pdftoimage 0.2.1 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7385d5aaa8f461f7214d25b9972e5b3cdfd528da1da7c7dfd18b61309e9dd010
-  data.tar.gz: ed6c231fa756f90c9330d9f68fcec469aa447b5446ded5074d711ddee9579d04
+  metadata.gz: 63b80a5a933c53e13c0928aeca1fc5592d91d2c6d93d6e1bc0712e33180469f0
+  data.tar.gz: aa20e7f2a5e45ae52ad1a40c826ba1b0bfdb5c4ead284e1332243d3ddcfd7efa
 SHA512:
-  metadata.gz: 182bac990daff942767ca44b8cd56e3979fa39f334f565a2b7efabb8497b8be042b04e0abfafc735ba0f2023440732093c6bc77edb7ac12ed1ebbb8fc7287634
-  data.tar.gz: 37df49043986c6c02720dec32d076144c199cac1b6b8fcf87c895f4fb1131e297eb85b91f0df1915a7571561076641c74527d18d9d2b74267b813eec4de63d51
+  metadata.gz: 2bde807b5302cf3f0de8fac2beb888b69b6a6b557e9a8a206405feb2b31e7cdc262e51c3bf6b32887a7580c1cea31b3c9aaa329500c12be25e7a237d681fc4cd
+  data.tar.gz: e5857849b1b9a4f60a0ba07501429eceae4a1973331caee859e6d31ae43efc52a48d87e7556e7509af2f1e401724e129c1f921d785d059438f8827814e81c005

data/CHANGELOG.md

@@ -0,0 +1,70 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com).
+
+## [0.3.0] - 2026-03-20
+
+### Added
+- `PDFToImage.open` now accepts IO objects in addition to file paths (#11)
+- `PDFToImage.from_blob` for opening PDFs from raw binary data (#11)
+- `Image#save` now accepts IO objects for output, enabling fully in-memory workflows (#11)
+- Support for opening PDFs from remote URLs (#16)
+
+### Changed
+- Replaced direct ImageMagick CLI calls with MiniMagick (#15)
+
+### Removed
+- Removed iconv dependency (#17)
+
+## [0.2.1] - 2025-04-08
+
+### Fixed
+- "Error determining page count" (#13)
+- Updated shellwords dependency to 0.2.0+ (#7)
+
+## [0.2.0] - 2023-04-20
+
+### Fixed
+- Use of deprecated `File.exists?` method (#4)
+- File paths are now escaped to properly handle spaces and special characters (#3)
+
+### Added
+- Specifying dpi resolution is now supported (#5)
+
+## [0.1.7] - 2018-05-01
+
+### Fixed
+- Updated yard to resolve a vulnerability
+
+## [0.1.6] - 2011-07-13
+
+### Fixed
+- Buggy PDF generators encoding CreationDate and ModDate as UTF-16 instead of ASCII, causing parsing errors
+
+## [0.1.5] - 2011-03-08
+
+### Fixed
+- poppler_utils no longer leaves off the extra padded zero
+
+## [0.1.4] - 2010-11-15
+
+### Fixed
+- Documents with page counts that are exact powers of 10 not parsing properly due to poppler_utils zero-padding behavior
+
+## [0.1.3] - 2010-11-12
+
+### Fixed
+- PDF documents with more than 9 pages not parsing properly (zero-padding issue)
+
+## [0.1.2] - 2010-11-11
+
+### Added
+- Support for blocks upon opening a PDF
+- `quality` method for JPEG/MIFF/PNG compression levels
+- Lazy conversion: PDF conversion is now deferred until saving, improving performance for partial conversions
+
+## [0.1.1] - 2010-11-10
+
+- Initial release

data/lib/pdftoimage/image.rb

@@ -1,3 +1,5 @@
+require 'tempfile'
+
 module PDFToImage
     # A class which is instantiated by PDFToImage when a PDF document
     # is opened.
@@ -26,7 +28,7 @@ module PDFToImage
 
         CUSTOM_IMAGE_METHODS.each do |method|
             define_method(method.to_sym) do |*args|
-                @args << "-#{method} #{args.join(' ')}"
+                @args << [method, args]
 
                 self
             end
@@ -67,18 +69,12 @@ module PDFToImage
         # @param outname [String] The output filename of the image
         #
         def save(outname)
-            generate_temp_file
-
-            cmd = "convert "
-
-            if not @args.empty?
-                cmd += "#{@args.join(' ')} "
+            if outname.respond_to?(:write)
+                save_to_io(outname)
+            else
+                save_to_file(outname)
             end
 
-            cmd += "#{Shellwords.escape(@filename)} #{Shellwords.escape(outname)}"
-
-            PDFToImage.exec(cmd)
-
             return true
         end
 
@@ -94,6 +90,29 @@ module PDFToImage
 
       private
 
+        def save_to_file(outname)
+            generate_temp_file
+
+            image = MiniMagick::Image.open(@filename)
+            @args.each do |method, args|
+                image.send(method, *args)
+            end
+            image.write(outname)
+        end
+
+        def save_to_io(io)
+            tempfile = Tempfile.new(['pdftoimage', '.png'])
+            tempfile.binmode
+            begin
+                save_to_file(tempfile.path)
+                tempfile.rewind
+                IO.copy_stream(tempfile, io)
+            ensure
+                tempfile.close
+                tempfile.unlink
+            end
+        end
+
         def generate_temp_file
             if @opened == false
                 cmd = "pdftoppm -png -f #{@page} #{@pdf_args.join(" ")} -l #{@page} #{Shellwords.escape(@pdf_name)} #{Shellwords.escape(@filename)}"

data/lib/pdftoimage/version.rb

@@ -1,4 +1,4 @@
 module PDFToImage
     # pdftoimage version
-    VERSION = "0.2.1"
+    VERSION = "0.3.0"
 end

data/lib/pdftoimage.rb

@@ -2,8 +2,11 @@ require 'pdftoimage/version'
 require 'pdftoimage/image'
 
 require 'tmpdir'
-require 'iconv'
 require 'shellwords'
+require 'mini_magick'
+require 'open-uri'
+require 'uri'
+require 'stringio'
 
 module PDFToImage
     class PDFError < RuntimeError; end
@@ -20,20 +23,15 @@ module PDFToImage
         raise PDFToImage::PDFError, "poppler_utils not installed"
     end
 
-    begin
-        tmp = `identify -version 2>&1`
-        raise(PDFToImage::PDFError, "ImageMagick not installed") unless tmp.index('ImageMagick')
-    rescue Errno::ENOENT
-        raise PDFToImage::PDFError, "ImageMagick not installed"
-    end
-
     class << self
         # Opens a PDF document and prepares it for splitting into images.
         #
-        # @param filename [String] The filename of the PDF to open
+        # @param source [String, IO] A filename, URL, or IO object containing PDF data
         #
         # @return [Array] An array of images
-        def open(filename, &block)
+        def open(source, &block)
+            filename = resolve_source(source)
+
             if not File.exist?(filename)
                 raise PDFError, "File '#{filename}' not found."
             end
@@ -54,6 +52,16 @@ module PDFToImage
             return images
         end
 
+        # Opens a PDF from raw binary data.
+        #
+        # @param data [String] Binary string of PDF content
+        #
+        # @return [Array] An array of images
+        def from_blob(data, &block)
+            filename = write_to_tempfile(data)
+            open(filename, &block)
+        end
+
         # Executes the specified command, returning the output.
         #
         # @param cmd [String] The command to run
@@ -102,6 +110,41 @@ module PDFToImage
             return matches[1].to_i
         end
 
+        def resolve_source(source)
+            if source.respond_to?(:read)
+                write_to_tempfile(source.read)
+            elsif url?(source)
+                download_file(source)
+            else
+                source
+            end
+        end
+
+        def write_to_tempfile(data)
+            tempfile = File.join(@@pdf_temp_dir, "#{random_name}.pdf")
+            File.open(tempfile, 'wb') { |f| f.write(data) }
+            tempfile
+        end
+
+        def url?(filename)
+            uri = URI.parse(filename)
+            uri.is_a?(URI::HTTP) || uri.is_a?(URI::HTTPS)
+        rescue URI::InvalidURIError
+            false
+        end
+
+        def download_file(url)
+            tempfile = File.join(@@pdf_temp_dir, "#{random_name}.pdf")
+            remote = URI.open(url)
+            File.open(tempfile, 'wb') do |file|
+                file.write(remote.read)
+            end
+            remote.close
+            tempfile
+        rescue OpenURI::HTTPError, SocketError, Errno::ECONNREFUSED => e
+            raise PDFError, "Failed to download '#{url}': #{e.message}"
+        end
+
         # Generate a random file name in the system's tmp folder
         def random_filename
             File.join(@@pdf_temp_dir, random_name)

metadata

@@ -1,43 +1,42 @@
 --- !ruby/object:Gem::Specification
 name: pdftoimage
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.3.0
 platform: ruby
 authors:
 - Rob Flynn
-autorequire: 
 bindir: bin
 cert_chain: []
-date: 2025-04-08 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: iconv
+  name: shellwords
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: 0.2.2
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: 0.2.2
 - !ruby/object:Gem::Dependency
-  name: shellwords
+  name: mini_magick
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.2.2
+        version: '4.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.2.2
+        version: '4.0'
 description: A ruby gem for converting PDF documents into a series of images. This
   module is based off poppler_utils and ImageMagick.
 email: rob@thingerly.com
@@ -45,7 +44,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- ChangeLog.rdoc
+- CHANGELOG.md
 - LICENSE
 - README.rdoc
 - lib/pdftoimage.rb
@@ -55,9 +54,8 @@ homepage: https://github.com/robflynn/pdftoimage
 licenses:
 - MIT
 metadata:
-  changelog_uri: https://github.com/robflynn/pdftoimage/blob/master/ChangeLog.rdoc
+  changelog_uri: https://github.com/robflynn/pdftoimage/blob/master/CHANGELOG.md
   source_code_uri: https://github.com/robflynn/pdftoimage/
-post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -65,15 +63,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: '2.7'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3.1
-signing_key: 
+rubygems_version: 3.6.7
 specification_version: 4
 summary: A ruby gem for converting PDF documents into a series of images.
 test_files: []

data/ChangeLog.rdoc

@@ -1,28 +0,0 @@
-=== 0.2.0 / 2023-04-20
-* Fixed use of deprecated File.exists? method (pr#4 from Thornolf)
-* File paths are now escaped to properly handle spaces and special characters (pr#3 from drnic)
-* Specifying dpi resolution is now supported (pr#5 from lehf)
-
-=== 0.1.7 / 2018-05-01
-* Updated yard to resolve a vulnerability.
-
-=== 0.1.6 / 2011-07-13
-* Buggy PDF generators try to encode CreationDate and ModDate as UTF-16 as opposed to ASCII.  This leads to parsing errors where the code was assuming UTF-8 encoding was in use.
-
-=== 0.1.5 / 2011-03-08
-* Fixed a bug due to the fact that poppler_utils no longer leaves off the extra padded zero.
-
-=== 0.1.4 / 2010-11-15
-* Fixed a bug concerning documents with page counts that are exact powers of 10. poppler_utils prepends one less zero to the page counts when a document count is a power of 10. This is now fixed in PDFToImage.
-
-=== 0.1.3 / 2010-11-12
-* Fixed a problem where PDF documents with more than 9 pages were not parsing properly. (embarrassing 0 padding problem.)
-
-=== 0.1.2 / 2010-11-11
-* Added support for blocks upon opening a PDF
-* Image objects now support the "quality" method for JPEG/MIFF/PNG compression levels.
-* PDF conversion is now deferred until saving. This greatly speeds up the conversion process in cases where you only want a few pages out of a large document converted.
-
-=== 0.1.1 / 2010-11-10
-
-* Initial release: