1 /*
2 * Copyright (C) 2010, 2013 Marc Strapetz <marc.strapetz@syntevo.com>
3 * Copyright (C) 2015, Ivan Motsch <ivan.motsch@bsiag.com>
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.util.io;
46
47 import java.io.IOException;
48 import java.io.InputStream;
49
50 import org.eclipse.jgit.diff.RawText;
51
52 /**
53 * An InputStream that normalizes CRLF to LF.
54 *
55 * Existing single CR are not changed to LF, but retained as is.
56 *
57 * Optionally, a binary check on the first 8000 bytes is performed and in case
58 * of binary files, canonicalization is turned off (for the complete file).
59 * <p>
60 * This is the former EolCanonicalizingInputStream with a new name in order to
61 * have same naming for all LF / CRLF streams
62 *
63 * @since 4.3
64 */
65 public class AutoLFInputStream extends InputStream {
66 private final byte[] single = new byte[1];
67
68 private final byte[] buf = new byte[8096];
69
70 private final InputStream in;
71
72 private int cnt;
73
74 private int ptr;
75
76 private boolean isBinary;
77
78 private boolean detectBinary;
79
80 private boolean abortIfBinary;
81
82 /**
83 * A special exception thrown when {@link AutoLFInputStream} is told to
84 * throw an exception when attempting to read a binary file. The exception
85 * may be thrown at any stage during reading.
86 *
87 * @since 3.3
88 */
89 public static class IsBinaryException extends IOException {
90 private static final long serialVersionUID = 1L;
91
92 IsBinaryException() {
93 super();
94 }
95 }
96
97 /**
98 * Creates a new InputStream, wrapping the specified stream
99 *
100 * @param in
101 * raw input stream
102 * @param detectBinary
103 * whether binaries should be detected
104 * @since 2.0
105 */
106 public AutoLFInputStream(InputStream in, boolean detectBinary) {
107 this(in, detectBinary, false);
108 }
109
110 /**
111 * Creates a new InputStream, wrapping the specified stream
112 *
113 * @param in
114 * raw input stream
115 * @param detectBinary
116 * whether binaries should be detected
117 * @param abortIfBinary
118 * throw an IOException if the file is binary
119 * @since 3.3
120 */
121 public AutoLFInputStream(InputStream in, boolean detectBinary,
122 boolean abortIfBinary) {
123 this.in = in;
124 this.detectBinary = detectBinary;
125 this.abortIfBinary = abortIfBinary;
126 }
127
128 /** {@inheritDoc} */
129 @Override
130 public int read() throws IOException {
131 final int read = read(single, 0, 1);
132 return read == 1 ? single[0] & 0xff : -1;
133 }
134
135 /** {@inheritDoc} */
136 @Override
137 public int read(byte[] bs, int off, int len)
138 throws IOException {
139 if (len == 0)
140 return 0;
141
142 if (cnt == -1)
143 return -1;
144
145 int i = off;
146 final int end = off + len;
147
148 while (i < end) {
149 if (ptr == cnt && !fillBuffer()) {
150 break;
151 }
152
153 byte b = buf[ptr++];
154 if (isBinary || b != '\r') {
155 // Logic for binary files ends here
156 bs[i++] = b;
157 continue;
158 }
159
160 if (ptr == cnt && !fillBuffer()) {
161 bs[i++] = '\r';
162 break;
163 }
164
165 if (buf[ptr] == '\n') {
166 bs[i++] = '\n';
167 ptr++;
168 } else
169 bs[i++] = '\r';
170 }
171
172 return i == off ? -1 : i - off;
173 }
174
175 /**
176 * Whether the stream has detected as a binary so far.
177 *
178 * @return true if the stream has detected as a binary so far.
179 * @since 3.3
180 */
181 public boolean isBinary() {
182 return isBinary;
183 }
184
185 /** {@inheritDoc} */
186 @Override
187 public void close() throws IOException {
188 in.close();
189 }
190
191 private boolean fillBuffer() throws IOException {
192 cnt = 0;
193 while (cnt < buf.length) {
194 int n = in.read(buf, cnt, buf.length - cnt);
195 if (n < 0) {
196 break;
197 }
198 cnt += n;
199 }
200 if (cnt < 1) {
201 cnt = -1;
202 return false;
203 }
204 if (detectBinary) {
205 isBinary = RawText.isBinary(buf, cnt);
206 detectBinary = false;
207 if (isBinary && abortIfBinary)
208 throw new IsBinaryException();
209 }
210 ptr = 0;
211 return true;
212 }
213 }