Kouhei Sutou
null+****@clear*****
Sun Feb 16 22:52:41 JST 2014
Kouhei Sutou 2014-02-16 22:52:41 +0900 (Sun, 16 Feb 2014) New Revision: d6cefcf01717126b2eed02e023cc2dfb04a011c1 https://github.com/ranguba/chupa-text-decomposer-pdf/commit/d6cefcf01717126b2eed02e023cc2dfb04a011c1 Message: Add new line between page Modified files: lib/chupa-text/decomposers/pdf.rb test/test-pdf.rb Modified: lib/chupa-text/decomposers/pdf.rb (+4 -1) =================================================================== --- lib/chupa-text/decomposers/pdf.rb 2014-01-05 16:06:58 +0900 (49b1981) +++ lib/chupa-text/decomposers/pdf.rb 2014-02-16 22:52:41 +0900 (94c864f) @@ -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 Modified: test/test-pdf.rb (+1 -1) =================================================================== --- test/test-pdf.rb 2014-01-05 16:06:58 +0900 (212fef7) +++ test/test-pdf.rb 2014-02-16 22:52:41 +0900 (1b71db4) @@ -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 -------------- next part -------------- HTML����������������������������... 다운로드