# coding: ASCII-8BIT require 'test_helper' class RbpdfHtmlTest < Test::Unit::TestCase class MYPDF < RBPDF def getPageBuffer(page) super end # get text count and x_pos from pdf page def get_html_text_position_x(page, regrep_text, x_pos_exp=nil) count_line, count_text, x_pos, y_pos = get_html_text_position(page, regrep_text, x_pos_exp) return count_line, count_text, x_pos end # get text count and y_pos from pdf page def get_html_text_position_y(page, regrep_text) count_line, count_text, x_pos, y_pos = get_html_text_position(page, regrep_text) return count_line, count_text, y_pos end # get text count and pos from pdf page def get_html_text_position(page, regrep_text, x_pos_exp=nil) content = [] contents = getPageBuffer(page) contents.each_line {|line| content.push line.chomp } count_line = count_text = 0 x_pos = y_pos = -1 content.each do |line| count_line += 1 if line =~ /TJ ET Q$/ # Text Line Count if line =~ regrep_text count_text += 1 line =~ /BT ([0-9.]+) ([0-9.]+) Td/ x_pos = $1 y_pos = $2 if y_pos == -1 # y first position only if x_pos.nil? or y_pos.nil? # Error return count_line, count_text, nil, nil end if !x_pos_exp.nil? and x_pos != x_pos_exp # Error return count_line, count_text, x_pos, y_pos end end end return count_line, count_text, x_pos, y_pos end # get text from pdf page def get_html_text(page) content = [] contents = getPageBuffer(page) contents.each_line {|line| content.push line.chomp } pdf_text = '' content.each do |line| if line =~ /\[\((.*)\)\] TJ ET/ pdf_text << $1 end end return pdf_text end end test "write_html Basic test" do pdf = RBPDF.new pdf.add_page() htmlcontent = '

HTML Example

' pdf.write_html(htmlcontent, true, 0, true, 0) htmlcontent = 'abcdefghijklmnopgrstuvwxyz01234567890 abcdefghijklmnopgrstuvwxyz01234567890 abcdefghijklmnopgrstuvwxyz01234567890 abcdefghijklmnopgrstuvwxyz01234567890 abcdefghijklmnopgrstuvwxyz01234567890' pdf.write_html(htmlcontent, true, 0, true, 0) htmlcontent = '1









2









3









4









5









6









7









8









9









10









11









' pdf.write_html(htmlcontent, true, 0, true, 0) pno = pdf.get_page assert_equal pno, 3 end test "write_html Table test 1" do pdf = RBPDF.new pdf.add_page() tablehtml = '
ab
cd
' pdf.write_html(tablehtml, true, 0, true, 0) htmlcontent = '1









2









3









4









5









6









7









8









9









10









11









' tablehtml = '
ab
c' + htmlcontent + '
' pdf.write_html(tablehtml, true, 0, true, 0) pno = pdf.get_page assert_equal pno, 3 end test "write_html Table test 2" do pdf = MYPDF.new pdf.add_page() htmlcontent = '1









2









3









4









5









6









7









8









9









10









11









' tablehtml = '
ABCDEFGHIJKL
abcdefghijkl
' + htmlcontent + '
' pdf.write_html(tablehtml, true, 0, true, 0) pno = pdf.get_page assert_equal pno, 3 # Page 1 count_line, count_text, xpos1 = pdf.get_html_text_position_x(1, /ABCD/) # Header assert_not_nil xpos1 assert_equal 1, count_text assert_equal 13, count_line count_line, count_text, xpos2 = pdf.get_html_text_position_x(1, /abcd/) assert_not_nil xpos2 assert_equal 1, count_text assert_equal xpos1, xpos2 assert_equal 13, count_line # Page 2 count_line, count_text, xpos2 = pdf.get_html_text_position_x(2, /\([6-9]\)/, xpos1) assert_not_nil xpos2 assert_equal xpos1, xpos2 assert_equal 7, count_line end test "write_html Table thead tag test 1" do pdf = MYPDF.new pdf.add_page() tablehtml = '
ABCDEFGHIJKL
abcdefghijkl
' pdf.write_html(tablehtml, true, 0, true, 0) page = pdf.get_page assert_equal 1, page count_line, count_text, xpos = pdf.get_html_text_position_x(1, /ABCD/) # Header assert_equal 1, count_text end test "write_html Table thead tag test 2" do pdf = MYPDF.new pdf.add_page() htmlcontent = '1









