leveldb 0.0.1

data/ext/leveldb/include/leveldb/options.h

@@ -0,0 +1,195 @@
+// 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 FilterPolicy;
+class Logger;
+class Snapshot;
+
+// 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 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
+  Logger* 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.
+  // Also, a larger write buffer will result in a longer recovery time
+  // the next time the database is opened.
+  //
+  // 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;
+
+  // 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
+  size_t 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;
+
+  // If non-NULL, use the specified filter policy to reduce disk reads.
+  // Many applications will benefit from passing the result of
+  // NewBloomFilterPolicy() here.
+  //
+  // Default: NULL
+  const FilterPolicy* filter_policy;
+
+  // 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;
+
+  WriteOptions()
+      : sync(false) {
+  }
+};
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_INCLUDE_OPTIONS_H_

data/ext/leveldb/include/leveldb/slice.h

@@ -0,0 +1,109 @@
+// 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.
+//
+// Multiple threads can invoke const methods on a Slice without
+// external synchronization, but if any of the threads may call a
+// non-const method, all threads accessing the same Slice must use
+// external synchronization.
+
+#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 d[0,n-1].
+  Slice(const char* d, size_t n) : data_(d), 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;
+}
+
+}  // namespace leveldb
+
+
+#endif  // STORAGE_LEVELDB_INCLUDE_SLICE_H_

data/ext/leveldb/include/leveldb/status.h

@@ -0,0 +1,106 @@
+// 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.
+//
+// Multiple threads can invoke const methods on a Status without
+// external synchronization, but if any of the threads may call a
+// non-const method, all threads accessing the same Status must use
+// external synchronization.
+
+#ifndef STORAGE_LEVELDB_INCLUDE_STATUS_H_
+#define STORAGE_LEVELDB_INCLUDE_STATUS_H_
+
+#include <string>
+#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, msg2);
+  }
+  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; }
+
+  // Returns true iff the status indicates a Corruption error.
+  bool IsCorruption() const { return code() == kCorruption; }
+
+  // Returns true iff the status indicates an IOError.
+  bool IsIOError() const { return code() == kIOError; }
+
+  // Return a string representation of this status suitable for printing.
+  // Returns the string "OK" for success.
+  std::string ToString() const;
+
+ private:
+  // OK status has a NULL state_.  Otherwise, state_ is a new[] array
+  // of the following form:
+  //    state_[0..3] == length of message
+  //    state_[4]    == code
+  //    state_[5..]  == message
+  const char* state_;
+
+  enum Code {
+    kOk = 0,
+    kNotFound = 1,
+    kCorruption = 2,
+    kNotSupported = 3,
+    kInvalidArgument = 4,
+    kIOError = 5
+  };
+
+  Code code() const {
+    return (state_ == NULL) ? kOk : static_cast<Code>(state_[4]);
+  }
+
+  Status(Code code, const Slice& msg, const Slice& msg2);
+  static const char* CopyState(const char* s);
+};
+
+inline Status::Status(const Status& s) {
+  state_ = (s.state_ == NULL) ? NULL : CopyState(s.state_);
+}
+inline void Status::operator=(const Status& s) {
+  // The following condition catches both aliasing (when this == &s),
+  // and the common case where both s and *this are ok.
+  if (state_ != s.state_) {
+    delete[] state_;
+    state_ = (s.state_ == NULL) ? NULL : CopyState(s.state_);
+  }
+}
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_INCLUDE_STATUS_H_

data/ext/leveldb/include/leveldb/table.h

@@ -0,0 +1,85 @@
+// 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;
+class Footer;
+struct Options;
+class RandomAccessFile;
+struct ReadOptions;
+class TableCache;
+
+// A Table is a sorted map from strings to strings.  Tables are
+// immutable and persistent.  A Table may be safely accessed from
+// multiple threads without external synchronization.
+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&);
+
+  // Calls (*handle_result)(arg, ...) with the entry found after a call
+  // to Seek(key).  May not make such a call if filter policy says
+  // that key is not present.
+  friend class TableCache;
+  Status InternalGet(
+      const ReadOptions&, const Slice& key,
+      void* arg,
+      void (*handle_result)(void* arg, const Slice& k, const Slice& v));
+
+
+  void ReadMeta(const Footer& footer);
+  void ReadFilter(const Slice& filter_handle_value);
+
+  // No copying allowed
+  Table(const Table&);
+  void operator=(const Table&);
+};
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_INCLUDE_TABLE_H_

data/ext/leveldb/include/leveldb/table_builder.h

@@ -0,0 +1,92 @@
+// 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).
+//
+// Multiple threads can invoke const methods on a TableBuilder without
+// external synchronization, but if any of the threads may call a
+// non-const method, all threads accessing the same TableBuilder must use
+// external synchronization.
+
+#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);
+  void WriteRawBlock(const Slice& data, CompressionType, BlockHandle* handle);
+
+  struct Rep;
+  Rep* rep_;
+
+  // No copying allowed
+  TableBuilder(const TableBuilder&);
+  void operator=(const TableBuilder&);
+};
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_INCLUDE_TABLE_BUILDER_H_

data/ext/leveldb/include/leveldb/write_batch.h

@@ -0,0 +1,64 @@
+// 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");
+//
+// Multiple threads can invoke const methods on a WriteBatch without
+// external synchronization, but if any of the threads may call a
+// non-const method, all threads accessing the same WriteBatch must use
+// external synchronization.
+
+#ifndef STORAGE_LEVELDB_INCLUDE_WRITE_BATCH_H_
+#define STORAGE_LEVELDB_INCLUDE_WRITE_BATCH_H_
+
+#include <string>
+#include "leveldb/status.h"
+
+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();
+
+  // Support for iterating over the contents of a batch.
+  class Handler {
+   public:
+    virtual ~Handler();
+    virtual void Put(const Slice& key, const Slice& value) = 0;
+    virtual void Delete(const Slice& key) = 0;
+  };
+  Status Iterate(Handler* handler) const;
+
+ private:
+  friend class WriteBatchInternal;
+
+  std::string rep_;  // See comment in write_batch.cc for the format of rep_
+
+  // Intentionally copyable
+};
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_INCLUDE_WRITE_BATCH_H_