idml 0.2.8 → 0.2.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e9833da9d4a8ddda74890980eab76f2a47b03cdb99977730fb1dee5d8809dd68
-  data.tar.gz: 1d771cc2775f1071329d2b2dbab681cc46197546be27681fcba39ee9313f9a2b
+  metadata.gz: 192799dde8a7c36a34473f5903934fa17a08c8ea05ae444797099ada2b03ff7c
+  data.tar.gz: 9b7659bb74cda7f6d8f9f47df07e2123605baa9df584138d3ef382934f999f60
 SHA512:
-  metadata.gz: e3dfbfc1c8ccdccdcd53070ff9aaf8de3f150699e524c3b6b4668c9a2d266cfb530ed5d8fb1e5b515be6da145df17e60832d9f9f60c0c9b2c106092adf716dfd
-  data.tar.gz: 437d8bcdc82e87f999b916ea9fc10486f2f4b8ae57965b9753fae465ab8f570684f4b2ea7eb8ae81fbc40fdf6a66288387429d265053562cf2dc4581101473be
+  metadata.gz: c113cb7d7a44f198c4c6746cde61f2301733f7f61f2ed5bfe6a3afd145e4446a2e144790916a5bad8106440e0f83b2901dff52e6ff2adf52dedbbe7fb8fcf655
+  data.tar.gz: 7960cfe58d64292369cfb23c87a5bcaeec495a7e20f3bbf8c87592040ec04d57630d61ecf7fe2916b1706c142d53c7561d3229c5563216eaf015119d28148a48

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    idml (0.2.8)
+    idml (0.2.9)
       bigdecimal
       fontisan
       lutaml-model (~> 0.8.18)
@@ -198,7 +198,7 @@ CHECKSUMS
   ffi (1.17.4-x86_64-linux-gnu) sha256=9d3db14c2eae074b382fa9c083fe95aec6e0a1451da249eab096c34002bc752d
   ffi (1.17.4-x86_64-linux-musl) sha256=3fdf9888483de005f8ef8d1cf2d3b20d86626af206cbf780f6a6a12439a9c49e
   fontisan (0.4.45) sha256=2337ca0205f806647b24b8cac57aa34f3769473026ae6f52dc36bde0feed6c62
-  idml (0.2.8)
+  idml (0.2.9)
   json (2.21.2) sha256=1f1d3b7cf2b3ba1a69beca0bb6db13d5438b80bff3cd54cdaaa620b9b07c1c6a
   language_server-protocol (3.17.0.6) sha256=5ef2c0c138f8267e1bc631d3328347d354f96724b0af22f2c79516120443b7f0
   lint_roller (1.1.0) sha256=2c0c845b632a7d172cb849cc90c1bce937a28c5c8ccccb50dfd46a485003cc87

data/TODO.pdf/75-pdf-metadata-from-xmp.md

@@ -1,103 +1,65 @@
 # TODO PDF 75: PDF metadata enrichment from IDML XMP
 
-## Status: BLOCKED (Lutaml XMP namespace parsing)
+## Status: DONE
 
-## Goal
+## What was implemented
 
 Pull IDML document metadata from `META-INF/metadata.xml` (XMP packet)
 into the PDF Info dictionary via `PdfrbWriter#set_info`:
 
-- `dc:title` → PDF `/Title`
-- `dc:creator` → PDF `/Author`
-- `dc:description` → PDF `/Subject`
-- `dc:subject` → PDF `/Keywords`
+- `dc:title` (rdf:Alt x-default) → PDF `/Title`
+- `dc:creator` (rdf:Seq first li) → PDF `/Author`
+- `dc:description` (rdf:Alt x-default) → PDF `/Subject`
+- `dc:subject` (rdf:Bag joined) → PDF `/Keywords`
 - `xmp:CreatorTool` → PDF `/Creator`
 - `xmp:CreateDate` → PDF `/CreationDate`
 - `xmp:ModifyDate` → PDF `/ModDate`
 
