Add support for comparing the "text" content of HTML files using html2text....

 gnupg-utils <!nocheck>,

 hdf5-tools <!nocheck>,

 help2man,

 html2text <!nocheck>,

 imagemagick <!nocheck>,

 jsbeautifier <!nocheck>,

 libarchive-tools <!nocheck>,

#   $ mv debian/tests/control.tmp debian/tests/control

Tests: pytest-with-recommends

Depends: python3-all, diffoscope, black, python3-pytest, python3-h5py, file, linux-image-amd64 [amd64] | linux-image-generic [amd64], abootimg, acl, apksigner, apktool [!ppc64el !s390x], binutils-multiarch, bzip2, caca-utils, colord, coreboot-utils, db-util, default-jdk-headless | default-jdk | java-sdk, device-tree-compiler, docx2txt, e2fsprogs, enjarify, ffmpeg, fontforge-extras, fonttools, fp-utils [!ppc64el !s390x], genisoimage, gettext, ghc, ghostscript, giflib-tools, gnumeric, gnupg, gnupg-utils, hdf5-tools, imagemagick, jsbeautifier, libarchive-tools, libxmlb-dev, llvm, lz4 | liblz4-tool, mono-utils, ocaml-nox, odt2txt, oggvideotools [!s390x], openssh-client, openssl, pgpdump, poppler-utils, procyon-decompiler, python3-pdfminer, r-base-core, rpm2cpio, sng, sqlite3, squashfs-tools, tcpdump, u-boot-tools, unzip, wabt, xmlbeans, xxd, xz-utils, zip, zstd, androguard, python3-argcomplete, python3-binwalk, python3-defusedxml, python3-distro, python3-guestfs, python3-jsondiff, python3-progressbar, python3-pypdf2, python3-debian, python3-pyxattr, python3-rpm, python3-tlsh

Depends: python3-all, diffoscope, black, python3-pytest, python3-h5py, file, linux-image-amd64 [amd64] | linux-image-generic [amd64], abootimg, acl, apksigner, apktool [!ppc64el !s390x], binutils-multiarch, bzip2, caca-utils, colord, coreboot-utils, db-util, default-jdk-headless | default-jdk | java-sdk, device-tree-compiler, docx2txt, e2fsprogs, enjarify, ffmpeg, fontforge-extras, fonttools, fp-utils [!ppc64el !s390x], genisoimage, gettext, ghc, ghostscript, giflib-tools, gnumeric, gnupg, gnupg-utils, hdf5-tools, html2text, imagemagick, jsbeautifier, libarchive-tools, libxmlb-dev, llvm, lz4 | liblz4-tool, mono-utils, ocaml-nox, odt2txt, oggvideotools [!s390x], openssh-client, openssl, pgpdump, poppler-utils, procyon-decompiler, python3-pdfminer, r-base-core, rpm2cpio, sng, sqlite3, squashfs-tools, tcpdump, u-boot-tools, unzip, wabt, xmlbeans, xxd, xz-utils, zip, zstd, 

Tests: pytest

Depends: python3-all, diffoscope, python3-pytest, python3-h5py, file, python3-tlsh

        ("xmlb.XMLBFile",),

        ("openssl.Pkcs7File",),

        ("openssl.MobileProvisionFile",),

        ("html.HtmlFile",),

        ("text.TextFile",),

        ("bzip2.Bzip2File",),

        ("cpio.CpioFile",),

#

# diffoscope: in-depth comparison of files, archives, and directories

#

# Copyright © 2022 Chris Lamb <lamby@debian.org>

#

# diffoscope is free software: you can redistribute it and/or modify

# it under the terms of the GNU General Public License as published by

# the Free Software Foundation, either version 3 of the License, or

# (at your option) any later version.

#

# diffoscope is distributed in the hope that it will be useful,

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

# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

# GNU General Public License for more details.

#

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

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

import re

from diffoscope.difference import Difference

from diffoscope.exc import RequiredToolNotFound

from diffoscope.tools import tool_required

from .text import TextFile

from .utils.command import Command

class Htmltotext(Command):

    @tool_required("html2text")

    def cmdline(self):

        return ["html2text", self.path]

class HtmlFile(TextFile):

    DESCRIPTION = "HTML files (.html)"

    FILE_TYPE_RE = re.compile(r"^HTML document")

    def compare(self, other, source=None):

        difference = super().compare(other, source)

        # Show text-only differences as a sub-diff.

        try:

            text = Difference.from_operation(Htmltotext, self.path, other.path)

            if text is not None:

                difference.add_details([text])

        except RequiredToolNotFound as exc:  # noqa

            difference.add_comment(exc.get_comment())

        return difference

    },

    "gzip": {"debian": "gzip", "arch": "gzip", "guix": "gzip"},

    "h5dump": {"debian": "hdf5-tools", "arch": "hdf5", "guix": "hdf5"},

    "html2text": {"debian": "html2text"},

    "identify": {

        "debian": "imagemagick",

        "arch": "imagemagick",