tabula-rb 1.0.0

data/lib/tabula.rb

@@ -0,0 +1,160 @@
+# frozen_string_literal: true
+
+require_relative 'tabula/version'
+require_relative 'tabula/configuration'
+
+# Core geometry
+require_relative 'tabula/core/point'
+require_relative 'tabula/core/rectangle'
+require_relative 'tabula/core/ruling'
+require_relative 'tabula/core/spatial_index'
+
+# Text handling
+require_relative 'tabula/text/text_element'
+require_relative 'tabula/text/text_chunk'
+require_relative 'tabula/text/line'
+
+# Table structures
+require_relative 'tabula/table/cell'
+require_relative 'tabula/table/table'
+
+# PDF processing
+require_relative 'tabula/pdf/page'
+require_relative 'tabula/pdf/text_stripper'
+require_relative 'tabula/pdf/object_extractor'
+
+# Extraction algorithms
+require_relative 'tabula/extractors/extraction_algorithm'
+require_relative 'tabula/extractors/basic_extraction_algorithm'
+require_relative 'tabula/extractors/spreadsheet_extraction_algorithm'
+
+# Detection algorithms
+require_relative 'tabula/detectors/detection_algorithm'
+require_relative 'tabula/detectors/spreadsheet_detection_algorithm'
+require_relative 'tabula/detectors/nurminen_detection_algorithm'
+
+# Writers
+require_relative 'tabula/writers/writer'
+require_relative 'tabula/writers/csv_writer'
+require_relative 'tabula/writers/tsv_writer'
+require_relative 'tabula/writers/json_writer'
+require_relative 'tabula/writers/markdown_writer'
+
+# Geometric algorithms
+require_relative 'tabula/algorithms/cohen_sutherland_clipping'
+require_relative 'tabula/algorithms/projection_profile'
+
+module Tabula
+  class Error < StandardError; end
+  class InvalidPDFError < Error; end
+  class PasswordRequiredError < Error; end
+  class FileNotFoundError < Error; end
+  class InvalidOptionsError < Error; end
+
+  VALID_METHODS = %i[lattice stream auto].freeze
+
+  class << self
+    # Extract tables from a PDF file
+    #
+    # @param path [String] path to PDF file
+    # @param options [Hash] extraction options
+    # @option options [Array<Integer>] :pages pages to extract (1-indexed, nil for all)
+    # @option options [Symbol] :method extraction method (:lattice, :stream, or :auto)
+    # @option options [Array<Float>] :area area to extract [top, left, bottom, right]
+    # @option options [Array<Float>] :columns column boundaries
+    # @option options [String] :password PDF password
+    # @option options [Boolean] :guess auto-detect table areas
+    # @return [Array<Table>] extracted tables
+    # @raise [FileNotFoundError] if the file does not exist
+    # @raise [InvalidOptionsError] if options are invalid
+    def extract(path, **options)
+      validate_file!(path)
+      validate_options!(options)
+
+      ObjectExtractor.open(path, password: options[:password]) do |extractor|
+        pages = options[:pages] || (1..extractor.page_count).to_a
+        method = options[:method] || :auto
+        area = options[:area]
+        columns = options[:columns]
+        guess = options.fetch(:guess, false)
+
+        tables = []
+
+        pages.each do |page_num|
+          page = extractor.extract_page(page_num)
+          page = page.get_area(*area) if area
+
+          if guess
+            detected_areas = Detectors::Nurminen.detect(page)
+            detected_areas.each do |detected_area|
+              sub_page = page.get_area(*detected_area.bounds)
+              tables.concat(extract_from_page(sub_page, method, columns))
+            end
+          else
+            tables.concat(extract_from_page(page, method, columns))
+          end
+        end
+
+        tables
+      end
+    end
+
+    private
+
+    def validate_file!(path)
+      raise FileNotFoundError, "File not found: #{path}" unless File.exist?(path)
+    end
+
+    def validate_options!(options)
+      validate_pages!(options[:pages]) if options[:pages]
+      validate_area!(options[:area]) if options[:area]
+      validate_method!(options[:method]) if options[:method]
+    end
+
+    def validate_pages!(pages)
+      raise InvalidOptionsError, "Pages must be an array, got #{pages.class}" unless pages.is_a?(Array)
+
+      pages.each do |page|
+        unless page.is_a?(Integer) && page.positive?
+          raise InvalidOptionsError, "Page numbers must be positive integers, got #{page.inspect}"
+        end
+      end
+    end
+
+    def validate_area!(area)
+      unless area.is_a?(Array) && area.size == 4
+        raise InvalidOptionsError,
+              "Area must be an array of exactly 4 values [top, left, bottom, right], got #{area.inspect}"
+      end
+
+      area.each_with_index do |value, index|
+        labels = %w[top left bottom right]
+        unless value.is_a?(Numeric)
+          raise InvalidOptionsError, "Area #{labels[index]} must be numeric, got #{value.inspect}"
+        end
+      end
+    end
+
+    def validate_method!(method)
+      return if VALID_METHODS.include?(method)
+
+      raise InvalidOptionsError,
+            "Method must be one of #{VALID_METHODS.map(&:inspect).join(', ')}, got #{method.inspect}"
+    end
+
+    def extract_from_page(page, method, columns)
+      case method
+      when :lattice
+        Extractors::Spreadsheet.extract(page)
+      when :stream
+        Extractors::Basic.extract(page, columns: columns)
+      when :auto
+        # Try lattice first, fall back to stream
+        tables = Extractors::Spreadsheet.extract(page)
+        tables.empty? ? Extractors::Basic.extract(page, columns: columns) : tables
+      else
+        raise ArgumentError, "Unknown extraction method: #{method}"
+      end
+    end
+  end
+end

