lexer.py 2.4 KB
Newer Older
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
#
# Copyright (C) 2009-2020 the sqlparse authors and contributors
# <see AUTHORS file>
#
# This module is part of python-sqlparse and is released under
# the BSD License: https://opensource.org/licenses/BSD-3-Clause

"""SQL Lexer"""

# This code is based on the SqlLexer in pygments.
# http://pygments.org/
# It's separated from the rest of pygments to increase performance
# and to allow some customizations.

from io import TextIOBase

from sqlparse import tokens
from sqlparse.keywords import SQL_REGEX
from sqlparse.utils import consume


class Lexer:
    """Lexer
    Empty class. Leaving for backwards-compatibility
    """

    @staticmethod
    def get_tokens(text, encoding=None):
        """
        Return an iterable of (tokentype, value) pairs generated from
        `text`. If `unfiltered` is set to `True`, the filtering mechanism
        is bypassed even if filters are defined.

        Also preprocess the text, i.e. expand tabs and strip it if
        wanted and applies registered filters.

        Split ``text`` into (tokentype, text) pairs.

        ``stack`` is the initial stack (default: ``['root']``)
        """
        if isinstance(text, TextIOBase):
            text = text.read()

        if isinstance(text, str):
            pass
        elif isinstance(text, bytes):
            if encoding:
                text = text.decode(encoding)
            else:
                try:
                    text = text.decode('utf-8')
                except UnicodeDecodeError:
                    text = text.decode('unicode-escape')
        else:
            raise TypeError("Expected text or file-like object, got {!r}".
                            format(type(text)))

        iterable = enumerate(text)
        for pos, char in iterable:
            for rexmatch, action in SQL_REGEX:
                m = rexmatch(text, pos)

                if not m:
                    continue
                elif isinstance(action, tokens._TokenType):
                    yield action, m.group()
                elif callable(action):
                    yield action(m.group())

                consume(iterable, m.end() - pos - 1)
                break
            else:
                yield tokens.Error, char


def tokenize(sql, encoding=None):
    """Tokenize sql.

    Tokenize *sql* using the :class:`Lexer` and return a 2-tuple stream
    of ``(token type, value)`` items.
    """
    return Lexer().get_tokens(sql, encoding)