hyperref and hyperxmp metadata improvements

MANIFEST

@@ -984,6 +984,9 @@ t/complex/hyperchars.xml
 t/complex/hypertest.pdf
 t/complex/hypertest.tex
 t/complex/hypertest.xml
+t/complex/hyperxmp.pdf
+t/complex/hyperxmp.tex
+t/complex/hyperxmp.xml
 t/complex/labelled.pdf
 t/complex/labelled.tex
 t/complex/labelled.xml

lib/LaTeXML/Engine/Base_Schema.pool.ltxml

@@ -81,6 +81,7 @@ RequireResource('LaTeXML.css');
     "ma"      => "http://www.w3.org/ns/ma-ont#",
     "og"      => "http://ogp.me/ns#",
     "owl"     => "http://www.w3.org/2002/07/owl#",
+    "prism"   => "http://prismstandard.org/namespaces/basic/3.0/",
     "rdf"     => "http://www.w3.org/1999/02/22-rdf-syntax-ns#",
     "rdfa"    => "http://www.w3.org/ns/rdfa#",
     "rdfs"    => "http://www.w3.org/2000/01/rdf-schema#",

lib/LaTeXML/Package/hyperref.sty.ltxml

@@ -86,21 +86,19 @@ foreach my $option (    # 3.1 General Options
   DeclareOption($option, undef); }
 
 # \hypersetup{keyvals} configures various parameters,
-# for each pdf keyword, provide [property,(content|resource),datatype]
-our %pdfkey_property = (
-  baseurl     => '',                                 # xmp:BaseURL ??
-  pdfauthor   => ['dcterms:creator',  'content'],
-  pdfkeywords => ['dcterms:subject',  'content'],    # & pdf:Keywords
-  pdflang     => ['dcterms:language', 'content'],
-  pdfproducer => '',                                 # pdf:Producer & xmp:CreatorTool
-  pdfsubject  => ['dcterms:subject', 'content'],
-  pdftitle    => ['dcterms:title',   'content'],
-  # Include hyperxmp's keywords, as well.
-  pdfauthortitle   => '',                                # photoshop:AuthorsPosition
-  pdfcaptionwriter => '',                                # photoshop:CaptionWriter !?!?!?
-  pdfcopyright     => ['dcterms:rights', 'content'],     # & xmpRights:Marked
-  pdflicenseurl    => ['cc:licence',     'resource'],    # xmpRights:WebStatement
-  pdfmetalang      => '',                                # dcterms:language ??
+# for each pdf keyword, provide [property,(content|resource),datatype,langsupport]
+# %pdfkey_property may have already been populated by hyperxmp
+our %pdfkey_property = (%pdfkey_property,
+  baseurl         => '',                                 # xmp:BaseURL ??
+  pdfauthor       => ['dcterms:creator', 'content'],
+  pdfcreationdate => '',                                 # xmp:CreateDate
+  pdfkeywords     => ['dcterms:subject',  'content'],    # & pdf:Keywords
+  pdflang         => ['dcterms:language', 'content'],
+  pdfmoddate      => '',                                 # xmp:ModifyDate
+  pdfproducer     => '',                                 # pdf:Producer & xmp:CreatorTool
+  pdfsubject      => ['dcterms:description', 'content'],
+  pdftitle        => ['dcterms:title',       'content'],
+  pdftrapped      => '',                                 # pdf:Trapped
 );
 # date=>dcterms:date xmp:CreateDate xmp:ModifyDate xmp:MetadataDate ?
 # document identifier => xmlMM:DocumentID
@@ -126,21 +124,24 @@ DefPrimitive('\hypersetup RequiredKeyVals:Hyp', sub {
     my @pairs = $kv->getPairs;
     while (@pairs) {
       my ($key, $value) = (shift(@pairs), shift(@pairs));
-      hyperref_setoption($key, Digest($value)); }
+      hyperref_setoption($key, Expand($value)); }
     return; });
 
 PushValue('@at@end@document', T_CS('\@add@PDF@RDFa@triples'));
 
 DefConstructor('\@add@PDF@RDFa@triples', sub {
     my ($document, $xproperty, $content) = @_;
     if (my $root = $document->getDocument->documentElement) {
+      my $metalang = LookupMapping('Hyperref_options', 'pdfmetalang') // LookupMapping('Hyperref_options', 'pdflang');
       foreach my $key (LookupMappingKeys('Hyperref_options')) {
         if (my $entry = ($pdfkey_property{$key})) {
-          my ($property, $object, $datatype) = @$entry;
-          my $value = LookupMapping('Hyperref_options', $key);
-          my $node  = $document->openElementAt($root, 'ltx:rdf',
-            property => $property, $object => $value,
-            ($datatype ? (datatype => $datatype) : ()));
+          my ($property, $object, $datatype, $langsupport) = @$entry;
+          my $value = ToString(LookupMapping('Hyperref_options', $key));
+          my ($lang, $localizedValue) = $value =~ m/^\[([^]]*)\](.*)/;
+          my $node = $document->openElementAt($root, 'ltx:rdf',
+            property => $property, $object => $langsupport ? $localizedValue // $value : $value,
+            ($langsupport && ($lang || $metalang) ? ('xml:lang' => $lang // $metalang) : ()),
+            ($datatype                            ? (datatype   => $datatype)          : ()));
           # Must do directly; $document->setAttribute omits empty attributes
           $node->setAttribute(about => '');
           $document->closeElementAt($node); } } } });

lib/LaTeXML/Package/hyperxmp.sty.ltxml

@@ -17,7 +17,63 @@ use LaTeXML::Package;
 
 RequirePackage('ifthen');
 
-# Basically, the effects of hyperxmp are already built
-# into the LaTeXML binding for hyperref.
+# macro to pass alternate language entries
+# TODO support entries in multiple languages
+# TODO pdfmetalang should affect *following* entries, not all of them
+Let('\XMPLangAlt', '\@gobbletwo');
+
+# macros for including commas in comma-separated lists
+# TODO implement comma-separated lists splitting
+Let('\xmpquote', '\relax');
+DefMacroI('\xmpcomma', undef, ',');
+
+# %pdfkey_property may have already been populated by hyperref
+our %pdfkey_property = (%pdfkey_property,
+  # modify hyperref keywords to support specifying the language
+  pdfsubject         => ['dcterms:description', 'content', undef, 1],
+  pdftitle           => ['dcterms:title',       'content', undef, 1],
+  pdfaconformance    => '',                                  # pdfaid:conformance
+  pdfapart           => '',                                  # pdfaid:part
+  pdfauthortitle     => '',                                  # photoshop:AuthorsPosition
+  pdfbookedition     => ['prism:bookEdition', 'content', undef, 1],
+  pdfbytes           => ['prism:byteCount',   'content'],
+  pdfcaptionwriter   => '',                                  # photoshop:CaptionWriter
+  pdfcontactaddress  => '',                                  # Iptc4xmpCore:CiAdrExtadr
+  pdfcontactcity     => '',                                  # Iptc4xmpCore:CiAdrCity
+  pdfcontactcountry  => '',                                  # Iptc4xmpCore:CiAdrCtry
+  pdfcontactemail    => '',                                  # Iptc4xmpCore:CiEmailWork
+  pdfcontactphone    => '',                                  # Iptc4xmpCore:CiTelWork
+  pdfcontactpostcode => '',                                  # Iptc4xmpCore:CiAdrPcode
+  pdfcontactregion   => '',                                  # Iptc4xmpCore:CiAdrRegion
+  pdfcontacturl      => '',                                  # Iptc4xmpCore:CiUrlWork
+  pdfcopyright => ['dcterms:rights', 'content', undef, 1], # & xmpRights:Marked, xmpRights:WebStatement
+  pdfdate => ['dcterms:date', 'content'], # (if missing, hyperxmp uses \date -- we delegate the default choice to postprocessing)
+  pdfdocumentid => '',                    # xmpMM:DocumentID
+  pdfdoi        => ['prism:doi',   'content'],
+  pdfeissn      => ['prism:eIssn', 'content'],
+  pdfidentifier => ['dcterms:identifier', 'content'], # (if missing, hyperxmp uses the first non-empty doi, eissn, issn, isbn with prefix info:doi/ or urn:ISS(B|N): -- we delegate the default choice to postprocessing)
+  pdfinstanceid  => '',                               # xmpMM:InstanceID
+  pdfisbn        => ['prism:isbn',   'content'],
+  pdfissn        => ['prism:issn',   'content'],
+  pdfissuenum    => ['prism:number', 'content'],
+  pdflicenseurl  => ['cc:licence',   'resource'],     # xmpRights:WebStatement
+  pdfmetadate    => '',    # xmp:MetadataDate
+  pdfmetalang    => '',    # the default language of the metadata entries themselves
+  pdfnumpages    => ['prism:pageCount',       'content'],    # xmpTPg:NPages
+  pdfpagerange   => ['prism:pageRange',       'content'],
+  pdfpublication => ['prism:publicationName', 'content', undef, 1],
+  pdfpublisher   => ['dcterms:publisher',     'content'],
+  pdfpubstatus   => '',                                      # jav:journal_article_version
+  pdfpubtype     => ['prism:aggregationType', 'content'],
+  pdfrendition   => '',                                      # xmpMM:RenditionClass
+  pdfsource      => ['dcterms:source', 'content'],
+  pdfsubtitle    => ['prism:subtitle', 'content', undef, 1],
+  pdftype        => ['dcterms:type',   'content'],
+  pdfuapart      => '',                                      # pdfuaid:part
+  pdfurl         => ['prism:url', 'content'],
+  pdfversionid   => '',                                      # xmpMM:VersionID
+  pdfvolumenum   => ['prism:volume', 'content'],
+  pdfxstandard   => '',                                      # {pdfx,pdfxid}:GTS_PDFXVersion
+);
 
