Skip to content
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.

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

Improve InvalidURL error message. #3250

Merged
merged 7 commits into from
Jul 26, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
1 change: 1 addition & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).

### Fixed

* Improved error messaging for `InvalidURL` exceptions. (#3250)
* Fix `app` type signature in `ASGITransport`. (#3109)

## 0.27.0 (21st February, 2024)
Expand Down
17 changes: 14 additions & 3 deletions httpx/_urlparse.py
Original file line number Diff line number Diff line change
Expand Up @@ -160,7 +160,12 @@ def urlparse(url: str = "", **kwargs: str | None) -> ParseResult:
# If a URL includes any ASCII control characters including \t, \r, \n,
# then treat it as invalid.
if any(char.isascii() and not char.isprintable() for char in url):
raise InvalidURL("Invalid non-printable ASCII character in URL")
char = next(char for char in url if char.isascii() and not char.isprintable())
idx = url.find(char)
error = (
f"Invalid non-printable ASCII character in URL, {char!r} at position {idx}."
)
raise InvalidURL(error)

# Some keyword arguments require special handling.
# ------------------------------------------------
Expand Down Expand Up @@ -205,9 +210,15 @@ def urlparse(url: str = "", **kwargs: str | None) -> ParseResult:
# If a component includes any ASCII control characters including \t, \r, \n,
# then treat it as invalid.
if any(char.isascii() and not char.isprintable() for char in value):
raise InvalidURL(
f"Invalid non-printable ASCII character in URL component '{key}'"
char = next(
char for char in value if char.isascii() and not char.isprintable()
)
idx = value.find(char)
error = (
f"Invalid non-printable ASCII character in URL {key} component, "
f"{char!r} at position {idx}."
)
raise InvalidURL(error)

# Ensure that keyword arguments match as a valid regex.
if not COMPONENT_REGEX[key].fullmatch(value):
Expand Down
10 changes: 6 additions & 4 deletions tests/models/test_url.py
Original file line number Diff line number Diff line change
Expand Up @@ -367,15 +367,17 @@ def test_url_excessively_long_component():
def test_url_non_printing_character_in_url():
with pytest.raises(httpx.InvalidURL) as exc:
httpx.URL("https://www.example.com/\n")
assert str(exc.value) == "Invalid non-printable ASCII character in URL"
assert str(exc.value) == (
"Invalid non-printable ASCII character in URL, '\\n' at position 24."
)


def test_url_non_printing_character_in_component():
with pytest.raises(httpx.InvalidURL) as exc:
httpx.URL("https://www.example.com", path="/\n")
assert (
str(exc.value)
== "Invalid non-printable ASCII character in URL component 'path'"
assert str(exc.value) == (
"Invalid non-printable ASCII character in URL path component, "
"'\\n' at position 1."
)


Expand Down