# but WITHOUT ANY WARRANTY; without even the implied warranty of

# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

# GNU Affero General Public License for more details.

#

# You should have received a copy of the GNU Affero General Public License

# along with this program.  If not, see <https://www.gnu.org/licenses/>.

import argparse

import logging

import os

import sys

import urllib.parse

from pathlib import Path

from zipfile import BadZipFile

import odf.opendocument  # type:ignore[import]

import odf.text  # type:ignore[import]

from typing import (

    Iterator,

    Optional,

    Sequence,

    Set,

    TextIO,

)

from .. import cliutil

PROGNAME = 'extract-odf-links'

logger = logging.getLogger('conservancy_beancount.tools.extract_odf_links')

def parse_delimiter(arg: str) -> str:

    try:

        retval = eval('"{}"'.format(arg.replace('"', r'\"')), {})

    except SyntaxError:

        retval = None

    if isinstance(retval, str):

        return retval

    else:

        raise ValueError(f"not a valid string: {arg!r}")

def parse_arguments(arglist: Optional[Sequence[str]]=None) -> argparse.Namespace:

    parser = argparse.ArgumentParser(prog=PROGNAME)

    cliutil.add_version_argument(parser)

    cliutil.add_loglevel_argument(parser)

    parser.add_argument(

        '--delimiter', '-d',

        type=parse_delimiter,

        default='\\n',

        help="""String to output between links. Accepts all backslash escapes

""")

    parser.add_argument(

        '--zero', '--null', '-z', '-0',

        action='store_const',

        dest='delimiter',

        const='\0',

        help="""Shortcut for --delimiter=\\0

""")

    parser.add_argument(

        'odf_paths',

        metavar='ODF_PATH',

        type=Path,

        nargs=argparse.ONE_OR_MORE,

        help="""ODF file(s) to extract links from. Note that %(prog)s cannot

read from stdin because it needs to know document paths to resolve links.

""")

    return parser.parse_args(arglist)

def extract_links(odf_path: Path) -> Iterator[Path]:

    odf_root = odf_path.parent.resolve()

    with odf_path.open('rb') as odf_file:

        odf_doc = odf.opendocument.load(odf_file)

    for a_elem in odf_doc.getElementsByType(odf.text.A):

        parts = urllib.parse.urlparse(a_elem.getAttribute('href') or '')

        if (parts.scheme and parts.scheme != 'file') or not parts.path:

            continue

        path = Path(urllib.parse.unquote(parts.path))

        if not path.is_absolute():

            path = (odf_path / path).resolve()

            try:

                path.relative_to(odf_root)

            except ValueError:

                logger.warning(f"link {path} is neither absolute nor relative to {odf_path}")

        yield path

def main(arglist: Optional[Sequence[str]]=None,

         stdout: TextIO=sys.stdout,

         stderr: TextIO=sys.stderr,

) -> int:

    args = parse_arguments(arglist)

    cliutil.set_loglevel(logger, args.loglevel)

    returncode = 0

    links: Set[Path] = set()

    for odf_path in args.odf_paths:

        try:

            links.update(extract_links(odf_path))

        except IOError as error: