added utility to dump leveldb files

5 files changed, 253 insertions, 5 deletions

diff --git a/src/leveldb/Makefile b/src/leveldb/Makefile
index fdc66f9a2b..fef085b9c4 100644
--- a/src/leveldb/Makefile
+++ b/src/leveldb/Makefile
@@ -50,7 +50,7 @@ TESTS = \
 	version_set_test \
 	write_batch_test
 
-PROGRAMS = db_bench $(TESTS)
+PROGRAMS = db_bench leveldbutil $(TESTS)
 BENCHMARKS = db_bench_sqlite3 db_bench_tree_db
 
 LIBRARY = libleveldb.a
@@ -69,7 +69,7 @@ SHARED = $(SHARED1)
 else
 # Update db.h if you change these.
 SHARED_MAJOR = 1
-SHARED_MINOR = 7
+SHARED_MINOR = 8
 SHARED1 = libleveldb.$(PLATFORM_SHARED_EXT)
 SHARED2 = $(SHARED1).$(SHARED_MAJOR)
 SHARED3 = $(SHARED1).$(SHARED_MAJOR).$(SHARED_MINOR)
@@ -107,6 +107,9 @@ db_bench_sqlite3: doc/bench/db_bench_sqlite3.o $(LIBOBJECTS) $(TESTUTIL)
 db_bench_tree_db: doc/bench/db_bench_tree_db.o $(LIBOBJECTS) $(TESTUTIL)
 	$(CXX) $(LDFLAGS) doc/bench/db_bench_tree_db.o $(LIBOBJECTS) $(TESTUTIL) -o $@ -lkyotocabinet $(LIBS)
 
+leveldbutil: db/leveldb_main.o $(LIBOBJECTS)
+	$(CXX) $(LDFLAGS) db/leveldb_main.o $(LIBOBJECTS) -o $@ $(LIBS)
+
 arena_test: util/arena_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(CXX) $(LDFLAGS) util/arena_test.o $(LIBOBJECTS) $(TESTHARNESS) -o $@ $(LIBS)
 
diff --git a/src/leveldb/build_detect_platform b/src/leveldb/build_detect_platform
index 1080df77f4..609cb51224 100755
--- a/src/leveldb/build_detect_platform
+++ b/src/leveldb/build_detect_platform
@@ -149,7 +149,8 @@ DIRS="$PREFIX/db $PREFIX/util $PREFIX/table"
 set -f # temporarily disable globbing so that our patterns aren't expanded
 PRUNE_TEST="-name *test*.cc -prune"
 PRUNE_BENCH="-name *_bench.cc -prune"
-PORTABLE_FILES=`find $DIRS $PRUNE_TEST -o $PRUNE_BENCH -o -name '*.cc' -print | sort | sed "s,^$PREFIX/,," | tr "\n" " "`
+PRUNE_TOOL="-name leveldb_main.cc -prune"
+PORTABLE_FILES=`find $DIRS $PRUNE_TEST -o $PRUNE_BENCH -o $PRUNE_TOOL -o -name '*.cc' -print | sort | sed "s,^$PREFIX/,," | tr "\n" " "`
 
