From 2d38c5cab3e4b63654b9947422ef67728a011850 Mon Sep 17 00:00:00 2001
From: David Majda <david@majda.cz>
Date: Sun, 22 Aug 2010 20:01:16 +0200
Subject: [PATCH] Handle non-unique expected values of match failuers
 differently

Before this commit, uniqueness was checked when addding the failure. Now
we make the entiries unique when generating the error report, saving a
little time when the parsing is successful. This does not increase the
benchmark numbers too much though.

Results of benchmark with 100 runs on V8:

  Before:  37.25 kB/s
  After:   37.41 kB/s
  Speedup: 0.241 %

Mozilla/5.0 (X11; U; Linux i686; en-US) AppleWebKit/534.3 (KHTML, like
Gecko) Chrome/6.0.472.63 Safari/534.3
---
 src/emitter.js | 39 ++++++++++++++++-----------------------
 src/parser.js  | 38 ++++++++++++++++----------------------
 src/utils.js   |  4 ----
 3 files changed, 32 insertions(+), 49 deletions(-)

diff --git a/src/emitter.js b/src/emitter.js
index 4ebd8b2..8cc9e1c 100644
--- a/src/emitter.js
+++ b/src/emitter.js
@@ -137,21 +137,6 @@ PEG.compiler.emitter = function(ast) {
         "          + '\"';",
         "      }",
         "      ",
-        /* This needs to be in sync with |contains| in utils.js. */
-        "      function contains(array, value) {",
-        "        /*",
-        "         * Stupid IE does not have Array.prototype.indexOf, otherwise this",
-        "         * function would be a one-liner.",
-        "         */",
-        "        var length = array.length;",
-        "        for (var i = 0; i < length; i++) {",
-        "          if (array[i] === value) {",
-        "            return true;",
-        "          }",
-        "        }",
-        "        return false;",
-        "      }",
-        "      ",
         "      function matchFailed(failure) {",
         "        if (pos < rightmostMatchFailuresPos) {",
         "          return;",
@@ -162,25 +147,33 @@ PEG.compiler.emitter = function(ast) {
         "          rightmostMatchFailuresExpected = [];",
         "        }",
         "        ",
-        "        if (!contains(rightmostMatchFailuresExpected, failure)) {",
-        "          rightmostMatchFailuresExpected.push(failure);",
-        "        }",
+        "        rightmostMatchFailuresExpected.push(failure);",
         "      }",
         "      ",
         "      ${parseFunctionDefinitions}",
         "      ",
         "      function buildErrorMessage() {",
         "        function buildExpected(failuresExpected) {",
-        "          switch (failuresExpected.length) {",
+        "          failuresExpected.sort();",
+        "          ",
+        "          var lastFailure = null;",
+        "          var failuresExpectedUnique = [];",
+        "          for (var i = 0; i < failuresExpected.length; i++) {",
+        "            if (failuresExpected[i] !== lastFailure) {",
+        "              failuresExpectedUnique.push(failuresExpected[i]);",
+        "              lastFailure = failuresExpected[i];",
+        "            }",
+        "          }",
+        "          ",
+        "          switch (failuresExpectedUnique.length) {",
         "            case 0:",
         "              return 'end of input';",
         "            case 1:",
-        "              return failuresExpected[0];",
+        "              return failuresExpectedUnique[0];",
         "            default:",
-        "              failuresExpected.sort();",
-        "              return failuresExpected.slice(0, failuresExpected.length - 1).join(', ')",
+        "              return failuresExpectedUnique.slice(0, failuresExpectedUnique.length - 1).join(', ')",
         "                + ' or '",
-        "                + failuresExpected[failuresExpected.length - 1];",
+        "                + failuresExpectedUnique[failuresExpectedUnique.length - 1];",
         "          }",
         "        }",
         "        ",
diff --git a/src/parser.js b/src/parser.js
index 7caf27d..94002a1 100644
--- a/src/parser.js
+++ b/src/parser.js
@@ -32,20 +32,6 @@ PEG.parser = (function(){
           + '"';
       }
       
-      function contains(array, value) {
-        /*
-         * Stupid IE does not have Array.prototype.indexOf, otherwise this
-         * function would be a one-liner.
-         */
-        var length = array.length;
-        for (var i = 0; i < length; i++) {
-          if (array[i] === value) {
-            return true;
-          }
-        }
-        return false;
-      }
-      
       function matchFailed(failure) {
         if (pos < rightmostMatchFailuresPos) {
           return;
@@ -56,9 +42,7 @@ PEG.parser = (function(){
           rightmostMatchFailuresExpected = [];
         }
         
-        if (!contains(rightmostMatchFailuresExpected, failure)) {
-          rightmostMatchFailuresExpected.push(failure);
-        }
+        rightmostMatchFailuresExpected.push(failure);
       }
       
       function parse_grammar() {
@@ -3443,16 +3427,26 @@ PEG.parser = (function(){
       
       function buildErrorMessage() {
         function buildExpected(failuresExpected) {
-          switch (failuresExpected.length) {
+          failuresExpected.sort();
+          
+          var lastFailure = null;
+          var failuresExpectedUnique = [];
+          for (var i = 0; i < failuresExpected.length; i++) {
+            if (failuresExpected[i] !== lastFailure) {
+              failuresExpectedUnique.push(failuresExpected[i]);
+              lastFailure = failuresExpected[i];
+            }
+          }
+          
+          switch (failuresExpectedUnique.length) {
             case 0:
               return 'end of input';
             case 1:
-              return failuresExpected[0];
+              return failuresExpectedUnique[0];
             default:
-              failuresExpected.sort();
-              return failuresExpected.slice(0, failuresExpected.length - 1).join(', ')
+              return failuresExpectedUnique.slice(0, failuresExpectedUnique.length - 1).join(', ')
                 + ' or '
-                + failuresExpected[failuresExpected.length - 1];
+                + failuresExpectedUnique[failuresExpectedUnique.length - 1];
           }
         }
         
diff --git a/src/utils.js b/src/utils.js
index d6bf8ba..7afdf88 100644
--- a/src/utils.js
+++ b/src/utils.js
@@ -1,7 +1,3 @@
-/*
- * The code needs to be in sync with the code template in the compilation
- * function for "action" nodes.
- */
 function contains(array, value) {
   /*
    * Stupid IE does not have Array.prototype.indexOf, otherwise this function