create

Pods/leveldb-library/db/builder.cc

@@ -0,0 +1,79 @@
+// 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/builder.h"
+
+#include "db/dbformat.h"
+#include "db/filename.h"
+#include "db/table_cache.h"
+#include "db/version_edit.h"
+#include "leveldb/db.h"
+#include "leveldb/env.h"
+#include "leveldb/iterator.h"
+
+namespace leveldb {
+
+Status BuildTable(const std::string& dbname, Env* env, const Options& options,
+                  TableCache* table_cache, Iterator* iter, FileMetaData* meta) {
+  Status s;
+  meta->file_size = 0;
+  iter->SeekToFirst();
+
+  std::string fname = TableFileName(dbname, meta->number);
+  if (iter->Valid()) {
+    WritableFile* file;
+    s = env->NewWritableFile(fname, &file);
+    if (!s.ok()) {
+      return s;
+    }
+
+    TableBuilder* builder = new TableBuilder(options, file);
+    meta->smallest.DecodeFrom(iter->key());
+    for (; iter->Valid(); iter->Next()) {
+      Slice key = iter->key();
+      meta->largest.DecodeFrom(key);
+      builder->Add(key, iter->value());
+    }
+
+    // Finish and check for builder errors
+    s = builder->Finish();
+    if (s.ok()) {
+      meta->file_size = builder->FileSize();
+      assert(meta->file_size > 0);
+    }
+    delete builder;
+
+    // Finish and check for file errors
+    if (s.ok()) {
+      s = file->Sync();
+    }
+    if (s.ok()) {
+      s = file->Close();
+    }
+    delete file;
+    file = nullptr;
+
+    if (s.ok()) {
+      // Verify that the table is usable
+      Iterator* it = table_cache->NewIterator(ReadOptions(), meta->number,
+                                              meta->file_size);
+      s = it->status();
+      delete it;
+    }
+  }
+
+  // Check for input iterator errors
+  if (!iter->status().ok()) {
+    s = iter->status();
+  }
+
+  if (s.ok() && meta->file_size > 0) {
+    // Keep it
+  } else {
+    env->RemoveFile(fname);
+  }
+  return s;
+}
+
+}  // namespace leveldb

Pods/leveldb-library/db/builder.h

@@ -0,0 +1,30 @@
+// 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_BUILDER_H_
+#define STORAGE_LEVELDB_DB_BUILDER_H_
+
+#include "leveldb/status.h"
+
+namespace leveldb {
+
+struct Options;
+struct FileMetaData;
+
+class Env;
+class Iterator;
+class TableCache;
+class VersionEdit;
+
+// Build a Table file from the contents of *iter.  The generated file
+// will be named according to meta->number.  On success, the rest of
+// *meta will be filled with metadata about the generated table.
+// If no data is present in *iter, meta->file_size will be set to
+// zero, and no Table file will be produced.
+Status BuildTable(const std::string& dbname, Env* env, const Options& options,
+                  TableCache* table_cache, Iterator* iter, FileMetaData* meta);
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_BUILDER_H_

Pods/leveldb-library/db/c.cc

@@ -0,0 +1,562 @@
+// 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 "leveldb/c.h"
+
+#include <cstdint>
+#include <cstdlib>
+
+#include "leveldb/cache.h"
+#include "leveldb/comparator.h"
+#include "leveldb/db.h"
+#include "leveldb/env.h"
+#include "leveldb/filter_policy.h"
+#include "leveldb/iterator.h"
+#include "leveldb/options.h"
+#include "leveldb/status.h"
+#include "leveldb/write_batch.h"
+
+using leveldb::Cache;
+using leveldb::Comparator;
+using leveldb::CompressionType;
+using leveldb::DB;
+using leveldb::Env;
+using leveldb::FileLock;
+using leveldb::FilterPolicy;
+using leveldb::Iterator;
+using leveldb::kMajorVersion;
+using leveldb::kMinorVersion;
+using leveldb::Logger;
+using leveldb::NewBloomFilterPolicy;
+using leveldb::NewLRUCache;
+using leveldb::Options;
+using leveldb::RandomAccessFile;
+using leveldb::Range;
+using leveldb::ReadOptions;
+using leveldb::SequentialFile;
+using leveldb::Slice;
+using leveldb::Snapshot;
+using leveldb::Status;
+using leveldb::WritableFile;
+using leveldb::WriteBatch;
+using leveldb::WriteOptions;
+
+extern "C" {
+
+struct leveldb_t {
+  DB* rep;
+};
+struct leveldb_iterator_t {
+  Iterator* rep;
+};
+struct leveldb_writebatch_t {
+  WriteBatch rep;
+};
+struct leveldb_snapshot_t {
+  const Snapshot* rep;
+};
+struct leveldb_readoptions_t {
+  ReadOptions rep;
+};
+struct leveldb_writeoptions_t {
+  WriteOptions rep;
+};
+struct leveldb_options_t {
+  Options rep;
+};
+struct leveldb_cache_t {
+  Cache* rep;
+};
+struct leveldb_seqfile_t {
+  SequentialFile* rep;
+};
+struct leveldb_randomfile_t {
+  RandomAccessFile* rep;
+};
+struct leveldb_writablefile_t {
+  WritableFile* rep;
+};
+struct leveldb_logger_t {
+  Logger* rep;
+};
+struct leveldb_filelock_t {
+  FileLock* rep;
+};
+
+struct leveldb_comparator_t : public Comparator {
+  ~leveldb_comparator_t() override { (*destructor_)(state_); }
+
+  int Compare(const Slice& a, const Slice& b) const override {
+    return (*compare_)(state_, a.data(), a.size(), b.data(), b.size());
+  }
+
+  const char* Name() const override { return (*name_)(state_); }
+
+  // No-ops since the C binding does not support key shortening methods.
+  void FindShortestSeparator(std::string*, const Slice&) const override {}
+  void FindShortSuccessor(std::string* key) const override {}
+
+  void* state_;
+  void (*destructor_)(void*);
+  int (*compare_)(void*, const char* a, size_t alen, const char* b,
+                  size_t blen);
+  const char* (*name_)(void*);
+};
+
+struct leveldb_filterpolicy_t : public FilterPolicy {
+  ~leveldb_filterpolicy_t() override { (*destructor_)(state_); }
+
+  const char* Name() const override { return (*name_)(state_); }
+
+  void CreateFilter(const Slice* keys, int n, std::string* dst) const override {
+    std::vector<const char*> key_pointers(n);
+    std::vector<size_t> key_sizes(n);
+    for (int i = 0; i < n; i++) {
+      key_pointers[i] = keys[i].data();
+      key_sizes[i] = keys[i].size();
+    }
+    size_t len;
+    char* filter = (*create_)(state_, &key_pointers[0], &key_sizes[0], n, &len);
+    dst->append(filter, len);
+    free(filter);
+  }
+
+  bool KeyMayMatch(const Slice& key, const Slice& filter) const override {
+    return (*key_match_)(state_, key.data(), key.size(), filter.data(),
+                         filter.size());
+  }
+
+  void* state_;
+  void (*destructor_)(void*);
+  const char* (*name_)(void*);
+  char* (*create_)(void*, const char* const* key_array,
+                   const size_t* key_length_array, int num_keys,
+                   size_t* filter_length);
+  uint8_t (*key_match_)(void*, const char* key, size_t length,
+                        const char* filter, size_t filter_length);
+};
+
+struct leveldb_env_t {
+  Env* rep;
+  bool is_default;
+};
+
+static bool SaveError(char** errptr, const Status& s) {
+  assert(errptr != nullptr);
+  if (s.ok()) {
+    return false;
+  } else if (*errptr == nullptr) {
+    *errptr = strdup(s.ToString().c_str());
+  } else {
+    // TODO(sanjay): Merge with existing error?
+    free(*errptr);
+    *errptr = strdup(s.ToString().c_str());
+  }
+  return true;
+}
+
+static char* CopyString(const std::string& str) {
+  char* result = reinterpret_cast<char*>(malloc(sizeof(char) * str.size()));
+  std::memcpy(result, str.data(), sizeof(char) * str.size());
+  return result;
+}
+
+leveldb_t* leveldb_open(const leveldb_options_t* options, const char* name,
+                        char** errptr) {
+  DB* db;
+  if (SaveError(errptr, DB::Open(options->rep, std::string(name), &db))) {
+    return nullptr;
+  }
+  leveldb_t* result = new leveldb_t;
+  result->rep = db;
+  return result;
+}
+
+void leveldb_close(leveldb_t* db) {
+  delete db->rep;
+  delete db;
+}
+
+void leveldb_put(leveldb_t* db, const leveldb_writeoptions_t* options,
+                 const char* key, size_t keylen, const char* val, size_t vallen,
+                 char** errptr) {
+  SaveError(errptr,
+            db->rep->Put(options->rep, Slice(key, keylen), Slice(val, vallen)));
+}
+
+void leveldb_delete(leveldb_t* db, const leveldb_writeoptions_t* options,
+                    const char* key, size_t keylen, char** errptr) {
+  SaveError(errptr, db->rep->Delete(options->rep, Slice(key, keylen)));
+}
+
+void leveldb_write(leveldb_t* db, const leveldb_writeoptions_t* options,
+                   leveldb_writebatch_t* batch, char** errptr) {
+  SaveError(errptr, db->rep->Write(options->rep, &batch->rep));
+}
+
+char* leveldb_get(leveldb_t* db, const leveldb_readoptions_t* options,
+                  const char* key, size_t keylen, size_t* vallen,
+                  char** errptr) {
+  char* result = nullptr;
+  std::string tmp;
+  Status s = db->rep->Get(options->rep, Slice(key, keylen), &tmp);
+  if (s.ok()) {
+    *vallen = tmp.size();
+    result = CopyString(tmp);
+  } else {
+    *vallen = 0;
+    if (!s.IsNotFound()) {
+      SaveError(errptr, s);
+    }
+  }
+  return result;
+}
+
+leveldb_iterator_t* leveldb_create_iterator(
+    leveldb_t* db, const leveldb_readoptions_t* options) {
+  leveldb_iterator_t* result = new leveldb_iterator_t;
+  result->rep = db->rep->NewIterator(options->rep);
+  return result;
+}
+
+const leveldb_snapshot_t* leveldb_create_snapshot(leveldb_t* db) {
+  leveldb_snapshot_t* result = new leveldb_snapshot_t;
+  result->rep = db->rep->GetSnapshot();
+  return result;
+}
+
+void leveldb_release_snapshot(leveldb_t* db,
+                              const leveldb_snapshot_t* snapshot) {
+  db->rep->ReleaseSnapshot(snapshot->rep);
+  delete snapshot;
+}
+
+char* leveldb_property_value(leveldb_t* db, const char* propname) {
+  std::string tmp;
+  if (db->rep->GetProperty(Slice(propname), &tmp)) {
+    // We use strdup() since we expect human readable output.
+    return strdup(tmp.c_str());
+  } else {
+    return nullptr;
+  }
+}
+
+void leveldb_approximate_sizes(leveldb_t* db, int num_ranges,
+                               const char* const* range_start_key,
+                               const size_t* range_start_key_len,
+                               const char* const* range_limit_key,
+                               const size_t* range_limit_key_len,
+                               uint64_t* sizes) {
+  Range* ranges = new Range[num_ranges];
+  for (int i = 0; i < num_ranges; i++) {
+    ranges[i].start = Slice(range_start_key[i], range_start_key_len[i]);
+    ranges[i].limit = Slice(range_limit_key[i], range_limit_key_len[i]);
+  }
+  db->rep->GetApproximateSizes(ranges, num_ranges, sizes);
+  delete[] ranges;
+}
+
+void leveldb_compact_range(leveldb_t* db, const char* start_key,
+                           size_t start_key_len, const char* limit_key,
+                           size_t limit_key_len) {
+  Slice a, b;
+  db->rep->CompactRange(
+      // Pass null Slice if corresponding "const char*" is null
+      (start_key ? (a = Slice(start_key, start_key_len), &a) : nullptr),
+      (limit_key ? (b = Slice(limit_key, limit_key_len), &b) : nullptr));
+}
+
+void leveldb_destroy_db(const leveldb_options_t* options, const char* name,
+                        char** errptr) {
+  SaveError(errptr, DestroyDB(name, options->rep));
+}
+
+void leveldb_repair_db(const leveldb_options_t* options, const char* name,
+                       char** errptr) {
+  SaveError(errptr, RepairDB(name, options->rep));
+}
+
+void leveldb_iter_destroy(leveldb_iterator_t* iter) {
+  delete iter->rep;
+  delete iter;
+}
+
+uint8_t leveldb_iter_valid(const leveldb_iterator_t* iter) {
+  return iter->rep->Valid();
+}
+
+void leveldb_iter_seek_to_first(leveldb_iterator_t* iter) {
+  iter->rep->SeekToFirst();
+}
+
+void leveldb_iter_seek_to_last(leveldb_iterator_t* iter) {
+  iter->rep->SeekToLast();
+}
+
+void leveldb_iter_seek(leveldb_iterator_t* iter, const char* k, size_t klen) {
+  iter->rep->Seek(Slice(k, klen));
+}
+
+void leveldb_iter_next(leveldb_iterator_t* iter) { iter->rep->Next(); }
+
+void leveldb_iter_prev(leveldb_iterator_t* iter) { iter->rep->Prev(); }
+
+const char* leveldb_iter_key(const leveldb_iterator_t* iter, size_t* klen) {
+  Slice s = iter->rep->key();
+  *klen = s.size();
+  return s.data();
+}
+
+const char* leveldb_iter_value(const leveldb_iterator_t* iter, size_t* vlen) {
+  Slice s = iter->rep->value();
+  *vlen = s.size();
+  return s.data();
+}
+
+void leveldb_iter_get_error(const leveldb_iterator_t* iter, char** errptr) {
+  SaveError(errptr, iter->rep->status());
+}
+
+leveldb_writebatch_t* leveldb_writebatch_create() {
+  return new leveldb_writebatch_t;
+}
+
+void leveldb_writebatch_destroy(leveldb_writebatch_t* b) { delete b; }
+
+void leveldb_writebatch_clear(leveldb_writebatch_t* b) { b->rep.Clear(); }
+
+void leveldb_writebatch_put(leveldb_writebatch_t* b, const char* key,
+                            size_t klen, const char* val, size_t vlen) {
+  b->rep.Put(Slice(key, klen), Slice(val, vlen));
+}
+
+void leveldb_writebatch_delete(leveldb_writebatch_t* b, const char* key,
+                               size_t klen) {
+  b->rep.Delete(Slice(key, klen));
+}
+
+void leveldb_writebatch_iterate(const leveldb_writebatch_t* b, void* state,
+                                void (*put)(void*, const char* k, size_t klen,
+                                            const char* v, size_t vlen),
+                                void (*deleted)(void*, const char* k,
+                                                size_t klen)) {
+  class H : public WriteBatch::Handler {
+   public:
+    void* state_;
+    void (*put_)(void*, const char* k, size_t klen, const char* v, size_t vlen);
+    void (*deleted_)(void*, const char* k, size_t klen);
+    void Put(const Slice& key, const Slice& value) override {
+      (*put_)(state_, key.data(), key.size(), value.data(), value.size());
+    }
+    void Delete(const Slice& key) override {
+      (*deleted_)(state_, key.data(), key.size());
+    }
+  };
+  H handler;
+  handler.state_ = state;
+  handler.put_ = put;
+  handler.deleted_ = deleted;
+  b->rep.Iterate(&handler);
+}
+
+void leveldb_writebatch_append(leveldb_writebatch_t* destination,
+                               const leveldb_writebatch_t* source) {
+  destination->rep.Append(source->rep);
+}
+
+leveldb_options_t* leveldb_options_create() { return new leveldb_options_t; }
+
+void leveldb_options_destroy(leveldb_options_t* options) { delete options; }
+
+void leveldb_options_set_comparator(leveldb_options_t* opt,
+                                    leveldb_comparator_t* cmp) {
+  opt->rep.comparator = cmp;
+}
+
+void leveldb_options_set_filter_policy(leveldb_options_t* opt,
+                                       leveldb_filterpolicy_t* policy) {
+  opt->rep.filter_policy = policy;
+}
+
+void leveldb_options_set_create_if_missing(leveldb_options_t* opt, uint8_t v) {
+  opt->rep.create_if_missing = v;
+}
+
+void leveldb_options_set_error_if_exists(leveldb_options_t* opt, uint8_t v) {
+  opt->rep.error_if_exists = v;
+}
+
+void leveldb_options_set_paranoid_checks(leveldb_options_t* opt, uint8_t v) {
+  opt->rep.paranoid_checks = v;
+}
+
+void leveldb_options_set_env(leveldb_options_t* opt, leveldb_env_t* env) {
+  opt->rep.env = (env ? env->rep : nullptr);
+}
+
+void leveldb_options_set_info_log(leveldb_options_t* opt, leveldb_logger_t* l) {
+  opt->rep.info_log = (l ? l->rep : nullptr);
+}
+
+void leveldb_options_set_write_buffer_size(leveldb_options_t* opt, size_t s) {
+  opt->rep.write_buffer_size = s;
+}
+
+void leveldb_options_set_max_open_files(leveldb_options_t* opt, int n) {
+  opt->rep.max_open_files = n;
+}
+
+void leveldb_options_set_cache(leveldb_options_t* opt, leveldb_cache_t* c) {
+  opt->rep.block_cache = c->rep;
+}
+
+void leveldb_options_set_block_size(leveldb_options_t* opt, size_t s) {
+  opt->rep.block_size = s;
+}
+
+void leveldb_options_set_block_restart_interval(leveldb_options_t* opt, int n) {
+  opt->rep.block_restart_interval = n;
+}
+
+void leveldb_options_set_max_file_size(leveldb_options_t* opt, size_t s) {
+  opt->rep.max_file_size = s;
+}
+
+void leveldb_options_set_compression(leveldb_options_t* opt, int t) {
+  opt->rep.compression = static_cast<CompressionType>(t);
+}
+
+leveldb_comparator_t* leveldb_comparator_create(
+    void* state, void (*destructor)(void*),
+    int (*compare)(void*, const char* a, size_t alen, const char* b,
+                   size_t blen),
+    const char* (*name)(void*)) {
+  leveldb_comparator_t* result = new leveldb_comparator_t;
+  result->state_ = state;
+  result->destructor_ = destructor;
+  result->compare_ = compare;
+  result->name_ = name;
+  return result;
+}
+
+void leveldb_comparator_destroy(leveldb_comparator_t* cmp) { delete cmp; }
+
+leveldb_filterpolicy_t* leveldb_filterpolicy_create(
+    void* state, void (*destructor)(void*),
+    char* (*create_filter)(void*, const char* const* key_array,
+                           const size_t* key_length_array, int num_keys,
+                           size_t* filter_length),
+    uint8_t (*key_may_match)(void*, const char* key, size_t length,
+                             const char* filter, size_t filter_length),
+    const char* (*name)(void*)) {
+  leveldb_filterpolicy_t* result = new leveldb_filterpolicy_t;
+  result->state_ = state;
+  result->destructor_ = destructor;
+  result->create_ = create_filter;
+  result->key_match_ = key_may_match;
+  result->name_ = name;
+  return result;
+}
+
+void leveldb_filterpolicy_destroy(leveldb_filterpolicy_t* filter) {
+  delete filter;
+}
+
+leveldb_filterpolicy_t* leveldb_filterpolicy_create_bloom(int bits_per_key) {
+  // Make a leveldb_filterpolicy_t, but override all of its methods so
+  // they delegate to a NewBloomFilterPolicy() instead of user
+  // supplied C functions.
+  struct Wrapper : public leveldb_filterpolicy_t {
+    static void DoNothing(void*) {}
+
+    ~Wrapper() { delete rep_; }
+    const char* Name() const { return rep_->Name(); }
+    void CreateFilter(const Slice* keys, int n, std::string* dst) const {
+      return rep_->CreateFilter(keys, n, dst);
+    }
+    bool KeyMayMatch(const Slice& key, const Slice& filter) const {
+      return rep_->KeyMayMatch(key, filter);
+    }
+
+    const FilterPolicy* rep_;
+  };
+  Wrapper* wrapper = new Wrapper;
+  wrapper->rep_ = NewBloomFilterPolicy(bits_per_key);
+  wrapper->state_ = nullptr;
+  wrapper->destructor_ = &Wrapper::DoNothing;
+  return wrapper;
+}
+
+leveldb_readoptions_t* leveldb_readoptions_create() {
+  return new leveldb_readoptions_t;
+}
+
+void leveldb_readoptions_destroy(leveldb_readoptions_t* opt) { delete opt; }
+
+void leveldb_readoptions_set_verify_checksums(leveldb_readoptions_t* opt,
+                                              uint8_t v) {
+  opt->rep.verify_checksums = v;
+}
+
+void leveldb_readoptions_set_fill_cache(leveldb_readoptions_t* opt, uint8_t v) {
+  opt->rep.fill_cache = v;
+}
+
+void leveldb_readoptions_set_snapshot(leveldb_readoptions_t* opt,
+                                      const leveldb_snapshot_t* snap) {
+  opt->rep.snapshot = (snap ? snap->rep : nullptr);
+}
+
+leveldb_writeoptions_t* leveldb_writeoptions_create() {
+  return new leveldb_writeoptions_t;
+}
+
+void leveldb_writeoptions_destroy(leveldb_writeoptions_t* opt) { delete opt; }
+
+void leveldb_writeoptions_set_sync(leveldb_writeoptions_t* opt, uint8_t v) {
+  opt->rep.sync = v;
+}
+
+leveldb_cache_t* leveldb_cache_create_lru(size_t capacity) {
+  leveldb_cache_t* c = new leveldb_cache_t;
+  c->rep = NewLRUCache(capacity);
+  return c;
+}
+
+void leveldb_cache_destroy(leveldb_cache_t* cache) {
+  delete cache->rep;
+  delete cache;
+}
+
+leveldb_env_t* leveldb_create_default_env() {
+  leveldb_env_t* result = new leveldb_env_t;
+  result->rep = Env::Default();
+  result->is_default = true;
+  return result;
+}
+
+void leveldb_env_destroy(leveldb_env_t* env) {
+  if (!env->is_default) delete env->rep;
+  delete env;
+}
+
+char* leveldb_env_get_test_directory(leveldb_env_t* env) {
+  std::string result;
+  if (!env->rep->GetTestDirectory(&result).ok()) {
+    return nullptr;
+  }
+
+  char* buffer = static_cast<char*>(malloc(result.size() + 1));
+  std::memcpy(buffer, result.data(), result.size());
+  buffer[result.size()] = '\0';
+  return buffer;
+}
+
+void leveldb_free(void* ptr) { free(ptr); }
+
+int leveldb_major_version() { return kMajorVersion; }
+
+int leveldb_minor_version() { return kMinorVersion; }
+
+}  // end extern "C"

