VimPlug/parso
1
0
Fork 0
mirror of https://github.com/davidhalter/parso.git synced 2025-12-06 04:44:29 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Support named unicode characters in f-strings (#160)

Browse Source 
* Support named unicode characters in f-strings

Fixes #154

The previous behavior misinterpreted the curly braces as enclosing an
expression.  This change does some cursory validation so we can still
get parse errors in the most egregious cases, but does not validate that
the names are actually valid, only that they are name-shaped and have a
chance of being valid.

The character names appear to obey a few rules:
* Case insensitive
* Name characters are `[A-Z0-9 \-]`
* Whitespace before or after is not allowed
* Whitespace in the middle may only be a single space between words
* Dashes may occur at the start or middle of a word

```py
f"\N{A B}"           # might be legal
f"\N{a b}"           # equivalent to above
f"\N{A     B}"       # no way
f"\N{    A B     }"  # no way
f"""\N{A
B}"""                # no way
```

For confirming this regex matches all (current) unicode character names:

```py
import re
import sys
import unicodedata

R = re.compile(r"[A-Za-z0-9\-]+(?: [A-Za-z0-9\-]+)*")

for i in range(sys.maxunicode):
    try:
        name = unicodedata.name(chr(i))
    except ValueError:
        # Some small values like 0 and 1 have no name, /shrug
        continue
    m = R.fullmatch(name)
    if m is None:
        print("FAIL", repr(name))
```

* Improve tests for named unicode escapes
This commit is contained in:
Tim Hatch
2020-11-22 04:37:04 -08:00
committed by GitHub
parent b08b61b578
commit d39aadc4cc
2 changed files with 26 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
parso/python/tokenize.py
View File

@@ -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'[^{}]+')

18
test/test_fstring.py
View File

@@ -67,6 +67,17 @@ 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"Combo {expr} and \\N{NO ENTRY}"',
'f"\\N{NO ENTRY} and {expr}"',
'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):
@@ -104,6 +115,11 @@ 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):
@@ -122,6 +138,8 @@ def test_invalid(code, grammar):
(1, 10), (1, 11), (1, 12), (1, 13)]),
('f"""\n {\nfoo\n }"""', [(1, 0), (1, 4), (2, 1), (3, 0), (4, 1),
(4, 2), (4, 5)]),
('f"\\N{NO ENTRY} and {expr}"', [(1, 0), (1, 2), (1, 19), (1, 20),
(1, 24), (1, 25), (1, 26)]),
]
)
def test_tokenize_start_pos(code, positions):