Persist sessionStorage on disk.

webkit/dom_storage/session_storage_database.cc

Index: webkit/dom_storage/session_storage_database.cc
diff --git a/webkit/dom_storage/session_storage_database.cc b/webkit/dom_storage/session_storage_database.cc
new file mode 100644
index 0000000000000000000000000000000000000000..ba2f9044d26391e79e072ec81e7f678853330beb
--- /dev/null
+++ b/webkit/dom_storage/session_storage_database.cc
@@ -0,0 +1,197 @@
+// Copyright (c) 2012 The Chromium Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file.
+
+#include "webkit/dom_storage/session_storage_database.h"
+
+#include "base/file_util.h"
+#include "base/string_number_conversions.h"
+#include "base/utf_string_conversions.h"
+#include "third_party/leveldatabase/src/include/leveldb/db.h"
+#include "third_party/leveldatabase/src/include/leveldb/iterator.h"
+#include "third_party/leveldatabase/src/include/leveldb/status.h"
+#include "third_party/leveldatabase/src/include/leveldb/options.h"
+
+#include <sstream>
+
+// Layout of the database:

[michaeln, 2012/04/03 22:56:45]

This seems like the best place to start hammering out the details on, the
'schema'. 

+// | key                       | value               |
+// ---------------------------------------------------
+// | area-1 (1 = namespace id) | dummy               | start of area-1-* keys

[michaeln, 2012/04/03 22:56:45]

what's the benefit of the dummy entries?

[marja, 2012/04/10 15:34:45]

To be able to iterate "all origins that belong to area-1" or "all keys that
belong to map-1". Otherwise we wouldn't know where to start. Now the first key
of those things to iterate is a known string, and the keys are stored in order.
So, we can start there, and iterate forward until we hit something that we're
not interested in any more.

Actually, the value of the entries "map-1" etc. can be used for storing the
refcount.

+// | area-1-origin1            | 1 (mapid)           |
+// | area-1-origin2            | 2                   |
+// | area-2                    | dummy               |
+// | area-2-origin1            | 1                   | shallow copy
+// | area-3                    |                     |
+// | area-3-origin1            | 3                   | deep copy
+// | map-1                     | dummy               | start of map-1-* keys
+// | map-1-a                   | b                   | a = b in map 1
+// | ...                       |                     |
+// | next-map-id               | 4                   |
+
+namespace {
+
+// Helper functions for creating the keys.
+std::string AreaKey(int64 namespace_id, const GURL& origin) {
+  std::ostringstream stream;

[michaeln, 2012/04/03 22:56:45]

do we use sstream elswhere in the project? if not, maybe we should be using our
base library functions to form these strings (like base::Int64ToString() and
base::StringPringf())

[marja, 2012/04/10 15:34:45]

Done.

+  stream << "area-" << namespace_id << "-" << origin.spec();
+  return stream.str();
+}
+
+std::string MapStartKey(const std::string& map_id) {
+  std::ostringstream stream;
+  stream << "map-" << map_id;
+  return stream.str();
+}
+
+std::string MapKey(const std::string& map_id, const std::string& key) {
+  std::ostringstream stream;
+  stream << "value-" << map_id << "-" << key;
+  return stream.str();
+}
+
+std::string NextMapIdKey() {
+  return "next-map-id";
+}
+
+}  // namespace
+
+namespace dom_storage {
+
+SessionStorageDatabase::SessionStorageDatabase(const FilePath& file_path)
+    : DomStorageDatabase(file_path) {
+}
+
+SessionStorageDatabase::~SessionStorageDatabase() { }
+
+void SessionStorageDatabase::ReadAllValues(int64 namespace_id,
+                                           const GURL& origin,
+                                           ValuesMap* result) {
+  // We don't create a database if it doesn't exist. In that case, there is
+  // nothing to be added to the result.
+  if (!LazyOpen(false))
+    return;
+  // Check if there is map for namespace_id-origin.
+  std::string area_key = AreaKey(namespace_id, origin);
+  std::string map_id;
+  leveldb::Status s = db_->Get(leveldb::ReadOptions(), area_key, &map_id);
+  if (!s.ok() || map_id.empty())
+    return;
+  ReadAllValuesInMap(map_id, result);
+}
+
+bool SessionStorageDatabase::CommitChanges(int64 namespace_id,

[michaeln, 2012/04/03 22:56:45]

Another detail to hammer out is around the read/write access patterns where the
class may be used from multiple threads. Not sure if we'll need to use the
'snapshot' facility, but i'm pretty sure we'll need to use the 'writebatch' for
a coherent set of changes in this sort of CommitChanges method.

[marja, 2012/04/10 15:34:45]

Added WriteBatch. If we allow writing from 2 threads, we'll also need snapshots.
I'll add them later.

+                                           const GURL& origin,
+                                           bool clear_all_first,
+                                           const ValuesMap& changes) {
+  if (!LazyOpen(!changes.empty())) {
+    // If we're being asked to commit changes that will result in an
+    // empty database, we return true if the database file doesn't exist.
+    return clear_all_first && changes.empty() &&
+           !file_util::PathExists(file_path_);
+  }
+  std::string area_key = AreaKey(namespace_id, origin);
+  std::string map_id;
+  leveldb::Status s = db_->Get(leveldb::ReadOptions(), area_key, &map_id);
+  DCHECK(s.ok() || s.IsNotFound());
+  if (s.IsNotFound()) {
+    // Create a new map.
+    std::string next_map_id_key = NextMapIdKey();
+    s = db_->Get(leveldb::ReadOptions(), next_map_id_key, &map_id);
+    DCHECK(s.ok() || s.IsNotFound());
+    int64 next_map_id = 0;
+    if (!s.IsNotFound() || !base::StringToInt64(map_id, &next_map_id))
+      map_id = "0";
+    ++next_map_id;
+    s = db_->Put(leveldb::WriteOptions(), next_map_id_key,
+                 base::Int64ToString(next_map_id));
+    DCHECK(s.ok());
+    s = db_->Put(leveldb::WriteOptions(), area_key, map_id);
+  } else if (clear_all_first) {
+    ValuesMap values;
+    ReadAllValuesInMap(map_id, &values);

[michaeln, 2012/04/03 22:56:45]

is there a way to clear values w/o having to read them?

[marja, 2012/04/10 15:34:45]

No, afaik. The interface is just Get(), Put(), Delete(), and we'd need to know
which keys to delete. (Otoh, DOMStorageArea has them in memory. Should I use
that information when deleting the keys?)

+    for (ValuesMap::const_iterator it = values.begin(); it != values.end();
+         ++it) {
+      leveldb::Status s =
+          db_->Delete(leveldb::WriteOptions(), UTF16ToUTF8(it->first));
+      DCHECK(s.ok());
+    }
+  }
+
+  for(ValuesMap::const_iterator it = changes.begin();
+      it != changes.end(); ++it) {
+    NullableString16 value = it->second;
+    std::string key = MapKey(map_id, UTF16ToUTF8(it->first));
+    if (value.is_null()) {
+      s = db_->Delete(leveldb::WriteOptions(), key);
+      DCHECK(s.ok());
+    } else {
+      s = db_->Put(leveldb::WriteOptions(), key, UTF16ToUTF8(value.string()));

[michaeln, 2012/04/03 22:56:45]

i think we need to treat the 'value' as binary data and not attempt to perform
any character type conversions on it. lets assume there can be embedded nulls
and invalid unicode chars in these values.

[marja, 2012/04/10 15:34:45]

Ok, UTF16ToUTF8 was definitely wrong. Otoh, we cannot store arbitrary blobs if
the raw byte count is not even (lots of APIs seem to handle string16's, and I
have no idea how to represent a odd-numbered amount of raw bytes as string16).
But I'll change this so that null bytes and invalid UTF16 char sequences don't
break it.

+      DCHECK(s.ok());
+    }
+  }
+  return true;
+}
+
+bool SessionStorageDatabase::LazyOpen(bool create_if_needed) {

[michaeln, 2012/04/03 22:56:45]

This stuff about lazily creating the directory on disk (a leveldb instance on
disk is a directory) seems secondary to the schema + r/w access pattern stuff.

+  if (failed_to_open_) {
+    // Don't try to open a database that we know has failed
+    // already.
+    return false;
+  }
+
+  if (IsOpen())
+    return true;
+
+  bool database_exists = file_util::PathExists(file_path_);
+
+  if (!database_exists && !create_if_needed) {
+    // If the file doesn't exist already and we haven't been asked to create
+    // a file on disk, then we don't bother opening the database. This means
+    // we wait until we absolutely need to put something onto disk before we
+    // do so.
+    return false;
+  }
+
+  leveldb::Options options;
+  options.create_if_missing = create_if_needed;
+  leveldb::Status s;
+  leveldb::DB* db;
+#if defined(OS_WIN)
+  s = leveldb::DB::Open(options, WideToUTF8(file_path_.value()), &db);
+#elif defined(OS_POSIX)
+  s = leveldb::DB::Open(options, file_path_.value(), &db);
+#endif
+  if (!s.ok()) {
+    DCHECK(db == NULL);
+    failed_to_open_ = true;
+    return false;
+  }
+
+  db_.reset(db);
+  return true;
+}
+
+bool SessionStorageDatabase::IsOpen() const {
+  return db_.get();
+}
+
+void SessionStorageDatabase::ReadAllValuesInMap(const std::string map_id,
+                                                ValuesMap* result) {
+  scoped_ptr<leveldb::Iterator> it(db_->NewIterator(leveldb::ReadOptions()));
+  std::string map_start_key = MapStartKey(map_id);
+  // Skip the dummy entry, then start iterating the keys in the map.
+  for (it->Seek(map_start_key), it->Next(); it->Valid(); it->Next()) {
+    string16 key = UTF8ToUTF16(it->key().ToString());
+    string16 value = UTF8ToUTF16(it->value().ToString());
+    // Key is of the form "value-<mapid>-<key>".
+    size_t second_dash = key.find('-', 6);
+    if (second_dash == std::string::npos) {
+      // Iterated beyond the keys in this map.
+      break;
+    }
+    (*result)[key.substr(second_dash + 1)] = NullableString16(value, false);
+  }
+}
+
+}  // namespace dom_storage