Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: jruby/jcodings
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: 8b729bfece90
Choose a base ref
...
head repository: jruby/jcodings
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: 514b3a4df9d4
Choose a head ref
  • 2 commits
  • 2 files changed
  • 1 contributor

Commits on Dec 29, 2017

  1. update code range list

    @lopex
    lopex committed Dec 29, 2017
    Copy the full SHA
    3fe384c View commit details

  2. update script

    @lopex
    lopex committed Dec 29, 2017
    Copy the full SHA
    514b3a4 View commit details
Showing with 31 additions and 7 deletions.
  1. +4 −4 scripts/generate.rb
  2. +27 −3 src/org/jcodings/unicode/UnicodeProperties.java
8 changes: 4 additions & 4 deletions scripts/generate.rb
View file
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
# coding: utf-8

REPO_PATH = ARGV.first || '/usr/src/ruby-2.4.3' # path to ruby repo
REPO_PATH = ARGV.first || '/usr/src/ruby-2.5.0' # path to ruby repo
SECTION_NAME = "rdata"
UNICODE_VERSION = "9.0.0"
UNICODE_VERSION = "10.0.0"
SRC_DIR = "../src/org/jcodings"
DST_BIN_DIR = "../resources/tables"
INDENT = " " * 4
@@ -169,10 +169,10 @@ def generate_coderange_list

ranges = unicode_src[/CodeRanges\[\]\s+=\s+\{(.*?)\}\;/m, 1].scan(/CR_(\w+)/).flatten

