KickJava   Java API By Example, From Geeks To Geeks.

Java > Open Source Codes > au > id > jericho > lib > html > StartTagTypeGenericImplementation


1 // Jericho HTML Parser - Java based library for analysing and manipulating HTML
2 // Version 2.2
3 // Copyright (C) 2006 Martin Jericho
4 // http://sourceforge.net/projects/jerichohtml/
5 //
6 // This library is free software; you can redistribute it and/or
7 // modify it under the terms of the GNU Lesser General Public
8 // License as published by the Free Software Foundation; either
9 // version 2.1 of the License, or (at your option) any later version.
10 // http://www.gnu.org/copyleft/lesser.html
11 //
12 // This library is distributed in the hope that it will be useful,
13 // but WITHOUT ANY WARRANTY; without even the implied warranty of
14 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
15 // Lesser General Public License for more details.
16 //
17 // You should have received a copy of the GNU Lesser General Public
18 // License along with this library; if not, write to the Free Software
19 // Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
20
21 package au.id.jericho.lib.html;
22
23 import java.util.*;
24
25 /**
26  * Provides a generic implementation of the abstract {@link StartTagType} class based on the most common start tag behaviour.
27  * <p>
28  * This class is only of interest to users who wish to create <a HREF="TagType.html#Custom">custom tag types</a>.
29  * <p>
30  * The only external difference between this class and its abstract superclass {@link StartTagType} is that it provides a default
31  * implementation of the {@link #constructTagAt(Source, int pos)} method.
32  * <p>
33  * Most of the <a HREF="Tag.html#Predefined">predefined</a> start tag types are implemented using this class or a subclass of it.
34  *
35  * @see EndTagTypeGenericImplementation
36  */
37 public class StartTagTypeGenericImplementation extends StartTagType {
38     final boolean nameCharAfterPrefixAllowed;
39
40     /**
41      * Constructs a new <code>StartTagTypeGenericImplementation</code> object with the specified properties.
42      * <br />(<a HREF="TagType.html#ImplementationAssistance">implementation assistance</a> method)
43      * <p>
44      * This is equivalent to calling
45      * <br /><code>new&nbsp;</code>{@link #StartTagTypeGenericImplementation(String,String,String,EndTagType,boolean,boolean,boolean) StartTagTypeGenericImplementation}<code>(description,startDelimiter,closingDelimiter,correspondingEndTagType,isServerTag,false,false)</code>.
46      *
47      * @param description a {@linkplain #getDescription() description} of the new start tag type useful for debugging purposes.
48      * @param startDelimiter the {@linkplain #getStartDelimiter() start delimiter} of the new start tag type.
49      * @param closingDelimiter the {@linkplain #getClosingDelimiter() closing delimiter} of the new start tag type.
50      * @param correspondingEndTagType the {@linkplain #getCorrespondingEndTagType() corresponding end tag type} of the new start tag type.
51      * @param isServerTag indicates whether the new start tag type is a {@linkplain #isServerTag() server tag}.
52      */
53     protected StartTagTypeGenericImplementation(final String JavaDoc description, final String JavaDoc startDelimiter, final String JavaDoc closingDelimiter, final EndTagType correspondingEndTagType, final boolean isServerTag) {
54         this(description,startDelimiter,closingDelimiter,correspondingEndTagType,isServerTag,false,false);
55     }
56
57     /**
58      * Constructs a new <code>StartTagTypeGenericImplementation</code> object with the specified properties.
59      * <br />(<a HREF="TagType.html#ImplementationAssistance">implementation assistance</a> method)
60      *
61      * @param description a {@linkplain #getDescription() description} of the new start tag type useful for debugging purposes.
62      * @param startDelimiter the {@linkplain #getStartDelimiter() start delimiter} of the new start tag type.
63      * @param closingDelimiter the {@linkplain #getClosingDelimiter() closing delimiter} of the new start tag type.
64      * @param correspondingEndTagType the {@linkplain #getCorrespondingEndTagType() corresponding end tag type} of the new start tag type.
65      * @param isServerTag indicates whether the new start tag type is a {@linkplain #isServerTag() server tag}.
66      * @param hasAttributes indicates whether the new start tag type {@linkplain #hasAttributes() has attributes}.
67      * @param isNameAfterPrefixRequired indicates whether a {@linkplain #isNameAfterPrefixRequired() name is required after the prefix}.
68      */
69     protected StartTagTypeGenericImplementation(final String JavaDoc description, final String JavaDoc startDelimiter, final String JavaDoc closingDelimiter, final EndTagType correspondingEndTagType, final boolean isServerTag, final boolean hasAttributes, final boolean isNameAfterPrefixRequired) {
70         super(description,startDelimiter,closingDelimiter,correspondingEndTagType,isServerTag,hasAttributes,isNameAfterPrefixRequired);
71         nameCharAfterPrefixAllowed=(getNamePrefix().length()==0 || !Character.isLetter(getNamePrefix().charAt(getNamePrefix().length()-1)));
72     }
73
74     /**
75      * Constructs a tag of this type at the specified position in the specified source document if it matches all of the required features.
76      * <br />(<a HREF="TagType.html#DefaultImplementation">default implementation</a> method)
77      * <p>
78      * This default implementation performs the following steps:
79      * <ol class="Separated">
80      * <li>
81      * If a {@linkplain #isNameAfterPrefixRequired() name is required after the prefix}, search for a valid
82      * {@linkplain Tag#isXMLName(CharSequence) XML tag name} directly after the
83      * {@linkplain #getNamePrefix() name prefix} using the {@link Source#findNameEnd(int pos)} method.
84      * If one is found, set the {@linkplain Tag#getName() name} to include it, otherwise return <code>null</code>.
85      * <li>
86      * If the last character of the {@linkplain #getNamePrefix() name prefix} is a letter
87      * (indicating that the prefix includes the full {@linkplain Tag#getName() name} of the tag),
88      * and the character following the prefix in the source text is also a letter
89      * or any other valid {@linkplain Tag#isXMLNameChar(char) XML name character},
90      * return <code>null</code>.
91      * <br />Example: the source text "<code>&lt;?xmlt ?&gt;</code>" should not be recognised as an
92      * {@linkplain #XML_PROCESSING_INSTRUCTION XML processing instruction}, which has the prefix "<code>&lt;?xml</code>".
93      * <li>
94      * If the tag type {@linkplain #hasAttributes() has attributes}, call
95      * {@link #parseAttributes(Source,int,String) parseAttributes(source,pos,name)} to parse them.
96      * Return <code>null</code> if too many errors occur while parsing the attributes.
97      * <li>
98      * Find the {@linkplain Tag#getEnd() end} of the tag using the {@link #findEnd(Source, int pos)} method,
99      * where <code>pos</code> is either the end of the {@linkplain StartTag#getAttributes() attributes} segment or the end of the
100      * {@linkplain Tag#getName() name} depending on whether the tag type {@linkplain #hasAttributes() has attributes}.
101      * Return <code>null</code> if the end of the tag can not be found.
102      * <li>
103      * Construct the {@link StartTag} object using the
104      * {@link #constructStartTag(Source,int,int,String,Attributes) constructStartTag(Source, int pos, int end, String name, Attributes)}
105      * method with the argument values collected over the previous steps.
106      * </ol>
107      * <p>
108      * See {@link TagType#constructTagAt(Source, int pos)} for more important information about this method.
109      *
110      * @param source the {@link Source} document.
111      * @param pos the position in the source document.
112      * @return a tag of this type at the specified position in the specified source document if it meets all of the required features, or <code>null</code> if it does not meet the criteria.
113      */
114     protected Tag constructTagAt(final Source source, final int pos) {
115         final ParseText parseText=source.getParseText();
116         final int nameBegin=pos+1;
117         String JavaDoc name=getNamePrefix();
118         int nameEnd=nameBegin+getNamePrefix().length();
119         if (isNameAfterPrefixRequired()) {
120             final int extendedNameEnd=source.findNameEnd(nameEnd);
121             if (extendedNameEnd==-1) return null;
122             name=parseText.substring(nameBegin,extendedNameEnd);
123             nameEnd=extendedNameEnd;
124         } else if (!nameCharAfterPrefixAllowed && Tag.isXMLNameChar(parseText.charAt(nameEnd))) {
125             return null;
126         }
127         int end;
128         Attributes attributes=null;
129         if (hasAttributes()) {
130             // it is necessary to get the attributes so that we can be sure that the search on the closing delimiter doesn't pick up
131 // anything from the attribute values, which can legally contain ">" characters.
132 attributes=parseAttributes(source,pos,name);
133             if (attributes==null) return null; // happens if attributes not properly formed
134 end=findEnd(source,attributes.getEnd()); // should always return a valid end
135 } else {
136             end=findEnd(source,nameEnd);
137             if (end==-1) {
138                 if (source.isLoggingEnabled()) source.log(source.getRowColumnVector(pos).appendTo(new StringBuffer JavaDoc(200).append("StartTag ").append(name).append(" at ")).append(" not recognised as type '").append(getDescription()).append("' because it has no closing delimiter").toString());
139                 return null;
140             }
141         }
142         return constructStartTag(source,pos,end,name,attributes);
143     }
144
145     /**
146      * Finds the {@linkplain Tag#getEnd() end} of a tag of this type, starting from the specified position in the specified source document.
147      * <br />(<a HREF="TagType.html#ImplementationAssistance">implementation assistance</a> method)
148      * <p>
149      * This default implementation simply searches for the first occurrence of the
150      * {@linkplain #getClosingDelimiter() closing delimiter} after the specified position, and returns the position immediately
151      * after the end of it.
152      * <p>
153      * If the closing delimiter is not found, the value <code>-1</code> is returned.
154      *
155      * @param source the {@link Source} document.
156      * @param pos the position in the source document.
157      * @return the {@linkplain Tag#getEnd() end} of a tag of this type, starting from the specified position in the specified source document, or <code>-1</code> if the end of the tag can not be found.
158      */
159     protected int findEnd(final Source source, final int pos) {
160         final int delimiterBegin=source.getParseText().indexOf(getClosingDelimiter(),pos);
161         return (delimiterBegin==-1 ? -1 : delimiterBegin+getClosingDelimiter().length());
162     }
163 }
164
Popular Tags