acro_that 1.0.3 → 1.0.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 31a0652c9e6d834244b0a296b017d82a1a77ef07666c3e4e1b482b622e1c80cd
-  data.tar.gz: 3af1db0522ab1a9a754afb6c1b297184c49ed05547093611d6f3dce838b1e782
+  metadata.gz: 8983cb8f5bef4f8085baf807e7fea9b8efc11d0d25efc3cbcd25b54a8e938af3
+  data.tar.gz: 646674f34985529556d9b36ee91351aa7fd25a3e0ca561814fa9ae2274da7653
 SHA512:
-  metadata.gz: f2265b5ee6e1ae3ffd9421b0c3944bbe59c52f4e4d1c437a0a555764a36aa7ed23f8c7b0189eb4b7c4aa3703889f7eb58e8cd44232826060fc4bc7599b84504a
-  data.tar.gz: 9c90530b5041bd419f28a7c4f9f82829897bbb0a83bb2527ab93e0c90af862ddeed7f4a070f133daf1ab0a149faabf1b7b517c8bf5e11f5719f36050804d9ec3
+  metadata.gz: f1827af100fbb441cd52015c146abc2522852c3c57f4cdcdec32b382c91db0896fef918a101bcd65ced3167ad201eed136c279baa4c59139318f41cfc6db5116
+  data.tar.gz: 877931eced47139862b7966fd9b73307532e075e218538e7fda02bd768a6a13354ed0e5fefe9481d2b1af3d756a7a81a1f129f34f42eb80b4c19031d8906e913

data/CHANGELOG.md

@@ -5,6 +5,16 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.0.4] - 2025-11-12
+
+### Fixed
+- Fixed `Encoding::CompatibilityError` when processing field values with special characters (e.g., "María", "José"). Special characters are now automatically transliterated to ASCII equivalents (e.g., "María" → "Maria") before encoding to PDF format, ensuring compatibility with PDF string encoding requirements.
+
+### Added
+- Added I18n gem as a runtime dependency for transliteration support
+- Added `DictScan.transliterate_to_ascii` method to convert special characters to ASCII equivalents
+- Automatic transliteration for text field values and radio button field export values
+
 ## [0.1.8] - 2025-11-04
 
 ### Fixed

data/Gemfile.lock

@@ -1,8 +1,9 @@
 PATH
   remote: .
   specs:
-    acro_that (1.0.2)
+    acro_that (1.0.3)
       chunky_png (~> 1.4)
+      i18n (~> 1.14)
 
 GEM
   remote: https://rubygems.org/
@@ -10,7 +11,10 @@ GEM
     ast (2.4.3)
     chunky_png (1.4.0)
     coderay (1.1.3)
+    concurrent-ruby (1.3.5)
     diff-lcs (1.6.2)
+    i18n (1.14.7)
+      concurrent-ruby (~> 1.0)
     json (2.15.2)
     language_server-protocol (3.17.0.5)
     lint_roller (1.1.0)

data/acro_that.gemspec

@@ -28,6 +28,7 @@ Gem::Specification.new do |spec|
   spec.require_paths = ["lib"]
 
   spec.add_runtime_dependency "chunky_png", "~> 1.4"
+  spec.add_runtime_dependency "i18n", "~> 1.14"
   spec.add_development_dependency "rspec", "~> 3.0"
   spec.add_development_dependency "pry", "~> 0.14"
   spec.add_development_dependency "rubocop", "~> 1.50"

data/lib/acro_that/actions/update_field.rb

@@ -591,23 +591,23 @@ module AcroThat
 
         # Calculate scale to maximize size while maintaining aspect ratio
         # Use the smaller dimension to ensure it fits
-        scale = [width, height].min * 0.85  # Use 85% of the smaller dimension
-        
+        scale = [width, height].min * 0.85 # Use 85% of the smaller dimension
+
         # Calculate checkmark dimensions
         check_width = scale
         check_height = scale
-        
+
         # Center the checkmark in the box
         offset_x = (width - check_width) / 2
         offset_y = (height - check_height) / 2
-        
+
         # Calculate actual coordinates
-        check_x1 = offset_x + norm_x1 * check_width
-        check_y1 = offset_y + norm_y1 * check_height
-        check_x2 = offset_x + norm_x2 * check_width
-        check_y2 = offset_y + norm_y2 * check_height
-        check_x3 = offset_x + norm_x3 * check_width
-        check_y3 = offset_y + norm_y3 * check_height
+        check_x1 = offset_x + (norm_x1 * check_width)
+        check_y1 = offset_y + (norm_y1 * check_height)
+        check_x2 = offset_x + (norm_x2 * check_width)
+        check_y2 = offset_y + (norm_y2 * check_height)
+        check_x3 = offset_x + (norm_x3 * check_width)
+        check_y3 = offset_y + (norm_y3 * check_height)
 
         content_stream = "q\n"
         # Draw square border around field bounds

data/lib/acro_that/dict_scan.rb

@@ -4,6 +4,26 @@ module AcroThat
   module DictScan
     module_function
 
+    # Configure I18n for transliteration (disable locale enforcement)
+    I18n.config.enforce_available_locales = false
+
+    # Transliterate a string to ASCII, converting special characters to their ASCII equivalents
+    # Example: "María Valentina" -> "Maria Valentina"
+    def transliterate_to_ascii(str)
+      return str unless str.is_a?(String)
+
+      # Ensure the string is in UTF-8 encoding
+      utf8_str = str.encode("UTF-8", invalid: :replace, undef: :replace)
+
+      # Use I18n transliteration to convert to ASCII
+      begin
+        I18n.transliterate(utf8_str, locale: :en, replacement: "")
+      rescue StandardError
+        # Fallback: if transliteration fails, try to encode to ASCII with replacements
+        utf8_str.encode("ASCII", invalid: :replace, undef: :replace)
+      end
+    end
+
     # --- low-level string helpers -------------------------------------------------
 
     def strip_stream_bodies(pdf)
@@ -118,10 +138,15 @@ module AcroThat
       when Symbol
         "/#{val}"
       when String
-        if val.ascii_only?
-          "(#{val.gsub(/([\\()])/, '\\\\\\1').gsub("\n", '\\n')})"
+        # Transliterate special characters to ASCII to avoid encoding issues
+        ascii_val = transliterate_to_ascii(val)
+
+        if ascii_val.ascii_only?
+          "(#{ascii_val.gsub(/([\\()])/, '\\\\\\1').gsub("\n", '\\n')})"
         else
-          utf16 = val.encode("UTF-16BE")
+          # Ensure string is in UTF-8 before encoding to UTF-16BE
+          utf8_str = ascii_val.encode("UTF-8", invalid: :replace, undef: :replace)
+          utf16 = utf8_str.encode("UTF-16BE")
           bytes = "\xFE\xFF#{utf16}"
           "<#{bytes.unpack1('H*')}>"
         end
@@ -138,8 +163,11 @@ module AcroThat
       # Remove leading / if present (we'll add it back)
       name_str = name_str[1..] if name_str.start_with?("/")
 
+      # Transliterate special characters to ASCII to avoid encoding issues
+      ascii_name = transliterate_to_ascii(name_str)
+
       # Encode special characters as hex
-      encoded = name_str.each_byte.map do |byte|
+      encoded = ascii_name.each_byte.map do |byte|
         char = byte.chr
         # PDF name special characters that need hex encoding: # ( ) < > [ ] { } / %
         # Also encode control characters (0x00-0x1F, 0x7F) and non-ASCII (0x80-0xFF)

data/lib/acro_that/fields/checkbox.rb

@@ -99,23 +99,23 @@ module AcroThat
 
         # Calculate scale to maximize size while maintaining aspect ratio
         # Use the smaller dimension to ensure it fits
-        scale = [width, height].min * 0.85  # Use 85% of the smaller dimension
-        
+        scale = [width, height].min * 0.85 # Use 85% of the smaller dimension
+
         # Calculate checkmark dimensions
         check_width = scale
         check_height = scale
-        
+
         # Center the checkmark in the box
         offset_x = (width - check_width) / 2
         offset_y = (height - check_height) / 2
-        
+
         # Calculate actual coordinates
-        check_x1 = offset_x + norm_x1 * check_width
-        check_y1 = offset_y + norm_y1 * check_height
-        check_x2 = offset_x + norm_x2 * check_width
-        check_y2 = offset_y + norm_y2 * check_height
-        check_x3 = offset_x + norm_x3 * check_width
-        check_y3 = offset_y + norm_y3 * check_height
+        check_x1 = offset_x + (norm_x1 * check_width)
+        check_y1 = offset_y + (norm_y1 * check_height)
+        check_x2 = offset_x + (norm_x2 * check_width)
+        check_y2 = offset_y + (norm_y2 * check_height)
+        check_x3 = offset_x + (norm_x3 * check_width)
+        check_y3 = offset_y + (norm_y3 * check_height)
 
         content_stream = "q\n"
         # Draw square border around field bounds

data/lib/acro_that/fields/radio.rb

@@ -176,23 +176,23 @@ module AcroThat
 
         # Calculate scale to maximize size while maintaining aspect ratio
         # Use the smaller dimension to ensure it fits
-        scale = [width, height].min * 0.85  # Use 85% of the smaller dimension
-        
+        scale = [width, height].min * 0.85 # Use 85% of the smaller dimension
+
         # Calculate checkmark dimensions
         check_width = scale
         check_height = scale
-        
+
         # Center the checkmark in the box
         offset_x = (width - check_width) / 2
         offset_y = (height - check_height) / 2
-        
+
         # Calculate actual coordinates
-        check_x1 = offset_x + norm_x1 * check_width
-        check_y1 = offset_y + norm_y1 * check_height
-        check_x2 = offset_x + norm_x2 * check_width
-        check_y2 = offset_y + norm_y2 * check_height
-        check_x3 = offset_x + norm_x3 * check_width
-        check_y3 = offset_y + norm_y3 * check_height
+        check_x1 = offset_x + (norm_x1 * check_width)
+        check_y1 = offset_y + (norm_y1 * check_height)
+        check_x2 = offset_x + (norm_x2 * check_width)
+        check_y2 = offset_y + (norm_y2 * check_height)
+        check_x3 = offset_x + (norm_x3 * check_width)
+        check_y3 = offset_y + (norm_y3 * check_height)
 
         content_stream = "q\n"
         # Draw checkmark only (no border)

data/lib/acro_that/pdf_writer.rb

@@ -58,12 +58,12 @@ module AcroThat
       while current_obj <= max_obj_num
         # Find next existing object
         next_existing = sorted.find { |num, _gen, _offset| num >= current_obj }
-        
+
         if next_existing && next_existing[0] == current_obj
           # Object exists - find consecutive run of existing objects
           first_num = current_obj
           run_length = 1
-          
+
           while (i + run_length) < sorted.length &&
                 sorted[i + run_length][0] == first_num + run_length &&
                 sorted[i + run_length][1] == sorted[i][1]
@@ -86,12 +86,13 @@ module AcroThat
           # Object doesn't exist - find consecutive run of missing objects
           first_missing = current_obj
           missing_count = 1
-          
+
           while current_obj + missing_count <= max_obj_num
             check_obj = current_obj + missing_count
             if sorted.any? { |num, _gen, _offset| num == check_obj }
               break
             end
+
             missing_count += 1
           end
 

data/lib/acro_that/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module AcroThat
-  VERSION = "1.0.3"
+  VERSION = "1.0.4"
 end

data/lib/acro_that.rb

@@ -5,6 +5,7 @@ require "stringio"
 require "zlib"
 require "base64"
 require "set"
+require "i18n"
 
 require_relative "acro_that/dict_scan"
 require_relative "acro_that/object_resolver"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: acro_that
 version: !ruby/object:Gem::Version
-  version: 1.0.3
+  version: 1.0.4
 platform: ruby
 authors:
 - Michael Wynkoop
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-11-07 00:00:00.000000000 Z
+date: 2025-11-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: chunky_png
@@ -24,6 +24,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.4'
+- !ruby/object:Gem::Dependency
+  name: i18n
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.14'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.14'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement