summaryrefslogtreecommitdiffstats
path: root/Doc/includes/sqlite3/text_factory.py
blob: 195949866f46a2ef340e567004b8157e333be69e (plain)
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
import sqlite3

con = sqlite3.connect(":memory:")
cur = con.cursor()

# Create the table
con.execute("create table person(lastname, firstname)")

AUSTRIA = u"\xd6sterreich"

# by default, rows are returned as Unicode
cur.execute("select ?", (AUSTRIA,))
row = cur.fetchone()
assert row[0] == AUSTRIA

# but we can make sqlite3 always return bytestrings ...
con.text_factory = str
cur.execute("select ?", (AUSTRIA,))
row = cur.fetchone()
assert type(row[0]) == str
# the bytestrings will be encoded in UTF-8, unless you stored garbage in the
# database ...
assert row[0] == AUSTRIA.encode("utf-8")

# we can also implement a custom text_factory ...
# here we implement one that will ignore Unicode characters that cannot be
# decoded from UTF-8
con.text_factory = lambda x: unicode(x, "utf-8", "ignore")
cur.execute("select ?", ("this is latin1 and would normally create errors" +
                         u"\xe4\xf6\xfc".encode("latin1"),))
row = cur.fetchone()
assert type(row[0]) == unicode

# sqlite3 offers a built-in optimized text_factory that will return bytestring
# objects, if the data is in ASCII only, and otherwise return unicode objects
con.text_factory = sqlite3.OptimizedUnicode
cur.execute("select ?", (AUSTRIA,))
row = cur.fetchone()
assert type(row[0]) == unicode

cur.execute("select ?", ("Germany",))
row = cur.fetchone()
assert type(row[0]) == str