pdf-reader 2.11.0 → 2.13.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2c84983c18d983798ff5f2ede514b540ee55a788229501976474b7341bf57fba
-  data.tar.gz: 79b8f092e72a194110062cf7d7e9425c0a6531e145009c9b7c10c2c072b3d1d5
+  metadata.gz: 5db630726ada74d004eb928e8cf164d9a65070150bc99268bed3c3c22a4b16fd
+  data.tar.gz: 186960431832f9808e292e823a1b8cd3ccbe96bf89b7f8e6801b111b0899b690
 SHA512:
-  metadata.gz: '09c97a875bb46389172ed48ae8b2779ba3a8e032852b6a9943f187de13c23649e2398a5374358c62b64cf9e13bbf7f819bb5072d9aaa6882b9b94e96d23f5c13'
-  data.tar.gz: ed92250acee85f4e355785dd043f7774a5883550fe82b01b3cd9e10011f93a1fcdd500108b0e1f4e2af562bddd833c03ca601078b3eba8ee2e9990fd5e76305a
+  metadata.gz: 4cc29c3f7d3dd36ff55178c6825dab455bbfd9f3e3b62298dac03a835c741ffeebaa1959f3b3ceba19c82fe8a516acad554ad41e5142bd4a8c75a9725857fc96
+  data.tar.gz: a89f8815c83d6f89bc51e3aa232776d6d365eb45f0cbfd01ae9de157390144c9ff8bdbdf3e1359048612d3febeffbfd77a01d0c2b08da0b53dad64b6290f6292

data/CHANGELOG

@@ -1,3 +1,12 @@
+v2.13.0 (2nd November 2024)
+- Permit Ascii86 v1.0 and v2.0 (https://github.com/yob/pdf-reader/pull/539)
+- Allow StringIO type for PDF::Reader input (https://github.com/yob/pdf-reader/pull/535)
+
+v2.12.0 (26th December 2023)
+- Fix a sorbet method signature (http://github.com/yob/pdf-reader/pull/512)
+- Reduce allocations when parsing PDFs with hex strings (http://github.com/yob/pdf-reader/pull/528)
+- Fix text extraction of some rare unicode codepoints (http://github.com/yob/pdf-reader/pull/529)
+
 v2.11.0 (26th October 2022)
 - Various bug fixes
 - Expanded sorbet type annotations

data/README.md

@@ -20,7 +20,7 @@ page.
 The recommended installation method is via Rubygems.
 
 ```ruby
-  gem install pdf-reader
+gem install pdf-reader
 ```
 
 # Usage
@@ -30,23 +30,23 @@ level information (metadata, page count, bookmarks, etc) is available via
 this object.
 
 ```ruby
-    reader = PDF::Reader.new("somefile.pdf")
+reader = PDF::Reader.new("somefile.pdf")
 
-    puts reader.pdf_version
-    puts reader.info
-    puts reader.metadata
-    puts reader.page_count
+puts reader.pdf_version
+puts reader.info
+puts reader.metadata
+puts reader.page_count
  ```
 
 PDF::Reader.new accepts an IO stream or a filename. Here's an example with
 an IO stream:
 
 ```ruby
-    require 'open-uri'
+require 'open-uri'
 
-    io     = open('http://example.com/somefile.pdf')
-    reader = PDF::Reader.new(io)
-    puts reader.info
+io     = open('http://example.com/somefile.pdf')
+reader = PDF::Reader.new(io)
+puts reader.info
  ```
 
 If you open a PDF with File#open or IO#open, I strongly recommend using "rb"
@@ -54,47 +54,47 @@ mode to ensure the file isn't mangled by ruby being 'helpful'. This is
 particularly important on windows and MRI >= 1.9.2.
 
 ```ruby
-    File.open("somefile.pdf", "rb") do |io|
-      reader = PDF::Reader.new(io)
-      puts reader.info
-    end
+File.open("somefile.pdf", "rb") do |io|
+  reader = PDF::Reader.new(io)
+  puts reader.info
+end
  ```
 
 PDF is a page based file format, so most visible information is available via
 page-based iteration
 
 ```ruby
-    reader = PDF::Reader.new("somefile.pdf")
+reader = PDF::Reader.new("somefile.pdf")
 
-    reader.pages.each do |page|
-      puts page.fonts
-      puts page.text
-      puts page.raw_content
-    end
+reader.pages.each do |page|
+  puts page.fonts
+  puts page.text
+  puts page.raw_content
+end
 ```
 
 If you need to access the full program for rendering a page, use the walk() method
 of PDF::Reader::Page.
 
 ```ruby
-    class RedGreenBlue
-      def set_rgb_color_for_nonstroking(r, g, b)
-        puts "R: #{r}, G: #{g}, B: #{b}"
-      end
-    end
-
-    reader   = PDF::Reader.new("somefile.pdf")
-    page     = reader.page(1)
-    receiver = RedGreenBlue.new
-    page.walk(receiver)
+class RedGreenBlue
+  def set_rgb_color_for_nonstroking(r, g, b)
+    puts "R: #{r}, G: #{g}, B: #{b}"
+  end
+end
+
+reader   = PDF::Reader.new("somefile.pdf")
+page     = reader.page(1)
+receiver = RedGreenBlue.new
+page.walk(receiver)
 ```
 
 For low level access to the objects in a PDF file, use the ObjectHash class like
 so:
 
 ```ruby
-    reader  = PDF::Reader.new("somefile.pdf")
-    puts reader.objects.inspect
+reader  = PDF::Reader.new("somefile.pdf")
+puts reader.objects.inspect
 ```
 
 # Text Encoding
@@ -141,7 +141,7 @@ the spec folder when you checkout a branch from Git.
 To remove any invalid CRLF characters added while checking out a branch from Git, run:
 
 ```ruby
-    rake fix_integrity
+rake fix_integrity
 ```
 
 # Maintainers

data/lib/pdf/reader/buffer.rb

@@ -1,5 +1,5 @@
 # coding: ASCII-8BIT
-# typed: strict
+# typed: true
 # frozen_string_literal: true
 
 ################################################################################
@@ -300,13 +300,12 @@ class PDF::Reader
     # we find a closing >
     #
     def prepare_hex_token
-      finished = :false
       str = "".dup
 
-      until finished == :true
+      loop do
         byte = @io.getbyte
         if byte.nil?
-          finished = :true # unbalanced params
+          break
         elsif (48..57).include?(byte) || (65..90).include?(byte) || (97..122).include?(byte)
           str << byte
         elsif byte <= 32
@@ -315,7 +314,7 @@ class PDF::Reader
           @tokens << str if str.size > 0
           @tokens << ">" if byte != 0x3E # '>'
           @tokens << byte.chr
-          finished = :true
+          break
         end
       end
     end

data/lib/pdf/reader/cmap.rb

@@ -1,5 +1,5 @@
 # coding: utf-8
-# typed: strict
+# typed: true
 # frozen_string_literal: true
 
 ################################################################################
@@ -118,8 +118,8 @@ class PDF::Reader
       result = []
       while unpacked_string.any? do
         if unpacked_string.size >= 2 &&
-            unpacked_string.first.to_i > 0xD800 &&
-            unpacked_string.first.to_i < 0xDBFF
+            unpacked_string.first.to_i >= 0xD800 &&
+            unpacked_string.first.to_i <= 0xDBFF
           # this is a Unicode UTF-16 "Surrogate Pair" see Unicode Spec. Chapter 3.7
           # lets convert to a UTF-32. (the high bit is between 0xD800-0xDBFF, the
           # low bit is between 0xDC00-0xDFFF) for example: U+1D44E (U+D835 U+DC4E)

data/lib/pdf/reader/encoding.rb

@@ -1,5 +1,5 @@
 # coding: utf-8
-# typed: strict
+# typed: true
 # frozen_string_literal: true
 
 ################################################################################
@@ -119,7 +119,7 @@ class PDF::Reader
     #     => [:A]
     #
     def int_to_name(glyph_code)
-      if @enc_name == "Identity-H" || @enc_name == "Identity-V"
+      if @enc_name == :"Identity-H" || @enc_name == :"Identity-V"
         []
       elsif differences[glyph_code]
         [differences[glyph_code]]
@@ -143,7 +143,6 @@ class PDF::Reader
         CONTROL_CHARS.include?(i) ? [i, UNKNOWN_CHAR] : [i,i]
       }
       mapping = Hash[tuples]
-      mapping[nil] = UNKNOWN_CHAR
       mapping
     end
 

data/lib/pdf/reader/font.rb

@@ -82,8 +82,8 @@ class PDF::Reader
       glyph_width_in_glyph_space = glyph_width(code_point)
 
       if @subtype == :Type3
-        x1, y1 = font_matrix_transform(0,0)
-        x2, y2 = font_matrix_transform(glyph_width_in_glyph_space, 0)
+        x1, _y1 = font_matrix_transform(0,0)
+        x2, _y2 = font_matrix_transform(glyph_width_in_glyph_space, 0)
         (x2 - x1).abs.round(2)
       else
         glyph_width_in_glyph_space / 1000.0

data/lib/pdf/reader/lzw.rb

@@ -42,7 +42,7 @@ module PDF
           while bits_left_in_chunk > 0 and @current_pos < @data.size
             chunk = 0 if chunk < 0
             codepoint = @data[@current_pos, 1].to_s.unpack("C*")[0].to_i
-            current_byte = codepoint & (2**@bits_left_in_byte - 1) #clear consumed bits
+            current_byte = codepoint & (2**@bits_left_in_byte - 1).to_i #clear consumed bits
             dif = bits_left_in_chunk - @bits_left_in_byte
             if dif > 0 then  current_byte <<= dif
             elsif dif < 0 then  current_byte >>= dif.abs

data/lib/pdf/reader/object_hash.rb

@@ -612,7 +612,7 @@ class PDF::Reader
       if File.respond_to?(:binread)
         File.binread(input.to_s)
       else
-        File.open(input.to_s,"rb") { |f| f.read } || ""
+        File.open(input.to_s,"rb") { |f| f.read }
       end
     end
 

data/lib/pdf/reader/pages_strategy.rb

@@ -1,5 +1,5 @@
 # coding: utf-8
-# typed: strict
+# typed: true
 # frozen_string_literal: true
 
 ################################################################################

data/lib/pdf/reader/parser.rb

@@ -173,9 +173,7 @@ class PDF::Reader
 
       # add a missing digit if required, as required by the spec
       str << "0" unless str.size % 2 == 0
-      str.chars.each_slice(2).map { |nibbles|
-        nibbles.join("").hex.chr
-      }.join.force_encoding("binary")
+      [str].pack('H*')
     end
     ################################################################################
     # Reads a PDF String from the buffer and converts it to a Ruby String

data/lib/pdf/reader/width_calculator/built_in.rb

@@ -1,5 +1,5 @@
 # coding: utf-8
-# typed: strict
+# typed: true
 # frozen_string_literal: true
 
 require 'afm'

data/rbi/pdf-reader.rbi

@@ -4,7 +4,7 @@ module PDF
     sig { returns(PDF::Reader::ObjectHash) }
     attr_reader :objects
 
-    sig { params(input: T.any(String, Tempfile, IO), opts: T::Hash[T.untyped, T.untyped]).void }
+    sig { params(input: T.any(String, Tempfile, IO, StringIO), opts: T::Hash[T.untyped, T.untyped]).void }
     def initialize(input, opts = {})
       @cache = T.let(T.unsafe(nil), PDF::Reader::ObjectCache)
       @objects = T.let(T.unsafe(nil), PDF::Reader::ObjectHash)
@@ -842,7 +842,7 @@ module PDF
       sig { params(runs: T::Array[PDF::Reader::TextRun]).returns(T::Array[PDF::Reader::TextRun]) }
       def self.exclude_redundant_runs(runs); end
 
-      sig { params(sweep_line_status: T::Array[PDF::Reader::TextRun], event_point: EventPoint).returns(T::Boolean) }
+      sig { params(sweep_line_status: T::Array[PDF::Reader::TextRun], event_point: PDF::Reader::EventPoint).returns(T::Boolean) }
       def self.detect_intersection(sweep_line_status, event_point); end
     end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pdf-reader
 version: !ruby/object:Gem::Version
-  version: 2.11.0
+  version: 2.13.0
 platform: ruby
 authors:
 - James Healy
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-10-26 00:00:00.000000000 Z
+date: 2024-11-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -98,16 +98,28 @@ dependencies:
   name: Ascii85
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
         version: '1.0'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+    - - "!="
+      - !ruby/object:Gem::Version
+        version: 2.0.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
         version: '1.0'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+    - - "!="
+      - !ruby/object:Gem::Version
+        version: 2.0.0
 - !ruby/object:Gem::Dependency
   name: ruby-rc4
   requirement: !ruby/object:Gem::Requirement
@@ -289,9 +301,9 @@ licenses:
 - MIT
 metadata:
   bug_tracker_uri: https://github.com/yob/pdf-reader/issues
-  changelog_uri: https://github.com/yob/pdf-reader/blob/v2.11.0/CHANGELOG
-  documentation_uri: https://www.rubydoc.info/gems/pdf-reader/2.11.0
-  source_code_uri: https://github.com/yob/pdf-reader/tree/v2.11.0
+  changelog_uri: https://github.com/yob/pdf-reader/blob/v2.13.0/CHANGELOG
+  documentation_uri: https://www.rubydoc.info/gems/pdf-reader/2.13.0
+  source_code_uri: https://github.com/yob/pdf-reader/tree/v2.13.0
 post_install_message:
 rdoc_options:
 - "--title"
@@ -312,7 +324,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.32
+rubygems_version: 3.4.10
 signing_key:
 specification_version: 4
 summary: A library for accessing the content of PDF files