-iVdZddlmZddlmZddlmZddlmZdZ dZ d Z Gd d Z e d kr ed dSdS)zQ stemNode represents the regrouped data resulted from the morpholocigal analysis )CounterN)WordCase) StemmedWordc |dvS)Nu$!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~،؟words N/var/www/html/speakWrite/venv/lib/python3.11/site-packages/qalsadi/stemnode.pyispunctr s ; ;;cHtt||jS)N)key)maxsetcount)Lists r most_frequent2rs s4yydj ) ) ))r c|tt|}|dddS)Nrr)rsorted most_common)roccurence_counts r most_frequentr"s3fTll++O  & &q ) )! ,Q //r ceZdZdZd.dZdZdZdZdZdZd Z d Z d Z d Z d Z dZdZdZdZdZdZ d/dZd0dZdZdZdZdZdZdZdZdZdZd Zd!Z d"Z!d#Z"d$Z#d%Z$d&Z%d'Z&d(Z'd)Z(d*Z)d+Z*d,Z+d-S)1StemNodez] stemNode represents the regrouped data resulted from the morpholocigal analysis Fc.||_t||_g}|D]O}t|tr#|t |:||P|}d|_i|_i|_ g|_ |rPd|D|_ tt|j |_ |j g|_|rPd|D|_tt|j|_|j g|_|rPd|D|_tt|j|_|j g|_|rPd|D|_tt|j|_|j i|_d|_d|_gggggd|_ggggd|_ggggd|_g|_g|_gggggggd |_i|_i|_i|_i|_tt=t||_|r|d  |_tC|D]8\}}|"|jvr3|j|"|n|g|j|"<|jd |#|$rR|jd ||jd |#|%rR|jd ||jd |#|&rR|jd||jd|#|'rR|jd||jd|#|(r|j|n|j||jr!tS|jd rd|_|*r|+r"|jd||,r"|jd|,|-r |jd|b|+r"|jd||,r"|jd||-r"|jd||.r |jd|:t|jd t|jd t|jdt|jdd|_tt|jd |jd <|jD]{tt|j|j<|jr"fd|jD|j<Zfd|jD|j<|dS)zJ Create the stemNode from a list of StemmedSynword cases c6g|]}|Sr) get_vocalized.0cases r z%StemNode.__init__..Ks$JJJt1133JJJr cfg|].}|dz|z/S):)get_tagsget_typer s r r#z%StemNode.__init__..Qs2WWWT3.@WWWr c6g|]}|Sr) get_affixr s r r#z%StemNode.__init__..Xs"CCCDNN,,CCCr c6g|]}|Sr)get_rootr s r r#z%StemNode.__init__.._s @@@d$--//@@@r F)verbnounpounctstopwordall)r,r-r.r/)mansoubmarfou3majrourmajzoumtanwin_mansoubtanwin_marfou3tanwin_majrourrr0r,r-r/r.Tr5r6r7r1r2r3r4)r,r-r/r.cg|]}|Srrr!ltype_keys r r#z%StemNode.__init__..s(V(V(VqX(V(V(V(Vr c<g|]}tj|Srarabystrip_tashkeelr9s r r#z%StemNode.__init__..s9)))01h)(++)))r N)/vocalized_lemmalen case_count isinstancerappendrr previous_nodes next_nodes vocalizedslistrsorttagsaffixesroots originalsguessed_type_tag break_endlemmas word_typerbreaks non_breaks syntax_mark syn_previous syn_nexts sem_previous sem_nextsrangechosen_indexesget_word enumerate get_original get_lemmais_verbis_noun is_stopword is_pounctis_breakr is_tanwin is_mansoub is_marfou3 is_majrour is_majzoum)self case_listr@ tmp_case_listr"idxr;s @r __init__zStemNode.__init__0s /i..  + +D$)) +$$[%6%67777$$T****!     #JJ JJJDO"3t#7#788DO O " " "  WWYWWWDIS^^,,DI INN     CCCCCDLDL 1 122DL L       @@i@@@DJc$*oo..DJ JOO   !#                  #5Y#8#899  0!! --//DI"9--0 <0 >+;+;<<<||~~ =v&--c222 F#**4>>+;+;<<<!! Az*11#666 J'..t~~/?/?@@@~~ ?x(//444 H%,,T^^-=-=>>>}} , ""3''''&&s+++y &WTYq\22 &!%~~ <??$$C$%56==cBBBB__&&C$%56==cBBBB__&&C$%56==cBBB??$$<$Y/66s;;;;__&&<$Y/66s;;;;__&&<$Y/66s;;;;__&&<$Y/66s;;;v.//v.//DN:677$.233   "#dk%&8"9"9:: E   H$(T[-B)C)C$D$DDK !# (V(V(V(VDK4I(V(V(V H%%))))59[5J))) H%%   r c||_dS)zz Set the case count. @param count: the number of stemmed word cases @tyep count: integer NrBrirs r set_case_countzStemNode.set_case_counts  r c|jS)zu get the case count. @return: the number of stemmed word cases @tyep count: integer roris r get_case_countzStemNode.get_case_counts r c||_dS)zk Set the guessed type tag. @param tag: guessed type tag @type tag: unicode NrN)ritags r set_guessed_type_tagzStemNode.set_guessed_type_tags !