pdfrb 0.7.43 → 0.7.44

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b0b004db58a66ef4268db7138eb13c2813fcceb4e22a492674597f631d6f889e
-  data.tar.gz: b29ee27e11e4aea41a482e3eb217c7ddf70a5cdf4b21f70b2d16be01747822df
+  metadata.gz: 836c9a2bfe781c6816a25f2db87e99c3b30265fcfb80f116f1b54ccfe9ce149d
+  data.tar.gz: 2a7b2a9f1d607b1dd29fd6aca4a2b9a977b315e98834026974ae73d384a62718
 SHA512:
-  metadata.gz: 25dc0c66f65bf454f2ac91c362031c57720d060edaeb54912aba896115216fbe43ce4fd947e21e94a445e521168e1eb629d51db42dc38c9ca5639ca41e8786e5
-  data.tar.gz: 3368f119c878bb7bcce11f21a4bd6edb267e4605ae079ca85dafbce6defa1397e9b5f0649bbdfc3a7084d161eb0f6c20da934b5b0f288344538f296703a031c7
+  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/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 = "0.7.43"
+  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

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pdfrb
 version: !ruby/object:Gem::Version
-  version: 0.7.43
+  version: 0.7.44
 platform: ruby
 authors:
 - Ribose Inc.