-iVWzdZddlmZddlmZddlmZddlZGddZ dZ e dkr e dSdS)z Arabic _collocations Class NcpeZdZdZddZdZdZdZdZdZ d Z d Z d Z d Z d ZdZdZdZddZdS)CollocationClassz( Arabic _collocations Class Fc0d|_d|_d|_d|_||_ddddddd }i|_d |_tjd ||_ tj D]"}tj |d |j|<#dS) N'~r)id vocalized unvocalizedrulecategorynoteT collocationsv) minimaxi delimiterunknown_delimitershow_delimiter collo_cache cache_enabledcollocationdictionarycollocationDictionary collo_dictcconstGENERAL_COLLOCATIONSkeys)selfrCOLLOCATION_DICTIONARY_INDEXkeys R/var/www/html/speakWrite/venv/lib/python3.11/site-packages/maskouk/collocations.py__init__zCollocationClass.__init__s  #', ( ( $!/E466.3355 3 3C  ( -c 2  S ! ! 3 3cnt||j|_t||j|_dS)z set minimum Nminrmaxr)r"min0s r%set_minzCollocationClass.set_min7. di(( di(( r'cnt||j|_t||j|_dS)z set maximum Nr))r"max0s r%set_maxzCollocationClass.set_max>r.r'c||_dS)z set the delimiter for collocations output @param delimiter : the given delimiter. @type delimiter : one unicode char. N)rr"rs r% set_delimiterzCollocationClass.set_delimiterEs #r'c||_dS)z set the delimiter for unvocalized collocations output @param delimiter: the given delimiter. @type delimiter: one unicode char. N)rr3s r%set_unknown_delimiterz&CollocationClass.set_unknown_delimiterMs "+r'cd|_dS)B Enable the option to show collocation delimiters TNrr"s r%enable_show_delimiterz&CollocationClass.enable_show_delimiterUs#r'cd|_dS)r8FNr9r:s r%disable_show_delimiterz'CollocationClass.disable_show_delimiter[s$r'cd|_dS)z3 Enable the option to enable cache TNrr:s r% enable_cachezCollocationClass.enable_cacheas"r'cd|_dS)zC disable the option to show collocation delimiters FNr?r:s r% disable_cachezCollocationClass.disable_cachegs#r'cd|}t|dkrdSt|dkr|jr ||jvr|Snttj|sdSd|}|jr ||jvr|S|j|}t|dkr*|jr!||jvr|d}|d|j|<|S|dtj tj tj tj tjfvr|d}|dd}|j|}t|dkrQ|jrH||jvr?|dd}|dkr||z|j|<n||j|<||jvr ||j|<|SdSdSdS) uc Return The vocalized text if the word list is collocated. Example: >>> wlist = [u"كرة", u"القدم"] >>> # test if collocation exists >>> results = mydict.is_collocated(wlist) >>> print("inuput:", wlist) >>> print("output:",results) inuput: ['كرة', 'القدم'] output: كرة القدم >>> wlist = [u"شمس", u"النهار"] >>> results = mydict.is_collocated(wlist) >>> print("inuput:", wlist) >>> print("output:",results) inuput: ['شمس', 'النهار'] output: False @param wordlist: word of list, 2 or more words. @type wordlist: list of unicode. @return : The collocation as a key if exists. else False. @rtype: dict/None.  rFr rrN)joinlenrrr token_patsearchrlookuparabyFEHWAWBEHLAMKAF)r"wordlistr$idlist first_entry first_letternew_keyvocalized_collocations r% is_collocatedzCollocationClass.is_collocatedms6ii!! x==??5 ]]1__! cT-=&=&= "))#..9 5))H%%C! cT-=&=&= _++C00F6{{a%FcT5E.E.E"()K-8-ED$S) q6eiEIuy#&q6L!!""gG"_33G<>> # detect collocations in phrase >>> text = u"لعبنا مباراة كرة القدم في بيت المقدس" >>> wordlist = araby.tokenize(text) >>> results = mydict.ngramfinder(2, wordlist) >>> print("inuput:", text) >>> print("output:",results) inuput: لعبنا مباراة كرة القدم في بيت المقدس output: ['لعبنا', 'مباراة', 'كرة القدم', 'في', 'بيت المقدس'] @param wordlist: word of list, 2 or more words. @type wordlist: list of unicode. @param mini: minimum number of words in the collocation @type mini: integer. @return : list of words and collocations, else False. @rtype: list /None. r) rGrangepopinsertis_possible_collocationrWappendextendreverse) r"rrQlistenewlistsublisticurrentresults r% ngramfinderzCollocationClass.ngramfinders#,%jjD  G4[[ + +))++q'**** *477@@ *++G44*NN6****NN7;;==111LL)))1%jjD  4  ur'ctjD]<}tj|tj|dd|}=|S)u[ Lookup for long collocations in a text. return a vocalized words collocations. Example: >>> # get Long collocations >>> text = u" قلت لهم السلام عليكم ورحمة الله تعالى وبركاته ثم رجعت" >>> results = mydict.lookup4long_collocations(text) >>> print("inuput:", text) inuput: قلت لهم السلام عليكم ورحمة الله تعالى وبركاته ثم رجعت >>> print("output:",results) output: قلت لهم السّلامُ عَلَيكُمْ وَرَحْمَةُ اللهِ تَعَالَى وبركاته ثم رجعت @param inputtext: given text @type inputtext: unicode. @return : text. @rtype: unicode. rrE)rr r!resubget)r" inputtextks r%lookup4long_collocationsz)CollocationClass.lookup4long_collocationss_(,1133  A6#>q#A#E#Ec $$IIr'cd}g}g}|D]3}||jvr||}||j|<|r||j|vr||d|d|j||}|||dnU|d||n*|d|||}5||fS)u  Lookup for all ngrams , in the word list. return a list of vocalized words collocations Example: >>> # detect collocations in phrase >>> text = u"لعبنا مباراة كرة القدم في بيت المقدس" >>> wordlist = araby.tokenize(text) >>> results = mydict.lookup(wordlist) >>> print("inuput:", text) >>> print("output:",results) inuput: لعبنا مباراة كرة القدم في بيت المقدس output: (['لعبنا', 'مباراة', 'كُرَة', 'الْقَدَمِ', 'في', 'بَيْت', 'الْمَقْدِسِ'], ['CO', 'CO', 'CB', 'CI', 'CO', 'CB', 'CI']) @param wordlist: word of list, 2 or more words. @type wordlist: list of unicode. @return : dict of words attributes like dict {'vocalized': vocalizedword list, 'category': categoryOf_collocation}. else False. @rtype: dict of dict /None. FCBCIrDCO)ris_collocated_wordr!rZr]r^split)r"rQprevioustaglistvocalized_listwordrevocalized_tuples r%rJzCollocationClass.lookupsT4  D4+++0066)/ & ,4+H5::<<<<KKMMMNN4(((NN4(((&*&6x&@&FO"&&((("))/*?*?*D*DEEEENN4((("))$////t$$$%%d+++HH''r'cvtjd|riSi}|j|d}t |dkr:|D]6}|ddd}|dr |d||<7n|dt jt jt j t j t j fvru|d}|dd }|j|d}t |dkr4|D]1}|ddd}||dz||<2|S) u Return The list of collocations started by given word, else False. Example: >>> # get all collocations for a specific word >>> word1 = u"كرة" >>> results = mydict.is_collocated_word(word1) >>> print("inuput:", word1) >>> print("output:",results) inuput: كرة output: {'القدم': 'كُرَة الْقَدَمِ'} >>> >>> word = u"بيت" >>> # get all collocations for a specific word >>> results = mydict.is_collocated_word(word) >>> print("inuput:", word) >>> print("output:",results) inuput: بيت output: {'العدة': 'بَيْت الْعِدَّةِ', 'المستأجر': 'بَيْت الْمُسْتَأْجِرِ', 'المشتري': 'بَيْتِ الْمُشْتَرِي', 'الرجل': 'بَيْت الرَّجُلِ', 'البناء': 'بَيْت الْبِنَاءِ', 'الزوج': 'بَيْت الزَّوْجِ', 'المال': 'بيت المال', 'المقدس': 'بَيْت الْمَقْدِسِ', 'البائع': 'بَيْت الْبَائِعِ', 'الخلاء': 'بَيْت الْخَلَاءِ', 'الأب': 'بَيْت الْأَبِ', 'الله': 'بَيْت اللّهِ'} @param word: input word. @type word: unicode. @return : dict of collocations and vocalized collocations if exists, the keys are second words in collocations. else False. @rtype: dict/Boolean. z[::pounctuation::]T) singlewordr rrDrrN) rhrIrrJrGrsrKrLrMrNrOrP)r"rwrerRitemr$rTnew_words r%rrz#CollocationClass.is_collocated_wordUsU4 9)4 0 0 I''4'@@ v;;!   4 4=)//44Q7 $4"&{"3F3K  4Aw59eiEI Y#Aw 8//t/LLv;;!## &GG"=177<>> text = u"ظهر رئيس الوزراء السيد عبد الملك بن عامر ومعه أمير دولة غرناطة ونهر النيل انطلاق السباق" >>> wordlist = araby.tokenize(text) >>> previous = "__" >>> for wrd in wordlist: >>> wlist = [previous, wrd] >>> results = mydict.is_possible_collocation(wlist, length = 2) >>> print("inuput:", wlist) >>> print("output:", results) >>> previous = wrd inuput: ['__', 'ظهر'] output: 100 inuput: ['ظهر', 'رئيس'] output: 100 inuput: ['رئيس', 'الوزراء'] output: 100 inuput: ['الوزراء', 'السيد'] output: 20 inuput: ['السيد', 'عبد'] output: 100 inuput: ['عبد', 'الملك'] output: 15 inuput: ['الملك', 'بن'] output: 100 inuput: ['بن', 'عامر'] output: 15 inuput: ['عامر', 'ومعه'] output: 100 inuput: ['ومعه', 'أمير'] output: 100 inuput: ['أمير', 'دولة'] output: 100 inuput: ['دولة', 'غرناطة'] output: 10 inuput: ['غرناطة', 'ونهر'] output: 100 inuput: ['ونهر', 'النيل'] output: 100 inuput: ['النيل', 'انطلاق'] output: 100 inuput: ['انطلاق', 'السباق'] output: 100 @param wordlist: word of list, 2 or more words. @type wordlist: list of unicode. @param length: minimum number of words in the collocation @type length: integer. @return : the rule of found collocation, 100 default. @rtype: interger. rr uالuة(rE2uات<d) rGrKstrip_tashkeelrrHrIADDITIONAL_WORDS NAMED_PRIORSPECIAL_DEFINED startswithendswithtab_noun_context) r"rQcontextlengthlist2item_v1item_v2item1item2s r%r\z(CollocationClass.is_possible_collocationsr u::f  1AhGAhG(11E(11E$++E22    # #E * * r&111r&,,,rv555$$W--53C3CG3L3L2^^E**u/?/?/H/H2 ^^E** u~~e/D/D 2nnF4K)K)K$$W--*L2^^G,,1A1A'1J1J23r'N)F)rEr)__name__ __module__ __qualname____doc__r&r-r1r4r6r;r=r@rBrWrfrmrJrrr\r'r%rrs3333<))))))###+++### $$$ """ ### ___B555n26(6(6(n888vaaaaaar'rcdt_t}gd}d}|dz }|dz }|dz }|d}|d|d |td D]M}||}t|d | d N|}tj D]}t| d tj |d d d ||vrtdt!j|tj |d d|}td| d dS)z main test zdata/collocations.sqlite) uقبلuصلاةu الفجرuكرةu القدمuفيuدولةuقطرuالآنuأنubتغمده الله برحمته . أشهد أن لا إله إلا الله وحده لا شريك له . أشهد أن محمدا عبده ورسوله . صلى الله عليه وآله وصحبه وسلم . أشهد أن لا إله إلا الله . أشهد أن محمدا رسول الله . صلى الله عليه وسلم . uوالحمد لله . الحمد لله . بالحمد لله . بسم الله الرحمن الرحيم . عبد الله . بعبد الله .u)بسم الله الرحمن الرحيمz taha zerrouki rD#@r  utf8rrEokz long collo, N)rFILE_DB_collocationClassrsr4r6r;rYrJprintrFencoderr r!rjrhri)collorQwordsrcrarkrls r%mainlyrs%@!   E<<> 4LLLFAv:1=AA#rJJ   .)**62277777r'__main__) rmaskouk.collocationdictionaryrmaskouk.collocation_constcollocation_constrpyarabic.arabyrKrhrrrrr'r%rs>=====****** ]]]]]]]]~$8$8$8P z FHHHHHr'