a &b @sLddlZddlZddlmZddZddZddZdd d Zdd dZ dS)N)replace_entitiescCs tt|S)aflatten(sequence) -> list Returns a single, flat list which contains all elements retrieved from the sequence and all recursively contained sub-sequences (iterables). Examples: >>> [1, 2, [3,4], (5,6)] [1, 2, [3, 4], (5, 6)] >>> flatten([[[1,2,3], (42,None)], [4,5], [6], 7, (8,9,10)]) [1, 2, 3, 42, None, 4, 5, 6, 7, 8, 9, 10] >>> flatten(["foo", "bar"]) ['foo', 'bar'] >>> flatten(["foo", ["baz", 42], "bar"]) ['foo', 'baz', 42, 'bar'] )listiflattenxr+lib/python3.9/site-packages/parsel/utils.pyflattensr ccs2|D](}t|r&t|D] }|Vqq|VqdS)zZiflatten(sequence) -> Iterator Similar to ``.flatten()``, but returns iterator insteadN) _is_listliker )rZelZel_rrrrs   rcCst|dot|tjtf S)at >>> _is_listlike("foo") False >>> _is_listlike(5) False >>> _is_listlike(b"foo") False >>> _is_listlike([b"foo"]) True >>> _is_listlike((b"foo",)) True >>> _is_listlike({}) True >>> _is_listlike(set()) True >>> _is_listlike((x for x in range(3))) True >>> _is_listlike(six.moves.xrange(5)) True __iter__)hasattr isinstancesixZ text_typebytesrrrrr #sr TcCst|tjrt|tj}d|jvrdz||d}Wnt yNg}Yqn0|dur^|gng}n | |}t |}|s~|Sdd|DS)abExtract a list of unicode strings from the given text/encoding using the following policies: * if the regex contains a named group called "extract" that will be returned * if the regex contains multiple numbered groups, all those will be returned (flattened) * if the regex doesn't contain any group the entire regex matching is returned extractNcSsg|]}t|ddgdqS)ltZamp)Zkeep)w3lib_replace_entities).0srrr Sz!extract_regex..) r rZ string_typesrecompileUNICODE groupindexsearchgroupAttributeErrorfindallr )ZregextextrZ extractedZstringsrrr extract_regex;s     r ...cCs\t||kr|S|t|kr4|d|t||S|dkrP|t||dStddS)z2Truncate the given text to fit in the given width.Nrz%width must be equal or greater than 0)len ValueError)rwidthsuffixrrrshortenVs  r&)T)r!) rrZ w3lib.htmlrrr rr r r&rrrrs