idml 0.4.9 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: bf684927e9227982c1773b71a6697b40ed9d93263eb1a272e413008ba6d2009b
-  data.tar.gz: 4fbd6e8ab4df4ba8281fb5353df9474348fe77b021703118c63c3f5d5a9f5ca1
+  metadata.gz: '09c5f631233897e7f1e18519b1031c1c87092a1e3ddffdc353bf2e121c47b15b'
+  data.tar.gz: 8c0b965da67d83e30f3b7002be6bbabe1dffec7d1a3557979fe4cdfbce99dd54
 SHA512:
-  metadata.gz: 61d12e84a29ccefd212d6f09221eee09045b8ae18c8736bab98fea27cfdc0073151e8ffa53eadf18508af7bf104ff44e171b98f2fdd8e6d96019191792d594c9
-  data.tar.gz: 26f5541332df26f45f169da739c7c47b13f483a1c42c690c85867e8f3151522b0440d41bc7b502e680ff79ab00ac09ad791f9308cf9a0d7d16acb3a5ae87567c
+  metadata.gz: 7675a8a5b799b1a2b420f74b26faec4f6630b55cbf7ca831201085f99947d9ee31d1380fe5a12039427e643988ec84228738fc92dd9d925423aa36822815a774
+  data.tar.gz: 266b6c589b715d727460eba5064dde878f104b079e3da2ae7a0b31c911492cd88d75d18946ff3536d358c12359bf4b4069592dba7ac0c4b5eb42a1dbebde0544

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    idml (0.4.9)
+    idml (0.5.0)
       bigdecimal
       lutaml-model (~> 0.8.18)
       pdfrb
@@ -183,7 +183,7 @@ CHECKSUMS
   ffi (1.17.4-x86_64-darwin) sha256=aa70390523cf3235096cf64962b709b4cfbd5c082a2cb2ae714eb0fe2ccda496
   ffi (1.17.4-x86_64-linux-gnu) sha256=9d3db14c2eae074b382fa9c083fe95aec6e0a1451da249eab096c34002bc752d
   ffi (1.17.4-x86_64-linux-musl) sha256=3fdf9888483de005f8ef8d1cf2d3b20d86626af206cbf780f6a6a12439a9c49e
-  idml (0.4.9)
+  idml (0.5.0)
   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/89-deep-audit-idml-vs-indesign.md

@@ -1,15 +1,22 @@
 # TODO PDF 89: Deep audit — idml-generated PDF vs InDesign PDF
 
-## Status: COMPLETE (audit); structural differences documented
+## Status: PARTIAL — font selection fixed; image bloat remains
 
 ## TL;DR
 
-**No** — the generated PDF is not byte-identical to the InDesign
-output. InDesign produces ~100KB, the idml render produces ~2.2MB
-(22x larger). The visual content is structurally similar but
-rendered through a different font pipeline, font subsetting
-strategy, image embedding path, and color management. Below is a
-side-by-side audit.
+**No** — the generated PDF is still not identical to InDesign's
+output, but the **font selection gap is closed** as of v0.5.0.
+
+After the font fix (FontSetup now prefers Regular weight over
+first-in-family):
+- Font: `MinionPro-Regular` (matches InDesign) — was
+  `MinionPro-BoldCn`.
+- File size: still ~2.2MB (the image bloat remains).
+
+The remaining 88% of the file size is the embedded GenAI JPEG
+(1,937,556 bytes embedded raw via DCTDecode). InDesign downsamples
+to ~12KB. Closing this gap requires pure-Ruby JPEG decode + resize
++ re-encode (TODO 91).
 
 ## File-level comparison (`sample-with-table-more`)
 

data/lib/idml/render/font_setup.rb

@@ -16,6 +16,12 @@ module Idml
     class FontSetup
       DEFAULT_FONT = Render::DEFAULT_FONT
 
+      # Style names treated as the "Regular" default for body text,
+      # in priority order. Used to pick the right font from a family
+      # when no per-run `AppliedFont` is specified — matches
+      # InDesign's default-text-font behavior.
+      REGULAR_STYLE_NAMES = %w[Regular Normal Book Roman].freeze
+
       def initialize(package:, font_search_paths: nil)
         @package = package
         @font_search_paths = font_search_paths
@@ -57,6 +63,10 @@ module Idml
       end
 
       def find_font_file(family)
+        regular = find_regular_font(family)
+        return regular if regular
+
+        # Fall back to the first non-missing font.
         family.font.each do |font|
           next unless font.post_script_name
           next if font.status == "Missing"
@@ -67,6 +77,28 @@ module Idml
         nil
       end
 
+      # Pick the first "Regular" / "Normal" / "Book" / "Roman" font
+      # in the family. This matches InDesign's default body-text
+      # behavior, which prefers Regular weight over the first font
+      # listed in the family.
+      def find_regular_font(family)
+        family.font.each do |font|
+          next unless font.post_script_name
+          next if font.status == "Missing"
+          next unless regular_style?(font.font_style_name)
+
+          path = resolver.find_by_ps_name(font.post_script_name)
+          return path if path
+        end
+        nil
+      end
+
+      def regular_style?(style_name)
+        return false unless style_name
+
+        REGULAR_STYLE_NAMES.any?(style_name)
+      end
+
       def resolver
         @resolver ||= Pdfrb::FontResolver.new(
           search_paths: @font_search_paths || Pdfrb::FontResolver::DEFAULT_SEARCH_PATHS,

data/lib/idml/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Idml
-  VERSION = "0.4.9"
+  VERSION = "0.5.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: idml
 version: !ruby/object:Gem::Version
-  version: 0.4.9
+  version: 0.5.0
 platform: ruby
 authors:
 - Ribose