idml 0.9.7 → 0.9.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0d49d9954838f3326eab4e65e2915eab9cd18a526ce7c4dd58669e6dacb8910e
-  data.tar.gz: 56713c3d26980c24c6baf8d080543cd2471aef5dea4ca83c33be82f73fe2e83e
+  metadata.gz: 29f97721ebdd63304b8c879eaa45764906dfa40b85363688aa9d860ccdd6f62c
+  data.tar.gz: 439a3e3454be081957617ce5107ae735a47d56c4dc206104d3e483c5a20db669
 SHA512:
-  metadata.gz: d52298b420e04ae5c4b8292e01d951eb23d03d4e01357f463111477e842aea9dd89f6e162a88ad05dd50fa8b721faf6522f891eb66e3405dd6207769f7a9bfe8
-  data.tar.gz: 1d7f89c274a8aac75868064826567901fbc0503ead631953fc7b24eaa282e0f1d8870d2e33f1dc6e81c834b4e3c00fc4b2b465b1a12cc349484b0e653628e63f
+  metadata.gz: 0c669bcf817d1e2b8ab74c116e3a0e472b8ca5529fdfeba4f0adb85d7f1ddb78da5d422c63907cbe68f4a7c381ce5862d17b674063070bce64e9664584159b97
+  data.tar.gz: b427dc2a77703a71074fc541eb8eea36485dc78607dea9faa8f13d3ca69c70e013a749374ef8abca81057bdf5e7563f6717bea30e45ad967a5836ead3e325d6a

data/TODO.pdf/125-script-spacing.md

@@ -0,0 +1,22 @@
+# TODO PDF 125: CJK/Latin automatic script spacing (mojikumi subset)
+
+## Status: COMPLETE — implemented 2026-08-20
+
+## What was done
+
+- `TextEngine::CjkLayout.apply_script_spacing` widens the leading
+  glyph by an eighth em at every CJK ↔ ASCII alphanumeric boundary
+  — InDesign's default inter-script auto spacing (a mojikumi
+  behavior).
+- Wired inside `TextEngine::Shaper#shape`, so every shaping path
+  (horizontal frame text, footnotes, ruby, vertical columns)
+  applies it uniformly — one integration point, no per-caller
+  changes.
+- Punctuation neighbors are ignored (only letters/digits form
+  boundaries).
+
+## Remaining from TODO 13
+
+Class-based mojikumi (per-pair punctuation compression tables,
+line-end punctuation hanging beyond half-em) remains a documented
+stretch goal.

data/TODO.pdf/126-part-cache.md

@@ -0,0 +1,22 @@
+# TODO PDF 126: Package#part memoization
+
+## Status: COMPLETE — implemented 2026-08-20
+
+## Problem
+
+`Package#part(name)` re-read and re-parsed the zip entry on every
+call. Rendering resolves `story_by_id` per frame plus preferences
+(Footnote.option), styles, and graphics repeatedly — each lookup
+decompressed and re-parsed the same XML.
+
+## What was done
+
+Parsed parts are memoized in a per-`Package` hash
+(`parse_part` remains the single read+parse path; `each_part` /
+`read_part` stay uncached raw reads for round-trip byte fidelity).
+
+## Acceptance criteria
+
+- [x] Repeated `part(name)` calls return the same object.
+- [x] Different parts do not share objects.
+- [x] Whole-package round-trip specs unchanged (raw reads).

data/TODO.pdf/13-cjk-text-layout.md

@@ -20,9 +20,11 @@ kinsoku shori, ruby annotations).
   frame width (previously they overflowed as one long line) — this
   also fixes horizontal CJK wrapping.
 
-Remaining stretch goals: tate-chu-yoko, mojikumi, Latin rotation in
-vertical mode, vertical ruby placement. See
-`lib/idml/text_engine/cjk_layout.rb` and
+2026-08-20 completions: tate-chu-yoko (TODO 124), Latin rotation
+and vertical ruby (TODO 122), CJK/Latin automatic script spacing
+(TODO 125, a mojikumi subset wired into Shaper). The remaining
+stretch goal is full class-based mojikumi (per-pair punctuation
+compression tables). See `lib/idml/text_engine/cjk_layout.rb` and
 `lib/idml/text_engine/vertical_text_layout.rb`.
 
 ## Progress 2026-08-17

data/lib/idml/package.rb

@@ -134,13 +134,23 @@ module Idml
     # Returns a typed part instance for `name` when a class is registered
     # for that file pattern (e.g. Designmap for designmap.xml). Falls
     # back to Parts::Raw — a lossless XML wrapper — for unmodeled parts.
+    # Parsed parts are memoized: rendering resolves stories,
+    # preferences, and styles repeatedly (per frame), and each
+    # un-memoized read would re-decompress and re-parse the zip
+    # entry.
     def part(name)
+      @part_cache ||= {}
+      @part_cache[name] ||= parse_part(name)
+    end
+
+    def parse_part(name)
       xml = read_part(name)
       klass = Idml::Parts.class_for(name)
       return Idml::Parts::Raw.from_xml(xml) unless klass
 
       klass.from_xml(xml)
     end
+    private :parse_part
 
     def each_part
       return enum_for(:each_part) unless block_given?

data/lib/idml/text_engine/cjk_layout.rb

@@ -7,6 +7,38 @@ module Idml
     module CjkLayout
       module_function
 
+      # Mojikumi subset: automatic inter-script spacing — an eighth
+      # em is inserted between adjacent CJK and ASCII alphanumeric
+      # glyphs (widenning the leading glyph of each pair), matching
+      # InDesign's default CJK/Latin auto spacing.
+      SCRIPT_SPACING_EM = 0.125
+
+      def apply_script_spacing(glyphs, size)
+        spacing = size * SCRIPT_SPACING_EM
+        (0...(glyphs.length - 1)).each do |index|
+          leading = glyphs[index]
+          following = glyphs[index + 1]
+          next unless script_boundary?(leading.codepoint,
+                                       following.codepoint)
+
+          leading.width += spacing
+        end
+        glyphs
+      end
+
+      # True when exactly one of the pair is CJK and the other is
+      # an ASCII letter or digit.
+      def script_boundary?(left, right)
+        (cjk?(left) && ascii_alnum?(right)) ||
+          (ascii_alnum?(left) && cjk?(right))
+      end
+
+      def ascii_alnum?(codepoint)
+        (0x30..0x39).cover?(codepoint) ||
+          (0x41..0x5A).cover?(codepoint) ||
+          (0x61..0x7A).cover?(codepoint)
+      end
+
       CJK_RANGES = [
         0x3000..0x303F, # CJK Symbols and Punctuation
         0x3040..0x309F, # Hiragana

data/lib/idml/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Idml
-  VERSION = "0.9.7"
+  VERSION = "0.9.8"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: idml
 version: !ruby/object:Gem::Version
-  version: 0.9.7
+  version: 0.9.8
 platform: ruby
 authors:
 - Ribose
@@ -183,6 +183,8 @@ files:
 - TODO.pdf/122-vertical-latin-ruby.md
 - TODO.pdf/123-keep-options.md
 - TODO.pdf/124-tatechuyoko-vertical.md
+- TODO.pdf/125-script-spacing.md
+- TODO.pdf/126-part-cache.md
 - TODO.pdf/13-cjk-text-layout.md
 - TODO.pdf/14-page-item-element-models.md
 - TODO.pdf/15-wire-spread-children.md