KaneAI - World’s First E2E Software Testing Agent.Book a Demo Join TestMu Conference

How to use query_dictionary method in pyresttest

Best Python code snippet using pyresttest_python

main.py

Source:main.py

1# order of functions2# 1. collectDocuments(path) -> Collect the documents to be indexed.3#       1.01 tokenization(document) -> Tokenize the text.4#   1.1 Index the documents that each term occurs in5# 2. processingQuery(query) -> taking query input6#       2.02 postfixQuery(query_stream) -> converting infix boolean query to postfix7#       2.03 postfixEvaluation()8#           2.03.1 intersection and union of postings lists9import os10import glob11import re12from contractions import contractions13from porterstemmer import PorterStemmer14from stack import Stack15sizes_of_stemmed_lists = []16term_document_dictionary = {}17list_of_documentID = []18query_dictionary = {}19#collecting documents20def collectDocuments(path):21    # opening files one by one in the directory22    for filename in glob.glob(os.path.join(path, '*.txt')):23        with open(os.path.join(os.getcwd(), filename), 'r') as f:24            #handling the encoding of the text files25            f = open(filename, "r", encoding="utf8")26            #Reading from file27            file_contents = f.read()28            f.close()29            # sending the document for tokenization30            final_tokenized_terms = []31            final_tokenized_terms = tokenization(file_contents)32            #extracting documentid from the path33            path_split = os.path.split(filename)34            document_id = path_split[1][:-4]35            integer_document_id = int(document_id)36            #saving document id37            list_of_documentID.append(integer_document_id)38            #maintaining dictionary with posting list39            for word in final_tokenized_terms:40                if word in term_document_dictionary.keys():41                    #if key exists then append the document list42                    term_document_dictionary[word].append(integer_document_id)43                    #sorting the postings list after a new posting is entered44                    term_document_dictionary[word].sort()45                else:46                    #if key does not exist then create a document list for the key47                    term_document_dictionary[word] = [integer_document_id]48#tokenizing49def tokenization(document):50    #CASEFOLDING51    # casefolding or lower casing the whole document52    document_to_work = document.casefold()53    #OPENING CONTRACTIONS54    # making a list for contractions processing55    list_terms = document_to_work.split()56    list_terms_to_work = list()57    for word in list_terms:58        if word in contractions:59            #using an imported dictionary for contractions60            list_terms_to_work.append(contractions[word])61        else:62            list_terms_to_work.append(word)63    #REMOVING PUNCTUATIONS64    document_to_work = ' '.join(list_terms_to_work)65    document_to_work = re.sub(r'[^\w\s]', '', document_to_work)66    #REMOVING FINAL LEFT OVER WHITESPACES67    finalised_terms_with_stopwords = document_to_work.split()68    # REMOVING STOP WORDS AND DUPLICATE WORDS69    # opening stopwords file70    f = open('dataset/Stopword-List.txt', 'r', encoding='utf8')71    stop_words = f.read()72    stop_list = stop_words.split()73    f.close()74    #removing stop words75    finalised_terms_without_stopwords = list(set(finalised_terms_with_stopwords)^set(stop_list))76    finalised_terms_without_stopwords = list(finalised_terms_without_stopwords)77    #STEMMING78    # stemmer = PorterStemmer()79    # stem_list = list()80    # stem_list = [stemmer.stem(word) for word in finalised_terms_without_stopwords]81    # #removing stemmed duplicates82    # stem_list = set(stem_list)83    # stem_list = list(stem_list)84    #SORTING THE TERMS85    # stem_list.sort()86    # sizes_of_stemmed_lists.append(len(stem_list))87    return finalised_terms_without_stopwords88#Query processing89def processingQuery(query):90    answer = []91    postfixed_query = list()92    #LOWER CASE HANDLING AND LISTING TERMS IN A QUERY93    query_stream = query.lower().split()94    # print(query_stream)95    #not a proximity query96    if len(query_stream) == 1:97        if query_stream[0] in term_document_dictionary.keys():98            answer = term_document_dictionary[query_stream[0]]99        return answer100    elif len(query_stream) > 1:101        if "/" not in query:102            #postfixing an infix boolean query103            postfixed_query = postfixQuery(query_stream)104            # print(postfixed_query)105            answer = evaluatePostfixQuery(postfixed_query)106        else:107            #handling proximity query108            if "and" not in query_stream:109                query=" + ".join(query_stream)110                # print(query)111                query_stream_positional=query.split()112            proximity = query_stream_positional.pop()113            query_stream_positional.pop()114            # print(query_stream_positional)115            proximity = proximity.replace("/","")116            proximity_len = int(proximity) + 1117            answer = evaluatePostfixQuery(query_stream_positional)118            query_stream.pop()119            prox_answer = []120            for document in answer:121                #checking proximity122                path = 'dataset/ShortStories/' + str(document)+'.txt'123                f = open(path, "r", encoding="utf8")124                # Reading from file125                file_contents = f.read()126                f.close()127                #fixing punctuations128                file_contents = re.sub(r'[^\w\s]', '', file_contents)129                #lower casing130                terms = file_contents.split()131                terms = [i.lower() for i in terms]132                # 2 term proximity query133                if len(query_stream) == 2:134                    index_1 = []135                    index_2 = []136                    count_1 = int(0)137                    for item in terms:138                        if item == query_stream[0]:139                            index_1.append(count_1)140                        if item == query_stream[1]:141                            index_2.append(count_1)142                        count_1 += 1143                    for item in index_1:144                        i = int(1)145                        while i != proximity_len + 1:146                            if item + i in index_2:147                                prox_answer.append(document)148                            elif item - i in index_2:149                                prox_answer.append(document)150                            i += 1151                # 3 term proximity query152                else:153                    index_1 = []154                    index_2 = []155                    index_3 = []156                    count_1 = int(0)157                    for item in terms:158                        if item == query_stream[0]:159                            index_1.append(count_1)160                        if item == query_stream[1]:161                            index_2.append(count_1)162                        if item == query_stream[2]:163                            index_3.append(count_1)164                        count_1 += 1165                    for item in index_1:166                        i = int(0)167                        while i != proximity_len + 1:168                            if item + i in index_2:169                                prox_answer.append(document)170                            elif item - i in index_2:171                                prox_answer.append(document)172                            i += 1173                answer = prox_answer174        return answer175#converting logical infix to postfix176def postfixQuery(query_stream):177    temp_stream = []178    for i in query_stream:179        if i == "not":180            temp_stream.append(i.replace("not", "-"))181        elif i == "and":182            temp_stream.append(i.replace("and", "*"))183        elif i == "or":184            temp_stream.append(i.replace("or", "+"))185        else:186            temp_stream.append(i)187    query_stream = temp_stream188    precedence = {"-": 3, "*": 2, "+": 1}189    postfix_query = []190    stack = Stack()191    for term_token in query_stream:192        if term_token.isidentifier():193            postfix_query.append(term_token)194        elif term_token == '(':195            stack.push(term_token)196        elif term_token == ')':197            topToken = stack.pop()198            while topToken != '(':199                postfix_query.append(topToken)200                topToken = stack.pop()201        else:  # must be operator202            if not stack.empty():203                while not stack.empty() and precedence[stack.peek()] >= precedence[term_token]:204                    postfix_query.append(stack.pop())205            stack.push(term_token)206    while not stack.empty():207        postfix_query.append(stack.pop())208    return postfix_query209#evaluating the postfix expression210def evaluatePostfixQuery(postfixed_query):211    stack = Stack()212    operators = ["*","+","-"]213    for token in postfixed_query:214        if token not in operators:215            stack.push(token)216        else:217            if token == "-":218                term_1 = stack.pop()219                # print(term_1)220                if term_1 in term_document_dictionary.keys():221                    not_term_1 = list(set(list_of_documentID)^set(term_document_dictionary[term_1]))222                    query_dictionary[term_1] = not_term_1223                else:224                    query_dictionary[term_1] = []225                stack.push(term_1)226            elif token == "*":227                term_2 = stack.pop()228                term_1 = stack.pop()229                # print(term_1, term_2)230                if term_1 not in query_dictionary.keys():231                    if term_1 in term_document_dictionary.keys():232                        query_dictionary[term_1] = term_document_dictionary[term_1]233                    else:234                        query_dictionary[term_1] = []235                if term_2 not in query_dictionary.keys():236                    if term_2 in term_document_dictionary.keys():237                        query_dictionary[term_2] = term_document_dictionary[term_2]238                    else:239                        query_dictionary[term_2] = []240                query_dictionary["answer"] = intersect(term_1,term_2)241                stack.push("answer")242            elif token == "+":243                term_2 = stack.pop()244                term_1 = stack.pop()245                # print(term_1, term_2)246                if term_1 not in query_dictionary.keys():247                    if term_1 in term_document_dictionary.keys():248                        query_dictionary[term_1] = term_document_dictionary[term_1]249                    else:250                        query_dictionary[term_1] = []251                if term_2 not in query_dictionary.keys():252                    if term_2 in term_document_dictionary.keys():253                        query_dictionary[term_2] = term_document_dictionary[term_2]254                    else:255                        query_dictionary[term_2] = []256                query_dictionary["answer"] = union(term_1, term_2)257                stack.push("answer")258    return query_dictionary["answer"]259#intersection of two postings lists260def intersect(term_1,term_2):261    answer = []262    postings_term_1 = query_dictionary[term_1]263    postings_term_2 = query_dictionary[term_2]264    len_p1 = len(postings_term_1)265    len_p2 = len(postings_term_2)266    index_p1 = int(0)267    index_p2 = int(0)268    while len_p1 != 0 and len_p2 != 0:269        if index_p1 <len(postings_term_1) and index_p2<len(postings_term_2):270            if postings_term_1[index_p1] == postings_term_2[index_p2]:271                answer.append(postings_term_1[index_p1])272                index_p1 += 1273                len_p1 -= 1274                index_p2 += 1275                len_p2 -= 1276            else:277                if postings_term_1[index_p1] < postings_term_2[index_p2]:278                    index_p1 += 1279                    len_p1 -= 1280                else:281                    index_p2 += 1282                    len_p2 -= 1283    return answer284#union of two postings lists285def union(term_1,term_2):286    answer = []287    postings_term_1 = query_dictionary[term_1]288    postings_term_2 = query_dictionary[term_2]289    answer = [term for term in postings_term_1]290    answer = [term for term in postings_term_2] + answer291    answer = set(answer)292    answer = list(answer)293    answer.sort()294    return answer295if __name__ == '__main__':296    collectDocuments('dataset/ShortStories')297    print("Size of the dictionary: "+ str(len(term_document_dictionary)))298    q = "god and man and love"299    print("Query: ",q)...

