Skip to content

gh-108590: Fix sqlite3.iterdump for invalid unicode in text columns. #108657

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
erlend-aasland merged 7 commits into from
Aug 30, 2023
Merged

gh-108590: Fix sqlite3.iterdump for invalid unicode in text columns. #108657

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
a689bbd
gh-108590: Fix sqlite3.iterdump for invalid unicode in text columns.
CorvinM Aug 29, 2023
03f41df
📜🤖 Added by blurb_it.
blurb-it[bot] Aug 29, 2023
e2939d5
Update Misc/NEWS.d/next/Library/2023-08-29-22-53-48.gh-issue-108590.6…
CorvinM Aug 30, 2023
0643ffc
Update Lib/sqlite3/dump.py
CorvinM Aug 30, 2023
608d919
Address comments
CorvinM Aug 30, 2023
cc7fba8
Use contextmanager
CorvinM Aug 30, 2023
c1b730d
Style nits and a comment
erlend-aasland Aug 30, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 13 additions & 3 deletions Lib/sqlite3/dump.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,11 @@ def _quote_name(name):
def _quote_value(value):
return "'{0}'".format(value.replace("'", "''"))

def _force_decode(bs, *args, **kwargs):
try:
return bs.decode(*args, **kwargs)
except UnicodeDecodeError:
return "".join(chr(c) for c in bs)

def _iterdump(connection):
"""
Expand Down Expand Up @@ -73,9 +78,14 @@ def _iterdump(connection):
"||quote({0})||".format(_quote_name(col)) for col in column_names
)
)
query_res = cu.execute(q)
for row in query_res:
yield("{0};".format(row[0]))
orig_text_factory = connection.text_factory
try:
connection.text_factory = bytes
query_res = cu.execute(q)
for row in query_res:
yield("{0};".format(_force_decode(row[0])))
finally:
connection.text_factory = orig_text_factory

# Now when the type is 'index', 'trigger', or 'view'
q = """
Expand Down
14 changes: 14 additions & 0 deletions Lib/test/test_sqlite3/test_dump.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,6 +133,20 @@ def test_dump_virtual_tables(self):
actual = list(self.cx.iterdump())
self.assertEqual(expected, actual)

def test_dump_unicode_invalid(self):
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()
1 change: 1 addition & 0 deletions Misc/NEWS.d/next/Library/2023-08-29-22-53-48.gh-issue-108590.6k0pOl.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Fixed an issue causing sqlite3.iterdump to crash when encountering invalid unicode in a TEXT column.