querystring: improve unescapeBuffer performance

PR-URL: #10837 Reviewed-By: James M Snell <jasnell@gmail.com>
nodejs · Mar 9, 2017 · db45bf8 · db45bf8
1 parent 32cdbca
commit db45bf8
Show file tree

Hide file tree

Showing 3 changed files with 65 additions and 19 deletions.
diff --git a/benchmark/querystring/querystring-unescapebuffer.js b/benchmark/querystring/querystring-unescapebuffer.js
@@ -0,0 +1,23 @@
+'use strict';
+var common = require('../common.js');
+var querystring = require('querystring');
+
+var bench = common.createBenchmark(main, {
+  input: [
+    'there is nothing to unescape here',
+    'there%20are%20several%20spaces%20that%20need%20to%20be%20unescaped',
+    'there%2Qare%0-fake%escaped values in%%%%this%9Hstring',
+    '%20%21%22%23%24%25%26%27%28%29%2A%2B%2C%2D%2E%2F%30%31%32%33%34%35%36%37'
+  ],
+  n: [10e6],
+});
+
+function main(conf) {
+  var input = conf.input;
+  var n = conf.n | 0;
+
+  bench.start();
+  for (var i = 0; i < n; i += 1)
+    querystring.unescapeBuffer(input);
+  bench.end(n);
+}
diff --git a/lib/querystring.js b/lib/querystring.js
@@ -22,15 +22,41 @@ const Buffer = require('buffer').Buffer;
 function ParsedQueryString() {}
 ParsedQueryString.prototype = Object.create(null);
 
-
+const unhexTable = [
+  -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 0 - 15
+  -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 16 - 31
+  -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 32 - 47
+  +0, +1, +2, +3, +4, +5, +6, +7, +8, +9, -1, -1, -1, -1, -1, -1, // 48 - 63
+  -1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 64 - 79
+  -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 80 - 95
+  -1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 96 - 111
+  -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 112 - 127
+  -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 128 ...
+  -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  // ... 255
+];
 // a safe fast alternative to decodeURIComponent
 function unescapeBuffer(s, decodeSpaces) {
   var out = Buffer.allocUnsafe(s.length);
   var state = 0;
-  var n, m, hexchar;
+  var n, m, hexchar, c;
 
-  for (var inIndex = 0, outIndex = 0; inIndex <= s.length; inIndex++) {
-    var c = inIndex < s.length ? s.charCodeAt(inIndex) : NaN;
+  for (var inIndex = 0, outIndex = 0; ; inIndex++) {
+    if (inIndex < s.length) {
+      c = s.charCodeAt(inIndex);
+    } else {
+      if (state > 0) {
+        out[outIndex++] = 37/*%*/;
+        if (state === 2)
+          out[outIndex++] = hexchar;
+      }
+      break;
+    }
     switch (state) {
       case 0: // Any character
         switch (c) {
@@ -51,13 +77,8 @@ function unescapeBuffer(s, decodeSpaces) {
 
       case 1: // First hex digit
         hexchar = c;
-        if (c >= 48/*0*/ && c <= 57/*9*/) {
-          n = c - 48/*0*/;
-        } else if (c >= 65/*A*/ && c <= 70/*F*/) {
-          n = c - 65/*A*/ + 10;
-        } else if (c >= 97/*a*/ && c <= 102/*f*/) {
-          n = c - 97/*a*/ + 10;
-        } else {
+        n = unhexTable[c];
+        if (!(n >= 0)) {
           out[outIndex++] = 37/*%*/;
           out[outIndex++] = c;
           state = 0;
@@ -68,13 +89,8 @@ function unescapeBuffer(s, decodeSpaces) {
 
       case 2: // Second hex digit
         state = 0;
-        if (c >= 48/*0*/ && c <= 57/*9*/) {
-          m = c - 48/*0*/;
-        } else if (c >= 65/*A*/ && c <= 70/*F*/) {
-          m = c - 65/*A*/ + 10;
-        } else if (c >= 97/*a*/ && c <= 102/*f*/) {
-          m = c - 97/*a*/ + 10;
-        } else {
+        m = unhexTable[c];
+        if (!(m >= 0)) {
           out[outIndex++] = 37/*%*/;
           out[outIndex++] = hexchar;
           out[outIndex++] = c;
@@ -87,7 +103,7 @@ function unescapeBuffer(s, decodeSpaces) {
 
   // TODO support returning arbitrary buffers.
 
-  return out.slice(0, outIndex - 1);
+  return out.slice(0, outIndex);
 }
 
 

diff --git a/test/parallel/test-querystring.js b/test/parallel/test-querystring.js
@@ -294,6 +294,13 @@ assert.equal(0xd8, b[17]);
 assert.equal(0xa2, b[18]);
 assert.equal(0xe6, b[19]);
 
+assert.strictEqual(qs.unescapeBuffer('a+b', true).toString(), 'a b');
+assert.strictEqual(qs.unescapeBuffer('a%').toString(), 'a%');
+assert.strictEqual(qs.unescapeBuffer('a%2').toString(), 'a%2');
+assert.strictEqual(qs.unescapeBuffer('a%20').toString(), 'a ');
+assert.strictEqual(qs.unescapeBuffer('a%2g').toString(), 'a%2g');
+assert.strictEqual(qs.unescapeBuffer('a%%').toString(), 'a%%');
+
 
 // Test custom decode
 function demoDecode(str) {