regexp_parser 2.8.0 → 2.8.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: bed928e92928d8f595241456658e516f3afd2474196ca4d6fdbb849c072d5024
-  data.tar.gz: 48d50057af6883cd2d67050fc05aed79e87342f6067eb80734729a8440c08a69
+  metadata.gz: e1426faee272654c45e3da8e262e94cfdbcf134dbad7804aed8cd945334c07be
+  data.tar.gz: 37eec721839fe2ebfc25c9d614756289b59ee766f5e7e60ecf4839b554bbb93e
 SHA512:
-  metadata.gz: 455e79dd780d7d5c130fae56140158615195601f68ea9eb83367d0b9faaf631586bbf12f5b9243d16bb42d29eeb57ba595f87a3b4604b32af059dc9a72c4d6d4
-  data.tar.gz: 37216a681eda06118b7317e64cab14cb06e39e4923433225598b60b8b36684ab831e4d90960516adbfdaa16811b274c2181eb38a13ddd259fb6790cbeef99ebf
+  metadata.gz: abed9d7f387634b5e16eb19cbfd5d9aab03288dd4d284b1c52688f958714479783275c5418ee623607ced96b301124ab82dff546e7e4146c7c5ec7feae3e089d
+  data.tar.gz: 62c0757df1c73df52fcf71ef8de666ab9a51a4a8145e71321424ab0ff8408cb2b707cf154dae64ebbcc5a9c8a12ee377a3eadab7549432a9d0e6ee0e65afddd1

data/CHANGELOG.md

@@ -7,6 +7,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [2.8.1] - 2023-06-10 - [Janosch Müller](mailto:janosch84@gmail.com)
+
+### Fixed
+
+- support for extpict unicode property, added in Ruby 2.6
+- support for 10 unicode script/block properties added in Ruby 3.2
+
 ## [2.8.0] - 2023-04-17 - [Janosch Müller](mailto:janosch84@gmail.com)
 
 ### Added

data/Gemfile

@@ -5,7 +5,7 @@ gemspec
 group :development, :test do
   gem 'leto', '~> 2.0'
   gem 'rake', '~> 13.0'
-  gem 'regexp_property_values', '~> 1.3'
+  gem 'regexp_property_values', '~> 1.4'
   gem 'rspec', '~> 3.10'
   if RUBY_VERSION.to_f >= 2.7
     gem 'benchmark-ips', '~> 2.1'

data/LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2010, 2012-2022,  Ammar Ali
+Copyright (c) 2010, 2012-2023,  Ammar Ali
 
 Permission is hereby granted, free of charge, to any person
 obtaining a copy of this software and associated documentation

data/README.md

@@ -503,4 +503,4 @@ Documentation and books used while working on this project.
 
 ---
 ##### Copyright
-_Copyright (c) 2010-2022 Ammar Ali. See LICENSE file for details._
+_Copyright (c) 2010-2023 Ammar Ali. See LICENSE file for details._

