lv2specgen: Fix offline XHTML validation and make it optional

4 files changed, 293 insertions, 29 deletions

diff --git a/lv2specgen/DTD/xhtml-rdfa-1.dtd b/lv2specgen/DTD/xhtml-rdfa-1.dtd
index 53890bb..0490b09 100644
--- a/lv2specgen/DTD/xhtml-rdfa-1.dtd
+++ b/lv2specgen/DTD/xhtml-rdfa-1.dtd
@@ -218,7 +218,7 @@
 <![%xhtml-ruby.module;[
 <!ENTITY % xhtml-ruby.mod
      PUBLIC "-//W3C//ELEMENTS XHTML Ruby 1.0//EN"
-            "http://www.w3.org/TR/ruby/xhtml-ruby-1.mod" >
+            "xhtml-ruby-1.mod" >
 %xhtml-ruby.mod;]]>
 
 <!-- Presentation Module  ........................................ -->
diff --git a/lv2specgen/DTD/xhtml-ruby-1.mod b/lv2specgen/DTD/xhtml-ruby-1.mod
new file mode 100644
index 0000000..978da8d
--- /dev/null
+++ b/lv2specgen/DTD/xhtml-ruby-1.mod
@@ -0,0 +1,242 @@
+<!-- ...................................................................... -->
+<!-- XHTML Ruby Module .................................................... -->
+<!-- file: xhtml-ruby-1.mod
+
+     This is XHTML, a reformulation of HTML as a modular XML application.
+     Copyright 1999-2001 W3C (MIT, INRIA, Keio), All Rights Reserved.
+     Revision: $Id: xhtml-ruby-1.mod,v 1.1 2008/06/21 19:42:10 smccarro Exp $
+
+     This module is based on the W3C Ruby Annotation Specification:
+
+        http://www.w3.org/TR/ruby
+
+     This DTD module is identified by the PUBLIC and SYSTEM identifiers:
+
+       PUBLIC "-//W3C//ELEMENTS XHTML Ruby 1.0//EN"
+       SYSTEM "http://www.w3.org/TR/ruby/xhtml-ruby-1.mod"
+
+     ...................................................................... -->
+
+<!-- Ruby Elements
+
+        ruby, rbc, rtc, rb, rt, rp
+
+     This module declares the elements and their attributes used to
+     support ruby annotation markup.
+-->
+
+<!-- declare qualified element type names:
+-->
+<!ENTITY % ruby.qname  "ruby" >
+<!ENTITY % rbc.qname  "rbc" >
+<!ENTITY % rtc.qname  "rtc" >
+<!ENTITY % rb.qname  "rb" >
+<!ENTITY % rt.qname  "rt" >
+<!ENTITY % rp.qname  "rp" >
+
+<!-- rp fallback is included by default.
+-->
+<!ENTITY % Ruby.fallback "INCLUDE" >
+<!ENTITY % Ruby.fallback.mandatory "IGNORE" >
+
+<!-- Complex ruby is included by default; it may be
+     overridden by other modules to ignore it.
+-->
+<!ENTITY % Ruby.complex "INCLUDE" >
+
+<!-- Fragments for the content model of the ruby element -->
+<![%Ruby.fallback;[
+<![%Ruby.fallback.mandatory;[
+<!ENTITY % Ruby.content.simple
+     "( %rb.qname;, %rp.qname;, %rt.qname;, %rp.qname; )"
+>
+]]>
+<!ENTITY % Ruby.content.simple
+     "( %rb.qname;, ( %rt.qname; | ( %rp.qname;, %rt.qname;, %rp.qname; ) ) )"
+>
+]]>
+<!ENTITY % Ruby.content.simple "( %rb.qname;, %rt.qname; )" >
+
+<![%Ruby.complex;[
+<!ENTITY % Ruby.content.complex
+     "| ( %rbc.qname;, %rtc.qname;, %rtc.qname;? )"
+>
+]]>
+<!ENTITY % Ruby.content.complex "" >
+
+<!-- Content models of the rb and the rt elements are intended to
+     allow other inline-level elements of its parent markup language,
