pdfrb 0.7.42 → 0.7.44

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ab4ad0a762217c8fdfc88589f78152f7ec382f5192cec734457cdba1c538139a
-  data.tar.gz: 1850f2ae9b0fa99006c5fa0fbdc4d290929c72aa5b5f990e30275eab8c19a66b
+  metadata.gz: 836c9a2bfe781c6816a25f2db87e99c3b30265fcfb80f116f1b54ccfe9ce149d
+  data.tar.gz: 2a7b2a9f1d607b1dd29fd6aca4a2b9a977b315e98834026974ae73d384a62718
 SHA512:
-  metadata.gz: 37b7a245a79cbf85cbaf8e82b353da55c01b688453589ce7b9bcd4e58a6a8acd988702e5a2af564a0a1516e5f554af32b36c8ca2b7db98a8ef03572b26b49f80
-  data.tar.gz: d3430314391486f081de9a2723857f0c266dff32c3e88487f6e409d6d74a16fdc348003d736b7af202de2761c3608dc48808832f08ed2c45c0b8ff245dd49493
+  metadata.gz: dc2be0c8bcf1f7a6a77f3db649dba782cc789e532a17afb2fd6152b5fa8109e2c0d6410a01f8df0c820e53fa3439035ff3db24fde8e889a32b6bc880a93cda25
+  data.tar.gz: ad3a5ae6eb6dc87577477bba0a7b4ccb6e75e5c914dee698ee4bc661f2df96b363172ef6aded34815b5965ec3f01edf0e6c710b70ba4a4ab95510acc6a0a2b2d

data/docs/USAGE.md

@@ -137,9 +137,18 @@ File.binwrite("linearized.pdf", io.string)
 ## Encryption
 
 ```ruby
-doc = Pdfrb.open("input.pdf")
+doc = Pdfrb::Document.new
+doc.pages.add
+doc.encrypt!(user_password: "secret", owner_password: "owner", bits: 128)
 doc.write("encrypted.pdf")
-# Encryption configuration via document.config
+
+# Opening an encrypted document:
+doc = Pdfrb.open("encrypted.pdf",
+                 config: { "encryption.password" => "secret" })
+
+# Removing encryption from a parsed document:
+doc.decrypt!
+doc.write("decrypted.pdf")
 ```
 
 ## Merging PDFs

data/lib/pdfrb/content/canvas.rb

@@ -64,7 +64,11 @@ module Pdfrb
         self
       end
 
-      def line(x1, y1, x2, y2)
+      def line(x1 = nil, y1 = nil, x2 = nil, y2 = nil, from: nil, to: nil)
+        if from && to
+          x1, y1 = from
+          x2, y2 = to
+        end
         move_to(x1, y1).line_to(x2, y2)
       end
 
@@ -189,8 +193,14 @@ module Pdfrb
         self
       end
 
-      def rectangle(x, y, width, height)
-        emit_op(Pdfrb::Content::Operator::Rectangle, x, y, width, height)
+      def rectangle(x = nil, y = nil, w = nil, h = nil,
+                    point: nil, width: nil, height: nil)
+        x, y = point if point
+        w = width if w.nil?
+        h = height if h.nil?
+        raise ArgumentError, "rectangle needs x, y, width and height" if [x, y, w, h].any?(&:nil?)
+
+        emit_op(Pdfrb::Content::Operator::Rectangle, x, y, w, h)
         self
       end
 

data/lib/pdfrb/content/inline_image.rb

@@ -0,0 +1,103 @@
+# frozen_string_literal: true
+
+module Pdfrb
+  module Content
+    # A BI ... ID ... EI inline image (s8.9.7). Carries the expanded
+    # header keys (abbreviations resolved by the parser), the raw
+    # encoded byte payload, and decodes on demand via the filter
+    # pipeline.
+    class InlineImage
+      # Filter-name abbreviations permitted in inline images
+      # (s8.9.7 Table 89).
+      FILTER_ABBREVIATIONS = {
+        AHx: :ASCIIHexDecode,
+        A85: :ASCII85Decode,
+        Fl: :FlateDecode,
+        LZW: :LZWDecode,
+        CCF: :CCITTFaxDecode,
+        DCT: :DCTDecode,
+        RL: :RunLengthDecode,
+      }.freeze
+
+      # Color-space-name abbreviations (s8.9.7 Table 89).
+      COLOR_SPACE_ABBREVIATIONS = {
+        G: :DeviceGray,
+        RGB: :DeviceRGB,
+        CMYK: :DeviceCMYK,
+        I: :Indexed,
+      }.freeze
+
+      attr_reader :header, :data
+
+      def initialize(header: {}, data: "")
+        @header = header.dup.freeze
+        @data = (data || "".b).dup.freeze
+      end
+
+      def width; header[:Width]; end
+      def height; header[:Height]; end
+      def bits_per_component; header[:BitsPerComponent]; end
+
+      def image_mask?
+        [true, 1].include?(header[:ImageMask])
+      end
+
+      def decode; header[:Decode]; end
+      def interpolate?; header[:Interpolate] == true; end
+
+      # /ColorSpace with the inline abbreviation expanded
+      # (/G -> /DeviceGray etc.).
+      def color_space
+        cs = header[:ColorSpace]
+        return nil unless cs.is_a?(::Symbol)
+
+        COLOR_SPACE_ABBREVIATIONS.fetch(cs, cs)
+      end
+
+      # Decoded filter chain as an array of Symbols; nil when the
+      # image data is stored raw.
+      def filters
+        f = header[:Filter]
+        return [] if f.nil?
+
+        arr = f.is_a?(::Array) ? f : [f]
+        arr.map { |name| FILTER_ABBREVIATIONS.fetch(name.to_sym, name.to_sym) }
+      end
+
+      # Apply the filter chain to the raw payload. Returns the raw
+      # data when no filter is declared.
+      def decoded_data
+        list = filters
+        return @data if list.empty?
+
+        Pdfrb::Filter.apply(
+          @data, filters: list, parms: Array(header[:DecodeParms]),
+                 direction: :decode
+        )
+      end
+
+      # Number of colour components implied by /ColorSpace.
+      def components
+        case color_space
+        when :DeviceGray, :Indexed then 1
+        when :DeviceRGB then 3
+        when :DeviceCMYK then 4
+        end
+      end
+
+      # Expected decoded byte count: rows * width * components *
+      # bits, packed per row.
+      def expected_decoded_size
+        return nil if width.nil? || height.nil? || bits_per_component.nil?
+        return nil if image_mask?
+
+        comps = components
+        return nil if comps.nil?
+
+        bits = width * comps * bits_per_component
+        bytes_per_row = (bits + 7) / 8
+        bytes_per_row * height
+      end
+    end
+  end
+end

data/lib/pdfrb/content/operator.rb

@@ -12,6 +12,12 @@ module Pdfrb
     module Operator
       @registry = {}
 
+      # Referenced directly by the Parser for BI ... ID ... EI
+      # sequences; the remaining operator classes load via
+      # eager_load! / Operator[].
+      autoload :BeginInlineImage, "pdfrb/content/operators/inline_image"
+      autoload :EndInlineImage, "pdfrb/content/operators/inline_image"
+
       class << self
         attr_reader :registry
 

data/lib/pdfrb/content/operators/inline_image.rb

@@ -29,8 +29,8 @@ module Pdfrb
           def invoke(processor, image = nil)
             processor.inline_image(image) if image
           end
-          register
         end
+        register
       end
 
       class EndInlineImage < Base
@@ -38,8 +38,8 @@ module Pdfrb
           def name; "EI"; end
 
           def invoke(_processor, *_operands); end
-          register
         end
+        register
       end
     end
   end

data/lib/pdfrb/content/operators.rb

@@ -16,7 +16,6 @@ module Pdfrb
       autoload :GraphicsStateParams, "pdfrb/content/operators/graphics_state_params"
       autoload :MarkedContent, "pdfrb/content/operators/marked_content"
       autoload :Clipping, "pdfrb/content/operators/clipping"
-      autoload :InlineImage, "pdfrb/content/operators/inline_image"
     end
   end
 end

data/lib/pdfrb/content/parser.rb

@@ -82,7 +82,7 @@ module Pdfrb
         # keyword from the data. Read raw bytes until "\nEI" or
         # " EI" terminator.
         data = read_inline_image_data
-        { header: header, data: data }
+        Pdfrb::Content::InlineImage.new(header: header, data: data)
       end
 
       # Map inline-image abbreviation keys to full PDF names per

data/lib/pdfrb/content/processor.rb

@@ -78,9 +78,9 @@ module Pdfrb
       def marked_content_point(_tag, _properties = nil); end
 
       # Called when a BI/ID/EI inline image is encountered in the
-      # content stream. +image+ is a Hash with :header (the image
-      # dict keys, expanded from abbreviations) and :data (the raw
-      # byte payload). Subclasses override to render or extract.
+      # content stream. +image+ is a Content::InlineImage with the
+      # expanded header keys, the raw payload, and decoded_data /
+      # geometry accessors. Subclasses override to render or extract.
       def inline_image(_image); end
     end
   end

data/lib/pdfrb/content.rb

@@ -5,6 +5,7 @@ module Pdfrb
     autoload :GraphicsState, "pdfrb/content/graphics_state"
     autoload :Operator, "pdfrb/content/operator"
     autoload :Parser, "pdfrb/content/parser"
+    autoload :InlineImage, "pdfrb/content/inline_image"
     autoload :Processor, "pdfrb/content/processor"
     autoload :ColorSpace, "pdfrb/content/color_space"
     autoload :TransformationMatrix, "pdfrb/content/transformation_matrix"

data/lib/pdfrb/document.rb

@@ -166,6 +166,14 @@ module Pdfrb
 
     def encryption; @encryption ||= Document::Encryption.new(self); end
 
+    def encrypt!(**)
+      encryption.encrypt!(**)
+    end
+
+    def decrypt!
+      encryption.decrypt!
+    end
+
     def info; @info ||= Document::Info.new(self); end
 
     def display; @display ||= Document::Display.new(self); end
@@ -306,6 +314,19 @@ module Pdfrb
 
       @xref, @trailer_dict = load_xref_and_trailer(io, sxref)
       @object_reader = Pdfrb::Source::ObjectReader.new(self, @xref) if @xref
+      seed_next_oid
+    end
+
+    # New/modified objects must not collide with objects loaded from
+    # the xref: continue allocating past the highest known oid (or
+    # the trailer /Size, whichever is larger).
+    def seed_next_oid
+      return if @xref.nil?
+
+      max_oid = @xref.entries.keys.max || 0
+      size = @trailer_dict && @trailer_dict[:Size]
+      size = size.to_i if size.respond_to?(:to_i)
+      @next_oid = [max_oid + 1, size.to_i, @next_oid].max
     end
 
     def load_xref_and_trailer(io, sxref)

data/lib/pdfrb/task/extract_text.rb

@@ -31,6 +31,18 @@ module Pdfrb
         block_given? ? document : results
       end
 
+      # Extract the text of a single page (see #call for the
+      # resolution strategy).
+      def call_single_page(page)
+        extractor = TextCollector.new(page.document, page)
+        begin
+          extractor.process(page.decoded_content)
+        rescue StandardError
+          # Malformed content stream — best effort, skip.
+        end
+        extractor.text
+      end
+
       # Internal: collects bytes from +Tj+ / +TJ+ / +'+ / +"'.
       # Tracks text-matrix y to insert line breaks at vertical moves.
       # Resolves glyph codes to Unicode via the active font's

data/lib/pdfrb/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Pdfrb
-  VERSION = "0.7.42"
+  VERSION = "0.7.44"
 end

data/lib/pdfrb.rb

@@ -58,6 +58,20 @@ module Pdfrb
   autoload :CLI, "pdfrb/cli"
 
   require "logger"
+  require "stringio"
+
+  class << self
+    # Open a PDF file (path or block over the file handle).
+    def open(path, **, &)
+      Document.open(path, **, &)
+    end
+
+    # Parse PDF bytes/IO into a Document.
+    def parse(io, **)
+      io = StringIO.new(io.b) if io.is_a?(String)
+      Document.new(io: io, **)
+    end
+  end
 
   def self.logger
     @logger ||= Logger.new($stderr, level: Logger::WARN)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pdfrb
 version: !ruby/object:Gem::Version
-  version: 0.7.42
+  version: 0.7.44
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-08-25 00:00:00.000000000 Z
+date: 2026-08-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: thor
@@ -782,6 +782,7 @@ files:
 - lib/pdfrb/content/graphic_object/rectangle.rb
 - lib/pdfrb/content/graphics_state.rb
 - lib/pdfrb/content/hidden_text_detector.rb
+- lib/pdfrb/content/inline_image.rb
 - lib/pdfrb/content/operator.rb
 - lib/pdfrb/content/operators.rb
 - lib/pdfrb/content/operators/clipping.rb