reverting disastrous MOE commit, returning to r21

git-svn-id: https://leveldb.googlecode.com/svn/trunk@23 62dab493-f737-651d-591e-8d6aee1b9529

11 files changed, 1289 insertions, 0 deletions

diff --git a/include/leveldb/cache.h b/include/leveldb/cache.h
new file mode 100644
index 0000000..79196d1
--- /dev/null
+++ b/include/leveldb/cache.h
@@ -0,0 +1,99 @@
+// Copyright (c) 2011 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.
+//
+// A Cache is an interface that maps keys to values.  It has internal
+// synchronization and may be safely accessed concurrently from
+// multiple threads.  It may automatically evict entries to make room
+// for new entries.  Values have a specified charge against the cache
+// capacity.  For example, a cache where the values are variable
+// length strings, may use the length of the string as the charge for
+// the string.
+//
+// A builtin cache implementation with a least-recently-used eviction
+// policy is provided.  Clients may use their own implementations if
+// they want something more sophisticated (like scan-resistance, a
+// custom eviction policy, variable cache sizing, etc.)
+
+#ifndef STORAGE_LEVELDB_INCLUDE_CACHE_H_
+#define STORAGE_LEVELDB_INCLUDE_CACHE_H_
+
+#include <stdint.h>
+#include "leveldb/slice.h"
+
+namespace leveldb {
+
+class Cache;
+
+// Create a new cache with a fixed size capacity.  This implementation
+// of Cache uses a least-recently-used eviction policy.
+extern Cache* NewLRUCache(size_t capacity);
+
+class Cache {
+ public:
+  Cache() { }
+
+  // Destroys all existing entries by calling the "deleter"
+  // function that was passed to the constructor.
+  virtual ~Cache();
+
+  // Opaque handle to an entry stored in the cache.
+  struct Handle { };
+
+  // Insert a mapping from key->value into the cache and assign it
+  // the specified charge against the total cache capacity.
+  //
+  // Returns a handle that corresponds to the mapping.  The caller
+  // must call this->Release(handle) when the returned mapping is no
+  // longer needed.
+  //
+  // When the inserted entry is no longer needed, the key and
+  // value will be passed to "deleter".
+  virtual Handle* Insert(const Slice& key, void* value, size_t charge,
+                         void (*deleter)(const Slice& key, void* value)) = 0;
+
+  // If the cache has no mapping for "key", returns NULL.
+  //
+  // Else return a handle that corresponds to the mapping.  The caller
+  // must call this->Release(handle) when the returned mapping is no
+  // longer needed.
+  virtual Handle* Lookup(const Slice& key) = 0;
+
+  // Release a mapping returned by a previous Lookup().
+  // REQUIRES: handle must not have been released yet.
+  // REQUIRES: handle must have been returned by a method on *this.
+  virtual void Release(Handle* handle) = 0;
+
+  // Return the value encapsulated in a handle returned by a
+  // successful Lookup().
+  // REQUIRES: handle must not have been released yet.
+  // REQUIRES: handle must have been returned by a method on *this.
+  virtual void* Value(Handle* handle) = 0;
+
+  // If the cache contains entry for key, erase it.  Note that the
+  // underlying entry will be kept around until all existing handles
+  // to it have been released.
+  virtual void Erase(const Slice& key) = 0;
+
+  // Return a new numeric id.  May be used by multiple clients who are
+  // sharing the same cache to partition the key space.  Typically the
+  // client will allocate a new id at startup and prepend the id to
+  // its cache keys.
+  virtual uint64_t NewId() = 0;
+
+ private:
+  void LRU_Remove(Handle* e);
+  void LRU_Append(Handle* e);
+  void Unref(Handle* e);
+
+  struct Rep;
+  Rep* rep_;
+
+  // No copying allowed
+  Cache(const Cache&);
+  void operator=(const Cache&);
+};
+
+}
+
+#endif  // STORAGE_LEVELDB_UTIL_CACHE_H_
diff --git a/include/leveldb/comparator.h b/include/leveldb/comparator.h
new file mode 100644
index 0000000..4e00e4d
--- /dev/null
+++ b/include/leveldb/comparator.h
@@ -0,0 +1,61 @@
+// Copyright (c) 2011 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.
+
+#ifndef STORAGE_LEVELDB_INCLUDE_COMPARATOR_H_
+#define STORAGE_LEVELDB_INCLUDE_COMPARATOR_H_
+
+#include <string>
+
+namespace leveldb {
+
+class Slice;
+
+// A Comparator object provides a total order across slices that are
+// used as keys in an sstable or a database.
+class Comparator {
+ public:
+  virtual ~Comparator();
+
+  // Three-way comparison.  Returns value:
+  //   < 0 iff "a" < "b",
+  //   == 0 iff "a" == "b",
+  //   > 0 iff "a" > "b"
+  virtual int Compare(const Slice& a, const Slice& b) const = 0;
+
+  // The name of the comparator.  Used to check for comparator
+  // mismatches (i.e., a DB created with one comparator is
+  // accessed using a different comparator.
+  //
+  // The client of this package should switch to a new name whenever
+  // the comparator implementation changes in a way that will cause
+  // the relative ordering of any two keys to change.
+  //
+  // Names starting with "leveldb." are reserved and should not be used
+  // by any clients of this package.
+  virtual const char* Name() const = 0;
+
+  // Advanced functions: these are used to reduce the space requirements
+  // for internal data structures like index blocks.
+
+  // If *start < limit, changes *start to a short string in [start,limit).
+  // Simple comparator implementations may return with *start unchanged,
+  // i.e., an implementation of this method that does nothing is correct.
+  virtual void FindShortestSeparator(
+      std::string* start,
+      const Slice& limit) const = 0;
+
+  // Changes *key to a short string >= *key.
+  // Simple comparator implementations may return with *key unchanged,
+  // i.e., an implementation of this method that does nothing is correct.
