filiptepper-leveldb-ruby 0.14

data/leveldb/db/dbformat.cc

@@ -0,0 +1,140 @@
+// 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 <stdio.h>
+#include "db/dbformat.h"
+#include "port/port.h"
+#include "util/coding.h"
+
+namespace leveldb {
+
+static uint64_t PackSequenceAndType(uint64_t seq, ValueType t) {
+  assert(seq <= kMaxSequenceNumber);
+  assert(t <= kValueTypeForSeek);
+  return (seq << 8) | t;
+}
+
+void AppendInternalKey(std::string* result, const ParsedInternalKey& key) {
+  result->append(key.user_key.data(), key.user_key.size());
+  PutFixed64(result, PackSequenceAndType(key.sequence, key.type));
+}
+
+std::string ParsedInternalKey::DebugString() const {
+  char buf[50];
+  snprintf(buf, sizeof(buf), "' @ %llu : %d",
+           (unsigned long long) sequence,
+           int(type));
+  std::string result = "'";
+  result += user_key.ToString();
+  result += buf;
+  return result;
+}
+
+std::string InternalKey::DebugString() const {
+  std::string result;
+  ParsedInternalKey parsed;
+  if (ParseInternalKey(rep_, &parsed)) {
+    result = parsed.DebugString();
+  } else {
+    result = "(bad)";
+    result.append(EscapeString(rep_));
+  }
+  return result;
+}
+
+const char* InternalKeyComparator::Name() const {
+  return "leveldb.InternalKeyComparator";
+}
+
+int InternalKeyComparator::Compare(const Slice& akey, const Slice& bkey) const {
+  // Order by:
+  //    increasing user key (according to user-supplied comparator)
+  //    decreasing sequence number
+  //    decreasing type (though sequence# should be enough to disambiguate)
+  int r = user_comparator_->Compare(ExtractUserKey(akey), ExtractUserKey(bkey));
+  if (r == 0) {
+    const uint64_t anum = DecodeFixed64(akey.data() + akey.size() - 8);
+    const uint64_t bnum = DecodeFixed64(bkey.data() + bkey.size() - 8);
+    if (anum > bnum) {
+      r = -1;
+    } else if (anum < bnum) {
+      r = +1;
+    }
+  }
+  return r;
+}
+
+void InternalKeyComparator::FindShortestSeparator(
+      std::string* start,
+      const Slice& limit) const {
+  // Attempt to shorten the user portion of the key
+  Slice user_start = ExtractUserKey(*start);
+  Slice user_limit = ExtractUserKey(limit);
+  std::string tmp(user_start.data(), user_start.size());
+  user_comparator_->FindShortestSeparator(&tmp, user_limit);
+  if (tmp.size() < user_start.size() &&
+      user_comparator_->Compare(user_start, tmp) < 0) {
+    // User key has become shorter physically, but larger logically.
+    // Tack on the earliest possible number to the shortened user key.
+    PutFixed64(&tmp, PackSequenceAndType(kMaxSequenceNumber,kValueTypeForSeek));
+    assert(this->Compare(*start, tmp) < 0);
+    assert(this->Compare(tmp, limit) < 0);
+    start->swap(tmp);
+  }
+}
+
+void InternalKeyComparator::FindShortSuccessor(std::string* key) const {
+  Slice user_key = ExtractUserKey(*key);
+  std::string tmp(user_key.data(), user_key.size());
+  user_comparator_->FindShortSuccessor(&tmp);
+  if (tmp.size() < user_key.size() &&
+      user_comparator_->Compare(user_key, tmp) < 0) {
+    // User key has become shorter physically, but larger logically.
+    // Tack on the earliest possible number to the shortened user key.
+    PutFixed64(&tmp, PackSequenceAndType(kMaxSequenceNumber,kValueTypeForSeek));
+    assert(this->Compare(*key, tmp) < 0);
+    key->swap(tmp);
+  }
+}
+
+const char* InternalFilterPolicy::Name() const {
+  return user_policy_->Name();
+}
+
+void InternalFilterPolicy::CreateFilter(const Slice* keys, int n,
+                                        std::string* dst) const {
+  // We rely on the fact that the code in table.cc does not mind us
+  // adjusting keys[].
+  Slice* mkey = const_cast<Slice*>(keys);
+  for (int i = 0; i < n; i++) {
+    mkey[i] = ExtractUserKey(keys[i]);
+    // TODO(sanjay): Suppress dups?
+  }
+  user_policy_->CreateFilter(keys, n, dst);
+}
+
+bool InternalFilterPolicy::KeyMayMatch(const Slice& key, const Slice& f) const {
+  return user_policy_->KeyMayMatch(ExtractUserKey(key), f);
+}
+
+LookupKey::LookupKey(const Slice& user_key, SequenceNumber s) {
+  size_t usize = user_key.size();
+  size_t needed = usize + 13;  // A conservative estimate
+  char* dst;
+  if (needed <= sizeof(space_)) {
+    dst = space_;
+  } else {
+    dst = new char[needed];
+  }
+  start_ = dst;
+  dst = EncodeVarint32(dst, usize + 8);
+  kstart_ = dst;
+  memcpy(dst, user_key.data(), usize);
+  dst += usize;
+  EncodeFixed64(dst, PackSequenceAndType(s, kValueTypeForSeek));
+  dst += 8;
+  end_ = dst;
+}
+
+}  // namespace leveldb

data/leveldb/db/dbformat.h

@@ -0,0 +1,227 @@
+// 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_DB_FORMAT_H_
+#define STORAGE_LEVELDB_DB_FORMAT_H_
+
+#include <stdio.h>
+#include "leveldb/comparator.h"
+#include "leveldb/db.h"
+#include "leveldb/filter_policy.h"
+#include "leveldb/slice.h"
+#include "leveldb/table_builder.h"
+#include "util/coding.h"
+#include "util/logging.h"
+
+namespace leveldb {
+
+// Grouping of constants.  We may want to make some of these
+// parameters set via options.
+namespace config {
+static const int kNumLevels = 7;
+
+// Level-0 compaction is started when we hit this many files.
+static const int kL0_CompactionTrigger = 4;
+
+// Soft limit on number of level-0 files.  We slow down writes at this point.
+static const int kL0_SlowdownWritesTrigger = 8;
+
+// Maximum number of level-0 files.  We stop writes at this point.
+static const int kL0_StopWritesTrigger = 12;
+
+// Maximum level to which a new compacted memtable is pushed if it
+// does not create overlap.  We try to push to level 2 to avoid the
+// relatively expensive level 0=>1 compactions and to avoid some
+// expensive manifest file operations.  We do not push all the way to
+// the largest level since that can generate a lot of wasted disk
+// space if the same key space is being repeatedly overwritten.
+static const int kMaxMemCompactLevel = 2;
+
+}  // namespace config
+
+class InternalKey;
+
+// Value types encoded as the last component of internal keys.
+// DO NOT CHANGE THESE ENUM VALUES: they are embedded in the on-disk
+// data structures.
+enum ValueType {
+  kTypeDeletion = 0x0,
+  kTypeValue = 0x1
+};
+// kValueTypeForSeek defines the ValueType that should be passed when
+// constructing a ParsedInternalKey object for seeking to a particular
+// sequence number (since we sort sequence numbers in decreasing order
+// and the value type is embedded as the low 8 bits in the sequence
+// number in internal keys, we need to use the highest-numbered
+// ValueType, not the lowest).
+static const ValueType kValueTypeForSeek = kTypeValue;
+
+typedef uint64_t SequenceNumber;
+
+// We leave eight bits empty at the bottom so a type and sequence#
+// can be packed together into 64-bits.
+static const SequenceNumber kMaxSequenceNumber =
+    ((0x1ull << 56) - 1);
+
+struct ParsedInternalKey {
+  Slice user_key;
+  SequenceNumber sequence;
+  ValueType type;
+
+  ParsedInternalKey() { }  // Intentionally left uninitialized (for speed)
+  ParsedInternalKey(const Slice& u, const SequenceNumber& seq, ValueType t)
+      : user_key(u), sequence(seq), type(t) { }
+  std::string DebugString() const;
+};
+
+// Return the length of the encoding of "key".
+inline size_t InternalKeyEncodingLength(const ParsedInternalKey& key) {
+  return key.user_key.size() + 8;
+}
+
+// Append the serialization of "key" to *result.
+extern void AppendInternalKey(std::string* result,
+                              const ParsedInternalKey& key);
+
+// Attempt to parse an internal key from "internal_key".  On success,
+// stores the parsed data in "*result", and returns true.
+//
+// On error, returns false, leaves "*result" in an undefined state.
+extern bool ParseInternalKey(const Slice& internal_key,
+                             ParsedInternalKey* result);
+
+// Returns the user key portion of an internal key.
+inline Slice ExtractUserKey(const Slice& internal_key) {
+  assert(internal_key.size() >= 8);
+  return Slice(internal_key.data(), internal_key.size() - 8);
+}
+
+inline ValueType ExtractValueType(const Slice& internal_key) {
+  assert(internal_key.size() >= 8);
+  const size_t n = internal_key.size();
+  uint64_t num = DecodeFixed64(internal_key.data() + n - 8);
+  unsigned char c = num & 0xff;
+  return static_cast<ValueType>(c);
+}
+
+// A comparator for internal keys that uses a specified comparator for
+// the user key portion and breaks ties by decreasing sequence number.
+class InternalKeyComparator : public Comparator {
+ private:
+  const Comparator* user_comparator_;
+ public:
+  explicit InternalKeyComparator(const Comparator* c) : user_comparator_(c) { }
+  virtual const char* Name() const;
+  virtual int Compare(const Slice& a, const Slice& b) const;
+  virtual void FindShortestSeparator(
+      std::string* start,
+      const Slice& limit) const;
+  virtual void FindShortSuccessor(std::string* key) const;
+
+  const Comparator* user_comparator() const { return user_comparator_; }
+
+  int Compare(const InternalKey& a, const InternalKey& b) const;
+};
+
+// Filter policy wrapper that converts from internal keys to user keys
+class InternalFilterPolicy : public FilterPolicy {
+ private:
+  const FilterPolicy* const user_policy_;
+ public:
+  explicit InternalFilterPolicy(const FilterPolicy* p) : user_policy_(p) { }
+  virtual const char* Name() const;
+  virtual void CreateFilter(const Slice* keys, int n, std::string* dst) const;
+  virtual bool KeyMayMatch(const Slice& key, const Slice& filter) const;
+};
+
+// Modules in this directory should keep internal keys wrapped inside
+// the following class instead of plain strings so that we do not
+// incorrectly use string comparisons instead of an InternalKeyComparator.
+class InternalKey {
+ private:
+  std::string rep_;
+ public:
+  InternalKey() { }   // Leave rep_ as empty to indicate it is invalid
+  InternalKey(const Slice& user_key, SequenceNumber s, ValueType t) {
+    AppendInternalKey(&rep_, ParsedInternalKey(user_key, s, t));
+  }
+
+  void DecodeFrom(const Slice& s) { rep_.assign(s.data(), s.size()); }
+  Slice Encode() const {
+    assert(!rep_.empty());
+    return rep_;
+  }
+
+  Slice user_key() const { return ExtractUserKey(rep_); }
+
+  void SetFrom(const ParsedInternalKey& p) {
+    rep_.clear();
+    AppendInternalKey(&rep_, p);
+  }
+
+  void Clear() { rep_.clear(); }
+
+  std::string DebugString() const;
+};
+
+inline int InternalKeyComparator::Compare(
+    const InternalKey& a, const InternalKey& b) const {
+  return Compare(a.Encode(), b.Encode());
+}
+
+inline bool ParseInternalKey(const Slice& internal_key,
+                             ParsedInternalKey* result) {
+  const size_t n = internal_key.size();
+  if (n < 8) return false;
+  uint64_t num = DecodeFixed64(internal_key.data() + n - 8);
+  unsigned char c = num & 0xff;
+  result->sequence = num >> 8;
+  result->type = static_cast<ValueType>(c);
+  result->user_key = Slice(internal_key.data(), n - 8);
+  return (c <= static_cast<unsigned char>(kTypeValue));
+}
+
+// A helper class useful for DBImpl::Get()
+class LookupKey {
+ public:
+  // Initialize *this for looking up user_key at a snapshot with
+  // the specified sequence number.
+  LookupKey(const Slice& user_key, SequenceNumber sequence);
+
+  ~LookupKey();
+
+  // Return a key suitable for lookup in a MemTable.
+  Slice memtable_key() const { return Slice(start_, end_ - start_); }
+
+  // Return an internal key (suitable for passing to an internal iterator)
+  Slice internal_key() const { return Slice(kstart_, end_ - kstart_); }
+
+  // Return the user key
+  Slice user_key() const { return Slice(kstart_, end_ - kstart_ - 8); }
+
+ private:
+  // We construct a char array of the form:
+  //    klength  varint32               <-- start_
+  //    userkey  char[klength]          <-- kstart_
+  //    tag      uint64
+  //                                    <-- end_
+  // The array is a suitable MemTable key.
+  // The suffix starting with "userkey" can be used as an InternalKey.
+  const char* start_;
+  const char* kstart_;
+  const char* end_;
+  char space_[200];      // Avoid allocation for short keys
+
+  // No copying allowed
+  LookupKey(const LookupKey&);
+  void operator=(const LookupKey&);
+};
+
+inline LookupKey::~LookupKey() {
+  if (start_ != space_) delete[] start_;
+}
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_FORMAT_H_

data/leveldb/db/dbformat_test.cc

@@ -0,0 +1,112 @@
+// 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 "db/dbformat.h"
+#include "util/logging.h"
+#include "util/testharness.h"
+
+namespace leveldb {
+
+static std::string IKey(const std::string& user_key,
+                        uint64_t seq,
+                        ValueType vt) {
+  std::string encoded;
+  AppendInternalKey(&encoded, ParsedInternalKey(user_key, seq, vt));
+  return encoded;
+}
+
+static std::string Shorten(const std::string& s, const std::string& l) {
+  std::string result = s;
+  InternalKeyComparator(BytewiseComparator()).FindShortestSeparator(&result, l);
+  return result;
+}
+
+static std::string ShortSuccessor(const std::string& s) {
+  std::string result = s;
+  InternalKeyComparator(BytewiseComparator()).FindShortSuccessor(&result);
+  return result;
+}
+
+static void TestKey(const std::string& key,
+                    uint64_t seq,
+                    ValueType vt) {
+  std::string encoded = IKey(key, seq, vt);
+
+  Slice in(encoded);
+  ParsedInternalKey decoded("", 0, kTypeValue);
+
+  ASSERT_TRUE(ParseInternalKey(in, &decoded));
+  ASSERT_EQ(key, decoded.user_key.ToString());
+  ASSERT_EQ(seq, decoded.sequence);
+  ASSERT_EQ(vt, decoded.type);
+
+  ASSERT_TRUE(!ParseInternalKey(Slice("bar"), &decoded));
+}
+
+class FormatTest { };
+
+TEST(FormatTest, InternalKey_EncodeDecode) {
+  const char* keys[] = { "", "k", "hello", "longggggggggggggggggggggg" };
+  const uint64_t seq[] = {
+    1, 2, 3,
+    (1ull << 8) - 1, 1ull << 8, (1ull << 8) + 1,
+    (1ull << 16) - 1, 1ull << 16, (1ull << 16) + 1,
+    (1ull << 32) - 1, 1ull << 32, (1ull << 32) + 1
+  };
+  for (int k = 0; k < sizeof(keys) / sizeof(keys[0]); k++) {
+    for (int s = 0; s < sizeof(seq) / sizeof(seq[0]); s++) {
+      TestKey(keys[k], seq[s], kTypeValue);
+      TestKey("hello", 1, kTypeDeletion);
+    }
+  }
+}
+
+TEST(FormatTest, InternalKeyShortSeparator) {
+  // When user keys are same
+  ASSERT_EQ(IKey("foo", 100, kTypeValue),
+            Shorten(IKey("foo", 100, kTypeValue),
+                    IKey("foo", 99, kTypeValue)));
+  ASSERT_EQ(IKey("foo", 100, kTypeValue),
+            Shorten(IKey("foo", 100, kTypeValue),
+                    IKey("foo", 101, kTypeValue)));
+  ASSERT_EQ(IKey("foo", 100, kTypeValue),
+            Shorten(IKey("foo", 100, kTypeValue),
+                    IKey("foo", 100, kTypeValue)));
+  ASSERT_EQ(IKey("foo", 100, kTypeValue),
+            Shorten(IKey("foo", 100, kTypeValue),
+                    IKey("foo", 100, kTypeDeletion)));
+
+  // When user keys are misordered
+  ASSERT_EQ(IKey("foo", 100, kTypeValue),
+            Shorten(IKey("foo", 100, kTypeValue),
+                    IKey("bar", 99, kTypeValue)));
+
+  // When user keys are different, but correctly ordered
+  ASSERT_EQ(IKey("g", kMaxSequenceNumber, kValueTypeForSeek),
+            Shorten(IKey("foo", 100, kTypeValue),
+                    IKey("hello", 200, kTypeValue)));
+
+  // When start user key is prefix of limit user key
+  ASSERT_EQ(IKey("foo", 100, kTypeValue),
+            Shorten(IKey("foo", 100, kTypeValue),
+                    IKey("foobar", 200, kTypeValue)));
+
+  // When limit user key is prefix of start user key
+  ASSERT_EQ(IKey("foobar", 100, kTypeValue),
+            Shorten(IKey("foobar", 100, kTypeValue),
+                    IKey("foo", 200, kTypeValue)));
+}
+
+TEST(FormatTest, InternalKeyShortestSuccessor) {
+  ASSERT_EQ(IKey("g", kMaxSequenceNumber, kValueTypeForSeek),
+            ShortSuccessor(IKey("foo", 100, kTypeValue)));
+  ASSERT_EQ(IKey("\xff\xff", 100, kTypeValue),
+            ShortSuccessor(IKey("\xff\xff", 100, kTypeValue)));
+}
+
+}  // namespace leveldb
+
+int main(int argc, char** argv) {
+  return leveldb::test::RunAllTests();
+}