pegjs/lib/runtime.js

/*
 * PEG.js runtime.
 *
 * Required by all parsers generated by PEG.js.
 */

PEG = {};

(function() {

/* ===== PEG.ArrayUtils ===== */

/* Array manipulation utility functions. */

PEG.ArrayUtils = {
  each: function(array, callback) {
    var length = array.length;
    for (var i = 0; i < length; i++) {
      callback(array[i]);
    }
  },

  map: function(array, callback) {
    var result = [];
    var length = array.length;
    for (var i = 0; i < length; i++) {
      result[i] = callback(array[i]);
    }
    return result;
  }
};

/* ===== PEG.StringUtils ===== */

/* String manipulation utility functions. */

PEG.StringUtils = {
  /*
   * Surrounds the string with quotes and escapes characters inside so that the
   * result is a valid JavaScript string.
   */
  quote: function(s) {
    /*
     * 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.
     */
    return '"' + s
      .replace(/\\/g, '\\\\')        // backslash
      .replace(/"/g, '\\"')          // closing quote character
      .replace(/\r/g, '\\r')         // carriage return
      .replace(/\u2028/g, '\\u2028') // line separator
      .replace(/\u2029/g, '\\u2029') // paragraph separator
      .replace(/\n/g, '\\n')         // line feed
      + '"';
  }

};

/* ===== PEG.RegExpUtils ===== */

/* RegExp manipulation utility functions. */

PEG.RegExpUtils = {
  /*
   * Escapes characters inside the string so that it can be used as a list of
   * characters in a character class of a regular expresion.
   */
  quoteForClass: function(s) {
    /* Based on ECMA-262, 5th ed., 7.8.5 & 15.10.1. */
    return s
      .replace(/\\/g, '\\\\')        // backslash
      .replace(/\//g, '\\/')         // closing slash
      .replace(/]/g, '\\]')          // closing bracket
      .replace(/-/g, '\\-')          // dash
      .replace(/\r/g, '\\r')         // carriage return
      .replace(/\u2028/g, '\\u2028') // line separator
      .replace(/\u2029/g, '\\u2029') // paragraph separator
      .replace(/\n/g, '\\n')         // line feed
  }
};

/* ===== PEG.Parser ===== */

/* Prototype of all parsers generated by PEG.js. */

PEG.Parser = function(startRule) { this._startRule = startRule; }

PEG.Parser.prototype = {
  _matchFailed: function(failure) {
    if (this._pos > this._rightmostMatchFailuresPos) {
      this._rightmostMatchFailuresPos = this._pos;
      this._rightmostMatchFailures = [];
    }
    this._rightmostMatchFailures.push(failure);
  },

  /*
   * Parses the input with a generated parser. If the parsing is successfull,
   * returns a value explicitly or implicitly specified by the grammar from
   * which the parser was generated (see |PEG.buildParser|). If the parsing is
   * unsuccessful, throws |PEG.Parser.SyntaxError| describing the error.
   */
  parse: function(input) {
    var that = this;

    function initialize() {
      that._input = input;
      that._pos = 0;
      that._rightmostMatchFailuresPos = 0;
      that._rightmostMatchFailures = [];
      that._cache = {};
    }

    function buildErrorMessage() {
      function buildExpectedFromMatchFailures(failures) {
        switch (failures.length) {
          case 0:
            return "end of input";
          case 1:
            return failures[0].toString();
          default:
            return PEG.ArrayUtils.map(
                failures.slice(0, failures.length - 1),
                function(failure) { return failure.toString(); }
              ).join(", ")
              + " or "
              + failures[failures.length - 1].toString();
        }
      }

      var expected = buildExpectedFromMatchFailures(
        that._rightmostMatchFailures
      );
      var pos = Math.max(that._pos, that._rightmostMatchFailuresPos);
      var actual = pos < that._input.length
        ? PEG.StringUtils.quote(that._input.charAt(pos))
        : "end of input";

      return "Expected " + expected + " but " + actual + " found.";
    }

    function computeErrorPosition() {
      /*
       * The first idea was to use |String.split| to break the input up to the
       * error position along newlines and derive the line and column from
       * there. However IE's |split| implementation is so broken that it was
       * enough to prevent it.
       */

      var input = that._input;
      var pos = that._rightmostMatchFailuresPos;
      var line = 1;
      var column = 1;
      var seenCR = false;

      for (var i = 0; i < pos; i++) {
        var ch = input.charAt(i);
        if (ch === "\n") {
          if (!seenCR) { line++; }
          column = 1;
          seenCR = false;
        } else if (ch === "\r" | ch === "\u2028" || ch === "\u2029") {
          line++;
          column = 1;
          seenCR = true;
        } else {
          column++;
          seenCR = false;
        }
      }

      return { line: line, column: column };
    }

    initialize();

    var initialContext = {
      reportMatchFailures: true
    };

    var result = this["_parse_" + this._startRule](initialContext);

    /*
     * The parser is now in one of the following three states:
     *
     * 1. The parser successfully parsed the whole input.
     *
     *    - |result !== null|
     *    - |that._pos === input.length|
     *    - |that._rightmostMatchFailures.length| may or may not contain
     *      something
     *
     * 2. The parser successfully parsed only a part of the input.
     *
     *    - |result !== null|
     *    - |that._pos < input.length|
     *    - |that._rightmostMatchFailures.length| may or may not contain
     *      something
     *
     * 3. The parser did not successfully parse any part of the input.
     *
     *   - |result === null|
     *   - |that._pos === 0|
     *   - |that._rightmostMatchFailures.length| contains at least one failure
     *
     * All code following this comment (including called functions) must
     * handle these states.
     */
    if (result === null || this._pos !== input.length) {
      var errorPosition = computeErrorPosition();
      throw new PEG.Parser.SyntaxError(
        buildErrorMessage(),
        errorPosition.line,
        errorPosition.column
      );
    }

    return result;
  },

  /* Returns the parser source code. */
  toSource: function() { return this._source; }
};

/* ===== PEG.Parser.LiteralMatchFailure ===== */

/* Stores information about a literal match failure. */

PEG.Parser.LiteralMatchFailure = function(value) { this._value = value; };

PEG.Parser.LiteralMatchFailure.prototype = {
  toString: function() { return PEG.StringUtils.quote(this._value); }
};

/* ===== PEG.Parser.ClassMatchFailure ===== */

/* Stores information about a class match failure. */

PEG.Parser.ClassMatchFailure = function(characters) {
  this._characters = characters;
};

PEG.Parser.ClassMatchFailure.prototype = {
  toString: function() { return "[" + this._characters + "]"; }
};

/* ===== PEG.Parser.AnyMatchFailure ===== */

/* Stores information about a failure to match a "." expression. */

PEG.Parser.AnyMatchFailure = function() {}

PEG.Parser.AnyMatchFailure.prototype = {
  toString: function() { return "any character"; }
};

/* ===== PEG.Parser.NamedRuleMatchFailure ===== */

/* Stores information about a failure to match a named rule. */

PEG.Parser.NamedRuleMatchFailure = function(displayName) {
  this._displayName = displayName;
}

PEG.Parser.NamedRuleMatchFailure.prototype = {
  toString: function() { return this._displayName; }
};

/* ===== PEG.Parser.SyntaxError ===== */

/* Thrown when a parser encounters a syntax error. */

PEG.Parser.SyntaxError = function(message, line, column) {
  this.name = "PEG.Parser.SyntaxError";
  this.message = message;
  this.line = line;
  this.column = column;
};

PEG.Parser.SyntaxError.prototype = Error.prototype;

})();