document v2.1.2

Signed-off-by: Brian S. Stephan <bss@incorporeal.org>

CHANGELOG.md

@@ -2,6 +2,66 @@
 
 Included is a summary of changes to the project, by version. Details can be found in the commit history.
 
+## v2.1.2
+
+### Features
+
+* An optional license declaration can be added to the footer, with a config "LICENSE" directive.
+
+### Improvements
+
+* Style changes in footnotes, hrs, table colors, footnote links, full width figures.
+* Have floats clear their side, to not have a waterfall/ratchet effect when too many floating things are next to each
+  other.
+* Add borders to the plain style tables.
+
+### Miscellaneous
+
+* One HTML tweak to make the W3C CSS validator happy.
+* Some old code from the pre-SSG days has been removed.
+
+## v2.1.1
+
+### Improvements
+
+* Use the h1-as-name feature from v2.1.0 also to generate the page name in breadcrumbs. This changes the behavior on
+  pages with an h1 but no Title: meta tag to have a better name, of course, but also changes the behavior on pages with
+  neither a h1 nor a Title: meta tag to have a leading slash (e.g. /page-filename) where there previously was not one
+  (e.g. just page-filename). This seems like an acceptable trade-off.
+
+### Miscellaneous
+
+* With the minor breadcrumb change, a method used to finagle the breadcrumb no-name name is no longer necessary.
+
+## v2.1.0
+
+### Features
+
+* The page title (also used in the `og:title` header) and the optional description used in the `og:description` header
+  can be derived from the contents of the page content, if the markdown meta tags are not supplied. The first `h1` is
+  used for the title, and the first `p` is used for the description. This is largely to save some time writing pages
+  that one wants to look nice, especially in a social media card, and removes some repetition.
+
+### Miscellaneous
+
+* Requirements bumped, which led to...
+* Python 3.9 has been removed from the supported versions.
+* Added some miscellaneous unit tests and coverage changes to keep us at 95% (which only dropped for a library reason I
+  don't understand).
+
+## v2.0.5
+
+### Features
+
+* The Markdown parser replaces links to e.g. `[Page](page.md)` with a href of `page`, rather than the Markdown source
+  specifying a link of `page` explicitly. This allows for some improved site navigation when browsing the Markdown
+  files, e.g. when going to files in Vim, or browsing a site in a Git web UI.
+
+### Miscellaneous
+
+* `tox.ini` also runs tests in a Python 3.13 environment now.
+* Some trivial bumps to CI requirements.
+
 ## v2.0.4
 
 ### Bugfixes

README.md

@@ -7,8 +7,8 @@ A lightweight static site generator for Markdown-based sites.
 Something like the following should suffice:
 
 ```
-% virtualenv --python=python3.9 env-py3.9
-% source env-py3.9/bin/activate
+% virtualenv --python=python3.10 env-py3.10
+% source env-py3.10/bin/activate
 % pip install -U pip
 % pip install incorporeal-cms
 % incorporealcms-build ./path/to/instance ./path/to/output/www/root

incorporealcms/__init__.py

@@ -22,7 +22,7 @@ jinja_env = Environment(
 try:
     # packaged/pip install -e . value
     from ._version import version as __version__
-except ImportError:
+except ImportError:  # pragma: no cover
     # local clone value
     from setuptools_scm import get_version
     __version__ = get_version(root='..', relative_to=__file__)

incorporealcms/feed.py

@@ -51,7 +51,7 @@ def generate_feed(feed_type: str, instance_dir: str, dest_dir: str) -> None:
         # get the actual file to parse it
         resolved_path = os.path.relpath(os.path.realpath(feed_entry_path), pages_dir)
         try:
-            content, md, page_name, page_title, mtime = parse_md(os.path.join(pages_dir, resolved_path), pages_dir)
+            content, md, page_name, page_title, _, mtime = parse_md(os.path.join(pages_dir, resolved_path), pages_dir)
             link = f'https://{Config.DOMAIN_NAME}{instance_resource_path_to_request_path(resolved_path)}'
         except (OSError, ValueError, TypeError):
             logger.exception("error loading/rendering markdown!")

