-iO dZddlZddlmZddlZddlZddlmZddl m Z ddl m Z idddddd d d d d ddddddddddddddddddd d!d"d#d$d%d&d'd(d)d*d+d,d-d.Z Gd/d0Zd1Zd2Zd3Zd4Zd5Zd6ZdS)7zX Arabic unknown word stemmer. Unkown words are stemmed as nouns with another dictionary N)stem_noun_const)wordcaseid vocalized unvocalizedwordtyperoot normalizedstampedoriginalmankous feminable number dualable masculin_plural feminin_plural broken_plural mamnou3_sarfrelative)w_suffix hm_suffix kal_prefix ha_suffixk_suffixannex definitionnotec8eZdZdZd dZdZdZdZdZdZ d S) UnknownStemmerzd Arabic unknown word stemmer. Unkown words are stemmed as nouns with another dictionary Fctj|_|jt j|jt j|j t j |j t j |j t j|jt j|jt j|jt jtj|_|jt j|jt j|j t j|j t j|j t j|jt j|jt j|jt jt=jdt<j |_!|j!|_"i|_#i|_$||_%dS)Nwordfreq)& tashaphynestemmingArabicLightStemmer comp_stemmerset_infix_letterssnconstCOMP_INFIX_LETTERSset_prefix_lettersCOMP_PREFIX_LETTERSset_suffix_lettersCOMP_SUFFIX_LETTERSset_max_prefix_lengthCOMP_MAX_PREFIXset_max_suffix_lengthCOMP_MAX_SUFFIXset_min_stem_length COMP_MIN_STEMset_prefix_listCOMP_PREFIX_LISTset_suffix_listCOMP_SUFFIX_LIST conj_stemmerCONJ_INFIX_LETTERSCONJ_PREFIX_LETTERSCONJ_SUFFIX_LETTERSCONJ_MAX_PREFIXCONJ_MAX_SUFFIX CONJ_MIN_STEMCONJ_PREFIX_LISTCONJ_SUFFIX_LISTwordfreqdictionaryclassWordFreqDictionaryWORDFREQ_DICTIONARY_INDEXr9noun_dictionary noun_cachenoun_vocalize_cachedebugselfr^s R/var/www/html/speakWrite/venv/lib/python3.11/site-packages/qalsadi/stem_unknown.py__init__zUnknownStemmer.__init__Es&/BBDD ++G,FGGG ,,W-HIII ,,W-HIII //0GHHH //0GHHH --g.CDDD ))'*BCCC ))'*BCCC'/BBDD ++G,FGGG ,,W-HIII ,,W-HIII //0GHHH //0GHHH --g.CDDD ))'*BCCC ))'*BCCC/B /I    $}#%  c g}|}|g}|tjdkrJ||tjtjtjz|D]}|j|}t||tj }|D]}|d|d}||d|d}||dd}|j r9tdd|||gd|g} |dkr|tjr#| |tjzn|tjr#| |tjzn|tjr+| |ddtjznI|tjr*| |ddtjzg} | D]}| |||||z } || z }Ð|S) z Analyze word morphologically as noun @param noun: the input noun. @type noun: unicode. @return: list of dictionaries of analyzed words with tags. @rtype: list. rNr -utf8)stripfindaraby ALEF_MADDAappendreplaceALEF_HAMZA_ABOVEr=segment verify_affixr?COMP_NOUN_AFFIXESr^printjoinencodeendswithYEHNOONWAWALEF ALEF_MAKSURATEH TEH_MARBUTAsteming_second_level) r`noundetailed_result noun_list list_seg_compseg procleticstemencletic list_stemresults ra stemming_nounzUnknownStemmer.stemming_nounisyzz||F 99U% & &! + +    $e&WXXM$ * * 3q6N CFSVO,A>:V$)T8)D E E L LV T TUUU"F r>>}}UY//H!(( ):;;;;uy11H!(( ):;;;;uz22H!((crcU5G)GHHHHuy11H!((crcU5F)FGGG%YYDd77dIxXXXFF6)5 *6rccBg}|j|}t||tj}g}|D]}|d|d} ||d|d} ||dd} tj| dD].} d| | d} t ||| r|| /|}|D]]}|d} |d} |d } tj | } t| | | }g}|D]}| |}||z }|D]}|d}d }|d }| ||| | |}|tj||| | |f| ||||d tj|d tj|d ztj| d zd d|g|dd |dd _|S)a% Analyze word morphologically by stemming the conjugation affixes. @param noun: the input noun. @type noun: unicode. @param noun2: the noun stemed from syntaxic affixes. @type noun2: unicode. @param procletic: the syntaxic prefixe extracted in the fisrt stage. @type procletic: unicode. @param encletic: the syntaxic suffixe extracted in the fisrt stage. @type encletic: unicode. @return: list of dictionaries of analyzed words with tags. @rtype: list. Nrrrrh)prefixsuffixrrrr word_type:tagsNounfreq) wordaffixrrlemmar semivocalizedrtyper originaltagssyntax)rOrqrrr?NOMINAL_CONJUGATION_AFFIXCONJ_SUFFIX_LIST_TAGSis_compatible_proaffix_affixrnr: normalizenormalize_hamzaget_stem_variants lookup_dictvocalizerWordCaseruCOMP_PREFIX_LIST_TAGSCOMP_SUFFIX_LIST_TAGS)r`rnoun2rrr list_seg_conjlist_seg_conj_vocseg_conj prefix_conj stem_conj suffix_conjvocalized_suffix seg_conj_vocpossible_noun_listinfnoun_form_listinfnouninfnoun_foundlist noun_tuple original_tagsr rs rarz#UnknownStemmer.steming_second_levels)11%88 $ ='"C  % ; ;H (1+ .KhqkHQK78I .K%,$A+$N% ; ; !.%   0 8EUVV;&,,\::: ;* %6 6 H"8,K (I"8,K#,<{KAN 5i@MaP   9 % %9D ||EJ ej(@AA||E. e>P0PQQvg +U[$??vh,b$77   ej594 5 5 3%,tAw:O:O 377DGU\48<==D%%ek22 3 -crc 2 f--h//'j(CC GG]FD*lSTT (1 %rcN)F) __name__ __module__ __qualname____doc__rbrrrrrrrcrar7r7?s """"H444leeeN   77777rcr7c|dkr|dkrdStj|d}tj|d}tj|d}d|vr d|vrd|vrdSd|vrd|vrdSd|vrd|vrdSd|vrd |vrdSd |vrd |vrdSdS) a` Verify if proaffixes (sytaxic affixes) are compatable with affixes (conjugation) @param procletic: first level prefix. @type procletic: unicode. @param encletic: first level suffix. @type encletic: unicode. @param suffix: second level suffix. @type suffix: unicode. @return: compatible. @rtype: True/False. rhTru تعريفuمضافu منسوبF تنوينu لايضافuجرu مجرور)r?rrr)rrrprocletic_tags encletic_tags suffix_tagss rarrTsB8r>>t29=fEN1(;FCM/7?K&& + % %  + +u~%%,+*E*Eu]""|{'B'Bu]""~'D'Du L $C$Cu 4rccttj|}|tjdkr=t |dkr*t jtjtj|}|dkr=|ddtjtj tj fvr|tj vrd}|S)u Get the suffix variant to be joined to the word. For example: word = مدرس, suffix = ة, encletic = ي. The suffix is convert to Teh. @param word: word found in dictionary. @type word: unicode. @param suffix: second level suffix. @type suffix: unicode. @param enclitic: first level suffix. @type enclitic: unicode. @return: variant of suffix. @rtype: unicode. rrhriN) rlstrip_tashkeelrkr~lenrrr}r|rxr{r)rrr enclitic_nms rarrxs&x00K {{5$%%**s;/?/?!/C/C)59f==r I%,eiD D D em # # Mrcc|}tj|}|ddtjvr |dd}|tjrp|tjtjztjtjztjtjtjztjzfvr |dd}n|tjr|dkr|ddtjz}nn|tjr|dkr|ddtjz}n0|tj r|dkr | tj r|ddtj z}n| tj r|ddtjz}n|tjtj zs9|tjtjztj zr6| tjr|ddtjz}|S)uW Get the word variant to be joined to the suffix. For example: word = ةمدرس, suffix = ي. The word is converted to مدرست. @param word: word found in dictionary. @type word: unicode. @param suffix: suffix ( firts or second level). @type suffix: unicode. @return: variant of word. @rtype: unicode. riNrh)rlrrrwr~r{r}rxr|HAMZA startswithDAMMA WAW_HAMZAKASRA YEH_HAMZArFATHATAN)rr word_stem suffix_nms rarrs I$V,,I~&&crcN %+,,9 UY E%%  EJ* ?22 crcN   E- . . 99??crcNUY.   E. / / 9IOOcrcNUY.   EK ( ( 9Y"__   U[ ) ) 9!#2#8II   u{ + + 9!#2#8II   uy5;6 7 7 9!!%)ek"9EK"GHH 9// 9"#2#8I rcct|g}tj|}tj|}|}|tjtjztjtjztjtjtjztjzfvr$|tjz}|||dks:|tjtjzks|tj tjzkr$|tjz}||| tjr,|ddtj z}|||}|S)u Generate the Noun stem variants according to the affixes. For example مدرستي = >مدرست+ي = > مدرسة +ي. Return a list of possible cases. @param stem: the input stem. @type stem: unicode. @param prefix: prefixe. @type prefix: unicode. @param suffix: suffixe. @type suffix: unicode. @return: list of stem variants. @rtype: list of unicode. rhNri) setrlrr{r}rxr~addryrzrwr|)rrrprefix_possible_noun_listr possible_nounvalidated_lists rarrs9"!$TF   !& ) )F  !& ) )F2  UY E%%  EJ*  u00 }---" UY+ + + UY+ + +uy( }--- }}UY.SbS E$66 }---'N rcc$fd|DS)a@ Verify possible affixes in the resulted segments according to the given affixes list. @param word: the input word. @type word: unicode. @param list_seg: list of word segments indexes (numbers). @type list_seg: list of pairs. @return: list of acceped segments. @rtype: list of pairs. c~g|]9}dd|d|ddgv7|:S)rfNrr)ru).0s affix_listrs ra z verify_affix..sL X X X!388T&AaD&\4!<,H#I#IZ#W#WA#W#W#Wrcr)rlist_segrs` `rarrrrs$ Y X X X Xx X X XXrcc*d|vr|ddkrdSdS)aF Test if the given word from dictionary is compabilbe with affixes tags. @param noun_tuple: the input word attributes given from dictionary. @type noun_tuple: dict. @param affix_tags: a list of tags given by affixes. @type affix_tags:list. @return: if the tags are compatible. @rtype: Boolean. rr noun_propFTr)r affix_tagss ra validate_tagsrs(z!!j&=&L&Lu 4rc)rrpyarabic.arabyrltashaphyne.stemmingr:tashaphyne.normalize arramooz.wordfreqdictionaryclassrXrhrr?rNOUN_DICTIONARY_INDEXr7rrrrrrrrrcrars CBBBBB)(((((!1   A  ! qq brbR B!"#$  3:RRRRRRRRj!!!H6%%%P***Z Y Y Y"rc