Commit ecdbf085 authored by Zsolt Dollenstein's avatar Zsolt Dollenstein Committed by Łukasz Langa
Browse files

Add support for all valid string literals (#115)

parent ecc29474
Loading
Loading
Loading
Loading
+4 −4
Changes for black.py: 4 added lines, 4 removed lines.
Original line number Diff line number Diff line
@@ -1923,8 +1923,8 @@ def normalize_string_quotes(leaf: Leaf) -> None:

    prefix = leaf.value[:first_quote_pos]
    body = leaf.value[first_quote_pos + len(orig_quote):-len(orig_quote)]
    unescaped_new_quote = re.compile(r"(([^\\]|^)(\\\\)*)" + new_quote)
    escaped_orig_quote = re.compile(r"\\(\\\\)*" + orig_quote)
    unescaped_new_quote = re.compile(rf"(([^\\]|^)(\\\\)*){new_quote}")
    escaped_orig_quote = re.compile(rf"\\(\\\\)*{orig_quote}")
    if "r" in prefix.casefold():
        if unescaped_new_quote.search(body):
            # There's at least one unescaped new_quote in this raw string
@@ -1934,8 +1934,8 @@ def normalize_string_quotes(leaf: Leaf) -> None:
        # Do not introduce or remove backslashes in raw strings
        new_body = body
    else:
        new_body = escaped_orig_quote.sub(f"\\1{orig_quote}", body)
        new_body = unescaped_new_quote.sub(f"\\1\\\\{new_quote}", new_body)
        new_body = escaped_orig_quote.sub(rf"\1{orig_quote}", body)
        new_body = unescaped_new_quote.sub(rf"\1\\{new_quote}", new_body)
    if new_quote == '"""' and new_body[-1] == '"':
        # edge case:
        new_body = new_body[:-1] + '\\"'
+1 −0
Changes for blib2to3/README: 1 added line, 0 removed lines.
Original line number Diff line number Diff line
@@ -7,6 +7,7 @@ Reasons for forking:
  *args and **kwargs
- backport of GH-6143 that restores the ability to reformat legacy usage of
  `async`
- support all types of string literals
- better ability to debug (better reprs)
- INDENT and DEDENT don't hold whitespace and comment prefixes
- ability to Cythonize
+26 −52
Changes for blib2to3/pgen2/tokenize.py: 26 added lines, 52 removed lines.
Original line number Diff line number Diff line
@@ -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]*'
@@ -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'\\]*)*'",
@@ -107,59 +111,29 @@ def maybe(*choices): return group(*choices) + '?'
pseudoprog = re.compile(PseudoToken, re.UNICODE)
single3prog = re.compile(Single3)
double3prog = re.compile(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

+2 −2
Changes for tests/python2.py: 2 added lines, 2 removed lines.
Original line number Diff line number Diff line
@@ -8,7 +8,7 @@


def function((_globals, _locals)):
    exec "print 'hi from exec!'" in _globals, _locals
    exec ur"print 'hi from exec!'" in _globals, _locals


function((globals(), locals()))
@@ -27,7 +27,7 @@ def function((_globals, _locals)):


def function((_globals, _locals)):
    exec "print 'hi from exec!'" in _globals, _locals
    exec ur"print 'hi from exec!'" in _globals, _locals


function((globals(), locals()))
+2 −0
Changes for tests/string_quotes.py: 2 added lines, 0 removed lines.
Original line number Diff line number Diff line
@@ -22,6 +22,7 @@
r'Date d\'expiration:(.*)'
r'Tricky "quote'
r'Not-so-tricky \"quote'
rf'{yay}'
'\n\
The \"quick\"\n\
brown fox\n\
@@ -56,6 +57,7 @@
r"Date d\'expiration:(.*)"
r'Tricky "quote'
r"Not-so-tricky \"quote"
rf"{yay}"
"\n\
The \"quick\"\n\
brown fox\n\