Lines Matching refs:data
3 # Creates the data structures needed by Onigurma to map Unicode codepoints to
50 data = {'Any' => (0x0000..0x10ffff).to_a, 'Assigned' => [],
74 data['Cn'].concat((last_cp.next...beg_cp).to_a)
78 data['Assigned'].concat(cps)
81 (data[fields[2]] ||= []).concat(cps)
85 (data[fields[2][0,1]] ||= []).concat(cps)
92 data['Cn'] += cn_remainder
93 data['C'] += data['Cn']
96 data['LC'] = data['Ll'] + data['Lt'] + data['Lu']
99 gcps = data.keys.sort - POSIX_NAMES
101 # Returns General Category Property names and the data
102 [gcps, data]
105 def define_posix_props(data)
109 data['Alpha'] = data['Alphabetic']
110 data['Upper'] = data['Uppercase']
111 data['Lower'] = data['Lowercase']
112 data['Punct'] = data['Punctuation']
113 data['Digit'] = data['Decimal_Number']
114 data['XDigit'] = (0x0030..0x0039).to_a + (0x0041..0x0046).to_a +
116 data['Alnum'] = data['Alpha'] + data['Digit']
117 data['Space'] = data['White_Space']
118 data['Blank'] = data['Space_Separator'] + [0x0009]
119 data['Cntrl'] = data['Cc']
120 data['Word'] = data['Alpha'] + data['Mark'] + data['Digit'] + data['Connector_Punctuation']
121 data['Graph'] = data['Any'] - data['Space'] - data['Cntrl'] -
122 data['Surrogate'] - data['Unassigned']
123 data['Print'] = data['Graph'] + data['Space_Separator']
126 def parse_scripts(data, categories)
138 data[current] = cps
150 data['Unknown'] = (0..0x10ffff).to_a - data.values_at(*names['Script']).flatten
155 def parse_aliases(data)
159 data[$1] = data[$2]
165 data[$3] = data[$2]
166 data[$4] = data[$2]
170 data[$2] = data[$3]
171 data[$4] = data[$3]
182 def parse_age(data)
191 cps.concat(data[last_constname]) if last_constname
192 data[constname] = cps
205 def parse_block(data)
214 data[constname] = cps
222 no_block = (0..0x10ffff).to_a - data.values_at(*blocks).flatten
239 def make_const(prop, data, name)
241 if origprop = $const_cache.key(data)
244 $const_cache[prop] = data
245 pairs = pair_codepoints(data)
279 props, data = parse_unicode_data(get_file('UnicodeData.txt'))
281 props.concat parse_scripts(data, categories)
282 aliases = parse_aliases(data)
283 define_posix_props(data)
285 make_const(name, data[name], "[[:#{name}:]]")
295 make_const(name, data[name], category)
297 ages = parse_age(data)
298 blocks = parse_block(data)