summaryrefslogtreecommitdiffstats
path: root/Tools/peg_generator/pegen/tokenizer.py
blob: 61a28efc84b62b667dbe7cf97039fbfe103b25bd (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
import token
import tokenize
from typing import List, Iterator

Mark = int  # NewType('Mark', int)

exact_token_types = token.EXACT_TOKEN_TYPES  # type: ignore


def shorttok(tok: tokenize.TokenInfo) -> str:
    return "%-25.25s" % f"{tok.start[0]}.{tok.start[1]}: {token.tok_name[tok.type]}:{tok.string!r}"


class Tokenizer:
    """Caching wrapper for the tokenize module.

    This is pretty tied to Python's syntax.
    """

    _tokens: List[tokenize.TokenInfo]

    def __init__(self, tokengen: Iterator[tokenize.TokenInfo], *, verbose: bool = False):
        self._tokengen = tokengen
        self._tokens = []
        self._index = 0
        self._verbose = verbose
        if verbose:
            self.report(False, False)

    def getnext(self) -> tokenize.TokenInfo:
        """Return the next token and updates the index."""
        cached = True
        while self._index == len(self._tokens):
            tok = next(self._tokengen)
            if tok.type in (tokenize.NL, tokenize.COMMENT):
                continue
            if tok.type == token.ERRORTOKEN and tok.string.isspace():
                continue
            self._tokens.append(tok)
            cached = False
        tok = self._tokens[self._index]
        self._index += 1
        if self._verbose:
            self.report(cached, False)
        return tok

    def peek(self) -> tokenize.TokenInfo:
        """Return the next token *without* updating the index."""
        while self._index == len(self._tokens):
            tok = next(self._tokengen)
            if tok.type in (tokenize.NL, tokenize.COMMENT):
                continue
            if tok.type == token.ERRORTOKEN and tok.string.isspace():
                continue
            self._tokens.append(tok)
        return self._tokens[self._index]

    def diagnose(self) -> tokenize.TokenInfo:
        if not self._tokens:
            self.getnext()
        return self._tokens[-1]

    def mark(self) -> Mark:
        return self._index

    def reset(self, index: Mark) -> None:
        if index == self._index:
            return
        assert 0 <= index <= len(self._tokens), (index, len(self._tokens))
        old_index = self._index
        self._index = index
        if self._verbose:
            self.report(True, index < old_index)

    def report(self, cached: bool, back: bool) -> None:
        if back:
            fill = "-" * self._index + "-"
        elif cached:
            fill = "-" * self._index + ">"
        else:
            fill = "-" * self._index + "*"
        if self._index == 0:
            print(f"{fill} (Bof)")
        else:
            tok = self._tokens[self._index - 1]
            print(f"{fill} {shorttok(tok)}")