$r c|jS)ze get the guessed type tag. @return: guessed type tag @rtype: unicode rvrss r get_guessed_type_tagzStemNode.get_guessed_type_tag $$r c|jS)zi get the guessed type tag. @return: guessed type tag @rtype tag: unicode rvrss r rtzStemNode.get_case_countr{r c||jd<dS)z Set the verb count. @param count: the number of stemmed word cases as verbs @tyep count: integer r,Nrrps r set_verb_countzStemNode.set_verb_count  # 6r c|jdS)z} get the verb count. @return: the number of stemmed word cases as verbs @tyep count: integer r,r~rss r get_verb_countzStemNode.get_verb_count( z&!!r c||jd<dS)z Set the noun count. @param count: the number of stemmed word cases as nouns @tyep count: integer r-Nr~rps r set_noun_countzStemNode.set_noun_count0rr c|jdS)z} get the noun count. @return: the number of stemmed word cases as nouns @tyep count: integer r-r~rss r get_noun_countzStemNode.get_noun_count8rr c||jd<dS)z Set the stopword count. @param count: the number of stemmed word cases as stopwords @tyep count: integer r/Nr~rps r set_stopword_countzStemNode.set_stopword_count@s "' :r c|jdS)z get the stopword count. @return: the number of stemmed word cases as stopwords @tyep count: integer r/r~rss r get_stopword_countzStemNode.get_stopword_countHs z*%%r c|jS)zr Get the input word given by user @return: the given word. @rtype: unicode string r rss r r[zStemNode.get_wordP yr c||_dS)z Set the input word given by user @param newword: the new given word. @type newword: unicode string Nr )rinewwords r set_wordzStemNode.set_wordZs  r c*t|jS)v Get the root forms of the input word @return: the given root. @rtype: unicode string )rHrLrss r get_rootszStemNode.get_rootsbsDJr c.|jr |jdSdS)rrr)rLrss r r+zStemNode.get_rootls : !:a= rr cNt|jS)z~ Get the original forms of the input word @return: the given original. @rtype: unicode string )rHrMkeysrss r r]zStemNode.get_originalxs DN''))***r rc|j||jdg}|js d|D}tt |}|S)zy Get all lemmas of the input word @return: the given lemmas list. @rtype: unicode string r0c6g|]}tj|Srr=)r!r:s r r#z'StemNode.get_lemmas..s#>>>!e*1-->>>r )rPgetr@rHr)riwordtyperPs r get_lemmaszStemNode.get_lemmass_$+//%*C*CDD# ?>>v>>>Fc&kk"" r c|d}d}|jdgrt|jd}d}nygd}|r5|}|dvrd}n|dvrd}n|dvrd}n |d vrd }nd }|g}|D];}|j|grt|j|}|}n<|s|S||fS) z Get a lemma of the input word, you can select a POS tag (n,v,s) @return: the given lemmas list. @rtype: unicode string rr.)r/r-r,r0)s stop_words stop_wordr/)nr-)ppunct)vr,r0)rPrrlower)ripos return_poslemma lemma_typeword_type_strategyrQs r r^zStemNode.get_lemmas+ ;??8R ( ( !$+h"788E!JJ"E!D!D  iikk:::$CCF]] CC#CCF]] CCC&"0   ;??9b11)$+i*@AAE!*JE 'L:& &r c*t|jS)v Get the affixes of the input word @return: the given affixes. @rtype: unicode string )rHrKrss r get_affixeszStemNode.get_affixessDL!!!r c.|jr |jdSdS)rrN)rKrss r r)zStemNode.get_affixs$ < #<? " # #r c|jS)z Get the vocalized forms of the input word @return: the given vocalizeds. @rtype: list of unicode string )rGrss r get_vocalizedszStemNode.get_vocalizedss r c|jS)zw Get the tags of the input word @return: the tags list. @rtype: list of unicode string )rJrss r r&zStemNode.get_tagsrr c|jS) Get the chosen_indexes forms of the input word @return: the given chosen_indexes. @rtype: unicode string )rZrss r get_chosen_indexeszStemNode.get_chosen_indexess ""r cF|D]}||jks|dkrdS||_dS)rrN)rBrZ)riindexesis r set_chosen_indexeszStemNode.set_chosen_indexessD * *ADO##q1uu(-#*D   r c$|jddkS)z Return if all cases are verbs. @return:True if the node has verb in one case at least. @rtype:boolean r,rr~rss r has_verbzStemNode.has_verbz&!A%%r c$|jddkS)z Return if all