Coverage for mindsdb / integrations / handlers / google_books_handler / google_books_tables.py: 0%

1import pandas as pd 

2from mindsdb_sql_parser import ast 

3from pandas import DataFrame 

4 

5from mindsdb.integrations.libs.api_handler import APITable 

6from mindsdb.integrations.utilities.sql_utils import extract_comparison_conditions 

7 

8 

9class VolumesTable(APITable): 

10 """ 

11 A class for handling the volumes table. 

12 """ 

13 

14 def select(self, query: ast.Select) -> DataFrame: 

15 """ 

16 Gets all info about the wanted contents of a bookshelf. 

17 

18 Args: 

19 query (ast.Select): SQL query to parse. 

20 

21 Returns: 

22 Response: Response object containing the results. 

23 """ 

24 

25 # Parse the query to get the conditions. 

26 conditions = extract_comparison_conditions(query.where) 

27 # Get the parameters for the request. 

28 params = {} 

29 for op, arg1, arg2 in conditions: 

30 if op != '=': 

31 raise NotImplementedError 

32 if arg1 == 'q' or arg1 == 'download' or arg1 == 'langRestrict' \ 

33 or arg1 == 'printType'\ 

34 or arg1 == 'source' or arg1 == 'partner' \ 

35 or arg1 == 'showPreorders' or arg1 == 'startIndex': 

36 params[arg1] = arg2 

37 elif arg1 == 'filter': 

38 if arg2 not in ['ebooks', 'free-ebooks', 'full', 'paid-ebooks', 'partial']: 

39 raise NotImplementedError 

40 params[arg1] = arg2 

41 elif arg1 == 'libraryRestrict': 

42 if arg2 not in ['my-library', 'no-restrictions']: 

43 raise NotImplementedError 

44 params[arg1] = arg2 

45 elif arg1 == 'printType': 

46 if arg2 not in ['all', 'books', 'magazines']: 

47 raise NotImplementedError 

48 params[arg1] = arg2 

49 elif arg1 == 'projection': 

50 if arg2 not in ['lite', 'full']: 

51 raise NotImplementedError 

52 params[arg1] = arg2 

53 else: 

54 raise NotImplementedError 

55 

56 # Get the order by from the query. 

57 if query.order_by is not None: 

58 if query.order_by[0].value == 'newest': 

59 params['orderBy'] = 'newest' 

60 elif query.order_by[0].value == 'relevance': 

61 params['orderBy'] = 'relevance' 

62 else: 

63 raise NotImplementedError 

64 

65 if query.limit is not None: 

66 params['maxResults'] = query.limit.value 

67 

68 # Get the volumes from the Google Books API. 

69 bookshelves = self.handler.\ 

70 call_application_api(method_name='get_volumes', params=params) 

71 

72 selected_columns = [] 

73 for target in query.targets: 

74 if isinstance(target, ast.Star): 

75 selected_columns = self.get_columns() 

76 break 

77 elif isinstance(target, ast.Identifier): 

78 selected_columns.append(target.parts[-1]) 

79 else: 

80 raise ValueError(f"Unknown query target {type(target)}") 

81 

82 if len(bookshelves) == 0: 

83 bookshelves = pd.DataFrame([], columns=selected_columns) 

84 else: 

85 bookshelves.columns = self.get_columns() 

86 for col in set(bookshelves.columns).difference(set(selected_columns)): 

87 bookshelves = bookshelves.drop(col, axis=1) 

88 return bookshelves 

89 

90 def get_columns(self) -> list: 

91 """ 

92 Gets the columns of the table. 

93 

94 Returns: 

95 list: List of column names. 

96 """ 

97 return [ 

98 'kind', 

99 'id', 

100 'etag', 

101 'selfLink', 

102 'volumeInfo', 

103 'userInfo' 

104 'saleInfo', 

105 'accessInfo', 

106 'searchInfo', 

107 ] 

108 

109 

110class BookshelvesTable(APITable): 

111 """ 

112 A class for handling the bookshelves table. 

113 """ 

114 

115 def select(self, query: ast.Select) -> DataFrame: 

116 """ 

117 Gets all info about the wanted bookshelves. 

118 

119 Args: 

120 query (ast.Select): SQL query to parse. 

121 

122 Returns: 

123 Response: Response object containing the results. 

124 """ 

125 

126 # Parse the query to get the conditions. 

127 conditions = extract_comparison_conditions(query.where) 

128 # Get the parameters for the request. 

129 params = {} 

130 for op, arg1, arg2 in conditions: 

131 if arg1 == 'userId' or arg1 == 'source' or arg1 == 'fields': 

132 if op != '=': 

133 raise NotImplementedError 

134 params[arg1] = arg2 

135 elif arg1 == 'shelf': 

136 if op == '=': 

137 params[arg1] = arg2 

138 elif op == '>': 

139 params['minShelf'] = arg2 

140 elif op == '<': 

141 params['maxShelf'] = arg2 

142 else: 

143 raise NotImplementedError 

144 else: 

145 raise NotImplementedError 

146 

147 # Get the bookshelves from the Google Books API. 

148 bookshelves = self.handler.\ 

149 call_application_api(method_name='get_bookshelves', params=params) 

150 

151 selected_columns = [] 

152 for target in query.targets: 

153 if isinstance(target, ast.Star): 

154 selected_columns = self.get_columns() 

155 break 

156 elif isinstance(target, ast.Identifier): 

157 selected_columns.append(target.parts[-1]) 

158 else: 

159 raise ValueError(f"Unknown query target {type(target)}") 

160 

161 if len(bookshelves) == 0: 

162 bookshelves = pd.DataFrame([], columns=selected_columns) 

163 else: 

164 bookshelves.columns = self.get_columns() 

165 for col in set(bookshelves.columns).difference(set(selected_columns)): 

166 bookshelves = bookshelves.drop(col, axis=1) 

167 return bookshelves 

168 

169 def get_columns(self) -> list: 

170 """Gets all columns to be returned in pandas DataFrame responses""" 

171 return [ 

172 'kind', 

173 'id', 

174 'selfLink', 

175 'title', 

176 'description', 

177 'access', 

178 'updated', 

179 'created', 

180 'volumeCount', 

181 'volumesLastUpdated' 

182 ]