2









3









4









5









6









7









8









9









10









11









' tablehtml = '
ABCDEFGHIJKL
abcdefghijkl
' + htmlcontent + '
' pdf.write_html(tablehtml, true, 0, true, 0) page = pdf.get_page assert_equal 3, page # Page 1 count_line, count_text, xpos1 = pdf.get_html_text_position_x(1, /ABCD/) # Header assert_not_nil xpos1 assert_equal 1, count_text assert_equal 13, count_line count_line, count_text, xpos2 = pdf.get_html_text_position_x(1, /abcd/) assert_not_nil xpos2 assert_equal 1, count_text assert_equal xpos1, xpos2 assert_equal 13, count_line # Page 2 count_line, count_text, xpos2 = pdf.get_html_text_position_x(2, /ABCD/, xpos1) # Header assert_not_nil xpos2 assert_equal 1, count_text assert_equal xpos1, xpos2 assert_equal 10, count_line count_line, count_text, xpos2 = pdf.get_html_text_position_x(2, /abcd/) assert_equal 0, count_text assert_equal 10, count_line count_line, count_text, xpos2 = pdf.get_html_text_position_x(2, /\([6-9]\)/, xpos1) assert_not_nil xpos2 assert_equal xpos1, xpos2 assert_equal 10, count_line # Page 3 count_line, count_text, xpos2 = pdf.get_html_text_position_x(3, /ABCD/, xpos1) # Header assert_not_nil xpos2 assert_equal 1, count_text assert_equal xpos1, xpos2 assert_equal 5, count_line count_line, count_text, xpos2 = pdf.get_html_text_position_x(3, /abcd/) assert_equal 0, count_text assert_equal 5, count_line count_line, count_text, xpos2 = pdf.get_html_text_position_x(3, /\(11\)/, xpos1) assert_not_nil xpos2 assert_equal 1, count_text assert_equal xpos1, xpos2 assert_equal 5, count_line end test "write_html_cell Table thead tag test" do pdf = MYPDF.new pdf.add_page() htmlcontent = '
1









2









3









4









5









6









7









8









9









10









11









' tablehtml ='
Left align Right align Center align
left' + htmlcontent + ' right center
' pdf.write_html_cell(0, 0, '', '',tablehtml) page = pdf.get_page assert_equal 1, page # Page 1 count_line, count_text, xpos1 = pdf.get_html_text_position_x(1, /Left align/) # Header assert_not_nil xpos1 assert_equal 1, count_text assert_equal 13, count_line count_line, count_text, xpos2 = pdf.get_html_text_position_x(1, /left/) assert_not_nil xpos2 assert_equal 1, count_text assert_equal 13, count_line assert_equal xpos1, xpos2 # Page 2 count_line, count_text, xpos2 = pdf.get_html_text_position_x(2, /Left align/, xpos1) # Header assert_not_nil xpos2 assert_equal 1, count_text assert_equal xpos1, xpos2 assert_equal 10, count_line count_line, count_text, xpos2 = pdf.get_html_text_position_x(2, /\(6\)/, xpos1) assert_not_nil xpos2 assert_equal 1, count_text assert_equal xpos1, xpos2 assert_equal 10, count_line # Page 3 count_line, count_text, xpos2 = pdf.get_html_text_position_x(3, /Left align/, xpos1) # Header assert_not_nil xpos2 assert_equal 1, count_text assert_equal xpos1, xpos2 assert_equal 5, count_line count_line, count_text, xpos2 = pdf.get_html_text_position_x(3, /\(11\)/, xpos1) assert_not_nil xpos2 assert_equal 1, count_text assert_equal xpos1, xpos2 assert_equal 5, count_line end test "write_html_cell Table thead tag cellpadding x position test" do pdf = MYPDF.new pdf.add_page() htmlcontent = '
1









