arabika - npm Package Compare versions

Comparing version 0.0.1 to 0.0.2

lib/3-chr.js

 // Generated by CoffeeScript 1.6.3
 (function() {
-  var $new, BNP, TRM, XRE, alert, badge, debug, echo, help, info, log, rpr, warn, whisper, ƒ;
+  var BNP, TRM, XRE, alert, badge, debug, echo, help, info, log, rpr, warn, whisper, ƒ;
 
@@ -27,15 +27,41 @@ TRM = require('coffeenode-trm');
 
-  BNP = require('coffeenode-bitsnpieces');
-
   ƒ = require('flowmatic');
 
-  $new = ƒ["new"];
+  this.$new = ƒ["new"]["new"](this);
 
+  BNP = require('coffeenode-bitsnpieces');
+
   XRE = require('./9-xre');
 
-  this.$_constants = {
-    'ascii-punctuation': "-!\"#%&'()*,./:;?@[\\]_{}",
+  this.$ = {
 
+    /* ASCII Punctuation: */
+    'ascii-punctuation': /[-_!"\#%&'(\[{\\}\])*,.\/:;?@]/,
+
+    /* Whitespace: */
+
+    /* Unicode line endings (RegEx should have the global flag set): */
+    'newlines': /\r\n|[\n\v\f\r\x85\u2028\u2029]/g,
+
+    /* Unicode linear whitespace: */
+    'linear-whitespace': XRE('\\L+'),
+
+    /* Anything but whitespace: */
+    'no-whitespace': /[^\s\x85]+/,
+
+    /* Names: */
+
+    /* Leading character in names (excluding sigils): */
+    'name-first-chr': XRE('\\p{L}'),
+
+    /* Trailing characters in names: */
+    'name-trailing-chrs': XRE('(?:-|\\p{L}|\\d)*'),
+
+    /* Character used to form URL-like routes out of crumbs: */
+    'crumbs-joiner': '/',
+
     /* Sigils may start and classify simple names: */
     'sigils': {
+      '@': 'attribute',
+      '~': 'system',
       '.': 'hidden',
@@ -48,72 +74,170 @@ '_': 'private',
 
+  this.$new.$ascii_punctuation = function(G, $) {
+    var R;
+    R = ƒ.regex($['ascii-punctuation']);
+    return R;
+  };
 
-  /* TAINT `ƒ.or` is an expedient here */
+  this.$new.$chr = function(G, $) {
+    var R;
+    R = ƒ.regex(XRE('.', 'Qs'));
+    R = R.onMatch(function(match) {
+      return match[0];
+    });
+    return R;
+  };
 
 
-  /* TAINT no memoizing */
+  /* TAINT `ƒ.or` is an expedient here */
 
-  this.$_ascii_punctuation = ƒ.or((function(_this) {
-    return function() {
-      return ƒ.regex(XRE('[' + (XRE.$esc(_this.$_constants['ascii-punctuation'])) + ']'));
-    };
-  })(this));
+  this.$new.chr = function(G, $) {
+    var R;
+    R = ƒ.or(function() {
+      return G.$chr;
+    });
+    R = R.onMatch(function(match) {
+      return ƒ["new"].literal('chr', match, match);
+    });
+    return R;
+  };
 
-  this.$_chr = (ƒ.regex(XRE('.', 'Qs'))).onMatch(function(match) {
-    return match[0];
-  });
 
-
   /* TAINT `ƒ.or` is an expedient here */
 
-  this.chr = (ƒ.or(this.$_chr)).onMatch(function(match) {
-    return $new.literal('chr', match, match);
-  });
+  this.$new.$letter = function(G, $) {
+    var R;
+    R = ƒ.regex(XRE('\\p{L}'));
+    R = R.onMatch(function(match) {
+      return match[0];
+    });
+    return R;
+  };
 
+  this.$new.$lws = function(G, $) {
 
-  /* Linear WhiteSpace */
+    /* Linear WhiteSpace */
+    var R;
+    R = ƒ.regex($['linear-whitespace']);
+    R = R.onMatch(function(match) {
+      return match[0];
+    });
+    R = R.describe('linear whitespace');
+    return R;
+  };
 
-  this.lws = (ƒ.regex(/\x20+/)).onMatch(function(match) {
-    return $new.literal('lws', match[0], match[0]);
-  });
+  this.$new.lws = function(G, $) {
 
+    /* Linear WhiteSpace */
+    var R;
+    R = G.$lws.onMatch(function(match) {
+      return ƒ["new"].literal('lws', match, match);
+    });
+    R = R.describe('linear whitespace');
+    return R;
+  };
 
