Skip to content

bpo-33266: [3.7] Add support for all string literals to lib2to3 (GH-6457) #6488

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
ambv merged 1 commit into from
Apr 16, 2018
Merged

bpo-33266: [3.7] Add support for all string literals to lib2to3 (GH-6457) #6488

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
78 changes: 26 additions & 52 deletions Lib/lib2to3/pgen2/tokenize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,6 +48,10 @@
def group(*choices): return '(' + '|'.join(choices) + ')'
def any(*choices): return group(*choices) + '*'
def maybe(*choices): return group(*choices) + '?'
def _combinations(*l):
return set(
x + y for x in l for y in l + ("",) if x.casefold() != y.casefold()
)

Whitespace = r'[ \f\t]*'
Comment = r'#[^\r\n]*'
Expand All @@ -74,7 +78,7 @@ def maybe(*choices): return group(*choices) + '?'
Single3 = r"[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''"
# Tail end of """ string.
Double3 = r'[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""'
_litprefix = r"(?:[uUrRbBfF]|[rR][bB]|[bBuU][rR])?"
_litprefix = r"(?:[uUrRbBfF]|[rR][fFbB]|[fFbBuU][rR])?"
Triple = group(_litprefix + "'''", _litprefix + '"""')
# Single-line ' or " string.
String = group(_litprefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*'",
Expand Down Expand Up @@ -105,59 +109,29 @@ def maybe(*choices): return group(*choices) + '?'

tokenprog, pseudoprog, single3prog, double3prog = list(map(
re.compile, (Token, PseudoToken, Single3, Double3)))

_strprefixes = (
_combinations('r', 'R', 'f', 'F') |
_combinations('r', 'R', 'b', 'B') |
{'u', 'U', 'ur', 'uR', 'Ur', 'UR'}
)

endprogs = {"'": re.compile(Single), '"': re.compile(Double),
"'''": single3prog, '"""': double3prog,
"r'''": single3prog, 'r"""': double3prog,
"u'''": single3prog, 'u"""': double3prog,
"b'''": single3prog, 'b"""': double3prog,
"f'''": single3prog, 'f"""': double3prog,
"ur'''": single3prog, 'ur"""': double3prog,
"br'''": single3prog, 'br"""': double3prog,
"rb'''": single3prog, 'rb"""': double3prog,
"R'''": single3prog, 'R"""': double3prog,
"U'''": single3prog, 'U"""': double3prog,
"B'''": single3prog, 'B"""': double3prog,
"F'''": single3prog, 'F"""': double3prog,
"uR'''": single3prog, 'uR"""': double3prog,
"Ur'''": single3prog, 'Ur"""': double3prog,
"UR'''": single3prog, 'UR"""': double3prog,
"bR'''": single3prog, 'bR"""': double3prog,
"Br'''": single3prog, 'Br"""': double3prog,
"BR'''": single3prog, 'BR"""': double3prog,
"rB'''": single3prog, 'rB"""': double3prog,
"Rb'''": single3prog, 'Rb"""': double3prog,
"RB'''": single3prog, 'RB"""': double3prog,
'r': None, 'R': None,
'u': None, 'U': None,
'f': None, 'F': None,
'b': None, 'B': None}

triple_quoted = {}
for t in ("'''", '"""',
"r'''", 'r"""', "R'''", 'R"""',
"u'''", 'u"""', "U'''", 'U"""',
"b'''", 'b"""', "B'''", 'B"""',
"f'''", 'f"""', "F'''", 'F"""',
"ur'''", 'ur"""', "Ur'''", 'Ur"""',
"uR'''", 'uR"""', "UR'''", 'UR"""',
"br'''", 'br"""', "Br'''", 'Br"""',
"bR'''", 'bR"""', "BR'''", 'BR"""',
"rb'''", 'rb"""', "Rb'''", 'Rb"""',
"rB'''", 'rB"""', "RB'''", 'RB"""',):
triple_quoted[t] = t
single_quoted = {}
for t in ("'", '"',
"r'", 'r"', "R'", 'R"',
"u'", 'u"', "U'", 'U"',
"b'", 'b"', "B'", 'B"',
"f'", 'f"', "F'", 'F"',
"ur'", 'ur"', "Ur'", 'Ur"',
"uR'", 'uR"', "UR'", 'UR"',
"br'", 'br"', "Br'", 'Br"',
"bR'", 'bR"', "BR'", 'BR"',
"rb'", 'rb"', "Rb'", 'Rb"',
"rB'", 'rB"', "RB'", 'RB"',):
single_quoted[t] = t
**{f"{prefix}'''": single3prog for prefix in _strprefixes},
**{f'{prefix}"""': double3prog for prefix in _strprefixes},
**{prefix: None for prefix in _strprefixes}}

triple_quoted = (
{"'''", '"""'} |
{f"{prefix}'''" for prefix in _strprefixes} |
{f'{prefix}"""' for prefix in _strprefixes}
)
single_quoted = (
{"'", '"'} |
{f"{prefix}'" for prefix in _strprefixes} |
{f'{prefix}"' for prefix in _strprefixes}
)

tabsize = 8

Expand Down
2 changes: 2 additions & 0 deletions Lib/lib2to3/tests/data/py3_test_grammar.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -147,6 +147,8 @@ def testStringLiterals(self):
the \'lazy\' dog.\n\
'
self.assertEquals(x, y)
x = rf"hello \{True}"; y = f"hello \\{True}"
self.assertEquals(x, y)

def testEllipsis(self):
x = ...
Expand Down