tag.java

java写的crawler

/*
 * WebSphinx web-crawling toolkit
 *
 * Copyright (c) 1998-2002 Carnegie Mellon University.  All rights
 * reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY CARNEGIE MELLON UNIVERSITY ``AS IS'' AND
 * ANY EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
 * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
 * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL CARNEGIE MELLON UNIVERSITY
 * NOR ITS EMPLOYEES BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 */

package websphinx;

import java.util.Enumeration;
import rcm.enum.ArrayEnumeration;

/**
 * Tag in an HTML page.
 */
public class Tag extends Region {

    String tagName;
    boolean startTag;
    String[] htmlAttributes;// HTML attributes on this tag (lower case and interned)
    Element element;

    /**
     * Make a Tag.
     * @param page Page containing tag
     * @param start Starting offset of tag in page
     * @param end Ending offset of tag
     * @param tagName Name of tag (like "p")
     * @param startTag true for start tags (like "<p>"), false for end tags ("</p>")
     */
    public Tag (Page page, int start, int end, String tagName, boolean startTag) {
        super (page, start, end);
        this.tagName = tagName.toLowerCase ().intern ();
        this.startTag = startTag;
        this.htmlAttributes = null;
    }

    /**
     * Get tag name.
     * @return tag name (like "p"), in lower-case, String.intern()'ed form.
     */
    public String getTagName () {
        return tagName;
    }

    /**
     * Get element to which this tag is the start or end tag.
     * @return element, or null if tag has no element.
     */
    public Element getElement () {
        return element;
    }

    /**
     * Convert a String to a tag name.  Tag names are lower-case, intern()'ed
     * Strings.  Thus you can compare tag names with ==, as in: 
     * <CODE>getTagName() == Tag.IMG</CODE>.
     * @param name Name to convert (e.g., "P")
     * @return tag name (e.g. "p"), in lower-case, String.intern()'ed form.
     */
    public static String toTagName (String name) {
        return name.toLowerCase().intern ();
    }

    /**
     * Test if tag is a start tag.  Equivalent to !isEndTag().
     * @return true if and only if tag is a start tag (like "&lt;P&gt;")
     */
    public boolean isStartTag () {
        return startTag;
    }

    /**
     * Test if tag is an end tag.  Equivalent to !isStartTag().
     * @return true if and only if tag is a start tag (like "&lt;/P&gt;")
     */
    public boolean isEndTag () {
        return !startTag;
    }

    /**
     * Test if tag is a block-level tag.  Equivalent to !isFlowTag().
     * @return true if and only if tag is a block-level tag (like "&lt;P&gt;")
     */
    public boolean isBlockTag () {
        return HTMLParser.blocktag.containsKey (tagName);
    }

    /**
     * Test if tag is a flow-level tag.  Equivalent to !isBlockTag().
     * @return true if and only if tag is a block-level tag (like "&lt;A&gt;")
     */
    public boolean isFlowTag () {
        return !isBlockTag ();
    }

    /**
     * Test if tag belongs in the <HEAD> element.
     * @return true if and only if tag is a HEAD-level tag (like "&lt;TITLE&gt;")
     */
    public boolean isHeadTag () {
        return HTMLParser.headtag.containsKey (tagName);
    }

    /**
     * Test if tag belongs in the <BODY> element.
     * @return true if and only if tag is a BODY-level tag (like "&lt;A&gt;")
     */
    public boolean isBodyTag () {
        return !isHeadTag() 
                && tagName != HTML 
                && tagName != HEAD 
                && tagName != BODY;
    }

    /**
     * Convert a String to an HTML attribute name.  Attribute names are
     * lower-case, intern()'ed
     * Strings.  Thus you can compare attribute names with ==.
     * @param name Name to convert (e.g., "HREF")
     * @return tag name (e.g. "href"), in lower-case, String.intern()'ed form.
     */
    public static String toHTMLAttributeName (String name) {
        return name.toLowerCase ().intern ();
    }

    /**
     * Test if tag has an HTML attribute.
     * @param name Name of HTML attribute (e.g. "HREF").  Doesn't have to be
     * converted with toHTMLAttributeName(). 
     * @return true if tag has the attribute, false if not
     */
    public boolean hasHTMLAttribute (String name) {
        if (htmlAttributes == null)
            return false;
        name = toHTMLAttributeName (name);
        for (int i=0; i<htmlAttributes.length; ++i)
            if (htmlAttributes[i] == name)
                return true;
        return false;
    }

    /**
     * Get an HTML attribute's value.
     * @param name Name of HTML attribute (e.g. "HREF").  Doesn't have to be
     * converted with toHTMLAttributeName(). 
     * @return value of attribute if it exists, TRUE if the attribute exists but has no value, or null if tag lacks the attribute.
     */
    public String getHTMLAttribute (String name) {
        if (htmlAttributes == null)
            return null;
        name = toHTMLAttributeName (name);
        for (int i=0; i<htmlAttributes.length; ++i)
            if (htmlAttributes[i] == name)
                return getLabel (name);
        return null;
    }

    /**
     * Get an HTML attribute's value, with a default value if it doesn't exist.
     * @param name Name of HTML attribute (e.g. "HREF").  Doesn't have to be
     * converted with toHTMLAttributeName(). 
     * @param defaultValue default value to return if the attribute 
     * doesn't exist
     * @return value of attribute if it exists, TRUE if the attribute exists but has no value, or defaultValue if tag lacks the attribute.
     */
    public String getHTMLAttribute (String name, String defaultValue) {
        String val = getHTMLAttribute (name);
        return val != null ? val : defaultValue;
    }
    
    /**
     * Get number of HTML attributes on this tag.
     * @return number of HTML attributes
     */
    public int countHTMLAttributes () {
        return htmlAttributes != null ? htmlAttributes.length : 0;
    }

    /**
     * Get all the HTML attributes found on this tag.
     * @return array of name-value pairs, alternating between 
     * names and values.  Thus array[0] is a name, array[1] is a value,
     * array[2] is a name, etc.
     */
    public String[] getHTMLAttributes () {
        if (htmlAttributes == null)
            return new String[0];

        String[] result = new String[htmlAttributes.length * 2];
        for (int i=0, j=0; i<htmlAttributes.length; ++i) {
            String name = htmlAttributes[i];
            result[j++] = name;
            result[j++] = getLabel (name);
        }
        return result;
    }

    /**