-## Blocker
-
-`META-INF/metadata.xml` is an XMP packet — RDF/XML with multiple XML
-namespaces (`dc:`, `xmp:`, `pdf:`, `xmpMM:`, `stFnt:`, etc.). Parsing
-it with `lutaml-model` requires namespace-aware element mapping.
-
-Lutaml 0.8.19's namespace API is in flux:
-
-- `namespace "..."` with a URI string raises
-  `String namespace URIs are not supported. Define an XmlNamespace
-  class instead.`
-- `namespace: Lutaml::Xml::XmlNamespace.new(uri, prefix)` raises
-  a `NoMethodError` inside `process_mapping`.
-- `map_element "dc:format"` (prefix in name) is silently ignored —
-  local-name lookup strips the prefix.
-- `prefix: "dc"` is ignored when there is no `namespace:` on the
-  mapping.
-
-The CLAUDE.md rule "no `Lutaml::Xml::Document.parse`" rules out
-falling back to a generic XmlDocument traversal. We must use a typed
-model.
-
-## Path forward
-
-Wait for Lutaml to stabilise its namespace API, then add a typed
-`Idml::Parts::XmpMetadata` model that maps each XMP field to a Ruby
-attribute. Pipeline reads `META-INF/metadata.xml`, calls
-`XmpMetadata.from_xml`, and threads the resulting attributes through
-`PdfrbWriter#set_info`.
-
-When the blocker clears, the implementation looks like:
-
-```ruby
-module Idml
-  module Parts
-    class XmpMetadata < Lutaml::Model::Serializable
-      attribute :title, :string
-      attribute :author, :string
-      attribute :subject, :string
-      attribute :keywords, :string
-      attribute :creator_tool, :string
-      attribute :create_date, :string
-      attribute :modify_date, :string
-
-      xml do
-        root "Description"
-        # …namespace-aware mappings once Lutaml supports them…
-      end
-    end
-  end
-end
-
-# In Pipeline:
-if @package.has_part?("META-INF/metadata.xml")
-  xmp = Idml::Parts::XmpMetadata.from_xml(
-    @package.read_part("META-INF/metadata.xml"),
-  )
-  writer.set_info(
-    Title: xmp.title,
-    Author: xmp.author,
-    Subject: xmp.subject,
-    Keywords: xmp.keywords,
-    Creator: xmp.creator_tool,
-    CreationDate: pdf_date(xmp.create_date),
-    ModDate: pdf_date(xmp.modify_date),
-  )
-end
-```
-
-## Acceptance criteria (after blocker clears)
-
-- [ ] Pipeline reads `META-INF/metadata.xml` when present.
-- [ ] `XmpMetadata` typed model parses dc:title/creator/description/
-      subject plus xmp:CreatorTool/CreateDate/ModifyDate.
-- [ ] Pipeline passes the parsed fields to `PdfrbWriter#set_info`.
-- [ ] Existing Producer/CreationDate defaults still apply when XMP
+## Architecture
+
+XMP has multiple XML namespaces (`dc:`, `xmp:`, `pdf:`) inside one
+`<rdf:Description>` element. Per Lutaml's namespace API, each
+namespaced child is its own `Lutaml::Model::Serializable` subclass
+carrying its own `namespace` declaration via a `Lutaml::Xml::Namespace`
+class. The parent composes the children via `map_element`.
+
+Layered models in `lib/idml/parts/xmp.rb`:
+
+- `Xmp::RdfNamespace`, `DcNamespace`, `XmpNamespace`, `XmetaNamespace` —
+  `Lutaml::Xml::Namespace` subclasses with `uri` and `prefix_default`.
+- `Xmp::Leaf` base + `Format`/`CreatorTool`/`CreateDate`/`ModifyDate`/
+  `MetadataDate` — single direct-value leaves.
+- `Xmp::ListItem` (rdf:li), `Alt` (rdf:Alt with x-default lookup),
+  `Seq` (rdf:Seq), `Bag` (rdf:Bag) — RDF container types.
+- `Xmp::Title`/`DcDescription`/`Creator`/`Subject` — dc: elements that
+  wrap the RDF containers.
+- `XmpDescription` — single rdf:Description composing all the leaves
+  and containers above.
+- `XmpRdf` — rdf:RDF with a collection of Descriptions plus merged
+  accessors (`title`, `author`, `keywords`, etc.) that pick the first
+  non-nil across Descriptions.
+- `XmpMeta` — outer `<x:xmpmeta>` wrapper.
+
+Pipeline threads this through `combined_metadata`, which starts from
+the default Producer+CreationDate and overrides each field that the
+XMP packet supplies.
+
+## Verification
+
+- `lib/idml/parts/xmp.rb` — typed XMP models.
+- `lib/idml/render/pipeline.rb:193` — `combined_metadata` merge.
+- `spec/idml/parts/xmp_meta_spec.rb` — 11 specs covering direct
+  elements, containers, missing fields, and the fixture.
+- `spec/idml/render/render_pdfrb_pipeline_spec.rb` — integration spec
+  asserts `/Creator` from XMP lands in the PDF.
+
+## Acceptance criteria
+
+- [x] Pipeline reads `META-INF/metadata.xml` when present.
+- [x] `XmpMeta` typed model parses dc:title/creator/description/subject
+      plus xmp:CreatorTool/CreateDate/ModifyDate.
+- [x] Pipeline passes the parsed fields to `PdfrbWriter#set_info`.
+- [x] Existing Producer/CreationDate defaults still apply when XMP
       or individual fields are absent.
-- [ ] Spec covers a synthetic XMP packet with all fields populated,
+- [x] Spec covers a synthetic XMP packet with all fields populated,
       plus the no-metadata fallback.
-
-## Dependencies
-
-- Lutaml namespace API stable enough that
-  `map_element "format", namespace: <XmlNamespace>` works without
-  raising. Tracked at the Lutaml migration guide referenced in the
-  error message: `docs/_guides/xml-namespaces.adoc`.

data/lib/idml/parts/xmp.rb

@@ -0,0 +1,305 @@
+# frozen_string_literal: true
+
+require "lutaml/model"
+
+module Idml
+  module Parts
+    # XMP (Extensible Metadata Platform) parser for IDML's
+    # `META-INF/metadata.xml`. The packet is RDF/XML with multiple
+    # namespaces (`dc:`, `xmp:`, `pdf:`, `xmpMM:`, etc.).
+    #
+    # Per Lutaml's namespace API, each namespaced element is a
+    # separate `Serializable` subclass that carries its own
+    # `namespace`. The parent `<rdf:Description>` composes the
+    # children via `map_element`, with the namespace binding handled
+    # on each child class.
+    module Xmp
+      class RdfNamespace < Lutaml::Xml::Namespace
+        uri "http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+        prefix_default "rdf"
+      end
+
+      class DcNamespace < Lutaml::Xml::Namespace
+        uri "http://purl.org/dc/elements/1.1/"
+        prefix_default "dc"
+      end
+
+      class XmpNamespace < Lutaml::Xml::Namespace
+        uri "http://ns.adobe.com/xap/1.0/"
+        prefix_default "xmp"
+      end
+
+      class XmetaNamespace < Lutaml::Xml::Namespace
+        uri "adobe:ns:meta/"
+        prefix_default "x"
+      end
+
+      # Single direct-value element. Subclasses set the element name
+      # and namespace.
+      class Leaf < Lutaml::Model::Serializable
+        attribute :value, :string
+      end
+
+      class Format < Leaf
+        xml do
+          root "format"
+          namespace DcNamespace
+          map_content to: :value
+        end
+      end
+
+      class CreatorTool < Leaf
+        xml do
+          root "CreatorTool"
+          namespace XmpNamespace
+          map_content to: :value
+        end
+      end
+
+      class CreateDate < Leaf
+        xml do
+          root "CreateDate"
+          namespace XmpNamespace
+          map_content to: :value
+        end
+      end
+
+      class ModifyDate < Leaf
+        xml do
+          root "ModifyDate"
+          namespace XmpNamespace
+          map_content to: :value
+        end
+      end
+
+      class MetadataDate < Leaf
+        xml do
+          root "MetadataDate"
+          namespace XmpNamespace
+          map_content to: :value
+        end
+      end
+
+      # rdf:li element inside rdf:Alt / rdf:Seq / rdf:Bag containers.
+      class ListItem < Lutaml::Model::Serializable
+        attribute :lang, :string
+        attribute :value, :string
+
+        xml do
+          root "li"
+          namespace RdfNamespace
+          map_attribute "lang", to: :lang
+          map_content to: :value
+        end
+      end
+
+      # rdf:Alt — alternative-language values. Used for dc:title and
+      # dc:description.
+      class Alt < Lutaml::Model::Serializable
+        attribute :items, ListItem, collection: true
+
+        xml do
+          root "Alt"
+          namespace RdfNamespace
+          map_element "li", to: :items
+        end
+
+        def default_value
+          x_default = items.find { |i| i.lang == "x-default" }
+          (x_default || items.first)&.value
+        end
+      end
+
+      # rdf:Seq — ordered sequence. Used for dc:creator.
+      class Seq < Lutaml::Model::Serializable
+        attribute :items, ListItem, collection: true
+
+        xml do
+          root "Seq"
+          namespace RdfNamespace
+          map_element "li", to: :items
+        end
+
+        def values
+          items.filter_map(&:value)
+        end
+      end
+
+      # rdf:Bag — unordered set. Used for dc:subject.
+      class Bag < Lutaml::Model::Serializable
+        attribute :items, ListItem, collection: true
+
+        xml do
+          root "Bag"
+          namespace RdfNamespace
+          map_element "li", to: :items
+        end
+
+        def values
+          items.filter_map(&:value)
+        end
+      end
+
+      # Container-wrapped dc elements.
+      class Title < Lutaml::Model::Serializable
+        attribute :alt, Alt
+
+        xml do
+          root "title"
+          namespace DcNamespace
+          map_element "Alt", to: :alt
+        end
+
+        def value
+          alt&.default_value
+        end
+      end
+
+      class DcDescription < Lutaml::Model::Serializable
+        attribute :alt, Alt
+
+        xml do
+          root "description"
+          namespace DcNamespace
+          map_element "Alt", to: :alt
+        end
+
+        def value
+          alt&.default_value
+        end
+      end
+
+      class Creator < Lutaml::Model::Serializable
+        attribute :seq, Seq
+
+        xml do
+          root "creator"
+          namespace DcNamespace
+          map_element "Seq", to: :seq
+        end
+
+        def values
+          seq&.values || []
+        end
+      end
+
+      class Subject < Lutaml::Model::Serializable
+        attribute :bag, Bag
+
+        xml do
+          root "subject"
+          namespace DcNamespace
+          map_element "Bag", to: :bag
+        end
+
+        def values
+          bag&.values || []
+        end
+      end
+    end
+
+    # Single `<rdf:Description>` element from an XMP packet. Combines
+    # children from multiple namespaces (`dc:`, `xmp:`) by composing
+    # nested `Serializable` models — each child carries its own
+    # `namespace` declaration per Lutaml's namespace API.
+    class XmpDescription < Lutaml::Model::Serializable
+      attribute :format, Xmp::Format
+      attribute :title, Xmp::Title
+      attribute :creator, Xmp::Creator
+      attribute :description, Xmp::DcDescription
+      attribute :subject, Xmp::Subject
+      attribute :creator_tool, Xmp::CreatorTool
+      attribute :create_date, Xmp::CreateDate
+      attribute :modify_date, Xmp::ModifyDate
+      attribute :metadata_date, Xmp::MetadataDate
+
+      xml do
+        root "Description"
+        namespace Xmp::RdfNamespace
+        map_element "format", to: :format
+        map_element "title", to: :title
+        map_element "creator", to: :creator
+        map_element "description", to: :description
+        map_element "subject", to: :subject
+        map_element "CreatorTool", to: :creator_tool
+        map_element "CreateDate", to: :create_date
+        map_element "ModifyDate", to: :modify_date
+        map_element "MetadataDate", to: :metadata_date
+      end
+
+      def author
+        creator&.values&.first
+      end
+
+      def keywords
+        subject&.values&.join(", ")
+      end
+    end
+
+    # `<rdf:RDF>` — collection of `<rdf:Description>` siblings inside
+    # an XMP packet. Per IDML's META-INF/metadata.xml, there is
+    # typically one Description per schema group.
+    class XmpRdf < Lutaml::Model::Serializable
+      attribute :descriptions, XmpDescription, collection: true
+
+      xml do
+        root "RDF"
+        namespace Xmp::RdfNamespace
+        map_element "Description", to: :descriptions
+      end
+
+      # Merged view across all Descriptions. Each attribute returns
+      # the first non-nil value across the descriptions.
+      def first_description
+        descriptions.first
+      end
+
+      def title
+        descriptions.map(&:title).find(&:itself)&.value
+      end
+
+      def author
+        descriptions.filter_map(&:author).first
+      end
+
+      def subject
+        descriptions.filter_map(&:subject).find(&:itself)&.values
+      end
+
+      def keywords
+        subject&.join(", ")
+      end
+
+      def description
+        descriptions.map(&:description).find(&:itself)&.value
+      end
+
+      def creator_tool
+        descriptions.filter_map(&:creator_tool).first&.value
+      end
+
+      def create_date
+        descriptions.filter_map(&:create_date).first&.value
+      end
+
+      def modify_date
+        descriptions.filter_map(&:modify_date).first&.value
+      end
+    end
+
+    # `<x:xmpmeta>` — outer wrapper of an XMP packet.
+    class XmpMeta < Lutaml::Model::Serializable
+      attribute :rdf, XmpRdf
+
+      xml do
+        root "xmpmeta"
+        namespace Xmp::XmetaNamespace
+        map_element "RDF", to: :rdf
+      end
+
+      def description
+        rdf&.first_description
+      end
+    end
+  end
+end

data/lib/idml/parts.rb

@@ -15,6 +15,10 @@ module Idml
     autoload :Preferences,  "idml/parts/preferences"
     autoload :Tags,         "idml/parts/tags"
     autoload :Mapping,      "idml/parts/mapping"
+    autoload :Xmp,            "idml/parts/xmp"
+    autoload :XmpDescription, "idml/parts/xmp"
+    autoload :XmpRdf,         "idml/parts/xmp"
+    autoload :XmpMeta,        "idml/parts/xmp"
 
     @registry = {}
 

data/lib/idml/render/pipeline.rb

@@ -21,7 +21,7 @@ module Idml
 
       def call
         writer = PdfrbWriter.new
-        writer.set_info(default_metadata)
+        writer.set_info(combined_metadata)
         writer.enable_tagged if @tagged
         layer_filter = LayerFilter.from_designmap(@package.designmap)
         font_ref_resolver = FontReferenceResolver.build(@package)
@@ -190,6 +190,46 @@ module Idml
         nil
       end
 
+      def combined_metadata
+        defaults = default_metadata
+        xmp_metadata.each do |key, value|
+          next if value.nil? || value.empty?
+
+          defaults[key] = value
+        end
+        defaults
+      end
+
+      def xmp_metadata
+        return {} unless @package.has_part?(XMP_PATH)
+
+        xml = @package.read_part(XMP_PATH)
+        meta = Parts::XmpMeta.from_xml(xml)
+        rdf = meta.rdf
+        return {} unless rdf
+
+        {
+          Title: rdf.title,
+          Author: rdf.author,
+          Subject: rdf.description,
+          Keywords: rdf.keywords,
+          Creator: rdf.creator_tool,
+          CreationDate: pdf_date_string(rdf.create_date),
+          ModDate: pdf_date_string(rdf.modify_date),
+        }
+      rescue StandardError
+        {}
+      end
+
+      def pdf_date_string(iso8601)
+        return nil unless iso8601
+
+        time = Time.iso8601(iso8601)
+        pdf_date(time)
+      rescue ArgumentError
+        nil
+      end
+
       def default_metadata
         {
           Producer: "idml gem v#{Idml::VERSION}",
@@ -200,6 +240,9 @@ module Idml
       def pdf_date(time)
         time.strftime("D:%Y%m%d%H%M%S+00'00'")
       end
+
+      XMP_PATH = "META-INF/metadata.xml"
+      private_constant :XMP_PATH
     end
   end
 end

data/lib/idml/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Idml
-  VERSION = "0.2.8"
+  VERSION = "0.2.9"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: idml
 version: !ruby/object:Gem::Version
-  version: 0.2.8
+  version: 0.2.9
 platform: ruby
 authors:
 - Ribose
@@ -381,6 +381,7 @@ files:
 - lib/idml/parts/style.rb
 - lib/idml/parts/style_mapping.rb
 - lib/idml/parts/tags.rb
+- lib/idml/parts/xmp.rb
 - lib/idml/render.rb
 - lib/idml/render/blending.rb
 - lib/idml/render/color_helper.rb