FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Download Repo ZIP]   [Original HTTPS Page]

[3.12] gh-108590: Fix sqlite3.iterdump for invalid Unicode in TEXT columns (GH-108657) by CorvinM · Pull Request #108673 · python/cpython · GitHub

Repository navigation

Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension .py  (2) .rst  (1) All 2 file types selected
Viewed files
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Unified
Split
Hide whitespace
Diff view
Unified
Split
Hide whitespace
27 changes: 25 additions & 2 deletions Lib/sqlite3/dump.py
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,28 @@
# future enhancements, you should normally quote any identifier that
# is an English language word, even if you do not have to."


from contextlib import contextmanager


def _force_decode(bs, *args, **kwargs):
# gh-108590: Don't fail if the database contains invalid Unicode data.
try:
return bs.decode(*args, **kwargs)
except UnicodeDecodeError:
return "".join([chr(c) for c in bs])


@contextmanager
def _text_factory(con, factory):
saved_factory = con.text_factory
con.text_factory = factory
try:
yield
finally:
con.text_factory = saved_factory


def _iterdump(connection):
"""
Returns an iterator to the dump of the database in an SQL text format.
Expand Down Expand Up @@ -63,8 +85,9 @@ def _iterdump(connection):
table_name_ident,
",".join("""'||quote("{0}")||'""".format(col.replace('"', '""')) for col in column_names))
query_res = cu.execute(q)
for row in query_res:
yield("{0};".format(row[0]))
with _text_factory(connection, bytes):
for row in query_res:
yield("{0};".format(_force_decode(row[0])))

# Now when the type is 'index', 'trigger', or 'view'
q = """
Expand Down
15 changes: 15 additions & 0 deletions Lib/test/test_sqlite3/test_dump.py
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Original file line number Diff line number Diff line change
Expand Up @@ -137,6 +137,21 @@ def test_dump_virtual_tables(self):
actual = list(self.cx.iterdump())
self.assertEqual(expected, actual)

def test_dump_unicode_invalid(self):
# gh-108590
expected = [
"BEGIN TRANSACTION;",
"CREATE TABLE foo (data TEXT);",
"INSERT INTO \"foo\" VALUES('a\x9f');",
"COMMIT;",
]
self.cu.executescript("""
CREATE TABLE foo (data TEXT);
INSERT INTO foo VALUES (CAST(X'619f' AS TEXT));
""")
actual = list(self.cx.iterdump())
self.assertEqual(expected, actual)


if __name__ == "__main__":
unittest.main()
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Fixed an issue where :meth:`sqlite3.Connection.iterdump` would fail and leave an incomplete SQL dump if a table includes invalid Unicode sequences. Patch by Corvin McPherson

Back | FazBrowse Home | New Git URL