add MIT License or something

LICENSE

@@ -0,0 +1,19 @@
+Copyright (c) 2024 xenofem
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

dlibrary/dlibrary.py

@@ -4,10 +4,12 @@ import argparse
 import asyncio
 import importlib_resources as resources
 from pathlib import Path
+from os import getenv
 from os.path import relpath, splitext
 import re
 import shutil
 import sqlite3
+import textwrap
 from urllib.parse import urlparse
 import zipfile
 
@@ -296,12 +298,15 @@ def metadata(args):
 
     con.close()
 
-def copy_contents(src, dest):
+def copy_recursive(src, dest):
     dest.mkdir(parents=True, exist_ok=True)
     for item in src.iterdir():
+        if item.is_dir() and not item.is_symlink():
+            copy_recursive(item, dest / item.name)
+        else:
             shutil.copyfile(item, dest / item.name)
 
-def publish(args):
+def generate(args):
     jenv = Environment(
         loader=PackageLoader("dlibrary"),
         autoescape=select_autoescape()
@@ -347,7 +352,7 @@ def publish(args):
         with open(viewer_dir / 'index.html', 'w') as f:
             f.write(viewer_template.render(depth=3, work=work, title=title, images=images))
 
-    def make_categorization(categorization, query, work_filter):
+    def make_categorization(categorization, query, work_filter, work_style_cards=False):
         categorization_dir = args.destdir / 'site' / categorization
 
         cats = [cat for (cat,) in cur.execute(query)]
@@ -374,6 +379,7 @@ def publish(args):
                 categorization=categorization,
                 categories=cats,
                 samples=cat_samples,
+                work_style_cards=work_style_cards,
             ))
 
     make_categorization(
@@ -395,10 +401,11 @@ def publish(args):
         'series',
         'SELECT DISTINCT series FROM works WHERE series NOT NULL ORDER BY series',
         lambda series: lambda work: work['series'] == series,
+        work_style_cards=True,
     )
 
     with resources.as_file(resources.files("dlibrary")) as r:
-        copy_contents(r / 'static', args.destdir / 'site' / 'static')
+        copy_recursive(r / 'static', args.destdir / 'site' / 'static')
 
     with open(args.destdir / 'site' / 'index.html', 'w') as f:
         f.write(list_template.render(depth=0, works=works))
@@ -406,12 +413,33 @@ def publish(args):
     con.close()
 
 
-argparser = argparse.ArgumentParser(prog='dlibrary')
+argparser = argparse.ArgumentParser(
+    prog='dlibrary',
+    formatter_class=argparse.RawDescriptionHelpFormatter,
+    description=textwrap.dedent("""\
+    Organize DRM-free works purchased from DLSite into a library
+    that can be viewed in a web browser.
+
+    Intended workflow:
+    - `extract` a collection of zipfiles downloaded from DLSite
+      into DLibrary's data directory, giving each work its own
+      subfolder.
+    - `fetch` metadata and thumbnail images for extracted works
+      from DLSite.
+    - `collate` and/or `manual-collate` extracted works,
+      producing a single sequence of image files (or symlinks
+      into the extracted data, when possible) for each work.
+    - Manually adjust works' `metadata` when necessary.
+    - `generate` a static website providing a catalog and viewer
+      for all collated works.
+    """),
+)
+
 argparser.add_argument(
     '-d', '--destdir',
     type=Path,
-    default=Path('./dlibrary'),
+    default=Path(getenv('DLIBRARY_DIR', './dlibrary')),
-    help='directory to store dlibrary content and metadata to (default: ./dlibrary)',
+    help='directory to store dlibrary content and metadata to (default: $DLIBRARY_DIR or ./dlibrary)',
 )
 subparsers = argparser.add_subparsers(title="subcommands", required=True)
 
@@ -433,23 +461,79 @@ parser_extract.set_defaults(func=extract)
 parser_fetch = subparsers.add_parser('fetch', help='fetch metadata and thumbnails')
 parser_fetch.set_defaults(func=fetch)
 
