natural 0.2.1 → 0.4.0

package/lib/natural/brill_pos_tagger/lib/TF_Parser.js

@@ -0,0 +1,717 @@
+module.exports = (function() {
+  /*
+   * Generated by PEG.js 0.8.0.
+   *
+   * http://pegjs.majda.cz/
+   */
+
+  function peg$subclass(child, parent) {
+    function ctor() { this.constructor = child; }
+    ctor.prototype = parent.prototype;
+    child.prototype = new ctor();
+  }
+
+  function SyntaxError(message, expected, found, offset, line, column) {
+    this.message  = message;
+    this.expected = expected;
+    this.found    = found;
+    this.offset   = offset;
+    this.line     = line;
+    this.column   = column;
+
+    this.name     = "SyntaxError";
+  }
+
+  peg$subclass(SyntaxError, Error);
+
+  function parse(input) {
+    var options = arguments.length > 1 ? arguments[1] : {},
+
+        peg$FAILED = {},
+
+        peg$startRuleFunctions = { transformation_rules: peg$parsetransformation_rules },
+        peg$startRuleFunction  = peg$parsetransformation_rules,
+
+        peg$c0 = [],
+        peg$c1 = peg$FAILED,
+        peg$c2 = function(rules) {
+          var result = [];
+
+          for (var i = 0; i < rules.length; i++) {
+            result.push(rules[i][1]);
+          }
+          return(result);
+        },
+        peg$c3 = null,
+        peg$c4 = function(c1, c2, pred, par1, par2) {
+          // Construct rule
+          var result = new TransformationRule(c1, c2, pred, par1, par2);
+          return(result);
+        },
+        peg$c5 = /^[a-zA-Z_0-9_\-.,()]/,
+        peg$c6 = { type: "class", value: "[a-zA-Z_0-9_\\-.,()]", description: "[a-zA-Z_0-9_\\-.,()]" },
+        peg$c7 = function(characters) {
+           var s = "";
+           for (var i = 0; i < characters.length; i++) {
+             s += characters[i];
+           }
+           return(s);
+          },
+        peg$c8 = "*",
+        peg$c9 = { type: "literal", value: "*", description: "\"*\"" },
+        peg$c10 = function(wc) {
+           return(wc)
+          },
+        peg$c11 = "\r\n",
+        peg$c12 = { type: "literal", value: "\r\n", description: "\"\\r\\n\"" },
+        peg$c13 = "\n",
+        peg$c14 = { type: "literal", value: "\n", description: "\"\\n\"" },
+        peg$c15 = "\r",
+        peg$c16 = { type: "literal", value: "\r", description: "\"\\r\"" },
+        peg$c17 = "//",
+        peg$c18 = { type: "literal", value: "//", description: "\"//\"" },
+        peg$c19 = void 0,
+        peg$c20 = { type: "any", description: "any character" },
+        peg$c21 = " ",
+        peg$c22 = { type: "literal", value: " ", description: "\" \"" },
+        peg$c23 = "\t",
+        peg$c24 = { type: "literal", value: "\t", description: "\"\\t\"" },
+
+        peg$currPos          = 0,
+        peg$reportedPos      = 0,
+        peg$cachedPos        = 0,
+        peg$cachedPosDetails = { line: 1, column: 1, seenCR: false },
+        peg$maxFailPos       = 0,
+        peg$maxFailExpected  = [],
+        peg$silentFails      = 0,
+
+        peg$result;
+
+    if ("startRule" in options) {
+      if (!(options.startRule in peg$startRuleFunctions)) {
+        throw new Error("Can't start parsing from rule \"" + options.startRule + "\".");
+      }
+
+      peg$startRuleFunction = peg$startRuleFunctions[options.startRule];
+    }
+
+    function text() {
+      return input.substring(peg$reportedPos, peg$currPos);
+    }
+
+    function offset() {
+      return peg$reportedPos;
+    }
+
+    function line() {
+      return peg$computePosDetails(peg$reportedPos).line;
+    }
+
+    function column() {
+      return peg$computePosDetails(peg$reportedPos).column;
+    }
+
+    function expected(description) {
+      throw peg$buildException(
+        null,
+        [{ type: "other", description: description }],
+        peg$reportedPos
+      );
+    }
+
+    function error(message) {
+      throw peg$buildException(message, null, peg$reportedPos);
+    }
+
+    function peg$computePosDetails(pos) {
+      function advance(details, startPos, endPos) {
+        var p, ch;
+
+        for (p = startPos; p < endPos; p++) {
+          ch = input.charAt(p);
+          if (ch === "\n") {
+            if (!details.seenCR) { details.line++; }
+            details.column = 1;
+            details.seenCR = false;
+          } else if (ch === "\r" || ch === "\u2028" || ch === "\u2029") {
+            details.line++;
+            details.column = 1;
+            details.seenCR = true;
+          } else {
+            details.column++;
+            details.seenCR = false;
+          }
+        }
+      }
+
+      if (peg$cachedPos !== pos) {
+        if (peg$cachedPos > pos) {
+          peg$cachedPos = 0;
+          peg$cachedPosDetails = { line: 1, column: 1, seenCR: false };
+        }
+        advance(peg$cachedPosDetails, peg$cachedPos, pos);
+        peg$cachedPos = pos;
+      }
+
+      return peg$cachedPosDetails;
+    }
+
+    function peg$fail(expected) {
+      if (peg$currPos < peg$maxFailPos) { return; }
+
+      if (peg$currPos > peg$maxFailPos) {
+        peg$maxFailPos = peg$currPos;
+        peg$maxFailExpected = [];
+      }
+
+      peg$maxFailExpected.push(expected);
+    }
+
+    function peg$buildException(message, expected, pos) {
+      function cleanupExpected(expected) {
+        var i = 1;
+
+        expected.sort(function(a, b) {
+          if (a.description < b.description) {
+            return -1;
+          } else if (a.description > b.description) {
+            return 1;
+          } else {
+            return 0;
+          }
+        });
+
+        while (i < expected.length) {
+          if (expected[i - 1] === expected[i]) {
+            expected.splice(i, 1);
+          } else {
+            i++;
+          }
+        }
+      }
+
+      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(/[\u0180-\u0FFF]/g,         function(ch) { return '\\u0' + hex(ch); })
+            .replace(/[\u1080-\uFFFF]/g,         function(ch) { return '\\u'  + hex(ch); });
+        }
+
+        var expectedDescs = new Array(expected.length),
+            expectedDesc, foundDesc, i;
+
+        for (i = 0; i < expected.length; i++) {
+          expectedDescs[i] = expected[i].description;
+        }
+
+        expectedDesc = expected.length > 1
+          ? expectedDescs.slice(0, -1).join(", ")
+              + " or "
+              + expectedDescs[expected.length - 1]
+          : expectedDescs[0];
+
+        foundDesc = found ? "\"" + stringEscape(found) + "\"" : "end of input";
+
+        return "Expected " + expectedDesc + " but " + foundDesc + " found.";
+      }
+
+      var posDetails = peg$computePosDetails(pos),
+          found      = pos < input.length ? input.charAt(pos) : null;
+
+      if (expected !== null) {
+        cleanupExpected(expected);
+      }
+
+      return new SyntaxError(
+        message !== null ? message : buildMessage(expected, found),
+        expected,
+        found,
+        pos,
+        posDetails.line,
+        posDetails.column
+      );
+    }
+
+    function peg$parsetransformation_rules() {
+      var s0, s1, s2, s3, s4, s5;
+
+      s0 = peg$currPos;
+      s1 = [];
+      s2 = peg$currPos;
+      s3 = peg$parseS();
+      if (s3 !== peg$FAILED) {
+        s4 = peg$parsetransformation_rule();
+        if (s4 !== peg$FAILED) {
+          s5 = peg$parseS();
+          if (s5 !== peg$FAILED) {
+            s3 = [s3, s4, s5];
+            s2 = s3;
+          } else {
+            peg$currPos = s2;
+            s2 = peg$c1;
+          }
+        } else {
+          peg$currPos = s2;
+          s2 = peg$c1;
+        }
