You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

PackFile.java 32KB

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130
  1. /*
  2. * Copyright (C) 2008-2009, Google Inc.
  3. * Copyright (C) 2007, Robin Rosenberg <robin.rosenberg@dewire.com>
  4. * Copyright (C) 2006-2008, Shawn O. Pearce <spearce@spearce.org>
  5. * and other copyright owners as documented in the project's IP log.
  6. *
  7. * This program and the accompanying materials are made available
  8. * under the terms of the Eclipse Distribution License v1.0 which
  9. * accompanies this distribution, is reproduced below, and is
  10. * available at http://www.eclipse.org/org/documents/edl-v10.php
  11. *
  12. * All rights reserved.
  13. *
  14. * Redistribution and use in source and binary forms, with or
  15. * without modification, are permitted provided that the following
  16. * conditions are met:
  17. *
  18. * - Redistributions of source code must retain the above copyright
  19. * notice, this list of conditions and the following disclaimer.
  20. *
  21. * - Redistributions in binary form must reproduce the above
  22. * copyright notice, this list of conditions and the following
  23. * disclaimer in the documentation and/or other materials provided
  24. * with the distribution.
  25. *
  26. * - Neither the name of the Eclipse Foundation, Inc. nor the
  27. * names of its contributors may be used to endorse or promote
  28. * products derived from this software without specific prior
  29. * written permission.
  30. *
  31. * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
  32. * CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
  33. * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
  34. * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  35. * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
  36. * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
  37. * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
  38. * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
  39. * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
  40. * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
  41. * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
  42. * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
  43. * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  44. */
  45. package org.eclipse.jgit.internal.storage.file;
  46. import static org.eclipse.jgit.internal.storage.pack.PackExt.BITMAP_INDEX;
  47. import static org.eclipse.jgit.internal.storage.pack.PackExt.INDEX;
  48. import java.io.EOFException;
  49. import java.io.File;
  50. import java.io.IOException;
  51. import java.io.InterruptedIOException;
  52. import java.io.RandomAccessFile;
  53. import java.nio.MappedByteBuffer;
  54. import java.nio.channels.FileChannel.MapMode;
  55. import java.text.MessageFormat;
  56. import java.util.Arrays;
  57. import java.util.Collections;
  58. import java.util.Comparator;
  59. import java.util.Iterator;
  60. import java.util.Set;
  61. import java.util.zip.CRC32;
  62. import java.util.zip.DataFormatException;
  63. import java.util.zip.Inflater;
  64. import org.eclipse.jgit.errors.CorruptObjectException;
  65. import org.eclipse.jgit.errors.LargeObjectException;
  66. import org.eclipse.jgit.errors.MissingObjectException;
  67. import org.eclipse.jgit.errors.PackInvalidException;
  68. import org.eclipse.jgit.errors.PackMismatchException;
  69. import org.eclipse.jgit.errors.StoredObjectRepresentationNotAvailableException;
  70. import org.eclipse.jgit.internal.JGitText;
  71. import org.eclipse.jgit.internal.storage.pack.BinaryDelta;
  72. import org.eclipse.jgit.internal.storage.pack.ObjectToPack;
  73. import org.eclipse.jgit.internal.storage.pack.PackExt;
  74. import org.eclipse.jgit.internal.storage.pack.PackOutputStream;
  75. import org.eclipse.jgit.lib.AbbreviatedObjectId;
  76. import org.eclipse.jgit.lib.AnyObjectId;
  77. import org.eclipse.jgit.lib.Constants;
  78. import org.eclipse.jgit.lib.ObjectId;
  79. import org.eclipse.jgit.lib.ObjectLoader;
  80. import org.eclipse.jgit.util.LongList;
  81. import org.eclipse.jgit.util.NB;
  82. import org.eclipse.jgit.util.RawParseUtils;
  83. /**
  84. * A Git version 2 pack file representation. A pack file contains Git objects in
  85. * delta packed format yielding high compression of lots of object where some
  86. * objects are similar.
  87. */
  88. public class PackFile implements Iterable<PackIndex.MutableEntry> {
  89. /** Sorts PackFiles to be most recently created to least recently created. */
  90. public static final Comparator<PackFile> SORT = new Comparator<PackFile>() {
  91. public int compare(final PackFile a, final PackFile b) {
  92. return b.packLastModified - a.packLastModified;
  93. }
  94. };
  95. private final File packFile;
  96. private final int extensions;
  97. private File keepFile;
  98. private volatile String packName;
  99. final int hash;
  100. private RandomAccessFile fd;
  101. /** Serializes reads performed against {@link #fd}. */
  102. private final Object readLock = new Object();
  103. long length;
  104. private int activeWindows;
  105. private int activeCopyRawData;
  106. private int packLastModified;
  107. private volatile boolean invalid;
  108. private boolean invalidBitmap;
  109. private byte[] packChecksum;
  110. private PackIndex loadedIdx;
  111. private PackReverseIndex reverseIdx;
  112. private PackBitmapIndex bitmapIdx;
  113. /**
  114. * Objects we have tried to read, and discovered to be corrupt.
  115. * <p>
  116. * The list is allocated after the first corruption is found, and filled in
  117. * as more entries are discovered. Typically this list is never used, as
  118. * pack files do not usually contain corrupt objects.
  119. */
  120. private volatile LongList corruptObjects;
  121. /**
  122. * Construct a reader for an existing, pre-indexed packfile.
  123. *
  124. * @param packFile
  125. * path of the <code>.pack</code> file holding the data.
  126. * @param extensions
  127. * additional pack file extensions with the same base as the pack
  128. */
  129. public PackFile(final File packFile, int extensions) {
  130. this.packFile = packFile;
  131. this.packLastModified = (int) (packFile.lastModified() >> 10);
  132. this.extensions = extensions;
  133. // Multiply by 31 here so we can more directly combine with another
  134. // value in WindowCache.hash(), without doing the multiply there.
  135. //
  136. hash = System.identityHashCode(this) * 31;
  137. length = Long.MAX_VALUE;
  138. }
  139. private synchronized PackIndex idx() throws IOException {
  140. if (loadedIdx == null) {
  141. if (invalid)
  142. throw new PackInvalidException(packFile);
  143. try {
  144. final PackIndex idx = PackIndex.open(extFile(INDEX));
  145. if (packChecksum == null) {
  146. packChecksum = idx.packChecksum;
  147. } else if (!Arrays.equals(packChecksum, idx.packChecksum)) {
  148. throw new PackMismatchException(MessageFormat.format(
  149. JGitText.get().packChecksumMismatch,
  150. packFile.getPath()));
  151. }
  152. loadedIdx = idx;
  153. } catch (InterruptedIOException e) {
  154. // don't invalidate the pack, we are interrupted from another thread
  155. throw e;
  156. } catch (IOException e) {
  157. invalid = true;
  158. throw e;
  159. }
  160. }
  161. return loadedIdx;
  162. }
  163. /** @return the File object which locates this pack on disk. */
  164. public File getPackFile() {
  165. return packFile;
  166. }
  167. /**
  168. * @return the index for this pack file.
  169. * @throws IOException
  170. */
  171. public PackIndex getIndex() throws IOException {
  172. return idx();
  173. }
  174. /** @return name extracted from {@code pack-*.pack} pattern. */
  175. public String getPackName() {
  176. String name = packName;
  177. if (name == null) {
  178. name = getPackFile().getName();
  179. if (name.startsWith("pack-")) //$NON-NLS-1$
  180. name = name.substring("pack-".length()); //$NON-NLS-1$
  181. if (name.endsWith(".pack")) //$NON-NLS-1$
  182. name = name.substring(0, name.length() - ".pack".length()); //$NON-NLS-1$
  183. packName = name;
  184. }
  185. return name;
  186. }
  187. /**
  188. * Determine if an object is contained within the pack file.
  189. * <p>
  190. * For performance reasons only the index file is searched; the main pack
  191. * content is ignored entirely.
  192. * </p>
  193. *
  194. * @param id
  195. * the object to look for. Must not be null.
  196. * @return true if the object is in this pack; false otherwise.
  197. * @throws IOException
  198. * the index file cannot be loaded into memory.
  199. */
  200. public boolean hasObject(final AnyObjectId id) throws IOException {
  201. final long offset = idx().findOffset(id);
  202. return 0 < offset && !isCorrupt(offset);
  203. }
  204. /**
  205. * Determines whether a .keep file exists for this pack file.
  206. *
  207. * @return true if a .keep file exist.
  208. */
  209. public boolean shouldBeKept() {
  210. if (keepFile == null)
  211. keepFile = new File(packFile.getPath() + ".keep"); //$NON-NLS-1$
  212. return keepFile.exists();
  213. }
  214. /**
  215. * Get an object from this pack.
  216. *
  217. * @param curs
  218. * temporary working space associated with the calling thread.
  219. * @param id
  220. * the object to obtain from the pack. Must not be null.
  221. * @return the object loader for the requested object if it is contained in
  222. * this pack; null if the object was not found.
  223. * @throws IOException
  224. * the pack file or the index could not be read.
  225. */
  226. ObjectLoader get(final WindowCursor curs, final AnyObjectId id)
  227. throws IOException {
  228. final long offset = idx().findOffset(id);
  229. return 0 < offset && !isCorrupt(offset) ? load(curs, offset) : null;
  230. }
  231. void resolve(Set<ObjectId> matches, AbbreviatedObjectId id, int matchLimit)
  232. throws IOException {
  233. idx().resolve(matches, id, matchLimit);
  234. }
  235. /**
  236. * Close the resources utilized by this repository
  237. */
  238. public void close() {
  239. WindowCache.purge(this);
  240. synchronized (this) {
  241. loadedIdx = null;
  242. reverseIdx = null;
  243. }
  244. }
  245. /**
  246. * Provide iterator over entries in associated pack index, that should also
  247. * exist in this pack file. Objects returned by such iterator are mutable
  248. * during iteration.
  249. * <p>
  250. * Iterator returns objects in SHA-1 lexicographical order.
  251. * </p>
  252. *
  253. * @return iterator over entries of associated pack index
  254. *
  255. * @see PackIndex#iterator()
  256. */
  257. public Iterator<PackIndex.MutableEntry> iterator() {
  258. try {
  259. return idx().iterator();
  260. } catch (IOException e) {
  261. return Collections.<PackIndex.MutableEntry> emptyList().iterator();
  262. }
  263. }
  264. /**
  265. * Obtain the total number of objects available in this pack. This method
  266. * relies on pack index, giving number of effectively available objects.
  267. *
  268. * @return number of objects in index of this pack, likewise in this pack
  269. * @throws IOException
  270. * the index file cannot be loaded into memory.
  271. */
  272. long getObjectCount() throws IOException {
  273. return idx().getObjectCount();
  274. }
  275. /**
  276. * Search for object id with the specified start offset in associated pack
  277. * (reverse) index.
  278. *
  279. * @param offset
  280. * start offset of object to find
  281. * @return object id for this offset, or null if no object was found
  282. * @throws IOException
  283. * the index file cannot be loaded into memory.
  284. */
  285. ObjectId findObjectForOffset(final long offset) throws IOException {
  286. return getReverseIdx().findObject(offset);
  287. }
  288. private final byte[] decompress(final long position, final int sz,
  289. final WindowCursor curs) throws IOException, DataFormatException {
  290. byte[] dstbuf;
  291. try {
  292. dstbuf = new byte[sz];
  293. } catch (OutOfMemoryError noMemory) {
  294. // The size may be larger than our heap allows, return null to
  295. // let the caller know allocation isn't possible and it should
  296. // use the large object streaming approach instead.
  297. //
  298. // For example, this can occur when sz is 640 MB, and JRE
  299. // maximum heap size is only 256 MB. Even if the JRE has
  300. // 200 MB free, it cannot allocate a 640 MB byte array.
  301. return null;
  302. }
  303. if (curs.inflate(this, position, dstbuf, false) != sz)
  304. throw new EOFException(MessageFormat.format(
  305. JGitText.get().shortCompressedStreamAt,
  306. Long.valueOf(position)));
  307. return dstbuf;
  308. }
  309. void copyPackAsIs(PackOutputStream out, WindowCursor curs)
  310. throws IOException {
  311. // Pin the first window, this ensures the length is accurate.
  312. curs.pin(this, 0);
  313. curs.copyPackAsIs(this, length, out);
  314. }
  315. final void copyAsIs(PackOutputStream out, LocalObjectToPack src,
  316. boolean validate, WindowCursor curs) throws IOException,
  317. StoredObjectRepresentationNotAvailableException {
  318. beginCopyAsIs(src);
  319. try {
  320. copyAsIs2(out, src, validate, curs);
  321. } finally {
  322. endCopyAsIs();
  323. }
  324. }
  325. private void copyAsIs2(PackOutputStream out, LocalObjectToPack src,
  326. boolean validate, WindowCursor curs) throws IOException,
  327. StoredObjectRepresentationNotAvailableException {
  328. final CRC32 crc1 = validate ? new CRC32() : null;
  329. final CRC32 crc2 = validate ? new CRC32() : null;
  330. final byte[] buf = out.getCopyBuffer();
  331. // Rip apart the header so we can discover the size.
  332. //
  333. readFully(src.offset, buf, 0, 20, curs);
  334. int c = buf[0] & 0xff;
  335. final int typeCode = (c >> 4) & 7;
  336. long inflatedLength = c & 15;
  337. int shift = 4;
  338. int headerCnt = 1;
  339. while ((c & 0x80) != 0) {
  340. c = buf[headerCnt++] & 0xff;
  341. inflatedLength += ((long) (c & 0x7f)) << shift;
  342. shift += 7;
  343. }
  344. if (typeCode == Constants.OBJ_OFS_DELTA) {
  345. do {
  346. c = buf[headerCnt++] & 0xff;
  347. } while ((c & 128) != 0);
  348. if (validate) {
  349. assert(crc1 != null && crc2 != null);
  350. crc1.update(buf, 0, headerCnt);
  351. crc2.update(buf, 0, headerCnt);
  352. }
  353. } else if (typeCode == Constants.OBJ_REF_DELTA) {
  354. if (validate) {
  355. assert(crc1 != null && crc2 != null);
  356. crc1.update(buf, 0, headerCnt);
  357. crc2.update(buf, 0, headerCnt);
  358. }
  359. readFully(src.offset + headerCnt, buf, 0, 20, curs);
  360. if (validate) {
  361. assert(crc1 != null && crc2 != null);
  362. crc1.update(buf, 0, 20);
  363. crc2.update(buf, 0, 20);
  364. }
  365. headerCnt += 20;
  366. } else if (validate) {
  367. assert(crc1 != null && crc2 != null);
  368. crc1.update(buf, 0, headerCnt);
  369. crc2.update(buf, 0, headerCnt);
  370. }
  371. final long dataOffset = src.offset + headerCnt;
  372. final long dataLength = src.length;
  373. final long expectedCRC;
  374. final ByteArrayWindow quickCopy;
  375. // Verify the object isn't corrupt before sending. If it is,
  376. // we report it missing instead.
  377. //
  378. try {
  379. quickCopy = curs.quickCopy(this, dataOffset, dataLength);
  380. if (validate && idx().hasCRC32Support()) {
  381. assert(crc1 != null);
  382. // Index has the CRC32 code cached, validate the object.
  383. //
  384. expectedCRC = idx().findCRC32(src);
  385. if (quickCopy != null) {
  386. quickCopy.crc32(crc1, dataOffset, (int) dataLength);
  387. } else {
  388. long pos = dataOffset;
  389. long cnt = dataLength;
  390. while (cnt > 0) {
  391. final int n = (int) Math.min(cnt, buf.length);
  392. readFully(pos, buf, 0, n, curs);
  393. crc1.update(buf, 0, n);
  394. pos += n;
  395. cnt -= n;
  396. }
  397. }
  398. if (crc1.getValue() != expectedCRC) {
  399. setCorrupt(src.offset);
  400. throw new CorruptObjectException(MessageFormat.format(
  401. JGitText.get().objectAtHasBadZlibStream,
  402. Long.valueOf(src.offset), getPackFile()));
  403. }
  404. } else if (validate) {
  405. // We don't have a CRC32 code in the index, so compute it
  406. // now while inflating the raw data to get zlib to tell us
  407. // whether or not the data is safe.
  408. //
  409. Inflater inf = curs.inflater();
  410. byte[] tmp = new byte[1024];
  411. if (quickCopy != null) {
  412. quickCopy.check(inf, tmp, dataOffset, (int) dataLength);
  413. } else {
  414. assert(crc1 != null);
  415. long pos = dataOffset;
  416. long cnt = dataLength;
  417. while (cnt > 0) {
  418. final int n = (int) Math.min(cnt, buf.length);
  419. readFully(pos, buf, 0, n, curs);
  420. crc1.update(buf, 0, n);
  421. inf.setInput(buf, 0, n);
  422. while (inf.inflate(tmp, 0, tmp.length) > 0)
  423. continue;
  424. pos += n;
  425. cnt -= n;
  426. }
  427. }
  428. if (!inf.finished() || inf.getBytesRead() != dataLength) {
  429. setCorrupt(src.offset);
  430. throw new EOFException(MessageFormat.format(
  431. JGitText.get().shortCompressedStreamAt,
  432. Long.valueOf(src.offset)));
  433. }
  434. assert(crc1 != null);
  435. expectedCRC = crc1.getValue();
  436. } else {
  437. expectedCRC = -1;
  438. }
  439. } catch (DataFormatException dataFormat) {
  440. setCorrupt(src.offset);
  441. CorruptObjectException corruptObject = new CorruptObjectException(
  442. MessageFormat.format(
  443. JGitText.get().objectAtHasBadZlibStream,
  444. Long.valueOf(src.offset), getPackFile()));
  445. corruptObject.initCause(dataFormat);
  446. StoredObjectRepresentationNotAvailableException gone;
  447. gone = new StoredObjectRepresentationNotAvailableException(src);
  448. gone.initCause(corruptObject);
  449. throw gone;
  450. } catch (IOException ioError) {
  451. StoredObjectRepresentationNotAvailableException gone;
  452. gone = new StoredObjectRepresentationNotAvailableException(src);
  453. gone.initCause(ioError);
  454. throw gone;
  455. }
  456. if (quickCopy != null) {
  457. // The entire object fits into a single byte array window slice,
  458. // and we have it pinned. Write this out without copying.
  459. //
  460. out.writeHeader(src, inflatedLength);
  461. quickCopy.write(out, dataOffset, (int) dataLength);
  462. } else if (dataLength <= buf.length) {
  463. // Tiny optimization: Lots of objects are very small deltas or
  464. // deflated commits that are likely to fit in the copy buffer.
  465. //
  466. if (!validate) {
  467. long pos = dataOffset;
  468. long cnt = dataLength;
  469. while (cnt > 0) {
  470. final int n = (int) Math.min(cnt, buf.length);
  471. readFully(pos, buf, 0, n, curs);
  472. pos += n;
  473. cnt -= n;
  474. }
  475. }
  476. out.writeHeader(src, inflatedLength);
  477. out.write(buf, 0, (int) dataLength);
  478. } else {
  479. // Now we are committed to sending the object. As we spool it out,
  480. // check its CRC32 code to make sure there wasn't corruption between
  481. // the verification we did above, and us actually outputting it.
  482. //
  483. out.writeHeader(src, inflatedLength);
  484. long pos = dataOffset;
  485. long cnt = dataLength;
  486. while (cnt > 0) {
  487. final int n = (int) Math.min(cnt, buf.length);
  488. readFully(pos, buf, 0, n, curs);
  489. if (validate) {
  490. assert(crc2 != null);
  491. crc2.update(buf, 0, n);
  492. }
  493. out.write(buf, 0, n);
  494. pos += n;
  495. cnt -= n;
  496. }
  497. if (validate) {
  498. assert(crc2 != null);
  499. if (crc2.getValue() != expectedCRC) {
  500. throw new CorruptObjectException(MessageFormat.format(
  501. JGitText.get().objectAtHasBadZlibStream,
  502. Long.valueOf(src.offset), getPackFile()));
  503. }
  504. }
  505. }
  506. }
  507. boolean invalid() {
  508. return invalid;
  509. }
  510. void setInvalid() {
  511. invalid = true;
  512. }
  513. private void readFully(final long position, final byte[] dstbuf,
  514. int dstoff, final int cnt, final WindowCursor curs)
  515. throws IOException {
  516. if (curs.copy(this, position, dstbuf, dstoff, cnt) != cnt)
  517. throw new EOFException();
  518. }
  519. private synchronized void beginCopyAsIs(ObjectToPack otp)
  520. throws StoredObjectRepresentationNotAvailableException {
  521. if (++activeCopyRawData == 1 && activeWindows == 0) {
  522. try {
  523. doOpen();
  524. } catch (IOException thisPackNotValid) {
  525. StoredObjectRepresentationNotAvailableException gone;
  526. gone = new StoredObjectRepresentationNotAvailableException(otp);
  527. gone.initCause(thisPackNotValid);
  528. throw gone;
  529. }
  530. }
  531. }
  532. private synchronized void endCopyAsIs() {
  533. if (--activeCopyRawData == 0 && activeWindows == 0)
  534. doClose();
  535. }
  536. synchronized boolean beginWindowCache() throws IOException {
  537. if (++activeWindows == 1) {
  538. if (activeCopyRawData == 0)
  539. doOpen();
  540. return true;
  541. }
  542. return false;
  543. }
  544. synchronized boolean endWindowCache() {
  545. final boolean r = --activeWindows == 0;
  546. if (r && activeCopyRawData == 0)
  547. doClose();
  548. return r;
  549. }
  550. private void doOpen() throws IOException {
  551. try {
  552. if (invalid)
  553. throw new PackInvalidException(packFile);
  554. synchronized (readLock) {
  555. fd = new RandomAccessFile(packFile, "r"); //$NON-NLS-1$
  556. length = fd.length();
  557. onOpenPack();
  558. }
  559. } catch (InterruptedIOException e) {
  560. // don't invalidate the pack, we are interrupted from another thread
  561. openFail(false);
  562. throw e;
  563. } catch (IOException ioe) {
  564. openFail(true);
  565. throw ioe;
  566. } catch (RuntimeException re) {
  567. openFail(true);
  568. throw re;
  569. } catch (Error re) {
  570. openFail(true);
  571. throw re;
  572. }
  573. }
  574. private void openFail(boolean invalidate) {
  575. activeWindows = 0;
  576. activeCopyRawData = 0;
  577. invalid = invalidate;
  578. doClose();
  579. }
  580. private void doClose() {
  581. synchronized (readLock) {
  582. if (fd != null) {
  583. try {
  584. fd.close();
  585. } catch (IOException err) {
  586. // Ignore a close event. We had it open only for reading.
  587. // There should not be errors related to network buffers
  588. // not flushed, etc.
  589. }
  590. fd = null;
  591. }
  592. }
  593. }
  594. ByteArrayWindow read(final long pos, int size) throws IOException {
  595. synchronized (readLock) {
  596. if (length < pos + size)
  597. size = (int) (length - pos);
  598. final byte[] buf = new byte[size];
  599. fd.seek(pos);
  600. fd.readFully(buf, 0, size);
  601. return new ByteArrayWindow(this, pos, buf);
  602. }
  603. }
  604. ByteWindow mmap(final long pos, int size) throws IOException {
  605. synchronized (readLock) {
  606. if (length < pos + size)
  607. size = (int) (length - pos);
  608. MappedByteBuffer map;
  609. try {
  610. map = fd.getChannel().map(MapMode.READ_ONLY, pos, size);
  611. } catch (IOException ioe1) {
  612. // The most likely reason this failed is the JVM has run out
  613. // of virtual memory. We need to discard quickly, and try to
  614. // force the GC to finalize and release any existing mappings.
  615. //
  616. System.gc();
  617. System.runFinalization();
  618. map = fd.getChannel().map(MapMode.READ_ONLY, pos, size);
  619. }
  620. if (map.hasArray())
  621. return new ByteArrayWindow(this, pos, map.array());
  622. return new ByteBufferWindow(this, pos, map);
  623. }
  624. }
  625. private void onOpenPack() throws IOException {
  626. final PackIndex idx = idx();
  627. final byte[] buf = new byte[20];
  628. fd.seek(0);
  629. fd.readFully(buf, 0, 12);
  630. if (RawParseUtils.match(buf, 0, Constants.PACK_SIGNATURE) != 4)
  631. throw new IOException(JGitText.get().notAPACKFile);
  632. final long vers = NB.decodeUInt32(buf, 4);
  633. final long packCnt = NB.decodeUInt32(buf, 8);
  634. if (vers != 2 && vers != 3)
  635. throw new IOException(MessageFormat.format(
  636. JGitText.get().unsupportedPackVersion, Long.valueOf(vers)));
  637. if (packCnt != idx.getObjectCount())
  638. throw new PackMismatchException(MessageFormat.format(
  639. JGitText.get().packObjectCountMismatch,
  640. Long.valueOf(packCnt), Long.valueOf(idx.getObjectCount()),
  641. getPackFile()));
  642. fd.seek(length - 20);
  643. fd.readFully(buf, 0, 20);
  644. if (!Arrays.equals(buf, packChecksum))
  645. throw new PackMismatchException(MessageFormat.format(
  646. JGitText.get().packObjectCountMismatch
  647. , ObjectId.fromRaw(buf).name()
  648. , ObjectId.fromRaw(idx.packChecksum).name()
  649. , getPackFile()));
  650. }
  651. ObjectLoader load(final WindowCursor curs, long pos)
  652. throws IOException, LargeObjectException {
  653. try {
  654. final byte[] ib = curs.tempId;
  655. Delta delta = null;
  656. byte[] data = null;
  657. int type = Constants.OBJ_BAD;
  658. boolean cached = false;
  659. SEARCH: for (;;) {
  660. readFully(pos, ib, 0, 20, curs);
  661. int c = ib[0] & 0xff;
  662. final int typeCode = (c >> 4) & 7;
  663. long sz = c & 15;
  664. int shift = 4;
  665. int p = 1;
  666. while ((c & 0x80) != 0) {
  667. c = ib[p++] & 0xff;
  668. sz += ((long) (c & 0x7f)) << shift;
  669. shift += 7;
  670. }
  671. switch (typeCode) {
  672. case Constants.OBJ_COMMIT:
  673. case Constants.OBJ_TREE:
  674. case Constants.OBJ_BLOB:
  675. case Constants.OBJ_TAG: {
  676. if (delta != null || sz < curs.getStreamFileThreshold())
  677. data = decompress(pos + p, (int) sz, curs);
  678. if (delta != null) {
  679. type = typeCode;
  680. break SEARCH;
  681. }
  682. if (data != null)
  683. return new ObjectLoader.SmallObject(typeCode, data);
  684. else
  685. return new LargePackedWholeObject(typeCode, sz, pos, p,
  686. this, curs.db);
  687. }
  688. case Constants.OBJ_OFS_DELTA: {
  689. c = ib[p++] & 0xff;
  690. long base = c & 127;
  691. while ((c & 128) != 0) {
  692. base += 1;
  693. c = ib[p++] & 0xff;
  694. base <<= 7;
  695. base += (c & 127);
  696. }
  697. base = pos - base;
  698. delta = new Delta(delta, pos, (int) sz, p, base);
  699. if (sz != delta.deltaSize)
  700. break SEARCH;
  701. DeltaBaseCache.Entry e = curs.getDeltaBaseCache().get(this, base);
  702. if (e != null) {
  703. type = e.type;
  704. data = e.data;
  705. cached = true;
  706. break SEARCH;
  707. }
  708. pos = base;
  709. continue SEARCH;
  710. }
  711. case Constants.OBJ_REF_DELTA: {
  712. readFully(pos + p, ib, 0, 20, curs);
  713. long base = findDeltaBase(ObjectId.fromRaw(ib));
  714. delta = new Delta(delta, pos, (int) sz, p + 20, base);
  715. if (sz != delta.deltaSize)
  716. break SEARCH;
  717. DeltaBaseCache.Entry e = curs.getDeltaBaseCache().get(this, base);
  718. if (e != null) {
  719. type = e.type;
  720. data = e.data;
  721. cached = true;
  722. break SEARCH;
  723. }
  724. pos = base;
  725. continue SEARCH;
  726. }
  727. default:
  728. throw new IOException(MessageFormat.format(
  729. JGitText.get().unknownObjectType,
  730. Integer.valueOf(typeCode)));
  731. }
  732. }
  733. // At this point there is at least one delta to apply to data.
  734. // (Whole objects with no deltas to apply return early above.)
  735. if (data == null)
  736. throw new IOException(JGitText.get().inMemoryBufferLimitExceeded);
  737. assert(delta != null);
  738. do {
  739. // Cache only the base immediately before desired object.
  740. if (cached)
  741. cached = false;
  742. else if (delta.next == null)
  743. curs.getDeltaBaseCache().store(this, delta.basePos, data, type);
  744. pos = delta.deltaPos;
  745. final byte[] cmds = decompress(pos + delta.hdrLen,
  746. delta.deltaSize, curs);
  747. if (cmds == null) {
  748. data = null; // Discard base in case of OutOfMemoryError
  749. throw new LargeObjectException.OutOfMemory(new OutOfMemoryError());
  750. }
  751. final long sz = BinaryDelta.getResultSize(cmds);
  752. if (Integer.MAX_VALUE <= sz)
  753. throw new LargeObjectException.ExceedsByteArrayLimit();
  754. final byte[] result;
  755. try {
  756. result = new byte[(int) sz];
  757. } catch (OutOfMemoryError tooBig) {
  758. data = null; // Discard base in case of OutOfMemoryError
  759. throw new LargeObjectException.OutOfMemory(tooBig);
  760. }
  761. BinaryDelta.apply(data, cmds, result);
  762. data = result;
  763. delta = delta.next;
  764. } while (delta != null);
  765. return new ObjectLoader.SmallObject(type, data);
  766. } catch (DataFormatException dfe) {
  767. CorruptObjectException coe = new CorruptObjectException(
  768. MessageFormat.format(
  769. JGitText.get().objectAtHasBadZlibStream,
  770. Long.valueOf(pos), getPackFile()));
  771. coe.initCause(dfe);
  772. throw coe;
  773. }
  774. }
  775. private long findDeltaBase(ObjectId baseId) throws IOException,
  776. MissingObjectException {
  777. long ofs = idx().findOffset(baseId);
  778. if (ofs < 0)
  779. throw new MissingObjectException(baseId,
  780. JGitText.get().missingDeltaBase);
  781. return ofs;
  782. }
  783. private static class Delta {
  784. /** Child that applies onto this object. */
  785. final Delta next;
  786. /** Offset of the delta object. */
  787. final long deltaPos;
  788. /** Size of the inflated delta stream. */
  789. final int deltaSize;
  790. /** Total size of the delta's pack entry header (including base). */
  791. final int hdrLen;
  792. /** Offset of the base object this delta applies onto. */
  793. final long basePos;
  794. Delta(Delta next, long ofs, int sz, int hdrLen, long baseOffset) {
  795. this.next = next;
  796. this.deltaPos = ofs;
  797. this.deltaSize = sz;
  798. this.hdrLen = hdrLen;
  799. this.basePos = baseOffset;
  800. }
  801. }
  802. byte[] getDeltaHeader(WindowCursor wc, long pos)
  803. throws IOException, DataFormatException {
  804. // The delta stream starts as two variable length integers. If we
  805. // assume they are 64 bits each, we need 16 bytes to encode them,
  806. // plus 2 extra bytes for the variable length overhead. So 18 is
  807. // the longest delta instruction header.
  808. //
  809. final byte[] hdr = new byte[18];
  810. wc.inflate(this, pos, hdr, true /* headerOnly */);
  811. return hdr;
  812. }
  813. int getObjectType(final WindowCursor curs, long pos) throws IOException {
  814. final byte[] ib = curs.tempId;
  815. for (;;) {
  816. readFully(pos, ib, 0, 20, curs);
  817. int c = ib[0] & 0xff;
  818. final int type = (c >> 4) & 7;
  819. switch (type) {
  820. case Constants.OBJ_COMMIT:
  821. case Constants.OBJ_TREE:
  822. case Constants.OBJ_BLOB:
  823. case Constants.OBJ_TAG:
  824. return type;
  825. case Constants.OBJ_OFS_DELTA: {
  826. int p = 1;
  827. while ((c & 0x80) != 0)
  828. c = ib[p++] & 0xff;
  829. c = ib[p++] & 0xff;
  830. long ofs = c & 127;
  831. while ((c & 128) != 0) {
  832. ofs += 1;
  833. c = ib[p++] & 0xff;
  834. ofs <<= 7;
  835. ofs += (c & 127);
  836. }
  837. pos = pos - ofs;
  838. continue;
  839. }
  840. case Constants.OBJ_REF_DELTA: {
  841. int p = 1;
  842. while ((c & 0x80) != 0)
  843. c = ib[p++] & 0xff;
  844. readFully(pos + p, ib, 0, 20, curs);
  845. pos = findDeltaBase(ObjectId.fromRaw(ib));
  846. continue;
  847. }
  848. default:
  849. throw new IOException(
  850. MessageFormat.format(JGitText.get().unknownObjectType,
  851. Integer.valueOf(type)));
  852. }
  853. }
  854. }
  855. long getObjectSize(final WindowCursor curs, final AnyObjectId id)
  856. throws IOException {
  857. final long offset = idx().findOffset(id);
  858. return 0 < offset ? getObjectSize(curs, offset) : -1;
  859. }
  860. long getObjectSize(final WindowCursor curs, final long pos)
  861. throws IOException {
  862. final byte[] ib = curs.tempId;
  863. readFully(pos, ib, 0, 20, curs);
  864. int c = ib[0] & 0xff;
  865. final int type = (c >> 4) & 7;
  866. long sz = c & 15;
  867. int shift = 4;
  868. int p = 1;
  869. while ((c & 0x80) != 0) {
  870. c = ib[p++] & 0xff;
  871. sz += ((long) (c & 0x7f)) << shift;
  872. shift += 7;
  873. }
  874. long deltaAt;
  875. switch (type) {
  876. case Constants.OBJ_COMMIT:
  877. case Constants.OBJ_TREE:
  878. case Constants.OBJ_BLOB:
  879. case Constants.OBJ_TAG:
  880. return sz;
  881. case Constants.OBJ_OFS_DELTA:
  882. c = ib[p++] & 0xff;
  883. while ((c & 128) != 0)
  884. c = ib[p++] & 0xff;
  885. deltaAt = pos + p;
  886. break;
  887. case Constants.OBJ_REF_DELTA:
  888. deltaAt = pos + p + 20;
  889. break;
  890. default:
  891. throw new IOException(MessageFormat.format(
  892. JGitText.get().unknownObjectType, Integer.valueOf(type)));
  893. }
  894. try {
  895. return BinaryDelta.getResultSize(getDeltaHeader(curs, deltaAt));
  896. } catch (DataFormatException e) {
  897. throw new CorruptObjectException(MessageFormat.format(
  898. JGitText.get().objectAtHasBadZlibStream, Long.valueOf(pos),
  899. getPackFile()));
  900. }
  901. }
  902. LocalObjectRepresentation representation(final WindowCursor curs,
  903. final AnyObjectId objectId) throws IOException {
  904. final long pos = idx().findOffset(objectId);
  905. if (pos < 0)
  906. return null;
  907. final byte[] ib = curs.tempId;
  908. readFully(pos, ib, 0, 20, curs);
  909. int c = ib[0] & 0xff;
  910. int p = 1;
  911. final int typeCode = (c >> 4) & 7;
  912. while ((c & 0x80) != 0)
  913. c = ib[p++] & 0xff;
  914. long len = (findEndOffset(pos) - pos);
  915. switch (typeCode) {
  916. case Constants.OBJ_COMMIT:
  917. case Constants.OBJ_TREE:
  918. case Constants.OBJ_BLOB:
  919. case Constants.OBJ_TAG:
  920. return LocalObjectRepresentation.newWhole(this, pos, len - p);
  921. case Constants.OBJ_OFS_DELTA: {
  922. c = ib[p++] & 0xff;
  923. long ofs = c & 127;
  924. while ((c & 128) != 0) {
  925. ofs += 1;
  926. c = ib[p++] & 0xff;
  927. ofs <<= 7;
  928. ofs += (c & 127);
  929. }
  930. ofs = pos - ofs;
  931. return LocalObjectRepresentation.newDelta(this, pos, len - p, ofs);
  932. }
  933. case Constants.OBJ_REF_DELTA: {
  934. len -= p;
  935. len -= Constants.OBJECT_ID_LENGTH;
  936. readFully(pos + p, ib, 0, 20, curs);
  937. ObjectId id = ObjectId.fromRaw(ib);
  938. return LocalObjectRepresentation.newDelta(this, pos, len, id);
  939. }
  940. default:
  941. throw new IOException(
  942. MessageFormat.format(JGitText.get().unknownObjectType,
  943. Integer.valueOf(typeCode)));
  944. }
  945. }
  946. private long findEndOffset(final long startOffset)
  947. throws IOException, CorruptObjectException {
  948. final long maxOffset = length - 20;
  949. return getReverseIdx().findNextOffset(startOffset, maxOffset);
  950. }
  951. synchronized PackBitmapIndex getBitmapIndex() throws IOException {
  952. if (invalid || invalidBitmap)
  953. return null;
  954. if (bitmapIdx == null && hasExt(BITMAP_INDEX)) {
  955. final PackBitmapIndex idx = PackBitmapIndex.open(
  956. extFile(BITMAP_INDEX), idx(), getReverseIdx());
  957. // At this point, idx() will have set packChecksum.
  958. if (Arrays.equals(packChecksum, idx.packChecksum))
  959. bitmapIdx = idx;
  960. else
  961. invalidBitmap = true;
  962. }
  963. return bitmapIdx;
  964. }
  965. private synchronized PackReverseIndex getReverseIdx() throws IOException {
  966. if (reverseIdx == null)
  967. reverseIdx = new PackReverseIndex(idx());
  968. return reverseIdx;
  969. }
  970. private boolean isCorrupt(long offset) {
  971. LongList list = corruptObjects;
  972. if (list == null)
  973. return false;
  974. synchronized (list) {
  975. return list.contains(offset);
  976. }
  977. }
  978. private void setCorrupt(long offset) {
  979. LongList list = corruptObjects;
  980. if (list == null) {
  981. synchronized (readLock) {
  982. list = corruptObjects;
  983. if (list == null) {
  984. list = new LongList();
  985. corruptObjects = list;
  986. }
  987. }
  988. }
  989. synchronized (list) {
  990. list.add(offset);
  991. }
  992. }
  993. private File extFile(PackExt ext) {
  994. String p = packFile.getName();
  995. int dot = p.lastIndexOf('.');
  996. String b = (dot < 0) ? p : p.substring(0, dot);
  997. return new File(packFile.getParentFile(), b + '.' + ext.getExtension());
  998. }
  999. private boolean hasExt(PackExt ext) {
  1000. return (extensions & ext.getBit()) != 0;
  1001. }
  1002. }