diff options
Diffstat (limited to 'Doc/includes/sqlite3/text_factory.py')
| -rw-r--r-- | Doc/includes/sqlite3/text_factory.py | 27 |
1 files changed, 19 insertions, 8 deletions
diff --git a/Doc/includes/sqlite3/text_factory.py b/Doc/includes/sqlite3/text_factory.py index a857a15..577378f 100644 --- a/Doc/includes/sqlite3/text_factory.py +++ b/Doc/includes/sqlite3/text_factory.py @@ -3,7 +3,7 @@ import sqlite3 con = sqlite3.connect(":memory:") cur = con.cursor() -AUSTRIA = "\xd6sterreich" +AUSTRIA = u"\xd6sterreich" # by default, rows are returned as Unicode cur.execute("select ?", (AUSTRIA,)) @@ -11,19 +11,30 @@ row = cur.fetchone() assert row[0] == AUSTRIA # but we can make sqlite3 always return bytestrings ... -con.text_factory = bytes +con.text_factory = str cur.execute("select ?", (AUSTRIA,)) row = cur.fetchone() -assert type(row[0]) is bytes +assert type(row[0]) is 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 appends "foo" to all strings -con.text_factory = lambda x: x.decode("utf-8") + "foo" -cur.execute("select ?", ("bar",)) +# 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 row[0] == "barfoo" +assert type(row[0]) is unicode -con.close() +# 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]) is unicode + +cur.execute("select ?", ("Germany",)) +row = cur.fetchone() +assert type(row[0]) is str |