regexp_parser 2.2.0 → 2.2.1

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

@@ -0,0 +1,242 @@
+# THIS FILE IS AUTO-GENERATED BY `rake props:update` - DO NOT EDIT
+adlm,adlam
+aghb,caucasian_albanian
+ahex,ascii_hex_digit
+arab,arabic
+armi,imperial_aramaic
+armn,armenian
+avst,avestan
+bali,balinese
+bamu,bamum
+bass,bassa_vah
+batk,batak
+beng,bengali
+bhks,bhaiksuki
+bidic,bidi_control
+bopo,bopomofo
+brah,brahmi
+brai,braille
+bugi,buginese
+buhd,buhid
+c,other
+cakm,chakma
+cans,canadian_aboriginal
+cari,carian
+cc,control
+cf,format
+cher,cherokee
+chrs,chorasmian
+ci,case_ignorable
+cn,unassigned
+co,private_use
+combiningmark,mark
+copt,coptic
+cprt,cypriot
+cs,surrogate
+cwcf,changes_when_casefolded
+cwcm,changes_when_casemapped
+cwl,changes_when_lowercased
+cwt,changes_when_titlecased
+cwu,changes_when_uppercased
+cyrl,cyrillic
+dep,deprecated
+deva,devanagari
+di,default_ignorable_code_point
+dia,diacritic
+diak,dives_akuru
+dogr,dogra
+dsrt,deseret
+dupl,duployan
+ebase,emoji_modifier_base
+ecomp,emoji_component
+egyp,egyptian_hieroglyphs
+elba,elbasan
+elym,elymaic
+emod,emoji_modifier
+epres,emoji_presentation
+ethi,ethiopic
+ext,extender
+geor,georgian
+glag,glagolitic
+gong,gunjala_gondi
+gonm,masaram_gondi
+goth,gothic
+gran,grantha
+grbase,grapheme_base
+grek,greek
+grext,grapheme_extend
+grlink,grapheme_link
+gujr,gujarati
+guru,gurmukhi
+hang,hangul
+hani,han
+hano,hanunoo
+hatr,hatran
+hebr,hebrew
+hex,hex_digit
+hira,hiragana
+hluw,anatolian_hieroglyphs
+hmng,pahawh_hmong
+hmnp,nyiakeng_puachue_hmong
+hung,old_hungarian
+idc,id_continue
+ideo,ideographic
+ids,id_start
+idsb,ids_binary_operator
+idst,ids_trinary_operator
+ital,old_italic
+java,javanese
+joinc,join_control
+kali,kayah_li
+kana,katakana
+khar,kharoshthi
+khmr,khmer
+khoj,khojki
+kits,khitan_small_script
+knda,kannada
+kthi,kaithi
+l,letter
+lana,tai_tham
+laoo,lao
+latn,latin
+lc,cased_letter
+lepc,lepcha
+limb,limbu
+lina,linear_a
+linb,linear_b
+ll,lowercase_letter
+lm,modifier_letter
+lo,other_letter
+loe,logical_order_exception
+lt,titlecase_letter
+lu,uppercase_letter
+lyci,lycian
+lydi,lydian
+m,mark
+mahj,mahajani
+maka,makasar
+mand,mandaic
+mani,manichaean
+marc,marchen
+mc,spacing_mark
+me,enclosing_mark
+medf,medefaidrin
+mend,mende_kikakui
+merc,meroitic_cursive
+mero,meroitic_hieroglyphs
+mlym,malayalam
+mn,nonspacing_mark
+mong,mongolian
+mroo,mro
+mtei,meetei_mayek
+mult,multani
+mymr,myanmar
+n,number
+nand,nandinagari
+narb,old_north_arabian
+nbat,nabataean
+nchar,noncharacter_code_point
+nd,decimal_number
+nkoo,nko
+nl,letter_number
+no,other_number
+nshu,nushu
+oalpha,other_alphabetic
+odi,other_default_ignorable_code_point
+ogam,ogham
+ogrext,other_grapheme_extend
+oidc,other_id_continue
+oids,other_id_start
+olck,ol_chiki
+olower,other_lowercase
+omath,other_math
+orkh,old_turkic
+orya,oriya
+osge,osage
+osma,osmanya
+oupper,other_uppercase
+p,punctuation
+palm,palmyrene
+patsyn,pattern_syntax
+patws,pattern_white_space
+pauc,pau_cin_hau
+pc,connector_punctuation
+pcm,prepended_concatenation_mark
+pd,dash_punctuation
+pe,close_punctuation
+perm,old_permic
+pf,final_punctuation
+phag,phags_pa
+phli,inscriptional_pahlavi
+phlp,psalter_pahlavi
+phnx,phoenician
+pi,initial_punctuation
+plrd,miao
+po,other_punctuation
+prti,inscriptional_parthian
+ps,open_punctuation
+qaac,coptic
+qaai,inherited
+qmark,quotation_mark
+ri,regional_indicator
+rjng,rejang
+rohg,hanifi_rohingya
+runr,runic
+s,symbol
+samr,samaritan
+sarb,old_south_arabian
+saur,saurashtra
+sc,currency_symbol
+sd,soft_dotted
+sgnw,signwriting
+shaw,shavian
+shrd,sharada
+sidd,siddham
+sind,khudawadi
+sinh,sinhala
+sk,modifier_symbol
+sm,math_symbol
+so,other_symbol
+sogd,sogdian
+sogo,old_sogdian
+sora,sora_sompeng
+soyo,soyombo
+sterm,sentence_terminal
+sund,sundanese
+sylo,syloti_nagri
+syrc,syriac
+tagb,tagbanwa
+takr,takri
+tale,tai_le
+talu,new_tai_lue
+taml,tamil
+tang,tangut
+tavt,tai_viet
+telu,telugu
+term,terminal_punctuation
+tfng,tifinagh
+tglg,tagalog
+thaa,thaana
+tibt,tibetan
+tirh,tirhuta
+ugar,ugaritic
+uideo,unified_ideograph
+vaii,vai
+vs,variation_selector
+wara,warang_citi
+wcho,wancho
+wspace,white_space
+xidc,xid_continue
+xids,xid_start
+xpeo,old_persian
+xsux,cuneiform
+yezi,yezidi
+yiii,yi
+z,separator
+zanb,zanabazar_square
+zinh,inherited
+zl,line_separator
+zp,paragraph_separator
+zs,space_separator
+zyyy,common
+zzzz,unknown

data/lib/regexp_parser/scanner/scanner.rl

@@ -759,14 +759,16 @@ class Regexp::Scanner
   end
 
   # lazy-load property maps when first needed
-  require 'yaml'
-
   def self.short_prop_map
-    @short_prop_map ||= YAML.load_file("#{__dir__}/scanner/properties/short.yml")
+    @short_prop_map ||= parse_prop_map('short')
   end
 
   def self.long_prop_map
-    @long_prop_map ||= YAML.load_file("#{__dir__}/scanner/properties/long.yml")
+    @long_prop_map ||= parse_prop_map('long')
+  end
+
+  def self.parse_prop_map(name)
+    File.read("#{__dir__}/scanner/properties/#{name}.csv").scan(/(.+),(.+)/).to_h
   end
 
   # Emits an array with the details of the scanned pattern