3 he)@stddlZddlmZddlmZmZmZGdddZeeeeefeefZ GdddZ Gdd d e Z dS) N) filterfalse)ListTupleUnionc@seZdZddZddZdS)_lazyclasspropertycCs||_|j|_|j|_dS)N)fn__doc____name__)selfrr 6/tmp/pip-build-fibhr3ey/pyparsing/pyparsing/unicode.py__init__ sz_lazyclassproperty.__init__csndkrt|td ssz-_lazyclassproperty.__get__..)typehasattrany__mro__rrr )r objrattrnamer )rr __get__s  z_lazyclassproperty.__get__N)r __module__ __qualname__r rr r r r rsrc@seZdZUdZgZeeeedddZ eedddZ eedddZ eedd d Z eedd d Z eedd dZeedddZeddZdS) 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 )returncCsfg}xJ|jD]@}|tkrPx0t|dfD] }|jt|d|ddq(Wq Wtddt|DS)N_rangesrrcss|]}t|VqdS)N)chr)rcr r r r?sz0unicode_set._chars_for_ranges..)rrrextendrangesortedset)rretccZrrr r r _chars_for_ranges7s $zunicode_set._chars_for_rangescCsdjttj|jS)z+all non-whitespace characters in this range)joinrstrisspacer))rr r r printablesAszunicode_set.printablescCsdjttj|jS)z'all alphabetic characters in this ranger*)r+filterr,isalphar))rr r r alphasFszunicode_set.alphascCsdjttj|jS)z*all numeric digit characters in this ranger*)r+r/r,isdigitr))rr r r numsKszunicode_set.numscCs |j|jS)z)all alphanumeric characters in this range)r1r3)rr r r alphanumsPszunicode_set.alphanumscCs$djttttj|jtdBS)zVall characters in this range that are valid identifier characters, plus underscore '_'r*uABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyzªµºÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ_)r+r%r&r/r, isidentifierr))rr r r identcharsUs zunicode_set.identcharscCs4tdd|jD}djt|t|jBtdBS)u all characters in this range that are valid identifier body characters, plus the digits 0-9, and · (Unicode MIDDLE DOT) css|]}d|jr|VqdS)_N)r5)rr!r r r rjsz-unicode_set.identbodychars..r*u 0123456789·)r&r)r+r%r6)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) pyparsingr9r6r8)rr9r r r identifierps zunicode_set.identifierN)r rrrrUnicodeRangeListrrr,r)r.r1r3r4r6r8r;r r r r rs"    rc@s2eZdZUdZdejfgZeGdddeZ GdddeZ GdddeZ Gd d d eZ Gd d d eZ Gd ddeZGdddeZGdddeZGdddeZeZGdddeeeZGdddeZGdddeZGdddeZGdddeZe ZeZeZeZe ZeZeZeZeZ eZ!dS) pyparsing_unicodezF A namespace class for defining common language unicode_sets. c@seZdZUdZdgZedS)z(pyparsing_unicode.BasicMultilingualPlanez,Unicode set for the Basic Multilingual Planer>N)r>r?)r rrrrr<r r r r BasicMultilingualPlanes r@c@seZdZUdZddgZedS) zpyparsing_unicode.Latin1z/Unicode set for Latin-1 Unicode Character Ranger>~N)r>rA)rBrC)r rrrrr<r r r r Latin1s rDc@seZdZUdZdgZedS)zpyparsing_unicode.LatinAz/Unicode set for Latin-A Unicode Character RangeN)rErF)r rrrrr<r r r r LatinAs rGc@seZdZUdZdgZedS)zpyparsing_unicode.LatinBz/Unicode set for Latin-B Unicode Character RangeON)rHrI)r rrrrr<r r r r LatinBs rJc$@s`eZdZUdZd@dAdBdCdDdEdFdGdHdIdJdKdLdMdNdOdPdQdRdSdTdUdVdWdXdYdZd[d\d]d^d_d`dadbg#Zed?S)czpyparsing_unicode.Greekz.Unicode set for Greek Unicode Character RangesBEpwz&*^`fj EHMPWY[]_})!''e@EN)rKrL)rMrN)rOrP)rQrR)rS)rTrU)rVrW)rXrY)rZr[)r\)r])r^r_)r`ra)rbrc)rdre)rfrg)rhri)rj)rk)rl)rmrn)rorp)rqrr)rsrt)rurv)rwrx)ryrz)r{r|)r})r~r)r)rr)r)rr)rr)r rrrrr<r r r r GreeksH rc @s*eZdZUdZddddddddgZedS)zpyparsing_unicode.Cyrillicz0Unicode set for Cyrillic Unicode Character Range/+x--@rt韦./N)rr)rr)r)r)rr)rr)rr)rr)r rrrrr<r r r r Cyrillics rc@s>eZdZUdZd'd(d)d*d+d,d-d.d/d0d1d2d3d4d5d6d7d8gZed&S)9zpyparsing_unicode.Chinesez/Unicode set for Chinese Unicode Character Range....114MNmpoo;@H֦4@ N)rr)rr)rr)rr)rr)rr)rr)rr)rr)rr)rr)rr)rr)rr)rr)rr)rr)rr)r rrrrr<r r r r Chineses& rc@s^eZdZdZGdddeZGdddeZGdddeZeZeZ eZ ej ej ej Z dS) zpyparsing_unicode.Japanesez`Unicode set for Japanese Unicode Character Range, combining Kanji, Hiragana, and Katakana rangesc@seZdZUdZddgZedS) z pyparsing_unicode.Japanese.Kanjiz-Unicode set for Kanji Unicode Character RangeN鿟0?0N)rr)rr)r rrrrr<r r r r Kanjis rc@s(eZdZUdZd ddddddgZed S)z#pyparsing_unicode.Japanese.Hiraganaz0Unicode set for Hiragana Unicode Character RangeA00000pPRN)rr)rr)r)r)r)rr)r)r rrrrr<r r r r Hiraganas rc @s,eZdZUdZdddddddddg ZedS)z#pyparsing_unicode.Japanese.Katakanaz1Unicode set for Katakana Unicode Character Range00001122edgN)rr)rr)rr)rr)rr)r)rr)rr)r)r rrrrr<r r r r Katakanas rN) r rrrrrrrt漢字t カタカナt ひらがなrr r r r Japaneses rc@s8eZdZUdZd d!d"d#d$d%d&d'd(d)d*d+d,d-d.gZedS)/zpyparsing_unicode.Hangulz7Unicode set for Hangul (Korean) Unicode Character Range.0/011122`2{2~2`|N)rr)rr)rr)rr)rr)r)rr)rr)rr)rr)rr)rr)rr)rr)rr)r rrrrr<r r r r Hanguls rc@seZdZdZdS)zpyparsing_unicode.CJKzTUnicode set for combined Chinese, Japanese, and Korean (CJK) Unicode Character RangeN)r rrrr r r r CJK0src@seZdZUdZddgZedS) zpyparsing_unicode.Thaiz,Unicode set for Thai Unicode Character Range:?[N)rr)rr)r rrrrr<r r r r Thai3s rc@s eZdZUdZd d d gZedS) zpyparsing_unicode.Arabicz.Unicode set for Arabic Unicode Character RangeN)rr)rr)rr)r rrrrr<r r r r Arabic:s r c @s,eZdZUdZdddddddddg ZedS)zpyparsing_unicode.Hebrewz.Unicode set for Hebrew Unicode Character Range68<>@ACDFON)r r )r r )rr)rr)rr)r)rr)rr)rr)r rrrrr<r r r r HebrewBs rc@seZdZUdZddgZedS) zpyparsing_unicode.Devanagariz2Unicode set for Devanagari Unicode Character Range  N)rr)rr)r rrrrr<r r r r DevanagariPs r N)"r rrrsys maxunicoderr<rr@rDrGrJrrrrrKoreanrrr rr ZBMPtالعربيةt中文tкириллицаtΕλληνικάtעִברִיתt 日本語t 한국어t ไทยtदेवनागरीr r r r r={s6 ( .r=) r! itertoolsrtypingrrrrintr<rr=r r r r s  \