File size: 9,172 Bytes
b759b87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
"""
 Copyright (c) 2020, salesforce.com, inc.
 All rights reserved.
 SPDX-License-Identifier: BSD-3-Clause
 For full license text, see the LICENSE file in the repo root or https://opensource.org/licenses/BSD-3-Clause

 Encode DB content.
"""

import difflib
from typing import List, Optional, Tuple
from rapidfuzz import fuzz
import sqlite3
import functools

# fmt: off
_stopwords = {'who', 'ourselves', 'down', 'only', 'were', 'him', 'at', "weren't", 'has', 'few', "it's", 'm', 'again',
              'd', 'haven', 'been', 'other', 'we', 'an', 'own', 'doing', 'ma', 'hers', 'all', "haven't", 'in', 'but',
              "shouldn't", 'does', 'out', 'aren', 'you', "you'd", 'himself', "isn't", 'most', 'y', 'below', 'is',
              "wasn't", 'hasn', 'them', 'wouldn', 'against', 'this', 'about', 'there', 'don', "that'll", 'a', 'being',
              'with', 'your', 'theirs', 'its', 'any', 'why', 'now', 'during', 'weren', 'if', 'should', 'those', 'be',
              'they', 'o', 't', 'of', 'or', 'me', 'i', 'some', 'her', 'do', 'will', 'yours', 'for', 'mightn', 'nor',
              'needn', 'the', 'until', "couldn't", 'he', 'which', 'yourself', 'to', "needn't", "you're", 'because',
              'their', 'where', 'it', "didn't", 've', 'whom', "should've", 'can', "shan't", 'on', 'had', 'have',
              'myself', 'am', "don't", 'under', 'was', "won't", 'these', 'so', 'as', 'after', 'above', 'each', 'ours',
              'hadn', 'having', 'wasn', 's', 'doesn', "hadn't", 'than', 'by', 'that', 'both', 'herself', 'his',
              "wouldn't", 'into', "doesn't", 'before', 'my', 'won', 'more', 'are', 'through', 'same', 'how', 'what',
              'over', 'll', 'yourselves', 'up', 'mustn', "mustn't", "she's", 're', 'such', 'didn', "you'll", 'shan',
              'when', "you've", 'themselves', "mightn't", 'she', 'from', 'isn', 'ain', 'between', 'once', 'here',
              'shouldn', 'our', 'and', 'not', 'too', 'very', 'further', 'while', 'off', 'couldn', "hasn't", 'itself',
              'then', 'did', 'just', "aren't"}
# fmt: on

_commonwords = {"no", "yes", "many"}


def is_number(s: str) -> bool:
    try:
        float(s.replace(",", ""))
        return True
    except:
        return False


def is_stopword(s: str) -> bool:
    return s.strip() in _stopwords


def is_commonword(s: str) -> bool:
    return s.strip() in _commonwords


def is_common_db_term(s: str) -> bool:
    return s.strip() in ["id"]


class Match(object):
    def __init__(self, start: int, size: int) -> None:
        self.start = start
        self.size = size


def is_span_separator(c: str) -> bool:
    return c in "'\"()`,.?! "


def split(s: str) -> List[str]:
    return [c.lower() for c in s.strip()]


def prefix_match(s1: str, s2: str) -> bool:
    i, j = 0, 0
    for i in range(len(s1)):
        if not is_span_separator(s1[i]):
            break
    for j in range(len(s2)):
        if not is_span_separator(s2[j]):
            break
    if i < len(s1) and j < len(s2):
        return s1[i] == s2[j]
    elif i >= len(s1) and j >= len(s2):
        return True
    else:
        return False


def get_effective_match_source(s: str, start: int, end: int) -> Match:
    _start = -1

    for i in range(start, start - 2, -1):
        if i < 0:
            _start = i + 1
            break
        if is_span_separator(s[i]):
            _start = i
            break

    if _start < 0:
        return None

    _end = -1
    for i in range(end - 1, end + 3):
        if i >= len(s):
            _end = i - 1
            break
        if is_span_separator(s[i]):
            _end = i
            break

    if _end < 0:
        return None

    while _start < len(s) and is_span_separator(s[_start]):
        _start += 1
    while _end >= 0 and is_span_separator(s[_end]):
        _end -= 1

    return Match(_start, _end - _start + 1)


def get_matched_entries(
    s: str, field_values: List[str], m_theta: float = 0.85, s_theta: float = 0.85
) -> Optional[List[Tuple[str, Tuple[str, str, float, float, int]]]]:
    if not field_values:
        return None

    if isinstance(s, str):
        n_grams = split(s)
    else:
        n_grams = s

    matched = dict()
    for field_value in field_values:
        if not isinstance(field_value, str):
            continue
        fv_tokens = split(field_value)
        sm = difflib.SequenceMatcher(None, n_grams, fv_tokens)
        match = sm.find_longest_match(0, len(n_grams), 0, len(fv_tokens))
        if match.size > 0:
            source_match = get_effective_match_source(
                n_grams, match.a, match.a + match.size
            )
            if source_match: # and source_match.size > 1
                match_str = field_value[match.b : match.b + match.size]
                source_match_str = s[
                    source_match.start : source_match.start + source_match.size
                ]
                c_match_str = match_str.lower().strip()
                c_source_match_str = source_match_str.lower().strip()
                c_field_value = field_value.lower().strip()
                if c_match_str and not is_common_db_term(c_match_str): # and not is_number(c_match_str)
                    if (
                        is_stopword(c_match_str)
                        or is_stopword(c_source_match_str)
                        or is_stopword(c_field_value)
                    ):
                        continue
                    if c_source_match_str.endswith(c_match_str + "'s"):
                        match_score = 1.0
                    else:
                        if prefix_match(c_field_value, c_source_match_str):
                            match_score = fuzz.ratio(c_field_value, c_source_match_str) / 100
                        else:
                            match_score = 0
                    if (
                        is_commonword(c_match_str)
                        or is_commonword(c_source_match_str)
                        or is_commonword(c_field_value)
                    ) and match_score < 1:
                        continue
                    s_match_score = match_score
                    if match_score >= m_theta and s_match_score >= s_theta:
                        if field_value.isupper() and match_score * s_match_score < 1:
                            continue
                        matched[match_str] = (
                            field_value,
                            source_match_str,
                            match_score,
                            s_match_score,
                            match.size,
                        )
    
    if not matched:
        return None
    else:
        return sorted(
            matched.items(),
            key=lambda x: (1e16 * x[1][2] + 1e8 * x[1][3] + x[1][4]),
            reverse=True,
        )


@functools.lru_cache(maxsize=1000, typed=False)
def get_column_picklist(table_name: str, column_name: str, db_path: str) -> list:
    fetch_sql = "SELECT DISTINCT `{}` FROM `{}`".format(column_name, table_name)
    try:
        conn = sqlite3.connect(db_path)
        conn.text_factory = bytes
        c = conn.cursor()
        c.execute(fetch_sql)
        picklist = set()
        for x in c.fetchall():
            if isinstance(x[0], str):
                picklist.add(x[0].encode("utf-8"))
            elif isinstance(x[0], bytes):
                try:
                    picklist.add(x[0].decode("utf-8"))
                except UnicodeDecodeError:
                    picklist.add(x[0].decode("latin-1"))
            else:
                picklist.add(x[0])
        picklist = list(picklist)
    except Exception as e:
        picklist = []
    finally:
        conn.close()
    return picklist


def get_database_matches(
    question: str,
    table_name: str,
    column_name: str,
    db_path: str,
    top_k_matches: int = 2,
    match_threshold: float = 0.85,
) -> List[str]:
    picklist = get_column_picklist(
        table_name=table_name, column_name=column_name, db_path=db_path
    )
    # only maintain data in ``str'' type
    picklist = [ele.strip() for ele in picklist if isinstance(ele, str)]
    # picklist is unordered, we sort it to ensure the reproduction stability
    picklist = sorted(picklist)
    
    matches = []
    if picklist and isinstance(picklist[0], str):
        matched_entries = get_matched_entries(
            s=question,
            field_values=picklist,
            m_theta=match_threshold,
            s_theta=match_threshold,
        )

        if matched_entries:
            num_values_inserted = 0
            for _match_str, (
                field_value,
                _s_match_str,
                match_score,
                s_match_score,
                _match_size,
            ) in matched_entries:
                if "name" in column_name and match_score * s_match_score < 1:
                    continue
                if table_name != "sqlite_sequence":  # Spider database artifact
                    matches.append(field_value.strip())
                    num_values_inserted += 1
                    if num_values_inserted >= top_k_matches:
                        break
    return matches