-iR7dZddlZddlZddlZddlZddlZdZddlm Z ddl m Z GddZ dZ ed kr e dSdS) z^ Arabic Dictionary Class from Arramooz Al Waseet. Used in multiporpus morpholigical treatment Nzdata/arabicdictionary.sqlite) nountuplecBeZdZdZdZdZdZdZdZdZ dZ d Z d S) ArabicDictionaryum Arabic dictionary Class Used to allow abstract acces to lexicon of arabic language, can get indexed and hashed entries from the basic lexicon add also, support to extract attributtes from entries Example: >>> import arramooz.arabicdictionary >>> mydict = arramooz.arabicdictionary.ArabicDictionary('verbs') >>> wordlist = [u"استقلّ", u'استقل', u"كذب"] >>> tmp_list = [] >>> for word in wordlist: >>> foundlist = mydict.lookup(word) >>> for word_tuple in foundlist: >>> word_tuple = dict(word_tuple) >>> vocalized = word_tuple['vocalized'] >>> tmp_list.append(dict(word_tuple)) >>> print(tmp_list) [{'think_trans': 1, 'passive': 0, 'confirmed': 0, 'vocalized': u'اِسْتَقَلَّ', 'stamped': u'ستقل', 'future_moode': 0, 'triliteral': 0, 'future': 0, 'unthink_trans': 0, 'past': 0, 'unvocalized': u'استقل', 'future_type': u'َ', 'double_trans': 0, 'normalized': u'استقل', 'reflexive_trans': 0, 'imperative': 0, 'transitive': 1, 'root': u'قلل', 'id': 7495}, {'think_trans': 1, 'passive': 0, 'confirmed': 0, 'vocalized': u'كَذَبَ', 'stamped': u'كذب', 'future_moode': 0, 'triliteral': 1, 'future': 0, 'unthink_trans': 0, 'past': 0, 'unvocalized': u'كذب', 'future_type': u'كسرة', 'double_trans': 0, 'normalized': u'كذب', 'reflexive_trans': 0, 'imperative': 0, 'transitive': 1, 'root': u'كذب', 'id': 1072}, {'think_trans': 1, 'passive': 0, 'confirmed': 0, 'vocalized': u'كَذَّبَ', 'stamped': u'كذب', 'future_moode': 0, 'triliteral': 0, 'future': 0, 'unthink_trans': 0, 'past': 0, 'unvocalized': u'كذب', 'future_type': u'َ', 'double_trans': 0, 'normalized': u'كذب', 'reflexive_trans': 0, 'imperative': 0, 'transitive': 1, 'root': u'كذب', 'id': 2869}] c4i|_i|_||_ttdr tj}nAt jt j t}t j |t}t j |rzd|zdz} tj|dd|_tj|j_|j|_nc#t($rt+d|YnGwxYwt+d d |d t jgd t1jd t4jt4jt4jt4jt4jt4j t4j!t4j"t4j#t4j$d t0j%|_&dS)zw initialisation of dictionary from a data dictionary, create indexes to speed up the access. frozenzfile:z?mode=roFT)check_same_threaduriz(Fatal Error Can't find the database file zInexistant Filez current dir utf8[]N)' dictionaryattrib_num_index table_namehasattrsysprefixospathdirnamerealpath__file__joinFILE_DBexistssqliteconnect db_connectRow row_factorycursorIOErrorprintcurdirencoderecompilearabyALEFYEHHAMZAALEF_HAMZA_ABOVE WAW_HAMZA YEH_HAMZAWAW ALEF_MAKSURASHADDA ALEF_MADDAUNICODE stamp_pat)selfrbase file_pathfile_uris W/var/www/html/speakWrite/venv/lib/python3.11/site-packages/arramooz/arabicdictionary.py__init__zArabicDictionary.__init__3s!#% 3 ! ! ?:DD7??27#3#3H#=#=>>DGLLw// 7>>) $ $ (i' 2H 7"(.UX\"]"]"]/5j+"o4466  M M M@)LLLLL M $)). ? Iv ( ( (  5;; 6 6 %))U%7%7uGWGWGW%Y sDD43D4cnt|dr"|jr|jdSdSdS)z? Delete instance and close database connection rN)rrclose)r6s r:__del__zArabicDictionary.__del__gsN 4 & & ( (%%''''' ( ( ( (cd|jd|d} |j||jr|jSn#tj$rYdSwxYwdS)z Get dictionary entry by id from the dictionary @param idf :word identifier @type idf: integer @return: all attributes @rtype: dict select * FROM WHERE id=''F)rr"executefetchallrOperationalError)r6idfsqls r:get_entry_by_idz ArabicDictionary.get_entry_by_idps48???CCCH . K   $ $ $ { .{++--- .'   55  usA AAcd|jd|d} |j||jr|jD] }||cSn#tj$rYdSwxYwdS)z Get attribute value by id from the dictionary @param idf :word identifier @type idf: integer @param attribute :the attribute name @type attribute: unicode @return: The attribute value @rtype: mix. rArBrCF)rr"rDrrF)r6rG attributerHrows r:get_attrib_by_idz!ArabicDictionary.get_attrib_by_idsR48???CCCH + K   $ $ $ { +;++C N*** '   55 usAAAcg}tj|}d|jd|d} |j||jr|jD]}|||S#t $rgcYStj$rgcYSwxYw)uI look up for all word forms in the dictionary @param normalized: the normalized word. @type normalized: unicode. @return: list of dictionary entries . @rtype: list. Example: >>> import arramooz.arabicdictionary >>> import arramooz.arabicdictionary >>> mydict = arramooz.arabicdictionary.ArabicDictionary('verbs') >>> wordlist = [u"استقلّ", u'استقل', u"كذب"] >>> tmp_list = [] >>> for word in wordlist: ... foundlist = mydict.lookup(word) ... for word_tuple in foundlist: ... print(dict(word_tuple)) ... {'id': 4743, 'vocalized': 'اِسْتَقَلَّ', 'unvocalized': 'استقل', 'root': 'قلل', 'normalized': 'استقل', 'stamped': 'ستقل', 'future_type': 'فتحة', 'triliteral': 0, 'transitive': 1, 'double_trans': 0, 'think_trans': 1, 'unthink_trans': 0, 'reflexive_trans': 0, 'past': 0, 'future': 0, 'imperative': 0, 'passive': 0, 'future_moode': 0, 'confirmed': 0} {'id': 118, 'vocalized': 'كَذَّبَ', 'unvocalized': 'كذب', 'root': 'كذب', 'normalized': 'كذب', 'stamped': 'كذب', 'future_type': 'فتحة', 'triliteral': 0, 'transitive': 1, 'double_trans': 0, 'think_trans': 1, 'unthink_trans': 0, 'reflexive_trans': 0, 'past': 0, 'future': 0, 'imperative': 0, 'passive': 0, 'future_moode': 0, 'confirmed': 0} {'id': 10205, 'vocalized': 'كَذَبَ', 'unvocalized': 'كذب', 'root': 'كذب', 'normalized': 'كذب', 'stamped': 'كذب', 'future_type': 'كسرة', 'triliteral': 1, 'transitive': 1, 'double_trans': 0, 'think_trans': 1, 'unthink_trans': 0, 'reflexive_trans': 0, 'past': 0, 'future': 0, 'imperative': 0, 'passive': 0, 'future_moode': 0, 'confirmed': 0} >>> rAz WHERE normalized='rC) r)normalize_hamzarr"rDappendAttributeErrorrrF)r6 normalizedidlistnormwordrHrLs r:lookupzArabicDictionary.lookups0(44<@???   K   $ $ $ { ';''CMM#&&&&M   III&   III sA(( B 6B B c||}d|jd|d} |j||jrdSn#tj$rYdSwxYwdS)aK look up for word if exists by using the stamp index, the input word is stamped by removing infixes letters like alef, teh the stamped word is looked up in the stamp index @param word: word to look for. @type word: unicode. @return: True if exists. @rtype: Boolean. zselect id FROM  WHERE stamped='rCTF) word_stamprr"rDrrF)r6wordstamprHs r:exists_as_stampz ArabicDictionary.exists_as_stamps%%9= 55  K   $ $ ${ t '   55 us!A AAcg}||}d|jd|d} |j||jr|jD]}|||S#t j$rgcYSwxYw)aS look up for word if exists by using the stamp index, the input word is stamped by removing infixes letters like alef, teh the stamped word is looked up in the stamp index @param word: to look for. @type word: unicode. @return: list of dictionary entries IDs. @rtype: list. rArWrC)rXrr"rDrPrrF)r6rYrSrZrHrLs r:lookup_by_stampz ArabicDictionary.lookup_by_stamps%%8<   K   $ $ ${ ';''CMM#&&&&M'   III sAA))A=<A=cx|dd|ddkr |dd}|jd|S)a generate a stamp for a word, remove all letters which can change form in the word : - ALEF, - HAMZA, - YEH, - WAW, - ALEF_MAKSURA - SHADDA @return: stamped word N)r5sub)r6rYs r:rXzArabicDictionary.word_stampsD 9be $ $9D~!!"d+++r?N) __name__ __module__ __qualname____doc__r;r>rIrMrUr[r]rXr?r:rrs0222h(((4444l)))T(6,,,,,r?rcftd}gd}g}|D]U}||}|D];}t|}|d}|t|rys  )N,N,N,N,N,N,N,N,bHHH  FHHHHHr?