+     but it should not include ruby descendent elements. The following
+     parameter entity %NoRuby.content; can be used to redefine
+     those content models with minimum effort.  It's defined as
+     '( #PCDATA )' by default.
+-->
+<!ENTITY % NoRuby.content "( #PCDATA )" >
+
+<!-- one or more digits (NUMBER) -->
+<!ENTITY % Number.datatype "CDATA" >
+
+<!-- ruby element ...................................... -->
+
+<!ENTITY % ruby.element  "INCLUDE" >
+<![%ruby.element;[
+<!ENTITY % ruby.content
+     "( %Ruby.content.simple; %Ruby.content.complex; )"
+>
+<!ELEMENT %ruby.qname;  %ruby.content; >
+<!-- end of ruby.element -->]]>
+
+<![%Ruby.complex;[
+<!-- rbc (ruby base component) element ................. -->
+
+<!ENTITY % rbc.element  "INCLUDE" >
+<![%rbc.element;[
+<!ENTITY % rbc.content
+     "(%rb.qname;)+"
+>
+<!ELEMENT %rbc.qname;  %rbc.content; >
+<!-- end of rbc.element -->]]>
+
+<!-- rtc (ruby text component) element ................. -->
+
+<!ENTITY % rtc.element  "INCLUDE" >
+<![%rtc.element;[
+<!ENTITY % rtc.content
+     "(%rt.qname;)+"
+>
+<!ELEMENT %rtc.qname;  %rtc.content; >
+<!-- end of rtc.element -->]]>
+]]>
+
+<!-- rb (ruby base) element ............................ -->
+
+<!ENTITY % rb.element  "INCLUDE" >
+<![%rb.element;[
+<!-- %rb.content; uses %NoRuby.content; as its content model,
+     which is '( #PCDATA )' by default. It may be overridden
+     by other modules to allow other inline-level elements
+     of its parent markup language, but it should not include
+     ruby descendent elements.
+-->
+<!ENTITY % rb.content "%NoRuby.content;" >
+<!ELEMENT %rb.qname;  %rb.content; >
+<!-- end of rb.element -->]]>
+
+<!-- rt (ruby text) element ............................ -->
+
+<!ENTITY % rt.element  "INCLUDE" >
+<![%rt.element;[
+<!-- %rt.content; uses %NoRuby.content; as its content model,
+     which is '( #PCDATA )' by default. It may be overridden
+     by other modules to allow other inline-level elements
+     of its parent markup language, but it should not include
+     ruby descendent elements.
+-->
+<!ENTITY % rt.content "%NoRuby.content;" >
+
+<!ELEMENT %rt.qname;  %rt.content; >
+<!-- end of rt.element -->]]>
+
+<!-- rbspan attribute is used for complex ruby only ...... -->
+<![%Ruby.complex;[
+<!ENTITY % rt.attlist  "INCLUDE" >
+<![%rt.attlist;[
+<!ATTLIST %rt.qname;
+      rbspan         %Number.datatype;      "1"
+>
+<!-- end of rt.attlist -->]]>
+]]>
+
+<!-- rp (ruby parenthesis) element ..................... -->
+
+<![%Ruby.fallback;[
+<!ENTITY % rp.element  "INCLUDE" >
+<![%rp.element;[
+<!ENTITY % rp.content
+     "( #PCDATA )"
+>
+<!ELEMENT %rp.qname;  %rp.content; >
+<!-- end of rp.element -->]]>
+]]>
+
+<!-- Ruby Common Attributes
+
+     The following optional ATTLIST declarations provide an easy way
+     to define common attributes for ruby elements.  These declarations
+     are ignored by default.
+
+     Ruby elements are intended to have common attributes of its
+     parent markup language.  For example, if a markup language defines
+     common attributes as a parameter entity %attrs;, you may add
+     those attributes by just declaring the following parameter entities
+
+         <!ENTITY % Ruby.common.attlists  "INCLUDE" >
+         <!ENTITY % Ruby.common.attrib  "%attrs;" >
+
+     before including the Ruby module.
+-->
+
+<!ENTITY % Ruby.common.attlists  "IGNORE" >
+<![%Ruby.common.attlists;[
+<!ENTITY % Ruby.common.attrib  "" >
+
+<!-- common attributes for ruby ........................ -->
+
+<!ENTITY % Ruby.common.attlist  "INCLUDE" >
+<![%Ruby.common.attlist;[
+<!ATTLIST %ruby.qname;
+      %Ruby.common.attrib;
+>
+<!-- end of Ruby.common.attlist -->]]>
+
+<![%Ruby.complex;[
+<!-- common attributes for rbc ......................... -->
+
+<!ENTITY % Rbc.common.attlist  "INCLUDE" >
+<![%Rbc.common.attlist;[
+<!ATTLIST %rbc.qname;
+      %Ruby.common.attrib;
+>
+<!-- end of Rbc.common.attlist -->]]>
+
+<!-- common attributes for rtc ......................... -->
+
+<!ENTITY % Rtc.common.attlist  "INCLUDE" >
+<![%Rtc.common.attlist;[
+<!ATTLIST %rtc.qname;
+      %Ruby.common.attrib;
+>
+<!-- end of Rtc.common.attlist -->]]>
+]]>
+
+<!-- common attributes for rb .......................... -->
+
+<!ENTITY % Rb.common.attlist  "INCLUDE" >
+<![%Rb.common.attlist;[
+<!ATTLIST %rb.qname;
+      %Ruby.common.attrib;
+>
+<!-- end of Rb.common.attlist -->]]>
+
+<!-- common attributes for rt .......................... -->
+
+<!ENTITY % Rt.common.attlist  "INCLUDE" >
+<![%Rt.common.attlist;[
+<!ATTLIST %rt.qname;
+      %Ruby.common.attrib;
+>
+<!-- end of Rt.common.attlist -->]]>
+
+<![%Ruby.fallback;[
+<!-- common attributes for rp .......................... -->
+
+<!ENTITY % Rp.common.attlist  "INCLUDE" >
+<![%Rp.common.attlist;[
+<!ATTLIST %rp.qname;
+      %Ruby.common.attrib;
+>
+<!-- end of Rp.common.attlist -->]]>
+]]>
+]]>
+
+<!-- end of xhtml-ruby-1.mod -->
diff --git a/lv2specgen/lv2specgen.py b/lv2specgen/lv2specgen.py
index 7927261..3eee372 100755
--- a/lv2specgen/lv2specgen.py
+++ b/lv2specgen/lv2specgen.py
@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 #
-# Copyright 2009-2022 David Robillard <d@drobilla.net>
+# Copyright 2009-2026 David Robillard <d@drobilla.net>
 # Copyright 2003-2008 Christopher Schmidt <crschmidt@crschmidt.net>
 # Copyright 2005-2008 Uldis Bojars <uldis.bojars@deri.org>
 # Copyright 2007-2008 Sergio Fernández <sergio.fernandez@fundacionctic.org>
@@ -18,9 +18,11 @@
 # pylint: disable=global-statement
 # pylint: disable=global-variable-not-assigned
 # pylint: disable=invalid-name
+# pylint: disable=missing-class-docstring
 # pylint: disable=missing-function-docstring
 # pylint: disable=no-member
 # pylint: disable=redefined-outer-name
+# pylint: disable=too-few-public-methods
 # pylint: disable=too-many-arguments
 # pylint: disable=too-many-boolean-expressions
 # pylint: disable=too-many-branches
@@ -43,7 +45,7 @@ import xml.sax.saxutils
 import markdown
 import markdown.extensions
 
