U Ev f)@stddlZddlmZddlmZmZmZGdddZeeeeefeefZ GdddZ Gdd d e Z dS) N) filterfalse)ListTupleUnionc@seZdZddZddZdS)_lazyclasspropertycCs||_|j|_|j|_dS)N)fn__doc____name__)selfrr 5/tmp/pip-unpacked-wheel-d514z_mh/pyparsing/unicode.py__init__ sz_lazyclassproperty.__init__csldkrt|tdr:tfddjddDr@i_|jj}|jkrb|j|<j|S)N_internc3s |]}jt|dgkVqdS)rN)rgetattr).0 superclassclsr r sz-_lazyclassproperty.__get__..)typehasattrany__mro__rrr )r objrattrnamer rr __get__s  z_lazyclassproperty.__get__N)r __module__ __qualname__r rr r r r rsrc@s~eZdZUdZgZeed<eddZeddZ eddZ ed d Z ed d Z ed dZ eddZeddZdS) unicode_seta A set of Unicode characters, for language-specific strings for ``alphas``, ``nums``, ``alphanums``, and ``printables``. A unicode_set is defined by a list of ranges in the Unicode character set, in a class attribute ``_ranges``. Ranges can be specified using 2-tuples or a 1-tuple, such as:: _ranges = [ (0x0020, 0x007e), (0x00a0, 0x00ff), (0x0100,), ] Ranges are left- and right-inclusive. A 1-tuple of (x,) is treated as (x, x). A unicode set can also be defined using multiple inheritance of other unicode sets:: class CJK(Chinese, Japanese, Korean): pass _rangescCs`g}|jD]>}|tkrqJt|ddD] }|t|d|ddq&q ddtt|DS)Nr r rrcSsg|] }t|qSr )chrrcr r r ?sz1unicode_set._chars_for_ranges..)rrrextendrangesortedset)rretccrrr r r _chars_for_ranges7s  zunicode_set._chars_for_rangescCsdttj|jS)z+all non-whitespace characters in this range)joinrstrisspacer-rr r r printablesAszunicode_set.printablescCsdttj|jS)z'all alphabetic characters in this ranger.)r/filterr0isalphar-rr r r alphasFszunicode_set.alphascCsdttj|jS)z*all numeric digit characters in this ranger.)r/r3r0isdigitr-rr r r numsKszunicode_set.numscCs |j|jS)z)all alphanumeric characters in this range)r5r7rr r r alphanumsPszunicode_set.alphanumsc Cs.dttdttj|jdddS)zVall characters in this range that are valid identifier characters, plus underscore '_'r.u:ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyzªµºu|ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ_)r/r(r)r3r0 isidentifierr-rr r r identcharsUszunicode_set.identcharscCs0tdd|jD}dt|t|jdBS)u all characters in this range that are valid identifier body characters, plus the digits 0-9, and · (Unicode MIDDLE DOT) css|]}d|r|VqdS)r9N)r:r#r r r ris z-unicode_set.identbodychars..r.u 0123456789·)r)r-r/r(r;)rZidentifier_charsr r r identbodycharscszunicode_set.identbodycharscCsddlm}||j|jS)z a pyparsing Word expression for an identifier using this range's definitions for identchars and identbodychars r)Word) pyparsingr=r;r<)rr=r r r identifierns zunicode_set.identifierN)r rrrr UnicodeRangeList__annotations__rr-r2r5r7r8r;r<r?r r r r rs$         rc@s6eZdZUdZdejfgZeed<Gddde Z Gddde Z Gdd d e Z Gd d d e Z Gd d d e ZGddde ZGddde ZGddde ZGddde ZeZGdddeeeZGddde ZGddde ZGddde ZGddde Ze ZeZeZeZeZeZeZeZ eZ!eZ"d S)!pyparsing_unicodezF A namespace class for defining common language unicode_sets. r c@s eZdZUdZdgZeed<dS)z(pyparsing_unicode.BasicMultilingualPlanez,Unicode set for the Basic Multilingual Plane)rCir Nr rrrr r@rAr r r r BasicMultilingualPlanes rEc@s"eZdZUdZddgZeed<dS)zpyparsing_unicode.Latin1z/Unicode set for Latin-1 Unicode Character Range)rC~)r NrDr r r r Latin1s rIc@s eZdZUdZdgZeed<dS)zpyparsing_unicode.LatinAz/Unicode set for Latin-A Unicode Character Range)ir NrDr r r r LatinAs rKc@s eZdZUdZdgZeed<dS)zpyparsing_unicode.LatinBz/Unicode set for Latin-B Unicode Character Range)iiOr NrDr r r r LatinBs rLc#@sdeZdZUdZdddddddd d d d d ddddddddddddddddddd d!d"d#d$g#Zeed%<d&S)'zpyparsing_unicode.Greekz.Unicode set for Greek Unicode Character Ranges)iBiE)ipiw)izi)ii)i)ii)ii)ii)i&i*)i^)i`)ifij)ii)ii)i iE)iHiM)iPiW)iY)i[)i])i_i})ii)ii)ii)ii)ii)ii)ii)i)!)i'i')ie)i@i)i)iiE)iir NrDr r r r GreeksJ rMc@s.eZdZUdZdddddddd gZeed <d S) zpyparsing_unicode.Cyrillicz0Unicode set for Cyrillic Unicode Character Range)ii/)ii)i+)ix)i-i-)i@ir)iti)i.i/r NrDr r r r Cyrillics rNc@sBeZdZUdZdddddddd d d d d ddddddgZeed<dS)zpyparsing_unicode.Chinesez/Unicode set for Chinese Unicode Character Range)i.i.)i.i.)i1i1)i4iM)Ni)ii)iim)ipi)ioio)ii)ii;)i@iH)ii֦)ii4)i@i)i i)ii)iir NrDr r r r Chineses( rPc@s^eZdZdZGdddeZGdddeZGdddeZeZeZ eZ ej ej ej Z dS) zpyparsing_unicode.Japanesez`Unicode set for Japanese Unicode Character Range, combining Kanji, Hiragana, and Katakana rangesc@s"eZdZUdZddgZeed<dS)z pyparsing_unicode.Japanese.Kanjiz-Unicode set for Kanji Unicode Character Range)rOi)i0i?0r NrDr r r r Kanjis rQc@s,eZdZUdZdddddddgZeed <d S) z#pyparsing_unicode.Japanese.Hiraganaz0Unicode set for Hiragana Unicode Character Range)iA0i0)00)i0)ip)i)iPiR)ir NrDr r r r Hiraganas rTc @s0eZdZUdZdddddddd d g Zeed <d S) z#pyparsing_unicode.Japanese.Katakanaz1Unicode set for Katakana Unicode Character Range)rRi0)rSi0)i1i1)i2i2)iei)i)idig)ii)ir NrDr r r r Katakanas rUN) r rrrrrQrTrU漢字 カタカナ ひらがなr r r r r Japaneses rYc@s<eZdZUdZdddddddd d d d d dddgZeed<dS)zpyparsing_unicode.Hangulz7Unicode set for Hangul (Korean) Unicode Character Range)ii)i.0i/0)i11i1)i2i2)i`2i{2)i~2)i`i|)ii)ii)ii)ii)ii)ii)ii)iir NrDr r r r Hanguls" rZc@seZdZdZdS)zpyparsing_unicode.CJKzTUnicode set for combined Chinese, Japanese, and Korean (CJK) Unicode Character RangeN)r rrrr r r r CJK.sr[c@s"eZdZUdZddgZeed<dS)zpyparsing_unicode.Thaiz,Unicode set for Thai Unicode Character Range)ii:)i?i[r NrDr r r r Thai1s r\c@s$eZdZUdZdddgZeed<dS)zpyparsing_unicode.Arabicz.Unicode set for Arabic Unicode Character Range)ii)ii)iir NrDr r r r Arabic8s r]c @s0eZdZUdZdddddddd d g Zeed <d S) zpyparsing_unicode.Hebrewz.Unicode set for Hebrew Unicode Character Range)ii)ii)ii)ii6)i8i<)i>)i@iA)iCiD)iFiOr NrDr r r r Hebrew@s r^c@s"eZdZUdZddgZeed<dS)zpyparsing_unicode.Devanagariz2Unicode set for Devanagari Unicode Character Range)i i )iir NrDr r r r DevanagariNs r_N)#r rrrsys maxunicoder r@rArrErIrKrLrMrNrPrYrZKoreanr[r\r]r^r_ZBMPالعربية中文кириллицаΕλληνικάעִברִית 日本語 한국어 ไทยदेवनागरीr r r r rBys8  ( .rB) r` itertoolsrtypingrrrrintr@rrBr r r r s  Z