pdfrb 0.1.0 → 0.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f000ed06c1fae85295e309ae1608acd27eac3c778d974e11aa94bb148e6670c4
-  data.tar.gz: 574f308269fc21fbb8f673da74fe24ff6c69d35db7b979bfd8f5fff98d40fdff
+  metadata.gz: 3b4392d590986dd2cf33d0596f355ea5cf05c32cf8bf0635ad069aa27bc1dfa4
+  data.tar.gz: c23d124eff4500baa4488ba6fa3c5353e37b191ae795708006aad46402f67758
 SHA512:
-  metadata.gz: 52475bfc6f98607fbabffd15154896dc2881e63411e9c6b0d86d1f25098bcab42b4f02a2f5a3ca774ef083fbff494830aa6041ff3776fcdaf5eec656681e27b0
-  data.tar.gz: 5717089d679437ccbf20c2fbc67a2bae9bdf156ecc268cb7fc3a75a4bf2136cc623e1e09f6268e25e157c726b0a10b9164cef319b87e2731b67f1f95aac92ff7
+  metadata.gz: efd253a06b41184caaa0f24dc3652a8216efe7bac7b926d8af3b645158fd467b1a3d2b2c12a5ab8c8c11da9c18abc4945934936e20e2b163008327d6a1421d8e
+  data.tar.gz: 3331dccbeff017114f54ce22cc36fe5977d20d497d889ebb4417602b9ca172f86564ce1af33913fba8b94e9376216904c8c85a4eaddf8adcf0b8fcfe82063592

data/.rubocop.yml

@@ -20,3 +20,8 @@ AllCops:
 
 # Project-specific: TSV files are data, not code; PDFs are binary.
 # Both are excluded via AllCops above. Local overrides go here.
+
+# Integration tests use string describes ("FOP-generated PDF reading")
+# because they exercise multiple classes through a real workflow.
+RSpec/DescribeClass:
+  Enabled: false

data/CHANGELOG.md

@@ -2,6 +2,67 @@
 
 All notable changes to the pdfrb gem will be documented in this file.
 
+## [0.1.1] — 2026-08-02
+
+### Housekeeping
+
+* **Layout/Composer extracted to sibling `arroolio` gem.** Pdfrb is now
+  pure PDF: bytes ↔ model. No page templates, no flows, no Knuth-Plass,
+  no tables, no SVG. Removed `lib/pdfrb/layout/`, `lib/pdfrb/composer.rb`,
+  `lib/pdfrb/layout.rb`, `spec/pdfrb/layout/`, `TODO.layout/`.
+* **Removed `rexml` runtime dependency** (was only needed for the FO
+  parser, which moved to Arroolio).
+* **Fixed all 12 rubocop offenses.** 0 offenses remaining. Disabled
+  `RSpec/DescribeClass` (legitimate string describes in integration tests).
+* **Added SimpleCov** (opt-in via `COVERAGE=1` env var). Current line
+  coverage: **84.5%**. Grouped by Source / Model / Filters / Content /
+  Font / Encryption / Tasks / CLI / Document.
+* **Replaced 3 `pending` specs with `skip`** — clearer exit semantics
+  for strict CI runs.
+* **Fixed `Model::Cos::Stream#as_parms_list`** — Hash parms now
+  correctly wraps to `[parms]` instead of `Array(parms)` which
+  produced `[[:k, :v], ...]`. Bug was hidden by tests that didn't
+  exercise DecodeParms as a Hash through the Stream facade.
+* **Renamed CMap format dispatchers** — `parse_format_4` →
+  `parse_format_four`, etc. (rubocop `Naming/VariableNumber`).
+* **README/CLAUDE.md** updated to reflect pure-PDF scope; layout
+  concerns documented as living in `arroolio`.
+
+### Verified
+
+* 503 examples, 0 failures, 3 pending (conformance specs awaiting
+  fixture corpus).
+* 0 rubocop offenses.
+* `gem build pdfrb.gemspec` produces `pdfrb-0.1.1.gem`.
+* End-to-end round-trip: build PDF → write → read → extract text →
+  matches.
+
+## [0.1.0] — 2026-08-02
+
+### Initial release
+
+Pure-Ruby PDF library: byte-level reader, Arlington-model-driven typed
+domain model, and serializer.
+
+* Source: bytes → tokens → COS graph.
+* Model: typed COS values + Type::* semantics, sourced from vendored
+  Arlington PDF Model TSVs (ISO 32000-2:2020).
+* Filter pipeline: FlateDecode, ASCII-Hex, ASCII-85, LZW, RunLength,
+  CCITTFax, DCT, JPX, JBIG2, Crypt.
+* Content: 52 content-stream operators + Canvas drawing API.
+* Encryption: RC4 (pure Ruby), AES (OpenSSL), StandardSecurityHandler
+  (V1-V6 / R2-R6).
+* Font machinery: AFM parser, 5 encoding tables, CMap parser, TrueType
+  file parser (head/hhea/hmtx/cmap/OS-2), Type1 metrics.
+* Image loaders: JPEG, PNG, PDF page import.
+* Tasks: ExtractText (with /ToUnicode CMap), ExtractImages, Merge,
+  Optimize.
+* CLI: version, info, tree, merge, extract-text/images, encrypt,
+  decrypt, optimize, form.
+* Conformance: PDF/A + PDF/UA rule subsets.
+* Round-trip property tested against ISO 32000-2 Annex H examples
+  (12 PDFs).
+
 ## [Unreleased]
 