-  /* invisible LWS */
+  this.$new.ilws = function(G, $) {
 
-  this.ilws = ƒ.drop(ƒ.regex(/\x20+/));
+    /* invisible LWS */
+    var R;
+    R = ƒ.drop(ƒ.regex($['linear-whitespace']));
+    return R;
+  };
 
+  this.$new.$nws = function(G, $) {
 
-  /* no WhiteSpace */
+    /* no WhiteSpace */
+    var R;
+    R = ƒ.regex($['no-whitespace']);
+    return R;
+  };
 
-  this.$nws = ƒ.regex(/[^\s\x85]+/);
+  this.$new.nws = function(G, $) {
+    var R;
+    R = ƒ.or(function() {
+      return G.$nws.onMatch(function(match) {
+        return ƒ["new"].literal('nws', match[0], match[0]);
+      });
+    });
+    R = R.describe("no-whitespace");
+    return R;
+  };
 
+  this.$new.$nl = function(G, $) {
+    var R;
+    R = ƒ.regex($['newlines']);
+    return R;
+  };
 
-  /* TAINT better way to chain methods? */
+  this.$new.$name_first_chr = function(G, $) {
+    var R;
+    R = ƒ.regex($['name-first-chr']);
+    R = R.onMatch(function(match) {
+      return match[0];
+    });
+    R = R.describe('first character of name');
+    return R;
+  };
 
-  this.nws = this.$nws.onMatch((function(_this) {
-    return function(match) {
-      return $new.literal('nws', match[0], match[0]);
-    };
-  })(this));
+  this.$new.$name_trailing_chrs = function(G, $) {
+    var R;
+    R = ƒ.regex($['name-trailing-chrs']);
+    R = R.onMatch(function(match) {
+      return match[0];
+    });
+    R = R.describe('trailing characters of name');
+    return R;
+  };
 
-  this.nws = this.nws.describe("no-whitespace");
+  this.$new.$name_sigil = function(G, $) {
+    var R, key, sigils;
+    sigils = ((function() {
+      var _results;
+      _results = [];
+      for (key in $['sigils']) {
+        _results.push(XRE.$esc(key));
+      }
+      return _results;
+    })()).join('');
+    R = ƒ.regex(XRE("[" + sigils + "]"));
+    R = R.onMatch(function(match) {
+      return match[0];
+    });
+    R = R.describe('name');
+    return R;
+  };
 
+  this.$new.$name = function(G, $) {
+    var R;
+    R = ƒ.seq(ƒ.optional(function() {
+      return G.$name_sigil;
+    }), (function() {
+      return G.$name_first_chr;
+    }), (function() {
+      return G.$name_trailing_chrs;
+    }));
+    R = R.onMatch(function(match) {
+      return match.join('');
+    });
+    R = R.describe('name');
+    return R;
+  };
 
-  /* Unicode line endings: */
 
-  this.$nl_re = /\r\n|[\n\v\f\r\x85\u2028\u2029]/g;
+  /* Run `@$new` to make `@` (`this`) an instance of this grammar with default options: */
 
-  this.$nl = ƒ.regex(this.$nl_re);
+  this.$new(this, null);
 
   this.$TESTS = {
     '$chr: matches code points (instead of code units) and newlines': function(test) {
-      test.eq(this.$_chr.run('x'), 'x');
-      test.eq(this.$_chr.run('\r'), '\r');
-      test.eq(this.$_chr.run('\n'), '\n');
-      return test.eq(this.$_chr.run('𠀝'), '𠀝');
+      test.eq(this.$chr.run('x'), 'x');
+      test.eq(this.$chr.run('\r'), '\r');
+      test.eq(this.$chr.run('\n'), '\n');
+      return test.eq(this.$chr.run('𠀝'), '𠀝');
     },
     'chr: matches code points (instead of code units) and newlines': function(test) {
-      test.eq(this.chr.run('x'), $new.literal('chr', 'x', 'x'));
-      test.eq(this.chr.run('\r'), $new.literal('chr', '\r', '\r'));
-      test.eq(this.chr.run('\n'), $new.literal('chr', '\n', '\n'));
-      return test.eq(this.chr.run('𠀝'), $new.literal('chr', '𠀝', '𠀝'));
+      test.eq(this.chr.run('x'), ƒ["new"].literal('chr', 'x', 'x'));
+      test.eq(this.chr.run('\r'), ƒ["new"].literal('chr', '\r', '\r'));
+      test.eq(this.chr.run('\n'), ƒ["new"].literal('chr', '\n', '\n'));
+      return test.eq(this.chr.run('𠀝'), ƒ["new"].literal('chr', '𠀝', '𠀝'));
     },
@@ -126,3 +250,3 @@ '$chr: accepts single character, be it one or two code units': function(test) {
         _ref = probes_and_results[_i], probe = _ref[0], result = _ref[1];
-        _results.push(test.eq(this.$_chr.run(probe), result));
+        _results.push(test.eq(this.$chr.run(probe), result));
       }
@@ -139,3 +263,3 @@ return _results;
           return function() {
-            return _this.$_chr.run(probe);
+            return _this.$chr.run(probe);
           };
@@ -154,3 +278,3 @@ })(this)), /Expected end/));
           return function() {
-            return _this.$_ascii_punctuation.run(probe);
+            return _this.$ascii_punctuation.run(probe);
           };
@@ -197,3 +321,3 @@ })(this)), /Expected /));
         probe = probes[_i];
-        _results.push(test.eq(this.nws.run(probe), $new.literal('nws', probe, probe)));
+        _results.push(test.eq(this.nws.run(probe), ƒ["new"].literal('nws', probe, probe)));
       }
@@ -208,3 +332,3 @@ return _results;
         probe = probes[_i];
-        _results.push(test.eq(this.lws.run(probe), $new.literal('lws', probe, probe)));
+        _results.push(test.eq(this.lws.run(probe), ƒ["new"].literal('lws', probe, probe)));
       }
@@ -223,7 +347,88 @@ return _results;
     },
-    '$nl_re: splits string with Unicode line endings correctly': function(test) {
-      return test.eq('1\r\n2\n3\v4\f5\r6\x857\u20288\u20299'.split(this.$nl_re), ['1', '2', '3', '4', '5', '6', '7', '8', '9']);
+    "G$[ 'newlines' ]: splits string with Unicode line endings correctly": function(test) {
+      var G;
+      G = this;
+      return test.eq('1\r\n2\n3\v4\f5\r6\x857\u20288\u20299'.split(this.$['newlines']), ['1', '2', '3', '4', '5', '6', '7', '8', '9']);
     },
-    '$nl_re: allows global replace': function(test) {
-      return test.eq('1\r\n2\n3\v4\f5\r6\x857\u20288\u20299'.replace(this.$nl_re, '#'), '1#2#3#4#5#6#7#8#9');
+    "G$[ 'newlines' ]: allows global replace": function(test) {
+      return test.eq('1\r\n2\n3\v4\f5\r6\x857\u20288\u20299'.replace(this.$['newlines'], '#'), '1#2#3#4#5#6#7#8#9');
+    },
+    '$letter: matches single letters, including 32bit code points': function(test) {
+      var probe, probes_and_results, result, _i, _len, _ref, _results;
+      probes_and_results = [['q', 'q'], ['中', '中'], ['𠀝', '𠀝']];
+      _results = [];
+      for (_i = 0, _len = probes_and_results.length; _i < _len; _i++) {
+        _ref = probes_and_results[_i], probe = _ref[0], result = _ref[1];
+        _results.push(test.eq(this.$letter.run(probe), result));
+      }
+      return _results;
+    },
+    '$letter: rejects anything but single letters': function(test) {
+      var probe, probes, _i, _len, _results;
+      probes = ['0', '-', '(', '؟', 'xx'];
+      _results = [];
+      for (_i = 0, _len = probes.length; _i < _len; _i++) {
+        probe = probes[_i];
+        _results.push(test.throws(((function(_this) {
+          return function() {
+            return _this.$letter.run(probe);
+          };
+        })(this)), /Expected/));
+      }
+      return _results;
+    },
+    '$name_first_chr: matches first character of names': function(test) {
+      var probe, probes, _i, _len, _results;
+      probes = ['a', 'A', '𠀁'];
+      _results = [];
+      for (_i = 0, _len = probes.length; _i < _len; _i++) {
+        probe = probes[_i];
+        _results.push(test.eq(this.$name_first_chr.run(probe), probe));
+      }
+      return _results;
+    },
+    '$name_trailing_chrs: matches trailing characters of names': function(test) {
+      var probe, probes, _i, _len, _results;
+      probes = ['abc', 'abc-def', 'abc-def-45'];
+      _results = [];
+      for (_i = 0, _len = probes.length; _i < _len; _i++) {
+        probe = probes[_i];
+        _results.push(test.eq(this.$name_trailing_chrs.run(probe), probe));
+      }
+      return _results;
+    },
+    '$name: matches names': function(test) {
+      var probe, probes, _i, _len, _results;
+      probes = ['n', 'n0', 'readable-names', 'foo-32'];
+      _results = [];
+      for (_i = 0, _len = probes.length; _i < _len; _i++) {
+        probe = probes[_i];
+        _results.push(test.eq(this.$name.run(probe), probe));
+      }
+      return _results;
+    },
+    '$name: matches names with sigils': function(test) {
+      var probe, probes, _i, _len, _results;
+      probes = ['@n', '%n0', '_readable-names', '.foo-32', '~isa'];
+      _results = [];
+      for (_i = 0, _len = probes.length; _i < _len; _i++) {
+        probe = probes[_i];
+        whisper(probe);
+        _results.push(test.eq(this.$name.run(probe), probe));
+      }
+      return _results;
+    },
+    '$name: rejects non-names': function(test) {
+      var probe, probes, _i, _len, _results;
+      probes = ['034', '-/-', '()', '؟?'];
+      _results = [];
+      for (_i = 0, _len = probes.length; _i < _len; _i++) {
+        probe = probes[_i];
+        _results.push(test.throws(((function(_this) {
+          return function() {
+            return _this.$name.run(probe);
+          };
+        })(this)), /Expected/));
+      }
+      return _results;
     }
@@ -230,0 +435,0 @@ };