standard_char_type_range = 15
standard_char_type_range = 16
out = ranges.take(standard_char_type_range).map{|range|[range.tr('_', '').downcase, range]} +
ranges.drop(standard_char_type_range).map do |range|
name = range =~ /Age_(\d)_(\d)/ ? "age=#{$1}.#{$2}" : range.tr('_', '').downcase
name = range =~ /Age_(\d+)_(\d+)/ ? "age=#{$1}.#{$2}" : range.tr('_', '').downcase
name = cr_map.delete(range) || name
name = "#{$1}=#{$2}" if name =~ /(graphemeclusterbreak)(.*)/i
([name] + aliases[name].to_a).map{|n|[n, range]}
30 changes: 27 additions & 3 deletions src/org/jcodings/unicode/UnicodeProperties.java
View file
Original file line number Diff line number Diff line change
@@ -31,13 +31,14 @@ public class UnicodeProperties {
new CodeRangeEntry("graph", "CR_Graph"),
new CodeRangeEntry("lower", "CR_Lower"),
new CodeRangeEntry("print", "CR_Print"),
new CodeRangeEntry("punct", "CR_Punct"),
new CodeRangeEntry("xposixpunct", "CR_XPosixPunct"),
new CodeRangeEntry("space", "CR_Space"),
new CodeRangeEntry("upper", "CR_Upper"),
new CodeRangeEntry("xdigit", "CR_XDigit"),
new CodeRangeEntry("word", "CR_Word"),
new CodeRangeEntry("alnum", "CR_Alnum"),
new CodeRangeEntry("ascii", "CR_ASCII"),
new CodeRangeEntry("punct", "CR_Punct"),
new CodeRangeEntry("any", "CR_Any"),
new CodeRangeEntry("assigned", "CR_Assigned"),
new CodeRangeEntry("c", "CR_C"),
@@ -411,6 +412,14 @@ public class UnicodeProperties {
new CodeRangeEntry("osge", "CR_Osage"),
new CodeRangeEntry("tangut", "CR_Tangut"),
new CodeRangeEntry("tang", "CR_Tangut"),
new CodeRangeEntry("masaramgondi", "CR_Masaram_Gondi"),
new CodeRangeEntry("gonm", "CR_Masaram_Gondi"),
new CodeRangeEntry("nushu", "CR_Nushu"),
new CodeRangeEntry("nshu", "CR_Nushu"),
new CodeRangeEntry("soyombo", "CR_Soyombo"),
new CodeRangeEntry("soyo", "CR_Soyombo"),
new CodeRangeEntry("zanabazarsquare", "CR_Zanabazar_Square"),
new CodeRangeEntry("zanb", "CR_Zanabazar_Square"),
new CodeRangeEntry("whitespace", "CR_Space"),
new CodeRangeEntry("wspace", "CR_Space"),
new CodeRangeEntry("bidicontrol", "CR_Bidi_Control"),
@@ -474,6 +483,12 @@ public class UnicodeProperties {
new CodeRangeEntry("patsyn", "CR_Pattern_Syntax"),
new CodeRangeEntry("prependedconcatenationmark", "CR_Prepended_Concatenation_Mark"),
new CodeRangeEntry("pcm", "CR_Prepended_Concatenation_Mark"),
new CodeRangeEntry("graphemeclusterbreak=regionalindicator", "CR_Regional_Indicator"),
new CodeRangeEntry("emoji", "CR_Emoji"),
new CodeRangeEntry("emojipresentation", "CR_Emoji_Presentation"),
new CodeRangeEntry("graphemeclusterbreak=emodifier", "CR_Emoji_Modifier"),
new CodeRangeEntry("emojimodifierbase", "CR_Emoji_Modifier_Base"),
new CodeRangeEntry("emojicomponent", "CR_Emoji_Component"),
new CodeRangeEntry("unknown", "CR_Unknown"),
new CodeRangeEntry("zzzz", "CR_Unknown"),
new CodeRangeEntry("age=1.1", "CR_Age_1_1"),
@@ -494,21 +509,23 @@ public class UnicodeProperties {
new CodeRangeEntry("age=7.0", "CR_Age_7_0"),
new CodeRangeEntry("age=8.0", "CR_Age_8_0"),
new CodeRangeEntry("age=9.0", "CR_Age_9_0"),
new CodeRangeEntry("age=10.0", "CR_Age_10_0"),
new CodeRangeEntry("graphemeclusterbreak=prepend", "CR_Grapheme_Cluster_Break_Prepend"),
new CodeRangeEntry("graphemeclusterbreak=cr", "CR_Grapheme_Cluster_Break_CR"),
new CodeRangeEntry("graphemeclusterbreak=lf", "CR_NEWLINE"),
new CodeRangeEntry("graphemeclusterbreak=control", "CR_Grapheme_Cluster_Break_Control"),
new CodeRangeEntry("graphemeextend", "CR_Grapheme_Extend"),
new CodeRangeEntry("grext", "CR_Grapheme_Extend"),
new CodeRangeEntry("graphemeclusterbreak=regionalindicator", "CR_Grapheme_Cluster_Break_Regional_Indicator"),
new CodeRangeEntry("regionalindicator", "CR_Regional_Indicator"),
new CodeRangeEntry("ri", "CR_Regional_Indicator"),
new CodeRangeEntry("graphemeclusterbreak=spacingmark", "CR_Grapheme_Cluster_Break_SpacingMark"),
new CodeRangeEntry("graphemeclusterbreak=l", "CR_Grapheme_Cluster_Break_L"),
new CodeRangeEntry("graphemeclusterbreak=v", "CR_Grapheme_Cluster_Break_V"),
new CodeRangeEntry("graphemeclusterbreak=t", "CR_Grapheme_Cluster_Break_T"),
new CodeRangeEntry("graphemeclusterbreak=lv", "CR_Grapheme_Cluster_Break_LV"),
new CodeRangeEntry("graphemeclusterbreak=lvt", "CR_Grapheme_Cluster_Break_LVT"),
new CodeRangeEntry("graphemeclusterbreak=ebase", "CR_Grapheme_Cluster_Break_E_Base"),
new CodeRangeEntry("graphemeclusterbreak=emodifier", "CR_Grapheme_Cluster_Break_E_Modifier"),
new CodeRangeEntry("emojimodifier", "CR_Emoji_Modifier"),
new CodeRangeEntry("graphemeclusterbreak=zwj", "CR_Grapheme_Cluster_Break_ZWJ"),
new CodeRangeEntry("graphemeclusterbreak=glueafterzwj", "CR_Grapheme_Cluster_Break_Glue_After_Zwj"),
new CodeRangeEntry("graphemeclusterbreak=ebasegaz", "CR_Grapheme_Cluster_Break_E_Base_GAZ"),
@@ -531,6 +548,7 @@ public class UnicodeProperties {
new CodeRangeEntry("innko", "CR_In_NKo"),
new CodeRangeEntry("insamaritan", "CR_In_Samaritan"),
new CodeRangeEntry("inmandaic", "CR_In_Mandaic"),
new CodeRangeEntry("insyriacsupplement", "CR_In_Syriac_Supplement"),
new CodeRangeEntry("inarabicextendeda", "CR_In_Arabic_Extended_A"),
new CodeRangeEntry("indevanagari", "CR_In_Devanagari"),
new CodeRangeEntry("inbengali", "CR_In_Bengali"),
@@ -741,9 +759,12 @@ public class UnicodeProperties {
new CodeRangeEntry("intakri", "CR_In_Takri"),
new CodeRangeEntry("inahom", "CR_In_Ahom"),
new CodeRangeEntry("inwarangciti", "CR_In_Warang_Citi"),
new CodeRangeEntry("inzanabazarsquare", "CR_In_Zanabazar_Square"),
new CodeRangeEntry("insoyombo", "CR_In_Soyombo"),
new CodeRangeEntry("inpaucinhau", "CR_In_Pau_Cin_Hau"),
new CodeRangeEntry("inbhaiksuki", "CR_In_Bhaiksuki"),
new CodeRangeEntry("inmarchen", "CR_In_Marchen"),
new CodeRangeEntry("inmasaramgondi", "CR_In_Masaram_Gondi"),
new CodeRangeEntry("incuneiform", "CR_In_Cuneiform"),
new CodeRangeEntry("incuneiformnumbersandpunctuation", "CR_In_Cuneiform_Numbers_and_Punctuation"),
new CodeRangeEntry("inearlydynasticcuneiform", "CR_In_Early_Dynastic_Cuneiform"),
@@ -758,6 +779,8 @@ public class UnicodeProperties {
new CodeRangeEntry("intangut", "CR_In_Tangut"),
new CodeRangeEntry("intangutcomponents", "CR_In_Tangut_Components"),
new CodeRangeEntry("inkanasupplement", "CR_In_Kana_Supplement"),
new CodeRangeEntry("inkanaextendeda", "CR_In_Kana_Extended_A"),
new CodeRangeEntry("innushu", "CR_In_Nushu"),
new CodeRangeEntry("induployan", "CR_In_Duployan"),
new CodeRangeEntry("inshorthandformatcontrols", "CR_In_Shorthand_Format_Controls"),
new CodeRangeEntry("inbyzantinemusicalsymbols", "CR_In_Byzantine_Musical_Symbols"),
@@ -788,6 +811,7 @@ public class UnicodeProperties {
new CodeRangeEntry("incjkunifiedideographsextensionc", "CR_In_CJK_Unified_Ideographs_Extension_C"),
new CodeRangeEntry("incjkunifiedideographsextensiond", "CR_In_CJK_Unified_Ideographs_Extension_D"),
new CodeRangeEntry("incjkunifiedideographsextensione", "CR_In_CJK_Unified_Ideographs_Extension_E"),
new CodeRangeEntry("incjkunifiedideographsextensionf", "CR_In_CJK_Unified_Ideographs_Extension_F"),
new CodeRangeEntry("incjkcompatibilityideographssupplement", "CR_In_CJK_Compatibility_Ideographs_Supplement"),
new CodeRangeEntry("intags", "CR_In_Tags"),
new CodeRangeEntry("invariationselectorssupplement", "CR_In_Variation_Selectors_Supplement"),