# SPDX-FileCopyrightText: 2022 Agathe Porte <microjoe@microjoe.org>
#
# SPDX-License-Identifier: MIT

"""dir_attach, a Pelican plugin to attach files from a directory named after
restructuredText file names.

If your file is named ``foobar.rst``, then the following
restructuredText entry:

    .. image:: {dir_attach}example-thumbnail.jpg
        :alt: An example image for demonstration.
        :target: {dir_attach}example.jpg

Will automatically be pre-processed by this plugin to become:

    .. image:: {attach}../images/foobar/example-thumbnail.jpg
        :alt: An example image for demonstration.
        :target: {attach}../images/foobar/example.jpg

Using ``../images/`` directory instead of ``images/`` is mandatory. This is
because the current Pelican implementation will simplify the path only if the
target directory is not in the same root as the current page.

If ``images/`` directory was used, then the resulting path in HTML would be:

    foobar/images/foobar/example.jpg

By using a directory outside of the page's source folder, the generated HTML
path is simplified by Pelican:

    foobar/example.jpg

"""

import os
import tempfile
import re

from pelican import signals
from pelican.readers import RstReader


def dirname_from_source_path(source_path):
    """Get the dirname to use from the .rst filename.

    >>> dirname_from_source_path("/tmp/foobar.rst")
    'foobar'

    """
    return os.path.splitext(os.path.basename(source_path))[0]


def expand_dir_attach(content, dirname):
    """Expand the {dir_attach} directives to image {attach} directives.

    >>> src = \
        ".. image:: {dir_attach}example.jpg\\n" \
        "    :alt: Example illustration.\\n" \
        "    :target: {dir_attach}example.jpg\\n"
    >>> expand_dir_attach(src, "foobar")
    '.. image:: {attach}../images/foobar/example.jpg\\n\
    :alt: Example illustration.\\n\
    :target: {attach}../images/foobar/example.jpg\\n'

    """

    dest = f"{{attach}}../images/{dirname}/"

    # We are trying to match only restructuredText directives instead of doing
    # a whole content.replace to avoid to replace inside of paragraphs, etc.
    regexes = (
        (r"^(.. \w+::) {dir_attach}(.*)$", fr"\1 {dest}\2"),
        (r"^(.. _.*:) {dir_attach}(.*)$", fr"\1 {dest}\2"),
        (r"^(    :\w+:) {dir_attach}(.*)$", fr"\1 {dest}\2"),
    )

    for match, replace in regexes:
        content = re.sub(match, replace, content, flags=re.MULTILINE)

    return content


class CustomRstReader(RstReader):
    """A custom restructuredText reader that will pre-process source first."""

    enabled = True
    file_extensions = ['rst']

    def read(self, source_path):
        """Parses restructured text."""
        dirname = dirname_from_source_path(source_path)

        # Open temporary file in "w" instead of default "w+b" in order to
        # use utf-8 by default.
        with tempfile.NamedTemporaryFile(mode="w") as tmp:
            with open(source_path) as src:
                tmp.write(expand_dir_attach(src.read(), dirname))

            # Force flush to disk before docutils tries to open the file
            # in super().read(), elsewise file may be empty.
            tmp.flush()

            return super().read(tmp.name)


def add_reader(readers):
    """Override the .rst reader with our custom reader."""
    readers.reader_classes['rst'] = CustomRstReader


def register():
    """Register the plugin to Pelican."""
    signals.readers_init.connect(add_reader)