src: replace naive search in Buffer::IndexOf

Adds the string search implementation from v8
which uses naive search if pattern length < 8
or to a specific badness then uses Boyer-Moore-Horspool

Added benchmark shows the expected improvements
Added option to use ucs2 encoding with Buffer::IndexOf

Reviewed-By: James M Snell <jasnell@gmail.com>
Reviewed-By: Trevor Norris <trev.norris@gmail.com>
PR-URL: https://github.com/nodejs/node/pull/2539

1 files changed, 38 insertions, 0 deletions

diff --git a/benchmark/buffers/buffer-indexof.js b/benchmark/buffers/buffer-indexof.js
new file mode 100644
index 0000000000..c575f54b6a
--- /dev/null
+++ b/benchmark/buffers/buffer-indexof.js
@@ -0,0 +1,38 @@
+var common = require('../common.js');
+var fs = require('fs');
+
+var bench = common.createBenchmark(main, {
+  search: ['@', 'SQ', '10x', '--l', 'Alice', 'Gryphon', 'Panther',
+           'Ou est ma chatte?', 'found it very', 'among mad people',
+           'neighbouring pool', 'Soo--oop', 'aaaaaaaaaaaaaaaaa',
+           'venture to go near the house till she had brought herself down to',
+           '</i> to the Caterpillar'],
+  encoding: ['undefined', 'utf8', 'ucs2', 'binary'],
+  type: ['buffer', 'string'],
+  iter: [1]
+});
+
+function main(conf) {
+  var iter = (conf.iter) * 100000;
+  var aliceBuffer = fs.readFileSync(__dirname + '/../fixtures/alice.html');
+  var search = conf.search;
+  var encoding = conf.encoding;
+
+  if (encoding === 'undefined') {
+    encoding = undefined;
+  }
+
+  if (encoding === 'ucs2') {
+    aliceBuffer = new Buffer(aliceBuffer.toString(), encoding);
+  }
+
+  if (conf.type === 'buffer') {
+    search = new Buffer(new Buffer(search).toString(), encoding);
+  }
+
+  bench.start();
+  for (var i = 0; i < iter; i++) {
+    aliceBuffer.indexOf(search, 0, encoding);
+  }
+  bench.end(iter);
+}