]> 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:

Make pre-commit do less (#3838)
[etc/vim.git] / src / blib2to3 / pgen2 / tokenize.py
index 82ac5130badd92724779136362bdb235a37bf757..d0607f4b1e17b202d4d19603287ed5cfc0a57288 100644 (file)
@@ -30,31 +30,41 @@ each time a new token is found."""
 import sys
 from typing import (
     Callable,
 import sys
 from typing import (
     Callable,
+    Final,
     Iterable,
     Iterator,
     List,
     Optional,
     Iterable,
     Iterator,
     List,
     Optional,
-    Text,
-    Tuple,
     Pattern,
     Pattern,
+    Set,
+    Tuple,
     Union,
     cast,
 )
 
     Union,
     cast,
 )
 
-if sys.version_info >= (3, 8):
-    from typing import Final
-else:
-    from typing_extensions import Final
-
-from blib2to3.pgen2.token import *
 from blib2to3.pgen2.grammar import Grammar
 from blib2to3.pgen2.grammar import Grammar
+from blib2to3.pgen2.token import (
+    ASYNC,
+    AWAIT,
+    COMMENT,
+    DEDENT,
+    ENDMARKER,
+    ERRORTOKEN,
+    INDENT,
+    NAME,
+    NEWLINE,
+    NL,
+    NUMBER,
+    OP,
+    STRING,
+    tok_name,
+)
 
 __author__ = "Ka-Ping Yee <ping@lfw.org>"
 __credits__ = "GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro"
 
 import re
 from codecs import BOM_UTF8, lookup
 
 __author__ = "Ka-Ping Yee <ping@lfw.org>"
 __credits__ = "GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro"
 
 import re
 from codecs import BOM_UTF8, lookup
-from blib2to3.pgen2.token import *
 
 from . import token
 
 
 from . import token
 
@@ -66,20 +76,20 @@ __all__ = [x for x in dir(token) if x[0] != "_"] + [
 del token
 
 
 del token
 
 
-def group(*choices):
+def group(*choices: str) -> str:
     return "(" + "|".join(choices) + ")"
 
 
     return "(" + "|".join(choices) + ")"
 
 
-def any(*choices):
+def any(*choices: str) -> str:
     return group(*choices) + "*"
 
 
     return group(*choices) + "*"
 
 
-def maybe(*choices):
+def maybe(*choices: str) -> str:
     return group(*choices) + "?"
 
 
     return group(*choices) + "?"
 
 
-def _combinations(*l):
-    return set(x + y for x in l for y in l + ("",) if x.casefold() != y.casefold())
+def _combinations(*l: str) -> Set[str]:
+    return {x + y for x in l for y in l + ("",) if x.casefold() != y.casefold()}
 
 
 Whitespace = r"[ \f\t]*"
 
 
 Whitespace = r"[ \f\t]*"
@@ -187,19 +197,23 @@ class StopTokenizing(Exception):
     pass
 
 
     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: str, srow_col: Coord, erow_col: Coord, line: str
+) -> 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))
     )
 
 
     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]
+TokenEater = Callable[[int, str, Coord, Coord, str], None]
 
 
 
 
-def tokenize(readline: Callable[[], Text], tokeneater: TokenEater = printtoken) -> None:
+def tokenize(readline: Callable[[], str], tokeneater: TokenEater = printtoken) -> None:
     """
     The tokenize() function accepts two parameters: one representing the
     input stream, and one providing an output mechanism for tokenize().
     """
     The tokenize() function accepts two parameters: one representing the
     input stream, and one providing an output mechanism for tokenize().
@@ -219,18 +233,17 @@ def tokenize(readline: Callable[[], Text], tokeneater: TokenEater = printtoken)
 
 
 # backwards compatible interface
 
 
 # backwards compatible interface
-def tokenize_loop(readline, tokeneater):
+def tokenize_loop(readline: Callable[[], str], tokeneater: TokenEater) -> None:
     for token_info in generate_tokens(readline):
         tokeneater(*token_info)
 
 
     for token_info in generate_tokens(readline):
         tokeneater(*token_info)
 
 
-GoodTokenInfo = Tuple[int, Text, Coord, Coord, Text]
+GoodTokenInfo = Tuple[int, str, Coord, Coord, str]
 TokenInfo = Union[Tuple[int, str], GoodTokenInfo]
 
 
 class Untokenizer:
 TokenInfo = Union[Tuple[int, str], GoodTokenInfo]
 
 
 class Untokenizer:
-
-    tokens: List[Text]
+    tokens: List[str]
     prev_row: int
     prev_col: int
 
     prev_row: int
     prev_col: int
 
@@ -246,13 +259,13 @@ class Untokenizer:
         if col_offset:
             self.tokens.append(" " * col_offset)
 
         if col_offset:
             self.tokens.append(" " * col_offset)
 
