Update app.py

app.py

@@ -134,189 +134,147 @@ def query_to_SQL_to_MongoDB(query, key, organization):
     return complex_SQL_to_MongoDB(SQL)
 
 
-keywords = {'INNER', 'FROM', 'WHERE', 'GROUP', 'BY', 'ON', 'SELECT', 'BETWEEN', 'LIMIT', 'AND', 'ORDER'}
-
-mapper = {} # maps SQL symbols to MongoDB functions
-
-mapper['<'] = '$lt'
-mapper['>'] = '$gt'
-mapper['!='] = '$ne'
 
 def complex_SQL_to_MongoDB(query):
 
+    keywords = {'INNER', 'FROM', 'WHERE', 'GROUP', 'BY', 'ON', 'SELECT', 'BETWEEN', 'LIMIT', 'AND', 'ORDER'} # keyword set used by my MongoDB function
+    mapper = {} # maps SQL symbols to MongoDB functions
+    mapper['<'] = '$lt'
+    mapper['>'] = '$gt'
+    mapper['!='] = '$ne'
+
     query = re.split(r' |\n', query) # split the query on spaces and turn in to array
-    query = [ x for x in query if len(x) > 0]
+    query = [ x for x in query if len(x) > 0] # remove empty strings in the array
+
+    while query[0][:3] not in ['MAX', 'MIN'] and query[0][:5] != 'COUNT' and query[0] not in keywords:
+
+        query = query[1:]
+
+    if query[1] == 'AS':
 
-    if len(query[0]) > 3 and (query[0][:3] == 'MAX' or query[0][:3] == 'MIN'):
+        rename = query[2]
+        
+        for i in range(3, len(query)):
+
+            if query[i] == rename:
+
+                query[i] = query[0]
+
+    if len(query[0]) > 3 and (query[0][:3] == 'MAX' or query[0][:3] == 'MIN'): # if the SQL contains a MAX or MIN select then we rewrite the SQL query in an easier format
         
         query += ['ORDER', 'BY', query[0][4:-1], 'DESC' if query[0][:3] == 'MAX' else 'ASC', 'LIMIT', '1']
 
-    count_str = ''
+    count_str = '' # builds a MongoDB statement if there is a count in the select statement
 
-    if len(query[0]) > 5 and query[0][:5] == 'COUNT': 
+    if len(query[0]) > 5 and query[0][:5] == 'COUNT': # if there is indeed a count
 
-        count_str += ' {$count : ' 
+        count_str += ' {$count : ' # construct the count sequence
         if query[0][6] == '*':
 
-            count_str += '{} }'
+            count_str += '{} }' # an asterisk means everything
 
         else:
 
-            count_str += query[0][6:-1] + ' }'
+            count_str += query[0][6:-1] + ' }' # otherwise write the actual field it wants
 
-    print(query)
-    fields = ''
-    i = 0 
-    while query[i] != 'FROM':
+    count_str += ','
+    i = 0 # iterator variable
+    while query[i] != 'FROM': # as long as we are still in the select continue because you cannot do select in db.Aggregate
 
-        fields += ' ' + query[i] + ' : 1,'
         i += 1
 
-    fields = fields[:-1]
-    i = i +1
-    collection = query[i]
+    i = i +1 # ignore the FROM
+    collection = query[i] # table from which the information will be taken
     i = i + 1
-    if i < len(query) and query[i] not in keywords:
+    if i < len(query) and query[i] not in keywords: # sometimes SQL queries rename tables but we ignore that in MongoDB
 
         i += 1
     answer = 'db.' + collection + ".aggregate( " # MongoDB function for aggregation
 
-    while i < len(query) and query[i] == 'INNER':
+    while i < len(query) and query[i] == 'INNER': # if there is an inner join
 
-        i = i + 2
-        lookup = '{$lookup: { from : "'
-        lookup += query[i] + '", localField: "'
-        if query[i+1] not in keywords:
+        i = i + 2 # ignore the keywords
+        lookup = '{$lookup: { from : "' # MongoDB structure
+        lookup += query[i] + '", localField: "' # specifies home key
+        if query[i+1] not in keywords: # skip renaming of tables
             i += 1
         i = i + 2
-        lookup += query[i].split('.')[1] + '", foreignField: "'
-        i = i+2
-        lookup += query[i].split('.')[1] + '", as: "' + collection + '"} },'
+        lookup += query[i].split('.')[1] + '", foreignField: "' # specifies foreign key
+        i = i+2 
+        lookup += query[i].split('.')[1] + '", as: "' + collection + '"} },' # rename final table to the original table
         i = i + 1
-        answer += lookup
+        answer += lookup # add this to the MongoDB query
 
 
-    if i < len(query) and query[i] == 'WHERE':
+    if i < len(query) and query[i] == 'WHERE': # if there is a WHERE clause
 
-        where = '{$match:'
-        count = 0 
+        where = '{$match:' # MongoB keyword
+        count = 0 # tells us if there is an AND in the where clause
+        conditions = '' # stores the actual conditions required
 
         while i < len(query) and (query[i] == 'WHERE' or query[i] == 'AND'):
 
-            count += 1
+            count += 1 # add one every time you find a where matching
             i = i+1 
-            conditions = ''
-            print(query[i])
-            conditions = '{' + (query[i].split('.')[1] if len(query[i].split('.')) > 1 else query[i] )  + " : "
-            if query[i+1] == '=':
+            conditions += '{' + (query[i].split('.')[1] if len(query[i].split('.')) > 1 else query[i] )  + " : " # format to MongoDB
+            if query[i+1] == '=': # if there is an equality then use a colon
 
                 conditions += query[i+2] 
                 i = i + 3
 
-            elif query[i+1] == 'BETWEEN':
+            elif query[i+1] == 'BETWEEN': # if there are dates then use the specified date format
 
                 conditions += '{$gt: ISODate(' + query[i+2] + '), $lt: ISODate(' + query[i+4] + ')}'
                 i+= 5
                 
-            else:
+            else: # else use the mapper function to map the write symbol here
                 
                 conditions += '{ ' + mapper[query[i+1]] + ' : ' + query[i+2] + ' }'
                 i = i+3
 
-            conditions += '},'
+            conditions += '},' # end the conditions
 
-        if count > 1:
+        if count > 1: # if you have been in there for more than once then 
 
-            where += '{ $and: [' + conditions[:-1] + ']}}'
+            where += '{ $and: [' + conditions[:-1] + ']}}' # use the AND version of MongoDB
 
         else:
             
-            where += conditions[:-1] + '}, '
+            where += conditions[:-1] + '},' # otherwise end the clause
 
-        answer += where
+        answer += where # add this to the final query
 
 
-    if i < len(query) and (query[i] == 'GROUP' or query[i] == 'ORDER'):
+    if i < len(query) and (query[i] == 'GROUP' or query[i] == 'ORDER'): # if there is a Group BY or Order BY
 
         i = i + 2
-        group = '{$group: { _id: "' + query[i] + '"'
+        group = '{$group: { _id: "' + query[i] + '"' # in any case, you use group in MongoDB
         i += 1
-        i -= 3 if query[i -3 ] == 'ORDER' else 0
-        if query[i] == 'ORDER' and len(query[i+2]) > 5 and query[i+2][0:5] == 'COUNT':
+        i -= 3 if query[i -3 ] == 'ORDER' else 0 # depending on which one you continue
+        if i < len(query) and query[i] == 'ORDER' and len(query[i+2]) > 5 and query[i+2][0:5] == 'COUNT': # if there is an order by with count
              
-            group += ', count: {$count: ' + ('{}' if query[i+2].split('(')[1][:-1] == '*' else ('{' + query[i+2].split('(')[1][:-1].split('.')[1] + '}') ) + '} }}, { $sort: {count : ' + ('1' if query[i+3] == 'ASC' else '-1') + '}}, '
+            group += ', count: {$count: ' + ('{}' if query[i+2].split('(')[1][:-1] == '*' else ('{' + query[i+2].split('(')[1][:-1].split('.')[1] + '}') ) + '} }}, { $sort: {count : ' + ('1' if query[i+3] == 'ASC' else '-1') + '}},'
              
-        else:
+        elif i < len(query) and query[i] == 'ORDER': # if there is an order by without count
 
             group += '} }, { $sort: {' + query[i+2] + ' : ' + ('1' if query[i+3] == 'ASC' else '-1') + '}},'
 
-        i += 4
-
-        answer += group
-
-    if i < len(query) and query[i] == 'LIMIT':
-
-        answer += '{ $limit : ' + query[i+1] + ' }, '
-
-    answer += count_str
-    answer += ')'
-
-    return answer
-
-
-def simple_SQL_to_MongoDB(query): #ignore function as it is replaced by new complex version
-
-    query = query.split(' ') # split the query on spaces and turn in to array
-    query = query[1:] # remove the initial space
-    answer = 'db.collection.find' # MongoDB function for selection
-    fields = ''
-    i = 0 
-    while query[i] != 'FROM':
+        else:group += '} },' # if there is no orde by and only group
 
-        fields += ' ' + query[i] + ' : 1,'
-        i += 1
-
-    fields = fields[:-1]
-    while query[i] != 'WHERE':
-
-        i += 1
-    
-    i += 1
-    conditions = ''
-    while i+2 < len(query):
-
-        print(i)
-
-        conditions += ' ' + query[i] + ' : '
-        if query[i+1] == '=':
-
-            conditions += query[i+2] 
-
-        elif query[i+1] == 'BETWEEN':
-
-            conditions += '{$gt: ISODate(' + query[i+2] + '), $lt: ISODate(' + query[i+4] + ')}'
-            i+= 6
-            conditions += ','
-            continue
-
-        else:
-
-            conditions += '{ ' + mapper[query[i+1]] + ' : ' + query[i+2] + ' }'
-
-        conditions += ','
-
-        i+= 4
+        i += 4
 
-    
+        answer += group # add answer to group
 
-        
+    if i < len(query) and query[i] == 'LIMIT': # if there is a limit then add that too
 
-    conditions = conditions[:-1]
+        answer += '{ $limit : ' + query[i+1] + ' },'
 
+    answer += '' if count_str == ',' else count_str# finally add back any count command
+    answer = answer[:-1]
+    answer += ')' # end the whole query
 
-    answer += '({' + conditions + '}, {' + fields + '})'
+    return answer # return
 
-    return answer
 
 """# Main method"""
 
@@ -343,17 +301,7 @@ def query_creator(key, organization, plain_query):
   MongoDB_query = query_to_SQL_to_MongoDB(modified_query, key, organization)
   return MongoDB_query
 
-"""#Testers of query creator"""
-
-tests = ["giv me number of orders from the driver elizbeth", "name of driver with maximum ordres", "first two orders with the highest order amount", "address of customer with lowest ordr amount",\
-           "id of customer with most complints", "date of customer support with sales id 21695-828", "number of drivers with order amount 20", "numbser of orders by customer martha", "order amount of most recent customer support",\
-           "amount of the highest order by customber Federica"]
-
-#for test in tests:
-
-   # print(query_creator(api_key, org_key, test)) # put in your api and org keys to use the tester
 
-"""# UI"""
 
 iface = gr.Interface(fn=query_creator, inputs= [gr.Textbox(label = "API Key"), gr.Textbox(label = "Organization Key"),  gr.Textbox(label = "Plain Text Query")], outputs=gr.Textbox(label = "MongoDB Query"), )
 iface.launch()