leveldb-ruby 0.1

data/leveldb/port/sha1_test.cc

@@ -0,0 +1,39 @@
+// 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.
+
+#include "port/port.h"
+#include "util/testharness.h"
+
+namespace leveldb {
+namespace port {
+
+class SHA1 { };
+
+static std::string TestSHA1(const char* data, size_t len) {
+  char hash_val[20];
+  SHA1_Hash(data, len, hash_val);
+  char buf[41];
+  for (int i = 0; i < 20; i++) {
+    snprintf(buf + i * 2, 41 - i * 2,
+             "%02x",
+             static_cast<unsigned int>(static_cast<unsigned char>(
+                 hash_val[i])));
+  }
+  return std::string(buf, 40);
+}
+
+TEST(SHA1, Simple) {
+  ASSERT_EQ("da39a3ee5e6b4b0d3255bfef95601890afd80709", TestSHA1("", 0));
+  ASSERT_EQ("aaf4c61ddcc5e8a2dabede0f3b482cd9aea9434d", TestSHA1("hello", 5));
+  std::string x(10000, 'x');
+  ASSERT_EQ("f8c5cde791c5056cf515881e701c8a9ecb439a75",
+            TestSHA1(x.data(), x.size()));
+}
+
+}
+}
+
+int main(int argc, char** argv) {
+  return leveldb::test::RunAllTests();
+}

data/leveldb/port/win/stdint.h

@@ -0,0 +1,24 @@
+// 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.
+
+// MSVC didn't ship with this file until the 2010 version.
+
+#ifndef STORAGE_LEVELDB_PORT_WIN_STDINT_H_
+#define STORAGE_LEVELDB_PORT_WIN_STDINT_H_
+
+#if !defined(_MSC_VER)
+#error This file should only be included when compiling with MSVC.
+#endif
+
+// Define C99 equivalent types.
+typedef signed char           int8_t;
+typedef signed short          int16_t;
+typedef signed int            int32_t;
+typedef signed long long      int64_t;
+typedef unsigned char         uint8_t;
+typedef unsigned short        uint16_t;
+typedef unsigned int          uint32_t;
+typedef unsigned long long    uint64_t;
+
+#endif  // STORAGE_LEVELDB_PORT_WIN_STDINT_H_

