]> git.madduck.net Git - etc/vim.git/blobdiff - src/blib2to3/pgen2/tokenize.py

madduck's git repository

Every one of the projects in this repository is available at the canonical URL git://git.madduck.net/madduck/pub/<projectpath> — see each project's metadata for the exact URL.

All patches and comments are welcome. Please squash your changes to logical commits before using git-format-patch and git-send-email to patches@git.madduck.net. If you'd read over the Git project's submission guidelines and adhered to them, I'd be especially grateful.

SSH access, as well as push access can be individually arranged.

If you use my repositories frequently, consider adding the following snippet to ~/.gitconfig and using the third clone URL listed for each project:

[url "git://git.madduck.net/madduck/"]
  insteadOf = madduck:

docs: update note on GitHub .git-blame-ignore-revs support (#3655)
[etc/vim.git] / src / blib2to3 / pgen2 / tokenize.py
index 283fac2d5375a8f9de49879447fb80bf622c8111..2d0cc4324ce75b7554500c96c1aea7ce69ea923b 100644 (file)
@@ -34,6 +34,7 @@ from typing import (
     Iterator,
     List,
     Optional,
+    Set,
     Text,
     Tuple,
     Pattern,
@@ -52,7 +53,7 @@ from blib2to3.pgen2.grammar import Grammar
 __author__ = "Ka-Ping Yee <ping@lfw.org>"
 __credits__ = "GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro"
 
-import regex as re
+import re
 from codecs import BOM_UTF8, lookup
 from blib2to3.pgen2.token import *
 
@@ -66,19 +67,19 @@ __all__ = [x for x in dir(token) if x[0] != "_"] + [
 del token
 
 
-def group(*choices):
+def group(*choices: str) -> str:
     return "(" + "|".join(choices) + ")"
 
 
-def any(*choices):
+def any(*choices: str) -> str:
     return group(*choices) + "*"
 
 
-def maybe(*choices):
+def maybe(*choices: str) -> str:
     return group(*choices) + "?"
 
 
-def _combinations(*l):
+def _combinations(*l: str) -> Set[str]:
     return set(x + y for x in l for y in l + ("",) if x.casefold() != y.casefold())
 
 
@@ -86,7 +87,7 @@ Whitespace = r"[ \f\t]*"
 Comment = r"#[^\r\n]*"
 Ignore = Whitespace + any(r"\\\r?\n" + Whitespace) + maybe(Comment)
 Name = (  # this is invalid but it's fine because Name comes after Number in all groups
-    r"\w+"
+    r"[^\s#\(\)\[\]\{\}+\-*/!@$%^&=|;:'\",\.<>/?`~\\]+"
 )
 
 Binnumber = r"0[bB]_?[01]+(?:_[01]+)*"
@@ -163,7 +164,6 @@ endprogs: Final = {
     '"""': double3prog,
     **{f"{prefix}'''": single3prog for prefix in _strprefixes},
     **{f'{prefix}"""': double3prog for prefix in _strprefixes},
-    **{prefix: None for prefix in _strprefixes},
 }
 
 triple_quoted: Final = (
@@ -188,15 +188,19 @@ class StopTokenizing(Exception):
     pass
 
 
-def printtoken(type, token, xxx_todo_changeme, xxx_todo_changeme1, line):  # for testing
-    (srow, scol) = xxx_todo_changeme
-    (erow, ecol) = xxx_todo_changeme1
+Coord = Tuple[int, int]
+
+
+def printtoken(
+    type: int, token: Text, srow_col: Coord, erow_col: Coord, line: Text
+) -> None:  # for testing
+    (srow, scol) = srow_col
+    (erow, ecol) = erow_col
     print(
         "%d,%d-%d,%d:\t%s\t%s" % (srow, scol, erow, ecol, tok_name[type], repr(token))
     )
 
 
-Coord = Tuple[int, int]
 TokenEater = Callable[[int, Text, Coord, Coord, Text], None]
 
 
@@ -220,7 +224,7 @@ def tokenize(readline: Callable[[], Text], tokeneater: TokenEater = printtoken)
 
 
 # backwards compatible interface
-def tokenize_loop(readline, tokeneater):
+def tokenize_loop(readline: Callable[[], Text], tokeneater: TokenEater) -> None:
     for token_info in generate_tokens(readline):
         tokeneater(*token_info)
 
@@ -230,7 +234,6 @@ TokenInfo = Union[Tuple[int, str], GoodTokenInfo]
 
 
 class Untokenizer:
-
     tokens: List[Text]
     prev_row: int
     prev_col: int
@@ -293,7 +296,7 @@ class Untokenizer:
 
 
 cookie_re = re.compile(r"^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)", re.ASCII)
-blank_re = re.compile(br"^[ \t\f]*(?:[#\r\n]|$)", re.ASCII)
+blank_re = re.compile(rb"^[ \t\f]*(?:[#\r\n]|$)", re.ASCII)
 
 
 def _get_normal_name(orig_enc: str) -> str:
@@ -425,7 +428,7 @@ def generate_tokens(
     logical line; continuation lines are included.
     """
     lnum = parenlev = continued = 0
-    numchars: Final = "0123456789"
+    numchars: Final[str] = "0123456789"
     contstr, needcont = "", 0
     contline: Optional[str] = None
     indents = [0]
@@ -599,11 +602,15 @@ def generate_tokens(
                 ):
                     if token[-1] == "\n":  # continued string
                         strstart = (lnum, start)
-                        endprog = (
-                            endprogs[initial]
-                            or endprogs[token[1]]
-                            or endprogs[token[2]]
+                        maybe_endprog = (
+                            endprogs.get(initial)
+                            or endprogs.get(token[1])
+                            or endprogs.get(token[2])
                         )
+                        assert (
+                            maybe_endprog is not None
+                        ), f"endprog not found for {token}"
+                        endprog = maybe_endprog
                         contstr, needcont = line[start:], 1
                         contline = line
                         break
@@ -631,7 +638,6 @@ def generate_tokens(
 
                     if token in ("def", "for"):
                         if stashed and stashed[0] == NAME and stashed[1] == "async":
-
                             if token == "def":
                                 async_def = True
                                 async_def_indent = indents[-1]