arrolio 0.1.0 → 0.1.1

data/lib/arrolio/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Arrolio
-  VERSION = '0.1.0'
+  VERSION = '0.1.1'
 end

data/lib/arrolio.rb

@@ -1,12 +1,13 @@
 # frozen_string_literal: true
 
 require 'pdfrb'
+require 'pdfrb/content/operators'
+require 'mml'
 
 # Arrolio -- a flavor-agnostic paged-media layout engine.
-# Core knows NOTHING about specific document formats (OIML,
-# ISO, IEC, BSI). Flavors are loaded on demand:
-#   require 'arroolio'
-#   require 'arrolio/oiml'  # Load the OIML flavor
+# Core knows NOTHING about specific document formats. Each flavor
+# lives in its own directory (XSL + 3 generated YAML files) outside
+# the gem and is rendered via Arrolio::ConfigDrivenPipeline.
 module Arrolio
   autoload :VERSION, 'arrolio/version'
   autoload :Error, 'arrolio/error'
@@ -36,7 +37,10 @@ module Arrolio
   autoload :AssetResolver, 'arrolio/asset_resolver'
   autoload :GenericAdapter, 'arrolio/generic_adapter'
   autoload :GenericFlowBuilder, 'arrolio/generic_flow_builder'
+  autoload :EmbeddedBlockExtractor, 'arrolio/embedded_block_extractor'
   autoload :ConfigDrivenPipeline, 'arrolio/config_driven_pipeline'
   autoload :TocBuilder, 'arrolio/toc_builder'
+  autoload :FontScanner, 'arrolio/font_scanner'
   autoload :Composer, 'arrolio/composer'
+  autoload :MathML, 'arrolio/math_ml'
 end

data/scripts/parity_check.rb

@@ -0,0 +1,52 @@
+# frozen_string_literal: true
+
+require 'arrolio'
+require 'fileutils'
+
+module ParityCheck
+  REFERENCE = File.expand_path('~/src/mn/mn-samples-oiml/_site/documents/r060/1/document.pdf')
+  FIXTURE = File.expand_path('~/src/mn/mn-samples-oiml/_site/documents/r060/1/document.presentation.xml')
+  SOURCE_DIR = File.expand_path('~/src/mn/mn-samples-oiml/sources/r060/1')
+  FLAVOR_DIR = File.expand_path('../flavors/oiml', __dir__)
+  OUTPUT = File.expand_path('../tmp/parity_check.pdf', __dir__)
+
+  def self.run
+    unless File.exist?(REFERENCE) && File.exist?(FIXTURE)
+      warn 'OIML fixture or reference PDF not found. Skipping parity check.'
+      warn "  Reference: #{REFERENCE}" unless File.exist?(REFERENCE)
+      warn "  Fixture:   #{FIXTURE}" unless File.exist?(FIXTURE)
+      return
+    end
+
+    FileUtils.mkdir_p(File.dirname(OUTPUT))
+    xml = File.read(FIXTURE)
+    Arrolio::ConfigDrivenPipeline.render(
+      xml,
+      io: OUTPUT,
+      flavor_dir: FLAVOR_DIR,
+      input_path: FIXTURE,
+      extra_image_dirs: [SOURCE_DIR]
+    )
+
+    require 'arrolio/harness'
+    diff = Arrolio::Harness::PdfDiff.new(OUTPUT, REFERENCE)
+    result = diff.call
+
+    puts "Overall similarity: #{(result.overall_similarity * 100).round(2)}%"
+    puts "Our pages: #{result.ours_pages}, Reference pages: #{result.theirs_pages}"
+    puts ''
+    result.per_page.each do |page|
+      pct = (page.similarity * 100).round(1)
+      status = if page.similarity > 0.5 then 'OK'
+               elsif page.similarity > 0.1 then 'PARTIAL'
+               else 'LOW'
+               end
+      puts "  Page #{page.number}: #{pct}% [#{status}]"
+    end
+    puts ''
+    puts 'Target: > 50% overall similarity'
+    result.overall_similarity
+  end
+end
+
+ParityCheck.run

data/scripts/parity_diff.rb

@@ -0,0 +1,89 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+# Parity diff diagnostics: shows per-page text differences between
+# our rendered PDF and the reference PDF.
+#
+# Usage:
+#   bundle exec ruby scripts/parity_diff.rb              # all pages
+#   bundle exec ruby scripts/parity_diff.rb 5             # page 5 only
+#   bundle exec ruby scripts/parity_diff.rb 19 20 21      # pages 19-21
+
+require 'arrolio'
+require 'fileutils'
+
+module ParityDiff
+  OURS = File.expand_path('tmp/parity_check.pdf', Dir.pwd)
+  REFERENCE = File.expand_path('~/src/mn/mn-samples-oiml/_site/documents/r060/1/document.pdf')
+  FIXTURE = File.expand_path('~/src/mn/mn-samples-oiml/_site/documents/r060/1/document.presentation.xml')
+  SOURCE_DIR = File.expand_path('~/src/mn/mn-samples-oiml/sources/r060/1')
+  FLAVOR_DIR = File.expand_path('flavors/oiml', Dir.pwd)
+
+  def self.run(pages = nil)
+    render_ours unless File.exist?(OURS)
+    unless File.exist?(OURS) && File.exist?(REFERENCE)
+      warn 'PDFs not found. Run parity:check first.'
+      return
+    end
+
+    ours_pages = page_count(OURS)
+    ref_pages = page_count(REFERENCE)
+    target_pages = pages&.map(&:to_i) || (1..[ours_pages, ref_pages].max).to_a
+
+    target_pages.each do |page_num|
+      puts '=' * 70
+      puts "PAGE #{page_num}"
+      puts '=' * 70
+      ours_text = extract_text(OURS, page_num)
+      ref_text = extract_text(REFERENCE, page_num)
+      show_diff(ours_text, ref_text)
+      puts ''
+    end
+  end
+
+  def self.render_ours
+    require 'arrolio/config_driven_pipeline'
+    xml = File.read(FIXTURE)
+    FileUtils.mkdir_p(File.dirname(OURS))
+    Arrolio::ConfigDrivenPipeline.render(
+      xml, io: OURS, flavor_dir: FLAVOR_DIR,
+           input_path: FIXTURE, extra_image_dirs: [SOURCE_DIR]
+    )
+  end
+
+  def self.page_count(pdf)
+    `pdftotext "#{pdf}" - 2>/dev/null`.scan("\f").length + 1
+  rescue StandardError
+    0
+  end
+
+  def self.extract_text(pdf, page)
+    `pdftotext -f #{page} -l #{page} "#{pdf}" - 2>/dev/null`
+      .delete("\f").strip
+  end
+
+  def self.show_diff(ours, ref)
+    our_lines = ours.split("\n")
+    ref_lines = ref.split("\n")
+    max_lines = [our_lines.length, ref_lines.length].max
+
+    max_lines.times do |i|
+      our_line = our_lines[i] || ''
+      ref_line = ref_lines[i] || ''
+
+      if our_line == ref_line
+        puts "  #{our_line}"
+      elsif our_line.empty?
+        puts "+ #{ref_line}"  # missing from ours
+      elsif ref_line.empty?
+        puts "- #{our_line}"  # extra in ours
+      else
+        puts "~ OURS:  #{our_line}"
+        puts "  REF:   #{ref_line}"
+      end
+    end
+  end
+end
+
+pages = ARGV.empty? ? nil : ARGV
+ParityDiff.run(pages)

data/scripts/xsl_profiles/standoc.yml

@@ -85,6 +85,9 @@ skip_metadata_elements:
   - referenceTo
   - origin
   - source
+  - xref
+  - eref
+  - identifier
 
 skip_elements:
   - title
@@ -146,6 +149,8 @@ metadata_fields:
   docnumber: docnumber
   edition: edition
   revision_date: version/revision-date
+  version_text: version
+  part_number: bibdata/ext/structuredidentifier/project-number/@part
   title: "title[@type='main']"
   title_intro: "title[@type='title-intro']"
   title_main: "title[@type='title-main']"
@@ -162,9 +167,10 @@ cover_fields:
   - title_main
   - title_complementary
   - title_part
+  - title_part_prefix
 
 style_overrides:
-  body_margin_bottom: 8
+  body_margin_bottom: 0
   strong_font_name: "Times New Roman Bold"
   em_font_name: "Times New Roman Italic"
   identifier_font_name: "Times New Roman Italic"
@@ -215,4 +221,4 @@ cover_content:
     source: "{{docidentifier}} {{edition}}"
     style: cover_label
 
-header_template: "{{docidentifier}}: {{edition}}"
+header_template: "{{docidentifier}}: {{revision_date}}"

data/scripts/xsl_to_config.rb

@@ -14,6 +14,9 @@ module XslConfigGenerator
   end
 
   class Builder
+    # Border/padding allowance added to the XSL row min-height.
+    ROW_ALLOWANCE = 1.92
+
     def initialize(xsl_path, output_dir, profile_path)
       @xsl_path = File.expand_path(xsl_path)
       @output_dir = File.expand_path(output_dir)
@@ -76,8 +79,11 @@ module XslConfigGenerator
 
     def text_styles
       o = @profile['style_overrides'] || {}
+      body_style = style_from('root-style', 'clause_style')
+      body_style['margin_bottom'] = o['body_margin_bottom'] || 8
+      body_style['line_break'] = o['body_line_break'] if o['body_line_break']
       {
-        'body' => style_from('root-style', 'clause_style').merge('margin_bottom' => o['body_margin_bottom'] || 8),
+        'body' => body_style,
         **heading_styles,
         'note' => style_from('note-style').merge('parent' => 'body'),
         'termnote' => style_from('termnote-style').merge('parent' => 'body'),
@@ -110,6 +116,26 @@ module XslConfigGenerator
       }
     end
 
+    # Row geometry extracted from the flavor XSL: table-row-style's
+    # min-height (e.g. 8.3mm) plus ROW_ALLOWANCE, the border/padding
+    # allowance measured against mn2pdf output (the rendered pitch is
+    # ~1.9pt above the bare min-height). Cell padding and footnote
+    # size default to values calibrated against the reference PDF.
+    def table_geometry
+      min_height = @attribute_sets.dig('table-row-style', 'min-height')
+      min_height_mm = min_height&.gsub(/[^\d.]/, '')
+      min_row_height = if min_height_mm
+                         ((min_height_mm.to_f * 2.83464567) + ROW_ALLOWANCE).round(2)
+                       else
+                         0.0
+                       end
+      {
+        'min_row_height' => min_row_height,
+        'cell_padding' => 3.3,
+        'footnote_font_size' => 9.0
+      }
+    end
+
     def table_styles
       o = @profile['style_overrides'] || {}
       {
@@ -222,6 +248,7 @@ module XslConfigGenerator
         'xsl_templates' => @templates.select { |template| template['name'] },
         'page_sequences' => page_sequences,
         'cover_content' => @profile['cover_content'] || [],
+        'table' => table_geometry,
         'section' => {
           'heading_style' => '{{title_style_id}}',
           'body_style' => '{{style_id}}',

metadata

@@ -1,13 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: arrolio
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
 platform: ruby
 authors:
 - Ribose Inc.
+autorequire:
 bindir: exe
 cert_chain: []
-date: 1980-01-02 00:00:00.000000000 Z
+date: 2026-08-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: fontisan
@@ -29,6 +30,34 @@ dependencies:
     - - "<"
       - !ruby/object:Gem::Version
         version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: fontist
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: mml
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.4'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.4'
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
@@ -49,14 +78,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.3.0
+        version: '0.7'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.3.0
+        version: '0.7'
 - !ruby/object:Gem::Dependency
   name: rexml
   requirement: !ruby/object:Gem::Requirement
@@ -168,6 +197,33 @@ files:
 - TODO.complete/63-purge-hardcoded-vocabulary-from-generic-core.md
 - TODO.complete/64-selector-driven-adapter-specs.md
 - TODO.complete/66-semantic-content-types.md
+- TODO.complete/70-ttf-font-metrics-parity.md
+- TODO.complete/71-cover-layout-parity.md
+- TODO.complete/72-table-layout-parity.md
+- TODO.complete/73-toc-leaders-parity.md
+- TODO.complete/74-svg-image-rendering-parity.md
+- TODO.complete/75-mathml-formula-rendering-parity.md
+- TODO.complete/76-odd-even-page-templates-parity.md
+- TODO.complete/77-text-formatting-parity.md
+- TODO.complete/78-bibliography-formatting-parity.md
+- TODO.complete/79-line-breaking-parity.md
+- TODO.complete/80-parity-diff-harness-in-ci.md
+- TODO.complete/81-conditional-style-refinements.md
+- TODO.complete/82-semantic-presentation-dedup.md
+- TODO.complete/83-nested-list-support.md
+- TODO.complete/84-figure-svg-rendering.md
+- TODO.complete/85-locality-reference-formatting.md
+- TODO.complete/86-list-item-text-overflow.md
+- TODO.complete/87-odd-even-page-templates.md
+- TODO.complete/88-hyphenation-support.md
+- TODO.complete/89-table-rowspan.md
+- TODO.complete/90-mathml-stacked-layout.md
+- TODO.complete/91-parity-diff-diagnostics.md
+- TODO.complete/92-table-cell-height-parity.md
+- TODO.complete/93-figure-text-searchability.md
+- TODO.complete/94-fo-space-resolution.md
+- TODO.complete/95-title-header-placement.md
+- TODO.complete/96-pagination-drift-parity.md
 - TODO.complete/README.md
 - TODO.implementation/01-foundation.md
 - TODO.implementation/02-content-contract.md
@@ -281,6 +337,7 @@ files:
 - lib/arrolio/content/table.rb
 - lib/arrolio/content/term_entry.rb
 - lib/arrolio/data_dir.rb
+- lib/arrolio/embedded_block_extractor.rb
 - lib/arrolio/engine.rb
 - lib/arrolio/engine/cross_reference_registry.rb
 - lib/arrolio/engine/paged.rb
@@ -291,13 +348,17 @@ files:
 - lib/arrolio/flow_context.rb
 - lib/arrolio/flowable.rb
 - lib/arrolio/flowables.rb
+- lib/arrolio/flowables/figure_flowable.rb
 - lib/arrolio/flowables/footnote_marker_flowable.rb
+- lib/arrolio/flowables/group_flowable.rb
 - lib/arrolio/flowables/heading_flowable.rb
 - lib/arrolio/flowables/image_flowable.rb
 - lib/arrolio/flowables/list_flowable.rb
 - lib/arrolio/flowables/note_flowable.rb
 - lib/arrolio/flowables/page_break.rb
 - lib/arrolio/flowables/page_sequence_start.rb
+- lib/arrolio/flowables/positioned_block.rb
+- lib/arrolio/flowables/rotated_text.rb
 - lib/arrolio/flowables/spacer.rb
 - lib/arrolio/flowables/table_flowable.rb
 - lib/arrolio/flowables/text_flowable.rb
@@ -312,8 +373,16 @@ files:
 - lib/arrolio/font_metrics/afm_metrics.rb
 - lib/arrolio/font_metrics/registry.rb
 - lib/arrolio/font_metrics/true_type_metrics.rb
+- lib/arrolio/font_scanner.rb
 - lib/arrolio/frame.rb
 - lib/arrolio/generic_adapter.rb
+- lib/arrolio/generic_adapter/document_extraction.rb
+- lib/arrolio/generic_adapter/footnote_extraction.rb
+- lib/arrolio/generic_adapter/heading_extraction.rb
+- lib/arrolio/generic_adapter/inline_run_collection.rb
+- lib/arrolio/generic_adapter/list_conversion.rb
+- lib/arrolio/generic_adapter/metadata_extraction.rb
+- lib/arrolio/generic_adapter/table_conversion.rb
 - lib/arrolio/generic_flow_builder.rb
 - lib/arrolio/glyph_measurer.rb
 - lib/arrolio/harness.rb
@@ -330,6 +399,8 @@ files:
 - lib/arrolio/layout_spec/region.rb
 - lib/arrolio/layout_spec/scale_length.rb
 - lib/arrolio/logger.rb
+- lib/arrolio/math_ml.rb
+- lib/arrolio/math_ml/inline_run_extractor.rb
 - lib/arrolio/output.rb
 - lib/arrolio/output/page.rb
 - lib/arrolio/output/placed_box.rb
@@ -349,6 +420,7 @@ files:
 - lib/arrolio/style/registry.rb
 - lib/arrolio/table.rb
 - lib/arrolio/table/auto_layout.rb
+- lib/arrolio/table/grid.rb
 - lib/arrolio/text_direction.rb
 - lib/arrolio/text_layout.rb
 - lib/arrolio/text_layout/break_opportunity.rb
@@ -362,6 +434,8 @@ files:
 - lib/arrolio/version.rb
 - lib/arrolio/writing_mode.rb
 - script/smoke.rb
+- scripts/parity_check.rb
+- scripts/parity_diff.rb
 - scripts/write_content_extras.py
 - scripts/xsl_profiles/standoc.yml
 - scripts/xsl_to_config.rb
@@ -374,6 +448,7 @@ metadata:
   changelog_uri: https://github.com/arrolio/arrolio/blob/main/CHANGELOG.md
   bug_tracker_uri: https://github.com/arrolio/arrolio/issues
   rubygems_mfa_required: 'true'
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -388,7 +463,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 4.0.16
+rubygems_version: 3.5.22
+signing_key:
 specification_version: 4
 summary: FOP-like paged layout engine for Ruby — renders to PDF via Pdfrb
 test_files: []