+      } else {
+        peg$currPos = s2;
+        s2 = peg$c1;
+      }
+      if (s2 !== peg$FAILED) {
+        while (s2 !== peg$FAILED) {
+          s1.push(s2);
+          s2 = peg$currPos;
+          s3 = peg$parseS();
+          if (s3 !== peg$FAILED) {
+            s4 = peg$parsetransformation_rule();
+            if (s4 !== peg$FAILED) {
+              s5 = peg$parseS();
+              if (s5 !== peg$FAILED) {
+                s3 = [s3, s4, s5];
+                s2 = s3;
+              } else {
+                peg$currPos = s2;
+                s2 = peg$c1;
+              }
+            } else {
+              peg$currPos = s2;
+              s2 = peg$c1;
+            }
+          } else {
+            peg$currPos = s2;
+            s2 = peg$c1;
+          }
+        }
+      } else {
+        s1 = peg$c1;
+      }
+      if (s1 !== peg$FAILED) {
+        peg$reportedPos = s0;
+        s1 = peg$c2(s1);
+      }
+      s0 = s1;
+
+      return s0;
+    }
+
+    function peg$parsetransformation_rule() {
+      var s0, s1, s2, s3, s4, s5;
+
+      s0 = peg$currPos;
+      s1 = peg$parsecategory1();
+      if (s1 !== peg$FAILED) {
+        s2 = peg$parseidentifier();
+        if (s2 !== peg$FAILED) {
+          s3 = peg$parseidentifier();
+          if (s3 !== peg$FAILED) {
+            s4 = peg$parseidentifier();
+            if (s4 !== peg$FAILED) {
+              s5 = peg$parseidentifier();
+              if (s5 === peg$FAILED) {
+                s5 = peg$c3;
+              }
+              if (s5 !== peg$FAILED) {
+                peg$reportedPos = s0;
+                s1 = peg$c4(s1, s2, s3, s4, s5);
+                s0 = s1;
+              } else {
+                peg$currPos = s0;
+                s0 = peg$c1;
+              }
+            } else {
+              peg$currPos = s0;
+              s0 = peg$c1;
+            }
+          } else {
+            peg$currPos = s0;
+            s0 = peg$c1;
+          }
+        } else {
+          peg$currPos = s0;
+          s0 = peg$c1;
+        }
+      } else {
+        peg$currPos = s0;
+        s0 = peg$c1;
+      }
+
+      return s0;
+    }
+
+    function peg$parsecategory1() {
+      var s0;
+
+      s0 = peg$parsewild_card();
+      if (s0 === peg$FAILED) {
+        s0 = peg$parseidentifier();
+      }
+
+      return s0;
+    }
+
+    function peg$parseidentifier() {
+      var s0, s1, s2;
+
+      s0 = peg$currPos;
+      s1 = [];
+      if (peg$c5.test(input.charAt(peg$currPos))) {
+        s2 = input.charAt(peg$currPos);
+        peg$currPos++;
+      } else {
+        s2 = peg$FAILED;
+        if (peg$silentFails === 0) { peg$fail(peg$c6); }
+      }
+      if (s2 !== peg$FAILED) {
+        while (s2 !== peg$FAILED) {
+          s1.push(s2);
+          if (peg$c5.test(input.charAt(peg$currPos))) {
+            s2 = input.charAt(peg$currPos);
+            peg$currPos++;
+          } else {
+            s2 = peg$FAILED;
+            if (peg$silentFails === 0) { peg$fail(peg$c6); }
+          }
+        }
+      } else {
+        s1 = peg$c1;
+      }
+      if (s1 !== peg$FAILED) {
+        s2 = peg$parseS_no_eol();
+        if (s2 !== peg$FAILED) {
+          peg$reportedPos = s0;
+          s1 = peg$c7(s1);
+          s0 = s1;
+        } else {
+          peg$currPos = s0;
+          s0 = peg$c1;
+        }
+      } else {
+        peg$currPos = s0;
+        s0 = peg$c1;
+      }
+
+      return s0;
+    }
+
+    function peg$parsewild_card() {
+      var s0, s1, s2;
+
+      s0 = peg$currPos;
+      if (input.charCodeAt(peg$currPos) === 42) {
+        s1 = peg$c8;
+        peg$currPos++;
+      } else {
+        s1 = peg$FAILED;
+        if (peg$silentFails === 0) { peg$fail(peg$c9); }
+      }
+      if (s1 !== peg$FAILED) {
+        s2 = peg$parseS_no_eol();
