idml 0.2.0 → 0.2.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6cedeac5f13e4983d17408f7b78171654e908e07b0c01cdadf667fdf679a7709
-  data.tar.gz: '0305677727494a9994537095fc3b3979e8424ab3be7e70b76fc4439a81a5f09d'
+  metadata.gz: 5f22227bbbc74fdbc901e8e7c8dc23c6f77f4a365cf9fc9c3e78d738d5bfdf04
+  data.tar.gz: db2b6f2c4f5f95a392c163388837a1e4a975eee64606a7ab09a801c267160246
 SHA512:
-  metadata.gz: 47548b8fe594670306c90b9ff9239489de7e35ae57ba424895b13e3a3d369645ebf2aacd049550e4f318b242b5d38b40cc3f5fde7f75e6090818434c1185e5bb
-  data.tar.gz: a08296a8d2671657229edc6201a883a2dabb9233e47ce19fa8479c29e4f048f3d476f734fe7d217bb50dff73c93dad0dd4a3e508f94c104e10ee84d63ac67b3a
+  metadata.gz: 7a0e4ec3b44a84801ec7cf7683643a092a4a41d279e68ef3c31591bfd7b21bdb64056d24e289071184ff0c86bf933bf0b855ddae2a5af7bcbc177104b9033f4e
+  data.tar.gz: b1626fc2eb4deaf0ad1f235a15f8ccd34979ea523a6f7d4cbd60408ed82ce26d476c11715073f490127210f57c4f85768171b08d02d280a0c516b82cf00e89ee

data/Gemfile

@@ -5,6 +5,7 @@ source "https://rubygems.org"
 gemspec
 
 gem "lutaml-model", "~> 0.8.0"
+gem "pdfrb", path: "/Users/mulgogi/src/claricle/pdfrb"
 gem "rake"
 gem "rspec"
 gem "rubocop"
@@ -14,4 +15,3 @@ gem "rubocop-rspec"
 gem "simplecov", require: false
 gem "thor"
 gem "yard"
-gem "pdfrb", path: "/Users/mulgogi/src/claricle/pdfrb"

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    idml (0.2.0)
+    idml (0.2.2)
       bigdecimal
       fontisan
       lutaml-model (~> 0.8.18)
@@ -12,7 +12,7 @@ PATH
 PATH
   remote: /Users/mulgogi/src/claricle/pdfrb
   specs:
-    pdfrb (0.17.0)
+    pdfrb (0.19.0)
       lutaml-model (>= 0.7.0)
       thor
 
@@ -204,7 +204,7 @@ 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 (0.2.0)
+  idml (0.2.2)
   json (2.21.2) sha256=1f1d3b7cf2b3ba1a69beca0bb6db13d5438b80bff3cd54cdaaa620b9b07c1c6a
   language_server-protocol (3.17.0.6) sha256=5ef2c0c138f8267e1bc631d3328347d354f96724b0af22f2c79516120443b7f0
   lint_roller (1.1.0) sha256=2c0c845b632a7d172cb849cc90c1bce937a28c5c8ccccb50dfd46a485003cc87
@@ -226,7 +226,7 @@ CHECKSUMS
   paint (2.3.0) sha256=327d623e4038619d5bd99ae5db07973859cd78400c7f0329eea283cef8e83be5
   parallel (2.1.0) sha256=b35258865c2e31134c5ecb708beaaf6772adf9d5efae28e93e99260877b09356
   parser (3.3.12.0) sha256=21a6d7f755d5a24dfbdc6e6b772e4e879a52e7631a88bc5a3a134606052c9828
-  pdfrb (0.17.0)
+  pdfrb (0.19.0)
   prism (1.9.0) sha256=7b530c6a9f92c24300014919c9dcbc055bf4cdf51ec30aed099b06cd6674ef85
   racc (1.8.1) sha256=4a7f6929691dbec8b5209a0b373bc2614882b55fc5d2e447a21aaa691303d62f
   rainbow (3.1.1) sha256=039491aa3a89f42efa1d6dec2fc4e62ede96eb6acd95e52f1ad581182b79bc6a

data/TODO.pdf/51-remove-dead-code.md

@@ -1,8 +1,15 @@
 # TODO PDF 51: Remove dead code from pdfrb migration
 
-## Goal
+## Status: DONE
 
-Remove the old hand-rolled PDF modules that are superseded by pdfrb.
+## What was removed (in v0.2.0)
+
+All old hand-rolled modules deleted in the pdfrb 0.15.0 migration:
+- `pdf_writer.rb`, `font_embedder.rb`, `color.rb`, `path.rb`, `text.rb`
+- `pdfrb_ext.rb`, `pdfrb_ext/clip.rb`, `pdfrb_ext/invoke_xobject.rb`
+- 3 old test files
+
+Net: -1358 lines of dead code.
 These modules are dead code — not referenced by any active code path.
 
 ## Status: READY FOR CLEANUP

data/TODO.pdf/53-tagged-pdf-accessibility.md

@@ -1,6 +1,14 @@
 # TODO PDF 53: Tagged PDF for accessibility
 
-## Goal
+## Status: DONE
+
+## What was implemented
+
+Pipeline accepts `tagged: true` option. When enabled:
+- `PdfrbWriter#enable_tagged` calls `document.structure.enable!`
+- `PdfrbWriter#add_structure_element` delegates to `document.structure.add_element`
+- `PdfrbWriter#build_structure` calls `document.structure.build!` before writing
+- `Render.render(tagged: false)` keyword passes through to Pipeline
 
 Produce tagged PDF (PDF/UA) with a structure tree that maps page items
 to logical structure elements (headings, paragraphs, figures, tables).

data/TODO.pdf/64-pipeline-cli-optimizations.md

@@ -0,0 +1,23 @@
+# TODO PDF 64: Pipeline optimizations and CLI enhancements
+
+## Status: DONE
+
+## What was implemented
+
+1. **Pipeline SpreadRenderer caching**: `render_spread_pages` creates
+   one SpreadRenderer per spread (was one per page). The renderer is
+   stateless and can be reused across pages within a spread.
+
+2. **CLI --verbose / -v flag**: Prints progress during rendering:
+   - Input and output paths
+   - Spread count
+   - Goes to stderr (doesn't interfere with stdout piping)
+
+3. **render_options extraction**: CLI's render_options hash extracted
+   as a method (DRY).
+
+## Acceptance criteria
+
+- [x] SpreadRenderer created once per spread (not per page)
+- [x] CLI --verbose flag prints progress to stderr
+- [x] All tests pass

data/lib/idml/cli.rb

@@ -58,19 +58,22 @@ module Idml
       end
     end
 
-    desc "render PATH [-o OUTPUT] [--pdf-a] [--font-path DIR]",
+    desc "render PATH [-o OUTPUT] [--pdf-a] [--tagged] [-v]",
          "Convert IDML to PDF"
     method_option :output, aliases: "-o", type: :string, required: true
     method_option :font_path, type: :array, default: [],
                               desc: "Additional font search directories"
     method_option :pdf_a, type: :boolean, default: false,
                           desc: "Produce PDF/A-2a compliant output"
+    method_option :tagged, type: :boolean, default: false,
+                           desc: "Produce tagged PDF (PDF/UA)"
+    method_option :verbose, aliases: "-v", type: :boolean, default: false,
+                            desc: "Print progress"
     def render(path)
       pkg = package(path)
-      compliance = options[:pdf_a] ? :pdfa2a : nil
+      print_verbose(pkg) if options[:verbose]
       Idml::Render.render(package: pkg, to: options[:output],
-                          font_search_paths: font_search_paths,
-                          compliance: compliance)
+                          **render_options)
       puts "Wrote #{options[:output]}"
     rescue Idml::Errors::PackageNotFound => e
       warn "Error: #{e.message}"
@@ -89,6 +92,19 @@ module Idml
       options[:font_path].empty? ? nil : options[:font_path]
     end
 