-    def untokenize(self, iterable: Iterable[TokenInfo]) -> Text:
+    def untokenize(self, iterable: Iterable[TokenInfo]) -> str:
         for t in iterable:
             if len(t) == 2:
                 self.compat(cast(Tuple[int, str], t), iterable)
                 break
             tok_type, token, start, end, line = cast(
         for t in iterable:
             if len(t) == 2:
                 self.compat(cast(Tuple[int, str], t), iterable)
                 break
             tok_type, token, start, end, line = cast(
-                Tuple[int, Text, Coord, Coord, Text], t
+                Tuple[int, str, Coord, Coord, str], t
             )
             self.add_whitespace(start)
             self.tokens.append(token)
             )
             self.add_whitespace(start)
             self.tokens.append(token)
@@ -262,7 +275,7 @@ class Untokenizer:
                 self.prev_col = 0
         return "".join(self.tokens)
 
                 self.prev_col = 0
         return "".join(self.tokens)
 
-    def compat(self, token: Tuple[int, Text], iterable: Iterable[TokenInfo]) -> None:
+    def compat(self, token: Tuple[int, str], iterable: Iterable[TokenInfo]) -> None:
         startline = False
         indents = []
         toks_append = self.tokens.append
         startline = False
         indents = []
         toks_append = self.tokens.append
@@ -334,7 +347,7 @@ def detect_encoding(readline: Callable[[], bytes]) -> Tuple[str, List[bytes]]:
         try:
             return readline()
         except StopIteration:
         try:
             return readline()
         except StopIteration:
-            return bytes()
+            return b""
 
     def find_cookie(line: bytes) -> Optional[str]:
         try:
 
     def find_cookie(line: bytes) -> Optional[str]:
         try:
@@ -383,7 +396,7 @@ def detect_encoding(readline: Callable[[], bytes]) -> Tuple[str, List[bytes]]:
     return default, [first, second]
 
 
     return default, [first, second]
 
 
-def untokenize(iterable: Iterable[TokenInfo]) -> Text:
+def untokenize(iterable: Iterable[TokenInfo]) -> str:
     """Transform tokens back into Python source code.
 
     Each element returned by the iterable must be a token sequence
     """Transform tokens back into Python source code.
 
     Each element returned by the iterable must be a token sequence
@@ -406,7 +419,7 @@ def untokenize(iterable: Iterable[TokenInfo]) -> Text:
 
 
 def generate_tokens(
 
 
 def generate_tokens(
-    readline: Callable[[], Text], grammar: Optional[Grammar] = None
+    readline: Callable[[], str], grammar: Optional[Grammar] = None
 ) -> Iterator[GoodTokenInfo]:
     """
     The generate_tokens() generator requires one argument, readline, which
 ) -> Iterator[GoodTokenInfo]:
     """
     The generate_tokens() generator requires one argument, readline, which
@@ -603,7 +616,9 @@ def generate_tokens(
                             or endprogs.get(token[1])
                             or endprogs.get(token[2])
                         )
                             or endprogs.get(token[1])
                             or endprogs.get(token[2])
                         )
-                        assert maybe_endprog is not None, f"endprog not found for {token}"
+                        assert (
+                            maybe_endprog is not None
+                        ), f"endprog not found for {token}"
                         endprog = maybe_endprog
                         contstr, needcont = line[start:], 1
                         contline = line
                         endprog = maybe_endprog
                         contstr, needcont = line[start:], 1
                         contline = line
@@ -632,7 +647,6 @@ def generate_tokens(
 
                     if token in ("def", "for"):
                         if stashed and stashed[0] == NAME and stashed[1] == "async":
 
                     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]
                             if token == "def":
                                 async_def = True
                                 async_def_indent = indents[-1]
@@ -675,14 +689,12 @@ def generate_tokens(
         yield stashed
         stashed = None
 
         yield stashed
         stashed = None
 
-    for indent in indents[1:]:  # pop remaining indent levels
+    for _indent in indents[1:]:  # pop remaining indent levels
         yield (DEDENT, "", (lnum, 0), (lnum, 0), "")
     yield (ENDMARKER, "", (lnum, 0), (lnum, 0), "")
 
 
 if __name__ == "__main__":  # testing
         yield (DEDENT, "", (lnum, 0), (lnum, 0), "")
     yield (ENDMARKER, "", (lnum, 0), (lnum, 0), "")
 
 
 if __name__ == "__main__":  # testing
-    import sys
-
     if len(sys.argv) > 1:
         tokenize(open(sys.argv[1]).readline)
     else:
     if len(sys.argv) > 1:
         tokenize(open(sys.argv[1]).readline)
     else: