gaspar-pdf 0.0.1 → 0.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 61dc07bbed984fb395fe3e6de603f862906c853a
-  data.tar.gz: b1130b45efc157db8a9c0ccc6a6f768d71b6e159
+  metadata.gz: 5d61897dcb86359510caf89940b8b4273f8df92d
+  data.tar.gz: 44482e7a3dd4bb9c53995ad16e49ae9a01142bc0
 SHA512:
-  metadata.gz: 1aa7157bf22ca40cb902fa894a17ac329e52d002b6387fe9fa0850537ab205b4063ad3e6e77a919e1d4e10461c8dc02eabdee733811a4e4481930be54a6fd989
-  data.tar.gz: b4aeb3d4ade931275b57d2924ae1639257634d98460bdfffe85c34a3e7b921d9e4dd7d18fb0f61cd8d17f0540de13875bb097ae582566ce2c49a53459ffee998
+  metadata.gz: a50d871c11e83bb6a696bee1d75df7be959dd2979337d408d3e84c70aa303a04760c343ed255b9385044745fe760bb6889b8881f78f771e1afa5efc8c1c67a42
+  data.tar.gz: 880bee08cf94da0969b4ee738b051a22219b94f0c8facc7bdc34ed9444a54156eb0cf033eb623c2988655229ef2f98b66771eb6bc0d98139f3844f1bf0335c8f

data/README.md

@@ -29,13 +29,18 @@ require 'gaspar'
 # This requires that the pdf-table-extract command is present in your PATH.
 
 Gaspar.parse('document.pdf', 'document.html', {
-  page: 1, format: 'table_html'
+  format: 'table_html'
 })
 
 # Available options:
 # page - page to parse
 # format -  the type of output: [cells_csv,cells_json,cells_xml,table_csv,table_html,table_chtml,table_list]
 
+content = Gaspar.parse_with_content('document.pdf', 'document.html', {
+  format: 'table_html'
+})
+
+# you can get parsed content
 ```
 
 Inspired by [Kristin](https://github.com/ricn/kristin)

data/gaspar-pdf.gemspec

@@ -14,7 +14,7 @@ Gem::Specification.new do |spec|
   spec.license       = 'MIT'
 
   spec.files         = `git ls-files`.split($RS)
-  
+
   spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
   spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
   spec.require_paths = ['lib']

data/lib/gaspar.rb

@@ -2,6 +2,7 @@ require 'gaspar/version'
 require 'open-uri'
 require 'net/http'
 require 'spoon'
+require 'pdf-reader'
 
 # Gaspar Gem
 module Gaspar
@@ -12,34 +13,92 @@ module Gaspar
       @source = source
       @target = target
       @options = options
+      @extractor = extractor
     end
 
     def parse
+      @extractor.extract
+    end
+
+    def parse_with_content
+      @extractor.extract
+      @extractor.content
+    end
+
+    private
+
+    def extractor
+      src = determine_source(@source)
+      pdf = Reader.new(src)
+
+      Extractor.new(
+        src, @target, pdf.page_count, @options
+      )
+    end
+
+    def random_source_name
+      rand(16**16).to_s(16)
+    end
+
+    def download_file(source)
+      tmp_file = "/tmp/#{random_source_name}.pdf"
+      File.open(tmp_file, 'wb') do |saved_file|
+        open(URI.encode(source), 'rb') do |read_file|
+          saved_file.write(read_file.read)
+        end
+      end
+
+      tmp_file
+    end
+
+    def determine_source(source)
+      is_file = File.exist?(source) && !File.directory?(source)
+      is_http = URI(source).scheme == 'http'
+      is_https = URI(source).scheme == 'https'
+
+      unless is_file || is_http || is_https
+        raise IOError, "Source (#{source}) is neither a file nor an URL."
+      end
+
+      is_file ? source : download_file(source)
+    end
+  end
+
+  # Extract data from all pages of PDF
+  class Extractor
+    def initialize(source, target, pages, options)
+      @source = source
+      @target = target
+      @pages = pages
+      @options = options
+    end
+
+    def extract
       unless command_available?
         io_error 'Can\'t find pdf-table-extract executable in PATH'
       end
 
-      src = determine_source(@source)
-      opts = process_options(src).split(' ')
+      opts = process_options.split(' ')
       args = [extract_command, opts].flatten
 
       pid = Spoon.spawnp(*args)
       Process.waitpid(pid)
+      io_error("Could not parse #{@source}") unless $?.exitstatus.zero?
+    end
 
-      io_error("Could not parse #{src}") unless $?.exitstatus.zero?
+    def content
+      open(@target, 'rb').read
     end
 
     private
 
-    def io_error(error_message)
-      raise IOError, error_message
-    end
-
-    def process_options(source)
+    def process_options
       opts = []
-      opts.push("-i #{source}") if source
+      opts.push("-i #{@source}") if @source
       opts.push("-o #{@target}") if @target
-      opts.push("-p #{@options[:page]}") if @options[:page]
+      @pages.times do |p|
+        opts.push("-p #{p + 1}")
+      end
       opts.push("-t #{@options[:format]}") if @options[:format]
 
       opts.join(' ')
@@ -64,38 +123,15 @@ module Gaspar
       nil
     end
 
-    def random_source_name
-      rand(16**16).to_s(16)
-    end
-
-    def download_file(source)
-      tmp_file = "/tmp/#{random_source_name}.pdf"
-      File.open(tmp_file, 'wb') do |saved_file|
-        open(URI.encode(source), 'rb') do |read_file|
-          saved_file.write(read_file.read)
-        end
-      end
-
-      tmp_file
-    end
-
-    def determine_source(source)
-      is_file = File.exist?(source) && !File.directory?(source)
-      is_http = URI(source).scheme == 'http'
-      is_https = URI(source).scheme == 'https'
-
-      unless is_file || is_http || is_https
-        raise IOError, "Source (#{source}) is neither a file nor an URL."
-      end
-
-      is_file ? source : download_file(source)
+    def io_error(error_message)
+      raise IOError, error_message
     end
   end
 
   # Read infor from PDF file usin pdf-reader
   class Reader
     def initialize(source)
-      @reader = PDF::Reader.new(source)
+      @reader = ::PDF::Reader.new(source)
     end
 
     def metadata
@@ -111,9 +147,11 @@ module Gaspar
     end
   end
 
-  # options[:type]
-  # {cells_csv,cells_json,cells_xml,table_csv,table_html,table_chtml,table_list}
   def self.parse(source, target, options = {})
     Parser.new(source, target, options).parse
   end
+
+  def self.parse_with_content(source, target, options = {})
+    Parser.new(source, target, options).parse_with_content
+  end
 end

data/lib/gaspar/version.rb

@@ -1,3 +1,3 @@
 module Gaspar
-  VERSION = '0.0.1'
+  VERSION = '0.0.2'
 end

data/spec/gaspar_spec.rb

@@ -2,35 +2,42 @@ require 'spec_helper'
 
 describe Gaspar do
   before(:all) do
-    @table_pdf = file_path("table.pdf")
-    @target_path = "#{Dir::tmpdir}"
-    @table_html = @target_path + "/output.html"
+    @table_pdf = file_path('table.pdf')
+    @target_path = Dir.tmpdir.to_s
+    @table_html = @target_path + '/output.html'
   end
 
-
   describe '#parse' do
     describe 'with wrong params' do
       it 'should raise error if source file does not exists' do
-        c = Gaspar::Parser.new('unknown.pdf', 'unknown.html')
-        expect { c.parse }.to raise_error(IOError)
+        expect do
+          c = Gaspar::Parser.new('unknown.pdf', 'unknown.html')
+          c.parse
+        end.to raise_error(IOError)
       end
 
       it 'should raise error if source is not file nor url' do
-        c = Gaspar::Parser.new('http://  /.pdf', 'unknown.html')
-        expect { c.parse }.to raise_error(URI::InvalidURIError)
+        expect do
+          c = Gaspar::Parser.new('http://  /.pdf', 'unknown.html')
+          c.parse
+        end.to raise_error(URI::InvalidURIError)
       end
     end
 
     describe 'with write params' do
-      it "should be possible to specify one page" do
-        Gaspar::Parser.new(@table_pdf, @table_html, {
-          page: 2, format: 'table_html'
-        }).parse
+      it 'should be parsed' do
+        Gaspar::Parser.new(@table_pdf, @table_html,
+                           format: 'table_html').parse
 
         doc = Nokogiri::HTML(File.open(@table_html))
         expect(doc.search('//comment()').text).not_to be_empty
       end
-    end
 
+      it 'should get content' do
+        content = Gaspar::Parser.new(@table_pdf, @table_html,
+                                     format: 'table_html').parse_with_content
+        expect(content).not_to be_empty
+      end
+    end
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: gaspar-pdf
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors:
 - 5rabbits