first working version since long time

README.md

@@ -18,13 +18,6 @@ packages:
 * [github.com/threatstack/libmagic](https://github.com/threatstack/libmagic)
 * [pillow.readthedocs.io](https://pillow.readthedocs.io/en/5.3.x/installation.html#external-libraries)
 
-### Optional requirements
-
-If you wish to use the `--caption` flag to add image captions read from EXIF comment metadata you will need a utility called `exiftool`.
-
-You can install it via your package manager. For other options please consult the website: [https://www.sno.phy.queensu.ca/~phil/exiftool/](https://www.sno.phy.queensu.ca/~phil/exiftool/)
-
-
 ## Install It
 
 ```bash
@@ -62,7 +55,7 @@ Create a quick gallery for the web:
 $ distribusi -d /path/to/my/photos -t
 ```
 
-This creates an `index.html` with `base64` encoded thumbnails.
+This creates an `index.html` with accompanying `_thumbnail.jpg` files
 
 Generate verbose output:
 

distribusi/cli.py

@@ -6,83 +6,79 @@ from distribusi.distribusi import distribusify
 
 def build_argparser():
     parser = argparse.ArgumentParser(
-    """
+        """
     distribusi is a content management system for the web that produces static
     index pages based on folders in the files system.  It is inspired by the
     automatic index functions featured in several popular web servers.
     distribusi works by traversing the file system and directory hierarchy to
     automatically list all the files in the directory, detect the file types
     and providing them with relevant html classes and tags for easy styling.
-    """)
+    """
-
-    parser.add_argument(
-        '-d', '--directory', help="Select which directory to distribute", default="."
     )
 
     parser.add_argument(
-        '-s', '--style', help="Select a CSS style sheet to include"
+        "-d",
+        "--directory",
+        help="Select which directory to distribute",
+        default=".",
     )
 
     parser.add_argument(
-        '-v', '--verbose', help="Print verbose debug output", action="store_true"
+        "-s", "--style", help="Select a CSS style sheet to include"
     )
 
     parser.add_argument(
-        '-t',
+        "-v",
-        '--thumbnail',
+        "--verbose",
-        help="Generate 450x450 thumbnails for images",
+        help="Print verbose debug output",
         action="store_true",
     )
 
     parser.add_argument(
-        '-n',
+        "-t",
-        '--no-template',
+        "--thumbnail",
-        help="Don't use the template to output html",
+        help="Generate 450x450 thumbnails for images",
         action="store_true",
     )
 
     parser.add_argument(
-        '-nf',
+        "-a",
-        '--no-filenames',
+        "--alttexts",
-        help="Don't add file names to listing",
+        help="Adds file alttext based on same named files",
         action="store_true",
     )
 
     parser.add_argument(
-        '-c',
+        "-r",
-        '--captions',
+        "--remove-index",
-        help="Adds image captions based on EXIF metadata, requires 'exiftool'",
+        help="Recursively removes all instances of index.html that have been previously made by distribusi",
         action="store_true",
     )
 
     parser.add_argument(
-        '-r',
+        "-e",
-        '--remove-index',
+        "--exclude-directory",
-        help="Recursively removes all instances of index.html that have been previously made by distribusi",
-        action="store_true")
-
-    parser.add_argument(
-        '-e',
-        '--exclude-directory',
         help="Exclude one or multiple directories from indexing",
         nargs="*",
-        metavar='DIR')
+        metavar="DIR",
+    )
 
     parser.add_argument(
-        '-f',
+        "-f",
-        '--force',
+        "--force",
         help="Force whether distribusi overwrites or removes instances of index.html not generated by distribusi, use at own risk!",
-        action="store_true")
+        action="store_true",
+    )
 
     parser.add_argument(
-        '--no-hidden',
+        "--no-hidden", help="Exclude hidden directories", action="store_true"
-        help="Exclude hidden directories",
+    )
-        action="store_true")
 
     parser.add_argument(
-        '--menu-with-index',
+        "--menu-with-index",
         help="Append index.html to menu items to aid navigation",
-        action="store_true")
+        action="store_true",
+    )
 
     return parser
 

distribusi/distribusi.py

@@ -1,75 +1,85 @@
-import base64
 import os
-import subprocess
-from io import BytesIO
 
 import magic
 from PIL import Image
-
+from distribusi.templates.page_template import html_footer, html_head
-from distribusi.page_template import html_footer, html_head
+from distribusi.templates.image_templates import (
+    image_no_description,
+    image_with_description,
+    image_with_alttext,
+    image_full_figure,
+)
 from distribusi.mappings import CODE_TYPES, FILE_TYPES, SUB_TYPES
 