data/lib/regexp_parser/scanner/properties/long.csv

@@ -7,6 +7,7 @@ age=12.0,age=12.0
 age=12.1,age=12.1
 age=13.0,age=13.0
 age=14.0,age=14.0
+age=15.0,age=15.0
 age=2.0,age=2.0
 age=2.1,age=2.1
 age=3.0,age=3.0
@@ -97,6 +98,7 @@ emojimodifierbase,emoji_modifier_base
 emojipresentation,emoji_presentation
 enclosingmark,enclosing_mark
 ethiopic,ethiopic
+extendedpictographic,extended_pictographic
 extender,extender
 finalpunctuation,final_punctuation
 format,format
@@ -139,6 +141,7 @@ inancientsymbols,in_ancient_symbols
 inarabic,in_arabic
 inarabicextendeda,in_arabic_extended_a
 inarabicextendedb,in_arabic_extended_b
+inarabicextendedc,in_arabic_extended_c
 inarabicmathematicalalphabeticsymbols,in_arabic_mathematical_alphabetic_symbols
 inarabicpresentationformsa,in_arabic_presentation_forms_a
 inarabicpresentationformsb,in_arabic_presentation_forms_b
@@ -186,6 +189,7 @@ incjkunifiedideographsextensiond,in_cjk_unified_ideographs_extension_d
 incjkunifiedideographsextensione,in_cjk_unified_ideographs_extension_e
 incjkunifiedideographsextensionf,in_cjk_unified_ideographs_extension_f
 incjkunifiedideographsextensiong,in_cjk_unified_ideographs_extension_g
+incjkunifiedideographsextensionh,in_cjk_unified_ideographs_extension_h
 incombiningdiacriticalmarks,in_combining_diacritical_marks
 incombiningdiacriticalmarksextended,in_combining_diacritical_marks_extended
 incombiningdiacriticalmarksforsymbols,in_combining_diacritical_marks_for_symbols
@@ -205,10 +209,12 @@ incyrillic,in_cyrillic
 incyrillicextendeda,in_cyrillic_extended_a
 incyrillicextendedb,in_cyrillic_extended_b
 incyrillicextendedc,in_cyrillic_extended_c
+incyrillicextendedd,in_cyrillic_extended_d
 incyrillicsupplement,in_cyrillic_supplement
 indeseret,in_deseret
 indevanagari,in_devanagari
 indevanagariextended,in_devanagari_extended
+indevanagariextendeda,in_devanagari_extended_a
 indingbats,in_dingbats
 indivesakuru,in_dives_akuru
 indogra,in_dogra
@@ -268,6 +274,7 @@ inipaextensions,in_ipa_extensions
 initialpunctuation,initial_punctuation
 injavanese,in_javanese
 inkaithi,in_kaithi
+inkaktoviknumerals,in_kaktovik_numerals
 inkanaextendeda,in_kana_extended_a
 inkanaextendedb,in_kana_extended_b
 inkanasupplement,in_kana_supplement
@@ -276,6 +283,7 @@ inkangxiradicals,in_kangxi_radicals
 inkannada,in_kannada
 inkatakana,in_katakana
 inkatakanaphoneticextensions,in_katakana_phonetic_extensions
+inkawi,in_kawi
 inkayahli,in_kayah_li
 inkharoshthi,in_kharoshthi
 inkhitansmallscript,in_khitan_small_script
@@ -339,6 +347,7 @@ inmyanmar,in_myanmar
 inmyanmarextendeda,in_myanmar_extended_a
 inmyanmarextendedb,in_myanmar_extended_b
 innabataean,in_nabataean
+innagmundari,in_nag_mundari
 innandinagari,in_nandinagari
 innewa,in_newa
 innewtailue,in_new_tai_lue
@@ -457,6 +466,7 @@ joincontrol,join_control
 kaithi,kaithi
 kannada,kannada
 katakana,katakana
+kawi,kawi
 kayahli,kayah_li
 kharoshthi,kharoshthi
 khitansmallscript,khitan_small_script
@@ -503,6 +513,7 @@ mro,mro
 multani,multani
 myanmar,myanmar
 nabataean,nabataean
+nagmundari,nag_mundari
 nandinagari,nandinagari
 newa,newa
 newline,newline

data/lib/regexp_parser/scanner/properties/short.csv

@@ -57,6 +57,7 @@ emod,emoji_modifier
 epres,emoji_presentation
 ethi,ethiopic
 ext,extender
+extpict,extended_pictographic
 geor,georgian
 glag,glagolitic
 gong,gunjala_gondi
@@ -133,6 +134,7 @@ mtei,meetei_mayek
 mult,multani
 mymr,myanmar
 n,number
+nagm,nag_mundari
 nand,nandinagari
 narb,old_north_arabian
 nbat,nabataean

data/lib/regexp_parser/syntax/token/unicode_property.rb

@@ -59,7 +59,7 @@ module Regexp::Syntax
 
       Age_V3_1_0 = %i[age=13.0]
 
-      Age_V3_2_0 = %i[age=14.0]
+      Age_V3_2_0 = %i[age=14.0 age=15.0]
 
       Age = all[:Age_V]
 
@@ -321,6 +321,8 @@ module Regexp::Syntax
 
       Script_V3_2_0 = %i[
         cypro_minoan
+        kawi
+        nag_mundari
         old_uyghur
         tangsa
         toto
@@ -667,11 +669,18 @@ module Regexp::Syntax
 
       UnicodeBlock_V3_2_0 = %i[
         in_arabic_extended_b
+        in_arabic_extended_c
+        in_cjk_unified_ideographs_extension_h
         in_cypro_minoan
+        in_cyrillic_extended_d
+        in_devanagari_extended_a
         in_ethiopic_extended_b
+        in_kaktovik_numerals
         in_kana_extended_b
+        in_kawi
         in_latin_extended_f
         in_latin_extended_g
+        in_nag_mundari
         in_old_uyghur
         in_tangsa
         in_toto
@@ -690,6 +699,10 @@ module Regexp::Syntax
         emoji_presentation
       ]
 
+      Emoji_V2_6_0 = %i[
+        extended_pictographic
+      ]
+
       Emoji = all[:Emoji_V]
 
       V1_9_0 = Category::All + POSIX + all[:V1_9_0]

data/lib/regexp_parser/version.rb

@@ -1,5 +1,5 @@
 class Regexp
   class Parser
-    VERSION = '2.8.0'
+    VERSION = '2.8.1'
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: regexp_parser
 version: !ruby/object:Gem::Version
-  version: 2.8.0
+  version: 2.8.1
 platform: ruby
 authors:
 - Ammar Ali
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-04-17 00:00:00.000000000 Z
+date: 2023-06-10 00:00:00.000000000 Z
 dependencies: []
 description: A library for tokenizing, lexing, and parsing Ruby regular expressions.
 email:
@@ -64,7 +64,6 @@ files:
 - lib/regexp_parser/scanner/errors/premature_end_error.rb
 - lib/regexp_parser/scanner/errors/scanner_error.rb
 - lib/regexp_parser/scanner/errors/validation_error.rb
-- lib/regexp_parser/scanner/mapping.rb
 - lib/regexp_parser/scanner/properties/long.csv
 - lib/regexp_parser/scanner/properties/short.csv
 - lib/regexp_parser/scanner/property.rl
@@ -132,7 +131,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.1
+rubygems_version: 3.4.10
 signing_key:
 specification_version: 4
 summary: Scanner, lexer, parser for ruby's regular expressions

data/lib/regexp_parser/scanner/mapping.rb

@@ -1,89 +0,0 @@
-# mapping for simple cases with a 1:1 relation between text and token
-class Regexp::Scanner
-  MAPPING = {
-    anchor: {
-      '\A' => :bos,
-      '\B' => :nonword_boundary,
-      '\G' => :match_start,
-      '\Z' => :eos_ob_eol,
-      '\b' => :word_boundary,
-      '\z' => :eos,
-    },
-    assertion: {
-      '(?='  => :lookahead,
-      '(?!'  => :nlookahead,
-      '(?<=' => :lookbehind,
-      '(?<!' => :nlookbehind,
-    },
-    conditional: {
-      '(?' => :open,
-    },
-    escape: {
-      '\.'   => :dot,
-      '\|'   => :alternation,
-      '\^'   => :bol,
-      '\$'   => :eol,
-      '\?'   => :zero_or_one,
-      '\*'   => :zero_or_more,
-      '\+'   => :one_or_more,
-      '\('   => :group_open,
-      '\)'   => :group_close,
-      '\{'   => :interval_open,
-      '\}'   => :interval_close,
-      '\['   => :set_open,
-      '\]'   => :set_close,
-      '\\\\' => :backslash,
-      '\a'   => :bell,
-      '\b'   => :backspace,
-      '\e'   => :escape,
-      '\f'   => :form_feed,
-      '\n'   => :newline,
-      '\r'   => :carriage,
-      '\t'   => :tab,
-      '\v'   => :vertical_tab,
-    },
-    group: {
-      '(?:' => :passive,
-      '(?>' => :atomic,
-      '(?~' => :absence,
-    },
-    meta: {
-      '|' => :alternation,
-      '.' => :dot,
-    },
-    quantifier: {
-      '?'  => :zero_or_one,
-      '??' => :zero_or_one_reluctant,
-      '?+' => :zero_or_one_possessive,
-      '*'  => :zero_or_more,
-      '*?' => :zero_or_more_reluctant,
-      '*+' => :zero_or_more_possessive,
-      '+'  => :one_or_more,
-      '+?' => :one_or_more_reluctant,
-      '++' => :one_or_more_possessive,
-    },
-    set: {
-      '['  => :character,
-      '-'  => :range,
-      '&&' => :intersection,
-    },
-    type: {
-      '\d' => :digit,
-      '\D' => :nondigit,
-      '\h' => :hex,
-      '\H' => :nonhex,
-      '\s' => :space,
-      '\S' => :nonspace,
-      '\w' => :word,
-      '\W' => :nonword,
-      '\R' => :linebreak,
-      '\X' => :xgrapheme,
-    }
-  }
-  ANCHOR_MAPPING     = MAPPING[:anchor]
-  ASSERTION_MAPPING  = MAPPING[:assertion]
-  ESCAPE_MAPPING     = MAPPING[:escape]
-  GROUP_MAPPING      = MAPPING[:group]
-  QUANTIFIER_MAPPING = MAPPING[:quantifier]
-  TYPE_MAPPING       = MAPPING[:type]
-end