| 1 |
// Jericho HTML Parser - Java based library for analysing and manipulating HTML
|
| 2 |
// Version 3.2
|
| 3 |
// Copyright (C) 2004-2009 Martin Jericho
|
| 4 |
// http://jericho.htmlparser.net/
|
| 5 |
//
|
| 6 |
// This library is free software; you can redistribute it and/or
|
| 7 |
// modify it under the terms of either one of the following licences:
|
| 8 |
//
|
| 9 |
// 1. The Eclipse Public License (EPL) version 1.0,
|
| 10 |
// included in this distribution in the file licence-epl-1.0.html
|
| 11 |
// or available at http://www.eclipse.org/legal/epl-v10.html
|
| 12 |
//
|
| 13 |
// 2. The GNU Lesser General Public License (LGPL) version 2.1 or later,
|
| 14 |
// included in this distribution in the file licence-lgpl-2.1.txt
|
| 15 |
// or available at http://www.gnu.org/licenses/lgpl.txt
|
| 16 |
//
|
| 17 |
// This library is distributed on an "AS IS" basis,
|
| 18 |
// WITHOUT WARRANTY OF ANY KIND, either express or implied.
|
| 19 |
// See the individual licence texts for more details.
|
| 20 |
|
| 21 |
package net.htmlparser.jericho;
|
| 22 |
|
| 23 |
class CharSequenceParseText implements ParseText {
|
| 24 |
private final CharSequence charSequence;
|
| 25 |
|
| 26 |
CharSequenceParseText(final CharSequence charSequence) {
|
| 27 |
this.charSequence=charSequence;
|
| 28 |
}
|
| 29 |
|
| 30 |
public final char charAt(final int index) {
|
| 31 |
final char ch=charSequence.charAt(index);
|
| 32 |
return (ch>='A' && ch<='Z') ? ((char)(ch ^ 0x20)) : ch;
|
| 33 |
}
|
| 34 |
|
| 35 |
public final boolean containsAt(final String str, final int pos) {
|
| 36 |
for (int i=0; i<str.length(); i++)
|
| 37 |
if (str.charAt(i)!=charAt(pos+i)) return false;
|
| 38 |
return true;
|
| 39 |
}
|
| 40 |
|
| 41 |
public final int indexOf(final char searchChar, final int fromIndex) {
|
| 42 |
return indexOf(searchChar,fromIndex,NO_BREAK);
|
| 43 |
}
|
| 44 |
|
| 45 |
public final int indexOf(final char searchChar, final int fromIndex, final int breakAtIndex) {
|
| 46 |
final int actualBreakAtIndex=(breakAtIndex==NO_BREAK || breakAtIndex>getEnd() ? getEnd() : breakAtIndex);
|
| 47 |
try {
|
| 48 |
for (int i=(fromIndex<0 ? 0 : fromIndex); i<actualBreakAtIndex; i++)
|
| 49 |
if (charAt(i)==searchChar) return i;
|
| 50 |
} catch (IndexOutOfBoundsException ex) {} // only happens in StreamedParseText subclass - this is the normal way to catch end of stream
|
| 51 |
return -1;
|
| 52 |
}
|
| 53 |
|
| 54 |
public final int indexOf(final String searchString, final int fromIndex) {
|
| 55 |
return indexOf(searchString,fromIndex,NO_BREAK);
|
| 56 |
}
|
| 57 |
|
| 58 |
public final int indexOf(final String searchString, final int fromIndex, final int breakAtIndex) {
|
| 59 |
if (searchString.length()==1) return indexOf(searchString.charAt(0),fromIndex,breakAtIndex);
|
| 60 |
if (searchString.length()==0) return fromIndex;
|
| 61 |
final char firstChar=searchString.charAt(0);
|
| 62 |
final int lastPossibleBreakAtIndex=getEnd()-searchString.length()+1;
|
| 63 |
final int actualBreakAtIndex=(breakAtIndex==NO_BREAK || breakAtIndex>lastPossibleBreakAtIndex) ? lastPossibleBreakAtIndex : breakAtIndex;
|
| 64 |
outerLoop: for (int i=(fromIndex<0 ? 0 : fromIndex); i<actualBreakAtIndex; i++) {
|
| 65 |
if (charAt(i)==firstChar) {
|
| 66 |
for (int j=1; j<searchString.length(); j++)
|
| 67 |
if (searchString.charAt(j)!=charAt(j+i)) continue outerLoop;
|
| 68 |
return i;
|
| 69 |
}
|
| 70 |
}
|
| 71 |
return -1;
|
| 72 |
}
|
| 73 |
|
| 74 |
public final int lastIndexOf(final char searchChar, final int fromIndex) {
|
| 75 |
return lastIndexOf(searchChar,fromIndex,NO_BREAK);
|
| 76 |
}
|
| 77 |
|
| 78 |
public final int lastIndexOf(final char searchChar, final int fromIndex, final int breakAtIndex) {
|
| 79 |
for (int i=(fromIndex>getEnd() ? getEnd() : fromIndex); i>breakAtIndex; i--)
|
| 80 |
if (charAt(i)==searchChar) return i;
|
| 81 |
return -1;
|
| 82 |
}
|
| 83 |
|
| 84 |
public final int lastIndexOf(final String searchString, final int fromIndex) {
|
| 85 |
return lastIndexOf(searchString,fromIndex,NO_BREAK);
|
| 86 |
}
|
| 87 |
|
| 88 |
public final int lastIndexOf(final String searchString, int fromIndex, final int breakAtIndex) {
|
| 89 |
if (searchString.length()==1) return lastIndexOf(searchString.charAt(0),fromIndex,breakAtIndex);
|
| 90 |
if (searchString.length()==0) return fromIndex;
|
| 91 |
final int rightIndex=getEnd()-searchString.length();
|
| 92 |
if (breakAtIndex>rightIndex) return -1;
|
| 93 |
if (fromIndex>rightIndex) fromIndex=rightIndex;
|
| 94 |
final int lastCharIndex=searchString.length()-1;
|
| 95 |
final char lastChar=searchString.charAt(lastCharIndex);
|
| 96 |
final int actualBreakAtPos=breakAtIndex+lastCharIndex;
|
| 97 |
outerLoop: for (int i=fromIndex+lastCharIndex; i>actualBreakAtPos; i--) {
|
| 98 |
if (charAt(i)==lastChar) {
|
| 99 |
final int startIndex=i-lastCharIndex;
|
| 100 |
for (int j=lastCharIndex-1; j>=0; j--)
|
| 101 |
if (searchString.charAt(j)!=charAt(j+startIndex)) continue outerLoop;
|
| 102 |
return startIndex;
|
| 103 |
}
|
| 104 |
}
|
| 105 |
return -1;
|
| 106 |
}
|
| 107 |
|
| 108 |
public final int length() {
|
| 109 |
return charSequence.length();
|
| 110 |
}
|
| 111 |
|
| 112 |
public final CharSequence subSequence(final int begin, final int end) {
|
| 113 |
// doesn't have to be efficient because it is not actually used anywhere internally.
|
| 114 |
return substring(begin,end);
|
| 115 |
}
|
| 116 |
|
| 117 |
public final String toString() {
|
| 118 |
return charSequence.toString();
|
| 119 |
}
|
| 120 |
|
| 121 |
protected int getEnd() {
|
| 122 |
return charSequence.length();
|
| 123 |
}
|
| 124 |
|
| 125 |
protected String substring(final int begin, final int end) {
|
| 126 |
return charSequence.subSequence(begin,end).toString().toLowerCase();
|
| 127 |
}
|
| 128 |
}
|
Parent Directory
| 
Revision Log