rn-leveldb 3.11.0

package/cpp/leveldb/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_

package/cpp/leveldb/db/filename_test.cc

@@ -0,0 +1,132 @@
+// 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 "gtest/gtest.h"
+#include "db/dbformat.h"
+#include "port/port.h"
+#include "util/logging.h"
+
+namespace leveldb {
+
+TEST(FileNameTest, Parse) {
+  Slice db;
+  FileType type;
+  uint64_t number;
+
+  // Successful parses
+  static struct {
+    const char* fname;
+    uint64_t number;
+    FileType type;
+  } cases[] = {
+      {"100.log", 100, kLogFile},
+      {"0.log", 0, kLogFile},
+      {"0.sst", 0, kTableFile},
+      {"0.ldb", 0, kTableFile},
+      {"CURRENT", 0, kCurrentFile},
+      {"LOCK", 0, kDBLockFile},
+      {"MANIFEST-2", 2, kDescriptorFile},
+      {"MANIFEST-7", 7, kDescriptorFile},
+      {"LOG", 0, kInfoLogFile},
+      {"LOG.old", 0, kInfoLogFile},
+      {"18446744073709551615.log", 18446744073709551615ull, kLogFile},
+  };
+  for (int i = 0; i < sizeof(cases) / sizeof(cases[0]); i++) {
+    std::string f = cases[i].fname;
+    ASSERT_TRUE(ParseFileName(f, &number, &type)) << f;
+    ASSERT_EQ(cases[i].type, type) << f;
+    ASSERT_EQ(cases[i].number, number) << f;
+  }
+
+  // Errors
+  static const char* errors[] = {"",
+                                 "foo",
+                                 "foo-dx-100.log",
+                                 ".log",
+                                 "",
+                                 "manifest",
+                                 "CURREN",
+                                 "CURRENTX",
+                                 "MANIFES",
+                                 "MANIFEST",
+                                 "MANIFEST-",
+                                 "XMANIFEST-3",
+                                 "MANIFEST-3x",
+                                 "LOC",
+                                 "LOCKx",
+                                 "LO",
+                                 "LOGx",
+                                 "18446744073709551616.log",
+                                 "184467440737095516150.log",
+                                 "100",
+                                 "100.",
+                                 "100.lop"};
+  for (int i = 0; i < sizeof(errors) / sizeof(errors[0]); i++) {
+    std::string f = errors[i];
+    ASSERT_TRUE(!ParseFileName(f, &number, &type)) << f;
+  }
+}
+
+TEST(FileNameTest, Construction) {
+  uint64_t number;
+  FileType type;
+  std::string fname;
+
+  fname = CurrentFileName("foo");
+  ASSERT_EQ("foo/", std::string(fname.data(), 4));
+  ASSERT_TRUE(ParseFileName(fname.c_str() + 4, &number, &type));
+  ASSERT_EQ(0, number);
+  ASSERT_EQ(kCurrentFile, type);
+
+  fname = LockFileName("foo");
+  ASSERT_EQ("foo/", std::string(fname.data(), 4));
+  ASSERT_TRUE(ParseFileName(fname.c_str() + 4, &number, &type));
+  ASSERT_EQ(0, number);
+  ASSERT_EQ(kDBLockFile, type);
+
+  fname = LogFileName("foo", 192);
+  ASSERT_EQ("foo/", std::string(fname.data(), 4));
+  ASSERT_TRUE(ParseFileName(fname.c_str() + 4, &number, &type));
+  ASSERT_EQ(192, number);
+  ASSERT_EQ(kLogFile, type);
+
+  fname = TableFileName("bar", 200);
+  ASSERT_EQ("bar/", std::string(fname.data(), 4));
+  ASSERT_TRUE(ParseFileName(fname.c_str() + 4, &number, &type));
+  ASSERT_EQ(200, number);
+  ASSERT_EQ(kTableFile, type);
+
+  fname = DescriptorFileName("bar", 100);
+  ASSERT_EQ("bar/", std::string(fname.data(), 4));
+  ASSERT_TRUE(ParseFileName(fname.c_str() + 4, &number, &type));
+  ASSERT_EQ(100, number);
+  ASSERT_EQ(kDescriptorFile, type);
+
+  fname = TempFileName("tmp", 999);
+  ASSERT_EQ("tmp/", std::string(fname.data(), 4));
+  ASSERT_TRUE(ParseFileName(fname.c_str() + 4, &number, &type));
+  ASSERT_EQ(999, number);
+  ASSERT_EQ(kTempFile, type);
+
+  fname = InfoLogFileName("foo");
+  ASSERT_EQ("foo/", std::string(fname.data(), 4));
+  ASSERT_TRUE(ParseFileName(fname.c_str() + 4, &number, &type));
+  ASSERT_EQ(0, number);
+  ASSERT_EQ(kInfoLogFile, type);
+
+  fname = OldInfoLogFileName("foo");
+  ASSERT_EQ("foo/", std::string(fname.data(), 4));
+  ASSERT_TRUE(ParseFileName(fname.c_str() + 4, &number, &type));
+  ASSERT_EQ(0, number);
+  ASSERT_EQ(kInfoLogFile, type);
+}
+
+}  // namespace leveldb
+
+int main(int argc, char** argv) {
+  testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}

package/cpp/leveldb/db/leveldbutil.cc

@@ -0,0 +1,64 @@
+// 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 <cstdio>
+
+#include "leveldb/dumpfile.h"
+#include "leveldb/env.h"
+#include "leveldb/status.h"
+
+namespace leveldb {
+namespace {
+
+class StdoutPrinter : public WritableFile {
+ public:
+  Status Append(const Slice& data) override {
+    fwrite(data.data(), 1, data.size(), stdout);
+    return Status::OK();
+  }
+  Status Close() override { return Status::OK(); }
+  Status Flush() override { return Status::OK(); }
+  Status Sync() override { return Status::OK(); }
+};
+
+bool HandleDumpCommand(Env* env, char** files, int num) {
+  StdoutPrinter printer;
+  bool ok = true;
+  for (int i = 0; i < num; i++) {
+    Status s = DumpFile(env, files[i], &printer);
+    if (!s.ok()) {
+      std::fprintf(stderr, "%s\n", s.ToString().c_str());
+      ok = false;
+    }
+  }
+  return ok;
+}
+
+}  // namespace
+}  // namespace leveldb
+
+static void Usage() {
+  std::fprintf(
+      stderr,
+      "Usage: leveldbutil command...\n"
+      "   dump files...         -- dump contents of specified files\n");
+}
+
+int main(int argc, char** argv) {
+  leveldb::Env* env = leveldb::Env::Default();
+  bool ok = true;
+  if (argc < 2) {
+    Usage();
+    ok = false;
+  } else {
+    std::string command = argv[1];
+    if (command == "dump") {
+      ok = leveldb::HandleDumpCommand(env, argv + 2, argc - 2);
+    } else {
+      Usage();
+      ok = false;
+    }
+  }
+  return (ok ? 0 : 1);
+}

package/cpp/leveldb/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_

package/cpp/leveldb/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

package/cpp/leveldb/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_