]> 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:

Migrate mypy config to pyproject.toml (#3936)
[etc/vim.git] / src / blib2to3 / pgen2 / tokenize.py
index bad79b2dc2c73d4ecac36b4a573c0d8bc42f9270..d0607f4b1e17b202d4d19603287ed5cfc0a57288 100644 (file)
@@ -27,27 +27,44 @@ are the same, except instead of generating tokens, tokeneater is a callback
 function to which the 5 fields described above are passed as 5 arguments,
 each time a new token is found."""
 
+import sys
 from typing import (
     Callable,
+    Final,
     Iterable,
     Iterator,
     List,
     Optional,
-    Text,
-    Tuple,
     Pattern,
+    Set,
+    Tuple,
     Union,
     cast,
 )
-from blib2to3.pgen2.token import *
+
 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 regex as re
+import re
 from codecs import BOM_UTF8, lookup
-from blib2to3.pgen2.token import *
 
 from . import token
 
@@ -59,27 +76,27 @@ __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):
-    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]*"
 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]+)*"
@@ -139,7 +156,7 @@ ContStr = group(
 PseudoExtras = group(r"\\\r?\n", Comment, Triple)
 PseudoToken = Whitespace + group(PseudoExtras, Number, Funny, ContStr, Name)
 
-pseudoprog = re.compile(PseudoToken, re.UNICODE)
+pseudoprog: Final = re.compile(PseudoToken, re.UNICODE)
 single3prog = re.compile(Single3)
 double3prog = re.compile(Double3)
 
@@ -149,22 +166,21 @@ _strprefixes = (
     | {"u", "U", "ur", "uR", "Ur", "UR"}
 )
 
-endprogs = {
+endprogs: Final = {
     "'": re.compile(Single),
     '"': re.compile(Double),
     "'''": single3prog,
     '"""': double3prog,
     **{f"{prefix}'''": single3prog for prefix in _strprefixes},
     **{f'{prefix}"""': double3prog for prefix in _strprefixes},
-    **{prefix: None for prefix in _strprefixes},
 }
 
-triple_quoted = (
+triple_quoted: Final = (
     {"'''", '"""'}
     | {f"{prefix}'''" for prefix in _strprefixes}
     | {f'{prefix}"""' for prefix in _strprefixes}
 )
-single_quoted = (
+single_quoted: Final = (
     {"'", '"'}
     | {f"{prefix}'" for prefix in _strprefixes}
     | {f'{prefix}"' for prefix in _strprefixes}
@@ -181,19 +197,23 @@ 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: 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))
     )
 
 
-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().
@@ -213,18 +233,17 @@ def tokenize(readline: Callable[[], Text], tokeneater: TokenEater = printtoken)
 
 
 # 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)
 
 
-GoodTokenInfo = Tuple[int, Text, Coord, Coord, Text]
+GoodTokenInfo = Tuple[int, str, Coord, Coord, str]
 TokenInfo = Union[Tuple[int, str], GoodTokenInfo]
 
 
 class Untokenizer:
-
-    tokens: List[Text]
+    tokens: List[str]
     prev_row: int
     prev_col: int
 
@@ -240,13 +259,13 @@ class Untokenizer:
         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(
-                Tuple[int, Text, Coord, Coord, Text], t
+                Tuple[int, str, Coord, Coord, str], t
             )
             self.add_whitespace(start)
             self.tokens.append(token)
@@ -256,7 +275,7 @@ class Untokenizer:
                 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
@@ -286,7 +305,7 @@ 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:
@@ -328,7 +347,7 @@ def detect_encoding(readline: Callable[[], bytes]) -> Tuple[str, List[bytes]]:
         try:
             return readline()
         except StopIteration:
-            return bytes()
+            return b""
 
     def find_cookie(line: bytes) -> Optional[str]:
         try:
@@ -377,7 +396,7 @@ def detect_encoding(readline: Callable[[], bytes]) -> Tuple[str, List[bytes]]:
     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
@@ -400,7 +419,7 @@ def untokenize(iterable: Iterable[TokenInfo]) -> Text:
 
 
 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
@@ -418,7 +437,7 @@ def generate_tokens(
     logical line; continuation lines are included.
     """
     lnum = parenlev = continued = 0
-    numchars = "0123456789"
+    numchars: Final[str] = "0123456789"
     contstr, needcont = "", 0
     contline: Optional[str] = None
     indents = [0]
@@ -427,7 +446,7 @@ def generate_tokens(
     # `await` as keywords.
     async_keywords = False if grammar is None else grammar.async_keywords
     # 'stashed' and 'async_*' are used for async/await parsing
-    stashed = None
+    stashed: Optional[GoodTokenInfo] = None
     async_def = False
     async_def_indent = 0
     async_def_nl = False
@@ -440,7 +459,7 @@ def generate_tokens(
             line = readline()
         except StopIteration:
             line = ""
-        lnum = lnum + 1
+        lnum += 1
         pos, max = 0, len(line)
 
         if contstr:  # continued string
@@ -481,14 +500,14 @@ def generate_tokens(
             column = 0
             while pos < max:  # measure leading whitespace
                 if line[pos] == " ":
-                    column = column + 1
+                    column += 1
                 elif line[pos] == "\t":
                     column = (column // tabsize + 1) * tabsize
                 elif line[pos] == "\f":
                     column = 0
                 else:
                     break
-                pos = pos + 1
+                pos += 1
             if pos == max:
                 break
 
@@ -507,7 +526,7 @@ def generate_tokens(
                     COMMENT,
                     comment_token,
                     (lnum, pos),
-                    (lnum, pos + len(comment_token)),
+                    (lnum, nl_pos),
                     line,
                 )
                 yield (NL, line[nl_pos:], (lnum, nl_pos), (lnum, len(line)), line)
@@ -592,11 +611,15 @@ 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
@@ -624,7 +647,6 @@ 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]
@@ -652,29 +674,27 @@ def generate_tokens(
                     continued = 1
                 else:
                     if initial in "([{":
-                        parenlev = parenlev + 1
+                        parenlev += 1
                     elif initial in ")]}":
-                        parenlev = parenlev - 1
+                        parenlev -= 1
                     if stashed:
                         yield stashed
                         stashed = None
                     yield (OP, token, spos, epos, line)
             else:
                 yield (ERRORTOKEN, line[pos], (lnum, pos), (lnum, pos + 1), line)
-                pos = pos + 1
+                pos += 1
 
     if stashed:
         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
-    import sys
-
     if len(sys.argv) > 1:
         tokenize(open(sys.argv[1]).readline)
     else: