corp_pdf 1.0.5

data/lib/corp_pdf/page.rb

@@ -0,0 +1,90 @@
+# frozen_string_literal: true
+
+module CorpPdf
+  # Represents a page in a PDF document
+  class Page
+    attr_reader :page, :width, :height, :ref, :metadata, :document
+
+    def initialize(page, width, height, ref, metadata, document)
+      @page = page # Page number (1-indexed)
+      @width = width
+      @height = height
+      @ref = ref # [obj_num, gen_num]
+      @metadata = metadata # Hash with :rotate, :media_box, :crop_box, etc.
+      @document = document
+    end
+
+    # Add a field to this page
+    # Options are the same as Document#add_field, but :page is automatically set
+    def add_field(name, options = {})
+      # Automatically set the page number to this page
+      options_with_page = options.merge(page: @page)
+      @document.add_field(name, options_with_page)
+    end
+
+    # Get the page number
+    def page_number
+      @page
+    end
+
+    # Get the page reference [obj_num, gen_num]
+    def page_ref
+      @ref
+    end
+
+    # Check if page has rotation
+    def rotated?
+      !@metadata[:rotate].nil? && @metadata[:rotate] != 0
+    end
+
+    # Get rotation angle (0, 90, 180, 270)
+    def rotation
+      @metadata[:rotate] || 0
+    end
+
+    # Get MediaBox dimensions
+    def media_box
+      @metadata[:media_box]
+    end
+
+    # Get CropBox dimensions
+    def crop_box
+      @metadata[:crop_box]
+    end
+
+    # Get ArtBox dimensions
+    def art_box
+      @metadata[:art_box]
+    end
+
+    # Get BleedBox dimensions
+    def bleed_box
+      @metadata[:bleed_box]
+    end
+
+    # Get TrimBox dimensions
+    def trim_box
+      @metadata[:trim_box]
+    end
+
+    # String representation for debugging
+    def to_s
+      dims = width && height ? " #{width}x#{height}" : ""
+      rot = rotated? ? " (rotated #{rotation}°)" : ""
+      "#<CorpPdf::Page page=#{page}#{dims}#{rot} ref=#{ref.inspect}>"
+    end
+
+    alias inspect to_s
+
+    # Convert to hash for backward compatibility
+    def to_h
+      {
+        page: @page,
+        width: @width,
+        height: @height,
+        ref: @ref,
+        metadata: @metadata
+      }
+    end
+  end
+end

data/lib/corp_pdf/pdf_writer.rb

@@ -0,0 +1,133 @@
+# frozen_string_literal: true
+
+module CorpPdf
+  # PDFWriter - Clean PDF writer for flattening documents
+  # Writes a complete PDF from parsed objects, consolidating incremental updates
+  class PDFWriter
+    def initialize
+      # Work entirely in binary encoding to avoid UTF-8/ASCII-8BIT conflicts
+      @buffer = "".b
+      @offsets = [] # Track [obj_num, gen, offset] for xref table
+      @xref_offset = 0
+    end
+
+    def write_header
+      @buffer << "%PDF-1.6\n".b
+      # Binary marker (helps PDF readers identify binary content)
+      @buffer << "%\xE2\xE3\xCF\xD3\n".b
+    end
+
+    def write_object(ref, body)
+      obj_num, gen = ref
+      offset = @buffer.bytesize
+      @offsets << [obj_num, gen, offset]
+
+      # Write object with proper PDF syntax
+      # Use ASCII-8BIT encoding throughout to avoid conflicts
+      @buffer << "#{obj_num} #{gen} obj\n".b
+
+      # Body is already in binary from ObjectResolver
+      @buffer << body.b
+
+      # Ensure proper spacing before endobj
+      @buffer << "\n".b unless body.end_with?("\n")
+      @buffer << "endobj\n".b
+    end
+
+    def write_xref
+      @xref_offset = @buffer.bytesize
+
+      # Build xref table
+      xref = "xref\n".b
+
+      # Object 0 (free list head)
+      xref << "0 1\n".b
+      xref << "0000000000 65535 f \n".b
+
+      # Sort offsets and group consecutive objects into subsections
+      sorted = @offsets.sort_by { |num, gen, _offset| [num, gen] }
+
+      # Find max object number to determine Size
+      max_obj_num = sorted.map { |num, _gen, _offset| num }.max || 0
+
+      # Build xref entries covering all objects from 0 to max_obj_num
+      # Missing objects are marked as free (type 'f')
+      i = 0
+      current_obj = 0
+
+      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]
+            run_length += 1
+          end
+
+          # Write subsection header
+          xref << "#{first_num} #{run_length}\n".b
+
+          # Write entries in this subsection
+          run_length.times do |j|
+            offset = sorted[i + j][2]
+            gen = sorted[i + j][1]
+            xref << format("%010d %05d n \n", offset, gen).b
+          end
+
+          i += run_length
+          current_obj = first_num + run_length
+        else
+          # 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
+
+          # Write subsection header for missing objects
+          xref << "#{first_missing} #{missing_count}\n".b
+
+          # Write free entries
+          missing_count.times do
+            xref << "0000000000 65535 f \n".b
+          end
+
+          current_obj = first_missing + missing_count
+        end
+      end
+
+      @buffer << xref
+    end
+
+    def write_trailer(size, root_ref, info_ref = nil)
+      trailer = "trailer\n".b
+      trailer << "<<".b
+      trailer << " /Size #{size}".b
+      trailer << " /Root #{root_ref[0]} #{root_ref[1]} R".b
+      trailer << " /Info #{info_ref[0]} #{info_ref[1]} R".b if info_ref
+      trailer << " >>".b
+      trailer << "\n".b
+      trailer << "startxref\n".b
+      trailer << "#{@xref_offset}\n".b
+      trailer << "%%EOF\n".b
+
+      @buffer << trailer
+    end
+
+    def output
+      @buffer
+    end
+  end
+end

data/lib/corp_pdf/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module CorpPdf
+  VERSION = "1.0.5"
+end

data/lib/corp_pdf.rb

@@ -0,0 +1,35 @@
+# frozen_string_literal: true
+
+require "strscan"
+require "stringio"
+require "zlib"
+require "base64"
+require "set"
+require "i18n"
+
+require_relative "corp_pdf/dict_scan"
+require_relative "corp_pdf/object_resolver"
+require_relative "corp_pdf/objstm"
+require_relative "corp_pdf/pdf_writer"
+require_relative "corp_pdf/incremental_writer"
+require_relative "corp_pdf/field"
+require_relative "corp_pdf/page"
+require_relative "corp_pdf/document"
+
+# Load actions base first (needed by fields)
+require_relative "corp_pdf/actions/base"
+
+# Load fields
+require_relative "corp_pdf/fields/base"
+require_relative "corp_pdf/fields/radio"
+require_relative "corp_pdf/fields/text"
+require_relative "corp_pdf/fields/checkbox"
+require_relative "corp_pdf/fields/signature"
+
+# Load actions
+require_relative "corp_pdf/actions/add_field"
+require_relative "corp_pdf/actions/update_field"
+require_relative "corp_pdf/actions/remove_field"
+
+module CorpPdf
+end

data/publish

@@ -0,0 +1,183 @@
+#!/bin/bash
+
+set -e  # Exit on any error
+
+VERSION_FILE="lib/corp_pdf/version.rb"
+GEMSPEC_FILE="corp_pdf.gemspec"
+GEM_NAME="corp_pdf"
+
+# Function to show usage
+usage() {
+    cat << EOF
+Usage: $0 [OPTIONS]
+
+Publish corp_pdf gem to RubyGems.
+
+OPTIONS:
+    -b, --bump TYPE        Bump version before publishing (major|minor|patch)
+    -k, --key KEY         RubyGems API key name (optional, uses credentials if not provided)
+    -h, --help            Show this help message
+
+EXAMPLES:
+    $0                     # Publish current version without bumping
+    $0 -b patch            # Bump patch version (0.1.2 -> 0.1.3)
+    $0 -b minor            # Bump minor version (0.1.2 -> 0.2.0)
+    $0 -b major            # Bump major version (0.1.2 -> 1.0.0)
+    $0 -b patch -k mykey   # Bump patch and use specific API key
+
+EOF
+    exit 1
+}
+
+# Function to get current version
+get_current_version() {
+    if [[ ! -f "$VERSION_FILE" ]]; then
+        echo "Error: $VERSION_FILE not found!" >&2
+        exit 1
+    fi
+    
+    # Extract version using awk (works reliably on both macOS and Linux)
+    awk -F'"' '/VERSION =/ {print $2}' "$VERSION_FILE"
+}
+
+# Function to bump version
+bump_version() {
+    local bump_type=$1
+    local current_version=$(get_current_version)
+    
+    IFS='.' read -ra VERSION_PARTS <<< "$current_version"
+    local major=${VERSION_PARTS[0]:-0}
+    local minor=${VERSION_PARTS[1]:-0}
+    local patch=${VERSION_PARTS[2]:-0}
+    
+    case "$bump_type" in
+        major)
+            major=$((major + 1))
+            minor=0
+            patch=0
+            ;;
+        minor)
+            minor=$((minor + 1))
+            patch=0
+            ;;
+        patch)
+            patch=$((patch + 1))
+            ;;
+        *)
+            echo "Error: Invalid bump type: $bump_type" >&2
+            echo "Must be one of: major, minor, patch" >&2
+            exit 1
+            ;;
+    esac
+    
+    local new_version="${major}.${minor}.${patch}"
+    
+    # Update version in version.rb
+    if [[ "$OSTYPE" == "darwin"* ]]; then
+        # macOS uses BSD sed
+        sed -i '' "s/VERSION = \".*\"/VERSION = \"$new_version\"/" "$VERSION_FILE"
+    else
+        # Linux uses GNU sed
+        sed -i "s/VERSION = \".*\"/VERSION = \"$new_version\"/" "$VERSION_FILE"
+    fi
+    
+    echo "$new_version"
+}
+
+# Parse arguments
+BUMP_TYPE=""
+API_KEY=""
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        -b|--bump)
+            BUMP_TYPE="$2"
+            shift 2
+            ;;
+        -k|--key)
+            API_KEY="$2"
+            shift 2
+            ;;
+        -h|--help)
+            usage
+            ;;
+        *)
+            echo "Error: Unknown option: $1" >&2
+            usage
+            ;;
+    esac
+done
+
+# Validate bump type if provided
+if [[ -n "$BUMP_TYPE" ]]; then
+    if [[ ! "$BUMP_TYPE" =~ ^(major|minor|patch)$ ]]; then
+        echo "Error: Invalid bump type: $BUMP_TYPE" >&2
+        echo "Must be one of: major, minor, patch" >&2
+        exit 1
+    fi
+fi
+
+# Get version (after potential bump)
+if [[ -n "$BUMP_TYPE" ]]; then
+    echo "Bumping $BUMP_TYPE version..."
+    VERSION=$(bump_version "$BUMP_TYPE")
+    echo "New version: $VERSION"
+else
+    VERSION=$(get_current_version)
+    echo "Using current version: $VERSION"
+fi
+
+# Build the gem
+echo "Building gem..."
+GEM_FILE="${GEM_NAME}-${VERSION}.gem"
+gem build "$GEMSPEC_FILE"
+
+if [[ ! -f "$GEM_FILE" ]]; then
+    echo "Error: Failed to build gem file: $GEM_FILE" >&2
+    exit 1
+fi
+
+echo "Gem built successfully: $GEM_FILE"
+
+# Push to RubyGems
+echo "Pushing to RubyGems..."
+if [[ -n "$API_KEY" ]]; then
+    gem push "$GEM_FILE" --key "$API_KEY"
+else
+    gem push "$GEM_FILE"
+fi
+
+if [[ $? -ne 0 ]]; then
+    echo "Error: Failed to push gem to RubyGems" >&2
+    exit 1
+fi
+
+echo "Gem pushed to RubyGems successfully"
+
+# Commit and push to git (only if version was bumped or if there are changes)
+if [[ -n "$BUMP_TYPE" ]] || ! git diff --quiet "$VERSION_FILE"; then
+    echo "Committing version change..."
+    git add "$VERSION_FILE"
+    git commit -m "v${VERSION}"
+    
+    echo "Creating and pushing tag..."
+    git tag -a "v${VERSION}" -m "Release version ${VERSION}"
+    
+    echo "Pushing to origin..."
+    git push origin main
+    git push origin "v${VERSION}"
+    
+    echo "Git operations completed successfully"
+else
+    echo "No version changes to commit"
+fi
+
+echo ""
+echo "✅ Successfully published ${GEM_NAME} v${VERSION}!"
+echo "   - Gem built: ${GEM_FILE}"
+echo "   - Pushed to RubyGems"
+if [[ -n "$BUMP_TYPE" ]]; then
+    echo "   - Version bumped and committed"
+    echo "   - Tagged as v${VERSION}"
+fi
+

metadata

@@ -0,0 +1,169 @@
+--- !ruby/object:Gem::Specification
+name: corp_pdf
+version: !ruby/object:Gem::Version
+  version: 1.0.5
+platform: ruby
+authors:
+- Michael Wynkoop
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2025-11-13 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: chunky_png
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.4'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !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
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.14'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.14'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.50'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.50'
+- !ruby/object:Gem::Dependency
+  name: rubocop-rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.20'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.20'
+description: A minimal pure Ruby library for parsing and editing PDF AcroForm fields
+  using only stdlib
+email:
+- michaelwynkoop@corporatetools.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rubocop.yml"
+- CHANGELOG.md
+- Gemfile
+- Gemfile.lock
+- README.md
+- Rakefile
+- corp_pdf.gemspec
+- docs/README.md
+- docs/clear_fields.md
+- docs/dict_scan_explained.md
+- docs/object_streams.md
+- docs/pdf_structure.md
+- issues/README.md
+- issues/memory-benchmark-results.md
+- issues/memory-improvements.md
+- issues/memory-optimization-summary.md
+- issues/refactoring-opportunities.md
+- lib/corp_pdf.rb
+- lib/corp_pdf/actions/add_field.rb
+- lib/corp_pdf/actions/base.rb
+- lib/corp_pdf/actions/remove_field.rb
+- lib/corp_pdf/actions/update_field.rb
+- lib/corp_pdf/dict_scan.rb
+- lib/corp_pdf/document.rb
+- lib/corp_pdf/field.rb
+- lib/corp_pdf/fields/base.rb
+- lib/corp_pdf/fields/checkbox.rb
+- lib/corp_pdf/fields/radio.rb
+- lib/corp_pdf/fields/signature.rb
+- lib/corp_pdf/fields/text.rb
+- lib/corp_pdf/incremental_writer.rb
+- lib/corp_pdf/object_resolver.rb
+- lib/corp_pdf/objstm.rb
+- lib/corp_pdf/page.rb
+- lib/corp_pdf/pdf_writer.rb
+- lib/corp_pdf/version.rb
+- publish
+homepage: https://github.com/corporatetools/corp_pdf
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/corporatetools/corp_pdf
+  source_code_uri: https://github.com/corporatetools/corp_pdf
+  changelog_uri: https://github.com/corporatetools/corp_pdf/blob/main/CHANGELOG.md
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 3.1.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.4.12
+signing_key:
+specification_version: 4
+summary: Pure Ruby PDF AcroForm editing library
+test_files: []