grim 1.3.0 → 1.3.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 351b803d58cd1849dbe87c987f23fe3bff91bdc1
-  data.tar.gz: 79a712dd44dee6e7f9e7dcb562242ed4b26d0652
+  metadata.gz: 30464651a26c1f6e432aff72789ab8f1f2af0ce1
+  data.tar.gz: cc290f2afdafe2e16001a8ed3e05a3c3730a1c00
 SHA512:
-  metadata.gz: b0eb570ca92b151dd08c0cc27481a7e8e56d87c65dcfd29d10ead8ec8b29b42f36568091bb6e781024c6ee14c14a0154591e55968582b112eca943d8e2c20a48
-  data.tar.gz: 3620c88137845bb798e4874a41ecc537d41982b988298fad9cd2c4caa4e5d9ce0ce0887a967fede7577acf229197321aeb3038ea5c381aa9bfd03d68cc35bf18
+  metadata.gz: e4aa1e307eb53b753676a77dc2d4b15880764c49b0c4b647062ed8f54e0757b1df24915c71a2aaceb28013a12250da7db283d3195a843c0a69d69b7cfb757913
+  data.tar.gz: 79d39dd5645978619f81f056e3c089e60193bc2358d6e37d8aaff6d49e4f33d23c091ffb4602e7e014ba244acb9199e3aed095db20ac9b7bce7e68cc58ade64c

data/README.md

@@ -113,6 +113,7 @@ pdf[3].save('/path/to/image.png')
 * [@BobaFaux](https://github.com/BobaFaux)
 * [@Rubikan](https://github.com/Rubikan)
 * [@victormier](https://github.com/victormier)
+* [@philgooch][(https://github.com/philgooch)]
 
 ## License
 

data/lib/grim/page.rb

@@ -40,17 +40,22 @@ module Grim
       Grim.processor.save(@pdf, @index, path, options)
     end
 
-    # Extracts the text from the selected page.
+    # Extracts the text from the selected page, using additional options.
     #
     # For example:
     #
     #   pdf[1].text
     #   # => "This is text from slide 2.\n\nAnd even more text from slide 2."
     #
+    #   pdf[1].text({flags: ["-table"]})
     # Returns a String.
     #
-    def text
-      command = [@pdftotext_path, "-enc", "UTF-8", "-f", @number, "-l", @number, Shellwords.escape(@pdf.path), "-"].join(' ')
+    def text(options={})
+      flags = options.fetch(:flags, [])
+      command_parts = [@pdftotext_path, "-enc", "UTF-8", "-f", @number, "-l", @number]
+      command_parts += flags if flags.length > 0
+      command_parts += [Shellwords.escape(@pdf.path), "-"]
+      command = command_parts.join(' ')
       Grim.logger.debug { "Running pdftotext command" }
       Grim.logger.debug { command }
       `#{command}`

data/lib/grim/version.rb

@@ -1,4 +1,4 @@
 # encoding: UTF-8
 module Grim
-  VERSION = "1.3.0" unless defined?(::Grim::VERSION)
+  VERSION = "1.3.1" unless defined?(::Grim::VERSION)
 end

data/spec/lib/grim/page_spec.rb

@@ -51,6 +51,14 @@ describe Grim::Page do
         eq("Step 1: get someone to print this curve for you to scale, 72” wide\nStep 2: Get a couple 55 gallon drums\n\n\f")
     end
 
+    it "should extract tabular data with the -table option" do
+      pdf = Grim::Pdf.new(fixture_path("table.pdf"))
+      expect(pdf[0].text({flags: ["-table"]})).to \
+        include(
+        "      Male                                                           979 (85)                  968 (85)\n\n" +
+        "      Female                                                         169 (15)                  169 (15)\n")
+    end
+
     it "works with full path to pdftotext" do
       pdftotext_path = `which pdftotext`.chomp
       pdf = Grim::Pdf.new(fixture_path("smoker.pdf"), pdftotext_path: pdftotext_path)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: grim
 version: !ruby/object:Gem::Version
-  version: 1.3.0
+  version: 1.3.1
 platform: ruby
 authors:
 - Jonathan Hoyt
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-06-14 00:00:00.000000000 Z
+date: 2017-05-08 00:00:00.000000000 Z
 dependencies: []
 description: Grim is a simple gem for extracting a page from a pdf and converting
   it to an image as well as extract the text from the page as a string. It basically
@@ -36,6 +36,7 @@ files:
 - lib/pdf_info.ps
 - spec/fixtures/remove_alpha.pdf
 - spec/fixtures/smoker.pdf
+- spec/fixtures/table.pdf
 - spec/fixtures/unprocessable.pdf
 - spec/lib/grim/image_magick_processor_spec.rb
 - spec/lib/grim/multi_processor_spec.rb
@@ -63,13 +64,14 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: grim
-rubygems_version: 2.4.5.1
+rubygems_version: 2.6.11
 signing_key: 
 specification_version: 4
 summary: Extract slides and text from a PDF.
 test_files:
 - spec/fixtures/remove_alpha.pdf
 - spec/fixtures/smoker.pdf
+- spec/fixtures/table.pdf
 - spec/fixtures/unprocessable.pdf
 - spec/lib/grim/image_magick_processor_spec.rb
 - spec/lib/grim/multi_processor_spec.rb