示例#1
0
文件: _epub.py 项目: kwinkunks/Objavi
def _test_spine_manifest_match():
    #every item in the spine should be in the manifest (thence in the zip, tested above)
    #every xhtml in the manifest should be in the spine. (XXX unless there are fallbacks)
    bad_spine_files = []
    for book in TEST_FILES:
        #print book
        spine, manifest, e = _get_elements(book, ('spine', 'manifest'))
        toc, order = epub.parse_spine(spine)
        pwd = os.path.dirname(e.opf_file)
        files = epub.parse_manifest(manifest, pwd)

        assert toc not in order
        xhtmls = set(order)
        for x in order:
            name, mimetype = files.pop(x)
            if mimetype != 'application/xhtml+xml':
                bad_spine_files.append((book, name, mimetype))

        name, mimetype = files.pop(toc)
        assert mimetype == 'application/x-dtbncx+xml'
        remaining = (x[1] for x in files.values())
        if any(x in ('application/x-dtbncx+xml', 'application/xhtml+xml') for x in remaining):
            print book, set(remaining)

        assert not any(x in ('application/x-dtbncx+xml', 'application/xhtml+xml') for x in remaining)

    if bad_spine_files:
        bsf = {}
        for book, fn, mt in bad_spine_files:
            mimecount = bsf.setdefault(book, {})
            mimecount[mt] = mimecount.get(mt, 0) + 1

        pprint(bsf)

        raise AssertionError('bad spine files in %s' % bsf.keys())
示例#2
0
文件: _epub.py 项目: kwinkunks/Objavi
def test_parse_manifest():
    # manifest should be dict of ids pointing to name, mime-type pairs
    # names should be found in zipfile
    all_mimetypes = {}
    for book in TEST_FILES:
        manifest, e = _get_elements(book, ['manifest'])
        pwd = os.path.dirname(e.opf_file)
        files = epub.parse_manifest(manifest, pwd)
        #print book
        mimetypes = set()
        filenames = e.names

        for name, mimetype in files.values():
            assert isinstance(name, basestring)
            assert isinstance(mimetype, basestring)
            mimetypes.add(mimetype)
            all_mimetypes[mimetype] = all_mimetypes.get(mimetype, 0) + 1
            if  name not in filenames:
                print book, name, filenames
            assert name in filenames

        print "%s: %s files, %s different types" % (book, len(files), len(mimetypes))

    for x in all_mimetypes.items():
        print "%30s: %s" % x