 set +f # re-enable globbing
 
diff --git a/src/leveldb/db/leveldb_main.cc b/src/leveldb/db/leveldb_main.cc
new file mode 100644
index 0000000000..995d76107a
--- /dev/null
+++ b/src/leveldb/db/leveldb_main.cc
@@ -0,0 +1,238 @@
+// Copyright (c) 2012 The LevelDB Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file. See the AUTHORS file for names of contributors.
+
+#include <stdio.h>
+#include "db/dbformat.h"
+#include "db/filename.h"
+#include "db/log_reader.h"
+#include "db/version_edit.h"
+#include "db/write_batch_internal.h"
+#include "leveldb/env.h"
+#include "leveldb/iterator.h"
+#include "leveldb/options.h"
+#include "leveldb/status.h"
+#include "leveldb/table.h"
+#include "leveldb/write_batch.h"
+#include "util/logging.h"
+
+namespace leveldb {
+
+namespace {
+
+bool GuessType(const std::string& fname, FileType* type) {
+  size_t pos = fname.rfind('/');
+  std::string basename;
+  if (pos == std::string::npos) {
+    basename = fname;
+  } else {
+    basename = std::string(fname.data() + pos + 1, fname.size() - pos - 1);
+  }
+  uint64_t ignored;
+  return ParseFileName(basename, &ignored, type);
+}
+
+// Notified when log reader encounters corruption.
+class CorruptionReporter : public log::Reader::Reporter {
+ public:
+  virtual void Corruption(size_t bytes, const Status& status) {
+    printf("corruption: %d bytes; %s\n",
+            static_cast<int>(bytes),
+            status.ToString().c_str());
+  }
+};
+
+// Print contents of a log file. (*func)() is called on every record.
+bool PrintLogContents(Env* env, const std::string& fname,
+                      void (*func)(Slice)) {
+  SequentialFile* file;
+  Status s = env->NewSequentialFile(fname, &file);
+  if (!s.ok()) {
+    fprintf(stderr, "%s\n", s.ToString().c_str());
+    return false;
+  }
+  CorruptionReporter reporter;
+  log::Reader reader(file, &reporter, true, 0);
+  Slice record;
+  std::string scratch;
+  while (reader.ReadRecord(&record, &scratch)) {
+    printf("--- offset %llu; ",
+           static_cast<unsigned long long>(reader.LastRecordOffset()));
+    (*func)(record);
+  }
+  delete file;
+  return true;
+}
+
+// Called on every item found in a WriteBatch.
+class WriteBatchItemPrinter : public WriteBatch::Handler {
+ public:
+  uint64_t offset_;
+  uint64_t sequence_;
+
+  virtual void Put(const Slice& key, const Slice& value) {
+    printf("  put '%s' '%s'\n",
+           EscapeString(key).c_str(),
+           EscapeString(value).c_str());
+  }
+  virtual void Delete(const Slice& key) {
+    printf("  del '%s'\n",
+           EscapeString(key).c_str());
+  }
+};
+
+
+// Called on every log record (each one of which is a WriteBatch)
+// found in a kLogFile.
+static void WriteBatchPrinter(Slice record) {
+  if (record.size() < 12) {
+    printf("log record length %d is too small\n",
+           static_cast<int>(record.size()));
+    return;
+  }
+  WriteBatch batch;
+  WriteBatchInternal::SetContents(&batch, record);
+  printf("sequence %llu\n",
+         static_cast<unsigned long long>(WriteBatchInternal::Sequence(&batch)));
+  WriteBatchItemPrinter batch_item_printer;
+  Status s = batch.Iterate(&batch_item_printer);
+  if (!s.ok()) {
+    printf("  error: %s\n", s.ToString().c_str());
+  }
+}
+
+bool DumpLog(Env* env, const std::string& fname) {
+  return PrintLogContents(env, fname, WriteBatchPrinter);
+}
+
+// Called on every log record (each one of which is a WriteBatch)
+// found in a kDescriptorFile.
+static void VersionEditPrinter(Slice record) {
+  VersionEdit edit;
+  Status s = edit.DecodeFrom(record);
+  if (!s.ok()) {
+    printf("%s\n", s.ToString().c_str());
+    return;
+  }
+  printf("%s", edit.DebugString().c_str());
+}
+
+bool DumpDescriptor(Env* env, const std::string& fname) {
+  return PrintLogContents(env, fname, VersionEditPrinter);
+}
+
+bool DumpTable(Env* env, const std::string& fname) {
+  uint64_t file_size;
+  RandomAccessFile* file = NULL;
+  Table* table = NULL;
+  Status s = env->GetFileSize(fname, &file_size);
+  if (s.ok()) {
+    s = env->NewRandomAccessFile(fname, &file);
+  }
+  if (s.ok()) {
+    // We use the default comparator, which may or may not match the
+    // comparator used in this database. However this should not cause
+    // problems since we only use Table operations that do not require
+    // any comparisons.  In particular, we do not call Seek or Prev.
+    s = Table::Open(Options(), file, file_size, &table);
+  }
+  if (!s.ok()) {
+    fprintf(stderr, "%s\n", s.ToString().c_str());
+    delete table;
+    delete file;
+    return false;
+  }
+
+  ReadOptions ro;
+  ro.fill_cache = false;
+  Iterator* iter = table->NewIterator(ro);
+  for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
+    ParsedInternalKey key;
+    if (!ParseInternalKey(iter->key(), &key)) {
+      printf("badkey '%s' => '%s'\n",
+             EscapeString(iter->key()).c_str(),
+             EscapeString(iter->value()).c_str());
+    } else {
+      char kbuf[20];
+      const char* type;
+      if (key.type == kTypeDeletion) {
+        type = "del";
+      } else if (key.type == kTypeValue) {
+        type = "val";
+      } else {
+        snprintf(kbuf, sizeof(kbuf), "%d", static_cast<int>(key.type));
+        type = kbuf;
+      }
+      printf("'%s' @ %8llu : %s => '%s'\n",
+             EscapeString(key.user_key).c_str(),
+             static_cast<unsigned long long>(key.sequence),
+             type,
+             EscapeString(iter->value()).c_str());
+    }
+  }
+  s = iter->status();
+  if (!s.ok()) {
+    printf("iterator error: %s\n", s.ToString().c_str());
+  }
+
+  delete iter;
+  delete table;
+  delete file;
+  return true;
+}
+
+bool DumpFile(Env* env, const std::string& fname) {
+  FileType ftype;
+  if (!GuessType(fname, &ftype)) {
+    fprintf(stderr, "%s: unknown file type\n", fname.c_str());
+    return false;
+  }
+  switch (ftype) {
+    case kLogFile:         return DumpLog(env, fname);
+    case kDescriptorFile:  return DumpDescriptor(env, fname);
+    case kTableFile:       return DumpTable(env, fname);
+
+    default: {
+      fprintf(stderr, "%s: not a dump-able file type\n", fname.c_str());
+      break;
+    }
+  }
+  return false;
+}
+
+bool HandleDumpCommand(Env* env, char** files, int num) {
+  bool ok = true;
+  for (int i = 0; i < num; i++) {
+    ok &= DumpFile(env, files[i]);
+  }
+  return ok;
+}
+
+}
+}  // namespace leveldb
+
+static void Usage() {
+  fprintf(
+      stderr,
+      "Usage: leveldbutil command...\n"
+      "   dump files...         -- dump contents of specified files\n"
+      );
+}
+
+int main(int argc, char** argv) {
+  leveldb::Env* env = leveldb::Env::Default();
+  bool ok = true;
+  if (argc < 2) {
+    Usage();
+    ok = false;
+  } else {
+    std::string command = argv[1];
+    if (command == "dump") {
+      ok = leveldb::HandleDumpCommand(env, argv+2, argc-2);
+    } else {
+      Usage();
+      ok = false;
+    }
+  }
+  return (ok ? 0 : 1);
+}
diff --git a/src/leveldb/include/leveldb/db.h b/src/leveldb/include/leveldb/db.h
index 79142f5b25..f1e70a01e9 100644
--- a/src/leveldb/include/leveldb/db.h
+++ b/src/leveldb/include/leveldb/db.h
@@ -14,7 +14,7 @@ namespace leveldb {
 