2









3









4









5









6









7









8









9









10









11









' tablehtml ='
Left align Center align Right align
left center right' + htmlcontent + '
' pdf.write_html_cell(0, 0, '', '',tablehtml) page = pdf.get_page assert_equal 1, page # Page 1 count_line, count_text, xpos1 = pdf.get_html_text_position_x(1, /Right align/) # Header assert_not_nil xpos1 assert_equal 1, count_text assert_equal 13, count_line count_line, count_text, xpos2 = pdf.get_html_text_position_x(1, /right/) assert_not_nil xpos2 assert_equal 1, count_text assert_equal xpos1, xpos2 assert_equal 13, count_line # Page 2 count_line, count_text, xpos2 = pdf.get_html_text_position_x(2, /Right align/, xpos1) # Header assert_not_nil xpos2 assert_equal 1, count_text assert_equal xpos1, xpos2 assert_equal 10, count_line count_line, count_text, xpos2 = pdf.get_html_text_position_x(2, /\(6\)/, xpos1) assert_not_nil xpos2 assert_equal 1, count_text assert_equal xpos1, xpos2 assert_equal 10, count_line end test "write_html_cell Table thead tag cellpadding y position test 1" do pdf = MYPDF.new pdf.add_page() table_start='' table_col='' table_end='
Left alignCenter alignRight align
AAABBBCCC
' tablehtml= table_start + table_col * 30 + table_end pdf.write_html_cell(0, 0, '', '',tablehtml) # Page 1 count_line, count_text, ypos1 = pdf.get_html_text_position_y(1, /Left align/) # Header assert_not_nil ypos1 assert_equal 1, count_text assert_equal 65, count_line count_line, count_text, ypos2 = pdf.get_html_text_position_y(1, /AAA/) assert_not_nil ypos2 assert_equal 20, count_text assert_equal 65, count_line base_pos = ypos1.to_i - ypos2.to_i # Page 2 count_line, count_text, ypos1 = pdf.get_html_text_position_y(2, /Left align/) # Header assert_not_nil ypos2 assert_equal 1, count_text assert_equal 34, count_line count_line, count_text, ypos2 = pdf.get_html_text_position_y(2, /AAA/) assert_not_nil ypos2 assert_equal 10, count_text assert_equal 34, count_line assert_equal base_pos, ypos1.to_i - ypos2.to_i end test "write_html_cell Table thead tag cellpadding y position test 2" do pdf = MYPDF.new pdf.add_page() table_start='abc
' table_col='' table_end='
Left alignCenter alignRight align
AAABBBCCC
' tablehtml= table_start + table_col * 30 + table_end pdf.write_html_cell(0, 0, '', '',tablehtml) # Page 1 count_line, count_text, ypos1 = pdf.get_html_text_position_y(1, /Left align/) # Header assert_not_nil ypos1 assert_equal 1, count_text assert_equal 66, count_line count_line, count_text, ypos2 = pdf.get_html_text_position_y(1, /AAA/) assert_not_nil ypos2 assert_equal 20, count_text assert_equal 66, count_line base_pos = ypos1.to_i - ypos2.to_i # Page 2 count_line, count_text, ypos1 = pdf.get_html_text_position_y(2, /Left align/) # Header assert_not_nil ypos2 assert_equal 1, count_text assert_equal 34, count_line count_line, count_text, ypos2 = pdf.get_html_text_position_y(2, /AAA/) assert_not_nil ypos2 assert_equal 10, count_text assert_equal 34, count_line assert_equal base_pos, ypos1.to_i - ypos2.to_i end test "write_html ASCII text test" do pdf = MYPDF.new pdf.add_page() text = 'HTML Example' htmlcontent = '

' + text + '

' pdf.write_html(htmlcontent, true, 0, true, 0) page = pdf.get_page assert_equal 1, page content = [] contents = pdf.getPageBuffer(1) contents.each_line {|line| content.push line.chomp } count_text = 0 content.each do |line| count_text += 1 unless line.scan(text).empty? end assert_equal count_text, 1 end test "write_html Non ASCII text test" do pdf = MYPDF.new pdf.add_page() text = 'HTML Example ' + "\xc2\x83\xc2\x86" htmlcontent = '

' + text + '