Pods/leveldb-library/db/db_impl.cc

@@ -0,0 +1,1554 @@
+// 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/db_impl.h"
+
+#include <algorithm>
+#include <atomic>
+#include <cstdint>
+#include <cstdio>
+#include <set>
+#include <string>
+#include <vector>
+
+#include "db/builder.h"
+#include "db/db_iter.h"
+#include "db/dbformat.h"
+#include "db/filename.h"
+#include "db/log_reader.h"
+#include "db/log_writer.h"
+#include "db/memtable.h"
+#include "db/table_cache.h"
+#include "db/version_set.h"
+#include "db/write_batch_internal.h"
+#include "leveldb/db.h"
+#include "leveldb/env.h"
+#include "leveldb/status.h"
+#include "leveldb/table.h"
+#include "leveldb/table_builder.h"
+#include "port/port.h"
+#include "table/block.h"
+#include "table/merger.h"
+#include "table/two_level_iterator.h"
+#include "util/coding.h"
+#include "util/logging.h"
+#include "util/mutexlock.h"
+
+namespace leveldb {
+
+const int kNumNonTableCacheFiles = 10;
+
+// Information kept for every waiting writer
+struct DBImpl::Writer {
+  explicit Writer(port::Mutex* mu)
+      : batch(nullptr), sync(false), done(false), cv(mu) {}
+
+  Status status;
+  WriteBatch* batch;
+  bool sync;
+  bool done;
+  port::CondVar cv;
+};
+
+struct DBImpl::CompactionState {
+  // Files produced by compaction
+  struct Output {
+    uint64_t number;
+    uint64_t file_size;
+    InternalKey smallest, largest;
+  };
+
+  Output* current_output() { return &outputs[outputs.size() - 1]; }
+
+  explicit CompactionState(Compaction* c)
+      : compaction(c),
+        smallest_snapshot(0),
+        outfile(nullptr),
+        builder(nullptr),
+        total_bytes(0) {}
+
+  Compaction* const compaction;
+
+  // Sequence numbers < smallest_snapshot are not significant since we
+  // will never have to service a snapshot below smallest_snapshot.
+  // Therefore if we have seen a sequence number S <= smallest_snapshot,
+  // we can drop all entries for the same key with sequence numbers < S.
+  SequenceNumber smallest_snapshot;
+
+  std::vector<Output> outputs;
+
+  // State kept for output being generated
+  WritableFile* outfile;
+  TableBuilder* builder;
+
+  uint64_t total_bytes;
+};
+
+// Fix user-supplied options to be reasonable
+template <class T, class V>
+static void ClipToRange(T* ptr, V minvalue, V maxvalue) {
+  if (static_cast<V>(*ptr) > maxvalue) *ptr = maxvalue;
+  if (static_cast<V>(*ptr) < minvalue) *ptr = minvalue;
+}
+Options SanitizeOptions(const std::string& dbname,
+                        const InternalKeyComparator* icmp,
+                        const InternalFilterPolicy* ipolicy,
+                        const Options& src) {
+  Options result = src;
+  result.comparator = icmp;
+  result.filter_policy = (src.filter_policy != nullptr) ? ipolicy : nullptr;
+  ClipToRange(&result.max_open_files, 64 + kNumNonTableCacheFiles, 50000);
+  ClipToRange(&result.write_buffer_size, 64 << 10, 1 << 30);
+  ClipToRange(&result.max_file_size, 1 << 20, 1 << 30);
+  ClipToRange(&result.block_size, 1 << 10, 4 << 20);
+  if (result.info_log == nullptr) {
+    // Open a log file in the same directory as the db
+    src.env->CreateDir(dbname);  // In case it does not exist
+    src.env->RenameFile(InfoLogFileName(dbname), OldInfoLogFileName(dbname));
+    Status s = src.env->NewLogger(InfoLogFileName(dbname), &result.info_log);
+    if (!s.ok()) {
+      // No place suitable for logging
+      result.info_log = nullptr;
+    }
+  }
+  if (result.block_cache == nullptr) {
+    result.block_cache = NewLRUCache(8 << 20);
+  }
+  return result;
+}
+
+static int TableCacheSize(const Options& sanitized_options) {
+  // Reserve ten files or so for other uses and give the rest to TableCache.
+  return sanitized_options.max_open_files - kNumNonTableCacheFiles;
+}
+
+DBImpl::DBImpl(const Options& raw_options, const std::string& dbname)
+    : env_(raw_options.env),
+      internal_comparator_(raw_options.comparator),
+      internal_filter_policy_(raw_options.filter_policy),
+      options_(SanitizeOptions(dbname, &internal_comparator_,
+                               &internal_filter_policy_, raw_options)),
+      owns_info_log_(options_.info_log != raw_options.info_log),
+      owns_cache_(options_.block_cache != raw_options.block_cache),
+      dbname_(dbname),
+      table_cache_(new TableCache(dbname_, options_, TableCacheSize(options_))),
+      db_lock_(nullptr),
+      shutting_down_(false),
+      background_work_finished_signal_(&mutex_),
+      mem_(nullptr),
+      imm_(nullptr),
+      has_imm_(false),
+      logfile_(nullptr),
+      logfile_number_(0),
+      log_(nullptr),
+      seed_(0),
+      tmp_batch_(new WriteBatch),
+      background_compaction_scheduled_(false),
+      manual_compaction_(nullptr),
+      versions_(new VersionSet(dbname_, &options_, table_cache_,
+                               &internal_comparator_)) {}
+
+DBImpl::~DBImpl() {
+  // Wait for background work to finish.
+  mutex_.Lock();
+  shutting_down_.store(true, std::memory_order_release);
+  while (background_compaction_scheduled_) {
+    background_work_finished_signal_.Wait();
+  }
+  mutex_.Unlock();
+
+  if (db_lock_ != nullptr) {
+    env_->UnlockFile(db_lock_);
+  }
+
+  delete versions_;
+  if (mem_ != nullptr) mem_->Unref();
+  if (imm_ != nullptr) imm_->Unref();
+  delete tmp_batch_;
+  delete log_;
+  delete logfile_;
+  delete table_cache_;
+
+  if (owns_info_log_) {
+    delete options_.info_log;
+  }
+  if (owns_cache_) {
+    delete options_.block_cache;
+  }
+}
+
+Status DBImpl::NewDB() {
+  VersionEdit new_db;
+  new_db.SetComparatorName(user_comparator()->Name());
+  new_db.SetLogNumber(0);
+  new_db.SetNextFile(2);
+  new_db.SetLastSequence(0);
+
+  const std::string manifest = DescriptorFileName(dbname_, 1);
+  WritableFile* file;
+  Status s = env_->NewWritableFile(manifest, &file);
+  if (!s.ok()) {
+    return s;
+  }
+  {
+    log::Writer log(file);
+    std::string record;
+    new_db.EncodeTo(&record);
+    s = log.AddRecord(record);
+    if (s.ok()) {
+      s = file->Close();
+    }
+  }
+  delete file;
+  if (s.ok()) {
+    // Make "CURRENT" file that points to the new manifest file.
+    s = SetCurrentFile(env_, dbname_, 1);
+  } else {
+    env_->RemoveFile(manifest);
+  }
+  return s;
+}
+
+void DBImpl::MaybeIgnoreError(Status* s) const {
+  if (s->ok() || options_.paranoid_checks) {
+    // No change needed
+  } else {
+    Log(options_.info_log, "Ignoring error %s", s->ToString().c_str());
+    *s = Status::OK();
+  }
+}
+
+void DBImpl::RemoveObsoleteFiles() {
+  mutex_.AssertHeld();
+
+  if (!bg_error_.ok()) {
+    // After a background error, we don't know whether a new version may
+    // or may not have been committed, so we cannot safely garbage collect.
+    return;
+  }
+
+  // Make a set of all of the live files
+  std::set<uint64_t> live = pending_outputs_;
+  versions_->AddLiveFiles(&live);
+
+  std::vector<std::string> filenames;
+  env_->GetChildren(dbname_, &filenames);  // Ignoring errors on purpose
+  uint64_t number;
+  FileType type;
+  std::vector<std::string> files_to_delete;
+  for (std::string& filename : filenames) {
+    if (ParseFileName(filename, &number, &type)) {
+      bool keep = true;
+      switch (type) {
+        case kLogFile:
+          keep = ((number >= versions_->LogNumber()) ||
+                  (number == versions_->PrevLogNumber()));
+          break;
+        case kDescriptorFile:
+          // Keep my manifest file, and any newer incarnations'
+          // (in case there is a race that allows other incarnations)
+          keep = (number >= versions_->ManifestFileNumber());
+          break;
+        case kTableFile:
+          keep = (live.find(number) != live.end());
+          break;
+        case kTempFile:
+          // Any temp files that are currently being written to must
+          // be recorded in pending_outputs_, which is inserted into "live"
+          keep = (live.find(number) != live.end());
+          break;
+        case kCurrentFile:
+        case kDBLockFile:
+        case kInfoLogFile:
+          keep = true;
+          break;
+      }
+
+      if (!keep) {
+        files_to_delete.push_back(std::move(filename));
+        if (type == kTableFile) {
+          table_cache_->Evict(number);
+        }
+        Log(options_.info_log, "Delete type=%d #%lld\n", static_cast<int>(type),
+            static_cast<unsigned long long>(number));
+      }
+    }
+  }
+
+  // While deleting all files unblock other threads. All files being deleted
+  // have unique names which will not collide with newly created files and
+  // are therefore safe to delete while allowing other threads to proceed.
+  mutex_.Unlock();
+  for (const std::string& filename : files_to_delete) {
+    env_->RemoveFile(dbname_ + "/" + filename);
+  }
+  mutex_.Lock();
+}
+
+Status DBImpl::Recover(VersionEdit* edit, bool* save_manifest) {
+  mutex_.AssertHeld();
+
+  // Ignore error from CreateDir since the creation of the DB is
+  // committed only when the descriptor is created, and this directory
+  // may already exist from a previous failed creation attempt.
+  env_->CreateDir(dbname_);
+  assert(db_lock_ == nullptr);
+  Status s = env_->LockFile(LockFileName(dbname_), &db_lock_);
+  if (!s.ok()) {
+    return s;
+  }
+
+  if (!env_->FileExists(CurrentFileName(dbname_))) {
+    if (options_.create_if_missing) {
+      s = NewDB();
+      if (!s.ok()) {
+        return s;
+      }
+    } else {
+      return Status::InvalidArgument(
+          dbname_, "does not exist (create_if_missing is false)");
+    }
+  } else {
+    if (options_.error_if_exists) {
+      return Status::InvalidArgument(dbname_,
+                                     "exists (error_if_exists is true)");
+    }
+  }
+
+  s = versions_->Recover(save_manifest);
+  if (!s.ok()) {
+    return s;
+  }
+  SequenceNumber max_sequence(0);
+
+  // Recover from all newer log files than the ones named in the
+  // descriptor (new log files may have been added by the previous
+  // incarnation without registering them in the descriptor).
+  //
+  // Note that PrevLogNumber() is no longer used, but we pay
+  // attention to it in case we are recovering a database
+  // produced by an older version of leveldb.
+  const uint64_t min_log = versions_->LogNumber();
+  const uint64_t prev_log = versions_->PrevLogNumber();
+  std::vector<std::string> filenames;
+  s = env_->GetChildren(dbname_, &filenames);
+  if (!s.ok()) {
+    return s;
+  }
+  std::set<uint64_t> expected;
+  versions_->AddLiveFiles(&expected);
+  uint64_t number;
+  FileType type;
+  std::vector<uint64_t> logs;
+  for (size_t i = 0; i < filenames.size(); i++) {
+    if (ParseFileName(filenames[i], &number, &type)) {
+      expected.erase(number);
+      if (type == kLogFile && ((number >= min_log) || (number == prev_log)))
+        logs.push_back(number);
+    }
+  }
+  if (!expected.empty()) {
+    char buf[50];
+    std::snprintf(buf, sizeof(buf), "%d missing files; e.g.",
+                  static_cast<int>(expected.size()));
+    return Status::Corruption(buf, TableFileName(dbname_, *(expected.begin())));
+  }
+
+  // Recover in the order in which the logs were generated
+  std::sort(logs.begin(), logs.end());
+  for (size_t i = 0; i < logs.size(); i++) {
+    s = RecoverLogFile(logs[i], (i == logs.size() - 1), save_manifest, edit,
+                       &max_sequence);
+    if (!s.ok()) {
+      return s;
+    }
+
+    // The previous incarnation may not have written any MANIFEST
+    // records after allocating this log number.  So we manually
+    // update the file number allocation counter in VersionSet.
+    versions_->MarkFileNumberUsed(logs[i]);
+  }
+
+  if (versions_->LastSequence() < max_sequence) {
+    versions_->SetLastSequence(max_sequence);
+  }
+
+  return Status::OK();
+}
+
+Status DBImpl::RecoverLogFile(uint64_t log_number, bool last_log,
+                              bool* save_manifest, VersionEdit* edit,
+                              SequenceNumber* max_sequence) {
+  struct LogReporter : public log::Reader::Reporter {
+    Env* env;
+    Logger* info_log;
+    const char* fname;
+    Status* status;  // null if options_.paranoid_checks==false
+    void Corruption(size_t bytes, const Status& s) override {
+      Log(info_log, "%s%s: dropping %d bytes; %s",
+          (this->status == nullptr ? "(ignoring error) " : ""), fname,
+          static_cast<int>(bytes), s.ToString().c_str());
+      if (this->status != nullptr && this->status->ok()) *this->status = s;
+    }
+  };
+
+  mutex_.AssertHeld();
+
+  // Open the log file
+  std::string fname = LogFileName(dbname_, log_number);
+  SequentialFile* file;
+  Status status = env_->NewSequentialFile(fname, &file);
+  if (!status.ok()) {
+    MaybeIgnoreError(&status);
+    return status;
+  }
+
+  // Create the log reader.
+  LogReporter reporter;
+  reporter.env = env_;
+  reporter.info_log = options_.info_log;
+  reporter.fname = fname.c_str();
+  reporter.status = (options_.paranoid_checks ? &status : nullptr);
+  // We intentionally make log::Reader do checksumming even if
+  // paranoid_checks==false so that corruptions cause entire commits
+  // to be skipped instead of propagating bad information (like overly
+  // large sequence numbers).
+  log::Reader reader(file, &reporter, true /*checksum*/, 0 /*initial_offset*/);
+  Log(options_.info_log, "Recovering log #%llu",
+      (unsigned long long)log_number);
+
+  // Read all the records and add to a memtable
+  std::string scratch;
+  Slice record;
+  WriteBatch batch;
+  int compactions = 0;
+  MemTable* mem = nullptr;
+  while (reader.ReadRecord(&record, &scratch) && status.ok()) {
+    if (record.size() < 12) {
+      reporter.Corruption(record.size(),
+                          Status::Corruption("log record too small"));
+      continue;
+    }
+    WriteBatchInternal::SetContents(&batch, record);
+
+    if (mem == nullptr) {
+      mem = new MemTable(internal_comparator_);
+      mem->Ref();
+    }
+    status = WriteBatchInternal::InsertInto(&batch, mem);
+    MaybeIgnoreError(&status);
+    if (!status.ok()) {
+      break;
+    }
+    const SequenceNumber last_seq = WriteBatchInternal::Sequence(&batch) +
+                                    WriteBatchInternal::Count(&batch) - 1;
+    if (last_seq > *max_sequence) {
+      *max_sequence = last_seq;
+    }
+
+    if (mem->ApproximateMemoryUsage() > options_.write_buffer_size) {
+      compactions++;
+      *save_manifest = true;
+      status = WriteLevel0Table(mem, edit, nullptr);
+      mem->Unref();
+      mem = nullptr;
+      if (!status.ok()) {
+        // Reflect errors immediately so that conditions like full
+        // file-systems cause the DB::Open() to fail.
+        break;
+      }
+    }
+  }
+
+  delete file;
+
+  // See if we should keep reusing the last log file.
+  if (status.ok() && options_.reuse_logs && last_log && compactions == 0) {
+    assert(logfile_ == nullptr);
+    assert(log_ == nullptr);
+    assert(mem_ == nullptr);
+    uint64_t lfile_size;
+    if (env_->GetFileSize(fname, &lfile_size).ok() &&
+        env_->NewAppendableFile(fname, &logfile_).ok()) {
+      Log(options_.info_log, "Reusing old log %s \n", fname.c_str());
+      log_ = new log::Writer(logfile_, lfile_size);
+      logfile_number_ = log_number;
+      if (mem != nullptr) {
+        mem_ = mem;
+        mem = nullptr;
+      } else {
+        // mem can be nullptr if lognum exists but was empty.
+        mem_ = new MemTable(internal_comparator_);
+        mem_->Ref();
+      }
+    }
+  }
+
+  if (mem != nullptr) {
+    // mem did not get reused; compact it.
+    if (status.ok()) {
+      *save_manifest = true;
+      status = WriteLevel0Table(mem, edit, nullptr);
+    }
+    mem->Unref();
+  }
+
+  return status;
+}
+
+Status DBImpl::WriteLevel0Table(MemTable* mem, VersionEdit* edit,
+                                Version* base) {
+  mutex_.AssertHeld();
+  const uint64_t start_micros = env_->NowMicros();
+  FileMetaData meta;
+  meta.number = versions_->NewFileNumber();
+  pending_outputs_.insert(meta.number);
+  Iterator* iter = mem->NewIterator();
+  Log(options_.info_log, "Level-0 table #%llu: started",
+      (unsigned long long)meta.number);
+
+  Status s;
+  {
+    mutex_.Unlock();
+    s = BuildTable(dbname_, env_, options_, table_cache_, iter, &meta);
+    mutex_.Lock();
+  }
+
+  Log(options_.info_log, "Level-0 table #%llu: %lld bytes %s",
+      (unsigned long long)meta.number, (unsigned long long)meta.file_size,
+      s.ToString().c_str());
+  delete iter;
+  pending_outputs_.erase(meta.number);
+
+  // Note that if file_size is zero, the file has been deleted and
+  // should not be added to the manifest.
+  int level = 0;
+  if (s.ok() && meta.file_size > 0) {
+    const Slice min_user_key = meta.smallest.user_key();
+    const Slice max_user_key = meta.largest.user_key();
+    if (base != nullptr) {
+      level = base->PickLevelForMemTableOutput(min_user_key, max_user_key);
+    }
+    edit->AddFile(level, meta.number, meta.file_size, meta.smallest,
+                  meta.largest);
+  }
+
+  CompactionStats stats;
+  stats.micros = env_->NowMicros() - start_micros;
+  stats.bytes_written = meta.file_size;
+  stats_[level].Add(stats);
+  return s;
+}
+
+void DBImpl::CompactMemTable() {
+  mutex_.AssertHeld();
+  assert(imm_ != nullptr);
+
+  // Save the contents of the memtable as a new Table
+  VersionEdit edit;
+  Version* base = versions_->current();
+  base->Ref();
+  Status s = WriteLevel0Table(imm_, &edit, base);
+  base->Unref();
+
+  if (s.ok() && shutting_down_.load(std::memory_order_acquire)) {
+    s = Status::IOError("Deleting DB during memtable compaction");
+  }
+
+  // Replace immutable memtable with the generated Table
+  if (s.ok()) {
+    edit.SetPrevLogNumber(0);
+    edit.SetLogNumber(logfile_number_);  // Earlier logs no longer needed
+    s = versions_->LogAndApply(&edit, &mutex_);
+  }
+
+  if (s.ok()) {
+    // Commit to the new state
+    imm_->Unref();
+    imm_ = nullptr;
+    has_imm_.store(false, std::memory_order_release);
+    RemoveObsoleteFiles();
+  } else {
+    RecordBackgroundError(s);
+  }
+}
+
+void DBImpl::CompactRange(const Slice* begin, const Slice* end) {
+  int max_level_with_files = 1;
+  {
+    MutexLock l(&mutex_);
+    Version* base = versions_->current();
+    for (int level = 1; level < config::kNumLevels; level++) {
+      if (base->OverlapInLevel(level, begin, end)) {
+        max_level_with_files = level;
+      }
+    }
+  }
+  TEST_CompactMemTable();  // TODO(sanjay): Skip if memtable does not overlap
+  for (int level = 0; level < max_level_with_files; level++) {
+    TEST_CompactRange(level, begin, end);
+  }
+}
+
+void DBImpl::TEST_CompactRange(int level, const Slice* begin,
+                               const Slice* end) {
+  assert(level >= 0);
+  assert(level + 1 < config::kNumLevels);
+
+  InternalKey begin_storage, end_storage;
+
+  ManualCompaction manual;
+  manual.level = level;
+  manual.done = false;
+  if (begin == nullptr) {
+    manual.begin = nullptr;
+  } else {
+    begin_storage = InternalKey(*begin, kMaxSequenceNumber, kValueTypeForSeek);
+    manual.begin = &begin_storage;
+  }
+  if (end == nullptr) {
+    manual.end = nullptr;
+  } else {
+    end_storage = InternalKey(*end, 0, static_cast<ValueType>(0));
+    manual.end = &end_storage;
+  }
+
+  MutexLock l(&mutex_);
+  while (!manual.done && !shutting_down_.load(std::memory_order_acquire) &&
+         bg_error_.ok()) {
+    if (manual_compaction_ == nullptr) {  // Idle
+      manual_compaction_ = &manual;
+      MaybeScheduleCompaction();
+    } else {  // Running either my compaction or another compaction.
+      background_work_finished_signal_.Wait();
+    }
+  }
+  if (manual_compaction_ == &manual) {
+    // Cancel my manual compaction since we aborted early for some reason.
+    manual_compaction_ = nullptr;
+  }
+}
+
+Status DBImpl::TEST_CompactMemTable() {
+  // nullptr batch means just wait for earlier writes to be done
+  Status s = Write(WriteOptions(), nullptr);
+  if (s.ok()) {
+    // Wait until the compaction completes
+    MutexLock l(&mutex_);
+    while (imm_ != nullptr && bg_error_.ok()) {
+      background_work_finished_signal_.Wait();
+    }
+    if (imm_ != nullptr) {
+      s = bg_error_;
+    }
+  }
+  return s;
+}
+
+void DBImpl::RecordBackgroundError(const Status& s) {
+  mutex_.AssertHeld();
+  if (bg_error_.ok()) {
+    bg_error_ = s;
+    background_work_finished_signal_.SignalAll();
+  }
+}
+
+void DBImpl::MaybeScheduleCompaction() {
+  mutex_.AssertHeld();
+  if (background_compaction_scheduled_) {
+    // Already scheduled
+  } else if (shutting_down_.load(std::memory_order_acquire)) {
+    // DB is being deleted; no more background compactions
+  } else if (!bg_error_.ok()) {
+    // Already got an error; no more changes
+  } else if (imm_ == nullptr && manual_compaction_ == nullptr &&
+             !versions_->NeedsCompaction()) {
+    // No work to be done
+  } else {
+    background_compaction_scheduled_ = true;
+    env_->Schedule(&DBImpl::BGWork, this);
+  }
+}
+
+void DBImpl::BGWork(void* db) {
+  reinterpret_cast<DBImpl*>(db)->BackgroundCall();
+}
+
+void DBImpl::BackgroundCall() {
+  MutexLock l(&mutex_);
+  assert(background_compaction_scheduled_);
+  if (shutting_down_.load(std::memory_order_acquire)) {
+    // No more background work when shutting down.
+  } else if (!bg_error_.ok()) {
+    // No more background work after a background error.
+  } else {
+    BackgroundCompaction();
+  }
+
+  background_compaction_scheduled_ = false;
+
+  // Previous compaction may have produced too many files in a level,
+  // so reschedule another compaction if needed.
+  MaybeScheduleCompaction();
+  background_work_finished_signal_.SignalAll();
+}
+
+void DBImpl::BackgroundCompaction() {
+  mutex_.AssertHeld();
+
+  if (imm_ != nullptr) {
+    CompactMemTable();
+    return;
+  }
+
+  Compaction* c;
+  bool is_manual = (manual_compaction_ != nullptr);
+  InternalKey manual_end;
+  if (is_manual) {
+    ManualCompaction* m = manual_compaction_;
+    c = versions_->CompactRange(m->level, m->begin, m->end);
+    m->done = (c == nullptr);
+    if (c != nullptr) {
+      manual_end = c->input(0, c->num_input_files(0) - 1)->largest;
+    }
+    Log(options_.info_log,
+        "Manual compaction at level-%d from %s .. %s; will stop at %s\n",
+        m->level, (m->begin ? m->begin->DebugString().c_str() : "(begin)"),
+        (m->end ? m->end->DebugString().c_str() : "(end)"),
+        (m->done ? "(end)" : manual_end.DebugString().c_str()));
+  } else {
+    c = versions_->PickCompaction();
+  }
+
+  Status status;
+  if (c == nullptr) {
+    // Nothing to do
+  } else if (!is_manual && c->IsTrivialMove()) {
+    // Move file to next level
+    assert(c->num_input_files(0) == 1);
+    FileMetaData* f = c->input(0, 0);
+    c->edit()->RemoveFile(c->level(), f->number);
+    c->edit()->AddFile(c->level() + 1, f->number, f->file_size, f->smallest,
+                       f->largest);
+    status = versions_->LogAndApply(c->edit(), &mutex_);
+    if (!status.ok()) {
+      RecordBackgroundError(status);
+    }
+    VersionSet::LevelSummaryStorage tmp;
+    Log(options_.info_log, "Moved #%lld to level-%d %lld bytes %s: %s\n",
+        static_cast<unsigned long long>(f->number), c->level() + 1,
+        static_cast<unsigned long long>(f->file_size),
+        status.ToString().c_str(), versions_->LevelSummary(&tmp));
+  } else {
+    CompactionState* compact = new CompactionState(c);
+    status = DoCompactionWork(compact);
+    if (!status.ok()) {
+      RecordBackgroundError(status);
+    }
+    CleanupCompaction(compact);
+    c->ReleaseInputs();
+    RemoveObsoleteFiles();
+  }
+  delete c;
+
+  if (status.ok()) {
+    // Done
+  } else if (shutting_down_.load(std::memory_order_acquire)) {
+    // Ignore compaction errors found during shutting down
+  } else {
+    Log(options_.info_log, "Compaction error: %s", status.ToString().c_str());
+  }
+
+  if (is_manual) {
+    ManualCompaction* m = manual_compaction_;
+    if (!status.ok()) {
+      m->done = true;
+    }
+    if (!m->done) {
+      // We only compacted part of the requested range.  Update *m
+      // to the range that is left to be compacted.
+      m->tmp_storage = manual_end;
+      m->begin = &m->tmp_storage;
+    }
+    manual_compaction_ = nullptr;
+  }
+}
+
+void DBImpl::CleanupCompaction(CompactionState* compact) {
+  mutex_.AssertHeld();
+  if (compact->builder != nullptr) {
+    // May happen if we get a shutdown call in the middle of compaction
+    compact->builder->Abandon();
+    delete compact->builder;
+  } else {
+    assert(compact->outfile == nullptr);
+  }
+  delete compact->outfile;
+  for (size_t i = 0; i < compact->outputs.size(); i++) {
+    const CompactionState::Output& out = compact->outputs[i];
+    pending_outputs_.erase(out.number);
+  }
+  delete compact;
+}
+
+Status DBImpl::OpenCompactionOutputFile(CompactionState* compact) {
+  assert(compact != nullptr);
+  assert(compact->builder == nullptr);
+  uint64_t file_number;
+  {
+    mutex_.Lock();
+    file_number = versions_->NewFileNumber();
+    pending_outputs_.insert(file_number);
+    CompactionState::Output out;
+    out.number = file_number;
+    out.smallest.Clear();
+    out.largest.Clear();
+    compact->outputs.push_back(out);
+    mutex_.Unlock();
+  }
+
+  // Make the output file
+  std::string fname = TableFileName(dbname_, file_number);
+  Status s = env_->NewWritableFile(fname, &compact->outfile);
+  if (s.ok()) {
+    compact->builder = new TableBuilder(options_, compact->outfile);
+  }
+  return s;
+}
+
+Status DBImpl::FinishCompactionOutputFile(CompactionState* compact,
+                                          Iterator* input) {
+  assert(compact != nullptr);
+  assert(compact->outfile != nullptr);
+  assert(compact->builder != nullptr);
+
+  const uint64_t output_number = compact->current_output()->number;
+  assert(output_number != 0);
+
+  // Check for iterator errors
+  Status s = input->status();
+  const uint64_t current_entries = compact->builder->NumEntries();
+  if (s.ok()) {
+    s = compact->builder->Finish();
+  } else {
+    compact->builder->Abandon();
+  }
+  const uint64_t current_bytes = compact->builder->FileSize();
+  compact->current_output()->file_size = current_bytes;
+  compact->total_bytes += current_bytes;
+  delete compact->builder;
+  compact->builder = nullptr;
+
+  // Finish and check for file errors
+  if (s.ok()) {
+    s = compact->outfile->Sync();
+  }
+  if (s.ok()) {
+    s = compact->outfile->Close();
+  }
+  delete compact->outfile;
+  compact->outfile = nullptr;
+
+  if (s.ok() && current_entries > 0) {
+    // Verify that the table is usable
+    Iterator* iter =
+        table_cache_->NewIterator(ReadOptions(), output_number, current_bytes);
+    s = iter->status();
+    delete iter;
+    if (s.ok()) {
+      Log(options_.info_log, "Generated table #%llu@%d: %lld keys, %lld bytes",
+          (unsigned long long)output_number, compact->compaction->level(),
+          (unsigned long long)current_entries,
+          (unsigned long long)current_bytes);
+    }
+  }
+  return s;
+}
+
+Status DBImpl::InstallCompactionResults(CompactionState* compact) {
+  mutex_.AssertHeld();
+  Log(options_.info_log, "Compacted %d@%d + %d@%d files => %lld bytes",
+      compact->compaction->num_input_files(0), compact->compaction->level(),
+      compact->compaction->num_input_files(1), compact->compaction->level() + 1,
+      static_cast<long long>(compact->total_bytes));
+
+  // Add compaction outputs
+  compact->compaction->AddInputDeletions(compact->compaction->edit());
+  const int level = compact->compaction->level();
+  for (size_t i = 0; i < compact->outputs.size(); i++) {
+    const CompactionState::Output& out = compact->outputs[i];
+    compact->compaction->edit()->AddFile(level + 1, out.number, out.file_size,
+                                         out.smallest, out.largest);
+  }
+  return versions_->LogAndApply(compact->compaction->edit(), &mutex_);
+}
+
+Status DBImpl::DoCompactionWork(CompactionState* compact) {
+  const uint64_t start_micros = env_->NowMicros();
+  int64_t imm_micros = 0;  // Micros spent doing imm_ compactions
+
+  Log(options_.info_log, "Compacting %d@%d + %d@%d files",
+      compact->compaction->num_input_files(0), compact->compaction->level(),
+      compact->compaction->num_input_files(1),
+      compact->compaction->level() + 1);
+
+  assert(versions_->NumLevelFiles(compact->compaction->level()) > 0);
+  assert(compact->builder == nullptr);
+  assert(compact->outfile == nullptr);
+  if (snapshots_.empty()) {
+    compact->smallest_snapshot = versions_->LastSequence();
+  } else {
+    compact->smallest_snapshot = snapshots_.oldest()->sequence_number();
+  }
+
+  Iterator* input = versions_->MakeInputIterator(compact->compaction);
+
+  // Release mutex while we're actually doing the compaction work
+  mutex_.Unlock();
+
+  input->SeekToFirst();
+  Status status;
+  ParsedInternalKey ikey;
+  std::string current_user_key;
+  bool has_current_user_key = false;
+  SequenceNumber last_sequence_for_key = kMaxSequenceNumber;
+  while (input->Valid() && !shutting_down_.load(std::memory_order_acquire)) {
+    // Prioritize immutable compaction work
+    if (has_imm_.load(std::memory_order_relaxed)) {
+      const uint64_t imm_start = env_->NowMicros();
+      mutex_.Lock();
+      if (imm_ != nullptr) {
+        CompactMemTable();
+        // Wake up MakeRoomForWrite() if necessary.
+        background_work_finished_signal_.SignalAll();
+      }
+      mutex_.Unlock();
+      imm_micros += (env_->NowMicros() - imm_start);
+    }
+
+    Slice key = input->key();
+    if (compact->compaction->ShouldStopBefore(key) &&
+        compact->builder != nullptr) {
+      status = FinishCompactionOutputFile(compact, input);
+      if (!status.ok()) {
+        break;
+      }
+    }
+
+    // Handle key/value, add to state, etc.
+    bool drop = false;
+    if (!ParseInternalKey(key, &ikey)) {
+      // Do not hide error keys
+      current_user_key.clear();
+      has_current_user_key = false;
+      last_sequence_for_key = kMaxSequenceNumber;
+    } else {
+      if (!has_current_user_key ||
+          user_comparator()->Compare(ikey.user_key, Slice(current_user_key)) !=
+              0) {
+        // First occurrence of this user key
+        current_user_key.assign(ikey.user_key.data(), ikey.user_key.size());
+        has_current_user_key = true;
+        last_sequence_for_key = kMaxSequenceNumber;
+      }
+
+      if (last_sequence_for_key <= compact->smallest_snapshot) {
+        // Hidden by an newer entry for same user key
+        drop = true;  // (A)
+      } else if (ikey.type == kTypeDeletion &&
+                 ikey.sequence <= compact->smallest_snapshot &&
+                 compact->compaction->IsBaseLevelForKey(ikey.user_key)) {
+        // For this user key:
+        // (1) there is no data in higher levels
+        // (2) data in lower levels will have larger sequence numbers
+        // (3) data in layers that are being compacted here and have
+        //     smaller sequence numbers will be dropped in the next
+        //     few iterations of this loop (by rule (A) above).
+        // Therefore this deletion marker is obsolete and can be dropped.
+        drop = true;
+      }
+
+      last_sequence_for_key = ikey.sequence;
+    }
+#if 0
+    Log(options_.info_log,
+        "  Compact: %s, seq %d, type: %d %d, drop: %d, is_base: %d, "
+        "%d smallest_snapshot: %d",
+        ikey.user_key.ToString().c_str(),
+        (int)ikey.sequence, ikey.type, kTypeValue, drop,
+        compact->compaction->IsBaseLevelForKey(ikey.user_key),
+        (int)last_sequence_for_key, (int)compact->smallest_snapshot);
+#endif
+
+    if (!drop) {
+      // Open output file if necessary
+      if (compact->builder == nullptr) {
+        status = OpenCompactionOutputFile(compact);
+        if (!status.ok()) {
+          break;
+        }
+      }
+      if (compact->builder->NumEntries() == 0) {
+        compact->current_output()->smallest.DecodeFrom(key);
+      }
+      compact->current_output()->largest.DecodeFrom(key);
+      compact->builder->Add(key, input->value());
+
+      // Close output file if it is big enough
+      if (compact->builder->FileSize() >=
+          compact->compaction->MaxOutputFileSize()) {
+        status = FinishCompactionOutputFile(compact, input);
+        if (!status.ok()) {
+          break;
+        }
+      }
+    }
+
+    input->Next();
+  }
+
+  if (status.ok() && shutting_down_.load(std::memory_order_acquire)) {
+    status = Status::IOError("Deleting DB during compaction");
+  }
+  if (status.ok() && compact->builder != nullptr) {
+    status = FinishCompactionOutputFile(compact, input);
+  }
+  if (status.ok()) {
+    status = input->status();
+  }
+  delete input;
+  input = nullptr;
+
+  CompactionStats stats;
+  stats.micros = env_->NowMicros() - start_micros - imm_micros;
+  for (int which = 0; which < 2; which++) {
+    for (int i = 0; i < compact->compaction->num_input_files(which); i++) {
+      stats.bytes_read += compact->compaction->input(which, i)->file_size;
+    }
+  }
+  for (size_t i = 0; i < compact->outputs.size(); i++) {
+    stats.bytes_written += compact->outputs[i].file_size;
+  }
+
+  mutex_.Lock();
+  stats_[compact->compaction->level() + 1].Add(stats);
+
+  if (status.ok()) {
+    status = InstallCompactionResults(compact);
+  }
+  if (!status.ok()) {
+    RecordBackgroundError(status);
+  }
+  VersionSet::LevelSummaryStorage tmp;
+  Log(options_.info_log, "compacted to: %s", versions_->LevelSummary(&tmp));
+  return status;
+}
+
+namespace {
+
+struct IterState {
+  port::Mutex* const mu;
+  Version* const version GUARDED_BY(mu);
+  MemTable* const mem GUARDED_BY(mu);
+  MemTable* const imm GUARDED_BY(mu);
+
+  IterState(port::Mutex* mutex, MemTable* mem, MemTable* imm, Version* version)
+      : mu(mutex), version(version), mem(mem), imm(imm) {}
+};
+
+static void CleanupIteratorState(void* arg1, void* arg2) {
+  IterState* state = reinterpret_cast<IterState*>(arg1);
+  state->mu->Lock();
+  state->mem->Unref();
+  if (state->imm != nullptr) state->imm->Unref();
+  state->version->Unref();
+  state->mu->Unlock();
+  delete state;
+}
+
+}  // anonymous namespace
+
+Iterator* DBImpl::NewInternalIterator(const ReadOptions& options,
+                                      SequenceNumber* latest_snapshot,
+                                      uint32_t* seed) {
+  mutex_.Lock();
+  *latest_snapshot = versions_->LastSequence();
+
+  // Collect together all needed child iterators
+  std::vector<Iterator*> list;
+  list.push_back(mem_->NewIterator());
+  mem_->Ref();
+  if (imm_ != nullptr) {
+    list.push_back(imm_->NewIterator());
+    imm_->Ref();
+  }
+  versions_->current()->AddIterators(options, &list);
+  Iterator* internal_iter =
+      NewMergingIterator(&internal_comparator_, &list[0], (uint32_t)list.size());
+  versions_->current()->Ref();
+
+  IterState* cleanup = new IterState(&mutex_, mem_, imm_, versions_->current());
+  internal_iter->RegisterCleanup(CleanupIteratorState, cleanup, nullptr);
+
+  *seed = ++seed_;
+  mutex_.Unlock();
+  return internal_iter;
+}
+
+Iterator* DBImpl::TEST_NewInternalIterator() {
+  SequenceNumber ignored;
+  uint32_t ignored_seed;
+  return NewInternalIterator(ReadOptions(), &ignored, &ignored_seed);
+}
+
+int64_t DBImpl::TEST_MaxNextLevelOverlappingBytes() {
+  MutexLock l(&mutex_);
+  return versions_->MaxNextLevelOverlappingBytes();
+}
+
+Status DBImpl::Get(const ReadOptions& options, const Slice& key,
+                   std::string* value) {
+  Status s;
+  MutexLock l(&mutex_);
+  SequenceNumber snapshot;
+  if (options.snapshot != nullptr) {
+    snapshot =
+        static_cast<const SnapshotImpl*>(options.snapshot)->sequence_number();
+  } else {
+    snapshot = versions_->LastSequence();
+  }
+
+  MemTable* mem = mem_;
+  MemTable* imm = imm_;
+  Version* current = versions_->current();
+  mem->Ref();
+  if (imm != nullptr) imm->Ref();
+  current->Ref();
+
+  bool have_stat_update = false;
+  Version::GetStats stats;
+
+  // Unlock while reading from files and memtables
+  {
+    mutex_.Unlock();
+    // First look in the memtable, then in the immutable memtable (if any).
+    LookupKey lkey(key, snapshot);
+    if (mem->Get(lkey, value, &s)) {
+      // Done
+    } else if (imm != nullptr && imm->Get(lkey, value, &s)) {
+      // Done
+    } else {
+      s = current->Get(options, lkey, value, &stats);
+      have_stat_update = true;
+    }
+    mutex_.Lock();
+  }
+
+  if (have_stat_update && current->UpdateStats(stats)) {
+    MaybeScheduleCompaction();
+  }
+  mem->Unref();
+  if (imm != nullptr) imm->Unref();
+  current->Unref();
+  return s;
+}
+
+Iterator* DBImpl::NewIterator(const ReadOptions& options) {
+  SequenceNumber latest_snapshot;
+  uint32_t seed;
+  Iterator* iter = NewInternalIterator(options, &latest_snapshot, &seed);
+  return NewDBIterator(this, user_comparator(), iter,
+                       (options.snapshot != nullptr
+                            ? static_cast<const SnapshotImpl*>(options.snapshot)
+                                  ->sequence_number()
+                            : latest_snapshot),
+                       seed);
+}
+
+void DBImpl::RecordReadSample(Slice key) {
+  MutexLock l(&mutex_);
+  if (versions_->current()->RecordReadSample(key)) {
+    MaybeScheduleCompaction();
+  }
+}
+
+const Snapshot* DBImpl::GetSnapshot() {
+  MutexLock l(&mutex_);
+  return snapshots_.New(versions_->LastSequence());
+}
+
+void DBImpl::ReleaseSnapshot(const Snapshot* snapshot) {
+  MutexLock l(&mutex_);
+  snapshots_.Delete(static_cast<const SnapshotImpl*>(snapshot));
+}
+
+// Convenience methods
+Status DBImpl::Put(const WriteOptions& o, const Slice& key, const Slice& val) {
+  return DB::Put(o, key, val);
+}
+
+Status DBImpl::Delete(const WriteOptions& options, const Slice& key) {
+  return DB::Delete(options, key);
+}
+
+Status DBImpl::Write(const WriteOptions& options, WriteBatch* updates) {
+  Writer w(&mutex_);
+  w.batch = updates;
+  w.sync = options.sync;
+  w.done = false;
+
+  MutexLock l(&mutex_);
+  writers_.push_back(&w);
+  while (!w.done && &w != writers_.front()) {
+    w.cv.Wait();
+  }
+  if (w.done) {
+    return w.status;
+  }
+
+  // May temporarily unlock and wait.
+  Status status = MakeRoomForWrite(updates == nullptr);
+  uint64_t last_sequence = versions_->LastSequence();
+  Writer* last_writer = &w;
+  if (status.ok() && updates != nullptr) {  // nullptr batch is for compactions
+    WriteBatch* write_batch = BuildBatchGroup(&last_writer);
+    WriteBatchInternal::SetSequence(write_batch, last_sequence + 1);
+    last_sequence += WriteBatchInternal::Count(write_batch);
+
+    // Add to log and apply to memtable.  We can release the lock
+    // during this phase since &w is currently responsible for logging
+    // and protects against concurrent loggers and concurrent writes
+    // into mem_.
+    {
+      mutex_.Unlock();
+      status = log_->AddRecord(WriteBatchInternal::Contents(write_batch));
+      bool sync_error = false;
+      if (status.ok() && options.sync) {
+        status = logfile_->Sync();
+        if (!status.ok()) {
+          sync_error = true;
+        }
+      }
+      if (status.ok()) {
+        status = WriteBatchInternal::InsertInto(write_batch, mem_);
+      }
+      mutex_.Lock();
+      if (sync_error) {
+        // The state of the log file is indeterminate: the log record we
+        // just added may or may not show up when the DB is re-opened.
+        // So we force the DB into a mode where all future writes fail.
+        RecordBackgroundError(status);
+      }
+    }
+    if (write_batch == tmp_batch_) tmp_batch_->Clear();
+
+    versions_->SetLastSequence(last_sequence);
+  }
+
+  while (true) {
+    Writer* ready = writers_.front();
+    writers_.pop_front();
+    if (ready != &w) {
+      ready->status = status;
+      ready->done = true;
+      ready->cv.Signal();
+    }
+    if (ready == last_writer) break;
+  }
+
+  // Notify new head of write queue
+  if (!writers_.empty()) {
+    writers_.front()->cv.Signal();
+  }
+
+  return status;
+}
+
+// REQUIRES: Writer list must be non-empty
+// REQUIRES: First writer must have a non-null batch
+WriteBatch* DBImpl::BuildBatchGroup(Writer** last_writer) {
+  mutex_.AssertHeld();
+  assert(!writers_.empty());
+  Writer* first = writers_.front();
+  WriteBatch* result = first->batch;
+  assert(result != nullptr);
+
+  size_t size = WriteBatchInternal::ByteSize(first->batch);
+
+  // Allow the group to grow up to a maximum size, but if the
+  // original write is small, limit the growth so we do not slow
+  // down the small write too much.
+  size_t max_size = 1 << 20;
+  if (size <= (128 << 10)) {
+    max_size = size + (128 << 10);
+  }
+
+  *last_writer = first;
+  std::deque<Writer*>::iterator iter = writers_.begin();
+  ++iter;  // Advance past "first"
+  for (; iter != writers_.end(); ++iter) {
+    Writer* w = *iter;
+    if (w->sync && !first->sync) {
+      // Do not include a sync write into a batch handled by a non-sync write.
+      break;
+    }
+
+    if (w->batch != nullptr) {
+      size += WriteBatchInternal::ByteSize(w->batch);
+      if (size > max_size) {
+        // Do not make batch too big
+        break;
+      }
+
+      // Append to *result
+      if (result == first->batch) {
+        // Switch to temporary batch instead of disturbing caller's batch
+        result = tmp_batch_;
+        assert(WriteBatchInternal::Count(result) == 0);
+        WriteBatchInternal::Append(result, first->batch);
+      }
+      WriteBatchInternal::Append(result, w->batch);
+    }
+    *last_writer = w;
+  }
+  return result;
+}
+
+// REQUIRES: mutex_ is held
+// REQUIRES: this thread is currently at the front of the writer queue
+Status DBImpl::MakeRoomForWrite(bool force) {
+  mutex_.AssertHeld();
+  assert(!writers_.empty());
+  bool allow_delay = !force;
+  Status s;
+  while (true) {
+    if (!bg_error_.ok()) {
+      // Yield previous error
+      s = bg_error_;
+      break;
+    } else if (allow_delay && versions_->NumLevelFiles(0) >=
+                                  config::kL0_SlowdownWritesTrigger) {
+      // We are getting close to hitting a hard limit on the number of
+      // L0 files.  Rather than delaying a single write by several
+      // seconds when we hit the hard limit, start delaying each
+      // individual write by 1ms to reduce latency variance.  Also,
+      // this delay hands over some CPU to the compaction thread in
+      // case it is sharing the same core as the writer.
+      mutex_.Unlock();
+      env_->SleepForMicroseconds(1000);
+      allow_delay = false;  // Do not delay a single write more than once
+      mutex_.Lock();
+    } else if (!force &&
+               (mem_->ApproximateMemoryUsage() <= options_.write_buffer_size)) {
+      // There is room in current memtable
+      break;
+    } else if (imm_ != nullptr) {
+      // We have filled up the current memtable, but the previous
+      // one is still being compacted, so we wait.
+      Log(options_.info_log, "Current memtable full; waiting...\n");
+      background_work_finished_signal_.Wait();
+    } else if (versions_->NumLevelFiles(0) >= config::kL0_StopWritesTrigger) {
+      // There are too many level-0 files.
+      Log(options_.info_log, "Too many L0 files; waiting...\n");
+      background_work_finished_signal_.Wait();
+    } else {
+      // Attempt to switch to a new memtable and trigger compaction of old
+      assert(versions_->PrevLogNumber() == 0);
+      uint64_t new_log_number = versions_->NewFileNumber();
+      WritableFile* lfile = nullptr;
+      s = env_->NewWritableFile(LogFileName(dbname_, new_log_number), &lfile);
+      if (!s.ok()) {
+        // Avoid chewing through file number space in a tight loop.
+        versions_->ReuseFileNumber(new_log_number);
+        break;
+      }
+      delete log_;
+      delete logfile_;
+      logfile_ = lfile;
+      logfile_number_ = new_log_number;
+      log_ = new log::Writer(lfile);
+      imm_ = mem_;
+      has_imm_.store(true, std::memory_order_release);
+      mem_ = new MemTable(internal_comparator_);
+      mem_->Ref();
+      force = false;  // Do not force another compaction if have room
+      MaybeScheduleCompaction();
+    }
+  }
+  return s;
+}
+
+bool DBImpl::GetProperty(const Slice& property, std::string* value) {
+  value->clear();
+
+  MutexLock l(&mutex_);
+  Slice in = property;
+  Slice prefix("leveldb.");
+  if (!in.starts_with(prefix)) return false;
+  in.remove_prefix(prefix.size());
+
+  if (in.starts_with("num-files-at-level")) {
+    in.remove_prefix(strlen("num-files-at-level"));
+    uint64_t level;
+    bool ok = ConsumeDecimalNumber(&in, &level) && in.empty();
+    if (!ok || level >= config::kNumLevels) {
+      return false;
+    } else {
+      char buf[100];
+      std::snprintf(buf, sizeof(buf), "%d",
+                    versions_->NumLevelFiles(static_cast<int>(level)));
+      *value = buf;
+      return true;
+    }
+  } else if (in == "stats") {
+    char buf[200];
+    std::snprintf(buf, sizeof(buf),
+                  "                               Compactions\n"
+                  "Level  Files Size(MB) Time(sec) Read(MB) Write(MB)\n"
+                  "--------------------------------------------------\n");
+    value->append(buf);
+    for (int level = 0; level < config::kNumLevels; level++) {
+      int files = versions_->NumLevelFiles(level);
+      if (stats_[level].micros > 0 || files > 0) {
+        std::snprintf(buf, sizeof(buf), "%3d %8d %8.0f %9.0f %8.0f %9.0f\n",
+                      level, files, versions_->NumLevelBytes(level) / 1048576.0,
+                      stats_[level].micros / 1e6,
+                      stats_[level].bytes_read / 1048576.0,
+                      stats_[level].bytes_written / 1048576.0);
+        value->append(buf);
+      }
+    }
+    return true;
+  } else if (in == "sstables") {
+    *value = versions_->current()->DebugString();
+    return true;
+  } else if (in == "approximate-memory-usage") {
+    size_t total_usage = options_.block_cache->TotalCharge();
+    if (mem_) {
+      total_usage += mem_->ApproximateMemoryUsage();
+    }
+    if (imm_) {
+      total_usage += imm_->ApproximateMemoryUsage();
+    }
+    char buf[50];
+    std::snprintf(buf, sizeof(buf), "%llu",
+                  static_cast<unsigned long long>(total_usage));
+    value->append(buf);
+    return true;
+  }
+
+  return false;
+}
+
+void DBImpl::GetApproximateSizes(const Range* range, int n, uint64_t* sizes) {
+  // TODO(opt): better implementation
+  MutexLock l(&mutex_);
+  Version* v = versions_->current();
+  v->Ref();
+
+  for (int i = 0; i < n; i++) {
+    // Convert user_key into a corresponding internal key.
+    InternalKey k1(range[i].start, kMaxSequenceNumber, kValueTypeForSeek);
+    InternalKey k2(range[i].limit, kMaxSequenceNumber, kValueTypeForSeek);
+    uint64_t start = versions_->ApproximateOffsetOf(v, k1);
+    uint64_t limit = versions_->ApproximateOffsetOf(v, k2);
+    sizes[i] = (limit >= start ? limit - start : 0);
+  }
+
+  v->Unref();
+}
+
+// Default implementations of convenience methods that subclasses of DB
+// can call if they wish
+Status DB::Put(const WriteOptions& opt, const Slice& key, const Slice& value) {
+  WriteBatch batch;
+  batch.Put(key, value);
+  return Write(opt, &batch);
+}
+
+Status DB::Delete(const WriteOptions& opt, const Slice& key) {
+  WriteBatch batch;
+  batch.Delete(key);
+  return Write(opt, &batch);
+}
+
+DB::~DB() = default;
+
+Status DB::Open(const Options& options, const std::string& dbname, DB** dbptr) {
+  *dbptr = nullptr;
+
+  DBImpl* impl = new DBImpl(options, dbname);
+  impl->mutex_.Lock();
+  VersionEdit edit;
+  // Recover handles create_if_missing, error_if_exists
+  bool save_manifest = false;
+  Status s = impl->Recover(&edit, &save_manifest);
+  if (s.ok() && impl->mem_ == nullptr) {
+    // Create new log and a corresponding memtable.
+    uint64_t new_log_number = impl->versions_->NewFileNumber();
+    WritableFile* lfile;
+    s = options.env->NewWritableFile(LogFileName(dbname, new_log_number),
+                                     &lfile);
+    if (s.ok()) {
+      edit.SetLogNumber(new_log_number);
+      impl->logfile_ = lfile;
+      impl->logfile_number_ = new_log_number;
+      impl->log_ = new log::Writer(lfile);
+      impl->mem_ = new MemTable(impl->internal_comparator_);
+      impl->mem_->Ref();
+    }
+  }
+  if (s.ok() && save_manifest) {
+    edit.SetPrevLogNumber(0);  // No older logs needed after recovery.
+    edit.SetLogNumber(impl->logfile_number_);
+    s = impl->versions_->LogAndApply(&edit, &impl->mutex_);
+  }
+  if (s.ok()) {
+    impl->RemoveObsoleteFiles();
+    impl->MaybeScheduleCompaction();
+  }
+  impl->mutex_.Unlock();
+  if (s.ok()) {
+    assert(impl->mem_ != nullptr);
+    *dbptr = impl;
+  } else {
+    delete impl;
+  }
+  return s;
+}
+
+Snapshot::~Snapshot() = default;
+
+Status DestroyDB(const std::string& dbname, const Options& options) {
+  Env* env = options.env;
+  std::vector<std::string> filenames;
+  Status result = env->GetChildren(dbname, &filenames);
+  if (!result.ok()) {
+    // Ignore error in case directory does not exist
+    return Status::OK();
+  }
+
+  FileLock* lock;
+  const std::string lockname = LockFileName(dbname);
+  result = env->LockFile(lockname, &lock);
+  if (result.ok()) {
+    uint64_t number;
+    FileType type;
+    for (size_t i = 0; i < filenames.size(); i++) {
+      if (ParseFileName(filenames[i], &number, &type) &&
+          type != kDBLockFile) {  // Lock file will be deleted at end
+        Status del = env->RemoveFile(dbname + "/" + filenames[i]);
+        if (result.ok() && !del.ok()) {
+          result = del;
+        }
+      }
+    }
+    env->UnlockFile(lock);  // Ignore error since state is already gone
+    env->RemoveFile(lockname);
+    env->RemoveDir(dbname);  // Ignore error in case dir contains other files
+  }
+  return result;
+}
+
+}  // namespace leveldb