+  virtual void FindShortSuccessor(std::string* key) const = 0;
+};
+
+// Return a builtin comparator that uses lexicographic byte-wise
+// ordering.  The result remains the property of this module and
+// must not be deleted.
+extern const Comparator* BytewiseComparator();
+
+}
+
+#endif  // STORAGE_LEVELDB_INCLUDE_COMPARATOR_H_
diff --git a/include/leveldb/db.h b/include/leveldb/db.h
new file mode 100644
index 0000000..f18ded3
--- /dev/null
+++ b/include/leveldb/db.h
@@ -0,0 +1,142 @@
+// Copyright (c) 2011 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.
+
+#ifndef STORAGE_LEVELDB_INCLUDE_DB_H_
+#define STORAGE_LEVELDB_INCLUDE_DB_H_
+
+#include <stdint.h>
+#include <stdio.h>
+#include "leveldb/iterator.h"
+#include "leveldb/options.h"
+
+namespace leveldb {
+
+static const int kMajorVersion = 1;
+static const int kMinorVersion = 1;
+
+struct Options;
+struct ReadOptions;
+struct WriteOptions;
+
+class Snapshot;
+class WriteBatch;
+
+// Some internal types.  Clients should ignore.
+class WriteBatchInternal;
+
+struct Range {
+  Slice start;
+  Slice limit;
+
+  Range(const Slice& s, const Slice& l) : start(s), limit(l) { }
+};
+
+// A DB is a persistent ordered map from keys to values.
+class DB {
+ public:
+  // Open the database with the specified "name".
+  // Stores a pointer to a heap-allocated database in *dbptr and returns
+  // OK on success.
+  // Stores NULL in *dbptr and returns a non-OK status on error.
+  // Caller should delete *dbptr when it is no longer needed.
+  static Status Open(const Options& options,
+                     const std::string& name,
+                     DB** dbptr);
+
+  DB() { }
+  virtual ~DB();
+
+  // Set the database entry for "key" to "value".  Returns OK on success,
+  // and a non-OK status on error.
+  // Note: consider setting options.sync = true.
+  virtual Status Put(const WriteOptions& options,
+                     const Slice& key,
+                     const Slice& value) = 0;
+
+  // Remove the database entry (if any) for "key".  Returns OK on
+  // success, and a non-OK status on error.  It is not an error if "key"
+  // did not exist in the database.
+  // Note: consider setting options.sync = true.
+  virtual Status Delete(const WriteOptions& options, const Slice& key) = 0;
+
+  // Apply the specified updates to the database.
+  // Returns OK on success, non-OK on failure.
+  // Note: consider setting options.sync = true.
+  virtual Status Write(const WriteOptions& options, WriteBatch* updates) = 0;
+
+  // If the database contains an entry for "key" store the
+  // corresponding value in *value and return OK.
+  //
+  // If there is no entry for "key" leave *value unchanged and return
+  // a status for which Status::IsNotFound() returns true.
+  //
+  // May return some other Status on an error.
+  virtual Status Get(const ReadOptions& options,
+                     const Slice& key, std::string* value) = 0;
+
+  // Return a heap-allocated iterator over the contents of the database.
+  // The result of NewIterator() is initially invalid (caller must
+  // call one of the Seek methods on the iterator before using it).
+  //
+  // Caller should delete the iterator when it is no longer needed.
+  // The returned iterator should be deleted before this db is deleted.
+  virtual Iterator* NewIterator(const ReadOptions& options) = 0;
+
+  // Return a handle to the current DB state.  Iterators created with
+  // this handle will all observe a stable snapshot of the current DB
+  // state.  The caller must call ReleaseSnapshot(result) when the
+  // snapshot is no longer needed.
+  virtual const Snapshot* GetSnapshot() = 0;
+
+  // Release a previously acquired snapshot.  The caller must not
+  // use "snapshot" after this call.
+  virtual void ReleaseSnapshot(const Snapshot* snapshot) = 0;
+
+  // DB implementations can export properties about their state
+  // via this method.  If "property" is a valid property understood by this
+  // DB implementation, fills "*value" with its current value and returns
+  // true.  Otherwise returns false.
+  //
+  //
+  // Valid property names include:
+  //
+  //  "leveldb.num-files-at-level<N>" - return the number of files at level <N>,
+  //     where <N> is an ASCII representation of a level number (e.g. "0").
+  //  "leveldb.stats" - returns a multi-line string that describes statistics
+  //     about the internal operation of the DB.
+  virtual bool GetProperty(const Slice& property, std::string* value) = 0;
+
+  // For each i in [0,n-1], store in "sizes[i]", the approximate
+  // file system space used by keys in "[range[i].start .. range[i].limit)".
+  //
+  // Note that the returned sizes measure file system space usage, so
+  // if the user data compresses by a factor of ten, the returned
+  // sizes will be one-tenth the size of the corresponding user data size.
+  //
+  // The results may not include the sizes of recently written data.
+  virtual void GetApproximateSizes(const Range* range, int n,
+                                   uint64_t* sizes) = 0;
+
+  // Possible extensions:
+  // (1) Add a method to compact a range of keys
+
+ private:
+  // No copying allowed
+  DB(const DB&);
+  void operator=(const DB&);
+};
+
+// Destroy the contents of the specified database.
+// Be very careful using this method.
+Status DestroyDB(const std::string& name, const Options& options);
+
+// If a DB cannot be opened, you may attempt to call this method to
+// resurrect as much of the contents of the database as possible.
+// Some data may be lost, so be careful when calling this function
+// on a database that contains important information.
+Status RepairDB(const std::string& dbname, const Options& options);
+
+}
+
+#endif  // STORAGE_LEVELDB_INCLUDE_DB_H_
diff --git a/include/leveldb/env.h b/include/leveldb/env.h
new file mode 100644
index 0000000..4b6e712
--- /dev/null
+++ b/include/leveldb/env.h
@@ -0,0 +1,290 @@
+// Copyright (c) 2011 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.
