Skip to content

Commit 9cb42f5

Browse files
committedDec 15, 2017
Basic properties should have low indices (ctypes)
1 parent d721b1f commit 9cb42f5

File tree

2 files changed

+26
-25
lines changed

2 files changed

+26
-25
lines changed
 

‎scripts/generate.rb

+3-2
Original file line numberDiff line numberDiff line change
@@ -167,10 +167,11 @@ def generate_coderange_list
167167
end
168168

169169
ranges = unicode_src[/CodeRanges\[\]\s+=\s+\{(.*?)\}\;/m, 1].scan(/CR_(\w+)/).flatten
170-
out = ranges.map do |range|
170+
171+
out = ranges.take(14).map{|range|[range.tr('_', '').downcase, range]} +
172+
ranges.drop(14).map do |range|
171173
name = range =~ /Age_(\d)_(\d)/ ? "age=#{$1}.#{$2}" : range.tr('_', '').downcase
172174
name = cr_map.delete(range) || name
173-
174175
([name] + aliases[name].to_a).map{|n|[n, range]}
175176
end.flatten(1)
176177

‎src/org/jcodings/unicode/UnicodeProperties.java

+23-23
Original file line numberDiff line numberDiff line change
@@ -23,31 +23,27 @@
2323

2424
public class UnicodeProperties {
2525
static final CodeRangeEntry[]CodeRangeTable = new CodeRangeEntry[] {
26-
new CodeRangeEntry("graphemeclusterbreaklf", "CR_NEWLINE"),
27-
new CodeRangeEntry("alphabetic", "CR_Alpha"),
26+
new CodeRangeEntry("newline", "CR_NEWLINE"),
27+
new CodeRangeEntry("alpha", "CR_Alpha"),
2828
new CodeRangeEntry("blank", "CR_Blank"),
29-
new CodeRangeEntry("cc", "CR_Cntrl"),
30-
new CodeRangeEntry("control", "CR_Cntrl"),
31-
new CodeRangeEntry("nd", "CR_Digit"),
32-
new CodeRangeEntry("decimalnumber", "CR_Digit"),
29+
new CodeRangeEntry("cntrl", "CR_Cntrl"),
30+
new CodeRangeEntry("digit", "CR_Digit"),
3331
new CodeRangeEntry("graph", "CR_Graph"),
34-
new CodeRangeEntry("lowercase", "CR_Lower"),
32+
new CodeRangeEntry("lower", "CR_Lower"),
3533
new CodeRangeEntry("print", "CR_Print"),
36-
new CodeRangeEntry("p", "CR_Punct"),
37-
new CodeRangeEntry("punctuation", "CR_Punct"),
38-
new CodeRangeEntry("whitespace", "CR_Space"),
39-
new CodeRangeEntry("wspace", "CR_Space"),
40-
new CodeRangeEntry("uppercase", "CR_Upper"),
41-
new CodeRangeEntry("asciihexdigit", "CR_XDigit"),
42-
new CodeRangeEntry("ahex", "CR_XDigit"),
34+
new CodeRangeEntry("punct", "CR_Punct"),
35+
new CodeRangeEntry("space", "CR_Space"),
36+
new CodeRangeEntry("upper", "CR_Upper"),
37+
new CodeRangeEntry("xdigit", "CR_XDigit"),
4338
new CodeRangeEntry("word", "CR_Word"),
4439
new CodeRangeEntry("alnum", "CR_Alnum"),
4540
new CodeRangeEntry("inbasiclatin", "CR_ASCII"),
4641
new CodeRangeEntry("any", "CR_Any"),
4742
new CodeRangeEntry("assigned", "CR_Assigned"),
4843
new CodeRangeEntry("c", "CR_C"),
4944
new CodeRangeEntry("other", "CR_C"),
50-
new CodeRangeEntry("cntrl", "CR_Cntrl"),
45+
new CodeRangeEntry("cc", "CR_Cntrl"),
46+
new CodeRangeEntry("control", "CR_Cntrl"),
5147
new CodeRangeEntry("cf", "CR_Cf"),
5248
new CodeRangeEntry("format", "CR_Cf"),
5349
new CodeRangeEntry("cn", "CR_Cn"),
@@ -81,12 +77,14 @@ public class UnicodeProperties {
8177
new CodeRangeEntry("nonspacingmark", "CR_Mn"),
8278
new CodeRangeEntry("n", "CR_N"),
8379
new CodeRangeEntry("number", "CR_N"),
84-
new CodeRangeEntry("digit", "CR_Digit"),
80+
new CodeRangeEntry("nd", "CR_Digit"),
81+
new CodeRangeEntry("decimalnumber", "CR_Digit"),
8582
new CodeRangeEntry("nl", "CR_Nl"),
8683
new CodeRangeEntry("letternumber", "CR_Nl"),
8784
new CodeRangeEntry("no", "CR_No"),
8885
new CodeRangeEntry("othernumber", "CR_No"),
89-
new CodeRangeEntry("punct", "CR_Punct"),
86+
new CodeRangeEntry("p", "CR_Punct"),
87+
new CodeRangeEntry("punctuation", "CR_Punct"),
9088
new CodeRangeEntry("pc", "CR_Pc"),
9189
new CodeRangeEntry("connectorpunctuation", "CR_Pc"),
9290
new CodeRangeEntry("pd", "CR_Pd"),
@@ -120,9 +118,9 @@ public class UnicodeProperties {
120118
new CodeRangeEntry("zs", "CR_Zs"),
121119
new CodeRangeEntry("spaceseparator", "CR_Zs"),
122120
new CodeRangeEntry("math", "CR_Math"),
123-
new CodeRangeEntry("alpha", "CR_Alpha"),
124-
new CodeRangeEntry("lower", "CR_Lower"),
125-
new CodeRangeEntry("upper", "CR_Upper"),
121+
new CodeRangeEntry("alphabetic", "CR_Alpha"),
122+
new CodeRangeEntry("lowercase", "CR_Lower"),
123+
new CodeRangeEntry("uppercase", "CR_Upper"),
126124
new CodeRangeEntry("cased", "CR_Cased"),
127125
new CodeRangeEntry("caseignorable", "CR_Case_Ignorable"),
128126
new CodeRangeEntry("ci", "CR_Case_Ignorable"),
@@ -413,7 +411,8 @@ public class UnicodeProperties {
413411
new CodeRangeEntry("osge", "CR_Osage"),
414412
new CodeRangeEntry("tangut", "CR_Tangut"),
415413
new CodeRangeEntry("tang", "CR_Tangut"),
416-
new CodeRangeEntry("space", "CR_Space"),
414+
new CodeRangeEntry("whitespace", "CR_Space"),
415+
new CodeRangeEntry("wspace", "CR_Space"),
417416
new CodeRangeEntry("bidicontrol", "CR_Bidi_Control"),
418417
new CodeRangeEntry("bidic", "CR_Bidi_Control"),
419418
new CodeRangeEntry("joincontrol", "CR_Join_Control"),
@@ -428,7 +427,8 @@ public class UnicodeProperties {
428427
new CodeRangeEntry("omath", "CR_Other_Math"),
429428
new CodeRangeEntry("hexdigit", "CR_Hex_Digit"),
430429
new CodeRangeEntry("hex", "CR_Hex_Digit"),
431-
new CodeRangeEntry("xdigit", "CR_XDigit"),
430+
new CodeRangeEntry("asciihexdigit", "CR_XDigit"),
431+
new CodeRangeEntry("ahex", "CR_XDigit"),
432432
new CodeRangeEntry("otheralphabetic", "CR_Other_Alphabetic"),
433433
new CodeRangeEntry("oalpha", "CR_Other_Alphabetic"),
434434
new CodeRangeEntry("ideographic", "CR_Ideographic"),
@@ -496,7 +496,7 @@ public class UnicodeProperties {
496496
new CodeRangeEntry("age=9.0", "CR_Age_9_0"),
497497
new CodeRangeEntry("graphemeclusterbreakprepend", "CR_Grapheme_Cluster_Break_Prepend"),
498498
new CodeRangeEntry("graphemeclusterbreakcr", "CR_Grapheme_Cluster_Break_CR"),
499-
new CodeRangeEntry("newline", "CR_NEWLINE"),
499+
new CodeRangeEntry("graphemeclusterbreaklf", "CR_NEWLINE"),
500500
new CodeRangeEntry("graphemeclusterbreakcontrol", "CR_Grapheme_Cluster_Break_Control"),
501501
new CodeRangeEntry("graphemeextend", "CR_Grapheme_Extend"),
502502
new CodeRangeEntry("grext", "CR_Grapheme_Extend"),

0 commit comments

Comments
 (0)
Please sign in to comment.