Revert "Remove info about found string from syntax errors"

This reverts commit 25ab98027d.

Part of work on #428.

README.md

@@ -155,8 +155,8 @@ Using the Parser
 Using the generated parser is simple — just call its `parse` method and pass an
 input string as a parameter. The method will return a parse result (the exact
 value depends on the grammar used to generate the parser) or throw an exception
-if the input is invalid. The exception will contain `location`, `expected` and
+if the input is invalid. The exception will contain `location`, `expected`,
-`message` properties with more details about the error.
+`found`,  and `message` properties with more details about the error.
 
 ```javascript
 parser.parse("abba"); // returns ["a", "b", "b", "a"]

lib/compiler/passes/generate-js.js

@@ -768,9 +768,10 @@ function generateJS(ast, options) {
       '  child.prototype = new ctor();',
       '}',
       '',
-      'function peg$SyntaxError(message, expected, location) {',
+      'function peg$SyntaxError(message, expected, found, location) {',
       '  this.message  = message;',
       '  this.expected = expected;',
+      '  this.found    = found;',
       '  this.location = location;',
       '  this.name     = "SyntaxError";',
       '',
@@ -965,6 +966,7 @@ function generateJS(ast, options) {
       '    throw peg$buildException(',
       '      null,',
       '      [{ type: "other", description: description }],',
+      '      input.substring(peg$savedPos, peg$currPos),',
       '      location',
       '    );',
       '  }',
@@ -972,7 +974,12 @@ function generateJS(ast, options) {
       '  function error(message, location) {',
       '    location = location !== void 0 ? location : peg$computeLocation(peg$savedPos, peg$currPos)',
       '',
-      '    throw peg$buildException(message, null, location);',
+      '    throw peg$buildException(',
+      '      message,',
+      '      null,',
+      '      input.substring(peg$savedPos, peg$currPos),',
+      '      location',
+      '    );',
       '  }',
       '',
       '  function peg$computePosDetails(pos) {',
@@ -1037,7 +1044,7 @@ function generateJS(ast, options) {
       '    peg$maxFailExpected.push(expected);',
       '  }',
       '',
-      '  function peg$buildException(message, expected, location) {',
+      '  function peg$buildException(message, expected, found, location) {',
       '    function cleanupExpected(expected) {',
       '      var i, j;',
       '',
@@ -1067,9 +1074,36 @@ function generateJS(ast, options) {
       '      }',
       '    }',
       '',
-      '    function buildMessage(expected) {',
+      '    function buildMessage(expected, found) {',
+      '      function stringEscape(s) {',
+      '        function hex(ch) { return ch.charCodeAt(0).toString(16).toUpperCase(); }',
+      '',
+      /*
+       * ECMA-262, 5th ed., 7.8.4: All characters may appear literally in a
+       * string literal except for the closing quote character, backslash,
+       * carriage return, line separator, paragraph separator, and line feed.
+       * Any character may appear in the form of an escape sequence.
+       *
+       * For portability, we also escape all control and non-ASCII characters.
+       * Note that "\0" and "\v" escape sequences are not used because JSHint
+       * does not like the first and IE the second.
+       */
+      '        return s',
+      '          .replace(/\\\\/g,   \'\\\\\\\\\')',   // backslash
+      '          .replace(/"/g,    \'\\\\"\')',        // closing double quote
+      '          .replace(/\\x08/g, \'\\\\b\')',       // backspace
+      '          .replace(/\\t/g,   \'\\\\t\')',       // horizontal tab
+      '          .replace(/\\n/g,   \'\\\\n\')',       // line feed
+      '          .replace(/\\f/g,   \'\\\\f\')',       // form feed
+      '          .replace(/\\r/g,   \'\\\\r\')',       // carriage return
+      '          .replace(/[\\x00-\\x07\\x0B\\x0E\\x0F]/g, function(ch) { return \'\\\\x0\' + hex(ch); })',
+      '          .replace(/[\\x10-\\x1F\\x80-\\xFF]/g,    function(ch) { return \'\\\\x\'  + hex(ch); })',
+      '          .replace(/[\\u0100-\\u0FFF]/g,         function(ch) { return \'\\\\u0\' + hex(ch); })',
+      '          .replace(/[\\u1000-\\uFFFF]/g,         function(ch) { return \'\\\\u\'  + hex(ch); });',
+      '      }',
+      '',
       '      var expectedDescs = new Array(expected.length),',
-      '          expectedDesc, i;',
+      '          expectedDesc, foundDesc, i;',
       '',
       '      for (i = 0; i < expected.length; i++) {',
       '        expectedDescs[i] = expected[i].description;',
@@ -1081,7 +1115,9 @@ function generateJS(ast, options) {
       '            + expectedDescs[expected.length - 1]',
       '        : expectedDescs[0];',
       '',
-      '      return "Expected " + expectedDesc + ".";',
+      '      foundDesc = found ? "\\"" + stringEscape(found) + "\\"" : "end of input";',
+      '',
+      '      return "Expected " + expectedDesc + " but " + foundDesc + " found.";',
       '    }',
       '',
       '    if (expected !== null) {',
@@ -1089,8 +1125,9 @@ function generateJS(ast, options) {
       '    }',
       '',
       '    return new peg$SyntaxError(',
-      '      message !== null ? message : buildMessage(expected),',
+      '      message !== null ? message : buildMessage(expected, found),',
       '      expected,',
+      '      found,',
       '      location',
       '    );',
       '  }',
@@ -1130,7 +1167,10 @@ function generateJS(ast, options) {
       '    throw peg$buildException(',
       '      null,',
       '      peg$maxFailExpected,',
-      '      peg$computeLocation(peg$maxFailPos, peg$maxFailPos)',
+      '      peg$maxFailPos < input.length ? input.charAt(peg$maxFailPos) : null,',
+      '      peg$maxFailPos < input.length',
+      '        ? peg$computeLocation(peg$maxFailPos, peg$maxFailPos + 1)',
+      '        : peg$computeLocation(peg$maxFailPos, peg$maxFailPos)',
       '    );',
       '  }',
       '}'

lib/parser.js

@@ -21,9 +21,10 @@
     child.prototype = new ctor();
   }
 
-  function peg$SyntaxError(message, expected, location) {
+  function peg$SyntaxError(message, expected, found, location) {
     this.message  = message;
     this.expected = expected;
+    this.found    = found;
     this.location = location;
     this.name     = "SyntaxError";
 
@@ -427,6 +428,7 @@
       throw peg$buildException(
         null,
         [{ type: "other", description: description }],
+        input.substring(peg$savedPos, peg$currPos),
         location
       );
     }
@@ -434,7 +436,12 @@
     function error(message, location) {
       location = location !== void 0 ? location : peg$computeLocation(peg$savedPos, peg$currPos)
 
-      throw peg$buildException(message, null, location);
+      throw peg$buildException(
+        message,
+        null,
+        input.substring(peg$savedPos, peg$currPos),
+        location
+      );
     }
 
     function peg$computePosDetails(pos) {
@@ -499,7 +506,7 @@
       peg$maxFailExpected.push(expected);
     }
 
-    function peg$buildException(message, expected, location) {
+    function peg$buildException(message, expected, found, location) {
       function cleanupExpected(expected) {
         var i, j;
 
@@ -524,9 +531,26 @@
         }
       }
 
-      function buildMessage(expected) {
+      function buildMessage(expected, found) {
+        function stringEscape(s) {
+          function hex(ch) { return ch.charCodeAt(0).toString(16).toUpperCase(); }
+
+          return s
+            .replace(/\\/g,   '\\\\')
+            .replace(/"/g,    '\\"')
+            .replace(/\x08/g, '\\b')
+            .replace(/\t/g,   '\\t')
+            .replace(/\n/g,   '\\n')
+            .replace(/\f/g,   '\\f')
+            .replace(/\r/g,   '\\r')
+            .replace(/[\x00-\x07\x0B\x0E\x0F]/g, function(ch) { return '\\x0' + hex(ch); })
+            .replace(/[\x10-\x1F\x80-\xFF]/g,    function(ch) { return '\\x'  + hex(ch); })
+            .replace(/[\u0100-\u0FFF]/g,         function(ch) { return '\\u0' + hex(ch); })
+            .replace(/[\u1000-\uFFFF]/g,         function(ch) { return '\\u'  + hex(ch); });
+        }
+
         var expectedDescs = new Array(expected.length),
-            expectedDesc, i;
+            expectedDesc, foundDesc, i;
 
         for (i = 0; i < expected.length; i++) {
           expectedDescs[i] = expected[i].description;
@@ -538,7 +562,9 @@
               + expectedDescs[expected.length - 1]
           : expectedDescs[0];
 
-        return "Expected " + expectedDesc + ".";
+        foundDesc = found ? "\"" + stringEscape(found) + "\"" : "end of input";
+
+        return "Expected " + expectedDesc + " but " + foundDesc + " found.";
       }
 
       if (expected !== null) {
@@ -546,8 +572,9 @@
       }
 
       return new peg$SyntaxError(
-        message !== null ? message : buildMessage(expected),
+        message !== null ? message : buildMessage(expected, found),
         expected,
+        found,
         location
       );
     }
@@ -4948,7 +4975,10 @@
       throw peg$buildException(
         null,
         peg$maxFailExpected,
-        peg$computeLocation(peg$maxFailPos, peg$maxFailPos)
+        peg$maxFailPos < input.length ? input.charAt(peg$maxFailPos) : null,
+        peg$maxFailPos < input.length
+          ? peg$computeLocation(peg$maxFailPos, peg$maxFailPos + 1)
+          : peg$computeLocation(peg$maxFailPos, peg$maxFailPos)
       );
     }
   }

spec/behavior/generated-parser-behavior.spec.js

@@ -1219,8 +1219,9 @@ describe("generated parser behavior", function() {
                   );
 
               expect(parser).toFailToParse("a", {
-                message:  'Expected a.',
+                message:  'Expected a but "a" found.',
                 expected: [{ type: "other", description: "a" }],
+                found:    "a",
                 location: {
                   start: { offset: 0, line: 1, column: 1 },
                   end:   { offset: 1, line: 1, column: 2 }
@@ -1239,8 +1240,9 @@ describe("generated parser behavior", function() {
                   ].join("\n"), options);
 
               expect(parser).toFailToParse("a", {
-                message:  'Expected a.',
+                message:  'Expected a but "a" found.',
                 expected: [{ type: "other", description: "a" }],
+                found:    "a",
                 location: {
                   start: { offset: 1, line: 1, column: 2 },
                   end:   { offset: 2, line: 1, column: 3 }
@@ -1258,6 +1260,7 @@ describe("generated parser behavior", function() {
 
               expect(parser).toFailToParse("a", {
                 message:  "a",
+                found:    "a",
                 expected: null,
                 location: {
                   start: { offset: 0, line: 1, column: 1 },
@@ -1279,6 +1282,7 @@ describe("generated parser behavior", function() {
               expect(parser).toFailToParse("a", {
                 message:  "a",
                 expected: null,
+                found:    "a",
                 location: {
                   start: { offset: 1, line: 1, column: 2 },
                   end:   { offset: 2, line: 1, column: 3 }
@@ -1395,12 +1399,26 @@ describe("generated parser behavior", function() {
         });
       });
 
+      describe("found string reporting", function() {
+        it("reports found string correctly at the end of input", function() {
+          var parser = peg.generate('start = "a"', options);
+
+          expect(parser).toFailToParse("", { found: null });
+        });
+
+        it("reports found string correctly in the middle of input", function() {
+          var parser = peg.generate('start = "a"', options);
+
+          expect(parser).toFailToParse("b", { found: "b" });
+        });
+      });
+
       describe("message building", function() {
         it("builds message correctly with no alternative", function() {
           var parser = peg.generate('start = "a"', options);
 
           expect(parser).toFailToParse("ab", {
-            message: 'Expected end of input.'
+            message: 'Expected end of input but "b" found.'
           });
         });
 
@@ -1408,7 +1426,7 @@ describe("generated parser behavior", function() {
           var parser = peg.generate('start = "a"', options);
 
           expect(parser).toFailToParse("b", {
-            message: 'Expected "a".'
+            message: 'Expected "a" but "b" found.'
           });
         });
 
@@ -1416,16 +1434,32 @@ describe("generated parser behavior", function() {
           var parser = peg.generate('start = "a" / "b" / "c"', options);
 
           expect(parser).toFailToParse("d", {
-            message: 'Expected "a", "b" or "c".'
+            message: 'Expected "a", "b" or "c" but "d" found.'
+          });
+        });
+
+        it("builds message correctly at the end of input", function() {
+          var parser = peg.generate('start = "a"', options);
+
+          expect(parser).toFailToParse("", {
+            message: 'Expected "a" but end of input found.'
+          });
+        });
+
+        it("builds message correctly in the middle of input", function() {
+          var parser = peg.generate('start = "a"', options);
+
+          expect(parser).toFailToParse("b", {
+            message: 'Expected "a" but "b" found.'
           });
         });
       });
 
       describe("position reporting", function() {
-        it("reports position correctly with no trailing input", function() {
+        it("reports position correctly at the end of input", function() {
           var parser = peg.generate('start = "a"', options);
 
-          expect(parser).toFailToParse("b", {
+          expect(parser).toFailToParse("", {
             location: {
               start: { offset: 0, line: 1, column: 1 },
               end:   { offset: 0, line: 1, column: 1 }
@@ -1433,13 +1467,24 @@ describe("generated parser behavior", function() {
           });
         });
 
+        it("reports position correctly in the middle of input", function() {
+          var parser = peg.generate('start = "a"', options);
+
+          expect(parser).toFailToParse("b", {
+            location: {
+              start: { offset: 0, line: 1, column: 1 },
+              end:   { offset: 1, line: 1, column: 2 }
+            }
+          });
+        });
+
         it("reports position correctly with trailing input", function() {
           var parser = peg.generate('start = "a"', options);
 
           expect(parser).toFailToParse("aa", {
             location: {
               start: { offset: 1, line: 1, column: 2 },
-              end:   { offset: 1, line: 1, column: 2 }
+              end:   { offset: 2, line: 1, column: 3 }
             }
           });
         });
@@ -1455,7 +1500,7 @@ describe("generated parser behavior", function() {
           expect(parser).toFailToParse("1\n2\n\n3\n\n\n4 5 x", {
             location: {
               start: { offset: 13, line: 7, column: 5 },
-              end:   { offset: 13, line: 7, column: 5 }
+              end:   { offset: 14, line: 7, column: 6 }
             }
           });
 
@@ -1463,13 +1508,13 @@ describe("generated parser behavior", function() {
           expect(parser).toFailToParse("1\nx", {     // Old Mac
             location: {
               start: { offset: 2, line: 2, column: 1 },
-              end:   { offset: 2, line: 2, column: 1 }
+              end:   { offset: 3, line: 2, column: 2 }
             }
           });
           expect(parser).toFailToParse("1\r\nx", {   // Windows
             location: {
               start: { offset: 3, line: 2, column: 1 },
-              end:   { offset: 3, line: 2, column: 1 }
+              end:   { offset: 4, line: 2, column: 2 }
             }
           });
         });