Pods/leveldb-library/db/db_impl.h

@@ -0,0 +1,217 @@
+// 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_DB_IMPL_H_
+#define STORAGE_LEVELDB_DB_DB_IMPL_H_
+
+#include <atomic>
+#include <deque>
+#include <set>
+#include <string>
+
+#include "db/dbformat.h"
+#include "db/log_writer.h"
+#include "db/snapshot.h"
+#include "leveldb/db.h"
+#include "leveldb/env.h"
+#include "port/port.h"
+#include "port/thread_annotations.h"
+
+namespace leveldb {
+
+class MemTable;
+class TableCache;
+class Version;
+class VersionEdit;
+class VersionSet;
+
+class DBImpl : public DB {
+ public:
+  DBImpl(const Options& options, const std::string& dbname);
+
+  DBImpl(const DBImpl&) = delete;
+  DBImpl& operator=(const DBImpl&) = delete;
+
+  ~DBImpl() override;
+
+  // Implementations of the DB interface
+  Status Put(const WriteOptions&, const Slice& key,
+             const Slice& value) override;
+  Status Delete(const WriteOptions&, const Slice& key) override;
+  Status Write(const WriteOptions& options, WriteBatch* updates) override;
+  Status Get(const ReadOptions& options, const Slice& key,
+             std::string* value) override;
+  Iterator* NewIterator(const ReadOptions&) override;
+  const Snapshot* GetSnapshot() override;
+  void ReleaseSnapshot(const Snapshot* snapshot) override;
+  bool GetProperty(const Slice& property, std::string* value) override;
+  void GetApproximateSizes(const Range* range, int n, uint64_t* sizes) override;
+  void CompactRange(const Slice* begin, const Slice* end) override;
+
+  // Extra methods (for testing) that are not in the public DB interface
+
+  // Compact any files in the named level that overlap [*begin,*end]
+  void TEST_CompactRange(int level, const Slice* begin, const Slice* end);
+
+  // Force current memtable contents to be compacted.
+  Status TEST_CompactMemTable();
+
+  // Return an internal iterator over the current state of the database.
+  // The keys of this iterator are internal keys (see format.h).
+  // The returned iterator should be deleted when no longer needed.
+  Iterator* TEST_NewInternalIterator();
+
+  // Return the maximum overlapping data (in bytes) at next level for any
+  // file at a level >= 1.
+  int64_t TEST_MaxNextLevelOverlappingBytes();
+
+  // Record a sample of bytes read at the specified internal key.
+  // Samples are taken approximately once every config::kReadBytesPeriod
+  // bytes.
+  void RecordReadSample(Slice key);
+
+ private:
+  friend class DB;
+  struct CompactionState;
+  struct Writer;
+
+  // Information for a manual compaction
+  struct ManualCompaction {
+    int level;
+    bool done;
+    const InternalKey* begin;  // null means beginning of key range
+    const InternalKey* end;    // null means end of key range
+    InternalKey tmp_storage;   // Used to keep track of compaction progress
+  };
+
+  // Per level compaction stats.  stats_[level] stores the stats for
+  // compactions that produced data for the specified "level".
+  struct CompactionStats {
+    CompactionStats() : micros(0), bytes_read(0), bytes_written(0) {}
+
+    void Add(const CompactionStats& c) {
+      this->micros += c.micros;
+      this->bytes_read += c.bytes_read;
+      this->bytes_written += c.bytes_written;
+    }
+
+    int64_t micros;
+    int64_t bytes_read;
+    int64_t bytes_written;
+  };
+
+  Iterator* NewInternalIterator(const ReadOptions&,
+                                SequenceNumber* latest_snapshot,
+                                uint32_t* seed);
+
+  Status NewDB();
+
+  // Recover the descriptor from persistent storage.  May do a significant
+  // amount of work to recover recently logged updates.  Any changes to
+  // be made to the descriptor are added to *edit.
+  Status Recover(VersionEdit* edit, bool* save_manifest)
+      EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+
+  void MaybeIgnoreError(Status* s) const;
+
+  // Delete any unneeded files and stale in-memory entries.
+  void RemoveObsoleteFiles() EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+
+  // Compact the in-memory write buffer to disk.  Switches to a new
+  // log-file/memtable and writes a new descriptor iff successful.
+  // Errors are recorded in bg_error_.
+  void CompactMemTable() EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+
+  Status RecoverLogFile(uint64_t log_number, bool last_log, bool* save_manifest,
+                        VersionEdit* edit, SequenceNumber* max_sequence)
+      EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+
+  Status WriteLevel0Table(MemTable* mem, VersionEdit* edit, Version* base)
+      EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+
+  Status MakeRoomForWrite(bool force /* compact even if there is room? */)
+      EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+  WriteBatch* BuildBatchGroup(Writer** last_writer)
+      EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+
+  void RecordBackgroundError(const Status& s);
+
+  void MaybeScheduleCompaction() EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+  static void BGWork(void* db);
+  void BackgroundCall();
+  void BackgroundCompaction() EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+  void CleanupCompaction(CompactionState* compact)
+      EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+  Status DoCompactionWork(CompactionState* compact)
+      EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+
+  Status OpenCompactionOutputFile(CompactionState* compact);
+  Status FinishCompactionOutputFile(CompactionState* compact, Iterator* input);
+  Status InstallCompactionResults(CompactionState* compact)
+      EXCLUSIVE_LOCKS_REQUIRED(mutex_);
+
+  const Comparator* user_comparator() const {
+    return internal_comparator_.user_comparator();
+  }
+
+  // Constant after construction
+  Env* const env_;
+  const InternalKeyComparator internal_comparator_;
+  const InternalFilterPolicy internal_filter_policy_;
+  const Options options_;  // options_.comparator == &internal_comparator_
+  const bool owns_info_log_;
+  const bool owns_cache_;
+  const std::string dbname_;
+
+  // table_cache_ provides its own synchronization
+  TableCache* const table_cache_;
+
+  // Lock over the persistent DB state.  Non-null iff successfully acquired.
+  FileLock* db_lock_;
+
+  // State below is protected by mutex_
+  port::Mutex mutex_;
+  std::atomic<bool> shutting_down_;
+  port::CondVar background_work_finished_signal_ GUARDED_BY(mutex_);
+  MemTable* mem_;
+  MemTable* imm_ GUARDED_BY(mutex_);  // Memtable being compacted
+  std::atomic<bool> has_imm_;         // So bg thread can detect non-null imm_
+  WritableFile* logfile_;
+  uint64_t logfile_number_ GUARDED_BY(mutex_);
+  log::Writer* log_;
+  uint32_t seed_ GUARDED_BY(mutex_);  // For sampling.
+
+  // Queue of writers.
+  std::deque<Writer*> writers_ GUARDED_BY(mutex_);
+  WriteBatch* tmp_batch_ GUARDED_BY(mutex_);
+
+  SnapshotList snapshots_ GUARDED_BY(mutex_);
+
+  // Set of table files to protect from deletion because they are
+  // part of ongoing compactions.
+  std::set<uint64_t> pending_outputs_ GUARDED_BY(mutex_);
+
+  // Has a background compaction been scheduled or is running?
+  bool background_compaction_scheduled_ GUARDED_BY(mutex_);
+
+  ManualCompaction* manual_compaction_ GUARDED_BY(mutex_);
+
+  VersionSet* const versions_ GUARDED_BY(mutex_);
+
+  // Have we encountered a background error in paranoid mode?
+  Status bg_error_ GUARDED_BY(mutex_);
+
+  CompactionStats stats_[config::kNumLevels] GUARDED_BY(mutex_);
+};
+
+// Sanitize db options.  The caller should delete result.info_log if
+// it is not equal to src.info_log.
+Options SanitizeOptions(const std::string& db,
+                        const InternalKeyComparator* icmp,
+                        const InternalFilterPolicy* ipolicy,
+                        const Options& src);
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_DB_IMPL_H_

Pods/leveldb-library/db/db_iter.cc

@@ -0,0 +1,318 @@
+// 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/db_iter.h"
+
+#include "db/db_impl.h"
+#include "db/dbformat.h"
+#include "db/filename.h"
+#include "leveldb/env.h"
+#include "leveldb/iterator.h"
+#include "port/port.h"
+#include "util/logging.h"
+#include "util/mutexlock.h"
+#include "util/random.h"
+
+namespace leveldb {
+
+#if 0
+static void DumpInternalIter(Iterator* iter) {
+  for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
+    ParsedInternalKey k;
+    if (!ParseInternalKey(iter->key(), &k)) {
+      std::fprintf(stderr, "Corrupt '%s'\n", EscapeString(iter->key()).c_str());
+    } else {
+      std::fprintf(stderr, "@ '%s'\n", k.DebugString().c_str());
+    }
+  }
+}
+#endif
+
+namespace {
+
+// Memtables and sstables that make the DB representation contain
+// (userkey,seq,type) => uservalue entries.  DBIter
+// combines multiple entries for the same userkey found in the DB
+// representation into a single entry while accounting for sequence
+// numbers, deletion markers, overwrites, etc.
+class DBIter : public Iterator {
+ public:
+  // Which direction is the iterator currently moving?
+  // (1) When moving forward, the internal iterator is positioned at
+  //     the exact entry that yields this->key(), this->value()
+  // (2) When moving backwards, the internal iterator is positioned
+  //     just before all entries whose user key == this->key().
+  enum Direction { kForward, kReverse };
+
+  DBIter(DBImpl* db, const Comparator* cmp, Iterator* iter, SequenceNumber s,
+         uint32_t seed)
+      : db_(db),
+        user_comparator_(cmp),
+        iter_(iter),
+        sequence_(s),
+        direction_(kForward),
+        valid_(false),
+        rnd_(seed),
+        bytes_until_read_sampling_(RandomCompactionPeriod()) {}
+
+  DBIter(const DBIter&) = delete;
+  DBIter& operator=(const DBIter&) = delete;
+
+  ~DBIter() override { delete iter_; }
+  bool Valid() const override { return valid_; }
+  Slice key() const override {
+    assert(valid_);
+    return (direction_ == kForward) ? ExtractUserKey(iter_->key()) : saved_key_;
+  }
+  Slice value() const override {
+    assert(valid_);
+    return (direction_ == kForward) ? iter_->value() : saved_value_;
+  }
+  Status status() const override {
+    if (status_.ok()) {
+      return iter_->status();
+    } else {
+      return status_;
+    }
+  }
+
+  void Next() override;
+  void Prev() override;
+  void Seek(const Slice& target) override;
+  void SeekToFirst() override;
+  void SeekToLast() override;
+
+ private:
+  void FindNextUserEntry(bool skipping, std::string* skip);
+  void FindPrevUserEntry();
+  bool ParseKey(ParsedInternalKey* key);
+
+  inline void SaveKey(const Slice& k, std::string* dst) {
+    dst->assign(k.data(), k.size());
+  }
+
+  inline void ClearSavedValue() {
+    if (saved_value_.capacity() > 1048576) {
+      std::string empty;
+      swap(empty, saved_value_);
+    } else {
+      saved_value_.clear();
+    }
+  }
+
+  // Picks the number of bytes that can be read until a compaction is scheduled.
+  size_t RandomCompactionPeriod() {
+    return rnd_.Uniform(2 * config::kReadBytesPeriod);
+  }
+
+  DBImpl* db_;
+  const Comparator* const user_comparator_;
+  Iterator* const iter_;
+  SequenceNumber const sequence_;
+  Status status_;
+  std::string saved_key_;    // == current key when direction_==kReverse
+  std::string saved_value_;  // == current raw value when direction_==kReverse
+  Direction direction_;
+  bool valid_;
+  Random rnd_;
+  size_t bytes_until_read_sampling_;
+};
+
+inline bool DBIter::ParseKey(ParsedInternalKey* ikey) {
+  Slice k = iter_->key();
+
+  size_t bytes_read = k.size() + iter_->value().size();
+  while (bytes_until_read_sampling_ < bytes_read) {
+    bytes_until_read_sampling_ += RandomCompactionPeriod();
+    db_->RecordReadSample(k);
+  }
+  assert(bytes_until_read_sampling_ >= bytes_read);
+  bytes_until_read_sampling_ -= bytes_read;
+
+  if (!ParseInternalKey(k, ikey)) {
+    status_ = Status::Corruption("corrupted internal key in DBIter");
+    return false;
+  } else {
+    return true;
+  }
+}
+
+void DBIter::Next() {
+  assert(valid_);
+
+  if (direction_ == kReverse) {  // Switch directions?
+    direction_ = kForward;
+    // iter_ is pointing just before the entries for this->key(),
+    // so advance into the range of entries for this->key() and then
+    // use the normal skipping code below.
+    if (!iter_->Valid()) {
+      iter_->SeekToFirst();
+    } else {
+      iter_->Next();
+    }
+    if (!iter_->Valid()) {
+      valid_ = false;
+      saved_key_.clear();
+      return;
+    }
+    // saved_key_ already contains the key to skip past.
+  } else {
+    // Store in saved_key_ the current key so we skip it below.
+    SaveKey(ExtractUserKey(iter_->key()), &saved_key_);
+
+    // iter_ is pointing to current key. We can now safely move to the next to
+    // avoid checking current key.
+    iter_->Next();
+    if (!iter_->Valid()) {
+      valid_ = false;
+      saved_key_.clear();
+      return;
+    }
+  }
+
+  FindNextUserEntry(true, &saved_key_);
+}
+
+void DBIter::FindNextUserEntry(bool skipping, std::string* skip) {
+  // Loop until we hit an acceptable entry to yield
+  assert(iter_->Valid());
+  assert(direction_ == kForward);
+  do {
+    ParsedInternalKey ikey;
+    if (ParseKey(&ikey) && ikey.sequence <= sequence_) {
+      switch (ikey.type) {
+        case kTypeDeletion:
+          // Arrange to skip all upcoming entries for this key since
+          // they are hidden by this deletion.
+          SaveKey(ikey.user_key, skip);
+          skipping = true;
+          break;
+        case kTypeValue:
+          if (skipping &&
+              user_comparator_->Compare(ikey.user_key, *skip) <= 0) {
+            // Entry hidden
+          } else {
+            valid_ = true;
+            saved_key_.clear();
+            return;
+          }
+          break;
+      }
+    }
+    iter_->Next();
+  } while (iter_->Valid());
+  saved_key_.clear();
+  valid_ = false;
+}
+
+void DBIter::Prev() {
+  assert(valid_);
+
+  if (direction_ == kForward) {  // Switch directions?
+    // iter_ is pointing at the current entry.  Scan backwards until
+    // the key changes so we can use the normal reverse scanning code.
+    assert(iter_->Valid());  // Otherwise valid_ would have been false
+    SaveKey(ExtractUserKey(iter_->key()), &saved_key_);
+    while (true) {
+      iter_->Prev();
+      if (!iter_->Valid()) {
+        valid_ = false;
+        saved_key_.clear();
+        ClearSavedValue();
+        return;
+      }
+      if (user_comparator_->Compare(ExtractUserKey(iter_->key()), saved_key_) <
+          0) {
+        break;
+      }
+    }
+    direction_ = kReverse;
+  }
+
+  FindPrevUserEntry();
+}
+
+void DBIter::FindPrevUserEntry() {
+  assert(direction_ == kReverse);
+
+  ValueType value_type = kTypeDeletion;
+  if (iter_->Valid()) {
+    do {
+      ParsedInternalKey ikey;
+      if (ParseKey(&ikey) && ikey.sequence <= sequence_) {
+        if ((value_type != kTypeDeletion) &&
+            user_comparator_->Compare(ikey.user_key, saved_key_) < 0) {
+          // We encountered a non-deleted value in entries for previous keys,
+          break;
+        }
+        value_type = ikey.type;
+        if (value_type == kTypeDeletion) {
+          saved_key_.clear();
+          ClearSavedValue();
+        } else {
+          Slice raw_value = iter_->value();
+          if (saved_value_.capacity() > raw_value.size() + 1048576) {
+            std::string empty;
+            swap(empty, saved_value_);
+          }
+          SaveKey(ExtractUserKey(iter_->key()), &saved_key_);
+          saved_value_.assign(raw_value.data(), raw_value.size());
+        }
+      }
+      iter_->Prev();
+    } while (iter_->Valid());
+  }
+
+  if (value_type == kTypeDeletion) {
+    // End
+    valid_ = false;
+    saved_key_.clear();
+    ClearSavedValue();
+    direction_ = kForward;
+  } else {
+    valid_ = true;
+  }
+}
+
+void DBIter::Seek(const Slice& target) {
+  direction_ = kForward;
+  ClearSavedValue();
+  saved_key_.clear();
+  AppendInternalKey(&saved_key_,
+                    ParsedInternalKey(target, sequence_, kValueTypeForSeek));
+  iter_->Seek(saved_key_);
+  if (iter_->Valid()) {
+    FindNextUserEntry(false, &saved_key_ /* temporary storage */);
+  } else {
+    valid_ = false;
+  }
+}
+
+void DBIter::SeekToFirst() {
+  direction_ = kForward;
+  ClearSavedValue();
+  iter_->SeekToFirst();
+  if (iter_->Valid()) {
+    FindNextUserEntry(false, &saved_key_ /* temporary storage */);
+  } else {
+    valid_ = false;
+  }
+}
+
+void DBIter::SeekToLast() {
+  direction_ = kReverse;
+  ClearSavedValue();
+  iter_->SeekToLast();
+  FindPrevUserEntry();
+}
+
+}  // anonymous namespace
+
+Iterator* NewDBIterator(DBImpl* db, const Comparator* user_key_comparator,
+                        Iterator* internal_iter, SequenceNumber sequence,
+                        uint32_t seed) {
+  return new DBIter(db, user_key_comparator, internal_iter, sequence, seed);
+}
+
+}  // namespace leveldb

Pods/leveldb-library/db/db_iter.h

@@ -0,0 +1,26 @@
+// 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_DB_ITER_H_
+#define STORAGE_LEVELDB_DB_DB_ITER_H_
+
+#include <cstdint>
+
+#include "db/dbformat.h"
+#include "leveldb/db.h"
+
+namespace leveldb {
+
+class DBImpl;
+
+// Return a new iterator that converts internal keys (yielded by
+// "*internal_iter") that were live at the specified "sequence" number
+// into appropriate user keys.
+Iterator* NewDBIterator(DBImpl* db, const Comparator* user_key_comparator,
+                        Iterator* internal_iter, SequenceNumber sequence,
+                        uint32_t seed);
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_DB_ITER_H_

Pods/leveldb-library/db/dbformat.cc

@@ -0,0 +1,136 @@
+// 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 <cstdio>
+#include <sstream>
+
+#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 {
+  std::ostringstream ss;
+  ss << '\'' << EscapeString(user_key.ToString()) << "' @ " << sequence << " : "
+     << static_cast<int>(type);
+  return ss.str();
+}
+
+std::string InternalKey::DebugString() const {
+  ParsedInternalKey parsed;
+  if (ParseInternalKey(rep_, &parsed)) {
+    return parsed.DebugString();
+  }
+  std::ostringstream ss;
+  ss << "(bad)" << EscapeString(rep_);
+  return ss.str();
+}
+
+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, (uint32_t)usize + 8);
+  kstart_ = dst;
+  std::memcpy(dst, user_key.data(), usize);
+  dst += usize;
+  EncodeFixed64(dst, PackSequenceAndType(s, kValueTypeForSeek));
+  dst += 8;
+  end_ = dst;
+}
+
+}  // namespace leveldb

Pods/leveldb-library/db/dbformat.h

@@ -0,0 +1,224 @@
+// 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_DBFORMAT_H_
+#define STORAGE_LEVELDB_DB_DBFORMAT_H_
+
+#include <cstddef>
+#include <cstdint>
+#include <string>
+
+#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;
+
+// Approximate gap in bytes between samples of data read during iteration.
+static const int kReadBytesPeriod = 1048576;
+
+}  // 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.
+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.
+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);
+}
+
+// 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) {}
+  const char* Name() const override;
+  int Compare(const Slice& a, const Slice& b) const override;
+  void FindShortestSeparator(std::string* start,
+                             const Slice& limit) const override;
+  void FindShortSuccessor(std::string* key) const override;
+
+  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) {}
+  const char* Name() const override;
+  void CreateFilter(const Slice* keys, int n, std::string* dst) const override;
+  bool KeyMayMatch(const Slice& key, const Slice& filter) const override;
+};
+
+// 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));
+  }
+
+  bool DecodeFrom(const Slice& s) {
+    rep_.assign(s.data(), s.size());
+    return !rep_.empty();
+  }
+
+  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);
+  uint8_t 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<uint8_t>(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(const LookupKey&) = delete;
+  LookupKey& operator=(const LookupKey&) = delete;
+
+  ~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
+};
+
+inline LookupKey::~LookupKey() {
+  if (start_ != space_) delete[] start_;
+}
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_DBFORMAT_H_

Pods/leveldb-library/db/dumpfile.cc

@@ -0,0 +1,232 @@
+// Copyright (c) 2012 The LevelDB Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file. See the AUTHORS file for names of contributors.
+
+#include "leveldb/dumpfile.h"
+
+#include <cstdio>
+
+#include "db/dbformat.h"
+#include "db/filename.h"
+#include "db/log_reader.h"
+#include "db/version_edit.h"
+#include "db/write_batch_internal.h"
+#include "leveldb/env.h"
+#include "leveldb/iterator.h"
+#include "leveldb/options.h"
+#include "leveldb/status.h"
+#include "leveldb/table.h"
+#include "leveldb/write_batch.h"
+#include "util/logging.h"
+
+namespace leveldb {
+
+namespace {
+
+bool GuessType(const std::string& fname, FileType* type) {
+  size_t pos = fname.rfind('/');
+  std::string basename;
+  if (pos == std::string::npos) {
+    basename = fname;
+  } else {
+    basename = std::string(fname.data() + pos + 1, fname.size() - pos - 1);
+  }
+  uint64_t ignored;
+  return ParseFileName(basename, &ignored, type);
+}
+
+// Notified when log reader encounters corruption.
+class CorruptionReporter : public log::Reader::Reporter {
+ public:
+  void Corruption(size_t bytes, const Status& status) override {
+    std::string r = "corruption: ";
+    AppendNumberTo(&r, bytes);
+    r += " bytes; ";
+    r += status.ToString();
+    r.push_back('\n');
+    dst_->Append(r);
+  }
+
+  WritableFile* dst_;
+};
+
+// Print contents of a log file. (*func)() is called on every record.
+Status PrintLogContents(Env* env, const std::string& fname,
+                        void (*func)(uint64_t, Slice, WritableFile*),
+                        WritableFile* dst) {
+  SequentialFile* file;
+  Status s = env->NewSequentialFile(fname, &file);
+  if (!s.ok()) {
+    return s;
+  }
+  CorruptionReporter reporter;
+  reporter.dst_ = dst;
+  log::Reader reader(file, &reporter, true, 0);
+  Slice record;
+  std::string scratch;
+  while (reader.ReadRecord(&record, &scratch)) {
+    (*func)(reader.LastRecordOffset(), record, dst);
+  }
+  delete file;
+  return Status::OK();
+}
+
+// Called on every item found in a WriteBatch.
+class WriteBatchItemPrinter : public WriteBatch::Handler {
+ public:
+  void Put(const Slice& key, const Slice& value) override {
+    std::string r = "  put '";
+    AppendEscapedStringTo(&r, key);
+    r += "' '";
+    AppendEscapedStringTo(&r, value);
+    r += "'\n";
+    dst_->Append(r);
+  }
+  void Delete(const Slice& key) override {
+    std::string r = "  del '";
+    AppendEscapedStringTo(&r, key);
+    r += "'\n";
+    dst_->Append(r);
+  }
+
+  WritableFile* dst_;
+};
+
+// Called on every log record (each one of which is a WriteBatch)
+// found in a kLogFile.
+static void WriteBatchPrinter(uint64_t pos, Slice record, WritableFile* dst) {
+  std::string r = "--- offset ";
+  AppendNumberTo(&r, pos);
+  r += "; ";
+  if (record.size() < 12) {
+    r += "log record length ";
+    AppendNumberTo(&r, record.size());
+    r += " is too small\n";
+    dst->Append(r);
+    return;
+  }
+  WriteBatch batch;
+  WriteBatchInternal::SetContents(&batch, record);
+  r += "sequence ";
+  AppendNumberTo(&r, WriteBatchInternal::Sequence(&batch));
+  r.push_back('\n');
+  dst->Append(r);
+  WriteBatchItemPrinter batch_item_printer;
+  batch_item_printer.dst_ = dst;
+  Status s = batch.Iterate(&batch_item_printer);
+  if (!s.ok()) {
+    dst->Append("  error: " + s.ToString() + "\n");
+  }
+}
+
+Status DumpLog(Env* env, const std::string& fname, WritableFile* dst) {
+  return PrintLogContents(env, fname, WriteBatchPrinter, dst);
+}
+
+// Called on every log record (each one of which is a WriteBatch)
+// found in a kDescriptorFile.
+static void VersionEditPrinter(uint64_t pos, Slice record, WritableFile* dst) {
+  std::string r = "--- offset ";
+  AppendNumberTo(&r, pos);
+  r += "; ";
+  VersionEdit edit;
+  Status s = edit.DecodeFrom(record);
+  if (!s.ok()) {
+    r += s.ToString();
+    r.push_back('\n');
+  } else {
+    r += edit.DebugString();
+  }
+  dst->Append(r);
+}
+
+Status DumpDescriptor(Env* env, const std::string& fname, WritableFile* dst) {
+  return PrintLogContents(env, fname, VersionEditPrinter, dst);
+}
+
+Status DumpTable(Env* env, const std::string& fname, WritableFile* dst) {
+  uint64_t file_size;
+  RandomAccessFile* file = nullptr;
+  Table* table = nullptr;
+  Status s = env->GetFileSize(fname, &file_size);
+  if (s.ok()) {
+    s = env->NewRandomAccessFile(fname, &file);
+  }
+  if (s.ok()) {
+    // We use the default comparator, which may or may not match the
+    // comparator used in this database. However this should not cause
+    // problems since we only use Table operations that do not require
+    // any comparisons.  In particular, we do not call Seek or Prev.
+    s = Table::Open(Options(), file, file_size, &table);
+  }
+  if (!s.ok()) {
+    delete table;
+    delete file;
+    return s;
+  }
+
+  ReadOptions ro;
+  ro.fill_cache = false;
+  Iterator* iter = table->NewIterator(ro);
+  std::string r;
+  for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
+    r.clear();
+    ParsedInternalKey key;
+    if (!ParseInternalKey(iter->key(), &key)) {
+      r = "badkey '";
+      AppendEscapedStringTo(&r, iter->key());
+      r += "' => '";
+      AppendEscapedStringTo(&r, iter->value());
+      r += "'\n";
+      dst->Append(r);
+    } else {
+      r = "'";
+      AppendEscapedStringTo(&r, key.user_key);
+      r += "' @ ";
+      AppendNumberTo(&r, key.sequence);
+      r += " : ";
+      if (key.type == kTypeDeletion) {
+        r += "del";
+      } else if (key.type == kTypeValue) {
+        r += "val";
+      } else {
+        AppendNumberTo(&r, key.type);
+      }
+      r += " => '";
+      AppendEscapedStringTo(&r, iter->value());
+      r += "'\n";
+      dst->Append(r);
+    }
+  }
+  s = iter->status();
+  if (!s.ok()) {
+    dst->Append("iterator error: " + s.ToString() + "\n");
+  }
+
+  delete iter;
+  delete table;
+  delete file;
+  return Status::OK();
+}
+
+}  // namespace
+
+Status DumpFile(Env* env, const std::string& fname, WritableFile* dst) {
+  FileType ftype;
+  if (!GuessType(fname, &ftype)) {
+    return Status::InvalidArgument(fname + ": unknown file type");
+  }
+  switch (ftype) {
+    case kLogFile:
+      return DumpLog(env, fname, dst);
+    case kDescriptorFile:
+      return DumpDescriptor(env, fname, dst);
+    case kTableFile:
+      return DumpTable(env, fname, dst);
+    default:
+      break;
+  }
+  return Status::InvalidArgument(fname + ": not a dump-able file type");
+}
+
+}  // namespace leveldb

Pods/leveldb-library/db/filename.cc

@@ -0,0 +1,141 @@
+// 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/filename.h"
+
+#include <cassert>
+#include <cstdio>
+
+#include "db/dbformat.h"
+#include "leveldb/env.h"
+#include "util/logging.h"
+
+namespace leveldb {
+
+// A utility routine: write "data" to the named file and Sync() it.
+Status WriteStringToFileSync(Env* env, const Slice& data,
+                             const std::string& fname);
+
+static std::string MakeFileName(const std::string& dbname, uint64_t number,
+                                const char* suffix) {
+  char buf[100];
+  std::snprintf(buf, sizeof(buf), "/%06llu.%s",
+                static_cast<unsigned long long>(number), suffix);
+  return dbname + buf;
+}
+
+std::string LogFileName(const std::string& dbname, uint64_t number) {
+  assert(number > 0);
+  return MakeFileName(dbname, number, "log");
+}
+
+std::string TableFileName(const std::string& dbname, uint64_t number) {
+  assert(number > 0);
+  return MakeFileName(dbname, number, "ldb");
+}
+
+std::string SSTTableFileName(const std::string& dbname, uint64_t number) {
+  assert(number > 0);
+  return MakeFileName(dbname, number, "sst");
+}
+
+std::string DescriptorFileName(const std::string& dbname, uint64_t number) {
+  assert(number > 0);
+  char buf[100];
+  std::snprintf(buf, sizeof(buf), "/MANIFEST-%06llu",
+                static_cast<unsigned long long>(number));
+  return dbname + buf;
+}
+
+std::string CurrentFileName(const std::string& dbname) {
+  return dbname + "/CURRENT";
+}
+
+std::string LockFileName(const std::string& dbname) { return dbname + "/LOCK"; }
+
+std::string TempFileName(const std::string& dbname, uint64_t number) {
+  assert(number > 0);
+  return MakeFileName(dbname, number, "dbtmp");
+}
+
+std::string InfoLogFileName(const std::string& dbname) {
+  return dbname + "/LOG";
+}
+
+// Return the name of the old info log file for "dbname".
+std::string OldInfoLogFileName(const std::string& dbname) {
+  return dbname + "/LOG.old";
+}
+
+// Owned filenames have the form:
+//    dbname/CURRENT
+//    dbname/LOCK
+//    dbname/LOG
+//    dbname/LOG.old
+//    dbname/MANIFEST-[0-9]+
+//    dbname/[0-9]+.(log|sst|ldb)
+bool ParseFileName(const std::string& filename, uint64_t* number,
+                   FileType* type) {
+  Slice rest(filename);
+  if (rest == "CURRENT") {
+    *number = 0;
+    *type = kCurrentFile;
+  } else if (rest == "LOCK") {
+    *number = 0;
+    *type = kDBLockFile;
+  } else if (rest == "LOG" || rest == "LOG.old") {
+    *number = 0;
+    *type = kInfoLogFile;
+  } else if (rest.starts_with("MANIFEST-")) {
+    rest.remove_prefix(strlen("MANIFEST-"));
+    uint64_t num;
+    if (!ConsumeDecimalNumber(&rest, &num)) {
+      return false;
+    }
+    if (!rest.empty()) {
+      return false;
+    }
+    *type = kDescriptorFile;
+    *number = num;
+  } else {
+    // Avoid strtoull() to keep filename format independent of the
+    // current locale
+    uint64_t num;
+    if (!ConsumeDecimalNumber(&rest, &num)) {
+      return false;
+    }
+    Slice suffix = rest;
+    if (suffix == Slice(".log")) {
+      *type = kLogFile;
+    } else if (suffix == Slice(".sst") || suffix == Slice(".ldb")) {
+      *type = kTableFile;
+    } else if (suffix == Slice(".dbtmp")) {
+      *type = kTempFile;
+    } else {
+      return false;
+    }
+    *number = num;
+  }
+  return true;
+}
+
+Status SetCurrentFile(Env* env, const std::string& dbname,
+                      uint64_t descriptor_number) {
+  // Remove leading "dbname/" and add newline to manifest file name
+  std::string manifest = DescriptorFileName(dbname, descriptor_number);
+  Slice contents = manifest;
+  assert(contents.starts_with(dbname + "/"));
+  contents.remove_prefix(dbname.size() + 1);
+  std::string tmp = TempFileName(dbname, descriptor_number);
+  Status s = WriteStringToFileSync(env, contents.ToString() + "\n", tmp);
+  if (s.ok()) {
+    s = env->RenameFile(tmp, CurrentFileName(dbname));
+  }
+  if (!s.ok()) {
+    env->RemoveFile(tmp);
+  }
+  return s;
+}
+
+}  // namespace leveldb

Pods/leveldb-library/db/filename.h

@@ -0,0 +1,83 @@
+// 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.
+//
+// File names used by DB code
+
+#ifndef STORAGE_LEVELDB_DB_FILENAME_H_
+#define STORAGE_LEVELDB_DB_FILENAME_H_
+
+#include <cstdint>
+#include <string>
+
+#include "leveldb/slice.h"
+#include "leveldb/status.h"
+#include "port/port.h"
+
+namespace leveldb {
+
+class Env;
+
+enum FileType {
+  kLogFile,
+  kDBLockFile,
+  kTableFile,
+  kDescriptorFile,
+  kCurrentFile,
+  kTempFile,
+  kInfoLogFile  // Either the current one, or an old one
+};
+
+// Return the name of the log file with the specified number
+// in the db named by "dbname".  The result will be prefixed with
+// "dbname".
+std::string LogFileName(const std::string& dbname, uint64_t number);
+
+// Return the name of the sstable with the specified number
+// in the db named by "dbname".  The result will be prefixed with
+// "dbname".
+std::string TableFileName(const std::string& dbname, uint64_t number);
+
+// Return the legacy file name for an sstable with the specified number
+// in the db named by "dbname". The result will be prefixed with
+// "dbname".
+std::string SSTTableFileName(const std::string& dbname, uint64_t number);
+
+// Return the name of the descriptor file for the db named by
+// "dbname" and the specified incarnation number.  The result will be
+// prefixed with "dbname".
+std::string DescriptorFileName(const std::string& dbname, uint64_t number);
+
+// Return the name of the current file.  This file contains the name
+// of the current manifest file.  The result will be prefixed with
+// "dbname".
+std::string CurrentFileName(const std::string& dbname);
+
+// Return the name of the lock file for the db named by
+// "dbname".  The result will be prefixed with "dbname".
+std::string LockFileName(const std::string& dbname);
+
+// Return the name of a temporary file owned by the db named "dbname".
+// The result will be prefixed with "dbname".
+std::string TempFileName(const std::string& dbname, uint64_t number);
+
+// Return the name of the info log file for "dbname".
+std::string InfoLogFileName(const std::string& dbname);
+
+// Return the name of the old info log file for "dbname".
+std::string OldInfoLogFileName(const std::string& dbname);
+
+// If filename is a leveldb file, store the type of the file in *type.
+// The number encoded in the filename is stored in *number.  If the
+// filename was successfully parsed, returns true.  Else return false.
+bool ParseFileName(const std::string& filename, uint64_t* number,
+                   FileType* type);
+
+// Make the CURRENT file point to the descriptor file with the
+// specified number.
+Status SetCurrentFile(Env* env, const std::string& dbname,
+                      uint64_t descriptor_number);
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_FILENAME_H_

Pods/leveldb-library/db/log_format.h

@@ -0,0 +1,35 @@
+// 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.
+//
+// Log format information shared by reader and writer.
+// See ../doc/log_format.md for more detail.
+
+#ifndef STORAGE_LEVELDB_DB_LOG_FORMAT_H_
+#define STORAGE_LEVELDB_DB_LOG_FORMAT_H_
+
+namespace leveldb {
+namespace log {
+
+enum RecordType {
+  // Zero is reserved for preallocated files
+  kZeroType = 0,
+
+  kFullType = 1,
+
+  // For fragments
+  kFirstType = 2,
+  kMiddleType = 3,
+  kLastType = 4
+};
+static const int kMaxRecordType = kLastType;
+
+static const int kBlockSize = 32768;
+
+// Header is checksum (4 bytes), length (2 bytes), type (1 byte).
+static const int kHeaderSize = 4 + 2 + 1;
+
+}  // namespace log
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_LOG_FORMAT_H_

Pods/leveldb-library/db/log_reader.cc

@@ -0,0 +1,274 @@
+// 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/log_reader.h"
+
+#include <cstdio>
+
+#include "leveldb/env.h"
+#include "util/coding.h"
+#include "util/crc32c.h"
+
+namespace leveldb {
+namespace log {
+
+Reader::Reporter::~Reporter() = default;
+
+Reader::Reader(SequentialFile* file, Reporter* reporter, bool checksum,
+               uint64_t initial_offset)
+    : file_(file),
+      reporter_(reporter),
+      checksum_(checksum),
+      backing_store_(new char[kBlockSize]),
+      buffer_(),
+      eof_(false),
+      last_record_offset_(0),
+      end_of_buffer_offset_(0),
+      initial_offset_(initial_offset),
+      resyncing_(initial_offset > 0) {}
+
+Reader::~Reader() { delete[] backing_store_; }
+
+bool Reader::SkipToInitialBlock() {
+  const size_t offset_in_block = initial_offset_ % kBlockSize;
+  uint64_t block_start_location = initial_offset_ - offset_in_block;
+
+  // Don't search a block if we'd be in the trailer
+  if (offset_in_block > kBlockSize - 6) {
+    block_start_location += kBlockSize;
+  }
+
+  end_of_buffer_offset_ = block_start_location;
+
+  // Skip to start of first block that can contain the initial record
+  if (block_start_location > 0) {
+    Status skip_status = file_->Skip(block_start_location);
+    if (!skip_status.ok()) {
+      ReportDrop(block_start_location, skip_status);
+      return false;
+    }
+  }
+
+  return true;
+}
+
+bool Reader::ReadRecord(Slice* record, std::string* scratch) {
+  if (last_record_offset_ < initial_offset_) {
+    if (!SkipToInitialBlock()) {
+      return false;
+    }
+  }
+
+  scratch->clear();
+  record->clear();
+  bool in_fragmented_record = false;
+  // Record offset of the logical record that we're reading
+  // 0 is a dummy value to make compilers happy
+  uint64_t prospective_record_offset = 0;
+
+  Slice fragment;
+  while (true) {
+    const unsigned int record_type = ReadPhysicalRecord(&fragment);
+
+    // ReadPhysicalRecord may have only had an empty trailer remaining in its
+    // internal buffer. Calculate the offset of the next physical record now
+    // that it has returned, properly accounting for its header size.
+    uint64_t physical_record_offset =
+        end_of_buffer_offset_ - buffer_.size() - kHeaderSize - fragment.size();
+
+    if (resyncing_) {
+      if (record_type == kMiddleType) {
+        continue;
+      } else if (record_type == kLastType) {
+        resyncing_ = false;
+        continue;
+      } else {
+        resyncing_ = false;
+      }
+    }
+
+    switch (record_type) {
+      case kFullType:
+        if (in_fragmented_record) {
+          // Handle bug in earlier versions of log::Writer where
+          // it could emit an empty kFirstType record at the tail end
+          // of a block followed by a kFullType or kFirstType record
+          // at the beginning of the next block.
+          if (!scratch->empty()) {
+            ReportCorruption(scratch->size(), "partial record without end(1)");
+          }
+        }
+        prospective_record_offset = physical_record_offset;
+        scratch->clear();
+        *record = fragment;
+        last_record_offset_ = prospective_record_offset;
+        return true;
+
+      case kFirstType:
+        if (in_fragmented_record) {
+          // Handle bug in earlier versions of log::Writer where
+          // it could emit an empty kFirstType record at the tail end
+          // of a block followed by a kFullType or kFirstType record
+          // at the beginning of the next block.
+          if (!scratch->empty()) {
+            ReportCorruption(scratch->size(), "partial record without end(2)");
+          }
+        }
+        prospective_record_offset = physical_record_offset;
+        scratch->assign(fragment.data(), fragment.size());
+        in_fragmented_record = true;
+        break;
+
+      case kMiddleType:
+        if (!in_fragmented_record) {
+          ReportCorruption(fragment.size(),
+                           "missing start of fragmented record(1)");
+        } else {
+          scratch->append(fragment.data(), fragment.size());
+        }
+        break;
+
+      case kLastType:
+        if (!in_fragmented_record) {
+          ReportCorruption(fragment.size(),
+                           "missing start of fragmented record(2)");
+        } else {
+          scratch->append(fragment.data(), fragment.size());
+          *record = Slice(*scratch);
+          last_record_offset_ = prospective_record_offset;
+          return true;
+        }
+        break;
+
+      case kEof:
+        if (in_fragmented_record) {
+          // This can be caused by the writer dying immediately after
+          // writing a physical record but before completing the next; don't
+          // treat it as a corruption, just ignore the entire logical record.
+          scratch->clear();
+        }
+        return false;
+
+      case kBadRecord:
+        if (in_fragmented_record) {
+          ReportCorruption(scratch->size(), "error in middle of record");
+          in_fragmented_record = false;
+          scratch->clear();
+        }
+        break;
+
+      default: {
+        char buf[40];
+        std::snprintf(buf, sizeof(buf), "unknown record type %u", record_type);
+        ReportCorruption(
+            (fragment.size() + (in_fragmented_record ? scratch->size() : 0)),
+            buf);
+        in_fragmented_record = false;
+        scratch->clear();
+        break;
+      }
+    }
+  }
+  return false;
+}
+
+uint64_t Reader::LastRecordOffset() { return last_record_offset_; }
+
+void Reader::ReportCorruption(uint64_t bytes, const char* reason) {
+  ReportDrop(bytes, Status::Corruption(reason));
+}
+
+void Reader::ReportDrop(uint64_t bytes, const Status& reason) {
+  if (reporter_ != nullptr &&
+      end_of_buffer_offset_ - buffer_.size() - bytes >= initial_offset_) {
+    reporter_->Corruption(static_cast<size_t>(bytes), reason);
+  }
+}
+
+unsigned int Reader::ReadPhysicalRecord(Slice* result) {
+  while (true) {
+    if (buffer_.size() < kHeaderSize) {
+      if (!eof_) {
+        // Last read was a full read, so this is a trailer to skip
+        buffer_.clear();
+        Status status = file_->Read(kBlockSize, &buffer_, backing_store_);
+        end_of_buffer_offset_ += buffer_.size();
+        if (!status.ok()) {
+          buffer_.clear();
+          ReportDrop(kBlockSize, status);
+          eof_ = true;
+          return kEof;
+        } else if (buffer_.size() < kBlockSize) {
+          eof_ = true;
+        }
+        continue;
+      } else {
+        // Note that if buffer_ is non-empty, we have a truncated header at the
+        // end of the file, which can be caused by the writer crashing in the
+        // middle of writing the header. Instead of considering this an error,
+        // just report EOF.
+        buffer_.clear();
+        return kEof;
+      }
+    }
+
+    // Parse the header
+    const char* header = buffer_.data();
+    const uint32_t a = static_cast<uint32_t>(header[4]) & 0xff;
+    const uint32_t b = static_cast<uint32_t>(header[5]) & 0xff;
+    const unsigned int type = header[6];
+    const uint32_t length = a | (b << 8);
+    if (kHeaderSize + length > buffer_.size()) {
+      size_t drop_size = buffer_.size();
+      buffer_.clear();
+      if (!eof_) {
+        ReportCorruption(drop_size, "bad record length");
+        return kBadRecord;
+      }
+      // If the end of the file has been reached without reading |length| bytes
+      // of payload, assume the writer died in the middle of writing the record.
+      // Don't report a corruption.
+      return kEof;
+    }
+
+    if (type == kZeroType && length == 0) {
+      // Skip zero length record without reporting any drops since
+      // such records are produced by the mmap based writing code in
+      // env_posix.cc that preallocates file regions.
+      buffer_.clear();
+      return kBadRecord;
+    }
+
+    // Check crc
+    if (checksum_) {
+      uint32_t expected_crc = crc32c::Unmask(DecodeFixed32(header));
+      uint32_t actual_crc = crc32c::Value(header + 6, 1 + length);
+      if (actual_crc != expected_crc) {
+        // Drop the rest of the buffer since "length" itself may have
+        // been corrupted and if we trust it, we could find some
+        // fragment of a real log record that just happens to look
+        // like a valid log record.
+        size_t drop_size = buffer_.size();
+        buffer_.clear();
+        ReportCorruption(drop_size, "checksum mismatch");
+        return kBadRecord;
+      }
+    }
+
+    buffer_.remove_prefix(kHeaderSize + length);
+
+    // Skip physical record that started before initial_offset_
+    if (end_of_buffer_offset_ - buffer_.size() - kHeaderSize - length <
+        initial_offset_) {
+      result->clear();
+      return kBadRecord;
+    }
+
+    *result = Slice(header + kHeaderSize, length);
+    return type;
+  }
+}
+
+}  // namespace log
+}  // namespace leveldb

Pods/leveldb-library/db/log_reader.h

@@ -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.
+
+#ifndef STORAGE_LEVELDB_DB_LOG_READER_H_
+#define STORAGE_LEVELDB_DB_LOG_READER_H_
+
+#include <cstdint>
+
+#include "db/log_format.h"
+#include "leveldb/slice.h"
+#include "leveldb/status.h"
+
+namespace leveldb {
+
+class SequentialFile;
+
+namespace log {
+
+class Reader {
+ public:
+  // Interface for reporting errors.
+  class Reporter {
+   public:
+    virtual ~Reporter();
+
+    // Some corruption was detected.  "size" is the approximate number
+    // of bytes dropped due to the corruption.
+    virtual void Corruption(size_t bytes, const Status& status) = 0;
+  };
+
+  // Create a reader that will return log records from "*file".
+  // "*file" must remain live while this Reader is in use.
+  //
+  // If "reporter" is non-null, it is notified whenever some data is
+  // dropped due to a detected corruption.  "*reporter" must remain
+  // live while this Reader is in use.
+  //
+  // If "checksum" is true, verify checksums if available.
+  //
+  // The Reader will start reading at the first record located at physical
+  // position >= initial_offset within the file.
+  Reader(SequentialFile* file, Reporter* reporter, bool checksum,
+         uint64_t initial_offset);
+
+  Reader(const Reader&) = delete;
+  Reader& operator=(const Reader&) = delete;
+
+  ~Reader();
+
+  // Read the next record into *record.  Returns true if read
+  // successfully, false if we hit end of the input.  May use
+  // "*scratch" as temporary storage.  The contents filled in *record
+  // will only be valid until the next mutating operation on this
+  // reader or the next mutation to *scratch.
+  bool ReadRecord(Slice* record, std::string* scratch);
+
+  // Returns the physical offset of the last record returned by ReadRecord.
+  //
+  // Undefined before the first call to ReadRecord.
+  uint64_t LastRecordOffset();
+
+ private:
+  // Extend record types with the following special values
+  enum {
+    kEof = kMaxRecordType + 1,
+    // Returned whenever we find an invalid physical record.
+    // Currently there are three situations in which this happens:
+    // * The record has an invalid CRC (ReadPhysicalRecord reports a drop)
+    // * The record is a 0-length record (No drop is reported)
+    // * The record is below constructor's initial_offset (No drop is reported)
+    kBadRecord = kMaxRecordType + 2
+  };
+
+  // Skips all blocks that are completely before "initial_offset_".
+  //
+  // Returns true on success. Handles reporting.
+  bool SkipToInitialBlock();
+
+  // Return type, or one of the preceding special values
+  unsigned int ReadPhysicalRecord(Slice* result);
+
+  // Reports dropped bytes to the reporter.
+  // buffer_ must be updated to remove the dropped bytes prior to invocation.
+  void ReportCorruption(uint64_t bytes, const char* reason);
+  void ReportDrop(uint64_t bytes, const Status& reason);
+
+  SequentialFile* const file_;
+  Reporter* const reporter_;
+  bool const checksum_;
+  char* const backing_store_;
+  Slice buffer_;
+  bool eof_;  // Last Read() indicated EOF by returning < kBlockSize
+
+  // Offset of the last record returned by ReadRecord.
+  uint64_t last_record_offset_;
+  // Offset of the first location past the end of buffer_.
+  uint64_t end_of_buffer_offset_;
+
+  // Offset at which to start looking for the first record to return
+  uint64_t const initial_offset_;
+
+  // True if we are resynchronizing after a seek (initial_offset_ > 0). In
+  // particular, a run of kMiddleType and kLastType records can be silently
+  // skipped in this mode
+  bool resyncing_;
+};
+
+}  // namespace log
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_LOG_READER_H_

Pods/leveldb-library/db/log_writer.cc

@@ -0,0 +1,111 @@
+// 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/log_writer.h"
+
+#include <cstdint>
+
+#include "leveldb/env.h"
+#include "util/coding.h"
+#include "util/crc32c.h"
+
+namespace leveldb {
+namespace log {
+
+static void InitTypeCrc(uint32_t* type_crc) {
+  for (int i = 0; i <= kMaxRecordType; i++) {
+    char t = static_cast<char>(i);
+    type_crc[i] = crc32c::Value(&t, 1);
+  }
+}
+
+Writer::Writer(WritableFile* dest) : dest_(dest), block_offset_(0) {
+  InitTypeCrc(type_crc_);
+}
+
+Writer::Writer(WritableFile* dest, uint64_t dest_length)
+    : dest_(dest), block_offset_(dest_length % kBlockSize) {
+  InitTypeCrc(type_crc_);
+}
+
+Writer::~Writer() = default;
+
+Status Writer::AddRecord(const Slice& slice) {
+  const char* ptr = slice.data();
+  size_t left = slice.size();
+
+  // Fragment the record if necessary and emit it.  Note that if slice
+  // is empty, we still want to iterate once to emit a single
+  // zero-length record
+  Status s;
+  bool begin = true;
+  do {
+    const int leftover = kBlockSize - block_offset_;
+    assert(leftover >= 0);
+    if (leftover < kHeaderSize) {
+      // Switch to a new block
+      if (leftover > 0) {
+        // Fill the trailer (literal below relies on kHeaderSize being 7)
+        static_assert(kHeaderSize == 7, "");
+        dest_->Append(Slice("\x00\x00\x00\x00\x00\x00", leftover));
+      }
+      block_offset_ = 0;
+    }
+
+    // Invariant: we never leave < kHeaderSize bytes in a block.
+    assert(kBlockSize - block_offset_ - kHeaderSize >= 0);
+
+    const size_t avail = kBlockSize - block_offset_ - kHeaderSize;
+    const size_t fragment_length = (left < avail) ? left : avail;
+
+    RecordType type;
+    const bool end = (left == fragment_length);
+    if (begin && end) {
+      type = kFullType;
+    } else if (begin) {
+      type = kFirstType;
+    } else if (end) {
+      type = kLastType;
+    } else {
+      type = kMiddleType;
+    }
+
+    s = EmitPhysicalRecord(type, ptr, fragment_length);
+    ptr += fragment_length;
+    left -= fragment_length;
+    begin = false;
+  } while (s.ok() && left > 0);
+  return s;
+}
+
+Status Writer::EmitPhysicalRecord(RecordType t, const char* ptr,
+                                  size_t length) {
+  assert(length <= 0xffff);  // Must fit in two bytes
+  assert(block_offset_ + kHeaderSize + length <= kBlockSize);
+
+  // Format the header
+  char buf[kHeaderSize];
+  buf[4] = static_cast<char>(length & 0xff);
+  buf[5] = static_cast<char>(length >> 8);
+  buf[6] = static_cast<char>(t);
+
+  // Compute the crc of the record type and the payload.
+  uint32_t crc = crc32c::Extend(type_crc_[t], ptr, length);
+  crc = crc32c::Mask(crc);  // Adjust for storage
+  EncodeFixed32(buf, crc);
+
+  // Write the header and the payload
+  Status s = dest_->Append(Slice(buf, kHeaderSize));
+  if (s.ok()) {
+    s = dest_->Append(Slice(ptr, length));
+    if (s.ok()) {
+      s = dest_->Flush();
+    }
+  }
+  block_offset_ += kHeaderSize + length;
+  return s;
+}
+
+}  // namespace log
+}  // namespace leveldb

Pods/leveldb-library/db/log_writer.h

@@ -0,0 +1,54 @@
+// 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_LOG_WRITER_H_
+#define STORAGE_LEVELDB_DB_LOG_WRITER_H_
+
+#include <cstdint>
+
+#include "db/log_format.h"
+#include "leveldb/slice.h"
+#include "leveldb/status.h"
+
+namespace leveldb {
+
+class WritableFile;
+
+namespace log {
+
+class Writer {
+ public:
+  // Create a writer that will append data to "*dest".
+  // "*dest" must be initially empty.
+  // "*dest" must remain live while this Writer is in use.
+  explicit Writer(WritableFile* dest);
+
+  // Create a writer that will append data to "*dest".
+  // "*dest" must have initial length "dest_length".
+  // "*dest" must remain live while this Writer is in use.
+  Writer(WritableFile* dest, uint64_t dest_length);
+
+  Writer(const Writer&) = delete;
+  Writer& operator=(const Writer&) = delete;
+
+  ~Writer();
+
+  Status AddRecord(const Slice& slice);
+
+ private:
+  Status EmitPhysicalRecord(RecordType type, const char* ptr, size_t length);
+
+  WritableFile* dest_;
+  int block_offset_;  // Current offset in block
+
+  // crc32c values for all supported record types.  These are
+  // pre-computed to reduce the overhead of computing the crc of the
+  // record type stored in the header.
+  uint32_t type_crc_[kMaxRecordType + 1];
+};
+
+}  // namespace log
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_LOG_WRITER_H_

Pods/leveldb-library/db/memtable.cc

@@ -0,0 +1,137 @@
+// 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/memtable.h"
+#include "db/dbformat.h"
+#include "leveldb/comparator.h"
+#include "leveldb/env.h"
+#include "leveldb/iterator.h"
+#include "util/coding.h"
+
+namespace leveldb {
+
+static Slice GetLengthPrefixedSlice(const char* data) {
+  uint32_t len;
+  const char* p = data;
+  p = GetVarint32Ptr(p, p + 5, &len);  // +5: we assume "p" is not corrupted
+  return Slice(p, len);
+}
+
+MemTable::MemTable(const InternalKeyComparator& comparator)
+    : comparator_(comparator), refs_(0), table_(comparator_, &arena_) {}
+
+MemTable::~MemTable() { assert(refs_ == 0); }
+
+size_t MemTable::ApproximateMemoryUsage() { return arena_.MemoryUsage(); }
+
+int MemTable::KeyComparator::operator()(const char* aptr,
+                                        const char* bptr) const {
+  // Internal keys are encoded as length-prefixed strings.
+  Slice a = GetLengthPrefixedSlice(aptr);
+  Slice b = GetLengthPrefixedSlice(bptr);
+  return comparator.Compare(a, b);
+}
+
+// Encode a suitable internal key target for "target" and return it.
+// Uses *scratch as scratch space, and the returned pointer will point
+// into this scratch space.
+static const char* EncodeKey(std::string* scratch, const Slice& target) {
+  scratch->clear();
+  PutVarint32(scratch, (uint32_t)target.size());
+  scratch->append(target.data(), target.size());
+  return scratch->data();
+}
+
+class MemTableIterator : public Iterator {
+ public:
+  explicit MemTableIterator(MemTable::Table* table) : iter_(table) {}
+
+  MemTableIterator(const MemTableIterator&) = delete;
+  MemTableIterator& operator=(const MemTableIterator&) = delete;
+
+  ~MemTableIterator() override = default;
+
+  bool Valid() const override { return iter_.Valid(); }
+  void Seek(const Slice& k) override { iter_.Seek(EncodeKey(&tmp_, k)); }
+  void SeekToFirst() override { iter_.SeekToFirst(); }
+  void SeekToLast() override { iter_.SeekToLast(); }
+  void Next() override { iter_.Next(); }
+  void Prev() override { iter_.Prev(); }
+  Slice key() const override { return GetLengthPrefixedSlice(iter_.key()); }
+  Slice value() const override {
+    Slice key_slice = GetLengthPrefixedSlice(iter_.key());
+    return GetLengthPrefixedSlice(key_slice.data() + key_slice.size());
+  }
+
+  Status status() const override { return Status::OK(); }
+
+ private:
+  MemTable::Table::Iterator iter_;
+  std::string tmp_;  // For passing to EncodeKey
+};
+
+Iterator* MemTable::NewIterator() { return new MemTableIterator(&table_); }
+
+void MemTable::Add(SequenceNumber s, ValueType type, const Slice& key,
+                   const Slice& value) {
+  // Format of an entry is concatenation of:
+  //  key_size     : varint32 of internal_key.size()
+  //  key bytes    : char[internal_key.size()]
+  //  value_size   : varint32 of value.size()
+  //  value bytes  : char[value.size()]
+  size_t key_size = key.size();
+  size_t val_size = value.size();
+  size_t internal_key_size = key_size + 8;
+  const size_t encoded_len = VarintLength(internal_key_size) +
+                             internal_key_size + VarintLength(val_size) +
+                             val_size;
+  char* buf = arena_.Allocate(encoded_len);
+  char* p = EncodeVarint32(buf, (uint32_t)internal_key_size);
+  std::memcpy(p, key.data(), key_size);
+  p += key_size;
+  EncodeFixed64(p, (s << 8) | type);
+  p += 8;
+  p = EncodeVarint32(p, (uint32_t)val_size);
+  std::memcpy(p, value.data(), val_size);
+  assert(p + val_size == buf + encoded_len);
+  table_.Insert(buf);
+}
+
+bool MemTable::Get(const LookupKey& key, std::string* value, Status* s) {
+  Slice memkey = key.memtable_key();
+  Table::Iterator iter(&table_);
+  iter.Seek(memkey.data());
+  if (iter.Valid()) {
+    // entry format is:
+    //    klength  varint32
+    //    userkey  char[klength]
+    //    tag      uint64
+    //    vlength  varint32
+    //    value    char[vlength]
+    // Check that it belongs to same user key.  We do not check the
+    // sequence number since the Seek() call above should have skipped
+    // all entries with overly large sequence numbers.
+    const char* entry = iter.key();
+    uint32_t key_length;
+    const char* key_ptr = GetVarint32Ptr(entry, entry + 5, &key_length);
+    if (comparator_.comparator.user_comparator()->Compare(
+            Slice(key_ptr, key_length - 8), key.user_key()) == 0) {
+      // Correct user key
+      const uint64_t tag = DecodeFixed64(key_ptr + key_length - 8);
+      switch (static_cast<ValueType>(tag & 0xff)) {
+        case kTypeValue: {
+          Slice v = GetLengthPrefixedSlice(key_ptr + key_length);
+          value->assign(v.data(), v.size());
+          return true;
+        }
+        case kTypeDeletion:
+          *s = Status::NotFound(Slice());
+          return true;
+      }
+    }
+  }
+  return false;
+}
+
+}  // namespace leveldb

Pods/leveldb-library/db/memtable.h

@@ -0,0 +1,87 @@
+// 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_MEMTABLE_H_
+#define STORAGE_LEVELDB_DB_MEMTABLE_H_
+
+#include <string>
+
+#include "db/dbformat.h"
+#include "db/skiplist.h"
+#include "leveldb/db.h"
+#include "util/arena.h"
+
+namespace leveldb {
+
+class InternalKeyComparator;
+class MemTableIterator;
+
+class MemTable {
+ public:
+  // MemTables are reference counted.  The initial reference count
+  // is zero and the caller must call Ref() at least once.
+  explicit MemTable(const InternalKeyComparator& comparator);
+
+  MemTable(const MemTable&) = delete;
+  MemTable& operator=(const MemTable&) = delete;
+
+  // Increase reference count.
+  void Ref() { ++refs_; }
+
+  // Drop reference count.  Delete if no more references exist.
+  void Unref() {
+    --refs_;
+    assert(refs_ >= 0);
+    if (refs_ <= 0) {
+      delete this;
+    }
+  }
+
+  // Returns an estimate of the number of bytes of data in use by this
+  // data structure. It is safe to call when MemTable is being modified.
+  size_t ApproximateMemoryUsage();
+
+  // Return an iterator that yields the contents of the memtable.
+  //
+  // The caller must ensure that the underlying MemTable remains live
+  // while the returned iterator is live.  The keys returned by this
+  // iterator are internal keys encoded by AppendInternalKey in the
+  // db/format.{h,cc} module.
+  Iterator* NewIterator();
+
+  // Add an entry into memtable that maps key to value at the
+  // specified sequence number and with the specified type.
+  // Typically value will be empty if type==kTypeDeletion.
+  void Add(SequenceNumber seq, ValueType type, const Slice& key,
+           const Slice& value);
+
+  // If memtable contains a value for key, store it in *value and return true.
+  // If memtable contains a deletion for key, store a NotFound() error
+  // in *status and return true.
+  // Else, return false.
+  bool Get(const LookupKey& key, std::string* value, Status* s);
+
+ private:
+  friend class MemTableIterator;
+  friend class MemTableBackwardIterator;
+
+  struct KeyComparator {
+    const InternalKeyComparator comparator;
+    explicit KeyComparator(const InternalKeyComparator& c) : comparator(c) {}
+    int operator()(const char* a, const char* b) const;
+  };
+
+  typedef SkipList<const char*, KeyComparator> Table;
+
+  ~MemTable();  // Private since only Unref() should be used to delete it
+
+  KeyComparator comparator_;
+  int refs_;
+  Arena arena_;
+  Table table_;
+};
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_MEMTABLE_H_

Pods/leveldb-library/db/repair.cc

@@ -0,0 +1,451 @@
+// 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.
+//
+// We recover the contents of the descriptor from the other files we find.
+// (1) Any log files are first converted to tables
+// (2) We scan every table to compute
+//     (a) smallest/largest for the table
+//     (b) largest sequence number in the table
+// (3) We generate descriptor contents:
+//      - log number is set to zero
+//      - next-file-number is set to 1 + largest file number we found
+//      - last-sequence-number is set to largest sequence# found across
+//        all tables (see 2c)
+//      - compaction pointers are cleared
+//      - every table file is added at level 0
+//
+// Possible optimization 1:
+//   (a) Compute total size and use to pick appropriate max-level M
+//   (b) Sort tables by largest sequence# in the table
+//   (c) For each table: if it overlaps earlier table, place in level-0,
+//       else place in level-M.
+// Possible optimization 2:
+//   Store per-table metadata (smallest, largest, largest-seq#, ...)
+//   in the table's meta section to speed up ScanTable.
+
+#include "db/builder.h"
+#include "db/db_impl.h"
+#include "db/dbformat.h"
+#include "db/filename.h"
+#include "db/log_reader.h"
+#include "db/log_writer.h"
+#include "db/memtable.h"
+#include "db/table_cache.h"
+#include "db/version_edit.h"
+#include "db/write_batch_internal.h"
+#include "leveldb/comparator.h"
+#include "leveldb/db.h"
+#include "leveldb/env.h"
+
+namespace leveldb {
+
+namespace {
+
+class Repairer {
+ public:
+  Repairer(const std::string& dbname, const Options& options)
+      : dbname_(dbname),
+        env_(options.env),
+        icmp_(options.comparator),
+        ipolicy_(options.filter_policy),
+        options_(SanitizeOptions(dbname, &icmp_, &ipolicy_, options)),
+        owns_info_log_(options_.info_log != options.info_log),
+        owns_cache_(options_.block_cache != options.block_cache),
+        next_file_number_(1) {
+    // TableCache can be small since we expect each table to be opened once.
+    table_cache_ = new TableCache(dbname_, options_, 10);
+  }
+
+  ~Repairer() {
+    delete table_cache_;
+    if (owns_info_log_) {
+      delete options_.info_log;
+    }
+    if (owns_cache_) {
+      delete options_.block_cache;
+    }
+  }
+
+  Status Run() {
+    Status status = FindFiles();
+    if (status.ok()) {
+      ConvertLogFilesToTables();
+      ExtractMetaData();
+      status = WriteDescriptor();
+    }
+    if (status.ok()) {
+      unsigned long long bytes = 0;
+      for (size_t i = 0; i < tables_.size(); i++) {
+        bytes += tables_[i].meta.file_size;
+      }
+      Log(options_.info_log,
+          "**** Repaired leveldb %s; "
+          "recovered %d files; %llu bytes. "
+          "Some data may have been lost. "
+          "****",
+          dbname_.c_str(), static_cast<int>(tables_.size()), bytes);
+    }
+    return status;
+  }
+
+ private:
+  struct TableInfo {
+    FileMetaData meta;
+    SequenceNumber max_sequence;
+  };
+
+  Status FindFiles() {
+    std::vector<std::string> filenames;
+    Status status = env_->GetChildren(dbname_, &filenames);
+    if (!status.ok()) {
+      return status;
+    }
+    if (filenames.empty()) {
+      return Status::IOError(dbname_, "repair found no files");
+    }
+
+    uint64_t number;
+    FileType type;
+    for (size_t i = 0; i < filenames.size(); i++) {
+      if (ParseFileName(filenames[i], &number, &type)) {
+        if (type == kDescriptorFile) {
+          manifests_.push_back(filenames[i]);
+        } else {
+          if (number + 1 > next_file_number_) {
+            next_file_number_ = number + 1;
+          }
+          if (type == kLogFile) {
+            logs_.push_back(number);
+          } else if (type == kTableFile) {
+            table_numbers_.push_back(number);
+          } else {
+            // Ignore other files
+          }
+        }
+      }
+    }
+    return status;
+  }
+
+  void ConvertLogFilesToTables() {
+    for (size_t i = 0; i < logs_.size(); i++) {
+      std::string logname = LogFileName(dbname_, logs_[i]);
+      Status status = ConvertLogToTable(logs_[i]);
+      if (!status.ok()) {
+        Log(options_.info_log, "Log #%llu: ignoring conversion error: %s",
+            (unsigned long long)logs_[i], status.ToString().c_str());
+      }
+      ArchiveFile(logname);
+    }
+  }
+
+  Status ConvertLogToTable(uint64_t log) {
+    struct LogReporter : public log::Reader::Reporter {
+      Env* env;
+      Logger* info_log;
+      uint64_t lognum;
+      void Corruption(size_t bytes, const Status& s) override {
+        // We print error messages for corruption, but continue repairing.
+        Log(info_log, "Log #%llu: dropping %d bytes; %s",
+            (unsigned long long)lognum, static_cast<int>(bytes),
+            s.ToString().c_str());
+      }
+    };
+
+    // Open the log file
+    std::string logname = LogFileName(dbname_, log);
+    SequentialFile* lfile;
+    Status status = env_->NewSequentialFile(logname, &lfile);
+    if (!status.ok()) {
+      return status;
+    }
+
+    // Create the log reader.
+    LogReporter reporter;
+    reporter.env = env_;
+    reporter.info_log = options_.info_log;
+    reporter.lognum = log;
+    // We intentionally make log::Reader do checksumming so that
+    // corruptions cause entire commits to be skipped instead of
+    // propagating bad information (like overly large sequence
+    // numbers).
+    log::Reader reader(lfile, &reporter, false /*do not checksum*/,
+                       0 /*initial_offset*/);
+
+    // Read all the records and add to a memtable
+    std::string scratch;
+    Slice record;
+    WriteBatch batch;
+    MemTable* mem = new MemTable(icmp_);
+    mem->Ref();
+    int counter = 0;
+    while (reader.ReadRecord(&record, &scratch)) {
+      if (record.size() < 12) {
+        reporter.Corruption(record.size(),
+                            Status::Corruption("log record too small"));
+        continue;
+      }
+      WriteBatchInternal::SetContents(&batch, record);
+      status = WriteBatchInternal::InsertInto(&batch, mem);
+      if (status.ok()) {
+        counter += WriteBatchInternal::Count(&batch);
+      } else {
+        Log(options_.info_log, "Log #%llu: ignoring %s",
+            (unsigned long long)log, status.ToString().c_str());
+        status = Status::OK();  // Keep going with rest of file
+      }
+    }
+    delete lfile;
+
+    // Do not record a version edit for this conversion to a Table
+    // since ExtractMetaData() will also generate edits.
+    FileMetaData meta;
+    meta.number = next_file_number_++;
+    Iterator* iter = mem->NewIterator();
+    status = BuildTable(dbname_, env_, options_, table_cache_, iter, &meta);
+    delete iter;
+    mem->Unref();
+    mem = nullptr;
+    if (status.ok()) {
+      if (meta.file_size > 0) {
+        table_numbers_.push_back(meta.number);
+      }
+    }
+    Log(options_.info_log, "Log #%llu: %d ops saved to Table #%llu %s",
+        (unsigned long long)log, counter, (unsigned long long)meta.number,
+        status.ToString().c_str());
+    return status;
+  }
+
+  void ExtractMetaData() {
+    for (size_t i = 0; i < table_numbers_.size(); i++) {
+      ScanTable(table_numbers_[i]);
+    }
+  }
+
+  Iterator* NewTableIterator(const FileMetaData& meta) {
+    // Same as compaction iterators: if paranoid_checks are on, turn
+    // on checksum verification.
+    ReadOptions r;
+    r.verify_checksums = options_.paranoid_checks;
+    return table_cache_->NewIterator(r, meta.number, meta.file_size);
+  }
+
+  void ScanTable(uint64_t number) {
+    TableInfo t;
+    t.meta.number = number;
+    std::string fname = TableFileName(dbname_, number);
+    Status status = env_->GetFileSize(fname, &t.meta.file_size);
+    if (!status.ok()) {
+      // Try alternate file name.
+      fname = SSTTableFileName(dbname_, number);
+      Status s2 = env_->GetFileSize(fname, &t.meta.file_size);
+      if (s2.ok()) {
+        status = Status::OK();
+      }
+    }
+    if (!status.ok()) {
+      ArchiveFile(TableFileName(dbname_, number));
+      ArchiveFile(SSTTableFileName(dbname_, number));
+      Log(options_.info_log, "Table #%llu: dropped: %s",
+          (unsigned long long)t.meta.number, status.ToString().c_str());
+      return;
+    }
+
+    // Extract metadata by scanning through table.
+    int counter = 0;
+    Iterator* iter = NewTableIterator(t.meta);
+    bool empty = true;
+    ParsedInternalKey parsed;
+    t.max_sequence = 0;
+    for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
+      Slice key = iter->key();
+      if (!ParseInternalKey(key, &parsed)) {
+        Log(options_.info_log, "Table #%llu: unparsable key %s",
+            (unsigned long long)t.meta.number, EscapeString(key).c_str());
+        continue;
+      }
+
+      counter++;
+      if (empty) {
+        empty = false;
+        t.meta.smallest.DecodeFrom(key);
+      }
+      t.meta.largest.DecodeFrom(key);
+      if (parsed.sequence > t.max_sequence) {
+        t.max_sequence = parsed.sequence;
+      }
+    }
+    if (!iter->status().ok()) {
+      status = iter->status();
+    }
+    delete iter;
+    Log(options_.info_log, "Table #%llu: %d entries %s",
+        (unsigned long long)t.meta.number, counter, status.ToString().c_str());
+
+    if (status.ok()) {
+      tables_.push_back(t);
+    } else {
+      RepairTable(fname, t);  // RepairTable archives input file.
+    }
+  }
+
+  void RepairTable(const std::string& src, TableInfo t) {
+    // We will copy src contents to a new table and then rename the
+    // new table over the source.
+
+    // Create builder.
+    std::string copy = TableFileName(dbname_, next_file_number_++);
+    WritableFile* file;
+    Status s = env_->NewWritableFile(copy, &file);
+    if (!s.ok()) {
+      return;
+    }
+    TableBuilder* builder = new TableBuilder(options_, file);
+
+    // Copy data.
+    Iterator* iter = NewTableIterator(t.meta);
+    int counter = 0;
+    for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
+      builder->Add(iter->key(), iter->value());
+      counter++;
+    }
+    delete iter;
+
+    ArchiveFile(src);
+    if (counter == 0) {
+      builder->Abandon();  // Nothing to save
+    } else {
+      s = builder->Finish();
+      if (s.ok()) {
+        t.meta.file_size = builder->FileSize();
+      }
+    }
+    delete builder;
+    builder = nullptr;
+
+    if (s.ok()) {
+      s = file->Close();
+    }
+    delete file;
+    file = nullptr;
+
+    if (counter > 0 && s.ok()) {
+      std::string orig = TableFileName(dbname_, t.meta.number);
+      s = env_->RenameFile(copy, orig);
+      if (s.ok()) {
+        Log(options_.info_log, "Table #%llu: %d entries repaired",
+            (unsigned long long)t.meta.number, counter);
+        tables_.push_back(t);
+      }
+    }
+    if (!s.ok()) {
+      env_->RemoveFile(copy);
+    }
+  }
+
+  Status WriteDescriptor() {
+    std::string tmp = TempFileName(dbname_, 1);
+    WritableFile* file;
+    Status status = env_->NewWritableFile(tmp, &file);
+    if (!status.ok()) {
+      return status;
+    }
+
+    SequenceNumber max_sequence = 0;
+    for (size_t i = 0; i < tables_.size(); i++) {
+      if (max_sequence < tables_[i].max_sequence) {
+        max_sequence = tables_[i].max_sequence;
+      }
+    }
+
+    edit_.SetComparatorName(icmp_.user_comparator()->Name());
+    edit_.SetLogNumber(0);
+    edit_.SetNextFile(next_file_number_);
+    edit_.SetLastSequence(max_sequence);
+
+    for (size_t i = 0; i < tables_.size(); i++) {
+      // TODO(opt): separate out into multiple levels
+      const TableInfo& t = tables_[i];
+      edit_.AddFile(0, t.meta.number, t.meta.file_size, t.meta.smallest,
+                    t.meta.largest);
+    }
+
+    // std::fprintf(stderr,
+    //              "NewDescriptor:\n%s\n", edit_.DebugString().c_str());
+    {
+      log::Writer log(file);
+      std::string record;
+      edit_.EncodeTo(&record);
+      status = log.AddRecord(record);
+    }
+    if (status.ok()) {
+      status = file->Close();
+    }
+    delete file;
+    file = nullptr;
+
+    if (!status.ok()) {
+      env_->RemoveFile(tmp);
+    } else {
+      // Discard older manifests
+      for (size_t i = 0; i < manifests_.size(); i++) {
+        ArchiveFile(dbname_ + "/" + manifests_[i]);
+      }
+
+      // Install new manifest
+      status = env_->RenameFile(tmp, DescriptorFileName(dbname_, 1));
+      if (status.ok()) {
+        status = SetCurrentFile(env_, dbname_, 1);
+      } else {
+        env_->RemoveFile(tmp);
+      }
+    }
+    return status;
+  }
+
+  void ArchiveFile(const std::string& fname) {
+    // Move into another directory.  E.g., for
+    //    dir/foo
+    // rename to
+    //    dir/lost/foo
+    const char* slash = strrchr(fname.c_str(), '/');
+    std::string new_dir;
+    if (slash != nullptr) {
+      new_dir.assign(fname.data(), slash - fname.data());
+    }
+    new_dir.append("/lost");
+    env_->CreateDir(new_dir);  // Ignore error
+    std::string new_file = new_dir;
+    new_file.append("/");
+    new_file.append((slash == nullptr) ? fname.c_str() : slash + 1);
+    Status s = env_->RenameFile(fname, new_file);
+    Log(options_.info_log, "Archiving %s: %s\n", fname.c_str(),
+        s.ToString().c_str());
+  }
+
+  const std::string dbname_;
+  Env* const env_;
+  InternalKeyComparator const icmp_;
+  InternalFilterPolicy const ipolicy_;
+  const Options options_;
+  bool owns_info_log_;
+  bool owns_cache_;
+  TableCache* table_cache_;
+  VersionEdit edit_;
+
+  std::vector<std::string> manifests_;
+  std::vector<uint64_t> table_numbers_;
+  std::vector<uint64_t> logs_;
+  std::vector<TableInfo> tables_;
+  uint64_t next_file_number_;
+};
+}  // namespace
+
+Status RepairDB(const std::string& dbname, const Options& options) {
+  Repairer repairer(dbname, options);
+  return repairer.Run();
+}
+
+}  // namespace leveldb

Pods/leveldb-library/db/skiplist.h

@@ -0,0 +1,382 @@
+// 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_SKIPLIST_H_
+#define STORAGE_LEVELDB_DB_SKIPLIST_H_
+
+// Thread safety
+// -------------
+//
+// Writes require external synchronization, most likely a mutex.
+// Reads require a guarantee that the SkipList will not be destroyed
+// while the read is in progress.  Apart from that, reads progress
+// without any internal locking or synchronization.
+//
+// Invariants:
+//
+// (1) Allocated nodes are never deleted until the SkipList is
+// destroyed.  This is trivially guaranteed by the code since we
+// never delete any skip list nodes.
+//
+// (2) The contents of a Node except for the next/prev pointers are
+// immutable after the Node has been linked into the SkipList.
+// Only Insert() modifies the list, and it is careful to initialize
+// a node and use release-stores to publish the nodes in one or
+// more lists.
+//
+// ... prev vs. next pointer ordering ...
+
+#include <atomic>
+#include <cassert>
+#include <cstdlib>
+
+#include "util/arena.h"
+#include "util/random.h"
+
+namespace leveldb {
+
+class Arena;
+
+template <typename Key, class Comparator>
+class SkipList {
+ private:
+  struct Node;
+
+ public:
+  // Create a new SkipList object that will use "cmp" for comparing keys,
+  // and will allocate memory using "*arena".  Objects allocated in the arena
+  // must remain allocated for the lifetime of the skiplist object.
+  explicit SkipList(Comparator cmp, Arena* arena);
+
+  SkipList(const SkipList&) = delete;
+  SkipList& operator=(const SkipList&) = delete;
+
+  // Insert key into the list.
+  // REQUIRES: nothing that compares equal to key is currently in the list.
+  void Insert(const Key& key);
+
+  // Returns true iff an entry that compares equal to key is in the list.
+  bool Contains(const Key& key) const;
+
+  // Iteration over the contents of a skip list
+  class Iterator {
+   public:
+    // Initialize an iterator over the specified list.
+    // The returned iterator is not valid.
+    explicit Iterator(const SkipList* list);
+
+    // Returns true iff the iterator is positioned at a valid node.
+    bool Valid() const;
+
+    // Returns the key at the current position.
+    // REQUIRES: Valid()
+    const Key& key() const;
+
+    // Advances to the next position.
+    // REQUIRES: Valid()
+    void Next();
+
+    // Advances to the previous position.
+    // REQUIRES: Valid()
+    void Prev();
+
+    // Advance to the first entry with a key >= target
+    void Seek(const Key& target);
+
+    // Position at the first entry in list.
+    // Final state of iterator is Valid() iff list is not empty.
+    void SeekToFirst();
+
+    // Position at the last entry in list.
+    // Final state of iterator is Valid() iff list is not empty.
+    void SeekToLast();
+
+   private:
+    const SkipList* list_;
+    Node* node_;
+    // Intentionally copyable
+  };
+
+ private:
+  enum { kMaxHeight = 12 };
+
+  inline int GetMaxHeight() const {
+    return max_height_.load(std::memory_order_relaxed);
+  }
+
+  Node* NewNode(const Key& key, int height);
+  int RandomHeight();
+  bool Equal(const Key& a, const Key& b) const { return (compare_(a, b) == 0); }
+
+  // Return true if key is greater than the data stored in "n"
+  bool KeyIsAfterNode(const Key& key, Node* n) const;
+
+  // Return the earliest node that comes at or after key.
+  // Return nullptr if there is no such node.
+  //
+  // If prev is non-null, fills prev[level] with pointer to previous
+  // node at "level" for every level in [0..max_height_-1].
+  Node* FindGreaterOrEqual(const Key& key, Node** prev) const;
+
+  // Return the latest node with a key < key.
+  // Return head_ if there is no such node.
+  Node* FindLessThan(const Key& key) const;
+
+  // Return the last node in the list.
+  // Return head_ if list is empty.
+  Node* FindLast() const;
+
+  // Immutable after construction
+  Comparator const compare_;
+  Arena* const arena_;  // Arena used for allocations of nodes
+
+  Node* const head_;
+
+  // Modified only by Insert().  Read racily by readers, but stale
+  // values are ok.
+  std::atomic<int> max_height_;  // Height of the entire list
+
+  // Read/written only by Insert().
+  Random rnd_;
+};
+
+// Implementation details follow
+template <typename Key, class Comparator>
+struct SkipList<Key, Comparator>::Node {
+  explicit Node(const Key& k) : key(k) {}
+
+  Key const key;
+
+  // Accessors/mutators for links.  Wrapped in methods so we can
+  // add the appropriate barriers as necessary.
+  Node* Next(int n) {
+    assert(n >= 0);
+    // Use an 'acquire load' so that we observe a fully initialized
+    // version of the returned Node.
+    return next_[n].load(std::memory_order_acquire);
+  }
+  void SetNext(int n, Node* x) {
+    assert(n >= 0);
+    // Use a 'release store' so that anybody who reads through this
+    // pointer observes a fully initialized version of the inserted node.
+    next_[n].store(x, std::memory_order_release);
+  }
+
+  // No-barrier variants that can be safely used in a few locations.
+  Node* NoBarrier_Next(int n) {
+    assert(n >= 0);
+    return next_[n].load(std::memory_order_relaxed);
+  }
+  void NoBarrier_SetNext(int n, Node* x) {
+    assert(n >= 0);
+    next_[n].store(x, std::memory_order_relaxed);
+  }
+
+ private:
+  // Array of length equal to the node height.  next_[0] is lowest level link.
+  std::atomic<Node*> next_[1];
+};
+
+template <typename Key, class Comparator>
+typename SkipList<Key, Comparator>::Node* SkipList<Key, Comparator>::NewNode(
+    const Key& key, int height) {
+  char* const node_memory = arena_->AllocateAligned(
+      sizeof(Node) + sizeof(std::atomic<Node*>) * (height - 1));
+  return new (node_memory) Node(key);
+}
+
+template <typename Key, class Comparator>
+inline SkipList<Key, Comparator>::Iterator::Iterator(const SkipList* list) {
+  list_ = list;
+  node_ = nullptr;
+}
+
+template <typename Key, class Comparator>
+inline bool SkipList<Key, Comparator>::Iterator::Valid() const {
+  return node_ != nullptr;
+}
+
+template <typename Key, class Comparator>
+inline const Key& SkipList<Key, Comparator>::Iterator::key() const {
+  assert(Valid());
+  return node_->key;
+}
+
+template <typename Key, class Comparator>
+inline void SkipList<Key, Comparator>::Iterator::Next() {
+  assert(Valid());
+  node_ = node_->Next(0);
+}
+
+template <typename Key, class Comparator>
+inline void SkipList<Key, Comparator>::Iterator::Prev() {
+  // Instead of using explicit "prev" links, we just search for the
+  // last node that falls before key.
+  assert(Valid());
+  node_ = list_->FindLessThan(node_->key);
+  if (node_ == list_->head_) {
+    node_ = nullptr;
+  }
+}
+
+template <typename Key, class Comparator>
+inline void SkipList<Key, Comparator>::Iterator::Seek(const Key& target) {
+  node_ = list_->FindGreaterOrEqual(target, nullptr);
+}
+
+template <typename Key, class Comparator>
+inline void SkipList<Key, Comparator>::Iterator::SeekToFirst() {
+  node_ = list_->head_->Next(0);
+}
+
+template <typename Key, class Comparator>
+inline void SkipList<Key, Comparator>::Iterator::SeekToLast() {
+  node_ = list_->FindLast();
+  if (node_ == list_->head_) {
+    node_ = nullptr;
+  }
+}
+
+template <typename Key, class Comparator>
+int SkipList<Key, Comparator>::RandomHeight() {
+  // Increase height with probability 1 in kBranching
+  static const unsigned int kBranching = 4;
+  int height = 1;
+  while (height < kMaxHeight && ((rnd_.Next() % kBranching) == 0)) {
+    height++;
+  }
+  assert(height > 0);
+  assert(height <= kMaxHeight);
+  return height;
+}
+
+template <typename Key, class Comparator>
+bool SkipList<Key, Comparator>::KeyIsAfterNode(const Key& key, Node* n) const {
+  // null n is considered infinite
+  return (n != nullptr) && (compare_(n->key, key) < 0);
+}
+
+template <typename Key, class Comparator>
+typename SkipList<Key, Comparator>::Node*
+SkipList<Key, Comparator>::FindGreaterOrEqual(const Key& key,
+                                              Node** prev) const {
+  Node* x = head_;
+  int level = GetMaxHeight() - 1;
+  while (true) {
+    Node* next = x->Next(level);
+    if (KeyIsAfterNode(key, next)) {
+      // Keep searching in this list
+      x = next;
+    } else {
+      if (prev != nullptr) prev[level] = x;
+      if (level == 0) {
+        return next;
+      } else {
+        // Switch to next list
+        level--;
+      }
+    }
+  }
+}
+
+template <typename Key, class Comparator>
+typename SkipList<Key, Comparator>::Node*
+SkipList<Key, Comparator>::FindLessThan(const Key& key) const {
+  Node* x = head_;
+  int level = GetMaxHeight() - 1;
+  while (true) {
+    assert(x == head_ || compare_(x->key, key) < 0);
+    Node* next = x->Next(level);
+    if (next == nullptr || compare_(next->key, key) >= 0) {
+      if (level == 0) {
+        return x;
+      } else {
+        // Switch to next list
+        level--;
+      }
+    } else {
+      x = next;
+    }
+  }
+}
+
+template <typename Key, class Comparator>
+typename SkipList<Key, Comparator>::Node* SkipList<Key, Comparator>::FindLast()
+    const {
+  Node* x = head_;
+  int level = GetMaxHeight() - 1;
+  while (true) {
+    Node* next = x->Next(level);
+    if (next == nullptr) {
+      if (level == 0) {
+        return x;
+      } else {
+        // Switch to next list
+        level--;
+      }
+    } else {
+      x = next;
+    }
+  }
+}
+
+template <typename Key, class Comparator>
+SkipList<Key, Comparator>::SkipList(Comparator cmp, Arena* arena)
+    : compare_(cmp),
+      arena_(arena),
+      head_(NewNode(0 /* any key will do */, kMaxHeight)),
+      max_height_(1),
+      rnd_(0xdeadbeef) {
+  for (int i = 0; i < kMaxHeight; i++) {
+    head_->SetNext(i, nullptr);
+  }
+}
+
+template <typename Key, class Comparator>
+void SkipList<Key, Comparator>::Insert(const Key& key) {
+  // TODO(opt): We can use a barrier-free variant of FindGreaterOrEqual()
+  // here since Insert() is externally synchronized.
+  Node* prev[kMaxHeight];
+  Node* x = FindGreaterOrEqual(key, prev);
+
+  // Our data structure does not allow duplicate insertion
+  assert(x == nullptr || !Equal(key, x->key));
+
+  int height = RandomHeight();
+  if (height > GetMaxHeight()) {
+    for (int i = GetMaxHeight(); i < height; i++) {
+      prev[i] = head_;
+    }
+    // It is ok to mutate max_height_ without any synchronization
+    // with concurrent readers.  A concurrent reader that observes
+    // the new value of max_height_ will see either the old value of
+    // new level pointers from head_ (nullptr), or a new value set in
+    // the loop below.  In the former case the reader will
+    // immediately drop to the next level since nullptr sorts after all
+    // keys.  In the latter case the reader will use the new node.
+    max_height_.store(height, std::memory_order_relaxed);
+  }
+
+  x = NewNode(key, height);
+  for (int i = 0; i < height; i++) {
+    // NoBarrier_SetNext() suffices since we will add a barrier when
+    // we publish a pointer to "x" in prev[i].
+    x->NoBarrier_SetNext(i, prev[i]->NoBarrier_Next(i));
+    prev[i]->SetNext(i, x);
+  }
+}
+
+template <typename Key, class Comparator>
+bool SkipList<Key, Comparator>::Contains(const Key& key) const {
+  Node* x = FindGreaterOrEqual(key, nullptr);
+  if (x != nullptr && Equal(key, x->key)) {
+    return true;
+  } else {
+    return false;
+  }
+}
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_SKIPLIST_H_

Pods/leveldb-library/db/snapshot.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.
+
+#ifndef STORAGE_LEVELDB_DB_SNAPSHOT_H_
+#define STORAGE_LEVELDB_DB_SNAPSHOT_H_
+
+#include "db/dbformat.h"
+#include "leveldb/db.h"
+
+namespace leveldb {
+
+class SnapshotList;
+
+// Snapshots are kept in a doubly-linked list in the DB.
+// Each SnapshotImpl corresponds to a particular sequence number.
+class SnapshotImpl : public Snapshot {
+ public:
+  SnapshotImpl(SequenceNumber sequence_number)
+      : sequence_number_(sequence_number) {}
+
+  SequenceNumber sequence_number() const { return sequence_number_; }
+
+ private:
+  friend class SnapshotList;
+
+  // SnapshotImpl is kept in a doubly-linked circular list. The SnapshotList
+  // implementation operates on the next/previous fields direcly.
+  SnapshotImpl* prev_;
+  SnapshotImpl* next_;
+
+  const SequenceNumber sequence_number_;
+
+#if !defined(NDEBUG)
+  SnapshotList* list_ = nullptr;
+#endif  // !defined(NDEBUG)
+};
+
+class SnapshotList {
+ public:
+  SnapshotList() : head_(0) {
+    head_.prev_ = &head_;
+    head_.next_ = &head_;
+  }
+
+  bool empty() const { return head_.next_ == &head_; }
+  SnapshotImpl* oldest() const {
+    assert(!empty());
+    return head_.next_;
+  }
+  SnapshotImpl* newest() const {
+    assert(!empty());
+    return head_.prev_;
+  }
+
+  // Creates a SnapshotImpl and appends it to the end of the list.
+  SnapshotImpl* New(SequenceNumber sequence_number) {
+    assert(empty() || newest()->sequence_number_ <= sequence_number);
+
+    SnapshotImpl* snapshot = new SnapshotImpl(sequence_number);
+
+#if !defined(NDEBUG)
+    snapshot->list_ = this;
+#endif  // !defined(NDEBUG)
+    snapshot->next_ = &head_;
+    snapshot->prev_ = head_.prev_;
+    snapshot->prev_->next_ = snapshot;
+    snapshot->next_->prev_ = snapshot;
+    return snapshot;
+  }
+
+  // Removes a SnapshotImpl from this list.
+  //
+  // The snapshot must have been created by calling New() on this list.
+  //
+  // The snapshot pointer should not be const, because its memory is
+  // deallocated. However, that would force us to change DB::ReleaseSnapshot(),
+  // which is in the API, and currently takes a const Snapshot.
+  void Delete(const SnapshotImpl* snapshot) {
+#if !defined(NDEBUG)
+    assert(snapshot->list_ == this);
+#endif  // !defined(NDEBUG)
+    snapshot->prev_->next_ = snapshot->next_;
+    snapshot->next_->prev_ = snapshot->prev_;
+    delete snapshot;
+  }
+
+ private:
+  // Dummy head of doubly-linked list of snapshots
+  SnapshotImpl head_;
+};
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_SNAPSHOT_H_

Pods/leveldb-library/db/table_cache.cc

@@ -0,0 +1,120 @@
+// 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/table_cache.h"
+
+#include "db/filename.h"
+#include "leveldb/env.h"
+#include "leveldb/table.h"
+#include "util/coding.h"
+
+namespace leveldb {
+
+struct TableAndFile {
+  RandomAccessFile* file;
+  Table* table;
+};
+
+static void DeleteEntry(const Slice& key, void* value) {
+  TableAndFile* tf = reinterpret_cast<TableAndFile*>(value);
+  delete tf->table;
+  delete tf->file;
+  delete tf;
+}
+
+static void UnrefEntry(void* arg1, void* arg2) {
+  Cache* cache = reinterpret_cast<Cache*>(arg1);
+  Cache::Handle* h = reinterpret_cast<Cache::Handle*>(arg2);
+  cache->Release(h);
+}
+
+TableCache::TableCache(const std::string& dbname, const Options& options,
+                       int entries)
+    : env_(options.env),
+      dbname_(dbname),
+      options_(options),
+      cache_(NewLRUCache(entries)) {}
+
+TableCache::~TableCache() { delete cache_; }
+
+Status TableCache::FindTable(uint64_t file_number, uint64_t file_size,
+                             Cache::Handle** handle) {
+  Status s;
+  char buf[sizeof(file_number)];
+  EncodeFixed64(buf, file_number);
+  Slice key(buf, sizeof(buf));
+  *handle = cache_->Lookup(key);
+  if (*handle == nullptr) {
+    std::string fname = TableFileName(dbname_, file_number);
+    RandomAccessFile* file = nullptr;
+    Table* table = nullptr;
+    s = env_->NewRandomAccessFile(fname, &file);
+    if (!s.ok()) {
+      std::string old_fname = SSTTableFileName(dbname_, file_number);
+      if (env_->NewRandomAccessFile(old_fname, &file).ok()) {
+        s = Status::OK();
+      }
+    }
+    if (s.ok()) {
+      s = Table::Open(options_, file, file_size, &table);
+    }
+
+    if (!s.ok()) {
+      assert(table == nullptr);
+      delete file;
+      // We do not cache error results so that if the error is transient,
+      // or somebody repairs the file, we recover automatically.
+    } else {
+      TableAndFile* tf = new TableAndFile;
+      tf->file = file;
+      tf->table = table;
+      *handle = cache_->Insert(key, tf, 1, &DeleteEntry);
+    }
+  }
+  return s;
+}
+
+Iterator* TableCache::NewIterator(const ReadOptions& options,
+                                  uint64_t file_number, uint64_t file_size,
+                                  Table** tableptr) {
+  if (tableptr != nullptr) {
+    *tableptr = nullptr;
+  }
+
+  Cache::Handle* handle = nullptr;
+  Status s = FindTable(file_number, file_size, &handle);
+  if (!s.ok()) {
+    return NewErrorIterator(s);
+  }
+
+  Table* table = reinterpret_cast<TableAndFile*>(cache_->Value(handle))->table;
+  Iterator* result = table->NewIterator(options);
+  result->RegisterCleanup(&UnrefEntry, cache_, handle);
+  if (tableptr != nullptr) {
+    *tableptr = table;
+  }
+  return result;
+}
+
+Status TableCache::Get(const ReadOptions& options, uint64_t file_number,
+                       uint64_t file_size, const Slice& k, void* arg,
+                       void (*handle_result)(void*, const Slice&,
+                                             const Slice&)) {
+  Cache::Handle* handle = nullptr;
+  Status s = FindTable(file_number, file_size, &handle);
+  if (s.ok()) {
+    Table* t = reinterpret_cast<TableAndFile*>(cache_->Value(handle))->table;
+    s = t->InternalGet(options, k, arg, handle_result);
+    cache_->Release(handle);
+  }
+  return s;
+}
+
+void TableCache::Evict(uint64_t file_number) {
+  char buf[sizeof(file_number)];
+  EncodeFixed64(buf, file_number);
+  cache_->Erase(Slice(buf, sizeof(buf)));
+}
+
+}  // namespace leveldb

Pods/leveldb-library/db/table_cache.h

@@ -0,0 +1,57 @@
+// 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.
+//
+// Thread-safe (provides internal synchronization)
+
+#ifndef STORAGE_LEVELDB_DB_TABLE_CACHE_H_
+#define STORAGE_LEVELDB_DB_TABLE_CACHE_H_
+
+#include <cstdint>
+#include <string>
+
+#include "db/dbformat.h"
+#include "leveldb/cache.h"
+#include "leveldb/table.h"
+#include "port/port.h"
+
+namespace leveldb {
+
+class Env;
+
+class TableCache {
+ public:
+  TableCache(const std::string& dbname, const Options& options, int entries);
+  ~TableCache();
+
+  // Return an iterator for the specified file number (the corresponding
+  // file length must be exactly "file_size" bytes).  If "tableptr" is
+  // non-null, also sets "*tableptr" to point to the Table object
+  // underlying the returned iterator, or to nullptr if no Table object
+  // underlies the returned iterator.  The returned "*tableptr" object is owned
+  // by the cache and should not be deleted, and is valid for as long as the
+  // returned iterator is live.
+  Iterator* NewIterator(const ReadOptions& options, uint64_t file_number,
+                        uint64_t file_size, Table** tableptr = nullptr);
+
+  // If a seek to internal key "k" in specified file finds an entry,
+  // call (*handle_result)(arg, found_key, found_value).
+  Status Get(const ReadOptions& options, uint64_t file_number,
+             uint64_t file_size, const Slice& k, void* arg,
+             void (*handle_result)(void*, const Slice&, const Slice&));
+
+  // Evict any entry for the specified file number
+  void Evict(uint64_t file_number);
+
+ private:
+  Status FindTable(uint64_t file_number, uint64_t file_size, Cache::Handle**);
+
+  Env* const env_;
+  const std::string dbname_;
+  const Options& options_;
+  Cache* cache_;
+};
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_TABLE_CACHE_H_

Pods/leveldb-library/db/version_edit.cc

@@ -0,0 +1,257 @@
+// 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/version_edit.h"
+
+#include "db/version_set.h"
+#include "util/coding.h"
+
+namespace leveldb {
+
+// Tag numbers for serialized VersionEdit.  These numbers are written to
+// disk and should not be changed.
+enum Tag {
+  kComparator = 1,
+  kLogNumber = 2,
+  kNextFileNumber = 3,
+  kLastSequence = 4,
+  kCompactPointer = 5,
+  kDeletedFile = 6,
+  kNewFile = 7,
+  // 8 was used for large value refs
+  kPrevLogNumber = 9
+};
+
+void VersionEdit::Clear() {
+  comparator_.clear();
+  log_number_ = 0;
+  prev_log_number_ = 0;
+  last_sequence_ = 0;
+  next_file_number_ = 0;
+  has_comparator_ = false;
+  has_log_number_ = false;
+  has_prev_log_number_ = false;
+  has_next_file_number_ = false;
+  has_last_sequence_ = false;
+  deleted_files_.clear();
+  new_files_.clear();
+}
+
+void VersionEdit::EncodeTo(std::string* dst) const {
+  if (has_comparator_) {
+    PutVarint32(dst, kComparator);
+    PutLengthPrefixedSlice(dst, comparator_);
+  }
+  if (has_log_number_) {
+    PutVarint32(dst, kLogNumber);
+    PutVarint64(dst, log_number_);
+  }
+  if (has_prev_log_number_) {
+    PutVarint32(dst, kPrevLogNumber);
+    PutVarint64(dst, prev_log_number_);
+  }
+  if (has_next_file_number_) {
+    PutVarint32(dst, kNextFileNumber);
+    PutVarint64(dst, next_file_number_);
+  }
+  if (has_last_sequence_) {
+    PutVarint32(dst, kLastSequence);
+    PutVarint64(dst, last_sequence_);
+  }
+
+  for (size_t i = 0; i < compact_pointers_.size(); i++) {
+    PutVarint32(dst, kCompactPointer);
+    PutVarint32(dst, compact_pointers_[i].first);  // level
+    PutLengthPrefixedSlice(dst, compact_pointers_[i].second.Encode());
+  }
+
+  for (const auto& deleted_file_kvp : deleted_files_) {
+    PutVarint32(dst, kDeletedFile);
+    PutVarint32(dst, deleted_file_kvp.first);   // level
+    PutVarint64(dst, deleted_file_kvp.second);  // file number
+  }
+
+  for (size_t i = 0; i < new_files_.size(); i++) {
+    const FileMetaData& f = new_files_[i].second;
+    PutVarint32(dst, kNewFile);
+    PutVarint32(dst, new_files_[i].first);  // level
+    PutVarint64(dst, f.number);
+    PutVarint64(dst, f.file_size);
+    PutLengthPrefixedSlice(dst, f.smallest.Encode());
+    PutLengthPrefixedSlice(dst, f.largest.Encode());
+  }
+}
+
+static bool GetInternalKey(Slice* input, InternalKey* dst) {
+  Slice str;
+  if (GetLengthPrefixedSlice(input, &str)) {
+    return dst->DecodeFrom(str);
+  } else {
+    return false;
+  }
+}
+
+static bool GetLevel(Slice* input, int* level) {
+  uint32_t v;
+  if (GetVarint32(input, &v) && v < config::kNumLevels) {
+    *level = v;
+    return true;
+  } else {
+    return false;
+  }
+}
+
+Status VersionEdit::DecodeFrom(const Slice& src) {
+  Clear();
+  Slice input = src;
+  const char* msg = nullptr;
+  uint32_t tag;
+
+  // Temporary storage for parsing
+  int level;
+  uint64_t number;
+  FileMetaData f;
+  Slice str;
+  InternalKey key;
+
+  while (msg == nullptr && GetVarint32(&input, &tag)) {
+    switch (tag) {
+      case kComparator:
+        if (GetLengthPrefixedSlice(&input, &str)) {
+          comparator_ = str.ToString();
+          has_comparator_ = true;
+        } else {
+          msg = "comparator name";
+        }
+        break;
+
+      case kLogNumber:
+        if (GetVarint64(&input, &log_number_)) {
+          has_log_number_ = true;
+        } else {
+          msg = "log number";
+        }
+        break;
+
+      case kPrevLogNumber:
+        if (GetVarint64(&input, &prev_log_number_)) {
+          has_prev_log_number_ = true;
+        } else {
+          msg = "previous log number";
+        }
+        break;
+
+      case kNextFileNumber:
+        if (GetVarint64(&input, &next_file_number_)) {
+          has_next_file_number_ = true;
+        } else {
+          msg = "next file number";
+        }
+        break;
+
+      case kLastSequence:
+        if (GetVarint64(&input, &last_sequence_)) {
+          has_last_sequence_ = true;
+        } else {
+          msg = "last sequence number";
+        }
+        break;
+
+      case kCompactPointer:
+        if (GetLevel(&input, &level) && GetInternalKey(&input, &key)) {
+          compact_pointers_.push_back(std::make_pair(level, key));
+        } else {
+          msg = "compaction pointer";
+        }
+        break;
+
+      case kDeletedFile:
+        if (GetLevel(&input, &level) && GetVarint64(&input, &number)) {
+          deleted_files_.insert(std::make_pair(level, number));
+        } else {
+          msg = "deleted file";
+        }
+        break;
+
+      case kNewFile:
+        if (GetLevel(&input, &level) && GetVarint64(&input, &f.number) &&
+            GetVarint64(&input, &f.file_size) &&
+            GetInternalKey(&input, &f.smallest) &&
+            GetInternalKey(&input, &f.largest)) {
+          new_files_.push_back(std::make_pair(level, f));
+        } else {
+          msg = "new-file entry";
+        }
+        break;
+
+      default:
+        msg = "unknown tag";
+        break;
+    }
+  }
+
+  if (msg == nullptr && !input.empty()) {
+    msg = "invalid tag";
+  }
+
+  Status result;
+  if (msg != nullptr) {
+    result = Status::Corruption("VersionEdit", msg);
+  }
+  return result;
+}
+
+std::string VersionEdit::DebugString() const {
+  std::string r;
+  r.append("VersionEdit {");
+  if (has_comparator_) {
+    r.append("\n  Comparator: ");
+    r.append(comparator_);
+  }
+  if (has_log_number_) {
+    r.append("\n  LogNumber: ");
+    AppendNumberTo(&r, log_number_);
+  }
+  if (has_prev_log_number_) {
+    r.append("\n  PrevLogNumber: ");
+    AppendNumberTo(&r, prev_log_number_);
+  }
+  if (has_next_file_number_) {
+    r.append("\n  NextFile: ");
+    AppendNumberTo(&r, next_file_number_);
+  }
+  if (has_last_sequence_) {
+    r.append("\n  LastSeq: ");
+    AppendNumberTo(&r, last_sequence_);
+  }
+  for (size_t i = 0; i < compact_pointers_.size(); i++) {
+    r.append("\n  CompactPointer: ");
+    AppendNumberTo(&r, compact_pointers_[i].first);
+    r.append(" ");
+    r.append(compact_pointers_[i].second.DebugString());
+  }
+  for (const auto& deleted_files_kvp : deleted_files_) {
+    r.append("\n  RemoveFile: ");
+    AppendNumberTo(&r, deleted_files_kvp.first);
+    r.append(" ");
+    AppendNumberTo(&r, deleted_files_kvp.second);
+  }
+  for (size_t i = 0; i < new_files_.size(); i++) {
+    const FileMetaData& f = new_files_[i].second;
+    r.append("\n  AddFile: ");
+    AppendNumberTo(&r, new_files_[i].first);
+    r.append(" ");
+    AppendNumberTo(&r, f.number);
+    r.append(" ");
+    AppendNumberTo(&r, f.file_size);
+    r.append(" ");
+    r.append(f.smallest.DebugString());
+    r.append(" .. ");
+    r.append(f.largest.DebugString());
+  }
+  r.append("\n}\n");
+  return r;
+}
+
+}  // namespace leveldb

Pods/leveldb-library/db/version_edit.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.
+
+#ifndef STORAGE_LEVELDB_DB_VERSION_EDIT_H_
+#define STORAGE_LEVELDB_DB_VERSION_EDIT_H_
+
+#include <set>
+#include <utility>
+#include <vector>
+
+#include "db/dbformat.h"
+
+namespace leveldb {
+
+class VersionSet;
+
+struct FileMetaData {
+  FileMetaData() : refs(0), allowed_seeks(1 << 30), file_size(0) {}
+
+  int refs;
+  int allowed_seeks;  // Seeks allowed until compaction
+  uint64_t number;
+  uint64_t file_size;    // File size in bytes
+  InternalKey smallest;  // Smallest internal key served by table
+  InternalKey largest;   // Largest internal key served by table
+};
+
+class VersionEdit {
+ public:
+  VersionEdit() { Clear(); }
+  ~VersionEdit() = default;
+
+  void Clear();
+
+  void SetComparatorName(const Slice& name) {
+    has_comparator_ = true;
+    comparator_ = name.ToString();
+  }
+  void SetLogNumber(uint64_t num) {
+    has_log_number_ = true;
+    log_number_ = num;
+  }
+  void SetPrevLogNumber(uint64_t num) {
+    has_prev_log_number_ = true;
+    prev_log_number_ = num;
+  }
+  void SetNextFile(uint64_t num) {
+    has_next_file_number_ = true;
+    next_file_number_ = num;
+  }
+  void SetLastSequence(SequenceNumber seq) {
+    has_last_sequence_ = true;
+    last_sequence_ = seq;
+  }
+  void SetCompactPointer(int level, const InternalKey& key) {
+    compact_pointers_.push_back(std::make_pair(level, key));
+  }
+
+  // Add the specified file at the specified number.
+  // REQUIRES: This version has not been saved (see VersionSet::SaveTo)
+  // REQUIRES: "smallest" and "largest" are smallest and largest keys in file
+  void AddFile(int level, uint64_t file, uint64_t file_size,
+               const InternalKey& smallest, const InternalKey& largest) {
+    FileMetaData f;
+    f.number = file;
+    f.file_size = file_size;
+    f.smallest = smallest;
+    f.largest = largest;
+    new_files_.push_back(std::make_pair(level, f));
+  }
+
+  // Delete the specified "file" from the specified "level".
+  void RemoveFile(int level, uint64_t file) {
+    deleted_files_.insert(std::make_pair(level, file));
+  }
+
+  void EncodeTo(std::string* dst) const;
+  Status DecodeFrom(const Slice& src);
+
+  std::string DebugString() const;
+
+ private:
+  friend class VersionSet;
+
+  typedef std::set<std::pair<int, uint64_t>> DeletedFileSet;
+
+  std::string comparator_;
+  uint64_t log_number_;
+  uint64_t prev_log_number_;
+  uint64_t next_file_number_;
+  SequenceNumber last_sequence_;
+  bool has_comparator_;
+  bool has_log_number_;
+  bool has_prev_log_number_;
+  bool has_next_file_number_;
+  bool has_last_sequence_;
+
+  std::vector<std::pair<int, InternalKey>> compact_pointers_;
+  DeletedFileSet deleted_files_;
+  std::vector<std::pair<int, FileMetaData>> new_files_;
+};
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_VERSION_EDIT_H_

Pods/leveldb-library/db/version_set.cc

@@ -0,0 +1,1562 @@
+// 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/version_set.h"
+
+#include <algorithm>
+#include <cstdio>
+
+#include "db/filename.h"
+#include "db/log_reader.h"
+#include "db/log_writer.h"
+#include "db/memtable.h"
+#include "db/table_cache.h"
+#include "leveldb/env.h"
+#include "leveldb/table_builder.h"
+#include "table/merger.h"
+#include "table/two_level_iterator.h"
+#include "util/coding.h"
+#include "util/logging.h"
+
+namespace leveldb {
+
+static size_t TargetFileSize(const Options* options) {
+  return options->max_file_size;
+}
+
+// Maximum bytes of overlaps in grandparent (i.e., level+2) before we
+// stop building a single file in a level->level+1 compaction.
+static int64_t MaxGrandParentOverlapBytes(const Options* options) {
+  return 10 * TargetFileSize(options);
+}
+
+// Maximum number of bytes in all compacted files.  We avoid expanding
+// the lower level file set of a compaction if it would make the
+// total compaction cover more than this many bytes.
+static int64_t ExpandedCompactionByteSizeLimit(const Options* options) {
+  return 25 * TargetFileSize(options);
+}
+
+static double MaxBytesForLevel(const Options* options, int level) {
+  // Note: the result for level zero is not really used since we set
+  // the level-0 compaction threshold based on number of files.
+
+  // Result for both level-0 and level-1
+  double result = 10. * 1048576.0;
+  while (level > 1) {
+    result *= 10;
+    level--;
+  }
+  return result;
+}
+
+static uint64_t MaxFileSizeForLevel(const Options* options, int level) {
+  // We could vary per level to reduce number of files?
+  return TargetFileSize(options);
+}
+
+static int64_t TotalFileSize(const std::vector<FileMetaData*>& files) {
+  int64_t sum = 0;
+  for (size_t i = 0; i < files.size(); i++) {
+    sum += files[i]->file_size;
+  }
+  return sum;
+}
+
+Version::~Version() {
+  assert(refs_ == 0);
+
+  // Remove from linked list
+  prev_->next_ = next_;
+  next_->prev_ = prev_;
+
+  // Drop references to files
+  for (int level = 0; level < config::kNumLevels; level++) {
+    for (size_t i = 0; i < files_[level].size(); i++) {
+      FileMetaData* f = files_[level][i];
+      assert(f->refs > 0);
+      f->refs--;
+      if (f->refs <= 0) {
+        delete f;
+      }
+    }
+  }
+}
+
+int FindFile(const InternalKeyComparator& icmp,
+             const std::vector<FileMetaData*>& files, const Slice& key) {
+  uint32_t left = 0;
+  uint32_t right = (uint32_t)files.size();
+  while (left < right) {
+    uint32_t mid = (left + right) / 2;
+    const FileMetaData* f = files[mid];
+    if (icmp.InternalKeyComparator::Compare(f->largest.Encode(), key) < 0) {
+      // Key at "mid.largest" is < "target".  Therefore all
+      // files at or before "mid" are uninteresting.
+      left = mid + 1;
+    } else {
+      // Key at "mid.largest" is >= "target".  Therefore all files
+      // after "mid" are uninteresting.
+      right = mid;
+    }
+  }
+  return right;
+}
+
+static bool AfterFile(const Comparator* ucmp, const Slice* user_key,
+                      const FileMetaData* f) {
+  // null user_key occurs before all keys and is therefore never after *f
+  return (user_key != nullptr &&
+          ucmp->Compare(*user_key, f->largest.user_key()) > 0);
+}
+
+static bool BeforeFile(const Comparator* ucmp, const Slice* user_key,
+                       const FileMetaData* f) {
+  // null user_key occurs after all keys and is therefore never before *f
+  return (user_key != nullptr &&
+          ucmp->Compare(*user_key, f->smallest.user_key()) < 0);
+}
+
+bool SomeFileOverlapsRange(const InternalKeyComparator& icmp,
+                           bool disjoint_sorted_files,
+                           const std::vector<FileMetaData*>& files,
+                           const Slice* smallest_user_key,
+                           const Slice* largest_user_key) {
+  const Comparator* ucmp = icmp.user_comparator();
+  if (!disjoint_sorted_files) {
+    // Need to check against all files
+    for (size_t i = 0; i < files.size(); i++) {
+      const FileMetaData* f = files[i];
+      if (AfterFile(ucmp, smallest_user_key, f) ||
+          BeforeFile(ucmp, largest_user_key, f)) {
+        // No overlap
+      } else {
+        return true;  // Overlap
+      }
+    }
+    return false;
+  }
+
+  // Binary search over file list
+  uint32_t index = 0;
+  if (smallest_user_key != nullptr) {
+    // Find the earliest possible internal key for smallest_user_key
+    InternalKey small_key(*smallest_user_key, kMaxSequenceNumber,
+                          kValueTypeForSeek);
+    index = FindFile(icmp, files, small_key.Encode());
+  }
+
+  if (index >= files.size()) {
+    // beginning of range is after all files, so no overlap.
+    return false;
+  }
+
+  return !BeforeFile(ucmp, largest_user_key, files[index]);
+}
+
+// An internal iterator.  For a given version/level pair, yields
+// information about the files in the level.  For a given entry, key()
+// is the largest key that occurs in the file, and value() is an
+// 16-byte value containing the file number and file size, both
+// encoded using EncodeFixed64.
+class Version::LevelFileNumIterator : public Iterator {
+ public:
+  LevelFileNumIterator(const InternalKeyComparator& icmp,
+                       const std::vector<FileMetaData*>* flist)
+      : icmp_(icmp), flist_(flist), index_((uint32_t)flist->size()) {  // Marks as invalid
+  }
+  bool Valid() const override { return index_ < flist_->size(); }
+  void Seek(const Slice& target) override {
+    index_ = FindFile(icmp_, *flist_, target);
+  }
+  void SeekToFirst() override { index_ = 0; }
+  void SeekToLast() override {
+    index_ = flist_->empty() ? 0 : (uint32_t)flist_->size() - 1;
+  }
+  void Next() override {
+    assert(Valid());
+    index_++;
+  }
+  void Prev() override {
+    assert(Valid());
+    if (index_ == 0) {
+      index_ = (uint32_t)flist_->size();  // Marks as invalid
+    } else {
+      index_--;
+    }
+  }
+  Slice key() const override {
+    assert(Valid());
+    return (*flist_)[index_]->largest.Encode();
+  }
+  Slice value() const override {
+    assert(Valid());
+    EncodeFixed64(value_buf_, (*flist_)[index_]->number);
+    EncodeFixed64(value_buf_ + 8, (*flist_)[index_]->file_size);
+    return Slice(value_buf_, sizeof(value_buf_));
+  }
+  Status status() const override { return Status::OK(); }
+
+ private:
+  const InternalKeyComparator icmp_;
+  const std::vector<FileMetaData*>* const flist_;
+  uint32_t index_;
+
+  // Backing store for value().  Holds the file number and size.
+  mutable char value_buf_[16];
+};
+
+static Iterator* GetFileIterator(void* arg, const ReadOptions& options,
+                                 const Slice& file_value) {
+  TableCache* cache = reinterpret_cast<TableCache*>(arg);
+  if (file_value.size() != 16) {
+    return NewErrorIterator(
+        Status::Corruption("FileReader invoked with unexpected value"));
+  } else {
+    return cache->NewIterator(options, DecodeFixed64(file_value.data()),
+                              DecodeFixed64(file_value.data() + 8));
+  }
+}
+
+Iterator* Version::NewConcatenatingIterator(const ReadOptions& options,
+                                            int level) const {
+  return NewTwoLevelIterator(
+      new LevelFileNumIterator(vset_->icmp_, &files_[level]), &GetFileIterator,
+      vset_->table_cache_, options);
+}
+
+void Version::AddIterators(const ReadOptions& options,
+                           std::vector<Iterator*>* iters) {
+  // Merge all level zero files together since they may overlap
+  for (size_t i = 0; i < files_[0].size(); i++) {
+    iters->push_back(vset_->table_cache_->NewIterator(
+        options, files_[0][i]->number, files_[0][i]->file_size));
+  }
+
+  // For levels > 0, we can use a concatenating iterator that sequentially
+  // walks through the non-overlapping files in the level, opening them
+  // lazily.
+  for (int level = 1; level < config::kNumLevels; level++) {
+    if (!files_[level].empty()) {
+      iters->push_back(NewConcatenatingIterator(options, level));
+    }
+  }
+}
+
+// Callback from TableCache::Get()
+namespace {
+enum SaverState {
+  kNotFound,
+  kFound,
+  kDeleted,
+  kCorrupt,
+};
+struct Saver {
+  SaverState state;
+  const Comparator* ucmp;
+  Slice user_key;
+  std::string* value;
+};
+}  // namespace
+static void SaveValue(void* arg, const Slice& ikey, const Slice& v) {
+  Saver* s = reinterpret_cast<Saver*>(arg);
+  ParsedInternalKey parsed_key;
+  if (!ParseInternalKey(ikey, &parsed_key)) {
+    s->state = kCorrupt;
+  } else {
+    if (s->ucmp->Compare(parsed_key.user_key, s->user_key) == 0) {
+      s->state = (parsed_key.type == kTypeValue) ? kFound : kDeleted;
+      if (s->state == kFound) {
+        s->value->assign(v.data(), v.size());
+      }
+    }
+  }
+}
+
+static bool NewestFirst(FileMetaData* a, FileMetaData* b) {
+  return a->number > b->number;
+}
+
+void Version::ForEachOverlapping(Slice user_key, Slice internal_key, void* arg,
+                                 bool (*func)(void*, int, FileMetaData*)) {
+  const Comparator* ucmp = vset_->icmp_.user_comparator();
+
+  // Search level-0 in order from newest to oldest.
+  std::vector<FileMetaData*> tmp;
+  tmp.reserve(files_[0].size());
+  for (uint32_t i = 0; i < files_[0].size(); i++) {
+    FileMetaData* f = files_[0][i];
+    if (ucmp->Compare(user_key, f->smallest.user_key()) >= 0 &&
+        ucmp->Compare(user_key, f->largest.user_key()) <= 0) {
+      tmp.push_back(f);
+    }
+  }
+  if (!tmp.empty()) {
+    std::sort(tmp.begin(), tmp.end(), NewestFirst);
+    for (uint32_t i = 0; i < tmp.size(); i++) {
+      if (!(*func)(arg, 0, tmp[i])) {
+        return;
+      }
+    }
+  }
+
+  // Search other levels.
+  for (int level = 1; level < config::kNumLevels; level++) {
+    size_t num_files = files_[level].size();
+    if (num_files == 0) continue;
+
+    // Binary search to find earliest index whose largest key >= internal_key.
+    uint32_t index = FindFile(vset_->icmp_, files_[level], internal_key);
+    if (index < num_files) {
+      FileMetaData* f = files_[level][index];
+      if (ucmp->Compare(user_key, f->smallest.user_key()) < 0) {
+        // All of "f" is past any data for user_key
+      } else {
+        if (!(*func)(arg, level, f)) {
+          return;
+        }
+      }
+    }
+  }
+}
+
+Status Version::Get(const ReadOptions& options, const LookupKey& k,
+                    std::string* value, GetStats* stats) {
+  stats->seek_file = nullptr;
+  stats->seek_file_level = -1;
+
+  struct State {
+    Saver saver;
+    GetStats* stats;
+    const ReadOptions* options;
+    Slice ikey;
+    FileMetaData* last_file_read;
+    int last_file_read_level;
+
+    VersionSet* vset;
+    Status s;
+    bool found;
+
+    static bool Match(void* arg, int level, FileMetaData* f) {
+      State* state = reinterpret_cast<State*>(arg);
+
+      if (state->stats->seek_file == nullptr &&
+          state->last_file_read != nullptr) {
+        // We have had more than one seek for this read.  Charge the 1st file.
+        state->stats->seek_file = state->last_file_read;
+        state->stats->seek_file_level = state->last_file_read_level;
+      }
+
+      state->last_file_read = f;
+      state->last_file_read_level = level;
+
+      state->s = state->vset->table_cache_->Get(*state->options, f->number,
+                                                f->file_size, state->ikey,
+                                                &state->saver, SaveValue);
+      if (!state->s.ok()) {
+        state->found = true;
+        return false;
+      }
+      switch (state->saver.state) {
+        case kNotFound:
+          return true;  // Keep searching in other files
+        case kFound:
+          state->found = true;
+          return false;
+        case kDeleted:
+          return false;
+        case kCorrupt:
+          state->s =
+              Status::Corruption("corrupted key for ", state->saver.user_key);
+          state->found = true;
+          return false;
+      }
+
+      // Not reached. Added to avoid false compilation warnings of
+      // "control reaches end of non-void function".
+      return false;
+    }
+  };
+
+  State state;
+  state.found = false;
+  state.stats = stats;
+  state.last_file_read = nullptr;
+  state.last_file_read_level = -1;
+
+  state.options = &options;
+  state.ikey = k.internal_key();
+  state.vset = vset_;
+
+  state.saver.state = kNotFound;
+  state.saver.ucmp = vset_->icmp_.user_comparator();
+  state.saver.user_key = k.user_key();
+  state.saver.value = value;
+
+  ForEachOverlapping(state.saver.user_key, state.ikey, &state, &State::Match);
+
+  return state.found ? state.s : Status::NotFound(Slice());
+}
+
+bool Version::UpdateStats(const GetStats& stats) {
+  FileMetaData* f = stats.seek_file;
+  if (f != nullptr) {
+    f->allowed_seeks--;
+    if (f->allowed_seeks <= 0 && file_to_compact_ == nullptr) {
+      file_to_compact_ = f;
+      file_to_compact_level_ = stats.seek_file_level;
+      return true;
+    }
+  }
+  return false;
+}
+
+bool Version::RecordReadSample(Slice internal_key) {
+  ParsedInternalKey ikey;
+  if (!ParseInternalKey(internal_key, &ikey)) {
+    return false;
+  }
+
+  struct State {
+    GetStats stats;  // Holds first matching file
+    int matches;
+
+    static bool Match(void* arg, int level, FileMetaData* f) {
+      State* state = reinterpret_cast<State*>(arg);
+      state->matches++;
+      if (state->matches == 1) {
+        // Remember first match.
+        state->stats.seek_file = f;
+        state->stats.seek_file_level = level;
+      }
+      // We can stop iterating once we have a second match.
+      return state->matches < 2;
+    }
+  };
+
+  State state;
+  state.matches = 0;
+  ForEachOverlapping(ikey.user_key, internal_key, &state, &State::Match);
+
+  // Must have at least two matches since we want to merge across
+  // files. But what if we have a single file that contains many
+  // overwrites and deletions?  Should we have another mechanism for
+  // finding such files?
+  if (state.matches >= 2) {
+    // 1MB cost is about 1 seek (see comment in Builder::Apply).
+    return UpdateStats(state.stats);
+  }
+  return false;
+}
+
+void Version::Ref() { ++refs_; }
+
+void Version::Unref() {
+  assert(this != &vset_->dummy_versions_);
+  assert(refs_ >= 1);
+  --refs_;
+  if (refs_ == 0) {
+    delete this;
+  }
+}
+
+bool Version::OverlapInLevel(int level, const Slice* smallest_user_key,
+                             const Slice* largest_user_key) {
+  return SomeFileOverlapsRange(vset_->icmp_, (level > 0), files_[level],
+                               smallest_user_key, largest_user_key);
+}
+
+int Version::PickLevelForMemTableOutput(const Slice& smallest_user_key,
+                                        const Slice& largest_user_key) {
+  int level = 0;
+  if (!OverlapInLevel(0, &smallest_user_key, &largest_user_key)) {
+    // Push to next level if there is no overlap in next level,
+    // and the #bytes overlapping in the level after that are limited.
+    InternalKey start(smallest_user_key, kMaxSequenceNumber, kValueTypeForSeek);
+    InternalKey limit(largest_user_key, 0, static_cast<ValueType>(0));
+    std::vector<FileMetaData*> overlaps;
+    while (level < config::kMaxMemCompactLevel) {
+      if (OverlapInLevel(level + 1, &smallest_user_key, &largest_user_key)) {
+        break;
+      }
+      if (level + 2 < config::kNumLevels) {
+        // Check that file does not overlap too many grandparent bytes.
+        GetOverlappingInputs(level + 2, &start, &limit, &overlaps);
+        const int64_t sum = TotalFileSize(overlaps);
+        if (sum > MaxGrandParentOverlapBytes(vset_->options_)) {
+          break;
+        }
+      }
+      level++;
+    }
+  }
+  return level;
+}
+
+// Store in "*inputs" all files in "level" that overlap [begin,end]
+void Version::GetOverlappingInputs(int level, const InternalKey* begin,
+                                   const InternalKey* end,
+                                   std::vector<FileMetaData*>* inputs) {
+  assert(level >= 0);
+  assert(level < config::kNumLevels);
+  inputs->clear();
+  Slice user_begin, user_end;
+  if (begin != nullptr) {
+    user_begin = begin->user_key();
+  }
+  if (end != nullptr) {
+    user_end = end->user_key();
+  }
+  const Comparator* user_cmp = vset_->icmp_.user_comparator();
+  for (size_t i = 0; i < files_[level].size();) {
+    FileMetaData* f = files_[level][i++];
+    const Slice file_start = f->smallest.user_key();
+    const Slice file_limit = f->largest.user_key();
+    if (begin != nullptr && user_cmp->Compare(file_limit, user_begin) < 0) {
+      // "f" is completely before specified range; skip it
+    } else if (end != nullptr && user_cmp->Compare(file_start, user_end) > 0) {
+      // "f" is completely after specified range; skip it
+    } else {
+      inputs->push_back(f);
+      if (level == 0) {
+        // Level-0 files may overlap each other.  So check if the newly
+        // added file has expanded the range.  If so, restart search.
+        if (begin != nullptr && user_cmp->Compare(file_start, user_begin) < 0) {
+          user_begin = file_start;
+          inputs->clear();
+          i = 0;
+        } else if (end != nullptr &&
+                   user_cmp->Compare(file_limit, user_end) > 0) {
+          user_end = file_limit;
+          inputs->clear();
+          i = 0;
+        }
+      }
+    }
+  }
+}
+
+std::string Version::DebugString() const {
+  std::string r;
+  for (int level = 0; level < config::kNumLevels; level++) {
+    // E.g.,
+    //   --- level 1 ---
+    //   17:123['a' .. 'd']
+    //   20:43['e' .. 'g']
+    r.append("--- level ");
+    AppendNumberTo(&r, level);
+    r.append(" ---\n");
+    const std::vector<FileMetaData*>& files = files_[level];
+    for (size_t i = 0; i < files.size(); i++) {
+      r.push_back(' ');
+      AppendNumberTo(&r, files[i]->number);
+      r.push_back(':');
+      AppendNumberTo(&r, files[i]->file_size);
+      r.append("[");
+      r.append(files[i]->smallest.DebugString());
+      r.append(" .. ");
+      r.append(files[i]->largest.DebugString());
+      r.append("]\n");
+    }
+  }
+  return r;
+}
+
+// A helper class so we can efficiently apply a whole sequence
+// of edits to a particular state without creating intermediate
+// Versions that contain full copies of the intermediate state.
+class VersionSet::Builder {
+ private:
+  // Helper to sort by v->files_[file_number].smallest
+  struct BySmallestKey {
+    const InternalKeyComparator* internal_comparator;
+
+    bool operator()(FileMetaData* f1, FileMetaData* f2) const {
+      int r = internal_comparator->Compare(f1->smallest, f2->smallest);
+      if (r != 0) {
+        return (r < 0);
+      } else {
+        // Break ties by file number
+        return (f1->number < f2->number);
+      }
+    }
+  };
+
+  typedef std::set<FileMetaData*, BySmallestKey> FileSet;
+  struct LevelState {
+    std::set<uint64_t> deleted_files;
+    FileSet* added_files;
+  };
+
+  VersionSet* vset_;
+  Version* base_;
+  LevelState levels_[config::kNumLevels];
+
+ public:
+  // Initialize a builder with the files from *base and other info from *vset
+  Builder(VersionSet* vset, Version* base) : vset_(vset), base_(base) {
+    base_->Ref();
+    BySmallestKey cmp;
+    cmp.internal_comparator = &vset_->icmp_;
+    for (int level = 0; level < config::kNumLevels; level++) {
+      levels_[level].added_files = new FileSet(cmp);
+    }
+  }
+
+  ~Builder() {
+    for (int level = 0; level < config::kNumLevels; level++) {
+      const FileSet* added = levels_[level].added_files;
+      std::vector<FileMetaData*> to_unref;
+      to_unref.reserve(added->size());
+      for (FileSet::const_iterator it = added->begin(); it != added->end();
+           ++it) {
+        to_unref.push_back(*it);
+      }
+      delete added;
+      for (uint32_t i = 0; i < to_unref.size(); i++) {
+        FileMetaData* f = to_unref[i];
+        f->refs--;
+        if (f->refs <= 0) {
+          delete f;
+        }
+      }
+    }
+    base_->Unref();
+  }
+
+  // Apply all of the edits in *edit to the current state.
+  void Apply(VersionEdit* edit) {
+    // Update compaction pointers
+    for (size_t i = 0; i < edit->compact_pointers_.size(); i++) {
+      const int level = edit->compact_pointers_[i].first;
+      vset_->compact_pointer_[level] =
+          edit->compact_pointers_[i].second.Encode().ToString();
+    }
+
+    // Delete files
+    for (const auto& deleted_file_set_kvp : edit->deleted_files_) {
+      const int level = deleted_file_set_kvp.first;
+      const uint64_t number = deleted_file_set_kvp.second;
+      levels_[level].deleted_files.insert(number);
+    }
+
+    // Add new files
+    for (size_t i = 0; i < edit->new_files_.size(); i++) {
+      const int level = edit->new_files_[i].first;
+      FileMetaData* f = new FileMetaData(edit->new_files_[i].second);
+      f->refs = 1;
+
+      // We arrange to automatically compact this file after
+      // a certain number of seeks.  Let's assume:
+      //   (1) One seek costs 10ms
+      //   (2) Writing or reading 1MB costs 10ms (100MB/s)
+      //   (3) A compaction of 1MB does 25MB of IO:
+      //         1MB read from this level
+      //         10-12MB read from next level (boundaries may be misaligned)
+      //         10-12MB written to next level
+      // This implies that 25 seeks cost the same as the compaction
+      // of 1MB of data.  I.e., one seek costs approximately the
+      // same as the compaction of 40KB of data.  We are a little
+      // conservative and allow approximately one seek for every 16KB
+      // of data before triggering a compaction.
+      f->allowed_seeks = static_cast<int>((f->file_size / 16384U));
+      if (f->allowed_seeks < 100) f->allowed_seeks = 100;
+
+      levels_[level].deleted_files.erase(f->number);
+      levels_[level].added_files->insert(f);
+    }
+  }
+
+  // Save the current state in *v.
+  void SaveTo(Version* v) {
+    BySmallestKey cmp;
+    cmp.internal_comparator = &vset_->icmp_;
+    for (int level = 0; level < config::kNumLevels; level++) {
+      // Merge the set of added files with the set of pre-existing files.
+      // Drop any deleted files.  Store the result in *v.
+      const std::vector<FileMetaData*>& base_files = base_->files_[level];
+      std::vector<FileMetaData*>::const_iterator base_iter = base_files.begin();
+      std::vector<FileMetaData*>::const_iterator base_end = base_files.end();
+      const FileSet* added_files = levels_[level].added_files;
+      v->files_[level].reserve(base_files.size() + added_files->size());
+      for (const auto& added_file : *added_files) {
+        // Add all smaller files listed in base_
+        for (std::vector<FileMetaData*>::const_iterator bpos =
+                 std::upper_bound(base_iter, base_end, added_file, cmp);
+             base_iter != bpos; ++base_iter) {
+          MaybeAddFile(v, level, *base_iter);
+        }
+
+        MaybeAddFile(v, level, added_file);
+      }
+
+      // Add remaining base files
+      for (; base_iter != base_end; ++base_iter) {
+        MaybeAddFile(v, level, *base_iter);
+      }
+
+#ifndef NDEBUG
+      // Make sure there is no overlap in levels > 0
+      if (level > 0) {
+        for (uint32_t i = 1; i < v->files_[level].size(); i++) {
+          const InternalKey& prev_end = v->files_[level][i - 1]->largest;
+          const InternalKey& this_begin = v->files_[level][i]->smallest;
+          if (vset_->icmp_.Compare(prev_end, this_begin) >= 0) {
+            std::fprintf(stderr, "overlapping ranges in same level %s vs. %s\n",
+                         prev_end.DebugString().c_str(),
+                         this_begin.DebugString().c_str());
+            std::abort();
+          }
+        }
+      }
+#endif
+    }
+  }
+
+  void MaybeAddFile(Version* v, int level, FileMetaData* f) {
+    if (levels_[level].deleted_files.count(f->number) > 0) {
+      // File is deleted: do nothing
+    } else {
+      std::vector<FileMetaData*>* files = &v->files_[level];
+      if (level > 0 && !files->empty()) {
+        // Must not overlap
+        assert(vset_->icmp_.Compare((*files)[files->size() - 1]->largest,
+                                    f->smallest) < 0);
+      }
+      f->refs++;
+      files->push_back(f);
+    }
+  }
+};
+
+VersionSet::VersionSet(const std::string& dbname, const Options* options,
+                       TableCache* table_cache,
+                       const InternalKeyComparator* cmp)
+    : env_(options->env),
+      dbname_(dbname),
+      options_(options),
+      table_cache_(table_cache),
+      icmp_(*cmp),
+      next_file_number_(2),
+      manifest_file_number_(0),  // Filled by Recover()
+      last_sequence_(0),
+      log_number_(0),
+      prev_log_number_(0),
+      descriptor_file_(nullptr),
+      descriptor_log_(nullptr),
+      dummy_versions_(this),
+      current_(nullptr) {
+  AppendVersion(new Version(this));
+}
+
+VersionSet::~VersionSet() {
+  current_->Unref();
+  assert(dummy_versions_.next_ == &dummy_versions_);  // List must be empty
+  delete descriptor_log_;
+  delete descriptor_file_;
+}
+
+void VersionSet::AppendVersion(Version* v) {
+  // Make "v" current
+  assert(v->refs_ == 0);
+  assert(v != current_);
+  if (current_ != nullptr) {
+    current_->Unref();
+  }
+  current_ = v;
+  v->Ref();
+
+  // Append to linked list
+  v->prev_ = dummy_versions_.prev_;
+  v->next_ = &dummy_versions_;
+  v->prev_->next_ = v;
+  v->next_->prev_ = v;
+}
+
+Status VersionSet::LogAndApply(VersionEdit* edit, port::Mutex* mu) {
+  if (edit->has_log_number_) {
+    assert(edit->log_number_ >= log_number_);
+    assert(edit->log_number_ < next_file_number_);
+  } else {
+    edit->SetLogNumber(log_number_);
+  }
+
+  if (!edit->has_prev_log_number_) {
+    edit->SetPrevLogNumber(prev_log_number_);
+  }
+
+  edit->SetNextFile(next_file_number_);
+  edit->SetLastSequence(last_sequence_);
+
+  Version* v = new Version(this);
+  {
+    Builder builder(this, current_);
+    builder.Apply(edit);
+    builder.SaveTo(v);
+  }
+  Finalize(v);
+
+  // Initialize new descriptor log file if necessary by creating
+  // a temporary file that contains a snapshot of the current version.
+  std::string new_manifest_file;
+  Status s;
+  if (descriptor_log_ == nullptr) {
+    // No reason to unlock *mu here since we only hit this path in the
+    // first call to LogAndApply (when opening the database).
+    assert(descriptor_file_ == nullptr);
+    new_manifest_file = DescriptorFileName(dbname_, manifest_file_number_);
+    edit->SetNextFile(next_file_number_);
+    s = env_->NewWritableFile(new_manifest_file, &descriptor_file_);
+    if (s.ok()) {
+      descriptor_log_ = new log::Writer(descriptor_file_);
+      s = WriteSnapshot(descriptor_log_);
+    }
+  }
+
+  // Unlock during expensive MANIFEST log write
+  {
+    mu->Unlock();
+
+    // Write new record to MANIFEST log
+    if (s.ok()) {
+      std::string record;
+      edit->EncodeTo(&record);
+      s = descriptor_log_->AddRecord(record);
+      if (s.ok()) {
+        s = descriptor_file_->Sync();
+      }
+      if (!s.ok()) {
+        Log(options_->info_log, "MANIFEST write: %s\n", s.ToString().c_str());
+      }
+    }
+
+    // If we just created a new descriptor file, install it by writing a
+    // new CURRENT file that points to it.
+    if (s.ok() && !new_manifest_file.empty()) {
+      s = SetCurrentFile(env_, dbname_, manifest_file_number_);
+    }
+
+    mu->Lock();
+  }
+
+  // Install the new version
+  if (s.ok()) {
+    AppendVersion(v);
+    log_number_ = edit->log_number_;
+    prev_log_number_ = edit->prev_log_number_;
+  } else {
+    delete v;
+    if (!new_manifest_file.empty()) {
+      delete descriptor_log_;
+      delete descriptor_file_;
+      descriptor_log_ = nullptr;
+      descriptor_file_ = nullptr;
+      env_->RemoveFile(new_manifest_file);
+    }
+  }
+
+  return s;
+}
+
+Status VersionSet::Recover(bool* save_manifest) {
+  struct LogReporter : public log::Reader::Reporter {
+    Status* status;
+    void Corruption(size_t bytes, const Status& s) override {
+      if (this->status->ok()) *this->status = s;
+    }
+  };
+
+  // Read "CURRENT" file, which contains a pointer to the current manifest file
+  std::string current;
+  Status s = ReadFileToString(env_, CurrentFileName(dbname_), &current);
+  if (!s.ok()) {
+    return s;
+  }
+  if (current.empty() || current[current.size() - 1] != '\n') {
+    return Status::Corruption("CURRENT file does not end with newline");
+  }
+  current.resize(current.size() - 1);
+
+  std::string dscname = dbname_ + "/" + current;
+  SequentialFile* file;
+  s = env_->NewSequentialFile(dscname, &file);
+  if (!s.ok()) {
+    if (s.IsNotFound()) {
+      return Status::Corruption("CURRENT points to a non-existent file",
+                                s.ToString());
+    }
+    return s;
+  }
+
+  bool have_log_number = false;
+  bool have_prev_log_number = false;
+  bool have_next_file = false;
+  bool have_last_sequence = false;
+  uint64_t next_file = 0;
+  uint64_t last_sequence = 0;
+  uint64_t log_number = 0;
+  uint64_t prev_log_number = 0;
+  Builder builder(this, current_);
+
+  {
+    LogReporter reporter;
+    reporter.status = &s;
+    log::Reader reader(file, &reporter, true /*checksum*/,
+                       0 /*initial_offset*/);
+    Slice record;
+    std::string scratch;
+    while (reader.ReadRecord(&record, &scratch) && s.ok()) {
+      VersionEdit edit;
+      s = edit.DecodeFrom(record);
+      if (s.ok()) {
+        if (edit.has_comparator_ &&
+            edit.comparator_ != icmp_.user_comparator()->Name()) {
+          s = Status::InvalidArgument(
+              edit.comparator_ + " does not match existing comparator ",
+              icmp_.user_comparator()->Name());
+        }
+      }
+
+      if (s.ok()) {
+        builder.Apply(&edit);
+      }
+
+      if (edit.has_log_number_) {
+        log_number = edit.log_number_;
+        have_log_number = true;
+      }
+
+      if (edit.has_prev_log_number_) {
+        prev_log_number = edit.prev_log_number_;
+        have_prev_log_number = true;
+      }
+
+      if (edit.has_next_file_number_) {
+        next_file = edit.next_file_number_;
+        have_next_file = true;
+      }
+
+      if (edit.has_last_sequence_) {
+        last_sequence = edit.last_sequence_;
+        have_last_sequence = true;
+      }
+    }
+  }
+  delete file;
+  file = nullptr;
+
+  if (s.ok()) {
+    if (!have_next_file) {
+      s = Status::Corruption("no meta-nextfile entry in descriptor");
+    } else if (!have_log_number) {
+      s = Status::Corruption("no meta-lognumber entry in descriptor");
+    } else if (!have_last_sequence) {
+      s = Status::Corruption("no last-sequence-number entry in descriptor");
+    }
+
+    if (!have_prev_log_number) {
+      prev_log_number = 0;
+    }
+
+    MarkFileNumberUsed(prev_log_number);
+    MarkFileNumberUsed(log_number);
+  }
+
+  if (s.ok()) {
+    Version* v = new Version(this);
+    builder.SaveTo(v);
+    // Install recovered version
+    Finalize(v);
+    AppendVersion(v);
+    manifest_file_number_ = next_file;
+    next_file_number_ = next_file + 1;
+    last_sequence_ = last_sequence;
+    log_number_ = log_number;
+    prev_log_number_ = prev_log_number;
+
+    // See if we can reuse the existing MANIFEST file.
+    if (ReuseManifest(dscname, current)) {
+      // No need to save new manifest
+    } else {
+      *save_manifest = true;
+    }
+  }
+
+  return s;
+}
+
+bool VersionSet::ReuseManifest(const std::string& dscname,
+                               const std::string& dscbase) {
+  if (!options_->reuse_logs) {
+    return false;
+  }
+  FileType manifest_type;
+  uint64_t manifest_number;
+  uint64_t manifest_size;
+  if (!ParseFileName(dscbase, &manifest_number, &manifest_type) ||
+      manifest_type != kDescriptorFile ||
+      !env_->GetFileSize(dscname, &manifest_size).ok() ||
+      // Make new compacted MANIFEST if old one is too big
+      manifest_size >= TargetFileSize(options_)) {
+    return false;
+  }
+
+  assert(descriptor_file_ == nullptr);
+  assert(descriptor_log_ == nullptr);
+  Status r = env_->NewAppendableFile(dscname, &descriptor_file_);
+  if (!r.ok()) {
+    Log(options_->info_log, "Reuse MANIFEST: %s\n", r.ToString().c_str());
+    assert(descriptor_file_ == nullptr);
+    return false;
+  }
+
+  Log(options_->info_log, "Reusing MANIFEST %s\n", dscname.c_str());
+  descriptor_log_ = new log::Writer(descriptor_file_, manifest_size);
+  manifest_file_number_ = manifest_number;
+  return true;
+}
+
+void VersionSet::MarkFileNumberUsed(uint64_t number) {
+  if (next_file_number_ <= number) {
+    next_file_number_ = number + 1;
+  }
+}
+
+void VersionSet::Finalize(Version* v) {
+  // Precomputed best level for next compaction
+  int best_level = -1;
+  double best_score = -1;
+
+  for (int level = 0; level < config::kNumLevels - 1; level++) {
+    double score;
+    if (level == 0) {
+      // We treat level-0 specially by bounding the number of files
+      // instead of number of bytes for two reasons:
+      //
+      // (1) With larger write-buffer sizes, it is nice not to do too
+      // many level-0 compactions.
+      //
+      // (2) The files in level-0 are merged on every read and
+      // therefore we wish to avoid too many files when the individual
+      // file size is small (perhaps because of a small write-buffer
+      // setting, or very high compression ratios, or lots of
+      // overwrites/deletions).
+      score = v->files_[level].size() /
+              static_cast<double>(config::kL0_CompactionTrigger);
+    } else {
+      // Compute the ratio of current size to size limit.
+      const uint64_t level_bytes = TotalFileSize(v->files_[level]);
+      score =
+          static_cast<double>(level_bytes) / MaxBytesForLevel(options_, level);
+    }
+
+    if (score > best_score) {
+      best_level = level;
+      best_score = score;
+    }
+  }
+
+  v->compaction_level_ = best_level;
+  v->compaction_score_ = best_score;
+}
+
+Status VersionSet::WriteSnapshot(log::Writer* log) {
+  // TODO: Break up into multiple records to reduce memory usage on recovery?
+
+  // Save metadata
+  VersionEdit edit;
+  edit.SetComparatorName(icmp_.user_comparator()->Name());
+
+  // Save compaction pointers
+  for (int level = 0; level < config::kNumLevels; level++) {
+    if (!compact_pointer_[level].empty()) {
+      InternalKey key;
+      key.DecodeFrom(compact_pointer_[level]);
+      edit.SetCompactPointer(level, key);
+    }
+  }
+
+  // Save files
+  for (int level = 0; level < config::kNumLevels; level++) {
+    const std::vector<FileMetaData*>& files = current_->files_[level];
+    for (size_t i = 0; i < files.size(); i++) {
+      const FileMetaData* f = files[i];
+      edit.AddFile(level, f->number, f->file_size, f->smallest, f->largest);
+    }
+  }
+
+  std::string record;
+  edit.EncodeTo(&record);
+  return log->AddRecord(record);
+}
+
+int VersionSet::NumLevelFiles(int level) const {
+  assert(level >= 0);
+  assert(level < config::kNumLevels);
+  return (uint32_t)current_->files_[level].size();
+}
+
+const char* VersionSet::LevelSummary(LevelSummaryStorage* scratch) const {
+  // Update code if kNumLevels changes
+  static_assert(config::kNumLevels == 7, "");
+  std::snprintf(
+      scratch->buffer, sizeof(scratch->buffer), "files[ %d %d %d %d %d %d %d ]",
+      int(current_->files_[0].size()), int(current_->files_[1].size()),
+      int(current_->files_[2].size()), int(current_->files_[3].size()),
+      int(current_->files_[4].size()), int(current_->files_[5].size()),
+      int(current_->files_[6].size()));
+  return scratch->buffer;
+}
+
+uint64_t VersionSet::ApproximateOffsetOf(Version* v, const InternalKey& ikey) {
+  uint64_t result = 0;
+  for (int level = 0; level < config::kNumLevels; level++) {
+    const std::vector<FileMetaData*>& files = v->files_[level];
+    for (size_t i = 0; i < files.size(); i++) {
+      if (icmp_.Compare(files[i]->largest, ikey) <= 0) {
+        // Entire file is before "ikey", so just add the file size
+        result += files[i]->file_size;
+      } else if (icmp_.Compare(files[i]->smallest, ikey) > 0) {
+        // Entire file is after "ikey", so ignore
+        if (level > 0) {
+          // Files other than level 0 are sorted by meta->smallest, so
+          // no further files in this level will contain data for
+          // "ikey".
+          break;
+        }
+      } else {
+        // "ikey" falls in the range for this table.  Add the
+        // approximate offset of "ikey" within the table.
+        Table* tableptr;
+        Iterator* iter = table_cache_->NewIterator(
+            ReadOptions(), files[i]->number, files[i]->file_size, &tableptr);
+        if (tableptr != nullptr) {
+          result += tableptr->ApproximateOffsetOf(ikey.Encode());
+        }
+        delete iter;
+      }
+    }
+  }
+  return result;
+}
+
+void VersionSet::AddLiveFiles(std::set<uint64_t>* live) {
+  for (Version* v = dummy_versions_.next_; v != &dummy_versions_;
+       v = v->next_) {
+    for (int level = 0; level < config::kNumLevels; level++) {
+      const std::vector<FileMetaData*>& files = v->files_[level];
+      for (size_t i = 0; i < files.size(); i++) {
+        live->insert(files[i]->number);
+      }
+    }
+  }
+}
+
+int64_t VersionSet::NumLevelBytes(int level) const {
+  assert(level >= 0);
+  assert(level < config::kNumLevels);
+  return TotalFileSize(current_->files_[level]);
+}
+
+int64_t VersionSet::MaxNextLevelOverlappingBytes() {
+  int64_t result = 0;
+  std::vector<FileMetaData*> overlaps;
+  for (int level = 1; level < config::kNumLevels - 1; level++) {
+    for (size_t i = 0; i < current_->files_[level].size(); i++) {
+      const FileMetaData* f = current_->files_[level][i];
+      current_->GetOverlappingInputs(level + 1, &f->smallest, &f->largest,
+                                     &overlaps);
+      const int64_t sum = TotalFileSize(overlaps);
+      if (sum > result) {
+        result = sum;
+      }
+    }
+  }
+  return result;
+}
+
+// Stores the minimal range that covers all entries in inputs in
+// *smallest, *largest.
+// REQUIRES: inputs is not empty
+void VersionSet::GetRange(const std::vector<FileMetaData*>& inputs,
+                          InternalKey* smallest, InternalKey* largest) {
+  assert(!inputs.empty());
+  smallest->Clear();
+  largest->Clear();
+  for (size_t i = 0; i < inputs.size(); i++) {
+    FileMetaData* f = inputs[i];
+    if (i == 0) {
+      *smallest = f->smallest;
+      *largest = f->largest;
+    } else {
+      if (icmp_.Compare(f->smallest, *smallest) < 0) {
+        *smallest = f->smallest;
+      }
+      if (icmp_.Compare(f->largest, *largest) > 0) {
+        *largest = f->largest;
+      }
+    }
+  }
+}
+
+// Stores the minimal range that covers all entries in inputs1 and inputs2
+// in *smallest, *largest.
+// REQUIRES: inputs is not empty
+void VersionSet::GetRange2(const std::vector<FileMetaData*>& inputs1,
+                           const std::vector<FileMetaData*>& inputs2,
+                           InternalKey* smallest, InternalKey* largest) {
+  std::vector<FileMetaData*> all = inputs1;
+  all.insert(all.end(), inputs2.begin(), inputs2.end());
+  GetRange(all, smallest, largest);
+}
+
+Iterator* VersionSet::MakeInputIterator(Compaction* c) {
+  ReadOptions options;
+  options.verify_checksums = options_->paranoid_checks;
+  options.fill_cache = false;
+
+  // Level-0 files have to be merged together.  For other levels,
+  // we will make a concatenating iterator per level.
+  // TODO(opt): use concatenating iterator for level-0 if there is no overlap
+  const int space = (c->level() == 0 ? (uint32_t)c->inputs_[0].size() + 1 : 2);
+  Iterator** list = new Iterator*[space];
+  int num = 0;
+  for (int which = 0; which < 2; which++) {
+    if (!c->inputs_[which].empty()) {
+      if (c->level() + which == 0) {
+        const std::vector<FileMetaData*>& files = c->inputs_[which];
+        for (size_t i = 0; i < files.size(); i++) {
+          list[num++] = table_cache_->NewIterator(options, files[i]->number,
+                                                  files[i]->file_size);
+        }
+      } else {
+        // Create concatenating iterator for the files from this level
+        list[num++] = NewTwoLevelIterator(
+            new Version::LevelFileNumIterator(icmp_, &c->inputs_[which]),
+            &GetFileIterator, table_cache_, options);
+      }
+    }
+  }
+  assert(num <= space);
+  Iterator* result = NewMergingIterator(&icmp_, list, num);
+  delete[] list;
+  return result;
+}
+
+Compaction* VersionSet::PickCompaction() {
+  Compaction* c;
+  int level;
+
+  // We prefer compactions triggered by too much data in a level over
+  // the compactions triggered by seeks.
+  const bool size_compaction = (current_->compaction_score_ >= 1);
+  const bool seek_compaction = (current_->file_to_compact_ != nullptr);
+  if (size_compaction) {
+    level = current_->compaction_level_;
+    assert(level >= 0);
+    assert(level + 1 < config::kNumLevels);
+    c = new Compaction(options_, level);
+
+    // Pick the first file that comes after compact_pointer_[level]
+    for (size_t i = 0; i < current_->files_[level].size(); i++) {
+      FileMetaData* f = current_->files_[level][i];
+      if (compact_pointer_[level].empty() ||
+          icmp_.Compare(f->largest.Encode(), compact_pointer_[level]) > 0) {
+        c->inputs_[0].push_back(f);
+        break;
+      }
+    }
+    if (c->inputs_[0].empty()) {
+      // Wrap-around to the beginning of the key space
+      c->inputs_[0].push_back(current_->files_[level][0]);
+    }
+  } else if (seek_compaction) {
+    level = current_->file_to_compact_level_;
+    c = new Compaction(options_, level);
+    c->inputs_[0].push_back(current_->file_to_compact_);
+  } else {
+    return nullptr;
+  }
+
+  c->input_version_ = current_;
+  c->input_version_->Ref();
+
+  // Files in level 0 may overlap each other, so pick up all overlapping ones
+  if (level == 0) {
+    InternalKey smallest, largest;
+    GetRange(c->inputs_[0], &smallest, &largest);
+    // Note that the next call will discard the file we placed in
+    // c->inputs_[0] earlier and replace it with an overlapping set
+    // which will include the picked file.
+    current_->GetOverlappingInputs(0, &smallest, &largest, &c->inputs_[0]);
+    assert(!c->inputs_[0].empty());
+  }
+
+  SetupOtherInputs(c);
+
+  return c;
+}
+
+// Finds the largest key in a vector of files. Returns true if files it not
+// empty.
+bool FindLargestKey(const InternalKeyComparator& icmp,
+                    const std::vector<FileMetaData*>& files,
+                    InternalKey* largest_key) {
+  if (files.empty()) {
+    return false;
+  }
+  *largest_key = files[0]->largest;
+  for (size_t i = 1; i < files.size(); ++i) {
+    FileMetaData* f = files[i];
+    if (icmp.Compare(f->largest, *largest_key) > 0) {
+      *largest_key = f->largest;
+    }
+  }
+  return true;
+}
+
+// Finds minimum file b2=(l2, u2) in level file for which l2 > u1 and
+// user_key(l2) = user_key(u1)
+FileMetaData* FindSmallestBoundaryFile(
+    const InternalKeyComparator& icmp,
+    const std::vector<FileMetaData*>& level_files,
+    const InternalKey& largest_key) {
+  const Comparator* user_cmp = icmp.user_comparator();
+  FileMetaData* smallest_boundary_file = nullptr;
+  for (size_t i = 0; i < level_files.size(); ++i) {
+    FileMetaData* f = level_files[i];
+    if (icmp.Compare(f->smallest, largest_key) > 0 &&
+        user_cmp->Compare(f->smallest.user_key(), largest_key.user_key()) ==
+            0) {
+      if (smallest_boundary_file == nullptr ||
+          icmp.Compare(f->smallest, smallest_boundary_file->smallest) < 0) {
+        smallest_boundary_file = f;
+      }
+    }
+  }
+  return smallest_boundary_file;
+}
+
+// Extracts the largest file b1 from |compaction_files| and then searches for a
+// b2 in |level_files| for which user_key(u1) = user_key(l2). If it finds such a
+// file b2 (known as a boundary file) it adds it to |compaction_files| and then
+// searches again using this new upper bound.
+//
+// If there are two blocks, b1=(l1, u1) and b2=(l2, u2) and
+// user_key(u1) = user_key(l2), and if we compact b1 but not b2 then a
+// subsequent get operation will yield an incorrect result because it will
+// return the record from b2 in level i rather than from b1 because it searches
+// level by level for records matching the supplied user key.
+//
+// parameters:
+//   in     level_files:      List of files to search for boundary files.
+//   in/out compaction_files: List of files to extend by adding boundary files.
+void AddBoundaryInputs(const InternalKeyComparator& icmp,
+                       const std::vector<FileMetaData*>& level_files,
+                       std::vector<FileMetaData*>* compaction_files) {
+  InternalKey largest_key;
+
+  // Quick return if compaction_files is empty.
+  if (!FindLargestKey(icmp, *compaction_files, &largest_key)) {
+    return;
+  }
+
+  bool continue_searching = true;
+  while (continue_searching) {
+    FileMetaData* smallest_boundary_file =
+        FindSmallestBoundaryFile(icmp, level_files, largest_key);
+
+    // If a boundary file was found advance largest_key, otherwise we're done.
+    if (smallest_boundary_file != NULL) {
+      compaction_files->push_back(smallest_boundary_file);
+      largest_key = smallest_boundary_file->largest;
+    } else {
+      continue_searching = false;
+    }
+  }
+}
+
+void VersionSet::SetupOtherInputs(Compaction* c) {
+  const int level = c->level();
+  InternalKey smallest, largest;
+
+  AddBoundaryInputs(icmp_, current_->files_[level], &c->inputs_[0]);
+  GetRange(c->inputs_[0], &smallest, &largest);
+
+  current_->GetOverlappingInputs(level + 1, &smallest, &largest,
+                                 &c->inputs_[1]);
+
+  // Get entire range covered by compaction
+  InternalKey all_start, all_limit;
+  GetRange2(c->inputs_[0], c->inputs_[1], &all_start, &all_limit);
+
+  // See if we can grow the number of inputs in "level" without
+  // changing the number of "level+1" files we pick up.
+  if (!c->inputs_[1].empty()) {
+    std::vector<FileMetaData*> expanded0;
+    current_->GetOverlappingInputs(level, &all_start, &all_limit, &expanded0);
+    AddBoundaryInputs(icmp_, current_->files_[level], &expanded0);
+    const int64_t inputs0_size = TotalFileSize(c->inputs_[0]);
+    const int64_t inputs1_size = TotalFileSize(c->inputs_[1]);
+    const int64_t expanded0_size = TotalFileSize(expanded0);
+    if (expanded0.size() > c->inputs_[0].size() &&
+        inputs1_size + expanded0_size <
+            ExpandedCompactionByteSizeLimit(options_)) {
+      InternalKey new_start, new_limit;
+      GetRange(expanded0, &new_start, &new_limit);
+      std::vector<FileMetaData*> expanded1;
+      current_->GetOverlappingInputs(level + 1, &new_start, &new_limit,
+                                     &expanded1);
+      if (expanded1.size() == c->inputs_[1].size()) {
+        Log(options_->info_log,
+            "Expanding@%d %d+%d (%ld+%ld bytes) to %d+%d (%ld+%ld bytes)\n",
+            level, int(c->inputs_[0].size()), int(c->inputs_[1].size()),
+            long(inputs0_size), long(inputs1_size), int(expanded0.size()),
+            int(expanded1.size()), long(expanded0_size), long(inputs1_size));
+        smallest = new_start;
+        largest = new_limit;
+        c->inputs_[0] = expanded0;
+        c->inputs_[1] = expanded1;
+        GetRange2(c->inputs_[0], c->inputs_[1], &all_start, &all_limit);
+      }
+    }
+  }
+
+  // Compute the set of grandparent files that overlap this compaction
+  // (parent == level+1; grandparent == level+2)
+  if (level + 2 < config::kNumLevels) {
+    current_->GetOverlappingInputs(level + 2, &all_start, &all_limit,
+                                   &c->grandparents_);
+  }
+
+  // Update the place where we will do the next compaction for this level.
+  // We update this immediately instead of waiting for the VersionEdit
+  // to be applied so that if the compaction fails, we will try a different
+  // key range next time.
+  compact_pointer_[level] = largest.Encode().ToString();
+  c->edit_.SetCompactPointer(level, largest);
+}
+
+Compaction* VersionSet::CompactRange(int level, const InternalKey* begin,
+                                     const InternalKey* end) {
+  std::vector<FileMetaData*> inputs;
+  current_->GetOverlappingInputs(level, begin, end, &inputs);
+  if (inputs.empty()) {
+    return nullptr;
+  }
+
+  // Avoid compacting too much in one shot in case the range is large.
+  // But we cannot do this for level-0 since level-0 files can overlap
+  // and we must not pick one file and drop another older file if the
+  // two files overlap.
+  if (level > 0) {
+    const uint64_t limit = MaxFileSizeForLevel(options_, level);
+    uint64_t total = 0;
+    for (size_t i = 0; i < inputs.size(); i++) {
+      uint64_t s = inputs[i]->file_size;
+      total += s;
+      if (total >= limit) {
+        inputs.resize(i + 1);
+        break;
+      }
+    }
+  }
+
+  Compaction* c = new Compaction(options_, level);
+  c->input_version_ = current_;
+  c->input_version_->Ref();
+  c->inputs_[0] = inputs;
+  SetupOtherInputs(c);
+  return c;
+}
+
+Compaction::Compaction(const Options* options, int level)
+    : level_(level),
+      max_output_file_size_(MaxFileSizeForLevel(options, level)),
+      input_version_(nullptr),
+      grandparent_index_(0),
+      seen_key_(false),
+      overlapped_bytes_(0) {
+  for (int i = 0; i < config::kNumLevels; i++) {
+    level_ptrs_[i] = 0;
+  }
+}
+
+Compaction::~Compaction() {
+  if (input_version_ != nullptr) {
+    input_version_->Unref();
+  }
+}
+
+bool Compaction::IsTrivialMove() const {
+  const VersionSet* vset = input_version_->vset_;
+  // Avoid a move if there is lots of overlapping grandparent data.
+  // Otherwise, the move could create a parent file that will require
+  // a very expensive merge later on.
+  return (num_input_files(0) == 1 && num_input_files(1) == 0 &&
+          TotalFileSize(grandparents_) <=
+              MaxGrandParentOverlapBytes(vset->options_));
+}
+
+void Compaction::AddInputDeletions(VersionEdit* edit) {
+  for (int which = 0; which < 2; which++) {
+    for (size_t i = 0; i < inputs_[which].size(); i++) {
+      edit->RemoveFile(level_ + which, inputs_[which][i]->number);
+    }
+  }
+}
+
+bool Compaction::IsBaseLevelForKey(const Slice& user_key) {
+  // Maybe use binary search to find right entry instead of linear search?
+  const Comparator* user_cmp = input_version_->vset_->icmp_.user_comparator();
+  for (int lvl = level_ + 2; lvl < config::kNumLevels; lvl++) {
+    const std::vector<FileMetaData*>& files = input_version_->files_[lvl];
+    while (level_ptrs_[lvl] < files.size()) {
+      FileMetaData* f = files[level_ptrs_[lvl]];
+      if (user_cmp->Compare(user_key, f->largest.user_key()) <= 0) {
+        // We've advanced far enough
+        if (user_cmp->Compare(user_key, f->smallest.user_key()) >= 0) {
+          // Key falls in this file's range, so definitely not base level
+          return false;
+        }
+        break;
+      }
+      level_ptrs_[lvl]++;
+    }
+  }
+  return true;
+}
+
+bool Compaction::ShouldStopBefore(const Slice& internal_key) {
+  const VersionSet* vset = input_version_->vset_;
+  // Scan to find earliest grandparent file that contains key.
+  const InternalKeyComparator* icmp = &vset->icmp_;
+  while (grandparent_index_ < grandparents_.size() &&
+         icmp->Compare(internal_key,
+                       grandparents_[grandparent_index_]->largest.Encode()) >
+             0) {
+    if (seen_key_) {
+      overlapped_bytes_ += grandparents_[grandparent_index_]->file_size;
+    }
+    grandparent_index_++;
+  }
+  seen_key_ = true;
+
+  if (overlapped_bytes_ > MaxGrandParentOverlapBytes(vset->options_)) {
+    // Too much overlap for current output; start new output
+    overlapped_bytes_ = 0;
+    return true;
+  } else {
+    return false;
+  }
+}
+
+void Compaction::ReleaseInputs() {
+  if (input_version_ != nullptr) {
+    input_version_->Unref();
+    input_version_ = nullptr;
+  }
+}
+
+}  // namespace leveldb

Pods/leveldb-library/db/version_set.h

@@ -0,0 +1,393 @@
+// 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.
+//
+// The representation of a DBImpl consists of a set of Versions.  The
+// newest version is called "current".  Older versions may be kept
+// around to provide a consistent view to live iterators.
+//
+// Each Version keeps track of a set of Table files per level.  The
+// entire set of versions is maintained in a VersionSet.
+//
+// Version,VersionSet are thread-compatible, but require external
+// synchronization on all accesses.
+
+#ifndef STORAGE_LEVELDB_DB_VERSION_SET_H_
+#define STORAGE_LEVELDB_DB_VERSION_SET_H_
+
+#include <map>
+#include <set>
+#include <vector>
+
+#include "db/dbformat.h"
+#include "db/version_edit.h"
+#include "port/port.h"
+#include "port/thread_annotations.h"
+
+namespace leveldb {
+
+namespace log {
+class Writer;
+}
+
+class Compaction;
+class Iterator;
+class MemTable;
+class TableBuilder;
+class TableCache;
+class Version;
+class VersionSet;
+class WritableFile;
+
+// Return the smallest index i such that files[i]->largest >= key.
+// Return files.size() if there is no such file.
+// REQUIRES: "files" contains a sorted list of non-overlapping files.
+int FindFile(const InternalKeyComparator& icmp,
+             const std::vector<FileMetaData*>& files, const Slice& key);
+
+// Returns true iff some file in "files" overlaps the user key range
+// [*smallest,*largest].
+// smallest==nullptr represents a key smaller than all keys in the DB.
+// largest==nullptr represents a key largest than all keys in the DB.
+// REQUIRES: If disjoint_sorted_files, files[] contains disjoint ranges
+//           in sorted order.
+bool SomeFileOverlapsRange(const InternalKeyComparator& icmp,
+                           bool disjoint_sorted_files,
+                           const std::vector<FileMetaData*>& files,
+                           const Slice* smallest_user_key,
+                           const Slice* largest_user_key);
+
+class Version {
+ public:
+  // Lookup the value for key.  If found, store it in *val and
+  // return OK.  Else return a non-OK status.  Fills *stats.
+  // REQUIRES: lock is not held
+  struct GetStats {
+    FileMetaData* seek_file;
+    int seek_file_level;
+  };
+
+  // Append to *iters a sequence of iterators that will
+  // yield the contents of this Version when merged together.
+  // REQUIRES: This version has been saved (see VersionSet::SaveTo)
+  void AddIterators(const ReadOptions&, std::vector<Iterator*>* iters);
+
+  Status Get(const ReadOptions&, const LookupKey& key, std::string* val,
+             GetStats* stats);
+
+  // Adds "stats" into the current state.  Returns true if a new
+  // compaction may need to be triggered, false otherwise.
+  // REQUIRES: lock is held
+  bool UpdateStats(const GetStats& stats);
+
+  // Record a sample of bytes read at the specified internal key.
+  // Samples are taken approximately once every config::kReadBytesPeriod
+  // bytes.  Returns true if a new compaction may need to be triggered.
+  // REQUIRES: lock is held
+  bool RecordReadSample(Slice key);
+
+  // Reference count management (so Versions do not disappear out from
+  // under live iterators)
+  void Ref();
+  void Unref();
+
+  void GetOverlappingInputs(
+      int level,
+      const InternalKey* begin,  // nullptr means before all keys
+      const InternalKey* end,    // nullptr means after all keys
+      std::vector<FileMetaData*>* inputs);
+
+  // Returns true iff some file in the specified level overlaps
+  // some part of [*smallest_user_key,*largest_user_key].
+  // smallest_user_key==nullptr represents a key smaller than all the DB's keys.
+  // largest_user_key==nullptr represents a key largest than all the DB's keys.
+  bool OverlapInLevel(int level, const Slice* smallest_user_key,
+                      const Slice* largest_user_key);
+
+  // Return the level at which we should place a new memtable compaction
+  // result that covers the range [smallest_user_key,largest_user_key].
+  int PickLevelForMemTableOutput(const Slice& smallest_user_key,
+                                 const Slice& largest_user_key);
+
+  int NumFiles(int level) const { return (uint32_t)files_[level].size(); }
+
+  // Return a human readable string that describes this version's contents.
+  std::string DebugString() const;
+
+ private:
+  friend class Compaction;
+  friend class VersionSet;
+
+  class LevelFileNumIterator;
+
+  explicit Version(VersionSet* vset)
+      : vset_(vset),
+        next_(this),
+        prev_(this),
+        refs_(0),
+        file_to_compact_(nullptr),
+        file_to_compact_level_(-1),
+        compaction_score_(-1),
+        compaction_level_(-1) {}
+
+  Version(const Version&) = delete;
+  Version& operator=(const Version&) = delete;
+
+  ~Version();
+
+  Iterator* NewConcatenatingIterator(const ReadOptions&, int level) const;
+
+  // Call func(arg, level, f) for every file that overlaps user_key in
+  // order from newest to oldest.  If an invocation of func returns
+  // false, makes no more calls.
+  //
+  // REQUIRES: user portion of internal_key == user_key.
+  void ForEachOverlapping(Slice user_key, Slice internal_key, void* arg,
+                          bool (*func)(void*, int, FileMetaData*));
+
+  VersionSet* vset_;  // VersionSet to which this Version belongs
+  Version* next_;     // Next version in linked list
+  Version* prev_;     // Previous version in linked list
+  int refs_;          // Number of live refs to this version
+
+  // List of files per level
+  std::vector<FileMetaData*> files_[config::kNumLevels];
+
+  // Next file to compact based on seek stats.
+  FileMetaData* file_to_compact_;
+  int file_to_compact_level_;
+
+  // Level that should be compacted next and its compaction score.
+  // Score < 1 means compaction is not strictly needed.  These fields
+  // are initialized by Finalize().
+  double compaction_score_;
+  int compaction_level_;
+};
+
+class VersionSet {
+ public:
+  VersionSet(const std::string& dbname, const Options* options,
+             TableCache* table_cache, const InternalKeyComparator*);
+  VersionSet(const VersionSet&) = delete;
+  VersionSet& operator=(const VersionSet&) = delete;
+
+  ~VersionSet();
+
+  // Apply *edit to the current version to form a new descriptor that
+  // is both saved to persistent state and installed as the new
+  // current version.  Will release *mu while actually writing to the file.
+  // REQUIRES: *mu is held on entry.
+  // REQUIRES: no other thread concurrently calls LogAndApply()
+  Status LogAndApply(VersionEdit* edit, port::Mutex* mu)
+      EXCLUSIVE_LOCKS_REQUIRED(mu);
+
+  // Recover the last saved descriptor from persistent storage.
+  Status Recover(bool* save_manifest);
+
+  // Return the current version.
+  Version* current() const { return current_; }
+
+  // Return the current manifest file number
+  uint64_t ManifestFileNumber() const { return manifest_file_number_; }
+
+  // Allocate and return a new file number
+  uint64_t NewFileNumber() { return next_file_number_++; }
+
+  // Arrange to reuse "file_number" unless a newer file number has
+  // already been allocated.
+  // REQUIRES: "file_number" was returned by a call to NewFileNumber().
+  void ReuseFileNumber(uint64_t file_number) {
+    if (next_file_number_ == file_number + 1) {
+      next_file_number_ = file_number;
+    }
+  }
+
+  // Return the number of Table files at the specified level.
+  int NumLevelFiles(int level) const;
+
+  // Return the combined file size of all files at the specified level.
+  int64_t NumLevelBytes(int level) const;
+
+  // Return the last sequence number.
+  uint64_t LastSequence() const { return last_sequence_; }
+
+  // Set the last sequence number to s.
+  void SetLastSequence(uint64_t s) {
+    assert(s >= last_sequence_);
+    last_sequence_ = s;
+  }
+
+  // Mark the specified file number as used.
+  void MarkFileNumberUsed(uint64_t number);
+
+  // Return the current log file number.
+  uint64_t LogNumber() const { return log_number_; }
+
+  // Return the log file number for the log file that is currently
+  // being compacted, or zero if there is no such log file.
+  uint64_t PrevLogNumber() const { return prev_log_number_; }
+
+  // Pick level and inputs for a new compaction.
+  // Returns nullptr if there is no compaction to be done.
+  // Otherwise returns a pointer to a heap-allocated object that
+  // describes the compaction.  Caller should delete the result.
+  Compaction* PickCompaction();
+
+  // Return a compaction object for compacting the range [begin,end] in
+  // the specified level.  Returns nullptr if there is nothing in that
+  // level that overlaps the specified range.  Caller should delete
+  // the result.
+  Compaction* CompactRange(int level, const InternalKey* begin,
+                           const InternalKey* end);
+
+  // Return the maximum overlapping data (in bytes) at next level for any
+  // file at a level >= 1.
+  int64_t MaxNextLevelOverlappingBytes();
+
+  // Create an iterator that reads over the compaction inputs for "*c".
+  // The caller should delete the iterator when no longer needed.
+  Iterator* MakeInputIterator(Compaction* c);
+
+  // Returns true iff some level needs a compaction.
+  bool NeedsCompaction() const {
+    Version* v = current_;
+    return (v->compaction_score_ >= 1) || (v->file_to_compact_ != nullptr);
+  }
+
+  // Add all files listed in any live version to *live.
+  // May also mutate some internal state.
+  void AddLiveFiles(std::set<uint64_t>* live);
+
+  // Return the approximate offset in the database of the data for
+  // "key" as of version "v".
+  uint64_t ApproximateOffsetOf(Version* v, const InternalKey& key);
+
+  // Return a human-readable short (single-line) summary of the number
+  // of files per level.  Uses *scratch as backing store.
+  struct LevelSummaryStorage {
+    char buffer[100];
+  };
+  const char* LevelSummary(LevelSummaryStorage* scratch) const;
+
+ private:
+  class Builder;
+
+  friend class Compaction;
+  friend class Version;
+
+  bool ReuseManifest(const std::string& dscname, const std::string& dscbase);
+
+  void Finalize(Version* v);
+
+  void GetRange(const std::vector<FileMetaData*>& inputs, InternalKey* smallest,
+                InternalKey* largest);
+
+  void GetRange2(const std::vector<FileMetaData*>& inputs1,
+                 const std::vector<FileMetaData*>& inputs2,
+                 InternalKey* smallest, InternalKey* largest);
+
+  void SetupOtherInputs(Compaction* c);
+
+  // Save current contents to *log
+  Status WriteSnapshot(log::Writer* log);
+
+  void AppendVersion(Version* v);
+
+  Env* const env_;
+  const std::string dbname_;
+  const Options* const options_;
+  TableCache* const table_cache_;
+  const InternalKeyComparator icmp_;
+  uint64_t next_file_number_;
+  uint64_t manifest_file_number_;
+  uint64_t last_sequence_;
+  uint64_t log_number_;
+  uint64_t prev_log_number_;  // 0 or backing store for memtable being compacted
+
+  // Opened lazily
+  WritableFile* descriptor_file_;
+  log::Writer* descriptor_log_;
+  Version dummy_versions_;  // Head of circular doubly-linked list of versions.
+  Version* current_;        // == dummy_versions_.prev_
+
+  // Per-level key at which the next compaction at that level should start.
+  // Either an empty string, or a valid InternalKey.
+  std::string compact_pointer_[config::kNumLevels];
+};
+
+// A Compaction encapsulates information about a compaction.
+class Compaction {
+ public:
+  ~Compaction();
+
+  // Return the level that is being compacted.  Inputs from "level"
+  // and "level+1" will be merged to produce a set of "level+1" files.
+  int level() const { return level_; }
+
+  // Return the object that holds the edits to the descriptor done
+  // by this compaction.
+  VersionEdit* edit() { return &edit_; }
+
+  // "which" must be either 0 or 1
+  int num_input_files(int which) const { return (uint32_t)inputs_[which].size(); }
+
+  // Return the ith input file at "level()+which" ("which" must be 0 or 1).
+  FileMetaData* input(int which, int i) const { return inputs_[which][i]; }
+
+  // Maximum size of files to build during this compaction.
+  uint64_t MaxOutputFileSize() const { return max_output_file_size_; }
+
+  // Is this a trivial compaction that can be implemented by just
+  // moving a single input file to the next level (no merging or splitting)
+  bool IsTrivialMove() const;
+
+  // Add all inputs to this compaction as delete operations to *edit.
+  void AddInputDeletions(VersionEdit* edit);
+
+  // Returns true if the information we have available guarantees that
+  // the compaction is producing data in "level+1" for which no data exists
+  // in levels greater than "level+1".
+  bool IsBaseLevelForKey(const Slice& user_key);
+
+  // Returns true iff we should stop building the current output
+  // before processing "internal_key".
+  bool ShouldStopBefore(const Slice& internal_key);
+
+  // Release the input version for the compaction, once the compaction
+  // is successful.
+  void ReleaseInputs();
+
+ private:
+  friend class Version;
+  friend class VersionSet;
+
+  Compaction(const Options* options, int level);
+
+  int level_;
+  uint64_t max_output_file_size_;
+  Version* input_version_;
+  VersionEdit edit_;
+
+  // Each compaction reads inputs from "level_" and "level_+1"
+  std::vector<FileMetaData*> inputs_[2];  // The two sets of inputs
+
+  // State used to check for number of overlapping grandparent files
+  // (parent == level_ + 1, grandparent == level_ + 2)
+  std::vector<FileMetaData*> grandparents_;
+  size_t grandparent_index_;  // Index in grandparent_starts_
+  bool seen_key_;             // Some output key has been seen
+  int64_t overlapped_bytes_;  // Bytes of overlap between current output
+                              // and grandparent files
+
+  // State for implementing IsBaseLevelForKey
+
+  // level_ptrs_ holds indices into input_version_->levels_: our state
+  // is that we are positioned at one of the file ranges for each
+  // higher level than the ones involved in this compaction (i.e. for
+  // all L >= level_ + 2).
+  size_t level_ptrs_[config::kNumLevels];
+};
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_VERSION_SET_H_

Pods/leveldb-library/db/write_batch.cc

@@ -0,0 +1,150 @@
+// 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::rep_ :=
+//    sequence: fixed64
+//    count: fixed32
+//    data: record[count]
+// record :=
+//    kTypeValue varstring varstring         |
+//    kTypeDeletion varstring
+// varstring :=
+//    len: varint32
+//    data: uint8[len]
+
+#include "leveldb/write_batch.h"
+
+#include "db/dbformat.h"
+#include "db/memtable.h"
+#include "db/write_batch_internal.h"
+#include "leveldb/db.h"
+#include "util/coding.h"
+
+namespace leveldb {
+
+// WriteBatch header has an 8-byte sequence number followed by a 4-byte count.
+static const size_t kHeader = 12;
+
+WriteBatch::WriteBatch() { Clear(); }
+
+WriteBatch::~WriteBatch() = default;
+
+WriteBatch::Handler::~Handler() = default;
+
+void WriteBatch::Clear() {
+  rep_.clear();
+  rep_.resize(kHeader);
+}
+
+size_t WriteBatch::ApproximateSize() const { return rep_.size(); }
+
+Status WriteBatch::Iterate(Handler* handler) const {
+  Slice input(rep_);
+  if (input.size() < kHeader) {
+    return Status::Corruption("malformed WriteBatch (too small)");
+  }
+
+  input.remove_prefix(kHeader);
+  Slice key, value;
+  int found = 0;
+  while (!input.empty()) {
+    found++;
+    char tag = input[0];
+    input.remove_prefix(1);
+    switch (tag) {
+      case kTypeValue:
+        if (GetLengthPrefixedSlice(&input, &key) &&
+            GetLengthPrefixedSlice(&input, &value)) {
+          handler->Put(key, value);
+        } else {
+          return Status::Corruption("bad WriteBatch Put");
+        }
+        break;
+      case kTypeDeletion:
+        if (GetLengthPrefixedSlice(&input, &key)) {
+          handler->Delete(key);
+        } else {
+          return Status::Corruption("bad WriteBatch Delete");
+        }
+        break;
+      default:
+        return Status::Corruption("unknown WriteBatch tag");
+    }
+  }
+  if (found != WriteBatchInternal::Count(this)) {
+    return Status::Corruption("WriteBatch has wrong count");
+  } else {
+    return Status::OK();
+  }
+}
+
+int WriteBatchInternal::Count(const WriteBatch* b) {
+  return DecodeFixed32(b->rep_.data() + 8);
+}
+
+void WriteBatchInternal::SetCount(WriteBatch* b, int n) {
+  EncodeFixed32(&b->rep_[8], n);
+}
+
+SequenceNumber WriteBatchInternal::Sequence(const WriteBatch* b) {
+  return SequenceNumber(DecodeFixed64(b->rep_.data()));
+}
+
+void WriteBatchInternal::SetSequence(WriteBatch* b, SequenceNumber seq) {
+  EncodeFixed64(&b->rep_[0], seq);
+}
+
+void WriteBatch::Put(const Slice& key, const Slice& value) {
+  WriteBatchInternal::SetCount(this, WriteBatchInternal::Count(this) + 1);
+  rep_.push_back(static_cast<char>(kTypeValue));
+  PutLengthPrefixedSlice(&rep_, key);
+  PutLengthPrefixedSlice(&rep_, value);
+}
+
+void WriteBatch::Delete(const Slice& key) {
+  WriteBatchInternal::SetCount(this, WriteBatchInternal::Count(this) + 1);
+  rep_.push_back(static_cast<char>(kTypeDeletion));
+  PutLengthPrefixedSlice(&rep_, key);
+}
+
+void WriteBatch::Append(const WriteBatch& source) {
+  WriteBatchInternal::Append(this, &source);
+}
+
+namespace {
+class MemTableInserter : public WriteBatch::Handler {
+ public:
+  SequenceNumber sequence_;
+  MemTable* mem_;
+
+  void Put(const Slice& key, const Slice& value) override {
+    mem_->Add(sequence_, kTypeValue, key, value);
+    sequence_++;
+  }
+  void Delete(const Slice& key) override {
+    mem_->Add(sequence_, kTypeDeletion, key, Slice());
+    sequence_++;
+  }
+};
+}  // namespace
+
+Status WriteBatchInternal::InsertInto(const WriteBatch* b, MemTable* memtable) {
+  MemTableInserter inserter;
+  inserter.sequence_ = WriteBatchInternal::Sequence(b);
+  inserter.mem_ = memtable;
+  return b->Iterate(&inserter);
+}
+
+void WriteBatchInternal::SetContents(WriteBatch* b, const Slice& contents) {
+  assert(contents.size() >= kHeader);
+  b->rep_.assign(contents.data(), contents.size());
+}
+
+void WriteBatchInternal::Append(WriteBatch* dst, const WriteBatch* src) {
+  SetCount(dst, Count(dst) + Count(src));
+  assert(src->rep_.size() >= kHeader);
+  dst->rep_.append(src->rep_.data() + kHeader, src->rep_.size() - kHeader);
+}
+
+}  // namespace leveldb

Pods/leveldb-library/db/write_batch_internal.h

@@ -0,0 +1,45 @@
+// 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_WRITE_BATCH_INTERNAL_H_
+#define STORAGE_LEVELDB_DB_WRITE_BATCH_INTERNAL_H_
+
+#include "db/dbformat.h"
+#include "leveldb/write_batch.h"
+
+namespace leveldb {
+
+class MemTable;
+
+// WriteBatchInternal provides static methods for manipulating a
+// WriteBatch that we don't want in the public WriteBatch interface.
+class WriteBatchInternal {
+ public:
+  // Return the number of entries in the batch.
+  static int Count(const WriteBatch* batch);
+
+  // Set the count for the number of entries in the batch.
+  static void SetCount(WriteBatch* batch, int n);
+
+  // Return the sequence number for the start of this batch.
+  static SequenceNumber Sequence(const WriteBatch* batch);
+
+  // Store the specified number as the sequence number for the start of
+  // this batch.
+  static void SetSequence(WriteBatch* batch, SequenceNumber seq);
+
+  static Slice Contents(const WriteBatch* batch) { return Slice(batch->rep_); }
+
+  static size_t ByteSize(const WriteBatch* batch) { return batch->rep_.size(); }
+
+  static void SetContents(WriteBatch* batch, const Slice& contents);
+
+  static Status InsertInto(const WriteBatch* batch, MemTable* memtable);
+
+  static void Append(WriteBatch* dst, const WriteBatch* src);
+};
+
+}  // namespace leveldb
+
+#endif  // STORAGE_LEVELDB_DB_WRITE_BATCH_INTERNAL_H_