incorporealcms/markdown.py

@@ -13,6 +13,7 @@ import os
 import re
 
 import markdown
+from bs4 import BeautifulSoup
 from markupsafe import Markup
 
 from incorporealcms import jinja_env
@@ -58,7 +59,18 @@ def parse_md(path: str, pages_root: str):
         with open(absolute_path, 'r') as input_file:
             mtime = datetime.datetime.fromtimestamp(os.path.getmtime(input_file.name), tz=datetime.timezone.utc)
             entry = input_file.read()
+
         logger.debug("path '%s' read", absolute_path)
+
+        # remove .md extensions used for navigating in vim and replace them with
+        # the pattern we use for HTML output here
+        # foo/index.md -> foo/, foo/index.md#anchor -> foo/#anchor
+        # ../index.md -> ../, ../index.md#anchor -> ../#anchor
+        entry = re.sub(r'\[([^]]+)\]\(([^)]+)index.md(#[^)]*)?\)', r'[\1](\2\3)', entry)
+        # index.md -> ., index.md#anchor -> .#anchor
+        entry = re.sub(r'\[([^]]+)\]\(index.md(#[^)]*)?\)', r'[\1](.\2)', entry)
+        # bar.md -> bar, foo/bar.md -> foo/bar, bar.md#anchor -> bar#anchor
+        entry = re.sub(r'\[([^]]+)\]\(([^)]+).md(#[^)]*)?\)', r'[\1](\2\3)', entry)
         md = init_md()
         content = Markup(md.convert(entry))     # nosec B704
     except (OSError, FileNotFoundError):
@@ -71,11 +83,42 @@ def parse_md(path: str, pages_root: str):
     logger.debug("file metadata: %s", md.Meta)
 
     rel_path = os.path.relpath(path, pages_root)
-    page_name = get_meta_str(md, 'title') if md.Meta.get('title') else instance_resource_path_to_request_path(rel_path)
+
+    page_name, page_description = _get_metadata_from_parsed_page(md, content, rel_path)
     page_title = f'{page_name} - {Config.TITLE_SUFFIX}' if page_name else Config.TITLE_SUFFIX
     logger.debug("title (potentially derived): %s", page_title)
 
-    return content, md, page_name, page_title, mtime
+    return content, md, page_name, page_title, page_description, mtime
+
+
+def _get_metadata_from_parsed_page(md, content, path: str):
+    """Get the page name and description from a Markdown object and/or HTML output of a page.
+
+    Args:
+        md: the parsed Markdown object, potentially including Meta tags
+        content: the Markdown page content converted to HTML, to run through BeautifulSoup
+        path: path of the page, to derive the name from as a fallback
+    """
+    soup = BeautifulSoup(content, features='lxml')
+
+    # get the page title first from the markdown tags, second from the first h1, last from the path
+    page_name = None
+    if md.Meta.get('title'):
+        page_name = get_meta_str(md, 'title')
+    elif h1_tag := soup.find('h1'):
+        page_name = h1_tag.string
+    elif not page_name:
+        page_name = instance_resource_path_to_request_path(path)
+
+    # get the page description from the markdown tags or first paragraph
+    page_description = None
+    if md.Meta.get('description'):
+        page_description = get_meta_str(md, 'description')
+    elif p_tag := soup.find('p'):
+        if page_description := p_tag.string:
+            page_description = page_description.replace('\n', ' ')
+
+    return page_name, page_description
 
 
 def handle_markdown_file_path(path: str, pages_root: str) -> str:
@@ -86,21 +129,16 @@ def handle_markdown_file_path(path: str, pages_root: str) -> str:
         pages_root: the absolute path to the pages/ dir, which the path should be within. necessary for
                     proper resolution of resolving parent pages (which needs to know when to stop)
     """
-    content, md, page_name, page_title, mtime = parse_md(path, pages_root)
+    content, md, page_name, page_title, page_description, mtime = parse_md(path, pages_root)
     relative_path = os.path.relpath(path, pages_root)
     parent_navs = generate_parent_navs(relative_path, pages_root)
     extra_footer = get_meta_str(md, 'footer') if md.Meta.get('footer') else None
     template_name = get_meta_str(md, 'template') if md.Meta.get('template') else 'base.html'
 
-    # check if this has a HTTP redirect
-    redirect_url = get_meta_str(md, 'redirect') if md.Meta.get('redirect') else None
-    if redirect_url:
-        raise NotImplementedError("redirects in markdown are unsupported!")
-
     template = jinja_env.get_template(template_name)
     return template.render(title=page_title,
                            config=Config,
-                           description=get_meta_str(md, 'description'),
+                           description=page_description,
                            image=Config.BASE_HOST + get_meta_str(md, 'image'),
                            content=content,
                            base_url=Config.BASE_HOST + instance_resource_path_to_request_path(relative_path),
@@ -144,16 +182,8 @@ def generate_parent_navs(path, pages_root: str):
         try:
             with open(os.path.join(pages_root, path), 'r') as entry_file:
                 entry = entry_file.read()
-            _ = Markup(md.convert(entry))       # nosec B704
-            page_name = (" ".join(md.Meta.get('title')) if md.Meta.get('title')
-                         else request_path_to_breadcrumb_display(request_path))
+            content = Markup(md.convert(entry))  # nosec B704
+            page_name, _ = _get_metadata_from_parsed_page(md, content, os.path.relpath(path, parent_resource_dir))
             return generate_parent_navs(parent_resource_path, pages_root) + [(page_name, request_path)]
         except FileNotFoundError:
             return generate_parent_navs(parent_resource_path, pages_root) + [(request_path, request_path)]
-
-
-def request_path_to_breadcrumb_display(path):
-    """Given a request path, e.g. "/foo/bar/baz/", turn it into breadcrumby text "baz"."""
-    undired = path.rstrip('/')
-    leaf = undired[undired.rfind('/'):]
-    return leaf.strip('/')

incorporealcms/static/css/base.css

@@ -116,19 +116,26 @@ img {
     max-width: 75% !important;
 }
 
+.full-width {
+    max-width: 100%;
+}
+
 .img-center {
     display: block;
+    clear: both;
     margin-left: auto;
     margin-right: auto;
 }
 
 .img-left {
     float: left;
+    clear: left;
     margin-right: 1em;
 }
 
 .img-right {
     float: right;
+    clear: right;
     margin-left: 1em;
 }
 
@@ -144,12 +151,14 @@ figure {
 
 figure.right {
     float: right;
+    clear: right;
     margin-left: 10px;
     display: block;
 }
 
 figure.left {
     float: left;
+    clear: left;
     margin-right: 10px;
     display: block;
 }
@@ -164,14 +173,19 @@ figcaption {
     font-size: 0.9em;
 }
 
-.footnote {
+div.content .footnote {
     font-size: 0.8em;
 }
 
-.footnote p {
+div.content .footnote p {
     margin: 0;
 }
 
 .footnote-ref:link, .footnote-ref:visited, .footnote-ref:hover, .footnote-ref:active {
     font-weight: normal;
 }
+
+.footnote-ref {
+    font-size: 0.75em;
+    margin-left: 1px;
+}

incorporealcms/static/css/dark.css

@@ -14,11 +14,15 @@ body {
     background: #111;
 }
 
+hr {
+    color: #333;
+}
+
 h1, h2, h3, h4, h5, h6 {
     color: #B31D15;
 }
 
-p a, ul a, ol a {
+p a, ul a, ol a, sup a {
     color: #DDD;
 }
 
@@ -26,7 +30,7 @@ footer a {
     color: #999;
 }
 
-p a:hover, ul a:hover, ol a:hover, footer a:hover {
+p a:hover, ul a:hover, ol a:hover, footer a:hover, sup a:hover {
     color: #B31D15;
 }
 
@@ -44,7 +48,7 @@ table, th, td {
 }
 
 th {
-    background: #333;
+    background: #111;
 }
 
 blockquote {

incorporealcms/static/css/light.css

@@ -14,11 +14,15 @@ body {
     background: #EEE;
 }
 
+hr {
+    color: #CCC;
+}
+
 h1, h2, h3, h4, h5, h6 {
     color: #811610;
 }
 
-p a, ul a, ol a {
+p a, ul a, ol a, sup a {
     color: #222;
 }
 
@@ -26,7 +30,7 @@ footer a {
     color: #999;
 }
 
-p a:hover, ul a:hover, ol a:hover, footer a:hover {
+p a:hover, ul a:hover, ol a:hover, footer a:hover, sup a:hover {
     color: #811610;
 }
 
@@ -44,7 +48,7 @@ table, th, td {
 }
 
 th {
-    background: #CCC;
+    background: #EEE;
 }
 
 blockquote {

incorporealcms/static/css/plain.css

@@ -9,6 +9,10 @@ div.header {
     justify-content: space-between;
 }
 
+table, th, td {
+    border: 1px solid;
+}
+
 .img-25 {
     max-width: 25% !important;
 }

incorporealcms/templates/base.html

@@ -18,7 +18,7 @@ SPDX-License-Identifier: GPL-3.0-or-later
 <link rel="icon" href="{{ config.FAVICON }}">
 <link rel="alternate" type="application/atom+xml" href="/feed/atom">
 <link rel="alternate" type="application/rss+xml" href="/feed/rss">
-<script type="text/javascript" src="/static/js/style_switcher.js"></script>
+<script src="/static/js/style_switcher.js"></script>
 
 <div {% block site_class %}class="site-wrap site-wrap-normal-width"{% endblock %}>
     {% block header %}
@@ -44,7 +44,11 @@ SPDX-License-Identifier: GPL-3.0-or-later
     </div>
     <footer>
         {% if extra_footer %}<div class="extra-footer"><i>{{ extra_footer|safe }}</i></div>{% endif %}
-        <div class="footer"><i>Last modified: {{ mtime }}</i></div>
+        <div class="footer">
+            <i>Last modified: {{ mtime }}.<br />
+               {% if config.LICENSE %} Available via {{ config.LICENSE|safe }}{% endif %}.
+            </i>
+        </div>
     </footer>
     {% endblock %}
 </div>

pyproject.toml

@@ -10,8 +10,8 @@ license = {text = "GPL-3.0-or-later"}
 authors = [
 	{name = "Brian S. Stephan", email = "bss@incorporeal.org"},
 ]
-requires-python = ">=3.9"
-dependencies = ["feedgen", "jinja2", "Markdown", "termcolor"]
+requires-python = ">=3.10"
+dependencies = ["beautifulsoup4", "feedgen", "jinja2", "Markdown", "termcolor"]
 dynamic = ["version"]
 classifiers = [
 	"Programming Language :: Python :: 3",

requirements/requirements-dev.txt

@@ -1,40 +1,41 @@
 #
-# This file is autogenerated by pip-compile with Python 3.12
+# This file is autogenerated by pip-compile with Python 3.13
 # by the following command:
 #
 #    pip-compile --extra=dev --output-file=requirements/requirements-dev.txt
 #
 annotated-types==0.7.0
     # via pydantic
-attrs==25.3.0
+anyio==4.12.1
+    # via httpx
+attrs==25.4.0
     # via reuse
-authlib==1.5.1
+authlib==1.6.6
     # via safety
-bandit==1.8.3
+bandit==1.9.3
     # via incorporeal-cms (pyproject.toml)
-binaryornot==0.4.4
-    # via reuse
-boolean-py==4.0
-    # via
-    #   license-expression
-    #   reuse
-build==1.2.2.post1
+beautifulsoup4==4.14.3
+    # via incorporeal-cms (pyproject.toml)
+boolean-py==5.0
+    # via license-expression
+build==1.4.0
     # via pip-tools
-cachetools==5.5.2
+cachetools==6.2.6
     # via tox
-certifi==2025.1.31
-    # via requests
-cffi==1.17.1
+certifi==2026.1.4
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+cffi==2.0.0
     # via cryptography
 chardet==5.2.0
-    # via
-    #   binaryornot
-    #   tox
-charset-normalizer==3.4.1
+    # via tox
+charset-normalizer==3.4.4
     # via
     #   python-debian
     #   requests
-click==8.1.8
+click==8.3.1
     # via
     #   nltk
     #   pip-tools
@@ -43,17 +44,17 @@ click==8.1.8
     #   typer
 colorama==0.4.6
     # via tox
-coverage[toml]==7.7.0
+coverage[toml]==7.13.2
     # via pytest-cov
-cryptography==44.0.2
+cryptography==46.0.4
     # via
     #   authlib
     #   secretstorage
-distlib==0.3.9
+distlib==0.4.0
     # via virtualenv
 dlint==0.16.0
     # via incorporeal-cms (pyproject.toml)
-docutils==0.21.2
+docutils==0.22.4
     # via readme-renderer
 dparse==0.6.4
     # via
@@ -61,12 +62,12 @@ dparse==0.6.4
     #   safety-schemas
 feedgen==1.0.0
     # via incorporeal-cms (pyproject.toml)
-filelock==3.16.1
+filelock==3.20.3
     # via
     #   safety
     #   tox
     #   virtualenv
-flake8==7.1.2
+flake8==7.3.0
     # via
     #   dlint
     #   flake8-builtins
@@ -78,7 +79,7 @@ flake8==7.1.2
     #   incorporeal-cms (pyproject.toml)
 flake8-blind-except==0.2.1
     # via incorporeal-cms (pyproject.toml)
-flake8-builtins==2.5.0
+flake8-builtins==3.1.0
     # via incorporeal-cms (pyproject.toml)
 flake8-docstrings==1.7.0
     # via incorporeal-cms (pyproject.toml)
@@ -86,27 +87,36 @@ flake8-executable==2.1.3
     # via incorporeal-cms (pyproject.toml)
 flake8-fixme==1.1.1
     # via incorporeal-cms (pyproject.toml)
-flake8-isort==6.1.2
+flake8-isort==7.0.0
     # via incorporeal-cms (pyproject.toml)
 flake8-logging-format==2024.24.12
     # via incorporeal-cms (pyproject.toml)
 flake8-mutable==1.2.0
     # via incorporeal-cms (pyproject.toml)
-flake8-pyproject==1.2.3
+flake8-pyproject==1.2.4
     # via incorporeal-cms (pyproject.toml)
+h11==0.16.0
+    # via httpcore
+httpcore==1.0.9
+    # via httpx
+httpx==0.28.1
+    # via safety
 id==1.5.0
     # via twine
-idna==3.10
-    # via requests
-iniconfig==2.0.0
+idna==3.11
+    # via
+    #   anyio
+    #   httpx
+    #   requests
+iniconfig==2.3.0
     # via pytest
-isort==6.0.1
+isort==7.0.0
     # via flake8-isort
 jaraco-classes==3.4.0
     # via keyring
-jaraco-context==6.0.1
+jaraco-context==6.1.0
     # via keyring
-jaraco-functools==4.1.0
+jaraco-functools==4.4.0
     # via keyring
 jeepney==0.9.0
     # via
@@ -117,43 +127,44 @@ jinja2==3.1.6
     #   incorporeal-cms (pyproject.toml)
     #   reuse
     #   safety
-joblib==1.4.2
+joblib==1.5.3
     # via nltk
-keyring==25.6.0
+keyring==25.7.0
     # via twine
-license-expression==30.4.1
+librt==0.7.8
+    # via mypy
+license-expression==30.4.4
     # via reuse
-lxml==5.3.1
+lxml==6.0.2
     # via feedgen
-markdown==3.7
+markdown==3.10.1
     # via incorporeal-cms (pyproject.toml)
-markdown-it-py==3.0.0
+markdown-it-py==4.0.0
     # via rich
-markupsafe==3.0.2
+markupsafe==3.0.3
     # via jinja2
-marshmallow==3.26.1
+marshmallow==4.2.1
     # via safety
 mccabe==0.7.0
     # via flake8
 mdurl==0.1.2
     # via markdown-it-py
-more-itertools==10.6.0
+more-itertools==10.8.0
     # via
     #   jaraco-classes
     #   jaraco-functools
-mypy==1.15.0
+mypy==1.19.1
     # via incorporeal-cms (pyproject.toml)
-mypy-extensions==1.0.0
+mypy-extensions==1.1.0
     # via mypy
-nh3==0.2.21
+nh3==0.3.2
     # via readme-renderer
-nltk==3.9.1
+nltk==3.9.2
     # via safety
-packaging==24.2
+packaging==26.0
     # via
     #   build
     #   dparse
-    #   marshmallow
     #   pyproject-api
     #   pytest
     #   safety
@@ -161,65 +172,68 @@ packaging==24.2
     #   setuptools-scm
     #   tox
     #   twine
-pbr==6.1.1
-    # via stevedore
-pip-tools==7.4.1
+    #   wheel
+pathspec==1.0.4
+    # via mypy
+pip-tools==7.5.2
     # via incorporeal-cms (pyproject.toml)
-platformdirs==4.3.6
+platformdirs==4.5.1
     # via
     #   tox
     #   virtualenv
-pluggy==1.5.0
+pluggy==1.6.0
     # via
     #   pytest
+    #   pytest-cov
     #   tox
-psutil==6.1.1
-    # via safety
-pycodestyle==2.12.1
+pycodestyle==2.14.0
     # via flake8
-pycparser==2.22
+pycparser==3.0
     # via cffi
-pydantic==2.9.2
+pydantic==2.12.5
     # via
     #   safety
     #   safety-schemas
-pydantic-core==2.23.4
+pydantic-core==2.41.5
     # via pydantic
 pydocstyle==6.3.0
     # via flake8-docstrings
-pydot==3.0.4
+pydot==4.0.1
     # via incorporeal-cms (pyproject.toml)
-pyflakes==3.2.0
+pyflakes==3.4.0
     # via flake8
-pygments==2.19.1
+pygments==2.19.2
     # via
+    #   pytest
     #   readme-renderer
     #   rich
-pyparsing==3.2.1
+pyparsing==3.3.2
     # via pydot
-pyproject-api==1.9.0
+pyproject-api==1.10.0
     # via tox
 pyproject-hooks==1.2.0
     # via
     #   build
     #   pip-tools
-pytest==8.3.5
+pytest==9.0.2
     # via
     #   incorporeal-cms (pyproject.toml)
     #   pytest-cov
-pytest-cov==6.0.0
+pytest-cov==7.0.0
     # via incorporeal-cms (pyproject.toml)
 python-dateutil==2.9.0.post0
     # via feedgen
 python-debian==1.0.1
     # via reuse
-pyyaml==6.0.2
+python-magic==0.4.27
+    # via reuse
+pyyaml==6.0.3
     # via bandit
 readme-renderer==44.0
     # via twine
-regex==2024.11.6
+regex==2026.1.15
     # via nltk
-requests==2.32.3
+requests==2.32.5
     # via
     #   id
     #   requests-toolbelt
@@ -227,64 +241,72 @@ requests==2.32.3
     #   twine
 requests-toolbelt==1.0.0
     # via twine
-reuse==5.0.2
+reuse==6.2.0
     # via incorporeal-cms (pyproject.toml)
 rfc3986==2.0.0
     # via twine
-rich==13.9.4
+rich==14.3.1
     # via
     #   bandit
     #   twine
     #   typer
-ruamel-yaml==0.18.10
+ruamel-yaml==0.19.1
     # via
     #   safety
     #   safety-schemas
-ruamel-yaml-clib==0.2.12
-    # via ruamel-yaml
-safety==3.3.1
+safety==3.7.0
     # via incorporeal-cms (pyproject.toml)
-safety-schemas==0.0.11
+safety-schemas==0.0.16
     # via safety
-secretstorage==3.3.3
+secretstorage==3.5.0
     # via keyring
-setuptools-scm==8.2.0
+setuptools-scm==9.2.2
     # via incorporeal-cms (pyproject.toml)
 shellingham==1.5.4
     # via typer
 six==1.17.0
     # via python-dateutil
-snowballstemmer==2.2.0
+snowballstemmer==3.0.1
     # via pydocstyle
-stevedore==5.4.1
+soupsieve==2.8.3
+    # via beautifulsoup4
+stevedore==5.6.0
     # via bandit
-termcolor==2.5.0
+tenacity==9.1.2
+    # via safety
+termcolor==3.3.0
     # via incorporeal-cms (pyproject.toml)
-tomlkit==0.13.2
-    # via reuse
-tox==4.24.2
+tomlkit==0.14.0
+    # via
+    #   reuse
+    #   safety
+tox==4.34.1
     # via incorporeal-cms (pyproject.toml)
 tqdm==4.67.1
     # via nltk
-twine==6.1.0
+twine==6.2.0
     # via incorporeal-cms (pyproject.toml)
-typer==0.15.2
+typer==0.21.1
     # via safety
-typing-extensions==4.12.2
+typing-extensions==4.15.0
     # via
+    #   beautifulsoup4
     #   mypy
     #   pydantic
     #   pydantic-core
     #   safety
     #   safety-schemas
     #   typer
-urllib3==2.3.0
+    #   typing-inspection
+typing-inspection==0.4.2
+    # via pydantic
+urllib3==2.6.3
     # via
     #   requests
     #   twine
-virtualenv==20.29.3
+virtualenv==20.36.1
     # via tox
-wheel==0.45.1
+wheel==0.46.3
     # via pip-tools
 
 # The following packages are considered to be unsafe in a requirements file:

requirements/requirements.txt

@@ -1,22 +1,28 @@
 #
-# This file is autogenerated by pip-compile with Python 3.12
+# This file is autogenerated by pip-compile with Python 3.13
 # by the following command:
 #
 #    pip-compile --output-file=requirements/requirements.txt
 #
+beautifulsoup4==4.14.3
+    # via incorporeal-cms (pyproject.toml)
 feedgen==1.0.0
     # via incorporeal-cms (pyproject.toml)
 jinja2==3.1.6
     # via incorporeal-cms (pyproject.toml)
-lxml==5.3.1
+lxml==6.0.2
     # via feedgen
-markdown==3.7
+markdown==3.10.1
     # via incorporeal-cms (pyproject.toml)
-markupsafe==3.0.2
+markupsafe==3.0.3
     # via jinja2
 python-dateutil==2.9.0.post0
     # via feedgen
 six==1.17.0
     # via python-dateutil
-termcolor==2.5.0
+soupsieve==2.8.3
+    # via beautifulsoup4
+termcolor==3.3.0
     # via incorporeal-cms (pyproject.toml)
+typing-extensions==4.15.0
+    # via beautifulsoup4

tests/instance/broken/redirect.md

@@ -1 +0,0 @@
-Redirect:           http://www.google.com/

tests/instance/pages/file-with-index.md-link.md

@@ -0,0 +1,6 @@
+[Cool](cool/index.md)
+[Anchored Cool](cool/index.md#anchor)
+[This Index](index.md)
+[Anchored This Index](index.md#anchor)
+[Parent](../index.md)
+[Anchored Parent](../index.md#anchor)

tests/instance/pages/file-with-md-link.md

@@ -0,0 +1,4 @@
+[Foo](foo.md)
+[Anchored Foo](foo.md#anchor)
+[Sub Foo](sub/foo.md)
+[Anchored Sub Foo](sub/foo.md#anchor)

tests/instance/pages/no-title-or-h1.md

@@ -0,0 +1 @@
+there's just some words here but no title tag or h1

tests/instance/pages/no-title-subdir/index.md

@@ -0,0 +1 @@
+there's just some words here but no title tag or h1

tests/instance/pages/no-title-subdir/no-title-or-h1.md

@@ -0,0 +1 @@
+there's just some words here but no title tag or h1

tests/instance/pages/rambling.md

@@ -0,0 +1,6 @@
+# rambling test for inferred description
+
+this is a long string of text where
+I am typing a lot over multiple lines
+
+this second paragraph shouldn't be in the metadata

tests/test_markdown.py

@@ -10,8 +10,7 @@ import pytest
 
 from incorporealcms import init_instance
 from incorporealcms.markdown import (generate_parent_navs, handle_markdown_file_path,
-                                     instance_resource_path_to_request_path, parse_md,
-                                     request_path_to_breadcrumb_display)
+                                     instance_resource_path_to_request_path, parse_md)
 
 HERE = os.path.dirname(os.path.abspath(__file__))
 INSTANCE_DIR = os.path.join(HERE, 'instance')
@@ -26,14 +25,21 @@ def test_generate_page_navs_index():
     assert generate_parent_navs('index.md', PAGES_DIR) == [('example.org', '/')]
 
 
+def test_generate_page_navs_title_from_h1():
+    """Test that the index page has navs to the root (itself)."""
+    assert generate_parent_navs('no-title.md', PAGES_DIR) == [('example.org', '/'),
+                                                              ('this page doesn\'t have a title!', '/no-title')]
+
+
 def test_generate_page_navs_subdir_index():
     """Test that dir pages have navs to the root and themselves."""
-    assert generate_parent_navs('subdir/index.md', PAGES_DIR) == [('example.org', '/'), ('subdir', '/subdir/')]
+    assert generate_parent_navs('subdir/index.md', PAGES_DIR) == [('example.org', '/'), ('another page', '/subdir/')]
 
 
 def test_generate_page_navs_subdir_real_page():
     """Test that real pages have navs to the root, their parent, and themselves."""
-    assert generate_parent_navs('subdir/page.md', PAGES_DIR) == [('example.org', '/'), ('subdir', '/subdir/'),
+    assert generate_parent_navs('subdir/page.md', PAGES_DIR) == [('example.org', '/'),
+                                                                 ('another page', '/subdir/'),
                                                                  ('Page', '/subdir/page')]
 
 
@@ -42,7 +48,7 @@ def test_generate_page_navs_subdir_with_title_parsing_real_page():
     assert generate_parent_navs('subdir-with-title/page.md', PAGES_DIR) == [
         ('example.org', '/'),
         ('SUB!', '/subdir-with-title/'),
-        ('page', '/subdir-with-title/page')
+        ('/page', '/subdir-with-title/page')
     ]
 
 
@@ -51,7 +57,7 @@ def test_generate_page_navs_subdir_with_no_index():
     assert generate_parent_navs('no-index-dir/page.md', PAGES_DIR) == [
         ('example.org', '/'),
         ('/no-index-dir/', '/no-index-dir/'),
-        ('page', '/no-index-dir/page')
+        ('/page', '/no-index-dir/page')
     ]
 
 
@@ -97,12 +103,6 @@ def test_render_with_default_style_override():
                 in handle_markdown_file_path('index.md', PAGES_DIR)
 
 
-def test_redirects_error_unsupported():
-    """Test that we throw a warning about the barely-used Markdown redirect tag, which we can't support via SSG."""
