1 /*
2 * Copyright (C) 2009, Google Inc.
3 * Copyright (C) 2008, Shawn O. Pearce <spearce@spearce.org>
4 * and other copyright owners as documented in the project's IP log.
5 *
6 * This program and the accompanying materials are made available
7 * under the terms of the Eclipse Distribution License v1.0 which
8 * accompanies this distribution, is reproduced below, and is
9 * available at http://www.eclipse.org/org/documents/edl-v10.php
10 *
11 * All rights reserved.
12 *
13 * Redistribution and use in source and binary forms, with or
14 * without modification, are permitted provided that the following
15 * conditions are met:
16 *
17 * - Redistributions of source code must retain the above copyright
18 * notice, this list of conditions and the following disclaimer.
19 *
20 * - Redistributions in binary form must reproduce the above
21 * copyright notice, this list of conditions and the following
22 * disclaimer in the documentation and/or other materials provided
23 * with the distribution.
24 *
25 * - Neither the name of the Eclipse Foundation, Inc. nor the
26 * names of its contributors may be used to endorse or promote
27 * products derived from this software without specific prior
28 * written permission.
29 *
30 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
31 * CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
32 * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
33 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
34 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
35 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
36 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
37 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
38 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
39 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
40 * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
41 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
42 * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
43 */
44
45 package org.eclipse.jgit.revwalk.filter;
46
47 import java.io.IOException;
48 import java.util.regex.Matcher;
49 import java.util.regex.Pattern;
50
51 import org.eclipse.jgit.errors.IncorrectObjectTypeException;
52 import org.eclipse.jgit.errors.MissingObjectException;
53 import org.eclipse.jgit.internal.JGitText;
54 import org.eclipse.jgit.lib.Constants;
55 import org.eclipse.jgit.revwalk.RevCommit;
56 import org.eclipse.jgit.revwalk.RevWalk;
57 import org.eclipse.jgit.util.RawCharSequence;
58
59 /** Abstract filter that searches text using extended regular expressions. */
60 public abstract class PatternMatchRevFilter extends RevFilter {
61 /**
62 * Encode a string pattern for faster matching on byte arrays.
63 * <p>
64 * Force the characters to our funny UTF-8 only convention that we use on
65 * raw buffers. This avoids needing to perform character set decodes on the
66 * individual commit buffers.
67 *
68 * @param patternText
69 * original pattern string supplied by the user or the
70 * application.
71 * @return same pattern, but re-encoded to match our funny raw UTF-8
72 * character sequence {@link RawCharSequence}.
73 */
74 protected static final String forceToRaw(final String patternText) {
75 final byte[] b = Constants.encode(patternText);
76 final StringBuilder needle = new StringBuilder(b.length);
77 for (int i = 0; i < b.length; i++)
78 needle.append((char) (b[i] & 0xff));
79 return needle.toString();
80 }
81
82 private final String patternText;
83
84 private final Matcher compiledPattern;
85
86 /**
87 * Construct a new pattern matching filter.
88 *
89 * @param pattern
90 * text of the pattern. Callers may want to surround their
91 * pattern with ".*" on either end to allow matching in the
92 * middle of the string.
93 * @param innerString
94 * should .* be wrapped around the pattern of ^ and $ are
95 * missing? Most users will want this set.
96 * @param rawEncoding
97 * should {@link #forceToRaw(String)} be applied to the pattern
98 * before compiling it?
99 * @param flags
100 * flags from {@link Pattern} to control how matching performs.
101 */
102 protected PatternMatchRevFilter(String pattern, final boolean innerString,
103 final boolean rawEncoding, final int flags) {
104 if (pattern.length() == 0)
105 throw new IllegalArgumentException(JGitText.get().cannotMatchOnEmptyString);
106 patternText = pattern;
107
108 if (innerString) {
109 if (!pattern.startsWith("^") && !pattern.startsWith(".*")) //$NON-NLS-1$ //$NON-NLS-2$
110 pattern = ".*" + pattern; //$NON-NLS-1$
111 if (!pattern.endsWith("$") && !pattern.endsWith(".*")) //$NON-NLS-1$ //$NON-NLS-2$
112 pattern = pattern + ".*"; //$NON-NLS-1$
113 }
114 final String p = rawEncoding ? forceToRaw(pattern) : pattern;
115 compiledPattern = Pattern.compile(p, flags).matcher(""); //$NON-NLS-1$
116 }
117
118 /**
119 * Get the pattern this filter uses.
120 *
121 * @return the pattern this filter is applying to candidate strings.
122 */
123 public String pattern() {
124 return patternText;
125 }
126
127 @Override
128 public boolean include(final RevWalk walker, final RevCommit cmit)
129 throws MissingObjectException, IncorrectObjectTypeException,
130 IOException {
131 return compiledPattern.reset(text(cmit)).matches();
132 }
133
134 @Override
135 public boolean requiresCommitBody() {
136 return true;
137 }
138
139 /**
140 * Obtain the raw text to match against.
141 *
142 * @param cmit
143 * current commit being evaluated.
144 * @return sequence for the commit's content that we need to match on.
145 */
146 protected abstract CharSequence text(RevCommit cmit);
147
148 @SuppressWarnings("nls")
149 @Override
150 public String toString() {
151 return super.toString() + "(\"" + patternText + "\")";
152 }
153 }