Skip to content
Snippets Groups Projects
Select Git revision
  • assignment-2.2
  • master default
  • assignment-2.1
  • assignment2.0 protected
4 results
Blame Permalink
Parser.py 3.62 KiB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93 






import re


def check_if_address_valid(address):
    """
    Take input address and scrape date
    :param addr:
    :return:
    """
    x = re.search("^https://www.goodreads.com/book/show/[0-9]+", address)
    if x:
        return True
    else:
        return False


def parse_query_to_url(query):
    elements = re.findall("[0-9A-Za-z_\"><.]+", query)
    count = len(elements)
    if count == 2:
        # can only be A.B:C or wrong
        if re.search("^[0-9a-zA-Z_.]+:[0-9a-zA-Z_\".]", query):
            return url_safe(elements[0] + ":3A" + elements[1])
        else:
            print("Invalid query1.")
            return ""
    elif count == 3:
        # a pair and one of [NOT, >, <].
        if re.search("^[0-9a-zA-Z_.]+:\s*NOT\s*[0-9a-zA-Z_\".]", query):
            return url_safe(elements[0] + "%3A" + "NOT" + elements[2])
        elif re.search("^[0-9a-zA-Z_.]+:\s*>\s*[0-9a-zA-Z_\".]", query):
            return url_safe(elements[0] + "%3A" + ">" + elements[2])
        elif re.search("^[0-9a-zA-Z_.]+:\s*<\s*[0-9a-zA-Z_\".]", query):
            return url_safe(elements[0] + "%3A" + "<" + elements[2])
        else:
            print("Invalid query2.")
            return ""
    elif 5 <= count <= 7:
        # AND or OR operator
        if re.search(".*\sAND\s.*", query):
            parts = query.split(" AND ")
            return parse_query_to_url(parts[0]) + "%26AND%26" + parse_query_to_url(parts[1])
        elif re.search(".*\sOR\s.*", query):
            parts = query.split(" OR ")
            return parse_query_to_url(parts[0]) + "%26OR%26" + parse_query_to_url(parts[1])
        else:
            print("Invalid query3.")
            return ""


def parse_url_to_query(url):
    query_str = url.replace("%20", " ").replace("%22", "\"").replace("%3C", "<").replace("%3E", ">").replace("%26", "&")
    return query_str.replace(" AND ", "&AND&").replace(" OR ", "&OR&").replace(": ", ":").replace(" > ", ">")\
        .replace(" < ", "<")


def parse_query_to_json(pair):
    elements = re.findall("[0-9A-Za-z\"_.]+", pair)
    count = len(elements)
    if count != 2 and count != 3:
        print("Failed to parse query: invalid args number")
        return {"wrong": "True"}            # will never be founded in database
    elif count == 3:
        # A.B: NOT C
        if re.search("^[0-9.]*$", elements[2]) and not re.search("id", elements[0]):
            return {elements[0].split(".")[1]: {"$ne": float(elements[2])}}
        else:
            return {elements[0].split(".")[1]: {"$not": {"$regex": elements[2], "$options": "i"}}}
    else:
        # can be A.B: C, A.B: "C", A.B > C, or A.B < C
        if re.search(":", pair):
            if re.search("^[0-9.]*$", elements[1]) and not re.search("id", elements[0]):
                return {elements[0].split(".")[1]: float(elements[1])}
            else:
                if re.search("\".*\"", elements[1]):
                    return {elements[0].split(".")[1]: elements[1]}
                else:
                    return {elements[0].split(".")[1]: {"$regex": elements[1], "$options": "i"}}
        else:
            if len(elements[0].split(".")) != 2:
                return {"wrong": "True"}
            if re.search(">", pair):
                return {elements[0].split(".")[1]: {"$gt": float(elements[1])}}
            elif re.search("<", pair):
                return {elements[0].split(".")[1]: {"$lt": float(elements[1])}}
            else:
                print("Failed to parse query: unknown operator")
                return {"wrong": "True"}


def url_safe(element):
    return element.replace("\"", "%22").replace(">", "%3E").replace("<", "%3C").replace("&", "%26").replace(":", "%3A")