lib/7-indentation.js

@@ -18,3 +18,3 @@ // Generated by CoffeeScript 1.6.3
 (function() {
-  var $new, CHR, TRM, TYPES, XRE, alert, badge, debug, echo, help, info, log, rainbow, rpr, warn, whisper, ƒ,
+  var CHR, TRM, TYPES, XRE, alert, badge, debug, echo, help, info, log, rainbow, rpr, warn, whisper, ƒ,
     __slice = [].slice;
@@ -50,3 +50,3 @@
 
-  $new = ƒ["new"];
+  this.$new = ƒ["new"]["new"](this);
 
@@ -102,5 +102,3 @@ CHR = require('./3-chr');
 
-  this.$new = $new["new"](this);
 
-
   /* TAINT must parameterize */
@@ -107,0 +105,0 @@

lib/9-xre.js

 // Generated by CoffeeScript 1.6.3
+
+/*
+
+[Whitespace in Unicode 6.3](http://en.wikipedia.org/wiki/Whitespace_character):
+
+Linear:
+
+  U+0009  HT, Horizontal Tab
+  U+0020  space
+  U+00A0  no-break space
+  U+1680  ogham space mark
+  U+2000  en quad
+  U+2001  em quad
+  U+2002  en space
+  U+2003  em space
+  U+2004  three-per-em space
+  U+2005  four-per-em space
+  U+2006  six-per-em space
+  U+2007  figure space
+  U+2008  punctuation space
+  U+2009  thin space
+  U+200A  hair space
+  U+202F  narrow no-break space
+  U+205F  medium mathematical space
+  U+3000  ideographic space
+
+Line breaking:
+  U+000A  LF, Line feed
+  U+000B  VT, Vertical Tab
+  U+000C  FF, Form feed
+  U+000D  CR, Carriage return
+  U+0085  NEL, Next line
+  U+2028  line separator
+  U+2029  paragraph separator
+ */
+
 (function() {
-  var BNP, TRM, XRE, XRegExp, alert, badge, debug, echo, extension_u, help, info, log, rainbow, rpr, warn, whisper,
+  var BNP, TRM, XRE, XRegExp, alert, badge, debug, echo, help, info, log, rainbow, rpr, warn, whisper,
     __slice = [].slice;
@@ -52,38 +88,37 @@
 
-  extension_u = {
-    matcher: /\\u{([0-9A-Fa-f]{1,6})}/,
-    handler: (function() {
-      var dec, hex, pad4;
-      pad4 = function(s) {
-        while (s.length < 4) {
-          s = "0" + s;
-        }
-        return s;
-      };
-      dec = function(hex) {
-        return parseInt(hex, 16);
-      };
-      hex = function(dec) {
-        return parseInt(dec, 10).toString(16);
-      };
-      return function(match) {
-        var code, offset;
-        code = dec(match[1]);
-        offset = void 0;
-        if (code > 0x10FFFF) {
-          throw new SyntaxError("invalid Unicode code point " + match[0]);
-        }
-        if (code <= 0xFFFF) {
-          return "\\u" + pad4(hex(code));
-        }
-        offset = code - 0x10000;
-        return "\\u" + pad4(hex(0xD800 + (offset >> 10))) + "\\u" + pad4(hex(0xDC00 + (offset & 0x3FF)));
-      };
-    })(),
-    options: {
-      scope: 'all'
-    }
-  };
+  XRegExp.addToken(/\\u{([0-9A-Fa-f]{1,6})}/, (function() {
+    var as_dec, as_hex, pad;
+    pad = function(literal) {
+      while (literal.length < 4) {
+        '0' + literal;
+      }
+      return literal;
+    };
+    as_dec = function(literal) {
+      return parseInt(literal, 16);
+    };
+    as_hex = function(n) {
+      return (parseInt(n, 10)).toString(16);
+    };
+    return function(match, scope, flags) {
+      var cid, lead_surrogate, offset, trail_surrogate;
+      cid = as_dec(match[1]);
+      if (cid > 0x10FFFF) {
+        throw new SyntaxError("invalid Unicode code point " + match[0]);
+      }
 
-  XRegExp.addToken(extension_u.matcher, extension_u.handler, extension_u.options);
+      /* Converting to \uNNNN avoids needing to escape the character and keep it separate
+      from preceding tokens:
+       */
+      if (cid <= 0xFFFF) {
+        return "\\u" + (pad(as_hex(cid)));
+      }
+      offset = cid - 0x10000;
+      lead_surrogate = pad(as_hex(0xD800 + (offset >> 10)));
+      trail_surrogate = pad(as_hex(0xDC00 + (offset & 0x3FF)));
+      return "\\u" + lead_surrogate + "\\u" + trail_surrogate;
+    };
+  })(), {
+    scope: 'all'
+  });
 
@@ -105,2 +140,11 @@
 
+  /* Add the \L escape that matches all linear whitespace: */
+
+  XRegExp.addToken(/\\L/, function(match, scope, flags) {
+    return "[\\u0009\\u0020\\u00A0\\u1680\\u2000\\u2001\\u2002\\u2003\\u2004\\u2005\\u2006\\u2007\\u2008\\u2009\\u200A\\u202F\\u205F\\u3000]";
+  }, {
+    scope: 'all'
+  });
+
+
   /* Add the U (ungreedy) flag from PCRE and RE2, which reverses greedy and lazy quantifiers: */
@@ -122,3 +166,3 @@
 
-  XRE.TESTS = {
+  XRE.$TESTS = {
     '(all): even without flag `A`, `\\p{}` expressions match astral characters': function(test) {
@@ -133,2 +177,30 @@ var matcher;
     },
+    '(all): even without flag `u`, `\\u{}` is rejected when argument is not a hexadecimal digit': function(test) {
+      test.throws((function() {
+        return '〇𠀝x'.match(XRegExp('\\u{}'));
+      }), /Invalid/);
+      return test.throws((function() {
+        return '〇𠀝x'.match(XRegExp('\\u{xxx}'));
+      }), /Invalid/);
+    },
+    '(all): even without flag `u`, `\\u{}` is rejected when argument is beyond limits': function(test) {
+      return test.throws((function() {
+        return '〇𠀝x'.match(XRegExp('\\u{201234}'));
+      }), /invalid Unicode code point/);
+    },
+    '(all): `\\L` matches linear whitespace': function(test) {
+      test.ok((XRegExp('\\L')).test(' '));
+      test.ok((XRegExp('\\L')).test('\t'));
+      return test.ok((XRegExp('\\L')).test('\u3000'));
+    },
+    '(all): `\\L+` matches stretches of linear whitespace': function(test) {
+      test.eq((' \t '.match(XRegExp('\\L+')))[0], ' \t ');
+      test.eq(('\t\t\t\t'.match(XRegExp('\\L+')))[0], '\t\t\t\t');
+      return test.eq(('\u3000 \t'.match(XRegExp('\\L+')))[0], '\u3000 \t');
+    },
+    '(all): `\\L` does not match other characters than linear whitespace': function(test) {
+      test.ok(!(XRegExp('\\L')).test('x'));
+      test.ok(!(XRegExp('\\L')).test('\n'));
+      return test.ok(!(XRegExp('\\L')).test('\r'));
+    },
     '(`Q` flag): make dot match code points (instead of code units)': function(test) {
@@ -135,0 +207,0 @@ return test.eq(('𠀝x'.match(XRegExp('.', 'Q')))[0], '𠀝');

package.json

 {
   "name": "arabika",
-  "version": "0.0.1",
+  "version": "0.0.2",
   "description": "A language that compiles to JavaScript",
@@ -5,0 +5,0 @@ "main": "lib/main.js",

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Major refactor

Supply chain risk

Package has recently undergone a major refactor. It may be unstable or indicate significant internal changes. Use caution when updating to versions that include significant changes.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

277769

increased by6.42%

Lines of code

2415

increased by12.01%

Number of medium supply chain risk alerts

1

decreased by-50%

No dependency changes