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.

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

Jump to bottom

Support named unicode characters in f-strings #160

Merged
merged 2 commits into from
Nov 22, 2020
Merged

Support named unicode characters in f-strings #160

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d42bc31
Support named unicode characters in f-strings
thatch Nov 21, 2020
ed7f35a
Improve tests for named unicode escapes
thatch Nov 22, 2020
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
11 changes: 8 additions & 3 deletions parso/python/tokenize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,9 +110,14 @@ def _get_token_collection(version_info):
_create_token_collection(version_info)
return result


fstring_string_single_line = _compile(r'(?:\{\{|\}\}|\\(?:\r\n?|\n)|[^{}\r\n])+')
fstring_string_multi_line = _compile(r'(?:[^{}]+|\{\{|\}\})+')
unicode_character_name = r'[A-Za-z0-9\-]+(?: [A-Za-z0-9\-]+)*'
fstring_string_single_line = _compile(
r'(?:\{\{|\}\}|\\N\{' + unicode_character_name +
r'\}|\\(?:\r\n?|\n)|\\[^\r\nN]|[^{}\r\n\\])+'
)
fstring_string_multi_line = _compile(
r'(?:\{\{|\}\}|\\N\{' + unicode_character_name + r'\}|\\[^N]|[^{}\\])+'
)
fstring_format_spec_single_line = _compile(r'(?:\\(?:\r\n?|\n)|[^{}\r\n])+')
fstring_format_spec_multi_line = _compile(r'[^{}]+')

Expand Down
14 changes: 14 additions & 0 deletions test/test_fstring.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,6 +67,15 @@ def grammar():
'f"{x, *y}"',
'f"{*x, y}"',
'f"{x for x in [1]}"',

# named unicode characters
'f"\\N{BULLET}"',
'f"\\N{FLEUR-DE-LIS}"',
'f"\\N{NO ENTRY}"',
'f"\\N{no entry}"',
'f"\\N{SOYOMBO LETTER -A}"',
'f"\\N{DOMINO TILE HORIZONTAL-00-00}"',
'f"""\\N{NO ENTRY}"""',
]
)
def test_valid(code, grammar):
Expand Down Expand Up @@ -104,6 +113,11 @@ def test_valid(code, grammar):

# a newline without a line continuation inside a single-line string
'f"abc\ndef"',

# various named unicode escapes that aren't name-shaped
'f"\\N{ BULLET }"',
'f"\\N{NO ENTRY}"',
'f"""\\N{NO\nENTRY}"""',
]
)
def test_invalid(code, grammar):
Expand Down