data/mise.toml

@@ -0,0 +1,2 @@
+[tools]
+ruby = "3.4"

data/tabula-rb.gemspec

@@ -0,0 +1,44 @@
+# frozen_string_literal: true
+
+require_relative 'lib/tabula/version'
+
+Gem::Specification.new do |spec|
+  spec.name = 'tabula-rb'
+  spec.version = Tabula::VERSION
+  spec.authors = ['Chris Hasiński']
+  spec.email = ['krzysztof.hasinski@gmail.com']
+
+  spec.summary = 'Extract tables from PDF files (Ruby port of tabula-java)'
+  spec.description = <<~DESC
+    Tabula is a Ruby port of tabula-java (https://github.com/tabulapdf/tabula-java),
+    the library that powers the Tabula PDF table extraction tool. It supports both
+    lattice-mode extraction (for PDFs with visible cell borders) and stream-mode
+    extraction (for PDFs without ruling lines, using text positioning).
+  DESC
+  spec.homepage = 'https://github.com/tabulapdf/tabula-rb'
+  spec.license = 'MIT'
+  spec.required_ruby_version = '>= 3.1.0'
+
+  spec.metadata['homepage_uri'] = spec.homepage
+  spec.metadata['source_code_uri'] = spec.homepage
+  spec.metadata['changelog_uri'] = "#{spec.homepage}/blob/main/CHANGELOG.md"
+
+  spec.files = Dir.chdir(__dir__) do
+    `git ls-files -z`.split("\x0").reject do |f|
+      (File.expand_path(f) == __FILE__) ||
+        f.start_with?(*%w[bin/ test/ spec/ features/ .git .github appveyor Gemfile])
+    end
+  end
+  spec.bindir = 'exe'
+  spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
+  spec.require_paths = ['lib']
+
+  # Runtime dependencies
+  spec.add_dependency 'csv', '~> 3.0'
+  spec.add_dependency 'pdf-reader', '~> 2.0'
+
+  # Optional dependencies for advanced features
+  # spec.add_dependency "mini_magick", "~> 4.0"  # For Nurminen detection
+
+  spec.metadata['rubygems_mfa_required'] = 'true'
+end

metadata

@@ -0,0 +1,115 @@
+--- !ruby/object:Gem::Specification
+name: tabula-rb
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Chris Hasiński
+bindir: exe
+cert_chain: []
+date: 1980-01-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: csv
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: pdf-reader
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+description: |
+  Tabula is a Ruby port of tabula-java (https://github.com/tabulapdf/tabula-java),
+  the library that powers the Tabula PDF table extraction tool. It supports both
+  lattice-mode extraction (for PDFs with visible cell borders) and stream-mode
+  extraction (for PDFs without ruling lines, using text positioning).
+email:
+- krzysztof.hasinski@gmail.com
+executables:
+- tabula
+extensions: []
+extra_rdoc_files: []
+files:
+- ".rspec"
+- ".rubocop.yml"
+- CHANGELOG.md
+- LICENSE
+- README.md
+- Rakefile
+- exe/tabula
+- lib/tabula.rb
+- lib/tabula/algorithms/cohen_sutherland_clipping.rb
+- lib/tabula/algorithms/projection_profile.rb
+- lib/tabula/cli.rb
+- lib/tabula/configuration.rb
+- lib/tabula/core/point.rb
+- lib/tabula/core/rectangle.rb
+- lib/tabula/core/ruling.rb
+- lib/tabula/core/spatial_index.rb
+- lib/tabula/detectors/detection_algorithm.rb
+- lib/tabula/detectors/nurminen_detection_algorithm.rb
+- lib/tabula/detectors/spreadsheet_detection_algorithm.rb
+- lib/tabula/extractors/basic_extraction_algorithm.rb
+- lib/tabula/extractors/extraction_algorithm.rb
+- lib/tabula/extractors/spreadsheet_extraction_algorithm.rb
+- lib/tabula/pdf/object_extractor.rb
+- lib/tabula/pdf/page.rb
+- lib/tabula/pdf/text_stripper.rb
+- lib/tabula/table/cell.rb
+- lib/tabula/table/table.rb
+- lib/tabula/text/line.rb
+- lib/tabula/text/text_chunk.rb
+- lib/tabula/text/text_element.rb
+- lib/tabula/version.rb
+- lib/tabula/writers/csv_writer.rb
+- lib/tabula/writers/json_writer.rb
+- lib/tabula/writers/markdown_writer.rb
+- lib/tabula/writers/tsv_writer.rb
+- lib/tabula/writers/writer.rb
+- mise.toml
+- tabula-rb.gemspec
+homepage: https://github.com/tabulapdf/tabula-rb
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/tabulapdf/tabula-rb
+  source_code_uri: https://github.com/tabulapdf/tabula-rb
+  changelog_uri: https://github.com/tabulapdf/tabula-rb/blob/main/CHANGELOG.md
+  rubygems_mfa_required: 'true'
+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: 4.0.2
+specification_version: 4
+summary: Extract tables from PDF files (Ruby port of tabula-java)
+test_files: []