-__date__ = "2011-10-26"
+__date__ = "2026-02-07"
 __version__ = __date__.replace("-", ".")
 __authors__ = """
 Christopher Schmidt,
@@ -104,6 +106,12 @@ doap = rdflib.Namespace("http://usefulinc.com/ns/doap#")
 foaf = rdflib.Namespace("http://xmlns.com/foaf/0.1/")
 
 
+class DTDResolver(etree.Resolver):
+    def resolve(self, url, _pubid, context):
+        path = os.path.join(specgendir, url)
+        return self.resolve_filename(path, context)
+
+
 def findStatements(model, s, p, o):
     return model.triples([s, p, o])
 
@@ -1160,6 +1168,7 @@ def specgen(
     tags,
     opts,
     instances=False,
+    validate=False,
 ):
     """The meat and potatoes: Everything starts here."""
 
@@ -1346,17 +1355,22 @@ def specgen(
     build_date = datetime.datetime.fromtimestamp(now, datetime.timezone.utc)
     template = template.replace("@DATE@", build_date.strftime("%F"))
     template = template.replace("@TIME@", build_date.strftime("%F %H:%M UTC"))
+    if not validate:
+        return template
 
     # Validate complete output page
     oldcwd = os.getcwd()
     try:
         os.chdir(specgendir)
+        parser = etree.XMLParser(dtd_validation=True, no_network=True)
+        parser.resolvers.add(DTDResolver())
+
         etree.fromstring(
             template.replace(
                 '"http://www.w3.org/MarkUp/DTD/xhtml-rdfa-1.dtd"',
                 '"DTD/xhtml-rdfa-1.dtd"',
             ).encode("utf-8"),
-            etree.XMLParser(dtd_validation=True, no_network=True),
+            parser,
         )
     except Exception as e:
         sys.stderr.write(
@@ -1429,31 +1443,31 @@ def _data_dirs():
 
 
 if __name__ == "__main__":
-    data_dir = None
-    for d in _data_dirs():
-        path = os.path.join(d, "lv2specgen")
-        if (
-            os.path.exists(os.path.join(path, "template.html"))
-            and os.path.exists(os.path.join(path, "style.css"))
-            and os.path.exists(os.path.join(path, "pygments.css"))
-        ):
-            data_dir = path
-            break
-
-    if data_dir:
-        # Use installed files
-        specgendir = data_dir
-        default_template_path = os.path.join(data_dir, "template.html")
-        default_style_dir = data_dir
+    script_path = os.path.realpath(__file__)
+    script_dir = os.path.dirname(os.path.realpath(__file__))
+    if os.path.exists(os.path.join(script_dir, "template.html")):
+        # Run from source repository
+        specgendir = script_dir
+        lv2_source_root = os.path.dirname(script_dir)
+        default_template_path = os.path.join(script_dir, "template.html")
+        default_style_dir = os.path.join(lv2_source_root, "doc", "style")
     else:
-        script_path = os.path.realpath(__file__)
-        script_dir = os.path.dirname(os.path.realpath(__file__))
-        if os.path.exists(os.path.join(script_dir, "template.html")):
-            # Run from source repository
-            specgendir = script_dir
-            lv2_source_root = os.path.dirname(script_dir)
-            default_template_path = os.path.join(script_dir, "template.html")
-            default_style_dir = os.path.join(lv2_source_root, "doc", "style")
+        data_dir = None
+        for d in _data_dirs():
+            path = os.path.join(d, "lv2specgen")
+            files_exist = all(
+                os.path.exists(os.path.join(path, name))
+                for name in ["template.html", "style.css", "pygments.css"]
+            )
+            if files_exist:
+                data_dir = path
+                break
+
+        if data_dir:
+            # Use installed files
+            specgendir = data_dir
+            default_template_path = os.path.join(data_dir, "template.html")
+            default_style_dir = data_dir
         else:
             sys.stderr.write("error: Unable to find lv2specgen data\n")
             sys.exit(-2)
@@ -1529,6 +1543,12 @@ if __name__ == "__main__":
         dest="copy_style",
         help="Copy style from template directory to output directory",
     )
+    opt.add_option(
+        "--validate",
+        action="store_true",
+        dest="validate",
+        help="Validate against local XML DTDs",
+    )
 
     (options, args) = opt.parse_args()
     opts = vars(options)
@@ -1564,6 +1584,7 @@ if __name__ == "__main__":
         tags,
         opts,
         instances=True,
+        validate=opts["validate"],
     )
 
     # Save to HTML output file
diff --git a/lv2specgen/meson.build b/lv2specgen/meson.build
index bc3a616..55cdecd 100644
--- a/lv2specgen/meson.build
+++ b/lv2specgen/meson.build
@@ -1,4 +1,4 @@
-# Copyright 2022-2025 David Robillard <d@drobilla.net>
+# Copyright 2022-2026 David Robillard <d@drobilla.net>
 # SPDX-License-Identifier: 0BSD OR ISC
 
 lv2specgen_py = files('lv2specgen.py')
@@ -12,6 +12,7 @@ lv2specgen_command_prefix = [
   '--list-page=' + lv2_list_page,
   '--style-dir=' + lv2_source_root / 'doc' / 'style',
   '--template', files('template.html'),
+  '--validate',
 ]
 
 if is_variable('lv2_tags')