 ### Added — 2026-08-01 (layout engine session)

data/Gemfile

@@ -11,3 +11,5 @@ gem "rubocop", "~> 1.75"
 gem "rubocop-performance", "~> 1.23"
 gem "rubocop-rake", "~> 0.7"
 gem "rubocop-rspec", "~> 3.5"
+
+gem "simplecov", require: false, group: :test

data/lib/pdfrb/font/true_type/cmap.rb

@@ -74,10 +74,10 @@ module Pdfrb
         def read_format_header
           @format = u16(@subtable_offset)
           case @format
-          when 0 then parse_format_0
-          when 4 then parse_format_4
-          when 6 then parse_format_6
-          when 12 then parse_format_12
+          when 0 then parse_format_zero
+          when 4 then parse_format_four
+          when 6 then parse_format_six
+          when 12 then parse_format_twelve
           else
             @format = nil
           end
@@ -85,27 +85,27 @@ module Pdfrb
 
         def lookup(unicode)
           case @format
-          when 0 then lookup_format_0(unicode)
-          when 4 then lookup_format_4(unicode)
-          when 6 then lookup_format_6(unicode)
-          when 12 then lookup_format_12(unicode)
+          when 0 then lookup_format_zero(unicode)
+          when 4 then lookup_format_four(unicode)
+          when 6 then lookup_format_six(unicode)
+          when 12 then lookup_format_twelve(unicode)
           else 0
           end
         end
 
         # Format 0: 256-entry byte table.
-        def parse_format_0
+        def parse_format_zero
           @f0_glyph_ids = (0..255).map { |i| u8(@subtable_offset + 6 + i) }
         end
 
-        def lookup_format_0(unicode)
+        def lookup_format_zero(unicode)
           return 0 unless unicode < 256
 
           @f0_glyph_ids[unicode]
         end
 
         # Format 4: segment mapping. BMP only.
-        def parse_format_4
+        def parse_format_four
           seg_count_x2 = u16(@subtable_offset + 6)
           seg_count = seg_count_x2 / 2
           end_codes_off = @subtable_offset + 14
@@ -123,7 +123,7 @@ module Pdfrb
           }
         end
 
-        def lookup_format_4(unicode)
+        def lookup_format_four(unicode)
           return 0 unless @f4
 
           seg = @f4
@@ -154,7 +154,7 @@ module Pdfrb
         end
 
         # Format 6: trimmed table.
-        def parse_format_6
+        def parse_format_six
           first = u16(@subtable_offset + 6)
           count = u16(@subtable_offset + 8)
           @f6 = {
@@ -164,7 +164,7 @@ module Pdfrb
           }
         end
 
-        def lookup_format_6(unicode)
+        def lookup_format_six(unicode)
           return 0 unless @f6
 
           idx = unicode - @f6[:first_code]
@@ -174,7 +174,7 @@ module Pdfrb
         end
 
         # Format 12: sparse coverage, full Unicode.
-        def parse_format_12
+        def parse_format_twelve
           num_groups = u32(@subtable_offset + 12)
           @f12 = []
           num_groups.times do |i|
@@ -187,7 +187,7 @@ module Pdfrb
           end
         end
 
-        def lookup_format_12(unicode)
+        def lookup_format_twelve(unicode)
           return 0 unless @f12
 
           # Binary search for the group covering this codepoint.

data/lib/pdfrb/model/cos/stream.rb

@@ -87,7 +87,7 @@ module Pdfrb
           when ::Array then parms
           when Pdfrb::Model::PdfArray then parms.value
           when ::Hash then [parms]
-          else [parms]
+          else []
           end
         end
       end

data/lib/pdfrb/version.rb

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

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pdfrb
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
 platform: ruby
 authors:
 - Ribose Inc.