>
		*/
		public THIS changeFreq(ChangeFreq changeFreq) {
		this.changeFreq = changeFreq;
		return getThis();
		}

		/**
		* <p>The priority of this URL relative to other URLs on your site. Valid
		* values range from 0.0 to 1.0. This value does not affect how your
		* pages are compared to pages on other sites—it only lets the search
		* engines know which pages you deem most important for the crawlers.</p>
		*
		* <p>The default priority of a page is 0.5.</p>
		*
		* <p>Please note that the priority you assign to a page is not likely to
		* influence the position of your URLs in a search engine's result
		* pages. Search engines may use this information when selecting between
		* URLs on the same site, so you can use this tag to increase the
		* likelihood that your most important pages are present in a search
		* index.</p>
		*
		* <p>Also, please note that assigning a high priority to all of the URLs
		* on your site is not likely to help you. Since the priority is
		* relative, it is only used to select between URLs on your site.</p>
		*/
		public THIS priority(Double priority) {
		if (priority > 1.0) throw new IllegalArgumentException("Priority may not be greater than 1.0: " + priority);
		if (priority < 0) throw new IllegalArgumentException("Priority may not be less than 0: " + priority);
		this.priority = priority;
		return getThis();
		}

		@SuppressWarnings("unchecked")
		THIS getThis() {
		return (THIS)this;
		}

		/** Return an URL based on these settings */
		public U build() {
		try {
		return clazz.getConstructor(getClass()).newInstance(this);
		} catch (Exception e) {
		throw new RuntimeException(e);
		}
		}

		}
		No newline at end of file

src/main/java/com/redfin/sitemapgenerator/AbstractSitemapUrlRenderer.java

0 → 100644

+48 −0

Original line number	Diff line number	Diff line
		package com.redfin.sitemapgenerator;

		import java.io.IOException;
		import java.io.OutputStreamWriter;

		abstract class AbstractSitemapUrlRenderer<T extends WebSitemapUrl> implements ISitemapUrlRenderer<T> {

		public void render(WebSitemapUrl url, OutputStreamWriter out, W3CDateFormat dateFormat, String additionalData)
		throws IOException {
		out.write(" <url>\n");
		out.write(" <loc>");
		out.write(url.getUrl().toString());
		out.write("</loc>\n");
		if (url.getLastMod() != null) {
		out.write(" <lastmod>");
		out.write(dateFormat.format(url.getLastMod()));
		out.write("</lastmod>\n");
		}
		if (url.getChangeFreq() != null) {
		out.write(" <changefreq>");
		out.write(url.getChangeFreq().toString());
		out.write("</changefreq>\n");
		}
		if (url.getPriority() != null) {
		out.write(" <priority>");
		out.write(url.getPriority().toString());
		out.write("</priority>\n");
		}
		if (additionalData != null) out.write(additionalData);
		out.write(" </url>\n");
		}

		public void renderTag(StringBuilder sb, String namespace, String tagName, Object value) {
		if (value == null) return;
		sb.append(" <");
		sb.append(namespace);
		sb.append(':');
		sb.append(tagName);
		sb.append('>');
		sb.append(value);
		sb.append("</");
		sb.append(namespace);
		sb.append(':');
		sb.append(tagName);
		sb.append(">\n");
		}

		}