chupa-text-decomposer-pdf 1.0.0 → 1.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 1f536d0590910cc072e5dc47308413752872d9e0
-  data.tar.gz: 21cd886ed411e604ad60026ad82ddd738650e6ce
+  metadata.gz: 6e31d3498186c960a9dae07539e83f77ffa5b995
+  data.tar.gz: 6ecc6033cd1420eb5c7dba3540cf9b4bdca569e9
 SHA512:
-  metadata.gz: 5063792608deea8b42f210ab05b276d0305cb50b4098328d8b85745c1115429a087030aabd05898ea1046e556d270703189ab5f1445af24e7b96523ea9e910d1
-  data.tar.gz: 5481c44dfca54ab40c90d11c555e37926fc466a72728b1a81e41d3bdc53cd0912322588d5b9a0b1f102c896aa7828449bca9a9f8f1fbccb9b84c12cd04d77d1e
+  metadata.gz: 661698768712b75f81cccef8df76cdd86ea76ef95bb38320d0e713c2a2a0a68cc222c62c64219baad59b72788bcb5ff5e0fee0277ef2f74125c3a6e24d1a6ca6
+  data.tar.gz: 54d47d4bbd031c02f8774200177b29c5c112a574f812bc68ee43d20019a00e461e8ca4aad955f6c50913e28578656ffdaa12fdca33e04d603df32f9c79662c62

data/chupa-text-decomposer-pdf.gemspec

@@ -22,14 +22,15 @@ end
 
 Gem::Specification.new do |spec|
   spec.name = "chupa-text-decomposer-pdf"
-  spec.version = "1.0.0"
+  spec.version = "1.0.1"
   spec.homepage = "https://github.com/ranguba/chupa-text-decomposer-pdf"
   spec.authors = ["Kouhei Sutou"]
   spec.email = ["kou@clear-code.com"]
   readme = File.read("README.md", :encoding => "UTF-8")
   entries = readme.split(/^\#\#\s(.*)$/)
   description = clean_white_space.call(entries[entries.index("Description") + 1])
-  spec.summary, spec.description, = description.split(/\n\n+/, 3)
+  spec.summary = description.split(/\n\n+/, 2).first
+  spec.description = description
   spec.license = "LGPLv2.1 or later"
   spec.files = ["#{spec.name}.gemspec"]
   spec.files += ["README.md", "LICENSE.txt", "Rakefile", "Gemfile"]

data/doc/text/news.md

@@ -1,5 +1,11 @@
 # News
 
+## 1.0.1: 2014-02-16
+
+### Improvements
+
+  * Added a new line between pages.
+
 ## 1.0.0: 2014-01-05
 
 The first release!!!

data/lib/chupa-text/decomposers/pdf.rb

@@ -32,7 +32,10 @@ module ChupaText
         document = Poppler::Document.new(data.body)
         text = ""
         document.each do |page|
-          text << page.get_text
+          page_text = page.get_text
+          next if page_text.empty?
+          text << "\n" unless text.empty?
+          text << page_text
         end
         text_data = TextData.new(text)
         text_data.uri = data.uri

data/test/test-pdf.rb

@@ -125,7 +125,7 @@ class TestPDF < Test::Unit::TestCase
 
     sub_test_case("multi pages") do
       def test_body
-        assert_equal(["Page1Page2"], decompose.collect(&:body))
+        assert_equal(["Page1\nPage2"], decompose.collect(&:body))
       end
 
       private

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: chupa-text-decomposer-pdf
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.0.1
 platform: ruby
 authors:
 - Kouhei Sutou
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-01-05 00:00:00.000000000 Z
+date: 2014-02-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: chupa-text
@@ -109,6 +109,9 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 description: |
+  This is a ChupaText decomposer plugin for to extract text and
+  meta-data from PDF.
+
   You can use `pdf` decomposer.
 email:
 - kou@clear-code.com