idml 0.5.3 → 0.5.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2956308b8fe6f09356fea8016d6a0b24591886d2d4b04071ddfaff55256f0200
-  data.tar.gz: 424536bb8501ceb97d6654c2b61429e4294104c3c75a77706ba9b8157760c9ab
+  metadata.gz: 3e04ef841e6a31cca3d3250835f8b9c7bbd985f9f3c101868258095a1191cb72
+  data.tar.gz: 131af1981ab67c2232024cc4eb7ddb912d7e7d813bd8fb144eecea303cc90af5
 SHA512:
-  metadata.gz: d85d3a00384ed297258957fece3cc099312205819810455b678b5b6db48d05c0b67507b787c7f3cd0d2e9f8790a58e44493fef8420a7ec08b3fd20c4974bc6f6
-  data.tar.gz: f4f8a104afeefc576fd7246eb6d87107232881de180883ffe0cbaa617b7dbb1216feff20e92b4f374cad84a4aeed0ef0e3944c5cc3180d02bd96cd9948d45d5f
+  metadata.gz: 5461d74817f4472d927fb5659cc2fe5bfc4c7cc623c20d41914314de432805e99c716d8ee32b09315785e1309c71a9bb1eeb17c507538fbd17897ba90ab5578b
+  data.tar.gz: 2d59931db19a7666eea95e73edc67a17a6a02951c06eb9e9c942aa5f8a59cef6699a77bdd56fd926b4a799909e246aa965c6b1293cdbf48e12c0d83652540a1f

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    idml (0.5.3)
+    idml (0.5.4)
       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 (0.5.3)
+  idml (0.5.4)
   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/92-xref-entry-byte-count.md

@@ -1,6 +1,6 @@
 # TODO PDF 92: XRef entry byte-count compliance (21 vs 20 bytes)
 
-## Status: IDENTIFIED — pdfrb upstream bug
+## Status: FIXED (pdfrb 0.6.0, issue claricle/pdfrb#59)
 
 ## Problem
 

data/TODO.pdf/93-per-run-font-resolution.md

@@ -0,0 +1,67 @@
+# TODO PDF 93: Per-run font resolution from CharacterStyleRange
+
+## Status: PLANNED (last major rendering fidelity gap)
+
+## Problem
+
+All text in the rendered PDF uses the same font (the document's
+default Regular weight). Real IDML documents specify per-run fonts
+via `CharacterStyleRange#AppliedCharacterStyle` → `CharacterStyle`
+→ `Properties/AppliedFont` (family name) + style attributes.
+
+For the `sample-with-table-more` fixture, all text happens to use
+`[No character style]` with `NormalParagraphStyle`, so the default
+Regular weight is correct. But other IDML documents have bold,
+italic, and mixed-family text that our renderer can't express.
+
+## What needs to happen
+
+1. **StyleResolver enhancement**: extract `applied_font` from each
+   CSR via its `AppliedCharacterStyle` reference. The chain is:
+   - CSR `AppliedCharacterStyle="CharacterStyle/$ID/bold_text"`
+   - → CharacterStyle `Self="CharacterStyle/$ID/bold_text"`
+   - → CharacterStyle `Properties/AppliedFont` → family name
+   - → CharacterStyle `FontStyle` → style (Bold, Italic, etc.)
+   - → Fonts.xml lookup → PostScriptName
+   - → Pdfrb::FontResolver → file path → pdfrb font resource
+
+2. **Multi-font registration**: FontSetup registers each distinct
+   font used by any CSR, not just the document default. Returns a
+   map of `applied_font_ref → pdfrb_symbol`.
+
+3. **StyledRun enhancement**: carries the resolved pdfrb font
+   resource Symbol (not just the PS name string).
+
+4. **TextFrameRenderer**: uses `run.font_resource` for each
+   `canvas.text` / `canvas.text_rich` call instead of the single
+   `context.font_ps_name`.
+
+5. **TableRenderer**: same — per-cell font resolution from the
+   cell's CSR.
+
+## Scope
+
+- For documents with uniform styling (like the test fixture), no
+  visible change — the default Regular font is already correct.
+- For documents with bold/italic/mixed-family runs, text would
+  render in the correct font per run.
+- Font subsetting becomes per-font: each registered font gets its
+  own used-codepoint set and subset.
+
+## Dependencies
+
+- pdfrb 0.6.0 with IO-based font loading (DONE, v0.5.3).
+- CharacterStyle element model (exists — verify AppliedFont
+  extraction from Properties).
+- FontReferenceResolver (exists — already builds family → PSName
+  lookup from Fonts.xml).
+
+## Acceptance criteria
+
+- [ ] StyledRun carries a resolved pdfrb font resource Symbol.
+- [ ] CSR with `AppliedCharacterStyle` referencing a bold style
+      renders in bold font.
+- [ ] CSR with no applied style renders in the document default.
+- [ ] Multiple fonts embedded when document uses multiple families.
+- [ ] Font subsetting works per-font (each font subsetted to its
+      own used codepoints).

data/lib/idml/render.rb

@@ -2,6 +2,16 @@
 
 require "pdfrb"
 
+# pdfrb 0.6.0 autoloads OptContentUsage from opt_content_ext.rb but
+# that file doesn't define it, causing eager_load! to crash.
+# Trigger the autoload (catching the failure) then define a stub.
+begin
+  Pdfrb::Model::Type::OptContentUsage
+rescue NameError
+  Pdfrb::Model::Type.const_set(:OptContentUsage,
+                               Class.new(Pdfrb::Model::Cos::Dictionary))
+end
+
 module Idml
   module Render
     autoload :ColorHelper,         "#{__dir__}/render/color_helper"

data/lib/idml/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Idml
-  VERSION = "0.5.3"
+  VERSION = "0.5.4"
 end

data/lib/idml.rb

@@ -1,6 +1,7 @@
 # frozen_string_literal: true
 
 require "lutaml/model"
+require "pdfrb"
 require "zip"
 require "fileutils"
 require "tempfile"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: idml
 version: !ruby/object:Gem::Version
-  version: 0.5.3
+  version: 0.5.4
 platform: ruby
 authors:
 - Ribose
@@ -218,6 +218,7 @@ files:
 - TODO.pdf/90-per-run-font-resolution.md
 - TODO.pdf/91-image-downsampling.md
 - TODO.pdf/92-xref-entry-byte-count.md
+- TODO.pdf/93-per-run-font-resolution.md
 - TODO.pdf/README.md
 - exe/idml
 - idml.gemspec