Example #1
0
def extract_from_nimbus_file_embed(
        div_tag, processing_options: NimbusProcessingOptions):
    """Extra file link from nimbus html including it's original file name"""
    if div_tag.name != 'div':
        return

    a_tag = div_tag.find('a')
    if not a_tag:
        return

    link_href = a_tag.get('href', '')

    try:  # use try except as 99.9% of time will be there.. probably.. anyway using ask for forgiveness approach
        filename_part = a_tag.find('span', class_='file-name-main').text
    except AttributeError:
        # if the file name parts are not in html use the parts of the href filename
        # it is the name of the file in the zip file
        filename_part = f"{Path(link_href).stem}."

    try:
        extension_part = a_tag.find('span', class_='file-name-ext').text
    except AttributeError:
        extension_part = str(Path(link_href).suffix).lstrip('.')

    dirty_filename = f"{filename_part}{extension_part}"
    # if filename parts were mot present, and so dirty filename is '' the clean file name will be a random string
    clean_filename = helper_functions.generate_clean_filename(
        dirty_filename, processing_options.filename_options)

    caption_text = get_caption_text(div_tag, processing_options)

    return FileEmbedNimbusHTML(processing_options, caption_text, link_href,
                               clean_filename)
Example #2
0
 def get_clean_file_name(self):
     target_suffix = file_mover.get_file_suffix_for(
         self.processing_options.export_format)
     dirty_name = f'{self.contents}{target_suffix}'
     clean_filename = helper_functions.generate_clean_filename(
         dirty_name, self.processing_options.filename_options)
     return clean_filename
def test_generate_clean_filename(value, filename_options, expected, tmp_path):
    result = helper_functions.generate_clean_filename(value, filename_options)

    assert result == expected

    Path(tmp_path, result).touch()

    assert Path(tmp_path, result).exists()
Example #4
0
    def create_file_name(self):
        self._file_name = Path(helper_functions.generate_clean_filename(self._name,
                                                                        self._conversion_settings.filename_options))
        if not Path(self._name).suffix:
            self.logger.warning(f'Original attachment name  "{self._name}" has no file extension')
            self.add_suffix_if_possible()

        if not self._name == str(self._file_name):
            self.logger.info(
                f'Original attachment name was "{self._name}" the cleaned name used is "{self._file_name}"')
    def _create_file_name(self, used_filenames):
        dirty_filename = self._title
        if self.conversion_settings.creation_time_in_exported_file_name:
            formatted_ctime = self.format_ctime_for_file_name()
            dirty_filename = f"{formatted_ctime}-{self._title}"

        dirty_filename = self._append_file_extension(dirty_filename)
        cleaned_filename = Path(
            helper_functions.generate_clean_filename(
                dirty_filename, self.conversion_settings.filename_options))

        new_filename = cleaned_filename
        n = 0
        while new_filename in used_filenames:
            n += 1
            new_filename = Path(
                f'{Path(cleaned_filename).stem}-{n}{Path(cleaned_filename).suffix}'
            )

        self._file_name = new_filename
        self.logger.info(
            f'For the note "{self._title}" the file name used is "{self._file_name}"'
        )
Example #6
0
def initialise_new_note(zip_file, conversion_settings,
                        processing_options: NimbusProcessingOptions):
    new_note = NimbusNote(processing_options,
                          contents=[],
                          conversion_settings=conversion_settings)

    new_note.title = zip_file.stem.replace('_', ' ')

    new_note.note_paths.path_to_note_source = Path(zip_file.parent)

    new_note.note_paths.path_to_source_folder = conversion_settings.source_absolute_root

    dirty_workspace_folder_name = Path(zip_file.parent).relative_to(
        conversion_settings.source_absolute_root).parts[0]

    new_note.note_paths.path_to_source_workspace = Path(
        conversion_settings.source_absolute_root, dirty_workspace_folder_name)

    new_note.note_paths.path_to_target_folder = conversion_settings.export_folder_absolute
    new_note.note_paths.note_target_suffix = get_file_suffix_for(
        conversion_settings.export_format)

    new_note.note_paths.note_source_file_name = zip_file.name
    clean_file_name = helper_functions.generate_clean_filename(
        new_note.title, processing_options.filename_options)

    new_note.note_paths.note_target_file_name = Path(
        f'{clean_file_name}'
        f'{new_note.note_paths.note_target_suffix}')

    new_note.note_paths.set_note_target_path(processing_options)

    new_note.note_paths.set_path_to_attachment_folder(
        conversion_settings.attachment_folder_name, processing_options)

    return new_note
def test_generate_clean_filename_force_windows_long_name(string_to_test, filename_options, expected):
    result = helper_functions.generate_clean_filename(string_to_test, filename_options)

    assert result == expected
Example #8
0
 def create_file_name(self):
     self._file_name = Path(helper_functions.generate_clean_filename(self._attachment_id,
                                                                     self._conversion_settings.filename_options))