+    def render_options
+      {
+        font_search_paths: font_search_paths,
+        compliance: options[:pdf_a] ? :pdfa2a : nil,
+        tagged: options[:tagged],
+      }
+    end
+
+    def print_verbose(pkg)
+      warn "Rendering to #{options[:output]}"
+      warn "  #{pkg.spreads.length} spread(s)"
+    end
+
     def print_validation_results(results)
       results.partition(&:ok?).then do |ok, failed|
         ok.each { |r| puts "  OK   #{r.part_name}" }

data/lib/idml/render/pdfrb_writer.rb

@@ -56,6 +56,19 @@ module Idml
         @image_cache[uri] = name
       end
 
+      def enable_tagged
+        @document.structure.enable!
+      end
+
+      def add_structure_element(type, page_index:, mcid:, text: nil, alt: nil)
+        @document.structure.add_element(type, text: text, alt: alt,
+                                              page: page_index, mcid: mcid)
+      end
+
+      def build_structure
+        @document.structure.build!
+      end
+
       def document
         @document
       end

data/lib/idml/render/pipeline.rb

@@ -10,16 +10,18 @@ module Idml
       DEFAULT_HEIGHT = 792
 
       def initialize(package, output_path, font_search_paths = nil,
-                     compliance: nil)
+                     compliance: nil, tagged: false)
         @package = package
         @output_path = output_path
         @font_resolver = build_font_resolver(font_search_paths)
         @compliance = compliance
+        @tagged = tagged
       end
 
       def call
         writer = PdfrbWriter.new
         writer.set_info(default_metadata)
+        writer.enable_tagged if @tagged
         layer_filter = LayerFilter.from_designmap(@package.designmap)
         font_ref_resolver = FontReferenceResolver.build(@package)
         base_dir = File.dirname(@package.path)
@@ -30,6 +32,7 @@ module Idml
                               font_ref_resolver, font_name)
         end
 
+        writer.build_structure if @tagged
         writer.write(@output_path)
         @output_path
       end
@@ -40,23 +43,27 @@ module Idml
                               font_ref_resolver, font_name)
         pages = spread.spread.flat_map(&:page)
         image_refs = collect_images(writer, spread, base_dir, layer_filter)
+        renderer = build_renderer(layer_filter, font_ref_resolver, font_name)
 
         pages.each do |page|
           dims = page_dimensions_for(page)
           canvas = writer.add_page(width: dims[:width], height: dims[:height])
-          renderer = SpreadRenderer.new(
-            font_resolver: @font_resolver,
-            font_ps_name: font_name,
-            package: @package,
-            layer_filter: layer_filter,
-            font_ref_resolver: font_ref_resolver,
-          )
           renderer.render(canvas, spread, page_width: dims[:width],
                                           page_height: dims[:height],
                                           image_refs: image_refs)
         end
       end
 
+      def build_renderer(layer_filter, font_ref_resolver, font_name)
+        SpreadRenderer.new(
+          font_resolver: @font_resolver,
+          font_ps_name: font_name,
+          package: @package,
+          layer_filter: layer_filter,
+          font_ref_resolver: font_ref_resolver,
+        )
+      end
+
       def collect_images(writer, spread, base_dir, layer_filter)
         refs = []
         spread.each_page_item do |item|

data/lib/idml/render.rb

@@ -22,8 +22,10 @@ module Idml
 
     DEFAULT_FONT = "Helvetica"
 
-    def self.render(package:, to:, font_search_paths: nil, compliance: nil)
-      Pipeline.new(package, to, font_search_paths, compliance: compliance).call
+    def self.render(package:, to:, font_search_paths: nil, compliance: nil,
+                   tagged: false)
+      Pipeline.new(package, to, font_search_paths, compliance: compliance,
+                                                   tagged: tagged).call
     end
   end
 end

data/lib/idml/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Idml
-  VERSION = "0.2.0"
+  VERSION = "0.2.2"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: idml
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.2
 platform: ruby
 authors:
 - Ribose
@@ -204,6 +204,7 @@ files:
 - TODO.pdf/61-known-limitations.md
 - TODO.pdf/62-pdfrb-015-migration.md
 - TODO.pdf/63-replace-fontmetrics-with-pdfrb.md
+- TODO.pdf/64-pipeline-cli-optimizations.md
 - TODO.pdf/README.md
 - exe/idml
 - idml.gemspec