Add changelog entry

[etc/vim.git] / blib2to3 / pgen2 / tokenize.py

diff --git a/blib2to3/pgen2/tokenize.py b/blib2to3/pgen2/tokenize.py
index 669c3f183bb8907a01e863167be8c1c2680b1e85..a352713f7deaba741e1d13c2a10da43be544d26a 100644 (file)
--- a/blib2to3/pgen2/tokenize.py
+++ b/blib2to3/pgen2/tokenize.py
@@ -29,7 +29,7 @@ __author__ = 'Ka-Ping Yee <ping@lfw.org>'
 __credits__ = \
     'GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro'
 
 __credits__ = \
     'GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro'
 

-import string, re
+import string, re, unicodedata

 from codecs import BOM_UTF8, lookup
 from blib2to3.pgen2.token import *
 
 from codecs import BOM_UTF8, lookup
 from blib2to3.pgen2.token import *
 


@@ -48,11 +48,15 @@ except NameError:
 def group(*choices): return '(' + '|'.join(choices) + ')'
 def any(*choices): return group(*choices) + '*'
 def maybe(*choices): return group(*choices) + '?'
 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]*'
 Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment)
 
 Whitespace = r'[ \f\t]*'
 Comment = r'#[^\r\n]*'
 Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment)

-Name = r'[a-zA-Z_]\w*'
+Name = r'[^\d\W]\w*'

 
 Binnumber = r'0[bB]_?[01]+(?:_[01]+)*'
 Hexnumber = r'0[xX]_?[\da-fA-F]+(?:_[\da-fA-F]+)*[lL]?'
 
 Binnumber = r'0[bB]_?[01]+(?:_[01]+)*'
 Hexnumber = r'0[xX]_?[\da-fA-F]+(?:_[\da-fA-F]+)*[lL]?'


@@ -74,7 +78,7 @@ Double = r'[^"\\]*(?:\\.[^"\\]*)*"'
 Single3 = r"[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''"
 # Tail end of """ string.
 Double3 = r'[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""'
 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'\\]*)*'",
 Triple = group(_litprefix + "'''", _litprefix + '"""')
 # Single-line ' or " string.
 String = group(_litprefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*'",


@@ -103,61 +107,33 @@ ContStr = group(_litprefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*" +
 PseudoExtras = group(r'\\\r?\n', Comment, Triple)
 PseudoToken = Whitespace + group(PseudoExtras, Number, Funny, ContStr, Name)
 
 PseudoExtras = group(r'\\\r?\n', Comment, Triple)
 PseudoToken = Whitespace + group(PseudoExtras, Number, Funny, ContStr, Name)
 

-tokenprog, pseudoprog, single3prog, double3prog = list(map(
-    re.compile, (Token, PseudoToken, Single3, Double3)))
+tokenprog = re.compile(Token, re.UNICODE)
+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,
 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
 
 
 tabsize = 8
 


@@ -358,6 +334,8 @@ def untokenize(iterable):
     ut = Untokenizer()
     return ut.untokenize(iterable)
 
     ut = Untokenizer()
     return ut.untokenize(iterable)
 

+InitialCategories = {'Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl', 'Mn', 'Mc', 'Nd', 'Pc'}
+

 def generate_tokens(readline):
     """
     The generate_tokens() generator requires one argument, readline, which
 def generate_tokens(readline):
     """
     The generate_tokens() generator requires one argument, readline, which


@@ -430,24 +408,24 @@ def generate_tokens(readline):
                 yield stashed
                 stashed = None
 
                 yield stashed
                 stashed = None
 

+            if line[pos] in '\r\n':            # skip blank lines
+                yield (NL, line[pos:], (lnum, pos), (lnum, len(line)), line)
+                continue
+
+            if line[pos] == '#':               # skip comments
+                comment_token = line[pos:].rstrip('\r\n')
+                nl_pos = pos + len(comment_token)
+                yield (COMMENT, comment_token,
+                        (lnum, pos), (lnum, pos + len(comment_token)), line)
+                yield (NL, line[nl_pos:],
+                        (lnum, nl_pos), (lnum, len(line)), line)
+                continue
+

             if column > indents[-1]:           # count indents
                 indents.append(column)
                 yield (INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
 
             if column > indents[-1]:           # count indents
                 indents.append(column)
                 yield (INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
 

-            if line[pos] in '#\r\n':           # skip comments or blank lines
-                if line[pos] == '#':
-                    comment_token = line[pos:].rstrip('\r\n')
-                    nl_pos = pos + len(comment_token)
-                    yield (COMMENT, comment_token,
-                           (lnum, pos), (lnum, pos + len(comment_token)), line)
-                    yield (NL, line[nl_pos:],
-                           (lnum, nl_pos), (lnum, len(line)), line)
-                else:
-                    yield ((NL, COMMENT)[line[pos] == '#'], line[pos:],
-                           (lnum, pos), (lnum, len(line)), line)
-                continue
-
-            while column < indents[-1]:         # count dedents
+            while column < indents[-1]:        # count dedents

                 if column not in indents:
                     raise IndentationError(
                         "unindent does not match any outer indentation level",
                 if column not in indents:
                     raise IndentationError(
                         "unindent does not match any outer indentation level",


@@ -528,7 +506,8 @@ def generate_tokens(readline):
                             yield stashed
                             stashed = None
                         yield (STRING, token, spos, epos, line)
                             yield stashed
                             stashed = None
                         yield (STRING, token, spos, epos, line)

-                elif initial in namechars:                 # ordinary name
+                elif (initial in namechars or              # ordinary name
+                      unicodedata.category(initial) in InitialCategories):

                     if token in ('async', 'await'):
                         if async_def:
                             yield (ASYNC if token == 'async' else AWAIT,
                     if token in ('async', 'await'):
                         if async_def:
                             yield (ASYNC if token == 'async' else AWAIT,