+        if (s2 !== peg$FAILED) {
+          peg$reportedPos = s0;
+          s1 = peg$c10(s1);
+          s0 = s1;
+        } else {
+          peg$currPos = s0;
+          s0 = peg$c1;
+        }
+      } else {
+        peg$currPos = s0;
+        s0 = peg$c1;
+      }
+
+      return s0;
+    }
+
+    function peg$parseEOL() {
+      var s0;
+
+      if (input.substr(peg$currPos, 2) === peg$c11) {
+        s0 = peg$c11;
+        peg$currPos += 2;
+      } else {
+        s0 = peg$FAILED;
+        if (peg$silentFails === 0) { peg$fail(peg$c12); }
+      }
+      if (s0 === peg$FAILED) {
+        if (input.charCodeAt(peg$currPos) === 10) {
+          s0 = peg$c13;
+          peg$currPos++;
+        } else {
+          s0 = peg$FAILED;
+          if (peg$silentFails === 0) { peg$fail(peg$c14); }
+        }
+        if (s0 === peg$FAILED) {
+          if (input.charCodeAt(peg$currPos) === 13) {
+            s0 = peg$c15;
+            peg$currPos++;
+          } else {
+            s0 = peg$FAILED;
+            if (peg$silentFails === 0) { peg$fail(peg$c16); }
+          }
+        }
+      }
+
+      return s0;
+    }
+
+    function peg$parseComment() {
+      var s0, s1, s2, s3, s4, s5;
+
+      s0 = peg$currPos;
+      if (input.substr(peg$currPos, 2) === peg$c17) {
+        s1 = peg$c17;
+        peg$currPos += 2;
+      } else {
+        s1 = peg$FAILED;
+        if (peg$silentFails === 0) { peg$fail(peg$c18); }
+      }
+      if (s1 !== peg$FAILED) {
+        s2 = [];
+        s3 = peg$currPos;
+        s4 = peg$currPos;
+        peg$silentFails++;
+        s5 = peg$parseEOL();
+        peg$silentFails--;
+        if (s5 === peg$FAILED) {
+          s4 = peg$c19;
+        } else {
+          peg$currPos = s4;
+          s4 = peg$c1;
+        }
+        if (s4 !== peg$FAILED) {
+          if (input.length > peg$currPos) {
+            s5 = input.charAt(peg$currPos);
+            peg$currPos++;
+          } else {
+            s5 = peg$FAILED;
+            if (peg$silentFails === 0) { peg$fail(peg$c20); }
+          }
+          if (s5 !== peg$FAILED) {
+            s4 = [s4, s5];
+            s3 = s4;
+          } else {
+            peg$currPos = s3;
+            s3 = peg$c1;
+          }
+        } else {
+          peg$currPos = s3;
+          s3 = peg$c1;
+        }
+        while (s3 !== peg$FAILED) {
+          s2.push(s3);
+          s3 = peg$currPos;
+          s4 = peg$currPos;
+          peg$silentFails++;
+          s5 = peg$parseEOL();
+          peg$silentFails--;
+          if (s5 === peg$FAILED) {
+            s4 = peg$c19;
+          } else {
+            peg$currPos = s4;
+            s4 = peg$c1;
+          }
+          if (s4 !== peg$FAILED) {
+            if (input.length > peg$currPos) {
+              s5 = input.charAt(peg$currPos);
+              peg$currPos++;
+            } else {
+              s5 = peg$FAILED;
+              if (peg$silentFails === 0) { peg$fail(peg$c20); }
+            }
+            if (s5 !== peg$FAILED) {
+              s4 = [s4, s5];
+              s3 = s4;
+            } else {
+              peg$currPos = s3;
+              s3 = peg$c1;
+            }
+          } else {
+            peg$currPos = s3;
+            s3 = peg$c1;
+          }
+        }
+        if (s2 !== peg$FAILED) {
+          s3 = peg$parseEOL();
+          if (s3 === peg$FAILED) {
+            s3 = peg$parseEOI();
+          }
+          if (s3 !== peg$FAILED) {
+            s1 = [s1, s2, s3];
+            s0 = s1;
+          } else {
+            peg$currPos = s0;
+            s0 = peg$c1;
+          }
+        } else {
+          peg$currPos = s0;
+          s0 = peg$c1;
+        }
+      } else {
+        peg$currPos = s0;
+        s0 = peg$c1;
+      }
+
+      return s0;
+    }
+
+    function peg$parseS() {
+      var s0, s1;
+
+      s0 = [];
+      if (input.charCodeAt(peg$currPos) === 32) {
+        s1 = peg$c21;
+        peg$currPos++;
+      } else {
+        s1 = peg$FAILED;
+        if (peg$silentFails === 0) { peg$fail(peg$c22); }
+      }
+      if (s1 === peg$FAILED) {
+        if (input.charCodeAt(peg$currPos) === 9) {
+          s1 = peg$c23;
+          peg$currPos++;
+        } else {
+          s1 = peg$FAILED;
+          if (peg$silentFails === 0) { peg$fail(peg$c24); }
+        }
+        if (s1 === peg$FAILED) {
+          s1 = peg$parseEOL();
+          if (s1 === peg$FAILED) {
+            s1 = peg$parseComment();
+          }
+        }
+      }
+      while (s1 !== peg$FAILED) {
+        s0.push(s1);
+        if (input.charCodeAt(peg$currPos) === 32) {
+          s1 = peg$c21;
+          peg$currPos++;
+        } else {
+          s1 = peg$FAILED;
+          if (peg$silentFails === 0) { peg$fail(peg$c22); }
+        }
+        if (s1 === peg$FAILED) {
+          if (input.charCodeAt(peg$currPos) === 9) {
+            s1 = peg$c23;
+            peg$currPos++;
+          } else {
+            s1 = peg$FAILED;
+            if (peg$silentFails === 0) { peg$fail(peg$c24); }
+          }
+          if (s1 === peg$FAILED) {
+            s1 = peg$parseEOL();
+            if (s1 === peg$FAILED) {
+              s1 = peg$parseComment();
+            }
+          }
+        }
+      }
+
+      return s0;
+    }
+
+    function peg$parseS_no_eol() {
+      var s0, s1;
+
+      s0 = [];
+      if (input.charCodeAt(peg$currPos) === 32) {
+        s1 = peg$c21;
+        peg$currPos++;
+      } else {
+        s1 = peg$FAILED;
+        if (peg$silentFails === 0) { peg$fail(peg$c22); }
+      }
+      if (s1 === peg$FAILED) {
+        if (input.charCodeAt(peg$currPos) === 9) {
+          s1 = peg$c23;
+          peg$currPos++;
+        } else {
+          s1 = peg$FAILED;
+          if (peg$silentFails === 0) { peg$fail(peg$c24); }
+        }
+        if (s1 === peg$FAILED) {
+          s1 = peg$parseComment();
+        }
+      }
+      while (s1 !== peg$FAILED) {
+        s0.push(s1);
+        if (input.charCodeAt(peg$currPos) === 32) {
+          s1 = peg$c21;
+          peg$currPos++;
+        } else {
+          s1 = peg$FAILED;
+          if (peg$silentFails === 0) { peg$fail(peg$c22); }
+        }
+        if (s1 === peg$FAILED) {
+          if (input.charCodeAt(peg$currPos) === 9) {
+            s1 = peg$c23;
+            peg$currPos++;
+          } else {
+            s1 = peg$FAILED;
+            if (peg$silentFails === 0) { peg$fail(peg$c24); }
+          }
+          if (s1 === peg$FAILED) {
+            s1 = peg$parseComment();
+          }
+        }
+      }
+
+      return s0;
+    }
+
+    function peg$parseEOI() {
+      var s0, s1;
+
+      s0 = peg$currPos;
+      peg$silentFails++;
+      if (input.length > peg$currPos) {
+        s1 = input.charAt(peg$currPos);
+        peg$currPos++;
+      } else {
+        s1 = peg$FAILED;
+        if (peg$silentFails === 0) { peg$fail(peg$c20); }
+      }
+      peg$silentFails--;
+      if (s1 === peg$FAILED) {
+        s0 = peg$c19;
+      } else {
+        peg$currPos = s0;
+        s0 = peg$c1;
+      }
+
+      return s0;
+    }
+
+
+      var TransformationRule = require("./TransformationRule");
+
+
+    peg$result = peg$startRuleFunction();
+
+    if (peg$result !== peg$FAILED && peg$currPos === input.length) {
+      return peg$result;
+    } else {
+      if (peg$result !== peg$FAILED && peg$currPos < input.length) {
+        peg$fail({ type: "end", description: "end of input" });
+      }
+
+      throw peg$buildException(null, peg$maxFailExpected, peg$maxFailPos);
+    }
+  }
+
+  return {
+    SyntaxError: SyntaxError,
+    parse:       parse
+  };
+})();