Cache


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   * Represents a cached map of character positions to tags.
27   * The allTagTypesSubCache object is used to cache all tags.
28   * Additional subcaches are used to cache single tag types, which increases the performance when searching for those tag types.
29   * A list of tag types to be cached separately is specified in the SeparatelyCachedTagTypes property.
30   * The standard implementation caches only COMMENT tag types separately, as these tag types are searched extensively
31   * in the process of ensuring that every non-server tag is not located inside a comment.
32   */
33  final class Cache {
34      public final Source source;
35      private final SubCache allTagTypesSubCache;
36      private final SubCache[] subCaches; // contains allTagTypesSubCache plus a SubCache object for each separately cached tag type
37  
38      public Cache(final Source source) {
39          this.source=source;
40          allTagTypesSubCache=new SubCache(this,null);
41          TagType[] separatelyCachedTagTypes=getSeparatelyCachedTagTypes();
42          subCaches=new SubCache[separatelyCachedTagTypes.length+1];
43          subCaches[0]=allTagTypesSubCache;
44          for (int i=0; i<separatelyCachedTagTypes.length; i++)
45              subCaches[i+1]=new SubCache(this,separatelyCachedTagTypes[i]);
46      }
47  
48      public void clear() {
49          for (int i=0; i<subCaches.length; i++) subCaches[i].clear();
50      }
51  
52      public Tag getTagAt(final int pos) {
53          return source.useAllTypesCache
54              ?   allTagTypesSubCache.getTagAt(pos)
55              : Tag.getTagAtUncached(source,pos);
56      }
57  
58      public Tag findPreviousOrNextTag(final int pos, final boolean previous) {
59          // returns null if pos is out of range.
60          return allTagTypesSubCache.findPreviousOrNextTag(pos,previous);
61      }
62  
63      public Tag findPreviousOrNextTag(final int pos, final TagType tagType, final boolean previous) {
64          // returns null if pos is out of range.
65          for (int i=source.useAllTypesCache ? 0 : 1; i<subCaches.length; i++)
66              if (tagType==subCaches[i].tagType) return subCaches[i].findPreviousOrNextTag(pos,previous);
67          return Tag.findPreviousOrNextTagUncached(source,pos,tagType,previous,ParseText.NO_BREAK);
68      }
69  
70      public Tag addTagAt(final int pos) {
71          final Tag tag=Tag.getTagAtUncached(source,pos);
72          allTagTypesSubCache.addTagAt(pos,tag);
73          if (tag==null) return tag;
74          final TagType tagType=tag.getTagType();
75          for (int i=1; i<subCaches.length; i++) {
76              if (tagType==subCaches[i].tagType) {
77                  subCaches[i].addTagAt(pos,tag);
78                  return tag;
79              }
80          }
81          return tag;
82      }
83  
84      public int getTagCount() {
85          return allTagTypesSubCache.size()-2;
86      }
87  
88      public Iterator getTagIterator() {
89          return allTagTypesSubCache.getTagIterator();
90      }
91  
92      public void loadAllTags(final List tags, final Tag[] allRegisteredTags, final StartTag[] allRegisteredStartTags) {
93          // assumes the tags list implements RandomAccess
94          final int tagCount=tags.size();
95          allTagTypesSubCache.bulkLoad_Init(tagCount);
96          int registeredTagIndex=0;
97          int registeredStartTagIndex=0;
98          for (int i=0; i<tagCount; i++) {
99              Tag tag=(Tag)tags.get(i);
100             if (!tag.isUnregistered()) {
101                 allRegisteredTags[registeredTagIndex++]=tag;
102                 if (tag instanceof StartTag) allRegisteredStartTags[registeredStartTagIndex++]=(StartTag)tag;
103             }
104             allTagTypesSubCache.bulkLoad_Set(i,tag);
105             for (int x=1; x<subCaches.length; x++) {
106                 if (tag.getTagType()==subCaches[x].tagType) {
107                     subCaches[x].bulkLoad_AddToTypeSpecificCache(tag);
108                     break;
109                 }
110             }
111         }
112         for (int x=1; x<subCaches.length; x++)
113             subCaches[x].bulkLoad_FinaliseTypeSpecificCache();
114     }
115 
116     public String   toString() {
117         StringBuffer   sb=new StringBuffer  ();
118         for (int i=0; i<subCaches.length; i++) subCaches[i].appendTo(sb);
119         return sb.toString();
120     }
121 
122     protected int getSourceLength() {
123         return source.end;
124     }
125     
126     private static TagType[] getSeparatelyCachedTagTypes() {
127         return TagType.getTagTypesIgnoringEnclosedMarkup();
128     }
129 }
130
A to Z: JavaDoc & Examples Daily Java News & Articles Open Source Projects Open Source Codes Free Computer Books Remove Frame
Popular Tags