-    with pytest.raises(NotImplementedError):
-        handle_markdown_file_path('redirect.md', os.path.join(INSTANCE_DIR, 'broken'))
-
-
 def test_instance_resource_path_to_request_path_on_index():
     """Test index.md -> /."""
     assert instance_resource_path_to_request_path('index.md') == '/'
@@ -123,43 +123,103 @@ def test_instance_resource_path_to_request_path_on_subdir_and_page():
     assert instance_resource_path_to_request_path('subdir/page.md') == '/subdir/page'
 
 
-def test_request_path_to_breadcrumb_display_patterns():
-    """Test various conversions from request path to leaf nodes for display in the breadcrumbs."""
-    assert request_path_to_breadcrumb_display('/foo') == 'foo'
-    assert request_path_to_breadcrumb_display('/foo/') == 'foo'
-    assert request_path_to_breadcrumb_display('/foo/bar') == 'bar'
-    assert request_path_to_breadcrumb_display('/foo/bar/') == 'bar'
-    assert request_path_to_breadcrumb_display('/') == ''
-
-
 def test_parse_md_metadata():
     """Test the direct results of parsing a markdown file."""
-    content, md, page_name, page_title, mtime = parse_md(os.path.join(PAGES_DIR, 'more-metadata.md'), PAGES_DIR)
+    content, md, page_name, page_title, page_desc, mtime = parse_md(
+        os.path.join(PAGES_DIR, 'more-metadata.md'),
+        PAGES_DIR
+    )
     assert page_name == 'title for the page'
     assert page_title == 'title for the page - example.org'
+    assert page_desc == 'description of this page made even longer'
 
 
 def test_parse_md_metadata_forced_no_title():
     """Test the direct results of parsing a markdown file."""
-    content, md, page_name, page_title, mtime = parse_md(os.path.join(PAGES_DIR, 'forced-no-title.md'), PAGES_DIR)
+    content, md, page_name, page_title, _, mtime = parse_md(os.path.join(PAGES_DIR, 'forced-no-title.md'), PAGES_DIR)
     assert page_name == ''
     assert page_title == 'example.org'
 
 
-def test_parse_md_metadata_no_title_so_path():
+def test_parse_md_metadata_no_title_so_h1():
     """Test the direct results of parsing a markdown file."""
-    content, md, page_name, page_title, mtime = parse_md(os.path.join(PAGES_DIR, 'subdir/index.md'), PAGES_DIR)
-    assert page_name == '/subdir/'
-    assert page_title == '/subdir/ - example.org'
+    content, md, page_name, page_title, _, mtime = parse_md(os.path.join(PAGES_DIR, 'subdir/index.md'), PAGES_DIR)
+    assert page_name == 'another page'
+    assert page_title == 'another page - example.org'
+
+
+def test_parse_md_metadata_no_title_or_h1_so_path():
+    """Test the direct results of parsing a markdown file."""
+    content, md, page_name, page_title, _, mtime = parse_md(os.path.join(PAGES_DIR, 'no-title-or-h1.md'), PAGES_DIR)
+    assert page_name == '/no-title-or-h1'
+    assert page_title == '/no-title-or-h1 - example.org'
+
+
+def test_parse_md_metadata_no_title_or_h1_so_path_dir():
+    """Test the direct results of parsing a markdown file."""
+    content, md, page_name, page_title, _, mtime = parse_md(os.path.join(PAGES_DIR, 'no-title-subdir/index.md'),
+                                                            PAGES_DIR)
+    assert page_name == '/no-title-subdir/'
+    assert page_title == '/no-title-subdir/ - example.org'
+
+
+def test_parse_md_metadata_no_title_or_h1_so_path_dir_file():
+    """Test the direct results of parsing a markdown file."""
+    content, md, page_name, page_title, _, mtime = parse_md(os.path.join(PAGES_DIR,
+                                                                         'no-title-subdir/no-title-or-h1.md'),
+                                                            PAGES_DIR)
+    assert page_name == '/no-title-subdir/no-title-or-h1'
+    assert page_title == '/no-title-subdir/no-title-or-h1 - example.org'
+
+
+def test_parse_md_derive_description_from_p():
+    """Test that we can get a description from the first paragraph in the file."""
+    content, md, page_name, page_title, page_desc, mtime = parse_md(
+        os.path.join(PAGES_DIR, 'rambling.md'),
+        PAGES_DIR
+    )
+    assert page_desc == 'this is a long string of text where I am typing a lot over multiple lines'
 
 
 def test_parse_md_no_file():
     """Test the direct results of parsing a markdown file."""
     with pytest.raises(FileNotFoundError):
-        content, md, page_name, page_title, mtime = parse_md(os.path.join(PAGES_DIR, 'nope.md'), PAGES_DIR)
+        content, md, page_name, page_title, _, mtime = parse_md(os.path.join(PAGES_DIR, 'nope.md'), PAGES_DIR)
 
 
 def test_parse_md_bad_file():
     """Test the direct results of parsing a markdown file."""
     with pytest.raises(ValueError):
-        content, md, page_name, page_title, mtime = parse_md(os.path.join(PAGES_DIR, 'actually-a-png.md'), PAGES_DIR)
+        content, md, page_name, page_title, _, mtime = parse_md(os.path.join(PAGES_DIR, 'actually-a-png.md'), PAGES_DIR)
+
+
+def test_md_extension_in_source_link_is_stripped():
+    """Test that if a foo.md file link is specified in the Markdown, it is foo in the HTML."""
+    content, _, _, _, _, _ = parse_md(os.path.join(PAGES_DIR, 'file-with-md-link.md'), PAGES_DIR)
+    assert '<a href="foo">Foo</a>' in content
+    assert '<a href="foo#anchor">Anchored Foo</a>' in content
+    assert '<a href="sub/foo">Sub Foo</a>' in content
+    assert '<a href="sub/foo#anchor">Anchored Sub Foo</a>' in content
+
+
+def test_index_in_source_link_is_stripped():
+    """Test that if a index.md file link is specified in the Markdown, it is just the dir in the HTML."""
+    content, _, _, _, _, _ = parse_md(os.path.join(PAGES_DIR, 'file-with-index.md-link.md'), PAGES_DIR)
+    assert '<a href="cool/">Cool</a>' in content
+    assert '<a href="cool/#anchor">Anchored Cool</a>' in content
+    assert '<a href=".">This Index</a>' in content
+    assert '<a href=".#anchor">Anchored This Index</a>' in content
+    assert '<a href="../">Parent</a>' in content
+    assert '<a href="../#anchor">Anchored Parent</a>' in content
+
+
+def test_license_link():
+    """Test that the config's license HTML is displayed in the footer."""
+    with patch('incorporealcms.Config.LICENSE',
+               '<a href="https://creativecommons.org/licenses/by-sa/4.0/">CC BY-SA 4.0</a>', create=True):
+        assert 'Available via <a href="https://creativecommons.org/licenses/by-sa/4.0/">CC BY-SA 4.0</a>.'\
+            in handle_markdown_file_path('index.md', PAGES_DIR)
+
+    # default, no config
+    assert '<a href="https://creativecommons.org/licenses/by-sa/4.0/">CC BY-SA 4.0</a>'\
+        not in handle_markdown_file_path('index.md', PAGES_DIR)

tests/test_ssg.py

@@ -129,3 +129,26 @@ def test_build_in_destination_ignores_dot_files():
         generator.build_in_destination(os.path.join(src_dir, 'pages'), tmpdir)
 
         assert not os.path.exists(os.path.join(tmpdir, '.ignored-file.md'))
+
+
+def test_build():
+    """Test that the high level build can work against two directories."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        src_dir = os.path.join(HERE, 'instance')
+        generator = ssg.StaticSiteGenerator(src_dir, tmpdir)
+        generator.build()
+
+        assert os.path.exists(os.path.join(tmpdir, 'index.md'))
+        assert os.path.exists(os.path.join(tmpdir, 'index.html'))
+        assert os.path.exists(os.path.join(tmpdir, 'subdir', 'index.md'))
+        assert os.path.exists(os.path.join(tmpdir, 'subdir', 'index.html'))
+        assert os.path.exists(os.path.join(tmpdir, 'symlink-to-subdir'))
+        assert os.path.isdir(os.path.join(tmpdir, 'symlink-to-subdir'))
+        assert os.path.islink(os.path.join(tmpdir, 'symlink-to-subdir'))
+        assert os.path.exists(os.path.join(tmpdir, 'media'))
+        assert os.path.isdir(os.path.join(tmpdir, 'media'))
+        assert not os.path.exists(os.path.join(tmpdir, '.ignored-file.md'))
+        assert os.path.exists(os.path.join(tmpdir, 'feed'))
+        assert os.path.isdir(os.path.join(tmpdir, 'feed'))
+        assert os.path.exists(os.path.join(tmpdir, 'feed/atom'))
+        assert os.path.exists(os.path.join(tmpdir, 'feed/rss'))

tox.ini

@@ -5,7 +5,7 @@
 
 [tox]
 isolated_build = true
-envlist = begin,py39,py310,py311,py312,coverage,security,lint,reuse
+envlist = begin,py310,py311,py312,py313,coverage,security,lint,reuse
 
 [testenv]
 allow_externals = pytest, coverage
@@ -21,11 +21,6 @@ deps = setuptools
 skip_install = true
 commands = coverage erase
 
-[testenv:py39]
-# run pytest with coverage
-commands =
-    pytest --cov-append --cov={envsitepackagesdir}/incorporealcms/ --cov-branch
-
 [testenv:py310]
 # run pytest with coverage
 commands =
@@ -41,6 +36,11 @@ commands =
 commands =
     pytest --cov-append --cov={envsitepackagesdir}/incorporealcms/ --cov-branch
 
+[testenv:py313]
+# run pytest with coverage
+commands =
+    pytest --cov-append --cov={envsitepackagesdir}/incorporealcms/ --cov-branch
+
 [testenv:coverage]
 # report on coverage runs from above
 skip_install = true