+//
+// An Env is an interface used by the leveldb implementation to access
+// operating system functionality like the filesystem etc.  Callers
+// may wish to provide a custom Env object when opening a database to
+// get fine gain control; e.g., to rate limit file system operations.
+
+#ifndef STORAGE_LEVELDB_INCLUDE_ENV_H_
+#define STORAGE_LEVELDB_INCLUDE_ENV_H_
+
+#include <cstdarg>
+#include <string>
+#include <vector>
+#include <stdint.h>
+#include "leveldb/status.h"
+
+namespace leveldb {
+
+class FileLock;
+class RandomAccessFile;
+class SequentialFile;
+class Slice;
+class WritableFile;
+
+class Env {
+ public:
+  Env() { }
+  virtual ~Env();
+
+  // Return a default environment suitable for the current operating
+  // system.  Sophisticated users may wish to provide their own Env
+  // implementation instead of relying on this default environment.
+  //
+  // The result of Default() belongs to leveldb and must never be deleted.
+  static Env* Default();
+
+  // Create a brand new sequentially-readable file with the specified name.
+  // On success, stores a pointer to the new file in *result and returns OK.
+  // On failure stores NULL in *result and returns non-OK.  If the file does
+  // not exist, returns a non-OK status.
+  //
+  // The returned file will only be accessed by one thread at a time.
+  virtual Status NewSequentialFile(const std::string& fname,
+                                   SequentialFile** result) = 0;
+
+  // Create a brand new random access read-only file with the
+  // specified name.  On success, stores a pointer to the new file in
+  // *result and returns OK.  On failure stores NULL in *result and
+  // returns non-OK.  If the file does not exist, returns a non-OK
+  // status.
+  //
+  // The returned file may be concurrently accessed by multiple threads.
+  virtual Status NewRandomAccessFile(const std::string& fname,
+                                     RandomAccessFile** result) = 0;
+
+  // Create an object that writes to a new file with the specified
+  // name.  Deletes any existing file with the same name and creates a
+  // new file.  On success, stores a pointer to the new file in
+  // *result and returns OK.  On failure stores NULL in *result and
+  // returns non-OK.
+  //
+  // The returned file will only be accessed by one thread at a time.
+  virtual Status NewWritableFile(const std::string& fname,
+                                 WritableFile** result) = 0;
+
+  // Returns true iff the named file exists.
+  virtual bool FileExists(const std::string& fname) = 0;
+
+  // Store in *result the names of the children of the specified directory.
+  // The names are relative to "dir".
+  // Original contents of *results are dropped.
+  virtual Status GetChildren(const std::string& dir,
+                             std::vector<std::string>* result) = 0;
+
+  // Delete the named file.
+  virtual Status DeleteFile(const std::string& fname) = 0;
+
+  // Create the specified directory.
+  virtual Status CreateDir(const std::string& dirname) = 0;
+
+  // Delete the specified directory.
+  virtual Status DeleteDir(const std::string& dirname) = 0;
+
+  // Store the size of fname in *file_size.
+  virtual Status GetFileSize(const std::string& fname, uint64_t* file_size) = 0;
+
+  // Rename file src to target.
+  virtual Status RenameFile(const std::string& src,
+                            const std::string& target) = 0;
+
+  // Lock the specified file.  Used to prevent concurrent access to
+  // the same db by multiple processes.  On failure, stores NULL in
+  // *lock and returns non-OK.
+  //
+  // On success, stores a pointer to the object that represents the
+  // acquired lock in *lock and returns OK.  The caller should call
+  // UnlockFile(*lock) to release the lock.  If the process exits,
+  // the lock will be automatically released.
+  //
+  // If somebody else already holds the lock, finishes immediately
+  // with a failure.  I.e., this call does not wait for existing locks
+  // to go away.
+  //
+  // May create the named file if it does not already exist.
+  virtual Status LockFile(const std::string& fname, FileLock** lock) = 0;
+
+  // Release the lock acquired by a previous successful call to LockFile.
+  // REQUIRES: lock was returned by a successful LockFile() call
+  // REQUIRES: lock has not already been unlocked.
+  virtual Status UnlockFile(FileLock* lock) = 0;
+
+  // Arrange to run "(*function)(arg)" once in a background thread.
+  //
+  // "function" may run in an unspecified thread.  Multiple functions
+  // added to the same Env may run concurrently in different threads.
+  // I.e., the caller may not assume that background work items are
+  // serialized.
+  virtual void Schedule(
+      void (*function)(void* arg),
+      void* arg) = 0;
+
+  // Start a new thread, invoking "function(arg)" within the new thread.
+  // When "function(arg)" returns, the thread will be destroyed.
+  virtual void StartThread(void (*function)(void* arg), void* arg) = 0;
+
+  // *path is set to a temporary directory that can be used for testing. It may
+  // or many not have just been created. The directory may or may not differ
+  // between runs of the same process, but subsequent calls will return the
+  // same directory.
+  virtual Status GetTestDirectory(std::string* path) = 0;
+
+  // Write an entry to the log file with the specified format.
+  virtual void Logv(WritableFile* log, const char* format, va_list ap) = 0;
+
+  // Returns the number of micro-seconds since some fixed point in time. Only
+  // useful for computing deltas of time.
+  virtual uint64_t NowMicros() = 0;
+
+  // Sleep/delay the thread for the perscribed number of micro-seconds.
+  virtual void SleepForMicroseconds(int micros) = 0;
+
+ private:
+  // No copying allowed
+  Env(const Env&);
+  void operator=(const Env&);
+};
+
+// A file abstraction for reading sequentially through a file
+class SequentialFile {
+ public:
+  SequentialFile() { }
+  virtual ~SequentialFile();
+
+  // Read up to "n" bytes from the file.  "scratch[0..n-1]" may be
+  // written by this routine.  Sets "*result" to the data that was
+  // read (including if fewer than "n" bytes were successfully read).