 MIME_TYPE = magic.Magic(mime=True)
 
 
-def caption(image):
+def add_alttext(full_path_image):
     try:
-        process = subprocess.Popen(
+        image_filename_no_ext = os.path.splitext(full_path_image)[0]
-            ['exiftool', '-Comment', image], stdout=subprocess.PIPE)
+        alttext_filename = f"{image_filename_no_ext}_alttext.txt"
-        out, err = process.communicate()
+        return _read_matching_text_file(
+            image_filename_no_ext, alttext_filename
+        )
     except Exception as e:
-        print(e)
+        print(f"exception {e} raised while making alttext")
-        print('Do you have exiftool installed?')
+        return
+
+
+def add_description(full_path_image):
     try:
-        caption = out.decode("utf-8").split(": ", 1)[1]
+        image_filename_no_ext = os.path.splitext(full_path_image)[0]
+        description_filename = f"{image_filename_no_ext}_dv_description.txt"
+        return _read_matching_text_file(
+            image_filename_no_ext, description_filename
+        )
     except Exception as e:
-        caption = ''
+        print(f"exception {e} raised while adding description")
-        print(e)
+        return
-    return caption
+
 
+def _read_matching_text_file(image_filename_no_ext, filename):
+    if not os.path.isfile(filename):
+        return
+    print(f"{image_filename_no_ext} has {filename}")
+    with open(filename, "r") as text_file:
+        return text_file.read()
 
-def thumbnail(image, name, args):
+
+def thumbnail(full_path_image, name, args):
+    if full_path_image.endswith("_thumbnail.jpg"):
+        return
     try:
         size = (450, 450)
-        im = Image.open(image)
+        thumbnail_image = Image.open(full_path_image)
-        im.thumbnail(size)
+        thumbnail_image.thumbnail(size)
-        
+
-        if (im.mode == 'RGBA'):
+        if thumbnail_image.mode == "RGBA":
-            bg = Image.new('RGBA', im.size, (255,255,255))
+            bg = Image.new("RGBA", thumbnail_image.size, (255, 255, 255))
-            composite = Image.alpha_composite(bg, im)
+            composite = Image.alpha_composite(bg, thumbnail_image)
-            im=composite.convert('RGB')
+            thumbnail_image = composite.convert("RGB")
-        
+
-        output = BytesIO()
+        image_filename_no_ext = os.path.splitext(full_path_image)[0]
-        im.save(output, format='JPEG')
+        thumbnail_filename = f"{image_filename_no_ext}_thumbnail.jpg"
-        im_data = output.getvalue()
+        thumbnail_image.save(thumbnail_filename, format="JPEG")
-        data_url = base64.b64encode(im_data).decode()
+        return os.path.basename(thumbnail_filename)
-        if args.captions:
-            cap = caption(image)
-        else:
-            cap = name
-        return (
-            "<figure><a href='{}'><img class='thumbnail' src='data:image/jpg;base64,{}'></a><figcaption>{}</figcaption></figure>"
-        ).format(name, data_url, cap)
     except Exception as e:
-        print('Thumbnailer:', e)
+        print("Thumbnailer:", e)
-        return "<figure><a href='{}'><img src='{}'></a><figcaption>{}</figcaption></figure>".format(name, name, name)
+        return
 
 
-def div(args, type_, subtype, tag, name):
+def format_div(args, type_, subtype, tag, name):
-    id_name = name.split('.')[0].replace(' ', '_')
+    id_name = name.split(".")[0].replace(" ", "_")
-    if args.no_filenames:
+    filename = f'<span class="filename">{name}</span>'
-        filename = ''
-    else:
-        filename = '<span class="filename">{}</span>'.format(name)
 
-    if 'image' in type_:
+    if "image" in type_:
         html = '<div id="{}" class="{}">{}</div>'
-    elif 'pdf' in subtype:
+    elif "pdf" in subtype:
-        html = '<div id="{}" class="{}">{}' + filename + '</div>'
+        html = '<div id="{}" class="{}">{}' + filename + "</div>"
-    elif 'dir' in type_ or 'html' in subtype or 'unkown-file' in subtype:
+    elif "dir" in type_ or "html" in subtype or "unkown-file" in subtype:
         html = '<div id="{}" class="{}">{}</div>'
     else:
-        html = '<div id="{}" class="{}">{}' + filename + '</div>'
+        html = '<div id="{}" class="{}">{}' + filename + "</div>"
 
     return html.format(id_name, subtype, tag)
 
@@ -78,142 +88,191 @@ def check_distribusi_index(args, index):
     """
     check whether a index.html file is generated by distribusi
     """
-
     if not args.force:
-        with open(index, 'r') as f:
+        with open(index, "r") as f:
             if '<meta name="generator" content="distribusi" />' in f.read():
                 return True
             else:
                 if args.verbose:
-                    print(index, 'not generated by distribusi, skipping')
+                    print(index, "not generated by distribusi, skipping")
                 return False
     elif args.force:
         return True
 
-def write_index(args,index, html, html_head, html_footer):
+
-    with open(index, 'w') as f:
+def write_index(args, index, html):
-        if not args.no_template:
+    with open(index, "w") as index_file:
-            if args.style:
+        if args.style:
-                fs = open(args.style, "r")
+            file_style = open(args.style, "r")
-                style = fs.read()
+            style = file_style.read()
-                styled_html_head = html_head % style
+            styled_html_head = html_head % style
-            else:
+        else:
-                styled_html_head = html_head % ''
+            styled_html_head = html_head % ""
-            f.write(styled_html_head)
+        index_file.write(styled_html_head)
 
         for line in html:
-            f.write(line + '\n')
+            index_file.write(line + "\n")
+
+        index_file.write(html_footer)
+
+
+def handle_text_files(name, full_path, subtype):
+    if name.endswith(".html") or subtype == "html":
+        subtype = "html"
+        # what types of text files to expand
+        tag = '<section id="{}">{}</section>'.format(
+            name, open(full_path).read()
+        )
+    elif subtype in CODE_TYPES or name.endswith(".txt"):
+        # if the plain text is code,
+        # which types do we wrap in pre-tags?
+        tag = "<pre>" + open(full_path).read() + "</pre>"
+    else:
+        subtype = subtype + " unkown-file"
+        tag = "<a href='{}'>{}</a>"
+        # a = FILE_TYPES[type_]
+    return subtype, tag
+
+
+def handle_image_files(name, full_path, args):
+    if args.thumbnail:
+        thumbnail_filename = thumbnail(full_path, name, args)
+        if thumbnail_filename is None:
+            return
+
+        image_alttext = add_alttext(full_path)
+        image_description = add_description(full_path)
+
+        if not image_alttext and not image_description:
+            return image_no_description.format(
+                name=name, thumbnail_filename=thumbnail_filename
+            )
+        if not image_alttext:
+            return image_with_description.format(
+                name=name,
+                thumbnail_filename=thumbnail_filename,
+                image_description=image_description,
+            )
+        if not image_description:
+            return image_with_alttext.format(
+                name=name,
+                thumbnail_filename=thumbnail_filename,
+                image_alttext=image_alttext,
+            )
+        return image_full_figure.format(
+            name=name,
+            thumbnail_filename=thumbnail_filename,
+            image_alttext=image_alttext,
+            image_description=image_description,
+        )
+    return FILE_TYPES["image"].format(name, image_alttext)
+
+
+def remove_index_html(root, files, args):
+    index = os.path.join(root, "index.html")
+    if "index.html" in files:
+        try:
+            if check_distribusi_index(args, index):
+                if args.verbose:
+                    print("Removing index.html from", root)
+                os.remove(index)
+        except Exception as e:
+            print(e)
+    return
 
-        if not args.no_template:
+
-            f.write(html_footer)
+def remove_hidden_files_and_folders(dirs, files):
+    dirs = list(filter(lambda d: not d.startswith("."), dirs))
+    files = list(filter(lambda f: not f.startswith("."), files))
+    return dirs, files
 
 
 def distribusify(args, directory):  # noqa
     for root, dirs, files in os.walk(directory):
+        html = []
 
         if args.exclude_directory:
             if args.verbose:
-                print('Excluding directory:', ", ".join(args.exclude_directory))
+                print(
+                    "Excluding directory:", ", ".join(args.exclude_directory)
+                )
             dirs[:] = [d for d in dirs if d not in args.exclude_directory]
 
         if args.no_hidden:
-            dirs = list(filter(lambda d: not d.startswith('.'), dirs))
+            dirs, files = remove_hidden_files_and_folders(dirs, files)
-            files = list(filter(lambda f: not f.startswith('.'), files))
+
+        if args.remove_index:
+            remove_index_html(root, files, args)
+
+        if args.verbose:
+            print("Generating directory listing for", root)
+
+        for name in sorted(files):
+            if "index.html" in name:
+                continue
+
+            if name.endswith("_thumbnail.jpg"):
+                continue
+
+            if name.endswith("_alttext.txt"):
+                continue
 
-        dirs.sort()
+            if name.endswith("_dv_description.txt"):
-        files.sort()
+                continue
 
-        if not args.remove_index:
+            full_path = os.path.join(root, name)
-            html = []
+            mime = MIME_TYPE.from_file(full_path)
+            type_, subtype = mime.split("/")
+            alttext = name
 
             if args.verbose:
-                print('Generating directory listing for', root)
+                print("Found", name, "as", mime)
-
+            if type_ in FILE_TYPES:
-            for name in sorted(files):
+                match type_:
-
+                    case "text":
-                if 'index.html' not in name:
+                        subtype, tag = handle_text_files(
-                    full_path = os.path.join(root, name)
+                            name, full_path, subtype
-                    mime = MIME_TYPE.from_file(full_path)
+                        )
-                    # example: MIME plain/text becomes 'type' plain 'subtype' text
+                    case "image":
-                    type_, subtype = mime.split('/')
+                        tag = handle_image_files(name, full_path, args)
-
+                        if tag is None:
-                    caption = name
+                            continue
-
+                    case _:
-                    if args.verbose:
+                        tag = FILE_TYPES[type_].format(name, alttext)
-                        print('Found', name, 'as', mime)
+
-
+            if subtype in SUB_TYPES:
-                    if type_ in FILE_TYPES:
+                tag = SUB_TYPES[subtype]
-                        
+
-                        a = FILE_TYPES[type_].format(name, caption)
+            if type_ not in FILE_TYPES and subtype not in SUB_TYPES:
-
+                # catch exceptions not yet defined in FILE_TYPES or SUB_TYPES
-                        # expansion for different kind of text files
+                tag = "<a href='{}'>{}</a>"
-                        if type_ == 'text':
+                if args.verbose:
-                            if name.endswith('.html') or subtype == 'html':
+                    message = (
-                                subtype = 'html'
+                        "not in list of file types, adding as plain href: \n"
-                                # what types of text files to expand
+                    )
-                                a = '<section id="{}">{}</section>'.format(name, open(full_path).read())
+                    print(type_, subtype, message, name)
-                            elif subtype in CODE_TYPES or name.endswith('.txt'):
+                    subtype = subtype + " unkown-file"
-                                # if the plain text is code,
+
-                                # which types do we wrap in pre-tags?
+            tag = tag.replace("{}", name)
-                                a = "<pre>" + open(full_path).read() + "</pre>"
+            html.append(format_div(args, type_, subtype, tag, name))
-                            else:
+
-                                subtype = subtype+' unkown-file'
+        if root != directory:
-                                a = "<a href='{}'>{}</a>"
+            if args.menu_with_index:
-                                # a = FILE_TYPES[type_]
+                html.append('<a href="../index.html">../</a>')
-
+            else:
-                        if type_ == 'image':
+                html.append('<a href="../">../</a>')
-                            if args.thumbnail:
-                                a = thumbnail(full_path, name, args)
-                            if args.no_filenames:
-                                caption = ""
-                                a = FILE_TYPES[type_].format(name, caption)
-                            if args.captions:
-                                caption = caption(full_path)
-                                a = FILE_TYPES[type_].format(name, caption)
-
-                    if subtype in SUB_TYPES:
-                        a = SUB_TYPES[subtype]
-
-                    if type_ not in FILE_TYPES and subtype not in SUB_TYPES:
-                        # catch exceptions not yet defined in FILE_TYPES or SUB_TYPES
-                        a = "<a href='{}'>{}</a>"
-                        if args.verbose:
-                            message = 'not in list of file types, adding as plain href: \n'
-                            print(type_, subtype, message, name)
-                            subtype = subtype + ' unkown-file'
-
-                    a = a.replace('{}', name)
-
-                    html.append(div(args, type_, subtype, a, name))
-
-            if root != directory:
-                if args.menu_with_index:
-                    html.append('<a href="../index.html">../</a>')
-                else:
-                    html.append('<a href="../">../</a>')
-
-            for name in dirs:
-                if args.menu_with_index:
-                    a = "<a href='{}/index.html'>{}</a>".replace('{}', name)
-                else:
-                    a = "<a href='{}'>{}/</a>".replace('{}', name)
-
-                html.insert(0, div(args, 'dir', 'dir', a, 'folder'))
-
-            index = os.path.join(root, 'index.html')
-            if os.path.exists(index):
-                if check_distribusi_index(args, index):
-                   write_index(args,index,html, html_head, html_footer)
-            elif not os.path.exists(index):
-                write_index(args,index,html, html_head, html_footer)
 
-        if args.remove_index:
+        for name in sorted(dirs):
-            index = os.path.join(root, 'index.html')
+            if args.menu_with_index:
-            if 'index.html' in files:
+                tag = "<a href='{}/index.html'>{}</a>".replace("{}", name)
-                try:
+            else:
-                    if check_distribusi_index(args, index):
+                tag = "<a href='{}'>{}/</a>".replace("{}", name)
-                        if args.verbose:
+
-                            print('Removing index.html from', root)
+            html.insert(0, format_div(args, "dir", "dir", tag, "folder"))
-                        os.remove(index)
+
-                except Exception as e:
+        index = os.path.join(root, "index.html")
-                    print(e)
+        if os.path.exists(index):
+            if check_distribusi_index(args, index):
+                write_index(args, index, html)
+        elif not os.path.exists(index):
+            write_index(args, index, html)

distribusi/mappings.py

@@ -1,14 +1,15 @@
-CODE_TYPES = ['x-c', 'x-shellscript', 'x-python']
+CODE_TYPES = ["x-c", "x-shellscript", "x-python"]
 
 FILE_TYPES = {
-    'image': '<figure><img class="image" src="{}"><figcaption>{}</figcaption></figure>',
+    "image": '<img class="image" src="{}" alt="{}">',
-    'text': '<a href="{}" class="text">{}</a>',
+    "text": '<a href="{}" class="text">{}</a>',
-    'video': ('<video controls>' '<source src="{}"></video>'),
+    "video": ("<video controls>" '<source src="{}"></video>'),
-    'audio': ('<audio controls class="audio">' '<source src="{}"></audio>'),
+    "audio": ('<audio controls class="audio">' '<source src="{}"></audio>'),
 }
 
