phystokens.py 文件源码

def source_token_lines(source):
    """Generate a series of lines, one for each line in `source`.

    Each line is a list of pairs, each pair is a token::

        [('key', 'def'), ('ws', ' '), ('nam', 'hello'), ('op', '('), ... ]

    Each pair has a token class, and the token text.

    If you concatenate all the token texts, and then join them with newlines,
    you should have your original `source` back, with two differences:
    trailing whitespace is not preserved, and a final line with no newline
    is indistinguishable from a final line with a newline.

    """

    ws_tokens = set([token.INDENT, token.DEDENT, token.NEWLINE, tokenize.NL])
    line = []
    col = 0

    # The \f is because of http://bugs.python.org/issue19035
    source = source.expandtabs(8).replace('\r\n', '\n').replace('\f', ' ')
    tokgen = generate_tokens(source)

    for ttype, ttext, (_, scol), (_, ecol), _ in phys_tokens(tokgen):
        mark_start = True
        for part in re.split('(\n)', ttext):
            if part == '\n':
                yield line
                line = []
                col = 0
                mark_end = False
            elif part == '':
                mark_end = False
            elif ttype in ws_tokens:
                mark_end = False
            else:
                if mark_start and scol > col:
                    line.append(("ws", u" " * (scol - col)))
                    mark_start = False
                tok_class = tokenize.tok_name.get(ttype, 'xx').lower()[:3]
                if ttype == token.NAME and keyword.iskeyword(ttext):
                    tok_class = "key"
                line.append((tok_class, part))
                mark_end = True
            scol = 0
        if mark_end:
            col = ecol

    if line:
        yield line