pdf-reader 1.1.1 → 2.5.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 652d05cf6a22fad5ecb4b92de1e27ba60cafc6525c5ca524e24c7f9796fe1b83
+  data.tar.gz: 2c7448e97890a9fcbd10ec2cd5bafb9025db2fb75dabaf71a4074c542b1065a1
+SHA512:
+  metadata.gz: ac82452924cf46af98ee15f2a20642b1d06d5b9c22104fe171b5b4612665e482f341e12473805016ccb9d921fc15324ba51675170b369adeace8b278cd1279fb
+  data.tar.gz: b1dc1c4422b0e6bf01092cf724630ba7424fdef1fdaf34f33aaa3a31397caf6ef5a73185a98e6e2828a9e082d87cbca311565397cb064cac20d86e72be27626f

data/CHANGELOG

@@ -1,3 +1,88 @@
+v2.5.0 (6th June 2021)
+- bump minimum ruby version to 2.0
+- Correctly handle trascoding to UTF-8 from some fonts that use a difference table [#344](https://github.com/yob/pdf-reader/pull/344/) 
+- Fix some character spacing issues with the TJ operator [#343](https://github.com/yob/pdf-reader/pull/343)
+- Fix crash with some encrypted PDFs [#348](https://github.com/yob/pdf-reader/pull/348/)
+- Fix positions of text on some PDFs with pages rotated 90° [#350](https://github.com/yob/pdf-reader/pull/350/)
+
+v2.4.2 (28th January 2021)
+- relax ASCII85 dependency to allow 1.x
+- improved support for decompressing objects with slightly malformed zlib data
+
+v.2.4.1 (24th September 2020)
+- Re-vendor font metrics from Adobe to clarify their license
+
+v2.4.0 (21st November 2019)
+- Optimise overlapping characters code introduced in 2.3.0. Text extraction of pages with
+  thousands of characters is still slower than it was in 2.2.1, but it might tolerable
+  for now. See https://github.com/yob/pdf-reader/pull/308 for details.
+- Implement very basic font substitution for Type1 and TrueType fonts that aren't embedded
+- Remove PDF::Hash class. It's been deprecated since 2010, and it's hard to believe anyone
+  is still using it.
+- Several small bug fixes
+
+v2.3.0 (7th November 2019)
+- Text extraction now makes an effort to skip duplicate characters that overlap, a
+  common approach used for a fake "bold" effect, This will make text extraction a bit
+  slower - if that turns out to be an issue I'll look into further optimisations or
+  provide a toggle to turn it off
+- Several small bug fixes
+
+v2.2.1 (27th July 2019)
+- Improve utf8 text extraction from CMaps that contain surrogate pair ligatures
+
+v2.2.0 (18th December 2018)
+- Support additional XRef Stream variants (thanks Stefan Wienert)
+- Add frozen_strings pragma to reduce object allocations on ruby 2.3+
+- various bug fixes
+
+v2.1.0 (15th February 2018)
+- Support extra encrypted PDF variants (thanks to Gyuchang Jun)
+- various bug fixes
+
+v2.0.0 (25th February 2017)
+- various bug fixes
+
+v2.0.0.beta1 (15th February 2017)
+- BREAKING CHANGE: remove all methods that were deprecated in 1.0.0
+- Bug: Support extra encrypted PDF variants (thanks to Gyuchang Jun)
+- various bug fixes
+
+v1.4.1 (2nd January 2017)
+- improve compatibility with ruby 2.4 (thanks Akira Matsuda)
+- various bug fixes
+
+v1.4.0 (22nd February 2016)
+- raise minimum ruby version to 1.9.3
+- print warnings to stderr when deprecated methods are used. These methods have been
+  deprecated for 4 years, so hopefully few people are depending on them
+- Fix exception when a non-breaking space (character 160) is used with a
+  built-in font (helvetica, etc)
+- various bug fixes
+
+v1.3.3 (7th April 2013)
+- various bug fixes
+
+v1.3.2 (26th February 2013)
+- various bug fixes
+
+v1.3.1 (12th February 2013)
+- various bug fixes
+
+v1.3.0 (30th December 2012)
+- Numerous performance optimisations (thanks Alex Dowad)
+- Improved text extraction (thanks Nathaniel Madura)
+- Load less of the hashery gem to reduce core monkey patches
+- various bug fixes
+
+v1.2.0 (28th August 2012)
+- Feature: correctly extract text using surrogate pairs and ligatures
+  (thanks Nathaniel Madura)
+- Speed optimisation: cache tokenised Form XObjects to avoid re-parsing them
+- Feature: support opening documents with some junk bytes prepended to file
+  (thanks Paul Gallagher)
+  - Acrobat does this, so it seemed reasonable to add support
+
 v1.1.1 (9th May 2012)
 - bugfix release to improve parsing of some PDFs
 
@@ -56,10 +141,10 @@ v0.9.2 (24th April 2011)
 
 v0.9.1 (21st December 2010)
 - force gem to only install on ruby 1.8.7 or higher
-  - maintaining supprot for earlier versions takes more time than I have
+  - maintaining support for earlier versions takes more time than I have
     available at the moment
 - bug: fix parsing of obscure pdf name format
-- bug: fix behaviour when loaded in confunction with htmldoc gem
+- bug: fix behaviour when loaded in conjunction with htmldoc gem
 
 v0.9.0 (19th November 2010)
 - support for pdf 1.5+ files that use object and xref streams

data/{README.rdoc → README.md}

@@ -1,4 +1,4 @@
-= Release Notes
+# pdf-reader
 
 The PDF::Reader library implements a PDF parser conforming as much as possible
 to the PDF specification from Adobe.
@@ -15,46 +15,55 @@ higher level functionality - it's not going to render a PDF for you. There are
 a few exceptions to support very common use cases like extracting text from a
 page.
 
-= Installation
+# Installation
 
 The recommended installation method is via Rubygems.
 
+```ruby
   gem install pdf-reader
+```
 
-= Usage
+# Usage
 
 Begin by creating a PDF::Reader instance that points to a PDF file. Document
 level information (metadata, page count, bookmarks, etc) is available via
 this object.
 
+```ruby
     reader = PDF::Reader.new("somefile.pdf")
 
     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'
 
     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"
 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
+ ```
 
 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.pages.each do |page|
@@ -62,10 +71,12 @@ page-based iteration
       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}"
@@ -76,37 +87,32 @@ of PDF::Reader::Page.
     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. You can
-build an ObjectHash instance directly:
-
-    puts PDF::Reader::ObjectHash.new("somefile.pdf")
-
-or via a PDF::Reader instance:
+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
-
-The second method is preferred to increase the effectiveness of internal caching.
+    puts reader.objects.inspect
+```
 
-= Text Encoding
+# Text Encoding
 
 Regardless of the internal encoding used in the PDF all text will be converted
 to UTF-8 before it is passed back from PDF::Reader.
 
-Strings that contain binary data (like font blobs) will be marked as such on
-M17N aware VMs.
+Strings that contain binary data (like font blobs) will be marked as such.
 
-= Former API
+# Former API
 
 Version 1.0.0 of PDF::Reader introduced a new page-based API that provides
 efficient and easy access to any page.
 
-The previous API is marked as deprecated but will continue to work for the
-time being. Eventually calls to the old API will begin triggering deprecation
-warnings before it is completely removed in version 2.0.0.
+The pre-1.0 API was deprecated during the 1.x release series, and has been
+removed from 2.0.0.
 
-= Exceptions
+# Exceptions
 
 There are two key exceptions that you will need to watch out for when processing a
 PDF file:
@@ -126,7 +132,7 @@ don't, 'rescue MalformedPDFError' will catch all the subclassed errors as well.
 Any other exceptions should be considered bugs in either PDF::Reader (please
 report it!).
 
-= PDF Integrity
+# PDF Integrity
 
 Windows developers may run into problems when running specs due to MalformedPDFError's
 This is usually because CRLF characters are automatically added to some of the PDF's in
@@ -134,18 +140,20 @@ 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
+```
 
-= Maintainers
+# Maintainers
 
-- James Healy <mailto:jimmy@deefa.com>
+* James Healy <mailto:jimmy@deefa.com>
 
-= Licensing
+# Licensing
 
 This library is distributed under the terms of the MIT License. See the included file for
 more detail.
 
-= Mailing List
+# Mailing List
 
 Any questions or feedback should be sent to the PDF::Reader google group. It's
 better that any answers be available for others instead of hiding in someone's
@@ -153,19 +161,23 @@ inbox.
 
 http://groups.google.com/group/pdf-reader
 
-= Examples
+# Examples
 
 The easiest way to explain how this works in practice is to show some examples.
 Check out the examples/ directory for a few files.
 
-= Known Limitations
+# Known Limitations
 
 Occasionally some text cannot be extracted properly due to the way it has been
 stored, or the use of invalid bytes. In these cases PDF::Reader will output a
 little UTF-8 friendly box to indicate an unrecognisable character.
 
-= Resources
+# Resources
+
+* PDF::Reader Code Repository: http://github.com/yob/pdf-reader
+
+* PDF Specification: http://www.adobe.com/devnet/pdf/pdf_reference.html
+
+* PDF Tutorial Slide Presentations: https://web.archive.org/web/20150110042057/http://home.comcast.net/~jk05/presentations/PDFTutorials.html
 
-- PDF::Reader Code Repository: http://github.com/yob/pdf-reader
-- PDF Specification: http://www.adobe.com/devnet/pdf/pdf_reference.html
-- PDF Tutorial Slide Presentations: http://home.comcast.net/~jk05/presentations/PDFTutorials.html
+* Developing with PDF (book): http://shop.oreilly.com/product/0636920025269.do

data/Rakefile

@@ -1,19 +1,26 @@
-require "rubygems"
-require "bundler"
-Bundler.setup
-
-require 'rake'
-require 'rake/rdoctask'
-require 'rspec/core/rake_task'
-require 'roodi'
-require 'roodi_task'
+require "bundler/gem_tasks"
+require "digest/md5"
+require "rdoc/task"
+require "rspec/core/rake_task"
+require "yaml"
 
 desc "Default Task"
-task :default => [ :spec ]
+task :default => [ :quality, :spec ]
+
+require 'cane/rake_task'
+require 'morecane'
+
+desc "Run cane to check quality metrics"
+Cane::RakeTask.new(:quality) do |cane|
+  cane.abc_max = 20
+  cane.style_measure = 100
+  cane.max_violations = 31
+
+  cane.use Morecane::EncodingCheck, :encoding_glob => "{app,lib,spec}/**/*.rb"
+end
 
-# run all rspecs
 desc "Run all rspec files"
-RSpec::Core::RakeTask.new("spec") do |t|
+RSpec::Core::RakeTask.new(:spec) do |t|
   t.rspec_opts  = ["--color", "--format progress"]
   t.ruby_opts = "-w"
 end
@@ -31,16 +38,14 @@ Rake::RDocTask.new("doc") do |rdoc|
   rdoc.options << "--inline-source"
 end
 
-RoodiTask.new 'roodi', ['lib/**/*.rb']
-
 desc "Create a YAML file of integrity info for PDFs in the spec suite"
 task :integrity_yaml do
   data = {}
-  Dir.glob("spec/data/**/*.*").each do |path|
+  Dir.glob("spec/data/**/*.*").sort.each do |path|
     path_without_spec = path.gsub("spec/","")
     data[path_without_spec] = {
       :bytes => File.size(path),
-      :md5   => `md5sum "#{path}"`.split.first
+      :md5 => Digest::MD5.hexdigest(File.read(path))
     } if File.file?(path)
   end
   File.open("spec/integrity.yml","wb") { |f| f.write YAML.dump(data)}

data/bin/pdf_callbacks

@@ -9,7 +9,7 @@ require 'pdf/reader'
 receiver = PDF::Reader::PrintReceiver.new
 
 if ARGV.empty?
-  browser = PDF::Reader.new($stdin)
+  browser = PDF::Reader.new(StringIO.new(ARGF.read))
 else
   browser = PDF::Reader.new(ARGV[0])
 end

data/bin/pdf_object

@@ -25,7 +25,10 @@ gen = gen.to_i
 
 # make magic happen
 begin
-  obj = PDF::Reader.object_file(filename, id, gen)
+  obj = nil
+  PDF::Reader.open(filename) do |pdf|
+    obj = pdf.objects[PDF::Reader::Reference.new(id, gen)]
+  end
 
   case obj
   when Hash, Array

data/bin/pdf_text

@@ -1,12 +1,10 @@
 #!/usr/bin/env ruby
 
 require 'rubygems'
-$LOAD_PATH.unshift(File.dirname(__FILE__) + "/../lib")
-
 require 'pdf/reader'
 
 if ARGV.empty?
-  browser = PDF::Reader.new($stdin)
+  browser = PDF::Reader.new(StringIO.new(ARGF.read))
 else
   browser = PDF::Reader.new(ARGV[0])
 end

data/examples/callbacks.rb

@@ -9,12 +9,13 @@
 require 'rubygems'
 require 'pdf/reader'
 
-receiver = PDF::Reader::RegisterReceiver.new
 filename = File.expand_path(File.dirname(__FILE__)) + "/../spec/data/cairo-basic.pdf"
 
 PDF::Reader.open(filename) do |reader|
   reader.pages.each do |page|
+    receiver = PDF::Reader::RegisterReceiver.new
     page.walk(receiver)
+    
     receiver.callbacks.each do |cb|
       puts cb
     end

data/examples/extract_images.rb

@@ -86,14 +86,15 @@ module ExtractImages
       tiff = header.dup
       tiff << short_tag.call( 256, 1, w ) # image width
       tiff << short_tag.call( 257, 1, h ) # image height
-      tiff << long_tag.call( 258, 4, (header.size + (tag_count*12))) # bits per pixel
+      tiff << long_tag.call( 258, 4, (header.size + (tag_count*12) + 4)) # bits per pixel
       tiff << short_tag.call( 259, 1, 1 ) # compression
       tiff << short_tag.call( 262, 1, 5 ) # colorspace - separation
-      tiff << long_tag.call( 273, 1, (10 + (tag_count*12) + 16) ) # data offset
+      tiff << long_tag.call( 273, 1, (10 + (tag_count*12) + 20) ) # data offset
       tiff << short_tag.call( 277, 1, 4 ) # samples per pixel
       tiff << long_tag.call( 279, 1, stream.unfiltered_data.size) # data byte size
       tiff << short_tag.call( 284, 1, 1 ) # planer config
       tiff << long_tag.call( 332, 1, 1)   # inkset - CMYK
+      tiff << [0].pack("I") # next IFD pointer
       tiff << [bpc, bpc, bpc, bpc].pack("IIII")
       tiff << stream.unfiltered_data
       File.open(filename, "wb") { |file| file.write tiff }
@@ -119,10 +120,12 @@ module ExtractImages
       tiff << short_tag.call( 258, 1, 8 ) # bits per pixel
       tiff << short_tag.call( 259, 1, 1 ) # compression
       tiff << short_tag.call( 262, 1, 1 ) # colorspace - grayscale
-      tiff << long_tag.call( 273, 1, (10 + (tag_count*12)) ) # data offset
+      tiff << long_tag.call( 273, 1, (10 + (tag_count*12) + 4) ) # data offset
       tiff << short_tag.call( 277, 1, 1 ) # samples per pixel
       tiff << long_tag.call( 279, 1, stream.unfiltered_data.size) # data byte size
       tiff << short_tag.call( 284, 1, 1 ) # planer config
+      tiff << [0].pack("I") # next IFD pointer
+      p stream.unfiltered_data.size
       tiff << stream.unfiltered_data
       File.open(filename, "wb") { |file| file.write tiff }
     end
@@ -144,12 +147,13 @@ module ExtractImages
       tiff = header.dup
       tiff << short_tag.call( 256, 1, w ) # image width
       tiff << short_tag.call( 257, 1, h ) # image height
-      tiff << long_tag.call( 258, 3, (header.size + (tag_count*12))) # bits per pixel
+      tiff << long_tag.call( 258, 3, (header.size + (tag_count*12) + 4)) # bits per pixel
       tiff << short_tag.call( 259, 1, 1 ) # compression
       tiff << short_tag.call( 262, 1, 2 ) # colorspace - RGB
-      tiff << long_tag.call( 273, 1, (header.size + (tag_count*12) + 12) ) # data offset
+      tiff << long_tag.call( 273, 1, (header.size + (tag_count*12) + 16) ) # data offset
       tiff << short_tag.call( 277, 1, 3 ) # samples per pixel
       tiff << long_tag.call( 279, 1, stream.unfiltered_data.size) # data byte size
+      tiff << [0].pack("I") # next IFD pointer
       tiff << [bpc, bpc, bpc].pack("III")
       tiff << stream.unfiltered_data
       File.open(filename, "wb") { |file| file.write tiff }
@@ -209,8 +213,9 @@ module ExtractImages
       + short_tag.call( 256, cols ) \
       + short_tag.call( 257, h ) \
       + short_tag.call( 259, 4 ) \
-      + long_tag.call( 273, (10 + (5*12)) ) \
+      + long_tag.call( 273, (10 + (5*12) + 4) ) \
       + long_tag.call( 279, len) \
+      + [0].pack("I") \
       + stream.data
       File.open(filename, "wb") { |file| file.write tiff }
     end