cases are nouns. @return:True if the node has noun in one case at least. @rtype:boolean r-rr~rss r has_nounzStemNode.has_nounrr c$|jddkS)z Return if all cases are stopwords. @return:True if the node has stopword in one case at least. @rtype:boolean r/rr~rss r has_stopwordzStemNode.has_stopwordsz*%))r c$|jddkS)z Return if all cases are pounctuations @return:True if the node has pounctation in one case at least. @rtype:boolean r.rr~rss r has_punctzStemNode.has_punct#sz(#a''r cp|jdo)|jd o|jd o |jd S)z Return if all cases are verbs. @return:True if the node is verb in alll cases. @rtype:boolean r,r.r/r-r~rss r r_zStemNode.is_verb-sK Jv  'Jx(( 'Jz** 'Jv&&  r cp|jd o(|jd o|jd o |jdS)z Return if all cases are nouns. @return:True if the node is noun in alll cases. @rtype:boolean r.r/r,r-r~rss r r`zStemNode.is_noun<sK 8$ $ #Jz** #Jv&& # 6"  r cp|jd o(|jdo|jd o |jd S)z Return if all cases are stopwords. @return:True if the node is stopword in alll cases. @rtype:boolean r.r/r,r-r~rss r razStemNode.is_stopwordKsK 8$ $ ' :& 'Jv&& 'Jv&&  r cp|jdo)|jd o|jd o |jd S)z Return if all cases are pounctuations @return:True if the node is pounctation in alll cases. @rtype:boolean r.r/r,r-r~rss r rbzStemNode.is_pounctZsK Jx  'Jz** 'Jv&& 'Jv&&  r cr|jd|jdko|jd|jdkS)z Return True if most cases are verbs. @return:True if the node is verb in most cases. @rtype:boolean r,r-r/r~rss r is_most_verbzStemNode.is_most_verbis: Jv F!3 3 < 6"TZ %;; r cr|jd|jdko|jd|jdkS)z Return True if most cases are nouns. @return:True if the node is noun in most cases. @rtype:boolean r-r,r/r~rss r is_most_nounzStemNode.is_most_nounws: Jv F!3 3 < 6"TZ %;; r cr|jd|jdko|jd|jdkS)z Return True if most cases are stopwords. @return:True if the node is stopword in most cases. @rtype:boolean r/r,r-r~rss r is_most_stopwordzStemNode.is_most_stopwords: Jz "TZ%7 7 < :&F);; r c:|rdS|rdS|rdS|rdS|rdS|rdS|rdSdS) zh Return the word type. @return:the word type or mosttype. @rtype:string r-r,r/r.mostnounmostverb moststopword ambiguous)r`r_rarbrrrrss r get_word_typezStemNode.get_word_types <<>> 6 \\^^ 6      : ^^   8     :     :  " " $ $ !>;r c>|jr |jsdS|r|js |jsdS|jr |jsdSt |jt |jkrdSt |jt |jkrdSdS)z Return the word break type, if the word break the sentences or not. @return:the word type or mosttype. @rtype:string break non_break mostNon_break most_breakr)rRrSrrWrXrArss r get_break_typezStemNode.get_break_types ; t 7    ): 4> 7 _ T[ ;  ! !C $4$4 4 4"?  ! !C $4$4 4 4<;r c|jS)z The syn node is break end like puctuation, if it hasn't any syntaxique or semantique relation with the previous word )rOrss r is_break_endzStemNode.is_break_ends ~r c.|dvS)zz The syn node is break, if it hasn't any syntaxique or semantique relation with the previous word )r mostBreak)rrss r rczStemNode.is_breaks""$$(>>>r c d|jdd|j|||jd|jd|jdfz}|t |jz }|t |jz }|t |jz }|dt |j zz }|S)Nz$ '%s':%s, [%s-%s]{V:%d, N:%d, S:%d} r z, r,r-r/z Indexes : ) __dict__joinrMrrrreprrTrQrZ)ritexts r __repr__zStemNode.__repr__s6 M& ! IIdn % %       ! ! Jv  Jv  Jz ":   T%&&& T^$$$ T^$$$ tD$78888 r N)F)r)rF),__name__ __module__ __qualname____doc__rmrqrtrxrzrrrrrrr[rrr+r]rr^rr)rr&rrrrrrr_r`rarbrrrrrrrcrrr r rr*s ||||P   $$$%%%%%%###"""###"""'''&&&      +++    /'/'/'/'b""" # # #### * * * &&&&&&***(((                            24???r r__main__zStem Node module)r collectionsrpyarabic.arabyr>wordcaser stemmedwordrr rrrrprintrr r rs $$$$$$<<< ***000| | | | | | | | ~ z E r