Merge pull request #31 from contentinnovation/add-tables

Adds ability to specify pdftotext options

Author: jonmagic

lib/grim/page.rb

@@ -40,17 +40,22 @@ def save(path, options={})
       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}`

lib/grim/version.rb

@@ -1,4 +1,4 @@
 # encoding: UTF-8
 module Grim
-  VERSION = "1.2.0" unless defined?(::Grim::VERSION)
+  VERSION = "1.2.1" unless defined?(::Grim::VERSION)
 end

spec/fixtures/table.pdf

@@ -51,6 +51,14 @@
         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)