-parser_collate = subparsers.add_parser('collate', help='collate a single sequence of image files for each work')
+parser_collate = subparsers.add_parser(
+    'collate',
+    help='collate each work into a sequence of image files',
+    formatter_class=argparse.RawDescriptionHelpFormatter,
+    description=textwrap.dedent("""\
+    For each extracted work that has not already been collated,
+    DLibrary will attempt to intuit its structure as follows:
+
+    - Enter the work's directory. If the directory contains
+      nothing except a single subdirectory (ignoring a few types
+      of files that are definitely not relevant), traverse
+      downwards repeatedly.
+    - If the current directory contains nothing except a single
+      PDF (again, ignoring irrelevant files), attempt to extract
+      a series of images from the PDF. This process expects that
+      each page of the PDF consists of a single embedded image,
+      which will be extracted at full resolution. Support for
+      more complex PDFs is not yet implemented.
+    - If the current directory contains nothing except image
+      files, and the image files are named in a way that clearly
+      indicates a complete numerical order (each filename
+      consists of a shared prefix followed by a distinct
+      number), symlink files in the inferred order.
+    - Otherwise, skip processing this work for now.
+
+    DLibrary can be given "collation hints" which provide
+    alternative starting points for this search process. A hint
+    is a path under $DLIBRARY_DIR/extract/[work id]/
+    indicating a different directory or PDF file to begin the
+    search process for that work, rather than starting at the
+    top level of the extracted data. There can be at most one
+    hint per work; for more complicated scenarios where a work
+    includes multiple folders that need to be collated together,
+    or where filenames do not clearly indicate an ordering, use
+    `manual-collate` instead.
+    """),
+)
 parser_collate.add_argument(
     'hints',
     metavar='PATH',
     type=Path,
     nargs='*',
-    help='manually-specified paths of subdirectories or PDFs within extraction folders, at most one per work',
+    help='paths within extraction folders as collation hints'
 )
 parser_collate.set_defaults(func=collate)
 
-parser_manual_collate = subparsers.add_parser('manual-collate', help='collate a specific work manually, specifying all paths to include')
+parser_manual_collate = subparsers.add_parser(
+    'manual-collate',
+    help='collate a single work manually',
+    formatter_class=argparse.RawDescriptionHelpFormatter,
+    description=textwrap.dedent("""\
+    All provided paths must be under $DLIBRARY_DIR/extract/[work id]/
+    for the work being manually collated. `manual-collate` can
+    only handle one work at a time. Paths are used as follows:
+
+    - If a path is a directory, all *image files* immediately
+      inside that directory will be appended to the sequence. If
+      files are named in a way which indicates a clear ordering,
+      that ordering will be used. Otherwise, filenames will be
+      sorted lexicographically. Non-image files and
+      subdirectories will be ignored.
+    - If a path is an image file, that image file will be
+      appended to the sequence.
+    - If a path is a PDF file, page images will be extracted
+      from that PDF and appended to the sequence.
+"""),
+)
 parser_manual_collate.add_argument(
     'paths',
     metavar='PATH',
     type=Path,
     nargs='+',
-    help='paths of files (images to symlink, pdfs to extract) or directories (symlink all images in the directory, no recursion, best-effort sorting)'
+    help='paths within a single work to be collated in sequence',
 )
 parser_manual_collate.set_defaults(func=manual_collate)
 
@@ -462,8 +546,20 @@ parser_metadata.add_argument(
 )
 parser_metadata.set_defaults(func=metadata)
 
-parser_publish = subparsers.add_parser('publish', help='generate HTML/CSS/JS for library site')
+parser_generate = subparsers.add_parser(
-parser_publish.set_defaults(func=publish)
+    'generate',
+    help='generate HTML/CSS/JS for library site',
+    formatter_class=argparse.RawDescriptionHelpFormatter,
+    description=textwrap.dedent("""\
+    The static site will be generated under $DLIBRARY_DIR/site/
+    and can be served by pointing an HTTP server at that
+    directory. Note that some files inside the static site
+    hierarchy will be symlinks into $DLIBRARY_DIR/extract/
+    outside the site hierarchy, so make sure your HTTP server
+    will allow those symlinks to be read.
+    """),
+)
+parser_generate.set_defaults(func=generate)
 
 def main():
     args = argparser.parse_args()

dlibrary/static/dlibrary.css

@@ -51,12 +51,19 @@ body {
 
 .work-container {
     display: flex;
+    flex-wrap: wrap;
     justify-content: center;
     gap: 30px;
 }
 
+.work-preview img {
+    max-width: 100%;
+}
+
 .work-info {
-    max-width: min(50%, 500px);
+    flex-basis: 40%;
+    flex-grow: 1;
+    max-width: 500px;
 }
 
 .work-info td, .work-info th {

dlibrary/static/viewer.css

@@ -4,3 +4,39 @@ html, body {
     padding: 0;
     margin: 0;
 }
+
+.tap {
+    background: #000000;
+    opacity: 0.8;
+    position: fixed;
+    animation: 2s linear forwards fade;
+    display: flex;
+    justify-content: center;
+    align-items: center;
+}
+
+@keyframes fade {
+    to { opacity: 0; }
+}
+
+#tap-left, #tap-right {
+    position: fixed;
+    bottom: 0px;
+    width: 30vw;
+    height: 100vh;
+}
+
+#tap-left {
+    left: 0px;
+}
+
+#tap-right {
+    right: 0px;
+}
+
+#tap-back {
+    top: 0px;
+    left: 30vw;
+    width: 40vw;
+    height: 20vh;
+}

dlibrary/static/viewer.js

@@ -5,6 +5,7 @@ document.addEventListener('DOMContentLoaded', () => {
     let paused = true;
     let interval;
     let elapsed = 0;
+    let rtl = (localStorage.getItem(`${WORK_ID}-rtl`) !== "false");
 
     function startTimer() {
         if (interval) {
@@ -78,16 +79,46 @@ document.addEventListener('DOMContentLoaded', () => {
         }
     }
 
+    function left() {
+        if (currentPage === 0) {
+            rtl = true;
+            localStorage.setItem(`${WORK_ID}-rtl`, rtl);
+        }
+        changePage(currentPage + (rtl ? 1 : -1));
+    }
+
+    function right() {
+        if (currentPage === 0) {
+            rtl = false;
+            localStorage.setItem(`${WORK_ID}-rtl`, rtl);
+        }
+        changePage(currentPage + (rtl ? -1 : 1));
+    }
+
+    function exitToWork() {
+        changeDuration(duration, true);
+        localStorage.setItem(`${WORK_ID}-currentPage`, 0);
+        window.location.href = `../${INDEX}`;
+    }
+
+    function hideTapZones() {
+        for (const el of document.getElementsByClassName('tap')) {
+            el.style.opacity = 0;
+        }
+    }
+
     changePage(currentPage);
     changeDuration(duration, paused);
 
-    document.onkeydown = event =>{
+    document.onkeydown = event => {
+        hideTapZones();
+
         switch (event.keyCode) {
         case 32: //space
             changeDuration(duration, !paused);
             break;
         case 37: //left
-            changePage(currentPage - 1);
+            left();
             break;
         case 38: //up
             if (2 <= duration && duration <= 10) {
@@ -99,7 +130,7 @@ document.addEventListener('DOMContentLoaded', () => {
             }
             break;
         case 39: //right
-            changePage(currentPage + 1);
+            right();
             break;
         case 40: //down
             if (duration < 10) {
@@ -111,10 +142,13 @@ document.addEventListener('DOMContentLoaded', () => {
             }
             break;
         case 13: //enter
-            changeDuration(duration, true);
+            exitToWork();
-            localStorage.setItem(`${WORK_ID}-currentPage`, 0);
-            window.location.href = "../";
             break;
         }
     };
+
+    document.onclick = hideTapZones;
+    document.getElementById("tap-left").onclick = left;
+    document.getElementById("tap-right").onclick = right;
+    document.getElementById("tap-back").onclick = exitToWork;
 });

dlibrary/templates/base.html

@@ -6,7 +6,7 @@
     <meta name="viewport" content="width=device-width, initial-scale=1">
     <meta name="color-scheme" content="dark">
     <title>{% block title %}{% if title %}{{ title }} - {% else %}{% endif %}DLibrary{% endblock %}</title>
-    <link rel="stylesheet" type="text/css" href="{{ root() }}static/dlibrary.css">
+    <link rel="stylesheet" type="text/css" href="{{ root() }}/static/dlibrary.css">
     {% block head %}{% endblock %}
   </head>
   <body>

dlibrary/templates/categorization.html

@@ -1,18 +1,18 @@
 {% extends "base.html" %}
 {% block title %}{{ categorization.capitalize() }} - DLibrary{% endblock %}
 {% block body %}
-{% from 'utils.html' import urlcat, root with context %}
+{% from 'utils.html' import urlcat, index, root with context %}
-<h1 id="title"><a href="{{ root() }}">DLibrary</a> &gt; <a href="{{ root() }}{{ categorization }}">{{ categorization.capitalize() }}</a></h1>
+<h1 id="title"><a href="{{ root() }}/{{ index() }}">DLibrary</a> &gt; {{ categorization.capitalize() }}</h1>
 {% include 'nav.html' %}
 <div class="card-listing">
   {% for cat in categories %}
-  <div class="card category">
+  <div class="card {% if not work_style_cards %}category{% endif %}">
-    <a href="{{ root() }}{{ categorization }}/{{ urlcat(cat) }}/">
+    <a href="{{ root() }}/{{ categorization }}/{{ urlcat(cat) }}/{{ index() }}">
       <div class="card-title">
         {{ cat }}
       </div>
       {% if samples[cat] %}
-      <img src="{{ root() }}thumbnails/{{ samples[cat]['id'] }}.jpg">
+      <img src="{{ root() }}/thumbnails/{{ samples[cat]['id'] }}.jpg">
       {% endif %}
     </a>
   </div>

