buffer: optimize hex_decode

PR-URL: https://github.com/nodejs/node/pull/7602
Reviewed-By: Anna Henningsen <anna@addaleax.net>

3 files changed, 93 insertions, 13 deletions

diff --git a/benchmark/buffers/buffer-hex.js b/benchmark/buffers/buffer-hex.js
new file mode 100644
index 0000000000..d05bb832b3
--- /dev/null
+++ b/benchmark/buffers/buffer-hex.js
@@ -0,0 +1,26 @@
+'use strict';
+
+const common = require('../common.js');
+
+const bench = common.createBenchmark(main, {
+  len: [0, 1, 64, 1024],
+  n: [1e7]
+});
+
+function main(conf) {
+  const len = conf.len | 0;
+  const n = conf.n | 0;
+  const buf = Buffer.alloc(len);
+
+  for (let i = 0; i < buf.length; i++)
+    buf[i] = i & 0xff;
+
+  const hex = buf.toString('hex');
+
+  bench.start();
+
+  for (let i = 0; i < n; i += 1)
+    Buffer.from(hex, 'hex');
+
+  bench.end(n);
+}
diff --git a/src/string_bytes.cc b/src/string_bytes.cc
index 6f15ad4884..668a3b1efe 100644
--- a/src/string_bytes.cc
+++ b/src/string_bytes.cc
@@ -143,16 +143,27 @@ const int8_t unbase64_table[256] =
   };
 
 
-template <typename TypeName>
-unsigned hex2bin(TypeName c) {
-  if (c >= '0' && c <= '9')
-    return c - '0';
-  if (c >= 'A' && c <= 'F')
-    return 10 + (c - 'A');
-  if (c >= 'a' && c <= 'f')
-    return 10 + (c - 'a');
-  return static_cast<unsigned>(-1);
-}
+static const int8_t unhex_table[256] =
+  { -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+     0,  1,  2,  3,  4,  5,  6,  7,  8,  9, -1, -1, -1, -1, -1, -1,
+    -1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1
+  };
+
+#define unhex(x)                                                              \
+  static_cast<unsigned>(unhex_table[static_cast<uint8_t>(x)])
 
 
 template <typename TypeName>
@@ -162,11 +173,11 @@ size_t hex_decode(char* buf,
                   const size_t srcLen) {
   size_t i;
   for (i = 0; i < len && i * 2 + 1 < srcLen; ++i) {
-    unsigned a = hex2bin(src[i * 2 + 0]);
-    unsigned b = hex2bin(src[i * 2 + 1]);
+    unsigned a = unhex(src[i * 2 + 0]);
+    unsigned b = unhex(src[i * 2 + 1]);
     if (!~a || !~b)
       return i;
-    buf[i] = a * 16 + b;
+    buf[i] = (a << 4) | b;
   }
 
   return i;
diff --git a/test/parallel/test-buffer-badhex.js b/test/parallel/test-buffer-badhex.js
new file mode 100644
index 0000000000..3611ba3a09
--- /dev/null
+++ b/test/parallel/test-buffer-badhex.js
@@ -0,0 +1,43 @@
+'use strict';
+require('../common');
+const assert = require('assert');
+const Buffer = require('buffer').Buffer;
+
+// Test hex strings and bad hex strings
+{
+  const buf1 = Buffer.alloc(4);
+  assert.strictEqual(buf1.length, 4);
+  assert.deepStrictEqual(buf1, new Buffer([0, 0, 0, 0]));
+  assert.strictEqual(buf1.write('abcdxx', 0, 'hex'), 2);
+  assert.deepStrictEqual(buf1, new Buffer([0xab, 0xcd, 0x00, 0x00]));
+  assert.strictEqual(buf1.toString('hex'), 'abcd0000');
+  assert.strictEqual(buf1.write('abcdef01', 0, 'hex'), 4);
+  assert.deepStrictEqual(buf1, new Buffer([0xab, 0xcd, 0xef, 0x01]));
+  assert.strictEqual(buf1.toString('hex'), 'abcdef01');
+
+  const buf2 = Buffer.from(buf1.toString('hex'), 'hex');
+  assert.strictEqual(buf1.toString('hex'), buf2.toString('hex'));
+
+  const buf3 = Buffer.alloc(5);
+  assert.strictEqual(buf3.write('abcdxx', 1, 'hex'), 2);
+  assert.strictEqual(buf3.toString('hex'), '00abcd0000');
+
+  const buf4 = Buffer.alloc(4);
+  assert.deepStrictEqual(buf4, new Buffer([0, 0, 0, 0]));
+  assert.strictEqual(buf4.write('xxabcd', 0, 'hex'), 0);
+  assert.deepStrictEqual(buf4, new Buffer([0, 0, 0, 0]));
+  assert.strictEqual(buf4.write('xxab', 1, 'hex'), 0);
+  assert.deepStrictEqual(buf4, new Buffer([0, 0, 0, 0]));
+  assert.strictEqual(buf4.write('cdxxab', 0, 'hex'), 1);
+  assert.deepStrictEqual(buf4, new Buffer([0xcd, 0, 0, 0]));
+
+  const buf5 = Buffer.alloc(256);
+  for (let i = 0; i < 256; i++)
+    buf5[i] = i;
+
+  const hex = buf5.toString('hex');
+  assert.deepStrictEqual(Buffer.from(hex, 'hex'), buf5);
+
+  const badHex = hex.slice(0, 256) + 'xx' + hex.slice(256, 510);
+  assert.deepStrictEqual(Buffer.from(badHex, 'hex'), buf5.slice(0, 128));
+}