regexp-examples 0.6.0 → 0.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 062a1310c8b7c861a7724fd75745c1e9bff9257f
-  data.tar.gz: b05ce36dbb3c0afee079091d5c1016a429f1d099
+  metadata.gz: f7dacce756110dd70823630de898a8c9f55d12b1
+  data.tar.gz: d3ee78e2ed48d91aacc9cb916d8ab71dd25e326d
 SHA512:
-  metadata.gz: 5519ec6e710a257c165b35f6b4138bc03d37973c31fcb4a7c6091713ab347438dd8e8bbde722c5ab21f63d6ede0565be2b77de0747d42f9f1e83413312b71d14
-  data.tar.gz: 58d67c5e25de2dbd238cb53a192c784047b8ab7e8a836d87c47c9cf5316133d3383a8fdec0a7c9fe07eec0518266b3c66a66c8953e830277b41e1bf9ca53e525
+  metadata.gz: 2655f9c1b1bbb8452a06d7debdba232ba53354131776bbf23a69fc1dc3b62d950600093b4581d2f4c5304f161db421ed95204e8c40cee2adc75c95670dcf42a1
+  data.tar.gz: da2dd9829aa3f5f2415f4a5ca4182133c19b1a481a40172140858ba72f65e05824eebdbff8899c6f0d84a90c93b0539c86c68dd7a23371fe6f577da738746824

data/README.md

@@ -44,6 +44,7 @@ For more detail on this, see [configuration options](#configuration-options).
 * Unicode characters, e.g. `/\u0123/`, `/\uabcd/`, `/\u{789}/`
 * Octal characters, e.g. `/\10/`, `/\177/`
 * POSIX bracket expressions (including negation), e.g. `/[[:alnum:]]/`, `/[[:^space:]]/`
+* Named properties, e.g. `/\p{L}/` ("Letter"), `/\p{Arabic}/` ("Arabic character"), `/\p{^Ll}/` ("Not a lowercase letter")
 * **Arbitrarily complex combinations of all the above!**
 
 * Regexp options can also be used:
@@ -60,11 +61,6 @@ For more detail on this, see [configuration options](#configuration-options).
 
 * Conditional capture groups, such as `/(group1) (?(1)yes|no)`
 
-Using any of the following will raise a RegexpExamples::UnsupportedSyntax exception (until such time as they are implemented!):
-
-* Named properties, e.g. `/\p{L}/` ("Letter"), `/\p{Arabic}/` ("Arabic character"), `/\p{^Ll}/` ("Not a lowercase letter")
-* Subexpression calls, e.g. `/(?<name> ... \g<name>* )/` (Note: These could get _really_ ugly to implement, and may even be impossible, so I highly doubt it's worth the effort!)
-
 There are loads more (increasingly obscure) unsupported bits of syntax, which I cannot be bothered to write out here. Full documentation on all the various other obscurities in the ruby (version 2.x) regexp parser can be found [here](https://raw.githubusercontent.com/k-takata/Onigmo/master/doc/RE).
 
 ## Impossible features ("illegal syntax")
@@ -77,6 +73,7 @@ Using any of the following will raise a RegexpExamples::IllegalSyntax exception:
 * Lookarounds, e.g. `/foo(?=bar)/`, `/foo(?!bar)/`, `/(?<=foo)bar/`, `/(?<!foo)bar/`
 * [Anchors](http://ruby-doc.org/core-2.2.0/Regexp.html#class-Regexp-label-Anchors) (`\b`, `\B`, `\G`, `^`, `\A`, `$`, `\z`, `\Z`), e.g. `/\bword\b/`, `/line1\n^line2/`
   * However, a special case has been made to allow `^`, `\A` and `\G` at the start of a pattern; and to allow `$`, `\z` and `\Z` at the end of pattern. In such cases, the characters are effectively just ignored.
+* Subexpression calls, e.g. `/(?<name> ... \g<name>* )/`
 
 (Note: Backreferences are not really "regular" either, but I got these to work with a bit of hackery!)
 

data/lib/regexp-examples/backreferences.rb

@@ -1,5 +1,7 @@
 module RegexpExamples
   class BackReferenceReplacer
+    BackrefNotFound = Class.new(StandardError)
+
     def substitute_backreferences(full_examples)
       full_examples.map do |full_example|
         begin
@@ -7,7 +9,7 @@ module RegexpExamples
             full_example.sub!(/__(\w+?)__/, find_backref_for(full_example, $1))
           end
           full_example
-        rescue RegexpExamples::BackrefNotFound
+        rescue BackrefNotFound
           # For instance, one "full example" from /(a|(b)) \2/: "a __2__"
           # should be rejected because the backref (\2) does not exist
           nil
@@ -27,7 +29,7 @@ module RegexpExamples
       if octal_chars =~ /\A[01]?[0-7]{1,2}\z/ && octal_chars.to_i >= 10
         Integer(octal_chars, 8).chr
       else
-        raise(RegexpExamples::BackrefNotFound)
+        raise(BackrefNotFound)
       end
     end
 

data/lib/regexp-examples/constants.rb

@@ -35,6 +35,9 @@ module RegexpExamples
     Lower        = Array('a'..'z')
     Upper        = Array('A'..'Z')
     Digit        = Array('0'..'9')
+    # Note: Punct should also include the following chars: $ + < = > ^ ` | ~
+    # I.e. Punct = %w(! " # $ % & ' ( ) * + , - . / : ; < = > ? @ [ \\ ] ^ _ ` { | } ~)
+    # However, due to a ruby bug (!!) these do not work properly at the moment!
     Punct        = %w(! " # % & ' ( ) * , - . / : ; ? @ [ \\ ] _ { })
     Hex          = Array('a'..'f') | Array('A'..'F') | Digit
     Word         = Lower | Upper | Digit | ['_']
@@ -81,5 +84,157 @@ module RegexpExamples
     'word'   => CharSets::Word,
     'ascii'  => CharSets::Any
   }.freeze
+
+  def self.ranges_to_unicode(*ranges)
+    result = []
+    ranges.each do |range|
+      if range.is_a? Fixnum # Small hack to improve readability below
+        result << hex_to_unicode(range.to_s(16))
+      else
+        range.each { |num| result << hex_to_unicode(num.to_s(16)) }
+      end
+    end
+    result
+  end
+
+  def self.hex_to_unicode(hex)
+    eval("?\\u{#{hex}}")
+  end
+
+  # These values were generated by: scripts/unicode_lister.rb
+  # Note: Only the first 128 results are listed, for performance.
+  # Also, some groups seem to have no matches (weird!)
+  NamedPropertyCharMap = {
+    'Alnum' => ranges_to_unicode(48..57, 65..90, 97..122, 170, 181, 186, 192..214, 216..246, 248..256),
+    'Alpha' => ranges_to_unicode(65..90, 97..122, 170, 181, 186, 192..214, 216..246, 248..266),
+    'Blank' => ranges_to_unicode(9, 32, 160, 5760, 8192..8202, 8239, 8287, 12288),
+    'Cntrl' => ranges_to_unicode(0..31, 127..159),
+    'Digit' => ranges_to_unicode(48..57, 1632..1641, 1776..1785, 1984..1993, 2406..2415, 2534..2543, 2662..2671, 2790..2799, 2918..2927, 3046..3055, 3174..3183, 3302..3311, 3430..3437),
+    'Graph' => ranges_to_unicode(33..126, 161..194),
+    'Lower' => ranges_to_unicode(97..122, 170, 181, 186, 223..246, 248..255, 257, 259, 261, 263, 265, 267, 269, 271, 273, 275, 277, 279, 281, 283, 285, 287, 289, 291, 293, 295, 297, 299, 301, 303, 305, 307, 309, 311..312, 314, 316, 318, 320, 322, 324, 326, 328..329, 331, 333, 335, 337, 339, 341, 343, 345, 347, 349, 351, 353, 355, 357, 359, 361, 363, 365, 367, 369, 371, 373, 375, 378, 380, 382..384, 387),
+    'Print' => ranges_to_unicode(32..126, 160..192),
+    'Punct' => ranges_to_unicode(33..35, 37..42, 44..47, 58..59, 63..64, 91..93, 95, 123, 125, 161, 167, 171, 182..183, 187, 191, 894, 903, 1370..1375, 1417..1418, 1470, 1472, 1475, 1478, 1523..1524, 1545..1546, 1548..1549, 1563, 1566..1567, 1642..1645, 1748, 1792..1805, 2039..2041, 2096..2110, 2142, 2404..2405, 2416, 2800, 3572, 3663, 3674..3675, 3844..3858, 3860, 3898..3901, 3973, 4048..4052, 4057..4058, 4170),
+    'Space' => ranges_to_unicode(9..13, 32, 133, 160, 5760, 8192..8202, 8232..8233, 8239, 8287, 12288),
+    'Upper' => ranges_to_unicode(65..90, 192..214, 216..222, 256, 258, 260, 262, 264, 266, 268, 270, 272, 274, 276, 278, 280, 282, 284, 286, 288, 290, 292, 294, 296, 298, 300, 302, 304, 306, 308, 310, 313, 315, 317, 319, 321, 323, 325, 327, 330, 332, 334, 336, 338, 340, 342, 344, 346, 348, 350, 352, 354, 356, 358, 360, 362, 364, 366, 368, 370, 372, 374, 376..377, 379, 381, 385..386, 388, 390..391, 393..395, 398),
+    'XDigit' => ranges_to_unicode(48..57, 65..70, 97..102),
+    'Word' => ranges_to_unicode(48..57, 65..90, 95, 97..122, 170, 181, 186, 192..214, 216..246, 248..255),
+    'ASCII' => ranges_to_unicode(0..127),
+    'Any' => ranges_to_unicode(0..127),
+    'Assigned' => ranges_to_unicode(0..127),
+    'L' => ranges_to_unicode(65..90, 97..122, 170, 181, 186, 192..214, 216..246, 248..266),
+    'Ll' => ranges_to_unicode(97..122, 181, 223..246, 248..255, 257, 259, 261, 263, 265, 267, 269, 271, 273, 275, 277, 279, 281, 283, 285, 287, 289, 291, 293, 295, 297, 299, 301, 303, 305, 307, 309, 311..312, 314, 316, 318, 320, 322, 324, 326, 328..329, 331, 333, 335, 337, 339, 341, 343, 345, 347, 349, 351, 353, 355, 357, 359, 361, 363, 365, 367, 369, 371, 373, 375, 378, 380, 382..384, 387, 389, 392),
+    'Lm' => ranges_to_unicode(688..705, 710..721, 736..740, 748, 750, 884, 890, 1369, 1600, 1765..1766, 2036..2037, 2042, 2074, 2084, 2088, 2417, 3654, 3782, 4348, 6103, 6211, 6823, 7288..7293, 7468..7530, 7544, 7579..7580),
+    'Lo' => ranges_to_unicode(170, 186, 443, 448..451, 660, 1488..1514, 1520..1522, 1568..1599, 1601..1610, 1646..1647, 1649..1694),
+    'Lt' => ranges_to_unicode(453, 456, 459, 498, 8072..8079, 8088..8095, 8104..8111, 8124, 8140, 8188),
+    'Lu' => ranges_to_unicode(65..90, 192..214, 216..222, 256, 258, 260, 262, 264, 266, 268, 270, 272, 274, 276, 278, 280, 282, 284, 286, 288, 290, 292, 294, 296, 298, 300, 302, 304, 306, 308, 310, 313, 315, 317, 319, 321, 323, 325, 327, 330, 332, 334, 336, 338, 340, 342, 344, 346, 348, 350, 352, 354, 356, 358, 360, 362, 364, 366, 368, 370, 372, 374, 376..377, 379, 381, 385..386, 388, 390..391, 393..395, 398),
+    'M' => ranges_to_unicode(768..879, 1155..1161, 1425..1433),
+    'Mn' => ranges_to_unicode(768..879, 1155..1159, 1425..1435),
+    'Mc' => ranges_to_unicode(2307, 2363, 2366..2368, 2377..2380, 2382..2383, 2434..2435, 2494..2496, 2503..2504, 2507..2508, 2519, 2563, 2622..2624, 2691, 2750..2752, 2761, 2763..2764, 2818..2819, 2878, 2880, 2887..2888, 2891..2892, 2903, 3006..3007, 3009..3010, 3014..3016, 3018..3020, 3031, 3073..3075, 3137..3140, 3202..3203, 3262, 3264..3268, 3271..3272, 3274..3275, 3285..3286, 3330..3331, 3390..3392, 3398..3400, 3402..3404, 3415, 3458..3459, 3535..3537, 3544..3551, 3570..3571, 3902..3903, 3967, 4139..4140, 4145, 4152, 4155..4156, 4182..4183, 4194..4196, 4199..4205, 4227..4228, 4231..4235),
+    'Me' => ranges_to_unicode(1160..1161, 6846, 8413..8416, 8418..8420, 42608..42610),
+    'N' => ranges_to_unicode(48..57, 178..179, 185, 188..190, 1632..1641, 1776..1785, 1984..1993, 2406..2415, 2534..2543, 2548..2553, 2662..2671, 2790..2799, 2918..2927, 2930..2935, 3046..3058, 3174..3180),
+    'Nd' => ranges_to_unicode(48..57, 1632..1641, 1776..1785, 1984..1993, 2406..2415, 2534..2543, 2662..2671, 2790..2799, 2918..2927, 3046..3055, 3174..3183, 3302..3311, 3430..3437),
+    'Nl' => ranges_to_unicode(5870..5872, 8544..8578, 8581..8584, 12295, 12321..12329, 12344..12346, 42726..42735),
+    'No' => ranges_to_unicode(178..179, 185, 188..190, 2548..2553, 2930..2935, 3056..3058, 3192..3198, 3440..3445, 3882..3891, 4969..4988, 6128..6137, 6618, 8304, 8308..8313, 8320..8329, 8528..8543, 8585, 9312..9330),
+    'P' => ranges_to_unicode(33..35, 37..42, 44..47, 58..59, 63..64, 91..93, 95, 123, 125, 161, 167, 171, 182..183, 187, 191, 894, 903, 1370..1375, 1417..1418, 1470, 1472, 1475, 1478, 1523..1524, 1545..1546, 1548..1549, 1563, 1566..1567, 1642..1645, 1748, 1792..1805, 2039..2041, 2096..2110, 2142, 2404..2405, 2416, 2800, 3572, 3663, 3674..3675, 3844..3858, 3860, 3898..3901, 3973, 4048..4052, 4057..4058, 4170),
+    'Pc' => ranges_to_unicode(95, 8255..8256, 8276),
+    'Pd' => ranges_to_unicode(45, 1418, 1470, 5120, 6150, 8208..8213, 11799, 11802, 11834..11835, 11840, 12316, 12336, 12448),
+    'Ps' => ranges_to_unicode(40, 91, 123, 3898, 3900, 5787, 8218, 8222, 8261, 8317, 8333, 8968, 8970, 9001, 10088, 10090, 10092, 10094, 10096, 10098, 10100, 10181, 10214, 10216, 10218, 10220, 10222, 10627, 10629, 10631, 10633, 10635, 10637, 10639, 10641, 10643, 10645, 10647, 10712, 10714, 10748, 11810, 11812, 11814, 11816, 11842, 12296, 12298, 12300, 12302, 12304, 12308, 12310, 12312, 12314, 12317),
+    'Pe' => ranges_to_unicode(41, 93, 125, 3899, 3901, 5788, 8262, 8318, 8334, 8969, 8971, 9002, 10089, 10091, 10093, 10095, 10097, 10099, 10101, 10182, 10215, 10217, 10219, 10221, 10223, 10628, 10630, 10632, 10634, 10636, 10638, 10640, 10642, 10644, 10646, 10648, 10713, 10715, 10749, 11811, 11813, 11815, 11817, 12297, 12299, 12301, 12303, 12305, 12309, 12311, 12313, 12315, 12318..12319),
+    'Pi' => ranges_to_unicode(171, 8216, 8219..8220, 8223, 8249, 11778, 11780, 11785, 11788, 11804, 11808),
+    'Pf' => ranges_to_unicode(187, 8217, 8221, 8250, 11779, 11781, 11786, 11789, 11805, 11809),
+    'Po' => ranges_to_unicode(33..35, 37..39, 42, 44, 46..47, 58..59, 63..64, 92, 161, 167, 182..183, 191, 894, 903, 1370..1375, 1417, 1472, 1475, 1478, 1523..1524, 1545..1546, 1548..1549, 1563, 1566..1567, 1642..1645, 1748, 1792..1805, 2039..2041, 2096..2110, 2142, 2404..2405, 2416, 2800, 3572, 3663, 3674..3675, 3844..3858, 3860, 3973, 4048..4052, 4057..4058, 4170..4175, 4347, 4960..4968, 5741),
+    'S' => ranges_to_unicode(36, 43, 60..62, 94, 96, 124, 126, 162..166, 168..169, 172, 174..177, 180, 184, 215, 247, 706..709, 722..735, 741..747, 749, 751..767, 885, 900..901, 1014, 1154, 1421..1423, 1542..1544, 1547, 1550..1551, 1758, 1769, 1789..1790, 2038, 2546..2547, 2554..2555, 2801, 2928, 3059..3066, 3199, 3449, 3647, 3841..3843, 3859, 3861..3863, 3866..3871, 3892, 3894, 3896, 4030..4037),
+    'Sm' => ranges_to_unicode(43, 60..62, 124, 126, 172, 177, 215, 247, 1014, 1542..1544, 8260, 8274, 8314..8316, 8330..8332, 8472, 8512..8516, 8523, 8592..8596, 8602..8603, 8608, 8611, 8614, 8622, 8654..8655, 8658, 8660, 8692..8775),
+    'Sc' => ranges_to_unicode(36, 162..165, 1423, 1547, 2546..2547, 2555, 2801, 3065, 3647, 6107, 8352..8381, 43064),
+    'Sk' => ranges_to_unicode(94, 96, 168, 175, 180, 184, 706..709, 722..735, 741..747, 749, 751..767, 885, 900..901, 8125, 8127..8129, 8141..8143, 8157..8159, 8173..8175, 8189..8190, 12443..12444, 42752..42774, 42784..42785, 42889..42890, 43867),
+    'So' => ranges_to_unicode(166, 169, 174, 176, 1154, 1421..1422, 1550..1551, 1758, 1769, 1789..1790, 2038, 2554, 2928, 3059..3064, 3066, 3199, 3449, 3841..3843, 3859, 3861..3863, 3866..3871, 3892, 3894, 3896, 4030..4037, 4039..4044, 4046..4047, 4053..4056, 4254..4255, 5008..5017, 6464, 6622..6655, 7009..7018, 7028..7036, 8448),
+    'Z' => ranges_to_unicode(32, 160, 5760, 8192..8202, 8232..8233, 8239, 8287, 12288),
+    'Zs' => ranges_to_unicode(32, 160, 5760, 8192..8202, 8239, 8287, 12288),
+    'Zl' => ranges_to_unicode(8232),
+    'Zp' => ranges_to_unicode(8233),