dlibrary/templates/list.html

@@ -1,13 +1,13 @@
 {% extends 'base.html' %}
 {% block body %}
-{% from 'utils.html' import root with context %}
+{% from 'utils.html' import index, root with context %}
-<h1 id="title"><a href="{{ root() }}">DLibrary</a>{% if categorization %} &gt; <a href="{{ root() }}{{ categorization }}">{{ categorization.capitalize() }}</a>{% endif %}{% if title %} &gt; {{ title }}{% endif %}</h1>
+<h1 id="title"><a href="{{ root() }}/{{ index() }}">DLibrary</a>{% if categorization %} &gt; <a href="{{ root() }}/{{ categorization }}/{{ index() }}">{{ categorization.capitalize() }}</a>{% endif %}{% if title %} &gt; {{ title }}{% endif %}</h1>
 {% include 'nav.html' %}
 <div class="card-listing">
   {% for work in works %}
   <div class="card">
-    <a href="{{ root() }}works/{{ work['id'] }}/">
+    <a href="{{ root() }}/works/{{ work['id'] }}/{{ index() }}">
-      <img src="{{ root() }}thumbnails/{{ work['id'] }}.jpg">
+      <img src="{{ root() }}/thumbnails/{{ work['id'] }}.jpg">
       <div class="card-authors">
         [{% if work['circle'] %}{{ work['circle'] }}{% endif %}{% if work['circle'] and work['authors'] %} ({% endif %}{{ ', '.join(work['authors']) }}{% if work['circle'] and work['authors'] %}){% endif %}]
       </div>

dlibrary/templates/nav.html

@@ -1,2 +1,2 @@
-{% from 'utils.html' import root with context %}
+{% from 'utils.html' import root, index with context %}
-<div class="nav">{% for c in ['circles', 'authors', 'tags', 'series'] %}<div class="nav-item"><a href="{{ root() }}{{ c }}">{{ c.capitalize() }}</a></div>{% endfor %}</div>
+<div class="nav">{% for c in ['circles', 'authors', 'tags', 'series'] %}<div class="nav-item"><a href="{{ root() }}/{{ c }}/{{ index() }}">{{ c.capitalize() }}</a></div>{% endfor %}</div>

dlibrary/templates/utils.html

@@ -1,2 +1,3 @@
-{% macro root() %}{% for i in range(depth) %}../{% endfor %}{% endmacro %}
+{% macro root() %}{% if depth == 0 %}.{% else %}..{% endif %}{{ '/..' * (depth-1) }}{% endmacro %}
+{% macro index() %}{% if not noindex %}index.html{% endif %}{% endmacro %}
 {% macro urlcat(s) %}{{ s | replace('/', ' ') | urlencode }}{% endmacro %}

dlibrary/templates/viewer.html

@@ -1,20 +1,38 @@
 {% extends 'base.html' %}
-{% from 'utils.html' import root with context %}
+{% from 'utils.html' import index, root with context %}
 {% block head %}
-<link rel="stylesheet" type="text/css" href="{{ root() }}static/viewer.css">
+<link rel="stylesheet" type="text/css" href="{{ root() }}/static/viewer.css">
 <script>
   const WORK_ID = "{{ work['id'] }}";
+  const INDEX = "{{ index() }}";
 </script>
-<script src="{{ root() }}static/viewer.js"></script>
+<script src="{{ root() }}/static/viewer.js"></script>
 {% endblock %}
 {% block body %}
 <div id="viewer-images">
   {% for filename in images %}
-  <img src="{{ root() }}images/{{ work['id'] }}/{{ filename }}" class="viewer-image">
+  <img src="{{ root() }}/images/{{ work['id'] }}/{{ filename }}" class="viewer-image">
   {% endfor %}
 </div>
 <div id="progress"></div>
 <div id="page-num"></div>
 <div id="duration"></div>
+<div id="controls">
+  <div id="tap-left" class="tap">
+    <svg version='1.1' xmlns='http://www.w3.org/2000/svg' xmlns:xlink='http://www.w3.org/1999/xlink' width='80' height='140' viewBox='-10 -70 80 140'>
+      <path d='M 60 -60 L 0 0 L 60 60' fill='none' stroke='#ffffff' stroke-linecap='round' stroke-linejoin='round' stroke-miterlimit='10' stroke-width='10'/>
+    </svg>
+  </div>
+  <div id="tap-right" class="tap">
+    <svg version='1.1' xmlns='http://www.w3.org/2000/svg' xmlns:xlink='http://www.w3.org/1999/xlink' width='80' height='140' viewBox='-10 -70 80 140'>
+      <path d='M 0 -60 L 60 0 L 0 60' fill='none' stroke='#ffffff' stroke-linecap='round' stroke-linejoin='round' stroke-miterlimit='10' stroke-width='10'/>
+    </svg>
+  </div>
+  <div id="tap-back" class="tap">
+    <svg version='1.1' xmlns='http://www.w3.org/2000/svg' xmlns:xlink='http://www.w3.org/1999/xlink' width='140' height='80' viewBox='-70 -10 140 80'>
+      <path d='M -60 60 L 0 0 L 60 60' fill='none' stroke='#ffffff' stroke-linecap='round' stroke-linejoin='round' stroke-miterlimit='10' stroke-width='10'/>
+    </svg>
+  </div>
+</div>
 <div id="image-container"></div>
 {% endblock %}

dlibrary/templates/work.html

@@ -1,11 +1,11 @@
 {% extends 'base.html' %}
 {% block body %}
-{% from 'utils.html' import urlcat, root with context %}
+{% from 'utils.html' import urlcat, root, index with context %}
-<h1 id="title"><a href="{{ root() }}">DL</a> &gt; {{ title }}</h1>
+<h1 id="title"><a href="{{ root() }}/{{ index() }}">DL</a> &gt; {{ title }}</h1>
 <div class="work-container">
   <div class="work-preview">
-    <a href="view/">
+    <a href="view/{{ index() }}">
-      <img src="{{ root() }}thumbnails/{{ work['id'] }}.jpg">
+      <img src="{{ root() }}/thumbnails/{{ work['id'] }}.jpg">
     </a>
   </div>
   <div class="work-info">
@@ -13,28 +13,29 @@
       {% if work['circle'] %}
       <tr>
         <th>Circle</th>
-        <td><a class="work-info-link" href="{{ root() }}circles/{{ urlcat(work['circle']) }}">{{ work['circle'] }}</a></td>
+        <td><a class="work-info-link" href="{{ root() }}/circles/{{ urlcat(work['circle']) }}/{{ index() }}">{{ work['circle'] }}</a></td>
       </tr>
       {% endif %}
       {% if work['authors'] %}
       <tr>
         <th>Authors</th>
-        <td>{% for author in work['authors'] %}<a class="work-info-link" href="{{ root() }}authors/{{ urlcat(author) }}">{{ author }}</a> {% endfor %}</td>
+        <td>{% for author in work['authors'] %}<a class="work-info-link" href="{{ root() }}/authors/{{ urlcat(author) }}/{{ index() }}">{{ author }}</a> {% endfor %}</td>
       </tr>
       {% endif %}
       {% if work['tags'] %}
       <tr>
         <th>Tags</th>
-        <td>{% for tag in work['tags'] %}<a class="work-info-link" href="{{ root() }}tags/{{ urlcat(tag) }}">{{ tag }}</a> {% endfor %}</td>
+        <td>{% for tag in work['tags'] %}<a class="work-info-link" href="{{ root() }}/tags/{{ urlcat(tag) }}/{{ index() }}">{{ tag }}</a> {% endfor %}</td>
       </tr>
       {% endif %}
       {% if work['series'] %}
       <tr>
         <th>Series</th>
-        <td><a class="work-info-link" href="{{ root() }}series/{{ urlcat(work['series']) }}">{{ work['series'] }}</a></td>
+        <td><a class="work-info-link" href="{{ root() }}/series/{{ urlcat(work['series']) }}/{{ index() }}">{{ work['series'] }}</a></td>
       </tr>
       {% endif %}
     </table>
+    {{ work['description'] }}
   </div>
 </div>
 {% endblock %}

pyproject.toml

@@ -1,6 +1,9 @@
 [project]
 name = "dlibrary"
 version = "0.1"
+description = "Cataloging tool and viewer for downloaded DLSite purchases"
+license = {file = "LICENSE"}
+authors = [{name = "xenofem"}]
 dependencies = [
     "requests",
     "PyMuPDF",