 SUB_TYPES = {
-        'pdf': (
+    "pdf": (
-            '<object data="{}" class="pdf" type="application/pdf">'
+        '<object data="{}" class="pdf" type="application/pdf">'
-            '<embed src="{}" type="application/pdf" /></object>')
+        '<embed src="{}" type="application/pdf" /></object>'
+    )
 }

distribusi/templates/image_templates.py

@@ -0,0 +1,4 @@
+image_no_description = '<a href="{name}"><img class="thumbnail" src="{thumbnail_filename}" alt="{name}"></a>'
+image_with_description = '<figure><a href="{name}"><img class="thumbnail" src="{thumbnail_filename}"></a><figcaption>{image_description}</figcaption></figure>'
+image_with_alttext = '<a href="{name}"><img class="thumbnail" src="{thumbnail_filename}" alt="{image_alttext}"></a>'
+image_full_figure = '<figure><a href="{name}"><img class="thumbnail" src="{thumbnail_filename}" alt="{image_alttext}"></a><figcaption>{image_description}</figcaption></figure>'

distribusi/page_template.py → distribusi/templates/page_template.py

@@ -2,7 +2,7 @@ html_head = """
 <!DOCTYPE html>
 <html lang="en">
   <head>
-    <!-- Generated with distribusi https://git.vvvvvvaria.org/varia/distribusi -->
+    <!-- Generated with distribusi https://git.vvvvvvaria.org/crunk/distribusi -->
     <meta name="generator" content="distribusi" />
     <meta http-equiv="content-type" content="text/html; charset=utf-8">
     <style>

pyproject.toml

@@ -7,3 +7,53 @@ build-backend = "setuptools.build_meta"
 
 [tool.black]
 skip-string-normalization = true
+
+[tool.ruff]
+line-length = 79
+target-version = "py311"
+#include = '\.pyi?$'
+exclude = [
+    ".bzr",
+    ".direnv",
+    ".eggs",
+    ".git",
+    ".git-rewrite",
+    ".hg",
+    ".ipynb_checkpoints",
+    ".mypy_cache",
+    ".nox",
+    ".pants.d",
+    ".pyenv",
+    ".pytest_cache",
+    ".pytype",
+    ".ruff_cache",
+    ".svn",
+    ".tox",
+    ".venv",
+    ".vscode",
+    "__pypackages__",
+    "_build",
+    "buck-out",
+    "build",
+    "dist",
+    "node_modules",
+    "site-packages",
+    "venv",
+]
+
+[tool.ruff.lint]
+# Enable Pyflakes (`F`) and a subset of the pycodestyle (`E`)  codes by default.
+select = ["E4", "E7", "E9", "F"]
+ignore = []
+# Allow fix for all enabled rules (when `--fix`) is provided.
+fixable = ["ALL"]
+unfixable = []
+# Allow unused variables when underscore-prefixed.
+dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+docstring-code-format = true
+line-ending = "auto"
+skip-magic-trailing-comma = false

setup.py

@@ -1,28 +1,36 @@
 from setuptools import find_packages, setup
 
-dependencies = ['pillow >= 6.1.0, < 7.0', 'python-magic >= 0.4.15, < 1.0']
+dependencies = [
+    "pillow >= 10.3.0",
+    "python-magic >= 0.4.15, < 1.0",
+]
 
-with open('README.md', 'r') as handle:
+with open("README.md", "r") as handle:
     long_description = handle.read()
 
 setup(
-    name='distribusi',
+    name="distribusi",
-    version='0.0.10',
+    version="0.0.12",
-    url='https://git.vvvvvvaria.org/varia/distribusi',
+    url="https://git.vvvvvvaria.org/crunk/distribusi",
-    license='GPLv3',
+    license="GPLv3",
-    author='Varia',
+    author="Varia",
     description=(
-        'Distribusi is a content management system for '
+        "Distribusi is a content management system for "
-        'the web that produces static pages based on '
+        "the web that produces static pages based on "
-        'the file system.'
+        "the file system."
     ),
     long_description=long_description,
-    long_description_content_type='text/markdown',
+    long_description_content_type="text/markdown",
-    packages=find_packages(exclude=['tests']),
+    packages=find_packages(exclude=["tests"]),
     include_package_data=True,
     zip_safe=False,
-    platforms='any',
+    platforms="any",
     install_requires=dependencies,
-    entry_points={'console_scripts': ['distribusi = distribusi.cli:cli_entrypoint']},
+    entry_points={
-    classifiers=['Programming Language :: Python :: 3', 'Environment :: Console'],
+        "console_scripts": ["distribusi = distribusi.cli:cli_entrypoint"]
+    },
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "Environment :: Console",
+    ],
 )