whatstyle.py 文件源码

def lines_from_sourcepairs(pairs, numlines=2, enc='utf-8'):
        # type: (List[BytesPair], int, str) -> Tuple[List[str], List[str]]
        def safeunistr(s):
            # type: (bytes) -> str
            # The bytes 0 and 1 that appear in the intermediate result of
            # difflib.HtmlDiff.make_table are replaced by opening and closing span tags.
            # If the input to make_table already contains 0 and 1 bytes we get mismatched
            # span tags.
            # We use '\x02' as escape character and encode '\x00', '\x01', '\x02' as
            # '\x02' followed by the digit 0, 1, 2 respectively.
            def escape_zeroonetwo(m):
                return b'\x02' + int2byte(ord('0') + ord(m.group(0)))

            s = re.sub(b'[\x00-\x02]', escape_zeroonetwo, s)
            return surrdecode(s, enc=enc)

        a = [a for a, _ in pairs]
        b = [b for _, b in pairs]
        a = concat_sources(a, numlines=numlines).splitlines(True)
        b = concat_sources(b, numlines=numlines).splitlines(True)
        atext = list(map(safeunistr, a))
        btext = list(map(safeunistr, b))
        return atext, btext


# yapf: disable
# ----------------------------------------------------------------------
# http://stackoverflow.com/questions/1707890/
#           fast-way-to-filter-illegal-xml-unicode-chars-in-python