o
    iP                     @   s  d dl mZmZmZmZmZmZmZmZm	Z	m
Z
mZ dZdd ZeeZg de
 e e e e	 Ze
e e e	 dddd	d
dddddjeddjeddjededdjeddddddddg Zee	 dd d!d"d#d$d%d&d'jeed(d)jed*d+jeed,d-jed*g ZeZeZeZd.S )/   )ALPHAALPHA_LOWERALPHA_UPPERCONCAT_QUOTESCURRENCYHYPHENSLIST_CURRENCYLIST_ELLIPSES
LIST_ICONS
LIST_PUNCTLIST_QUOTESuk  km km² km³ m m² m³ dm dm² dm³ cm cm² cm³ mm mm² mm³ ha µm nm yd in ft kg g mg µg t lb oz m/s km/h kmh mph hPa Pa mbar mb MB kb KB gb GB tb TB T G M K км км² км³ м м² м³ дм дм² дм³ см см² см³ мм мм² мм³ нм кг г мг м/с км/ч кПа Па мбар Кб КБ кб Мб МБ мб Гб ГБ гб Тб ТБ тбc                 C   s   |   ddS )N |)stripreplace)char r   M/home/ubuntu/.local/lib/python3.10/site-packages/spacy/lang/el/punctuation.pymerge_chars   s   r   )z''   §%=z	\+[0-9]+%z\'([0-9]){2}([\-]\'([0-9]){2})*z\-([0-9]){1,9}\.([0-9]){1,9}u)   \'([Α-Ωα-ωίϊΐόάέύϋΰήώ]+)\'u+   ([Α-Ωα-ωίϊΐόάέύϋΰήώ]){1,3}\'zIhttp://www.[A-Za-z]+\-[A-Za-z]+(\.[A-Za-z]+)+(\/[A-Za-z]+)*(\.[A-Za-z]+)*u+   [ΈΆΊΑ-Ωα-ωίϊΐόάέύϋΰήώ]+\*z\$([0-9])+([\,\.]([0-9])+){0,1}z(?<=[0-9])\+z
([0-9])+\'z([A-Za-z])?\'z^([0-9]){1,2}\.z ([0-9]){1,2}\.z([0-9]){1}\) z^([0-9]){1}\)$u   (?<=°[FfCcKk])\.z
([0-9])+\&z(?<=[0-9])(?:{c}))cz(?<=[0-9])(?:{u}))uz(?<=[0-9{al}{e}(?:{q})])\.u   ²\-\+)aleqz(?<=[{au}][{au}])\.)auu)   (?<=[Α-Ωα-ωίϊΐόάέύϋΰήώ])\-u)   (?<=[Α-Ωα-ωίϊΐόάέύϋΰήώ])\.u   ^[Α-Ω]{1}\.u   \ [Α-Ω]{1}\.u_   [ΈΆΊΑΌ-Ωα-ωίϊΐόάέύϋΰήώ]+([\-]([ΈΆΊΑΌ-Ωα-ωίϊΐόάέύϋΰήώ]+))+z
([0-9]+)mgz([0-9]+)\.([0-9]+)mz(?<=[0-9])[+\/\-\*^](?=[0-9])z%([a-zA-Z]+)\/([a-zA-Z]+)\/([a-zA-Z]+)z$([0-9])+(\.([0-9]+))*([\-]([0-9])+)+z*([0-9])+[,]([0-9])+[\-]([0-9])+[,]([0-9])+u   ([0-9])+[ης]+([\-]([0-9])+)+z3([0-9]){1,4}[\/]([0-9]){1,2}([\/]([0-9]){0,4}){0,1}z-[A-Za-z]+\@[A-Za-z]+(\-[A-Za-z]+)*\.[A-Za-z]+z([a-zA-Z]+)(\-([a-zA-Z]+))+z(?<=[{al}])\.(?=[{au}]))r   r   z(?<=[{a}]),(?=[{a}]))az(?<=[{a}])(?:{h})(?=[{a}]))r   hz(?<=[{a}])[:<>=/](?=[{a}])N)char_classesr   r   r   r   r   r   r   r	   r
   r   r   _unitsr   UNITS	_prefixesformat	_suffixes_infixesTOKENIZER_PREFIXESTOKENIZER_SUFFIXESTOKENIZER_INFIXESr   r   r   r   <module>   s   4 


!