 // Update Makefile if you change these
 static const int kMajorVersion = 1;
-static const int kMinorVersion = 7;
+static const int kMinorVersion = 8;
 
 struct Options;
 struct ReadOptions;
diff --git a/src/leveldb/port/port_posix.h b/src/leveldb/port/port_posix.h
index 6ca352e2ca..f2b89bffb9 100644
--- a/src/leveldb/port/port_posix.h
+++ b/src/leveldb/port/port_posix.h
@@ -26,11 +26,17 @@
   #include <sys/endian.h>
   #define PLATFORM_IS_LITTLE_ENDIAN (_BYTE_ORDER == _LITTLE_ENDIAN)
 #elif defined(OS_OPENBSD) || defined(OS_NETBSD) ||\
-      defined(OS_DRAGONFLYBSD) || defined(OS_ANDROID)
+      defined(OS_DRAGONFLYBSD)
   #include <sys/types.h>
   #include <sys/endian.h>
 #elif defined(OS_HPUX)
   #define PLATFORM_IS_LITTLE_ENDIAN false
+#elif defined(OS_ANDROID)
+  // Due to a bug in the NDK x86 <sys/endian.h> definition,
+  // _BYTE_ORDER must be used instead of __BYTE_ORDER on Android.
+  // See http://code.google.com/p/android/issues/detail?id=39824
+  #include <endian.h>
+  #define PLATFORM_IS_LITTLE_ENDIAN  (_BYTE_ORDER == _LITTLE_ENDIAN)
 #else
   #include <endian.h>
 #endif