#!/usr/bin/env python3

import hashlib
import logging
import os
from typing import Any, Optional

logger = logging.getLogger(__name__)


class DirectoryFileFilter(object):
    """A predicate that will return False if / when a proposed file's
    content to-be-written is identical to the contents of the file on
    disk allowing calling code to safely skip the write.

    >>> testfile = '/tmp/directory_filter_text_f39e5b58-c260-40da-9448-ad1c3b2a69c2.txt'
    >>> contents = b'This is a test'
    >>> with open(testfile, 'wb') as wf:
    ...     wf.write(contents)
    14

    >>> d = DirectoryFileFilter('/tmp')

    >>> d.apply(contents, testfile)     # False if testfile already contains contents
    False

    >>> d.apply(b'That was a test', testfile)    # True otherwise
    True

    >>> os.remove(testfile)

    """
    def __init__(self, directory: str):
        super().__init__()
        import file_utils
        if not file_utils.does_directory_exist(directory):
            raise ValueError(directory)
        self.directory = directory
        self.md5_by_filename = {}
        self.mtime_by_filename = {}
        self._update()

    def _update(self):
        for direntry in os.scandir(self.directory):
            if direntry.is_file(follow_symlinks=True):
                mtime = direntry.stat(follow_symlinks=True).st_mtime
                path = f'{self.directory}/{direntry.name}'
                self._update_file(path, mtime)

    def _update_file(self, filename: str, mtime: Optional[float] = None):
        import file_utils
        assert file_utils.does_file_exist(filename)
        if mtime is None:
            mtime = file_utils.get_file_raw_mtime(filename)
        if self.mtime_by_filename.get(filename, 0) != mtime:
            md5 = file_utils.get_file_md5(filename)
            logger.debug(f'Computed/stored {filename}\'s MD5 at ts={mtime} ({md5})')
            self.mtime_by_filename[filename] = mtime
            self.md5_by_filename[filename] = md5

    def apply(self, item: Any, filename: str) -> bool:
        self._update_file(filename)
        file_md5 = self.md5_by_filename.get(filename, 0)
        logger.debug(f'{filename}\'s checksum is {file_md5}')
        mem_hash = hashlib.md5()
        mem_hash.update(item)
        md5 = mem_hash.hexdigest()
        logger.debug(f'Item\'s checksum is {md5}')
        return md5 != file_md5


class DirectoryAllFilesFilter(DirectoryFileFilter):
    """A predicate that will return False if a file to-be-written to a
    particular directory is identical to any other file in that same
    directory.

    i.e. this is the same as the above except that its apply() method
    will return true not only if the contents to be written are
    identical to the contents of filename on the disk but also it
    returns true if there exists some other file sitting in the same
    directory which already contains those identical contents.

    >>> testfile = '/tmp/directory_filter_text_f39e5b58-c260-40da-9448-ad1c3b2a69c3.txt'

    >>> contents = b'This is a test'
    >>> with open(testfile, 'wb') as wf:
    ...     wf.write(contents)
    14

    >>> d = DirectoryAllFilesFilter('/tmp')

    >>> d.apply(contents)    # False is _any_ file in /tmp contains contents
    False

    >>> d.apply(b'That was a test')    # True otherwise
    True

    >>> os.remove(testfile)
    """
    def __init__(self, directory: str):
        self.all_md5s = set()
        super().__init__(directory)

    def _update_file(self, filename: str, mtime: Optional[float] = None):
        import file_utils
        assert file_utils.does_file_exist(filename)
        if mtime is None:
            mtime = file_utils.get_file_raw_mtime(filename)
        if self.mtime_by_filename.get(filename, 0) != mtime:
            md5 = file_utils.get_file_md5(filename)
            self.mtime_by_filename[filename] = mtime
            self.md5_by_filename[filename] = md5
            self.all_md5s.add(md5)

    def apply(self, item: Any) -> bool:
        self._update()
        mem_hash = hashlib.md5()
        mem_hash.update(item)
        md5 = mem_hash.hexdigest()
        return md5 not in self.all_md5s


if __name__ == '__main__':
    import doctest
    doctest.testmod()