+    'C' => ranges_to_unicode(0..31, 127..159, 173, 888..889, 896..899, 907, 909, 930, 1328, 1367..1368, 1376, 1416, 1419..1420, 1424, 1480..1487, 1515..1519, 1525..1541, 1564..1565, 1757, 1806..1807, 1867..1868, 1970..1977),
+    'Cc' => ranges_to_unicode(0..31, 127..159),
+    'Cf' => ranges_to_unicode(173, 1536..1541, 1564, 1757, 1807, 6158, 8203..8207, 8234..8238, 8288..8292, 8294..8303),
+    'Cn' => ranges_to_unicode(888..889, 896..899, 907, 909, 930, 1328, 1367..1368, 1376, 1416, 1419..1420, 1424, 1480..1487, 1515..1519, 1525..1535, 1565, 1806, 1867..1868, 1970..1983, 2043..2047, 2094..2095, 2111, 2140..2141, 2143..2201),
+    'Co' => ranges_to_unicode(),
+    'Cs' => ranges_to_unicode(),
+    'Arabic' => ranges_to_unicode(1536..1540, 1542..1547, 1549..1562, 1566, 1568..1599, 1601..1610, 1622..1631, 1642..1647, 1649..1692),
+    'Armenian' => ranges_to_unicode(1329..1366, 1369..1375, 1377..1415, 1418, 1421..1423),
+    'Balinese' => ranges_to_unicode(6912..6987, 6992..7036),
+    'Bengali' => ranges_to_unicode(2432..2435, 2437..2444, 2447..2448, 2451..2472, 2474..2480, 2482, 2486..2489, 2492..2500, 2503..2504, 2507..2510, 2519, 2524..2525, 2527..2531, 2534..2555),
+    'Bopomofo' => ranges_to_unicode(746..747, 12549..12589, 12704..12730),
+    'Braille' => ranges_to_unicode(10240..10367),
+    'Buginese' => ranges_to_unicode(6656..6683, 6686..6687),
+    'Buhid' => ranges_to_unicode(5952..5971),
+    'Canadian_Aboriginal' => ranges_to_unicode(5120..5247),
+    'Carian' => ranges_to_unicode(),
+    'Cham' => ranges_to_unicode(43520..43574, 43584..43597, 43600..43609, 43612..43615),
+    'Cherokee' => ranges_to_unicode(5024..5108),
+    'Common' => ranges_to_unicode(0..64, 91..96, 123..169, 171..180),
+    'Coptic' => ranges_to_unicode(994..1007, 11392..11505),
+    'Cuneiform' => ranges_to_unicode(),
+    'Cypriot' => ranges_to_unicode(),
+    'Cyrillic' => ranges_to_unicode(1024..1151),
+    'Deseret' => ranges_to_unicode(),
+    'Devanagari' => ranges_to_unicode(2304..2384, 2387..2403, 2406..2431, 43232..43235),
+    'Ethiopic' => ranges_to_unicode(4608..4680, 4682..4685, 4688..4694, 4696, 4698..4701, 4704..4742),
+    'Georgian' => ranges_to_unicode(4256..4293, 4295, 4301, 4304..4346, 4348..4351, 11520..11557, 11559, 11565),
+    'Glagolitic' => ranges_to_unicode(11264..11310, 11312..11358),
+    'Gothic' => ranges_to_unicode(),
+    'Greek' => ranges_to_unicode(880..883, 885..887, 890..893, 895, 900, 902, 904..906, 908, 910..929, 931..993, 1008..1023, 7462..7466, 7517..7521, 7526),
+    'Gujarati' => ranges_to_unicode(2689..2691, 2693..2701, 2703..2705, 2707..2728, 2730..2736, 2738..2739, 2741..2745, 2748..2757, 2759..2761, 2763..2765, 2768, 2784..2787, 2790..2801),
+    'Gurmukhi' => ranges_to_unicode(2561..2563, 2565..2570, 2575..2576, 2579..2600, 2602..2608, 2610..2611, 2613..2614, 2616..2617, 2620, 2622..2626, 2631..2632, 2635..2637, 2641, 2649..2652, 2654, 2662..2677),
+    'Han' => ranges_to_unicode(11904..11929, 11931..12019, 12032..12044),
+    'Hangul' => ranges_to_unicode(4352..4479),
+    'Hanunoo' => ranges_to_unicode(5920..5940),
+    'Hebrew' => ranges_to_unicode(1425..1479, 1488..1514, 1520..1524),
+    'Hiragana' => ranges_to_unicode(12353..12438, 12445..12447),
+    'Inherited' => ranges_to_unicode(768..879, 1157..1158, 1611..1621, 1648, 2385..2386),
+    'Kannada' => ranges_to_unicode(3201..3203, 3205..3212, 3214..3216, 3218..3240, 3242..3251, 3253..3257, 3260..3268, 3270..3272, 3274..3277, 3285..3286, 3294, 3296..3299, 3302..3311, 3313..3314),
+    'Katakana' => ranges_to_unicode(12449..12538, 12541..12543, 12784..12799, 13008..13026),
+    'Kayah_Li' => ranges_to_unicode(43264..43309, 43311),
+    'Kharoshthi' => ranges_to_unicode(),
+    'Khmer' => ranges_to_unicode(6016..6109, 6112..6121, 6128..6137, 6624..6637),
+    'Lao' => ranges_to_unicode(3713..3714, 3716, 3719..3720, 3722, 3725, 3732..3735, 3737..3743, 3745..3747, 3749, 3751, 3754..3755, 3757..3769, 3771..3773, 3776..3780, 3782, 3784..3789, 3792..3801, 3804..3807),
+    'Latin' => ranges_to_unicode(65..90, 97..122, 170, 186, 192..214, 216..246, 248..267),
+    'Lepcha' => ranges_to_unicode(7168..7223, 7227..7241, 7245..7247),
+    'Limbu' => ranges_to_unicode(6400..6430, 6432..6443, 6448..6459, 6464, 6468..6479),
+    'Linear_B' => ranges_to_unicode(),
+    'Lycian' => ranges_to_unicode(),
+    'Lydian' => ranges_to_unicode(),
+    'Malayalam' => ranges_to_unicode(3329..3331, 3333..3340, 3342..3344, 3346..3386, 3389..3396, 3398..3400, 3402..3406, 3415, 3424..3427, 3430..3445, 3449..3455),
+    'Mongolian' => ranges_to_unicode(6144..6145, 6148, 6150..6158, 6160..6169, 6176..6263, 6272..6289),
+    'Myanmar' => ranges_to_unicode(4096..4223),
+    'New_Tai_Lue' => ranges_to_unicode(6528..6571, 6576..6601, 6608..6618, 6622..6623),
+    'Nko' => ranges_to_unicode(1984..2042),
+    'Ogham' => ranges_to_unicode(5760..5788),
+    'Ol_Chiki' => ranges_to_unicode(7248..7295),
+    'Old_Italic' => ranges_to_unicode(),
+    'Old_Persian' => ranges_to_unicode(),
+    'Oriya' => ranges_to_unicode(2817..2819, 2821..2828, 2831..2832, 2835..2856, 2858..2864, 2866..2867, 2869..2873, 2876..2884, 2887..2888, 2891..2893, 2902..2903, 2908..2909, 2911..2915, 2918..2935),
+    'Osmanya' => ranges_to_unicode(),
+    'Phags_Pa' => ranges_to_unicode(43072..43127),
+    'Phoenician' => ranges_to_unicode(),
+    'Rejang' => ranges_to_unicode(43312..43347, 43359),
+    'Runic' => ranges_to_unicode(5792..5866, 5870..5880),
+    'Saurashtra' => ranges_to_unicode(43136..43204, 43214..43225),
+    'Shavian' => ranges_to_unicode(),
+    'Sinhala' => ranges_to_unicode(3458..3459, 3461..3478, 3482..3505, 3507..3515, 3517, 3520..3526, 3530, 3535..3540, 3542, 3544..3551, 3558..3567, 3570..3572),
+    'Sundanese' => ranges_to_unicode(7040..7103, 7360..7367),
+    'Syloti_Nagri' => ranges_to_unicode(43008..43051),
+    'Syriac' => ranges_to_unicode(1792..1805, 1807..1866, 1869..1871),
+    'Tagalog' => ranges_to_unicode(5888..5900, 5902..5908),
+    'Tagbanwa' => ranges_to_unicode(5984..5996, 5998..6000, 6002..6003),
+    'Tai_Le' => ranges_to_unicode(6480..6509, 6512..6516),
+    'Tamil' => ranges_to_unicode(2946..2947, 2949..2954, 2958..2960, 2962..2965, 2969..2970, 2972, 2974..2975, 2979..2980, 2984..2986, 2990..3001, 3006..3010, 3014..3016, 3018..3021, 3024, 3031, 3046..3066),
+    'Telugu' => ranges_to_unicode(3072..3075, 3077..3084, 3086..3088, 3090..3112, 3114..3129, 3133..3140, 3142..3144, 3146..3149, 3157..3158, 3160..3161, 3168..3171, 3174..3183, 3192..3199),
+    'Thaana' => ranges_to_unicode(1920..1969),
+    'Thai' => ranges_to_unicode(3585..3642, 3648..3675),
+    'Tibetan' => ranges_to_unicode(3840..3911, 3913..3948, 3953..3972),
+    'Tifinagh' => ranges_to_unicode(11568..11623, 11631..11632, 11647),
+    'Ugaritic' => ranges_to_unicode(),
+    'Vai' => ranges_to_unicode(42240..42367),
+    'Yi' => ranges_to_unicode(40960..41087),
+  }.freeze
 end
 

data/lib/regexp-examples/parser.rb

@@ -1,4 +1,5 @@
 module RegexpExamples
+  IllegalSyntaxError = Class.new(StandardError)
   class Parser
     attr_reader :regexp_string
     def initialize(regexp_string, regexp_options, config_options={})
@@ -85,8 +86,6 @@ module RegexpExamples
         group = parse_backreference_group($1)
       when BackslashCharMap.keys.include?(next_char)
         group = CharGroup.new(
-          # Note: The `.dup` is important, as it prevents modifying the constant, in
-          # CharGroup#init_ranges (where the '-' is moved to the front)
           BackslashCharMap[next_char].dup,
           @ignorecase
         )
@@ -100,16 +99,22 @@ module RegexpExamples
         @current_position += $1.length
         sequence = $1.match(/\h{1,4}/)[0] # Strip off "{" and "}"
         group = parse_single_char_group( parse_unicode_sequence(sequence) )
-      when rest_of_string =~ /\Ap\{([^}]+)\}/ # Named properties
-        @current_position += ($1.length + 2)
-        raise UnsupportedSyntaxError, "Named properties ({\\p#{$1}}) are not yet supported"
+      when rest_of_string =~ /\Ap\{(\^?)([^}]+)\}/ # Named properties
+        @current_position += ($1.length + $2.length + 2)
+        group = CharGroup.new(
+          if($1 == "^")
+            CharSets::Any.dup - NamedPropertyCharMap[$2]
+          else
+            NamedPropertyCharMap[$2]
+          end,
+          @ignorecase
+        )
       when next_char == 'K' # Keep (special lookbehind that CAN be supported safely!)
         group = PlaceHolderGroup.new
       when next_char == 'R' # Linebreak
         group = CharGroup.new(["\r\n", "\n", "\v", "\f", "\r"], @ignorecase) # A bit hacky...
       when next_char == 'g' # Subexpression call
-        # TODO: Should this be IllegalSyntaxError ?
-        raise UnsupportedSyntaxError, "Subexpression calls (\g) are not yet supported"
+        raise IllegalSyntaxError, "Subexpression calls (\g) are not yet supported"
       when next_char =~ /[bB]/ # Anchors
         raise IllegalSyntaxError, "Anchors ('\\#{next_char}') cannot be supported, as they are not regular"
       when next_char =~ /[AG]/ # Start of string

data/lib/regexp-examples/version.rb

@@ -1,3 +1,3 @@
 module RegexpExamples
-  VERSION = '0.6.0'
+  VERSION = '0.7.0'
 end

data/scripts/unicode_lister.rb

@@ -0,0 +1,180 @@
+# A script to generate lists of all unicode characters
+# that match all named group/character properties regexps.
+# For use in e.g. /\p{Arabic}/.examples
+
+# To (re-)generate this list, simply run this file!
+# > ruby scripts/unicode_lister.rb
+OutputFilename = 'unicode_result'
+
+# Taken from ruby documentation:
+# http://ruby-doc.org//core-2.2.0/Regexp.html#class-Regexp-label-Character+Properties
+NamedGroups = %w(
+  Alnum
+  Alpha
+  Blank
+  Cntrl
+  Digit
+  Graph
+  Lower
+  Print
+  Punct
+  Space
+  Upper
+  XDigit
+  Word
+  ASCII
+  Any
+  Assigned
+
+  L
+  Ll
+  Lm
+  Lo
+  Lt
+  Lu
+  M
+  Mn
+  Mc
+  Me
+  N
+  Nd
+  Nl
+  No
+  P
+  Pc
+  Pd
+  Ps
+  Pe
+  Pi
+  Pf
+  Po
+  S
+  Sm
+  Sc
+  Sk
+  So
+  Z
+  Zs
+  Zl
+  Zp
+  C
+  Cc
+  Cf
+  Cn
+  Co
+  Cs
+
+  Arabic
+  Armenian
+  Balinese
+  Bengali
+  Bopomofo
+  Braille
+  Buginese
+  Buhid
+  Canadian_Aboriginal
+  Carian
+  Cham
+  Cherokee
+  Common
+  Coptic
+  Cuneiform
+  Cypriot
+  Cyrillic
+  Deseret
+  Devanagari
+  Ethiopic
+  Georgian
+  Glagolitic
+  Gothic
+  Greek
+  Gujarati
+  Gurmukhi
+  Han
+  Hangul
+  Hanunoo
+  Hebrew
+  Hiragana
+  Inherited
+  Kannada
+  Katakana
+  Kayah_Li
+  Kharoshthi
+  Khmer
+  Lao
+  Latin
+  Lepcha
+  Limbu
+  Linear_B
+  Lycian
+  Lydian
+  Malayalam
+  Mongolian
+  Myanmar
+  New_Tai_Lue
+  Nko
+  Ogham
+  Ol_Chiki
+  Old_Italic
+  Old_Persian
+  Oriya
+  Osmanya
+  Phags_Pa
+  Phoenician
+  Rejang
+  Runic
+  Saurashtra
+  Shavian
+  Sinhala
+  Sundanese
+  Syloti_Nagri
+  Syriac
+  Tagalog
+  Tagbanwa
+  Tai_Le
+  Tamil
+  Telugu
+  Thaana
+  Thai
+  Tibetan
+  Tifinagh
+  Ugaritic
+  Vai
+  Yi
+)
+
+# Note: For some reason, a character encoding-related exception gets raised
+# when I do `/regex/ =~ eval("?\\u{#{x.to_s(16)}}")` in the range: 55296..57343
+# This means my calculation is MISSING results in the range: 55296..65535
+# However, for the sake of performance, I'm also being "lazy" and only calculating/saving
+# the first 128 matches anyway!
+# If anyone ever cares about this (I doubt it), I'll look into fixing/improving it.
+
+# Example input: [1, 2, 3, 4, 6, 7, 12, 14] (Array)
+# Example output: "1..4, 6..7, 12, 14" (String)
+def calculate_ranges(matching_codes)
+  return "" if matching_codes.empty?
+  first = matching_codes.shift
+  matching_codes.inject([first..first]) do |r,x|
+    if r.last.last.succ != x
+      r << (x..x) # Start new range
+    else
+      r[0..-2] << (r.last.first..x) # Update last range
+    end
+  end
+    .map { |range| range.size == 1 ? range.first : range}
+    .join(", ")
+end
+
+count = 0
+File.open(OutputFilename, 'w') do |f|
+  NamedGroups.each do |name|
+  count += 1
+    matching_codes = (0..55295).lazy.select { |x| /\p{#{name}}/ =~ eval("?\\u{#{x.to_s(16)}}") }.first(128)
+    f.puts "'#{name}' => ranges_to_unicode(#{calculate_ranges(matching_codes)}),"
+    puts "(#{count}/#{NamedGroups.length}) Finished property: #{name}"
+  end
+  puts "*"*50
+  puts "Finished! Result stored in: #{OutputFilename}"
+end
+

data/spec/regexp-examples_spec.rb

@@ -1,14 +1,9 @@
 RSpec.describe Regexp, "#examples" do
   def self.examples_exist_and_match(*regexps)
     regexps.each do |regexp|
-      it do
-        begin
-          regexp_examples = regexp.examples(max_group_results: 999)
-        rescue
-          # TODO: Find a nicer way to display this?
-          puts "Error generating examples for /#{regexp.source}/"
-          raise $!
-        end
+      it "examples for /#{regexp.source}/" do
+        regexp_examples = regexp.examples(max_group_results: 999)
+
         expect(regexp_examples).not_to be_empty, "No examples were generated for regexp: /#{regexp.source}/"
         regexp_examples.each { |example| expect(example).to match(/\A(?:#{regexp.source})\z/) }
         # Note: /\A...\z/ is used to prevent misleading examples from passing the test.
@@ -21,24 +16,16 @@ RSpec.describe Regexp, "#examples" do
 
   def self.examples_raise_illegal_syntax_error(*regexps)
     regexps.each do |regexp|
-      it do
+      it "examples for /#{regexp.source}/" do
         expect{regexp.examples}.to raise_error RegexpExamples::IllegalSyntaxError
       end
     end
   end
 
-  def self.examples_raise_unsupported_syntax_error(*regexps)
-    regexps.each do |regexp|
-      it do
-        expect{regexp.examples}.to raise_error RegexpExamples::UnsupportedSyntaxError
-      end
-    end
-  end
-
   def self.examples_are_empty(*regexps)
     regexps.each do |regexp|
-      it do
-        expect(regexp.examples).to be_empty, "Unexpected examples for regexp: /#{regexp.source}/"
+      it "examples for /#{regexp.source}/" do
+        expect(regexp.examples).to be_empty
       end
     end
   end
@@ -167,7 +154,8 @@ RSpec.describe Regexp, "#examples" do
         /start-of^-line/,
         /end-of\Z-string/,
         /end-of\z-string/,
-        /end-of$-line/
+        /end-of$-line/,
+        /(?<name> ... \g<name>*)/
       )
     end
 
@@ -182,13 +170,13 @@ RSpec.describe Regexp, "#examples" do
       )
     end
 
-    context "for unsupported syntax" do
-      examples_raise_unsupported_syntax_error(
+    context "for named properties" do
+      examples_exist_and_match(
         /\p{L}/,
         /\p{Arabic}/,
-        /\p{^Ll}/,
-        /(?<name> ... \g<name>*)/
+        /\p{^Ll}/
       )
+
     end
 
     context "for control characters" do

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: regexp-examples
 version: !ruby/object:Gem::Version
-  version: 0.6.0
+  version: 0.7.0
 platform: ruby
 authors:
 - Tom Lord
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-02-22 00:00:00.000000000 Z
+date: 2015-02-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -58,13 +58,13 @@ files:
 - lib/regexp-examples/chargroup_parser.rb
 - lib/regexp-examples/constants.rb
 - lib/regexp-examples/core_extensions/regexp/examples.rb
-- lib/regexp-examples/exceptions.rb
 - lib/regexp-examples/groups.rb
 - lib/regexp-examples/helpers.rb
 - lib/regexp-examples/parser.rb
 - lib/regexp-examples/repeaters.rb
 - lib/regexp-examples/version.rb
 - regexp-examples.gemspec
+- scripts/unicode_lister.rb
 - spec/regexp-examples_spec.rb
 - spec/spec_helper.rb
 homepage: http://rubygems.org/gems/regexp-examples

data/lib/regexp-examples/exceptions.rb

@@ -1,6 +0,0 @@
-module RegexpExamples
-  class Error < StandardError; end
-  class UnsupportedSyntaxError < Error; end
-  class IllegalSyntaxError < Error; end
-  class BackrefNotFound < Error; end
-end