This repository was archived by the owner on Mar 12, 2020. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 39
Expand file tree
/
Copy pathParseUtils.py
More file actions
119 lines (100 loc) · 4.32 KB
/
ParseUtils.py
File metadata and controls
119 lines (100 loc) · 4.32 KB
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
import os
import sys
import itertools
from collections import namedtuple
dirpath = os.path.join(os.path.dirname(__file__), 'lib')
if dirpath not in sys.path:
sys.path.append(dirpath)
import sqlparse
from sqlparse.sql import IdentifierList, Identifier, Function
from sqlparse.tokens import Keyword, DML
class Reference(namedtuple('Reference', ['schema', 'name', 'alias', 'is_function'])):
__slots__ = ()
def has_alias(self):
return self.alias is not None
@property
def is_query_alias(self):
return self.name is None and self.alias is not None
@property
def is_table_alias(self):
return self.name is not None and self.alias is not None and not self.is_function
@property
def full_name(self):
if self.schema is None:
return self.name
else:
return self.schema + '.' + self.name
def _is_subselect(parsed):
if not parsed.is_group:
return False
for item in parsed.tokens:
if item.ttype is DML and item.value.upper() in ('SELECT', 'INSERT',
'UPDATE', 'CREATE', 'DELETE'):
return True
return False
def _identifier_is_function(identifier):
return any(isinstance(t, Function) for t in identifier.tokens)
def _extract_from_part(parsed):
tbl_prefix_seen = False
for item in parsed.tokens:
if item.is_group:
for x in _extract_from_part(item):
yield x
if tbl_prefix_seen:
if _is_subselect(item):
for x in _extract_from_part(item):
yield x
# An incomplete nested select won't be recognized correctly as a
# sub-select. eg: 'SELECT * FROM (SELECT id FROM user'. This causes
# the second FROM to trigger this elif condition resulting in a
# StopIteration. So we need to ignore the keyword if the keyword
# FROM.
# Also 'SELECT * FROM abc JOIN def' will trigger this elif
# condition. So we need to ignore the keyword JOIN and its variants
# INNER JOIN, FULL OUTER JOIN, etc.
elif item.ttype is Keyword and (
not item.value.upper() == 'FROM') and (
not item.value.upper().endswith('JOIN')):
tbl_prefix_seen = False
else:
yield item
elif item.ttype is Keyword or item.ttype is Keyword.DML:
item_val = item.value.upper()
if (item_val in ('COPY', 'FROM', 'INTO', 'UPDATE', 'TABLE') or
item_val.endswith('JOIN')):
tbl_prefix_seen = True
# 'SELECT a, FROM abc' will detect FROM as part of the column list.
# So this check here is necessary.
elif isinstance(item, IdentifierList):
for identifier in item.get_identifiers():
if (identifier.ttype is Keyword and
identifier.value.upper() == 'FROM'):
tbl_prefix_seen = True
break
def _extract_table_identifiers(token_stream):
for item in token_stream:
if isinstance(item, IdentifierList):
for ident in item.get_identifiers():
try:
alias = ident.get_alias()
schema_name = ident.get_parent_name()
real_name = ident.get_real_name()
except AttributeError:
continue
if real_name:
yield Reference(schema_name, real_name,
alias, _identifier_is_function(ident))
elif isinstance(item, Identifier):
yield Reference(item.get_parent_name(), item.get_real_name(),
item.get_alias(), _identifier_is_function(item))
elif isinstance(item, Function):
yield Reference(item.get_parent_name(), item.get_real_name(),
item.get_alias(), _identifier_is_function(item))
def extractTables(sql):
# let's handle multiple statements in one sql string
extracted_tables = []
statements = list(sqlparse.parse(sql))
for statement in statements:
stream = _extract_from_part(statement)
extracted_tables.append(list(_extract_table_identifiers(stream)))
return list(itertools.chain(*extracted_tables))