rpdfium 0.4.1

data/lib/rpdfium.rb

@@ -0,0 +1,92 @@
+# frozen_string_literal: true
+
+require_relative "rpdfium/version"
+require_relative "rpdfium/errors"
+
+# Carica la gemma companion rpdfium-binary se presente: deve avvenire PRIMA
+# di raw.rb, che chiama ffi_lib al momento del require e interroga
+# Rpdfium::Binary.library_path per trovare il path assoluto al .so/.dylib.
+begin
+  require "rpdfium/binary"
+rescue LoadError
+  nil
+end
+
+require_relative "rpdfium/raw"
+
+require_relative "rpdfium/io/png"
+
+require_relative "rpdfium/structure/outline"
+require_relative "rpdfium/structure/attachment"
+require_relative "rpdfium/structure/element"
+require_relative "rpdfium/structure/tree"
+
+require_relative "rpdfium/image/embedded"
+require_relative "rpdfium/annotation/annotation"
+require_relative "rpdfium/form/form"
+require_relative "rpdfium/search/search"
+
+require_relative "rpdfium/document"
+require_relative "rpdfium/page"
+
+require_relative "rpdfium/util/cluster"
+require_relative "rpdfium/util/word_extractor"
+require_relative "rpdfium/util/text_extraction"
+require_relative "rpdfium/util/word_merger"
+require_relative "rpdfium/util/column_inference"
+require_relative "rpdfium/util/label_matcher"
+
+require_relative "rpdfium/table/edges"
+require_relative "rpdfium/table/cells"
+require_relative "rpdfium/table/table"
+require_relative "rpdfium/table/extractor"
+require_relative "rpdfium/table/debugger"
+
+# rpdfium - Ruby bindings to PDFium with table extraction.
+#
+# Top-level API:
+#   Rpdfium.open(path_or_io_or_bytes) { |doc| ... }
+#   Rpdfium.extract_text(path)
+#   Rpdfium.extract_tables(path)
+#   Rpdfium.render_to_pngs(path, output_dir:)
+module Rpdfium
+  def self.open(input, password: nil, &block)
+    Document.open(input, password: password, &block)
+  end
+
+  # Estrai tutto il testo di tutte le pagine, una stringa per pagina.
+  def self.extract_text(input, password: nil)
+    open(input, password: password) { |doc| doc.map(&:text) }
+  end
+
+  # Estrai tutte le tabelle di tutte le pagine.
+  # Ritorna Array<{ page: Integer, rows: Array<Array<String>> }>.
+  #
+  # `keep_blank_rows: false` (default) elimina le righe completamente vuote
+  # che la strategia `:text` di words_to_edges_h genera per costruzione (ogni
+  # riga visiva produce due edges, top + bottom, e tra coppie di edges
+  # adiacenti si formano "righe spurie" di altezza pari al gap interlinea).
+  # Con `keep_blank_rows: true` ottieni l'output grezzo di Table#extract.
+  def self.extract_tables(input, password: nil, keep_blank_rows: false, **opts)
+    open(input, password: password) do |doc|
+      doc.flat_map do |page|
+        Table::Extractor.new(page, **opts).extract.map do |rows|
+          rows = rows.reject { |r| r.all? { |c| c.nil? || c.empty? } } unless keep_blank_rows
+          { page: page.index, rows: rows }
+        end
+      end
+    end
+  end
+
+  # Renderizza ogni pagina in un PNG dentro output_dir.
+  def self.render_to_pngs(input, output_dir:, scale: 2.0, password: nil)
+    Dir.mkdir(output_dir) unless Dir.exist?(output_dir)
+    open(input, password: password) do |doc|
+      doc.map do |page|
+        path = File.join(output_dir, format("page_%04d.png", page.index + 1))
+        page.render_to_png(path, scale: scale)
+        path
+      end
+    end
+  end
+end

metadata

@@ -0,0 +1,134 @@
+--- !ruby/object:Gem::Specification
+name: rpdfium
+version: !ruby/object:Gem::Version
+  version: 0.4.1
+platform: ruby
+authors:
+- Roberto Scinocca
+bindir: bin
+cert_chain: []
+date: 1980-01-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: ffi
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.13'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.13'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.0'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.60'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.60'
+description: |
+  FFI bindings to Google's PDFium library, the same engine that powers
+  Chrome's PDF viewer. Provides text extraction with character-level
+  metadata (font, weight, origin, angle), vector path access, image
+  extraction, annotations, AcroForm fields, page rendering, and
+  pdfplumber-style table detection. Inspired by pypdfium2 and pdfplumber.
+email:
+- roberto.scinocca@hey.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- CHANGELOG.md
+- LICENSE
+- README.md
+- lib/rpdfium.rb
+- lib/rpdfium/annotation/annotation.rb
+- lib/rpdfium/document.rb
+- lib/rpdfium/errors.rb
+- lib/rpdfium/form/form.rb
+- lib/rpdfium/image/embedded.rb
+- lib/rpdfium/io/png.rb
+- lib/rpdfium/page.rb
+- lib/rpdfium/raw.rb
+- lib/rpdfium/search/search.rb
+- lib/rpdfium/structure/attachment.rb
+- lib/rpdfium/structure/element.rb
+- lib/rpdfium/structure/outline.rb
+- lib/rpdfium/structure/tree.rb
+- lib/rpdfium/table/cells.rb
+- lib/rpdfium/table/debugger.rb
+- lib/rpdfium/table/edges.rb
+- lib/rpdfium/table/extractor.rb
+- lib/rpdfium/table/table.rb
+- lib/rpdfium/util/cluster.rb
+- lib/rpdfium/util/column_inference.rb
+- lib/rpdfium/util/label_matcher.rb
+- lib/rpdfium/util/text_extraction.rb
+- lib/rpdfium/util/word_extractor.rb
+- lib/rpdfium/util/word_merger.rb
+- lib/rpdfium/version.rb
+homepage: https://github.com/retsef/rpdfium
+licenses:
+- Apache-2.0
+metadata:
+  source_code_uri: https://github.com/retsef/rpdfium
+  changelog_uri: https://github.com/retsef/rpdfium/blob/main/CHANGELOG.md
+  bug_tracker_uri: https://github.com/retsef/rpdfium/issues
+  rubygems_mfa_required: 'true'
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 3.0.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 4.0.6
+specification_version: 4
+summary: Ruby bindings for PDFium with table extraction
+test_files: []