+  // If an error was encountered, returns a non-OK status.
+  //
+  // REQUIRES: External synchronization
+  virtual Status Read(size_t n, Slice* result, char* scratch) = 0;
+};
+
+// A file abstraction for randomly reading the contents of a file.
+class RandomAccessFile {
+ public:
+  RandomAccessFile() { }
+  virtual ~RandomAccessFile();
+
+  // Read up to "n" bytes from the file starting at "offset".
+  // "scratch[0..n-1]" may be written by this routine.  Sets "*result"
+  // to the data that was read (including if fewer than "n" bytes were
+  // successfully read).  If an error was encountered, returns a
+  // non-OK status.
+  //
+  // Safe for concurrent use by multiple threads.
+  virtual Status Read(uint64_t offset, size_t n, Slice* result,
+                      char* scratch) const = 0;
+};
+
+// A file abstraction for sequential writing.  The implementation
+// must provide buffering since callers may append small fragments
+// at a time to the file.
+class WritableFile {
+ public:
+  WritableFile() { }
+  virtual ~WritableFile();
+
+  virtual Status Append(const Slice& data) = 0;
+  virtual Status Close() = 0;
+  virtual Status Flush() = 0;
+  virtual Status Sync() = 0;
+
+ private:
+  // No copying allowed
+  WritableFile(const WritableFile&);
+  void operator=(const WritableFile&);
+};
+
+// Identifies a locked file.
+class FileLock {
+ public:
+  FileLock() { }
+  virtual ~FileLock();
+ private:
+  // No copying allowed
+  FileLock(const FileLock&);
+  void operator=(const FileLock&);
+};
+
+// Log the specified data to *info_log if info_log is non-NULL.
+extern void Log(Env* env, WritableFile* info_log, const char* format, ...)
+#   if defined(__GNUC__) || defined(__clang__)
+    __attribute__((__format__ (__printf__, 3, 4)))
+#   endif
+    ;
+
+// A utility routine: write "data" to the named file.
+extern Status WriteStringToFile(Env* env, const Slice& data,
+                                const std::string& fname);
+
+// A utility routine: read contents of named file into *data
+extern Status ReadFileToString(Env* env, const std::string& fname,
+                               std::string* data);
+
+// An implementation of Env that forwards all calls to another Env.
+// May be useful to clients who wish to override just part of the
+// functionality of another Env.
+class EnvWrapper : public Env {
+ public:
+  // Initialize an EnvWrapper that delegates all calls to *target
+  explicit EnvWrapper(Env* target) : target_(target) { }
+  virtual ~EnvWrapper();
+
+  // Return the target to which this Env forwards all calls
+  Env* target() const { return target_; }
+
+  // The following text is boilerplate that forwards all methods to target()
+  Status NewSequentialFile(const std::string& f, SequentialFile** r) {
+    return target_->NewSequentialFile(f, r);
+  }
+  Status NewRandomAccessFile(const std::string& f, RandomAccessFile** r) {
+    return target_->NewRandomAccessFile(f, r);
+  }
+  Status NewWritableFile(const std::string& f, WritableFile** r) {
+    return target_->NewWritableFile(f, r);
+  }
+  bool FileExists(const std::string& f) { return target_->FileExists(f); }
+  Status GetChildren(const std::string& dir, std::vector<std::string>* r) {
+    return target_->GetChildren(dir, r);
+  }
+  Status DeleteFile(const std::string& f) { return target_->DeleteFile(f); }
+  Status CreateDir(const std::string& d) { return target_->CreateDir(d); }
+  Status DeleteDir(const std::string& d) { return target_->DeleteDir(d); }
+  Status GetFileSize(const std::string& f, uint64_t* s) {
+    return target_->GetFileSize(f, s);
+  }
+  Status RenameFile(const std::string& s, const std::string& t) {
+    return target_->RenameFile(s, t);
+  }
+  Status LockFile(const std::string& f, FileLock** l) {
+    return target_->LockFile(f, l);
+  }
+  Status UnlockFile(FileLock* l) { return target_->UnlockFile(l); }
+  void Schedule(void (*f)(void*), void* a) {
+    return target_->Schedule(f, a);
+  }
+  void StartThread(void (*f)(void*), void* a) {
+    return target_->StartThread(f, a);
+  }
+  virtual Status GetTestDirectory(std::string* path) {
+    return target_->GetTestDirectory(path);
+  }
+  virtual void Logv(WritableFile* log, const char* format, va_list ap) {
+    return target_->Logv(log, format, ap);
+  }
+  uint64_t NowMicros() {
+    return target_->NowMicros();
+  }
+  void SleepForMicroseconds(int micros) {
+    target_->SleepForMicroseconds(micros);
+  }
+ private:
+  Env* target_;
+};
+
+}
+
+#endif  // STORAGE_LEVELDB_INCLUDE_ENV_H_
diff --git a/include/leveldb/iterator.h b/include/leveldb/iterator.h
new file mode 100644
index 0000000..1866fb5
--- /dev/null
+++ b/include/leveldb/iterator.h
@@ -0,0 +1,95 @@
+// Copyright (c) 2011 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.
+//
+// An iterator yields a sequence of key/value pairs from a source.
+// The following class defines the interface.  Multiple implementations
+// are provided by this library.  In particular, iterators are provided
+// to access the contents of a Table or a DB.
+
+#ifndef STORAGE_LEVELDB_INCLUDE_ITERATOR_H_
+#define STORAGE_LEVELDB_INCLUDE_ITERATOR_H_
+
+#include "leveldb/slice.h"
+#include "leveldb/status.h"
+
+namespace leveldb {
+
+class Iterator {
+ public:
+  Iterator();
+  virtual ~Iterator();
+
+  // An iterator is either positioned at a key/value pair, or
+  // not valid.  This method returns true iff the iterator is valid.