data/leveldb/table/block.cc

@@ -0,0 +1,263 @@
+// 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.
+//
+// Decodes the blocks generated by block_builder.cc.
+
+#include "table/block.h"
+
+#include <vector>
+#include <algorithm>
+#include "leveldb/comparator.h"
+#include "util/coding.h"
+#include "util/logging.h"
+
+namespace leveldb {
+
+inline uint32_t Block::NumRestarts() const {
+  assert(size_ >= 2*sizeof(uint32_t));
+  return DecodeFixed32(data_ + size_ - sizeof(uint32_t));
+}
+
+Block::Block(const char* data, size_t size)
+    : data_(data),
+      size_(size) {
+  if (size_ < sizeof(uint32_t)) {
+    size_ = 0;  // Error marker
+  } else {
+    restart_offset_ = size_ - (1 + NumRestarts()) * sizeof(uint32_t);
+    if (restart_offset_ > size_ - sizeof(uint32_t)) {
+      // The size is too small for NumRestarts() and therefore
+      // restart_offset_ wrapped around.
+      size_ = 0;
+    }
+  }
+}
+
+Block::~Block() {
+  delete[] data_;
+}
+
+// Helper routine: decode the next block entry starting at "p",
+// storing the number of shared key bytes, non_shared key bytes,
+// and the length of the value in "*shared", "*non_shared", and
+// "*value_length", respectively.  Will not derefence past "limit".
+//
+// If any errors are detected, returns NULL.  Otherwise, returns a
+// pointer to the key delta (just past the three decoded values).
+static inline const char* DecodeEntry(const char* p, const char* limit,
+                                      uint32_t* shared,
+                                      uint32_t* non_shared,
+                                      uint32_t* value_length) {
+  if (limit - p < 3) return NULL;
+  *shared = reinterpret_cast<const unsigned char*>(p)[0];
+  *non_shared = reinterpret_cast<const unsigned char*>(p)[1];
+  *value_length = reinterpret_cast<const unsigned char*>(p)[2];
+  if ((*shared | *non_shared | *value_length) < 128) {
+    // Fast path: all three values are encoded in one byte each
+    p += 3;
+  } else {
+    if ((p = GetVarint32Ptr(p, limit, shared)) == NULL) return NULL;
+    if ((p = GetVarint32Ptr(p, limit, non_shared)) == NULL) return NULL;
+    if ((p = GetVarint32Ptr(p, limit, value_length)) == NULL) return NULL;
+  }
+
+  if (static_cast<uint32_t>(limit - p) < (*non_shared + *value_length)) {
+    return NULL;
+  }
+  return p;
+}
+
+class Block::Iter : public Iterator {
+ private:
+  const Comparator* const comparator_;
+  const char* const data_;      // underlying block contents
+  uint32_t const restarts_;     // Offset of restart array (list of fixed32)
+  uint32_t const num_restarts_; // Number of uint32_t entries in restart array
+
+  // current_ is offset in data_ of current entry.  >= restarts_ if !Valid
+  uint32_t current_;
+  uint32_t restart_index_;  // Index of restart block in which current_ falls
+  std::string key_;
+  Slice value_;
+  Status status_;
+
+  inline int Compare(const Slice& a, const Slice& b) const {
+    return comparator_->Compare(a, b);
+  }
+
+  // Return the offset in data_ just past the end of the current entry.
+  inline uint32_t NextEntryOffset() const {
+    return (value_.data() + value_.size()) - data_;
+  }
+
+  uint32_t GetRestartPoint(uint32_t index) {
+    assert(index < num_restarts_);
+    return DecodeFixed32(data_ + restarts_ + index * sizeof(uint32_t));
+  }
+
+  void SeekToRestartPoint(uint32_t index) {
+    key_.clear();
+    restart_index_ = index;
+    // current_ will be fixed by ParseNextKey();
+
+    // ParseNextKey() starts at the end of value_, so set value_ accordingly
+    uint32_t offset = GetRestartPoint(index);
+    value_ = Slice(data_ + offset, 0);
+  }
+
+ public:
+  Iter(const Comparator* comparator,
+       const char* data,
+       uint32_t restarts,
+       uint32_t num_restarts)
+      : comparator_(comparator),
+        data_(data),
+        restarts_(restarts),
+        num_restarts_(num_restarts),
+        current_(restarts_),
+        restart_index_(num_restarts_) {
+    assert(num_restarts_ > 0);
+  }
+
+  virtual bool Valid() const { return current_ < restarts_; }
+  virtual Status status() const { return status_; }
+  virtual Slice key() const {
+    assert(Valid());
+    return key_;
+  }
+  virtual Slice value() const {
+    assert(Valid());
+    return value_;
+  }
+
+  virtual void Next() {
+    assert(Valid());
+    ParseNextKey();
+  }
+
+  virtual void Prev() {
+    assert(Valid());
+
+    // Scan backwards to a restart point before current_
+    const uint32_t original = current_;
+    while (GetRestartPoint(restart_index_) >= original) {
+      if (restart_index_ == 0) {
+        // No more entries
+        current_ = restarts_;
+        restart_index_ = num_restarts_;
+        return;
+      }
+      restart_index_--;
+    }
+
+    SeekToRestartPoint(restart_index_);
+    do {
+      // Loop until end of current entry hits the start of original entry
+    } while (ParseNextKey() && NextEntryOffset() < original);
+  }
+
+  virtual void Seek(const Slice& target) {
+    // Binary search in restart array to find the first restart point
+    // with a key >= target
+    uint32_t left = 0;
+    uint32_t right = num_restarts_ - 1;
+    while (left < right) {
+      uint32_t mid = (left + right + 1) / 2;
+      uint32_t region_offset = GetRestartPoint(mid);
+      uint32_t shared, non_shared, value_length;
+      const char* key_ptr = DecodeEntry(data_ + region_offset,
+                                        data_ + restarts_,
+                                        &shared, &non_shared, &value_length);
+      if (key_ptr == NULL || (shared != 0)) {
+        CorruptionError();
+        return;
+      }
+      Slice mid_key(key_ptr, non_shared);
+      if (Compare(mid_key, target) < 0) {
+        // Key at "mid" is smaller than "target".  Therefore all
+        // blocks before "mid" are uninteresting.
+        left = mid;
+      } else {
+        // Key at "mid" is >= "target".  Therefore all blocks at or
+        // after "mid" are uninteresting.
+        right = mid - 1;
+      }
+    }
+
+    // Linear search (within restart block) for first key >= target
+    SeekToRestartPoint(left);
+    while (true) {
+      if (!ParseNextKey()) {
+        return;
+      }
+      if (Compare(key_, target) >= 0) {
+        return;
+      }
+    }
+  }
+
+  virtual void SeekToFirst() {
+    SeekToRestartPoint(0);
+    ParseNextKey();
+  }
+
+  virtual void SeekToLast() {
+    SeekToRestartPoint(num_restarts_ - 1);
+    while (ParseNextKey() && NextEntryOffset() < restarts_) {
+      // Keep skipping
+    }
+  }
+
+ private:
+  void CorruptionError() {
+    current_ = restarts_;
+    restart_index_ = num_restarts_;
+    status_ = Status::Corruption("bad entry in block");
+    key_.clear();
+    value_.clear();
+  }
+
+  bool ParseNextKey() {
+    current_ = NextEntryOffset();
+    const char* p = data_ + current_;
+    const char* limit = data_ + restarts_;  // Restarts come right after data
+    if (p >= limit) {
+      // No more entries to return.  Mark as invalid.
+      current_ = restarts_;
+      restart_index_ = num_restarts_;
+      return false;
+    }
+
+    // Decode next entry
+    uint32_t shared, non_shared, value_length;
+    p = DecodeEntry(p, limit, &shared, &non_shared, &value_length);
+    if (p == NULL || key_.size() < shared) {
+      CorruptionError();
+      return false;
+    } else {
+      key_.resize(shared);
+      key_.append(p, non_shared);
+      value_ = Slice(p + non_shared, value_length);
+      while (restart_index_ + 1 < num_restarts_ &&
+             GetRestartPoint(restart_index_ + 1) < current_) {
+        ++restart_index_;
+      }
+      return true;
+    }
+  }
+};
+
+Iterator* Block::NewIterator(const Comparator* cmp) {
+  if (size_ < 2*sizeof(uint32_t)) {
+    return NewErrorIterator(Status::Corruption("bad block contents"));
+  }
+  const uint32_t num_restarts = NumRestarts();
+  if (num_restarts == 0) {
+    return NewEmptyIterator();
+  } else {
+    return new Iter(cmp, data_, restart_offset_, num_restarts);
+  }
+}
+
+}

data/leveldb/table/block.h

@@ -0,0 +1,43 @@
+// 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_TABLE_BLOCK_H_
+#define STORAGE_LEVELDB_TABLE_BLOCK_H_
+
+#include <stddef.h>
+#include <stdint.h>
+#include "leveldb/iterator.h"
+
+namespace leveldb {
+
+class Comparator;
+
+class Block {
+ public:
+  // Initialize the block with the specified contents.
+  // Takes ownership of data[] and will delete[] it when done.
+  Block(const char* data, size_t size);
+
+  ~Block();
+
+  size_t size() const { return size_; }
+  Iterator* NewIterator(const Comparator* comparator);
+
+ private:
+  uint32_t NumRestarts() const;
+
+  const char* data_;
+  size_t size_;
+  uint32_t restart_offset_;     // Offset in data_ of restart array
+
+  // No copying allowed
+  Block(const Block&);
+  void operator=(const Block&);
+
+  class Iter;
+};
+
+}
+
+#endif  // STORAGE_LEVELDB_TABLE_BLOCK_H_

data/leveldb/table/block_builder.cc

@@ -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.
+//
+// BlockBuilder generates blocks where keys are prefix-compressed:
+//
+// When we store a key, we drop the prefix shared with the previous
+// string.  This helps reduce the space requirement significantly.
+// Furthermore, once every K keys, we do not apply the prefix
+// compression and store the entire key.  We call this a "restart
+// point".  The tail end of the block stores the offsets of all of the
+// restart points, and can be used to do a binary search when looking
+// for a particular key.  Values are stored as-is (without compression)
+// immediately following the corresponding key.
+//
+// An entry for a particular key-value pair has the form:
+//     shared_bytes: varint32
+//     unshared_bytes: varint32
+//     value_length: varint32
+//     key_delta: char[unshared_bytes]
+//     value: char[value_length]
+// shared_bytes == 0 for restart points.
+//
+// The trailer of the block has the form:
+//     restarts: uint32[num_restarts]
+//     num_restarts: uint32
+// restarts[i] contains the offset within the block of the ith restart point.
+
+#include "table/block_builder.h"
+
+#include <algorithm>
+#include <assert.h>
+#include "leveldb/comparator.h"
+#include "leveldb/table_builder.h"
+#include "util/coding.h"
+
+namespace leveldb {
+
+BlockBuilder::BlockBuilder(const Options* options)
+    : options_(options),
+      restarts_(),
+      counter_(0),
+      finished_(false) {
+  assert(options->block_restart_interval >= 1);
+  restarts_.push_back(0);       // First restart point is at offset 0
+}
+
+void BlockBuilder::Reset() {
+  buffer_.clear();
+  restarts_.clear();
+  restarts_.push_back(0);       // First restart point is at offset 0
+  counter_ = 0;
+  finished_ = false;
+  last_key_.clear();
+}
+
+size_t BlockBuilder::CurrentSizeEstimate() const {
+  return (buffer_.size() +                        // Raw data buffer
+          restarts_.size() * sizeof(uint32_t) +   // Restart array
+          sizeof(uint32_t));                      // Restart array length
+}
+
+Slice BlockBuilder::Finish() {
+  // Append restart array
+  for (size_t i = 0; i < restarts_.size(); i++) {
+    PutFixed32(&buffer_, restarts_[i]);
+  }
+  PutFixed32(&buffer_, restarts_.size());
+  finished_ = true;
+  return Slice(buffer_);
+}
+
+void BlockBuilder::Add(const Slice& key, const Slice& value) {
+  Slice last_key_piece(last_key_);
+  assert(!finished_);
+  assert(counter_ <= options_->block_restart_interval);
+  assert(buffer_.empty() // No values yet?
+         || options_->comparator->Compare(key, last_key_piece) > 0);
+  size_t shared = 0;
+  if (counter_ < options_->block_restart_interval) {
+    // See how much sharing to do with previous string
+    const size_t min_length = std::min(last_key_piece.size(), key.size());
+    while ((shared < min_length) && (last_key_piece[shared] == key[shared])) {
+      shared++;
+    }
+  } else {
+    // Restart compression
+    restarts_.push_back(buffer_.size());
+    counter_ = 0;
+  }
+  const size_t non_shared = key.size() - shared;
+
+  // Add "<shared><non_shared><value_size>" to buffer_
+  PutVarint32(&buffer_, shared);
+  PutVarint32(&buffer_, non_shared);
+  PutVarint32(&buffer_, value.size());
+
+  // Add string delta to buffer_ followed by value
+  buffer_.append(key.data() + shared, non_shared);
+  buffer_.append(value.data(), value.size());
+
+  // Update state
+  last_key_.resize(shared);
+  last_key_.append(key.data() + shared, non_shared);
+  assert(Slice(last_key_) == key);
+  counter_++;
+}
+
+}