create_queries.py

Source:create_queries.py

1'''2    Authors:3    Valentina Guerrero4    Aishwarya Varma 5'''6def create_movie_table_query(items_dictionary):7    query_dictionary = {}8    language_string = ''9    numbers = ['rating', 'revenue', 'runtime', 'release_year', 'budget']10    for item in items_dictionary:11        if items_dictionary[item]:12            if item not in numbers:13                query_dictionary[item] = "LIKE '%{}%'".format(items_dictionary[item])14            else:15                if item in ['rating', 'revenue', 'budget']:16                    query_dictionary[item] = ">= '{}' AND movies.{} > 0".format(items_dictionary[item], item)17                elif item == 'runtime':18                    query_dictionary[item] = "<= '{}' AND movies.runtime > 0 ".format(items_dictionary[item])19                else:20                    query_dictionary[item] = "= '{}'".format(items_dictionary[item])21        else:22            query_dictionary[item] = 'IS NOT NULL'23    query_skeleton = '''24        movies.title {}25        AND26        movies.rating {}27        AND28        movies.revenue {}29        AND 30        movies.runtime {}31        AND32        movies.release_year {}33        AND 34        movies.budget {}35        AND36        languages.lang_full {}37        AND 38        countries.country_name {}39        AND40        companies.company_name {}41        AND42        genres.genre {}43        AND44        movie_langs.movie_id = movies.id45        AND 46        movie_langs.lang_id = languages.id47        AND48        movie_countries.movie_id = movies.id49        AND50        movie_countries.country_id = countries.id51        AND52        movie_companies.movie_id = movies.id53        AND54        movie_companies.company_id = companies.id55        AND56        movies.id = movie_genres.movie_id57        AND58        movie_genres.genre_id = genres.id59        60    '''.format(query_dictionary['title'], query_dictionary['rating'], query_dictionary['revenue'], query_dictionary['runtime'], query_dictionary['release_year'], query_dictionary['budget'],query_dictionary['language'], query_dictionary['country'], query_dictionary['company'], query_dictionary['genre'] )61    return query_skeleton62def create_genres_table_query(movie_id):63    query = '''64    SELECT genres.genre65    FROM 66    movies,67    genres,68    movie_genres69    WHERE70    movies.id = '{}'71    72    ;'''.format(movie_id)73    return query74def create_search_all_query(search_string):75    if search_string.isnumeric():76        int_keyword = "= '{}'".format(search_string)77        string_keyword = "LIKE '%{}%'".format(search_string)78        query_skeleton = '''79            release_year {int_key}80            OR81            rating {int_key}82            OR83            runtime {int_key}84            OR85            title {string_key}86        '''.format(int_key=  int_keyword, string_key = string_keyword)87    else:88        string_keyword = "LIKE '%{}%'".format(search_string)89        query_skeleton = '''90            title {string_key}91        '''.format(string_key = string_keyword)92    return query_skeleton93def create_genre_query(keyword):94    genre_query = ''' 95    SELECT 96    movies.id, movies.title, movies.release_year, movies.rating, movies.poster_path97    FROM 98    movies,99    genres,100    movie_genres101    WHERE102    genres.genre LIKE '%{}%'103    AND104    movies.id = movie_genres.movie_id105    AND106    movie_genres.genre_id = genres.id107    '''.format(keyword)...

Automation Testing Tutorials

Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.