+  virtual bool Valid() const = 0;
+
+  // Position at the first key in the source.  The iterator is Valid()
+  // after this call iff the source is not empty.
+  virtual void SeekToFirst() = 0;
+
+  // Position at the last key in the source.  The iterator is
+  // Valid() after this call iff the source is not empty.
+  virtual void SeekToLast() = 0;
+
+  // Position at the first key in the source that at or past target
+  // The iterator is Valid() after this call iff the source contains
+  // an entry that comes at or past target.
+  virtual void Seek(const Slice& target) = 0;
+
+  // Moves to the next entry in the source.  After this call, Valid() is
+  // true iff the iterator was not positioned at the last entry in the source.
+  // REQUIRES: Valid()
+  virtual void Next() = 0;
+
+  // Moves to the previous entry in the source.  After this call, Valid() is
+  // true iff the iterator was not positioned at the first entry in source.
+  // REQUIRES: Valid()
+  virtual void Prev() = 0;
+
+  // Return the key for the current entry.  The underlying storage for
+  // the returned slice is valid only until the next modification of
+  // the iterator.
+  // REQUIRES: Valid()
+  virtual Slice key() const = 0;
+
+  // Return the value for the current entry.  The underlying storage for
+  // the returned slice is valid only until the next modification of
+  // the iterator.
+  // REQUIRES: !AtEnd() && !AtStart()
+  virtual Slice value() const = 0;
+
+  // If an error has occurred, return it.  Else return an ok status.
+  virtual Status status() const = 0;
+
+  // Clients are allowed to register function/arg1/arg2 triples that
+  // will be invoked when this iterator is destroyed.
+  //
+  // Note that unlike all of the preceding methods, this method is
+  // not abstract and therefore clients should not override it.
+  typedef void (*CleanupFunction)(void* arg1, void* arg2);
+  void RegisterCleanup(CleanupFunction function, void* arg1, void* arg2);
+
+ private:
+  struct Cleanup {
+    CleanupFunction function;
+    void* arg1;
+    void* arg2;
+    Cleanup* next;
+  };
+  Cleanup cleanup_;
+
+  // No copying allowed
+  Iterator(const Iterator&);
+  void operator=(const Iterator&);
+};
+
+// Return an empty iterator (yields nothing).
+extern Iterator* NewEmptyIterator();
+
+// Return an empty iterator with the specified status.
+extern Iterator* NewErrorIterator(const Status& status);
+
+}
+
+#endif  // STORAGE_LEVELDB_INCLUDE_ITERATOR_H_
diff --git a/include/leveldb/options.h b/include/leveldb/options.h
new file mode 100644
index 0000000..87d388e
--- /dev/null
+++ b/include/leveldb/options.h
@@ -0,0 +1,208 @@
+// Copyright (c) 2011 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.
+
+#ifndef STORAGE_LEVELDB_INCLUDE_OPTIONS_H_
+#define STORAGE_LEVELDB_INCLUDE_OPTIONS_H_
+
+#include <stddef.h>
+
+namespace leveldb {
+
+class Cache;
+class Comparator;
+class Env;
+class Snapshot;
+class WritableFile;
+
+// DB contents are stored in a set of blocks, each of which holds a
+// sequence of key,value pairs.  Each block may be compressed before
+// being stored in a file.  The following enum describes which
+// compression method (if any) is used to compress a block.
+enum CompressionType {
+  // NOTE: do not change the values of existing entries, as these are
+  // part of the persistent format on disk.
+  kNoCompression     = 0x0,
+  kSnappyCompression = 0x1,
+};
+
+// Options to control the behavior of a database (passed to DB::Open)
+struct Options {
+  // -------------------
+  // Parameters that affect behavior
+
+  // Comparator used to define the order of keys in the table.
+  // Default: a comparator that uses lexicographic byte-wise ordering
+  //
+  // REQUIRES: The client must ensure that the comparator supplied
+  // here has the same name and orders keys *exactly* the same as the
+  // comparator provided to previous open calls on the same DB.
+  const Comparator* comparator;
+
+  // If true, the database will be created if it is missing.
+  // Default: false
+  bool create_if_missing;
+
+  // If true, an error is raised if the database already exists.
+  // Default: false
+  bool error_if_exists;
+
+  // If true, the implementation will do aggressive checking of the
+  // data it is processing and will stop early if it detects any
+  // errors.  This may have unforeseen ramifications: for example, a
+  // corruption of one DB entry may cause a large number of entries to
+  // become unreadable or for the entire DB to become unopenable.
+  // Default: false
+  bool paranoid_checks;
+
+  // Use the specified object to interact with the environment,
+  // e.g. to read/write files, schedule background work, etc.
+  // Default: Env::Default()
+  Env* env;
+
+  // Any internal progress/error information generated by the db will
+  // be to written to info_log if it is non-NULL, or to a file stored
+  // in the same directory as the DB contents if info_log is NULL.
+  // Default: NULL
+  WritableFile* info_log;
+
+  // -------------------
+  // Parameters that affect performance
+
+  // Amount of data to build up in memory (backed by an unsorted log
+  // on disk) before converting to a sorted on-disk file.
+  //
+  // Larger values increase performance, especially during bulk loads.
+  // Up to two write buffers may be held in memory at the same time,
+  // so you may wish to adjust this parameter to control memory usage.
+  //
+  // Default: 4MB
+  size_t write_buffer_size;
+
+  // Number of open files that can be used by the DB.  You may need to
+  // increase this if your database has a large working set (budget
+  // one open file per 2MB of working set).
+  //
+  // Default: 1000
+  int max_open_files;
+
+  // Handle values larger than "large_value_threshold" bytes
+  // specially, by writing them into their own files (to avoid
+  // compaction overhead) and doing content-based elimination of
+  // duplicate values to save space.
+  //
+  // We recommend against changing this value.
+  //
+  // Default: 64K
+  size_t large_value_threshold;
+
+  // Control over blocks (user data is stored in a set of blocks, and
+  // a block is the unit of reading from disk).
+
+  // If non-NULL, use the specified cache for blocks.
+  // If NULL, leveldb will automatically create and use an 8MB internal cache.
+  // Default: NULL
+  Cache* block_cache;
+
+  // Approximate size of user data packed per block.  Note that the
+  // block size specified here corresponds to uncompressed data.  The
+  // actual size of the unit read from disk may be smaller if
+  // compression is enabled.  This parameter can be changed dynamically.
+  //
+  // Default: 4K
+  int block_size;
+
+  // Number of keys between restart points for delta encoding of keys.
+  // This parameter can be changed dynamically.  Most clients should
+  // leave this parameter alone.
+  //
+  // Default: 16
+  int block_restart_interval;
+
+  // Compress blocks using the specified compression algorithm.  This
+  // parameter can be changed dynamically.
+  //
+  // Default: kSnappyCompression, which gives lightweight but fast
+  // compression.
+  //
+  // Typical speeds of kSnappyCompression on an Intel(R) Core(TM)2 2.4GHz:
+  //    ~200-500MB/s compression
+  //    ~400-800MB/s decompression
+  // Note that these speeds are significantly faster than most
+  // persistent storage speeds, and therefore it is typically never
+  // worth switching to kNoCompression.  Even if the input data is
+  // incompressible, the kSnappyCompression implementation will
+  // efficiently detect that and will switch to uncompressed mode.
+  CompressionType compression;
+
+  // Create an Options object with default values for all fields.
+  Options();
+};
+
+// Options that control read operations
+struct ReadOptions {
+  // If true, all data read from underlying storage will be
+  // verified against corresponding checksums.
+  // Default: false
+  bool verify_checksums;
+
+  // Should the data read for this iteration be cached in memory?
+  // Callers may wish to set this field to false for bulk scans.
+  // Default: true
+  bool fill_cache;
+
+  // If "snapshot" is non-NULL, read as of the supplied snapshot
+  // (which must belong to the DB that is being read and which must
+  // not have been released).  If "snapshot" is NULL, use an impliicit
+  // snapshot of the state at the beginning of this read operation.
+  // Default: NULL
+  const Snapshot* snapshot;
+
+  ReadOptions()
+      : verify_checksums(false),
+        fill_cache(true),
+        snapshot(NULL) {
+  }
+};
+
+// Options that control write operations
+struct WriteOptions {
+  // If true, the write will be flushed from the operating system
+  // buffer cache (by calling WritableFile::Sync()) before the write
+  // is considered complete.  If this flag is true, writes will be
+  // slower.
+  //
+  // If this flag is false, and the machine crashes, some recent
+  // writes may be lost.  Note that if it is just the process that
+  // crashes (i.e., the machine does not reboot), no writes will be
+  // lost even if sync==false.
+  //
+  // In other words, a DB write with sync==false has similar
+  // crash semantics as the "write()" system call.  A DB write
+  // with sync==true has similar crash semantics to a "write()"
+  // system call followed by "fsync()".
+  //
+  // Default: false
+  bool sync;
+
+  // If "post_write_snapshot" is non-NULL, and the write succeeds,
+  // *post_write_snapshot will be modified to point to a snapshot of
+  // the DB state immediately after this write.  The caller must call
+  // DB::ReleaseSnapshot(*post_write_snapshotsnapshot) when the
+  // snapshot is no longer needed.
+  //
+  // If "post_write_snapshot" is non-NULL, and the write fails,
+  // *post_write_snapshot will be set to NULL.
+  //
+  // Default: NULL
+  const Snapshot** post_write_snapshot;
+
+  WriteOptions()
+      : sync(false),
+        post_write_snapshot(NULL) {
+  }
+};
+
+}
+
+#endif  // STORAGE_LEVELDB_INCLUDE_OPTIONS_H_
diff --git a/include/leveldb/slice.h b/include/leveldb/slice.h
new file mode 100644
index 0000000..62cb894
--- /dev/null
+++ b/include/leveldb/slice.h
@@ -0,0 +1,104 @@
+// Copyright (c) 2011 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.
+//
+// Slice is a simple structure containing a pointer into some external
+// storage and a size.  The user of a Slice must ensure that the slice
+// is not used after the corresponding external storage has been
+// deallocated.
+
+#ifndef STORAGE_LEVELDB_INCLUDE_SLICE_H_
+#define STORAGE_LEVELDB_INCLUDE_SLICE_H_
+
+#include <assert.h>
+#include <stddef.h>
+#include <string.h>
+#include <string>
+
+namespace leveldb {
+
+class Slice {
+ public:
+  // Create an empty slice.
+  Slice() : data_(""), size_(0) { }
+
+  // Create a slice that refers to data[0,n-1].
+  Slice(const char* data, size_t n) : data_(data), size_(n) { }
+
+  // Create a slice that refers to the contents of "s"
+  Slice(const std::string& s) : data_(s.data()), size_(s.size()) { }
+
+  // Create a slice that refers to s[0,strlen(s)-1]
+  Slice(const char* s) : data_(s), size_(strlen(s)) { }
+
+  // Return a pointer to the beginning of the referenced data
+  const char* data() const { return data_; }
+
+  // Return the length (in bytes) of the referenced data
+  size_t size() const { return size_; }
+
+  // Return true iff the length of the referenced data is zero
+  bool empty() const { return size_ == 0; }
+
+  // Return the ith byte in the referenced data.
+  // REQUIRES: n < size()
+  char operator[](size_t n) const {
+    assert(n < size());
+    return data_[n];
+  }
+
+  // Change this slice to refer to an empty array
+  void clear() { data_ = ""; size_ = 0; }
+
+  // Drop the first "n" bytes from this slice.
+  void remove_prefix(size_t n) {
+    assert(n <= size());
+    data_ += n;
+    size_ -= n;
+  }
+
+  // Return a string that contains the copy of the referenced data.
+  std::string ToString() const { return std::string(data_, size_); }
+
+  // Three-way comparison.  Returns value:
+  //   <  0 iff "*this" <  "b",
+  //   == 0 iff "*this" == "b",
+  //   >  0 iff "*this" >  "b"
+  int compare(const Slice& b) const;
+
+  // Return true iff "x" is a prefix of "*this"
+  bool starts_with(const Slice& x) const {
+    return ((size_ >= x.size_) &&
+            (memcmp(data_, x.data_, x.size_) == 0));
+  }
+
+ private:
+  const char* data_;
+  size_t size_;
+
+  // Intentionally copyable
+};
+
+inline bool operator==(const Slice& x, const Slice& y) {
+  return ((x.size() == y.size()) &&
+          (memcmp(x.data(), y.data(), x.size()) == 0));
+}
+
+inline bool operator!=(const Slice& x, const Slice& y) {
+  return !(x == y);
+}
+
+inline int Slice::compare(const Slice& b) const {
+  const int min_len = (size_ < b.size_) ? size_ : b.size_;
+  int r = memcmp(data_, b.data_, min_len);
+  if (r == 0) {
+    if (size_ < b.size_) r = -1;
+    else if (size_ > b.size_) r = +1;
+  }
+  return r;
+}
+
+}
+
+
+#endif  // STORAGE_LEVELDB_INCLUDE_SLICE_H_
diff --git a/include/leveldb/status.h b/include/leveldb/status.h
new file mode 100644
index 0000000..47e3edf
--- /dev/null
+++ b/include/leveldb/status.h
@@ -0,0 +1,86 @@
+// Copyright (c) 2011 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.
+//
+// A Status encapsulates the result of an operation.  It may indicate success,
+// or it may indicate an error with an associated error message.
+
+#ifndef STORAGE_LEVELDB_INCLUDE_STATUS_H_
+#define STORAGE_LEVELDB_INCLUDE_STATUS_H_
+
+#include <string>
+#include <utility>
+#include "leveldb/slice.h"
+
+namespace leveldb {
+
+class Status {
+ public:
+  // Create a success status.
+  Status() : state_(NULL) { }
+  ~Status() { delete state_; }
+
+  // Copy the specified status.
+  Status(const Status& s);
+  void operator=(const Status& s);
+
+  // Return a success status.
+  static Status OK() { return Status(); }
+
+  // Return error status of an appropriate type.
+  static Status NotFound(const Slice& msg, const Slice& msg2 = Slice()) {
+    return Status(kNotFound, msg, Slice());
+  }
+  static Status Corruption(const Slice& msg, const Slice& msg2 = Slice()) {
+    return Status(kCorruption, msg, msg2);
+  }
+  static Status NotSupported(const Slice& msg, const Slice& msg2 = Slice()) {
+    return Status(kNotSupported, msg, msg2);
+  }
+  static Status InvalidArgument(const Slice& msg, const Slice& msg2 = Slice()) {
+    return Status(kInvalidArgument, msg, msg2);
+  }
+  static Status IOError(const Slice& msg, const Slice& msg2 = Slice()) {
+    return Status(kIOError, msg, msg2);
+  }
+
+  // Returns true iff the status indicates success.
+  bool ok() const { return (state_ == NULL); }
+
+  // Returns true iff the status indicates a NotFound error.
+  bool IsNotFound() const { return code() == kNotFound; }
+
+  // Return a string representation of this status suitable for printing.
+  // Returns the string "OK" for success.
+  std::string ToString() const;
+
+ private:
+  enum Code {
+    kOk = 0,
+    kNotFound = 1,
+    kCorruption = 2,
+    kNotSupported = 3,
+    kInvalidArgument = 4,
+    kIOError = 5,
+  };
+  Code code() const { return (state_ == NULL) ? kOk : state_->first; }
+
+  Status(Code code, const Slice& msg, const Slice& msg2);
+
+  typedef std::pair<Code, std::string> State;
+  State* state_;
+};
+
+inline Status::Status(const Status& s) {
+  state_ = (s.state_ == NULL) ? NULL : new State(*s.state_);
+}
+inline void Status::operator=(const Status& s) {
+  if (this != &s) {
+    delete state_;
+    state_ = (s.state_ == NULL) ? NULL : new State(*s.state_);
+  }
+}
+
+}
+
+#endif  // STORAGE_LEVELDB_INCLUDE_STATUS_H_
diff --git a/include/leveldb/table.h b/include/leveldb/table.h
new file mode 100644
index 0000000..bd99176
--- /dev/null
+++ b/include/leveldb/table.h
@@ -0,0 +1,69 @@
+// Copyright (c) 2011 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.
+
+#ifndef STORAGE_LEVELDB_INCLUDE_TABLE_H_
+#define STORAGE_LEVELDB_INCLUDE_TABLE_H_
+
+#include <stdint.h>
+#include "leveldb/iterator.h"
+
+namespace leveldb {
+
+class Block;
+class BlockHandle;
+struct Options;
+class RandomAccessFile;
+struct ReadOptions;
+
+// A Table is a sorted map from strings to strings.  Tables are
+// immutable and persistent.
+class Table {
+ public:
+  // Attempt to open the table that is stored in bytes [0..file_size)
+  // of "file", and read the metadata entries necessary to allow
+  // retrieving data from the table.
+  //
+  // If successful, returns ok and sets "*table" to the newly opened
+  // table.  The client should delete "*table" when no longer needed.
+  // If there was an error while initializing the table, sets "*table"
+  // to NULL and returns a non-ok status.  Does not take ownership of
+  // "*source", but the client must ensure that "source" remains live
+  // for the duration of the returned table's lifetime.
+  //
+  // *file must remain live while this Table is in use.
+  static Status Open(const Options& options,
+                     RandomAccessFile* file,
+                     uint64_t file_size,
+                     Table** table);
+
+  ~Table();
+
+  // Returns a new iterator over the table contents.
+  // The result of NewIterator() is initially invalid (caller must
+  // call one of the Seek methods on the iterator before using it).
+  Iterator* NewIterator(const ReadOptions&) const;
+
+  // Given a key, return an approximate byte offset in the file where
+  // the data for that key begins (or would begin if the key were
+  // present in the file).  The returned value is in terms of file
+  // bytes, and so includes effects like compression of the underlying data.
+  // E.g., the approximate offset of the last key in the table will
+  // be close to the file length.
+  uint64_t ApproximateOffsetOf(const Slice& key) const;
+
+ private:
+  struct Rep;
+  Rep* rep_;
+
+  explicit Table(Rep* rep) { rep_ = rep; }
+  static Iterator* BlockReader(void*, const ReadOptions&, const Slice&);
+
+  // No copying allowed
+  Table(const Table&);
+  void operator=(const Table&);
+};
+
+}
+
+#endif  // STORAGE_LEVELDB_INCLUDE_TABLE_H_
diff --git a/include/leveldb/table_builder.h b/include/leveldb/table_builder.h
new file mode 100644
index 0000000..49d2d51
--- /dev/null
+++ b/include/leveldb/table_builder.h
@@ -0,0 +1,86 @@
+// Copyright (c) 2011 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.
+//
+// TableBuilder provides the interface used to build a Table
+// (an immutable and sorted map from keys to values).
+
+#ifndef STORAGE_LEVELDB_INCLUDE_TABLE_BUILDER_H_
+#define STORAGE_LEVELDB_INCLUDE_TABLE_BUILDER_H_
+
+#include <stdint.h>
+#include "leveldb/options.h"
+#include "leveldb/status.h"
+
+namespace leveldb {
+
+class BlockBuilder;
+class BlockHandle;
+class WritableFile;
+
+class TableBuilder {
+ public:
+  // Create a builder that will store the contents of the table it is
+  // building in *file.  Does not close the file.  It is up to the
+  // caller to close the file after calling Finish().
+  TableBuilder(const Options& options, WritableFile* file);
+
+  // REQUIRES: Either Finish() or Abandon() has been called.
+  ~TableBuilder();
+
+  // Change the options used by this builder.  Note: only some of the
+  // option fields can be changed after construction.  If a field is
+  // not allowed to change dynamically and its value in the structure
+  // passed to the constructor is different from its value in the
+  // structure passed to this method, this method will return an error
+  // without changing any fields.
+  Status ChangeOptions(const Options& options);
+
+  // Add key,value to the table being constructed.
+  // REQUIRES: key is after any previously added key according to comparator.
+  // REQUIRES: Finish(), Abandon() have not been called
+  void Add(const Slice& key, const Slice& value);
+
+  // Advanced operation: flush any buffered key/value pairs to file.
+  // Can be used to ensure that two adjacent entries never live in
+  // the same data block.  Most clients should not need to use this method.
+  // REQUIRES: Finish(), Abandon() have not been called
+  void Flush();
+
+  // Return non-ok iff some error has been detected.
+  Status status() const;
+
+  // Finish building the table.  Stops using the file passed to the
+  // constructor after this function returns.
+  // REQUIRES: Finish(), Abandon() have not been called
+  Status Finish();
+
+  // Indicate that the contents of this builder should be abandoned.  Stops
+  // using the file passed to the constructor after this function returns.
+  // If the caller is not going to call Finish(), it must call Abandon()
+  // before destroying this builder.
+  // REQUIRES: Finish(), Abandon() have not been called
+  void Abandon();
+
+  // Number of calls to Add() so far.
+  uint64_t NumEntries() const;
+
+  // Size of the file generated so far.  If invoked after a successful
+  // Finish() call, returns the size of the final generated file.
+  uint64_t FileSize() const;
+
+ private:
+  bool ok() const { return status().ok(); }
+  void WriteBlock(BlockBuilder* block, BlockHandle* handle);
+
+  struct Rep;
+  Rep* rep_;
+
+  // No copying allowed
+  TableBuilder(const TableBuilder&);
+  void operator=(const TableBuilder&);
+};
+
+}
+
+#endif  // STORAGE_LEVELDB_INCLUDE_TABLE_BUILDER_H_
diff --git a/include/leveldb/write_batch.h b/include/leveldb/write_batch.h
new file mode 100644
index 0000000..3411952
--- /dev/null
+++ b/include/leveldb/write_batch.h
@@ -0,0 +1,49 @@
+// Copyright (c) 2011 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.
+//
+// WriteBatch holds a collection of updates to apply atomically to a DB.
+//
+// The updates are applied in the order in which they are added
+// to the WriteBatch.  For example, the value of "key" will be "v3"
+// after the following batch is written:
+//
+//    batch.Put("key", "v1");
+//    batch.Delete("key");
+//    batch.Put("key", "v2");
+//    batch.Put("key", "v3");
+
+#ifndef STORAGE_LEVELDB_INCLUDE_WRITE_BATCH_H_
+#define STORAGE_LEVELDB_INCLUDE_WRITE_BATCH_H_
+
+#include <string>
+
+namespace leveldb {
+
+class Slice;
+
+class WriteBatch {
+ public:
+  WriteBatch();
+  ~WriteBatch();
+
+  // Store the mapping "key->value" in the database.
+  void Put(const Slice& key, const Slice& value);
+
+  // If the database contains a mapping for "key", erase it.  Else do nothing.
+  void Delete(const Slice& key);
+
+  // Clear all updates buffered in this batch.
+  void Clear();
+
+ private:
+  friend class WriteBatchInternal;
+
+  std::string rep_;  // See comment in write_batch.cc for the format of rep_
+
+  // Intentionally copyable
+};
+
+}
+
+#endif  // STORAGE_LEVELDB_INCLUDE_WRITE_BATCH_H_