 1;

t/80_complex.t

@@ -9,6 +9,7 @@ latexml_tests("t/complex",
     cleveref_minimal => 'cleveref.sty',
     figure_dual_caption => {packages => 'graphicx.sty', texlive_min => 2021},
     figure_mixed_content => {packages => 'graphicx.sty', texlive_min => 2021},
+    hyperxmp => 'babel.sty',
     si               => {
       env=>'CI', # only runs in continuous integration
       packages => 'siunitx.sty', texlive_min => 2015 } });

t/complex/hypertest.xml

@@ -50,6 +50,6 @@
   <rdf about="" content="Not subject to copyright" property="dcterms:rights"/>
   <rdf about="" content="test,hyperref" property="dcterms:subject"/>
   <rdf about="" property="cc:licence" resource="http://creativecommons.org/licenses/by/3.0/"/>
-  <rdf about="" content="Testing LaTeXML’s processing of hyperref metadata" property="dcterms:subject"/>
+  <rdf about="" content="Testing LaTeXML's processing of hyperref metadata" property="dcterms:description"/>
   <rdf about="" content="Test Hyperref Metadata" property="dcterms:title"/>
 </document>

t/complex/hyperxmp.tex

@@ -0,0 +1,64 @@
+% example copied from hyperxmp with minor modifications
+\pdfobjcompresslevel=0 % added to easily inspect the XMP packet
+\documentclass[british]{article} % added british to test pdflang and pdfmetalang
+\usepackage[utf8]{inputenc}
+\usepackage{babel}
+\usepackage[unicode]{hyperref}
+\usepackage{hyperxmp}
+%
+\title{%
+  On a heuristic viewpoint concerning the production and
+  transformation of light}
+\author{Albert Einstein}
+\date{March 17, 1905}
+%
+\hypersetup{%
+  pdfmetalang={en-AU}, % added to test pdfmetalang
+  pdftitle={%
+    On a heuristic viewpoint concerning the production and
+    transformation of light},
+  pdfsubtitle={[en-US]Putting that bum Maxwell in his place},
+  pdfauthor={Albert Einstein},
+  pdfauthortitle={\xmpquote{Technical Assistant\xmpcomma\ Level III}},
+  pdfdate={1905-03-17},
+  pdfcopyright={Copyright (C) 1905, Albert Einstein},
+  pdfsubject={photoelectric effect},
+  pdfkeywords={energy quanta, Hertz effect, quantum physics},
+  pdflicenseurl={http://creativecommons.org/licenses/by-nc-nd/3.0/},
+  pdfcaptionwriter={Scott Pakin},
+  pdfcontactaddress={Kramgasse 49},
+  pdfcontactcity={Bern},
+  pdfcontactpostcode={3011},
+  pdfcontactcountry={Switzerland},
+  pdfcontactphone={031 312 00 91},
+  pdfcontactemail={aeinstein@ipi.ch},
+  pdfcontacturl={%
+    http://einstein.biz/,
+    https://www.facebook.com/AlbertEinstein
+  },
+  pdfdocumentid={uuid:6d1ac9ec-4ff2-515a-954b-648eeb4853b0},
+  pdfversionid={2.998e8},
+  pdfpublication={[de]Annalen der Physik},
+  pdfpublisher={Wiley-VCH},
+  pdfpubtype={journal},
+  pdfvolumenum={322},
+  pdfissuenum={6},
+  pdfpagerange={132-148},
+  pdfissn={0003-3804},
+  pdfeissn={1521-3889},
+  pdfpubstatus={VoR},
+  pdflang={en-GB},
+  pdfurl={http://www.physik.uni-augsburg.de/annalen/history/einstein-papers/1905_17_132-148.pdf},
+  pdfdoi={10.1002/andp.19053220607},
+  pdfidentifier={info:lccn/50013519}
+}
+\XMPLangAlt{de}{pdftitle={Über einen die Erzeugung und Verwandlung des
+  Lichtes betreffenden heuristischen Gesichtspunkt}}
+%
+\begin{document}
+\maketitle
+A profound formal difference exists between the theoretical
+concepts that physicists have formed about gases and other
+ponderable bodies, and Maxwell's theory of electromagnetic
+processes in so-called empty space\dots
+\end{document}

t/complex/hyperxmp.xml

@@ -0,0 +1,43 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<?latexml class="article" options="british"?>
+<?latexml package="inputenc" options="utf8"?>
+<?latexml package="babel"?>
+<?latexml package="hyperref" options="unicode"?>
+<?latexml package="hyperxmp"?>
+<?latexml RelaxNGSchema="LaTeXML"?>
+<document xmlns="http://dlmf.nist.gov/LaTeXML" class="ltx_authors_1line" prefix="cc: http://creativecommons.org/ns# dcterms: http://purl.org/dc/terms/ prism: http://prismstandard.org/namespaces/basic/3.0/" xml:lang="en-GB">
+  <resource src="LaTeXML.css" type="text/css"/>
+  <resource src="ltx-article.css" type="text/css"/>
+  <title>On a heuristic viewpoint concerning the production and
+transformation of light</title>
+  <creator role="author">
+    <personname>Albert Einstein</personname>
+  </creator>
+  <date role="creation">March 17, 1905</date>
+  <para xml:id="p1">
+    <p>A profound formal difference exists between the theoretical
+concepts that physicists have formed about gases and other
+ponderable bodies, and Maxwell’s theory of electromagnetic
+processes in so-called empty space…</p>
+  </para>
+  <rdf about="" content="Albert Einstein" property="dcterms:creator"/>
+  <rdf about="" content="Copyright (C) 1905, Albert Einstein" property="dcterms:rights" xml:lang="en-AU"/>
+  <rdf about="" content="1905-03-17" property="dcterms:date"/>
+  <rdf about="" content="10.1002/andp.19053220607" property="prism:doi"/>
+  <rdf about="" content="1521-3889" property="prism:eIssn"/>
+  <rdf about="" content="info:lccn/50013519" property="dcterms:identifier"/>
+  <rdf about="" content="0003-3804" property="prism:issn"/>
+  <rdf about="" content="6" property="prism:number"/>
+  <rdf about="" content="energy quanta, Hertz effect, quantum physics" property="dcterms:subject"/>
+  <rdf about="" content="en-GB" property="dcterms:language"/>
+  <rdf about="" property="cc:licence" resource="http://creativecommons.org/licenses/by-nc-nd/3.0/"/>
+  <rdf about="" content="132-148" property="prism:pageRange"/>
+  <rdf about="" content="Annalen der Physik" property="prism:publicationName" xml:lang="de"/>
+  <rdf about="" content="Wiley-VCH" property="dcterms:publisher"/>
+  <rdf about="" content="journal" property="prism:aggregationType"/>
+  <rdf about="" content="photoelectric effect" property="dcterms:description" xml:lang="en-AU"/>
+  <rdf about="" content="Putting that bum Maxwell in his place" property="prism:subtitle" xml:lang="en-US"/>
+  <rdf about="" content="On a heuristic viewpoint concerning the production and&#10;transformation of light" property="dcterms:title" xml:lang="en-AU"/>
+  <rdf about="" content="http://www.physik.uni-augsburg.de/annalen/history/einstein-papers/1905_17_132-148.pdf" property="prism:url"/>
+  <rdf about="" content="322" property="prism:volume"/>
+</document>