2 * Copyright (C) 2008, Robin Rosenberg <robin.rosenberg@dewire.com>
3 * Copyright (C) 2008, Shawn O. Pearce <spearce@spearce.org>
4 * Copyright (C) 2008, Google Inc.
8 * Redistribution and use in source and binary forms, with or
9 * without modification, are permitted provided that the following
12 * - Redistributions of source code must retain the above copyright
13 * notice, this list of conditions and the following disclaimer.
15 * - Redistributions in binary form must reproduce the above
16 * copyright notice, this list of conditions and the following
17 * disclaimer in the documentation and/or other materials provided
18 * with the distribution.
20 * - Neither the name of the Git Development Community nor the
21 * names of its contributors may be used to endorse or promote
22 * products derived from this software without specific prior
25 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
26 * CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
27 * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
28 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
29 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
30 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
31 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
32 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
33 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
34 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
35 * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
36 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
37 * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
40 package org
.spearce
.jgit
.lib
;
42 import java
.nio
.ByteBuffer
;
43 import java
.nio
.charset
.Charset
;
44 import java
.security
.MessageDigest
;
45 import java
.security
.NoSuchAlgorithmException
;
47 import org
.spearce
.jgit
.errors
.CorruptObjectException
;
48 import org
.spearce
.jgit
.util
.MutableInteger
;
50 /** Misc. constants used throughout JGit. */
51 public final class Constants
{
52 /** Hash function used natively by Git for all objects. */
53 private static final String HASH_FUNCTION
= "SHA-1";
55 /** Length of an object hash. */
56 public static final int OBJECT_ID_LENGTH
= 20;
58 /** Special name for the "HEAD" symbolic-ref. */
59 public static final String HEAD
= "HEAD";
62 * Text string that identifies an object as a commit.
64 * Commits connect trees into a string of project histories, where each
65 * commit is an assertion that the best way to continue is to use this other
66 * tree (set of files).
68 public static final String TYPE_COMMIT
= "commit";
71 * Text string that identifies an object as a blob.
73 * Blobs store whole file revisions. They are used for any user file, as
74 * well as for symlinks. Blobs form the bulk of any project's storage space.
76 public static final String TYPE_BLOB
= "blob";
79 * Text string that identifies an object as a tree.
81 * Trees attach object ids (hashes) to names and file modes. The normal use
82 * for a tree is to store a version of a directory and its contents.
84 public static final String TYPE_TREE
= "tree";
87 * Text string that identifies an object as an annotated tag.
89 * Annotated tags store a pointer to any other object, and an additional
90 * message. It is most commonly used to record a stable release of the
93 public static final String TYPE_TAG
= "tag";
95 private static final byte[] ENCODED_TYPE_COMMIT
= encodeASCII(TYPE_COMMIT
);
97 private static final byte[] ENCODED_TYPE_BLOB
= encodeASCII(TYPE_BLOB
);
99 private static final byte[] ENCODED_TYPE_TREE
= encodeASCII(TYPE_TREE
);
101 private static final byte[] ENCODED_TYPE_TAG
= encodeASCII(TYPE_TAG
);
103 /** An unknown or invalid object type code. */
104 public static final int OBJ_BAD
= -1;
107 * In-pack object type: extended types.
109 * This header code is reserved for future expansion. It is currently
110 * undefined/unsupported.
112 public static final int OBJ_EXT
= 0;
115 * In-pack object type: commit.
117 * Indicates the associated object is a commit.
119 * <b>This constant is fixed and is defined by the Git packfile format.</b>
123 public static final int OBJ_COMMIT
= 1;
126 * In-pack object type: tree.
128 * Indicates the associated object is a tree.
130 * <b>This constant is fixed and is defined by the Git packfile format.</b>
134 public static final int OBJ_TREE
= 2;
137 * In-pack object type: blob.
139 * Indicates the associated object is a blob.
141 * <b>This constant is fixed and is defined by the Git packfile format.</b>
145 public static final int OBJ_BLOB
= 3;
148 * In-pack object type: annotated tag.
150 * Indicates the associated object is an annotated tag.
152 * <b>This constant is fixed and is defined by the Git packfile format.</b>
156 public static final int OBJ_TAG
= 4;
158 /** In-pack object type: reserved for future use. */
159 public static final int OBJ_TYPE_5
= 5;
162 * In-pack object type: offset delta
164 * Objects stored with this type actually have a different type which must
165 * be obtained from their delta base object. Delta objects store only the
166 * changes needed to apply to the base object in order to recover the
169 * An offset delta uses a negative offset from the start of this object to
170 * refer to its delta base. The base object must exist in this packfile
171 * (even in the case of a thin pack).
173 * <b>This constant is fixed and is defined by the Git packfile format.</b>
175 public static final int OBJ_OFS_DELTA
= 6;
178 * In-pack object type: reference delta
180 * Objects stored with this type actually have a different type which must
181 * be obtained from their delta base object. Delta objects store only the
182 * changes needed to apply to the base object in order to recover the
185 * A reference delta uses a full object id (hash) to reference the delta
186 * base. The base object is allowed to be omitted from the packfile, but
187 * only in the case of a thin pack being transferred over the network.
189 * <b>This constant is fixed and is defined by the Git packfile format.</b>
191 public static final int OBJ_REF_DELTA
= 7;
194 * Pack file signature that occurs at file header - identifies file as Git
195 * packfile formatted.
197 * <b>This constant is fixed and is defined by the Git packfile format.</b>
199 public static final byte[] PACK_SIGNATURE
= { 'P', 'A', 'C', 'K' };
201 /** Native character encoding for commit messages, file names... */
202 public static final String CHARACTER_ENCODING
= "UTF-8";
204 /** Native character encoding for commit messages, file names... */
205 public static final Charset CHARSET
;
207 /** Default main branch name */
208 public static final String MASTER
= "master";
210 /** Prefix for branch refs */
211 public static final String R_HEADS
= "refs/heads/";
213 /** Prefix for remotes refs */
214 public static final String R_REMOTES
= "refs/remotes/";
216 /** Prefix for tag refs */
217 public static final String R_TAGS
= "refs/tags/";
219 /** Logs folder name */
220 public static final String LOGS
= "logs";
222 /** Info refs folder */
223 public static final String INFO_REFS
= "info/refs";
225 /** Packed refs file */
226 public static final String PACKED_REFS
= "packed-refs";
229 * Create a new digest function for objects.
231 * @return a new digest object.
232 * @throws RuntimeException
233 * this Java virtual machine does not support the required hash
234 * function. Very unlikely given that JGit uses a hash function
235 * that is in the Java reference specification.
237 public static MessageDigest
newMessageDigest() {
239 return MessageDigest
.getInstance(HASH_FUNCTION
);
240 } catch (NoSuchAlgorithmException nsae
) {
241 throw new RuntimeException("Required hash function "
242 + HASH_FUNCTION
+ " not available.", nsae
);
247 * Convert an OBJ_* type constant to a TYPE_* type constant.
249 * @param typeCode the type code, from a pack representation.
250 * @return the canonical string name of this type.
252 public static String
typeString(final int typeCode
) {
263 throw new IllegalArgumentException("Bad object type: " + typeCode
);
268 * Convert an OBJ_* type constant to an ASCII encoded string constant.
270 * The ASCII encoded string is often the canonical representation of
271 * the type within a loose object header, or within a tag header.
273 * @param typeCode the type code, from a pack representation.
274 * @return the canonical ASCII encoded name of this type.
276 public static byte[] encodedTypeString(final int typeCode
) {
279 return ENCODED_TYPE_COMMIT
;
281 return ENCODED_TYPE_TREE
;
283 return ENCODED_TYPE_BLOB
;
285 return ENCODED_TYPE_TAG
;
287 throw new IllegalArgumentException("Bad object type: " + typeCode
);
292 * Parse an encoded type string into a type constant.
295 * object id this type string came from; may be null if that is
296 * not known at the time the parse is occurring.
298 * string version of the type code.
300 * character immediately following the type string. Usually ' '
301 * (space) or '\n' (line feed).
303 * position within <code>typeString</code> where the parse
304 * should start. Updated with the new position (just past
305 * <code>endMark</code> when the parse is successful.
306 * @return a type code constant (one of {@link #OBJ_BLOB},
307 * {@link #OBJ_COMMIT}, {@link #OBJ_TAG}, {@link #OBJ_TREE}.
308 * @throws CorruptObjectException
309 * there is no valid type identified by <code>typeString</code>.
311 public static int decodeTypeString(final ObjectId id
,
312 final byte[] typeString
, final byte endMark
,
313 final MutableInteger offset
) throws CorruptObjectException
{
315 int position
= offset
.value
;
316 switch (typeString
[position
]) {
318 if (typeString
[position
+ 1] != 'l'
319 || typeString
[position
+ 2] != 'o'
320 || typeString
[position
+ 3] != 'b'
321 || typeString
[position
+ 4] != endMark
)
322 throw new CorruptObjectException(id
, "invalid type");
323 offset
.value
= position
+ 5;
324 return Constants
.OBJ_BLOB
;
327 if (typeString
[position
+ 1] != 'o'
328 || typeString
[position
+ 2] != 'm'
329 || typeString
[position
+ 3] != 'm'
330 || typeString
[position
+ 4] != 'i'
331 || typeString
[position
+ 5] != 't'
332 || typeString
[position
+ 6] != endMark
)
333 throw new CorruptObjectException(id
, "invalid type");
334 offset
.value
= position
+ 7;
335 return Constants
.OBJ_COMMIT
;
338 switch (typeString
[position
+ 1]) {
340 if (typeString
[position
+ 2] != 'g'
341 || typeString
[position
+ 3] != endMark
)
342 throw new CorruptObjectException(id
, "invalid type");
343 offset
.value
= position
+ 4;
344 return Constants
.OBJ_TAG
;
347 if (typeString
[position
+ 2] != 'e'
348 || typeString
[position
+ 3] != 'e'
349 || typeString
[position
+ 4] != endMark
)
350 throw new CorruptObjectException(id
, "invalid type");
351 offset
.value
= position
+ 5;
352 return Constants
.OBJ_TREE
;
355 throw new CorruptObjectException(id
, "invalid type");
359 throw new CorruptObjectException(id
, "invalid type");
361 } catch (ArrayIndexOutOfBoundsException bad
) {
362 throw new CorruptObjectException(id
, "invalid type");
367 * Convert an integer into its decimal representation.
370 * the integer to convert.
371 * @return a decimal representation of the input integer. The returned array
372 * is the smallest array that will hold the value.
374 public static byte[] encodeASCII(final long s
) {
375 return encodeASCII(Long
.toString(s
));
379 * Convert a string to US-ASCII encoding.
382 * the string to convert. Must not contain any characters over
383 * 127 (outside of 7-bit ASCII).
384 * @return a byte array of the same length as the input string, holding the
385 * same characters, in the same order.
386 * @throws IllegalArgumentException
387 * the input string contains one or more characters outside of
388 * the 7-bit ASCII character space.
390 public static byte[] encodeASCII(final String s
) {
391 final byte[] r
= new byte[s
.length()];
392 for (int k
= r
.length
- 1; k
>= 0; k
--) {
393 final char c
= s
.charAt(k
);
395 throw new IllegalArgumentException("Not ASCII string: " + s
);
402 * Convert a string to a byte array in the standard character encoding.
405 * the string to convert. May contain any Unicode characters.
406 * @return a byte array representing the requested string, encoded using the
407 * default character encoding (UTF-8).
408 * @see #CHARACTER_ENCODING
410 public static byte[] encode(final String str
) {
411 final ByteBuffer bb
= Constants
.CHARSET
.encode(str
);
412 final int len
= bb
.limit();
413 if (bb
.hasArray() && bb
.arrayOffset() == 0) {
414 final byte[] arr
= bb
.array();
415 if (arr
.length
== len
)
419 final byte[] arr
= new byte[len
];
425 if (OBJECT_ID_LENGTH
!= newMessageDigest().getDigestLength())
426 throw new LinkageError("Incorrect OBJECT_ID_LENGTH.");
427 CHARSET
= Charset
.forName(CHARACTER_ENCODING
);
430 private Constants() {
431 // Hide the default constructor