' pdf.write_html(htmlcontent, true, 0, true, 0) page = pdf.get_page assert_equal 1, page content = [] contents = pdf.getPageBuffer(1) contents.each_line {|line| content.push line.chomp } text = 'HTML Example ' + "\x83\x86" text.force_encoding('ASCII-8BIT') if text.respond_to?(:force_encoding) count_text = 0 content.each do |line| line.force_encoding('ASCII-8BIT') if line.respond_to?(:force_encoding) count_text += 1 unless line.scan(text).empty? end assert_equal count_text, 1 end test "works internal links out of page range" do pdf = RBPDF.new pdf.add_page() htmlcontent = 'FooLink' pdf.write_html(htmlcontent, true, 0, true, 0) assert_nothing_raised do pdf.Close end assert_nothing_raised do pdf.Output end end test "write_html tag test" do pdf = MYPDF.new pdf.set_print_header(false) pdf.add_page() text = ' ' + 'A' * 70 htmlcontent = '' + text + '' pdf.write_html(htmlcontent, true, 0, true, 0) pdf_text = pdf.get_html_text(1) assert_equal 'A' * 70, pdf_text end test "write_html tag test" do pdf = MYPDF.new pdf.set_print_header(false) pdf.add_page() text = ' ' + 'A' * 70 htmlcontent = '' + text + '' pdf.write_html(htmlcontent, true, 0, true, 0) pdf_text = pdf.get_html_text(1) assert_equal 'A' * 70, pdf_text end test "write_html tag test" do pdf = MYPDF.new pdf.set_print_header(false) pdf.add_page() text = ' ' + 'A' * 70 htmlcontent = '' + text + '' pdf.write_html(htmlcontent, true, 0, true, 0) pdf_text = pdf.get_html_text(1) assert_equal 'A' * 70, pdf_text end test "write_html 
 tag space 1 test" do
    pdf = MYPDF.new
    pdf.set_print_header(false)
    pdf.add_page()

    text = ' ' + 'A' * 70
    htmlcontent = '
' + text + '
'

    pdf.write_html(htmlcontent, true, 0, true, 0)
    pdf_text = pdf.get_html_text(1)
    assert_equal "\xa0" + 'A' * 70, pdf_text
  end

  test "write_html 
 tag space 2 test" do
    pdf = MYPDF.new
    pdf.set_print_header(false)
    pdf.add_page()

    text = '  ' + 'A' * 70
    htmlcontent = '
' + text + '
'

    pdf.write_html(htmlcontent, true, 0, true, 0)
    pdf_text = pdf.get_html_text(1)
    assert_equal "\xa0" * 2 + 'A' * 70, pdf_text
  end

  test "write_html Character Entities test" do
    pdf = MYPDF.new
    pdf.set_print_header(false)

    character_entities = {
      '<'    => '<',
      '>'    => '>',
      '&'   => '&',
      '"'  => '"',
      ' '  => "\xa0",
      '¢'  => "\xa2",
      '£' => "\xa3",
      '¥'   => "\xa5",
      '©'  => "\xa9",
      '®'   => "\xae",
      '€'  => "\x80",
    }
    character_entities.each {|ce, c|
      pdf.add_page()
      page = pdf.get_page
      pdf.write_html(ce, true, 0, true, 0)
      pdf_text = pdf.get_html_text(page)
      assert_equal '[' + ce + ']:' + c, '[' + ce + ']:' + pdf_text
    }
  end

  test "write_html Character Entities test pre mode" do
    pdf = MYPDF.new
    pdf.set_print_header(false)

    character_entities = {
      '<'    => '<',
      '>'    => '>',
      '&'   => '&',
      '"'  => '"',
      ' '  => "\xa0",
      '¢'  => "\xa2",
      '£' => "\xa3",
      '¥'   => "\xa5",
      '©'  => "\xa9",
      '®'   => "\xae",
      '€'  => "\x80",
    }
    character_entities.each {|ce, c|
      pdf.add_page()
      page = pdf.get_page
      pdf.write_html('
' + ce + '
', true, 0, true, 0)
      pdf_text = pdf.get_html_text(page)
      assert_equal '[' + ce + ']:' + c, '[' + ce + ']:' + pdf_text
    }
  end

  test "unhtmlentities test" do
    pdf = RBPDF.new
    character_entities = {
      '<'    => '<',
      '>'    => '>',
      '&'   => '&',
      '"'  => '"',
      ' '  => "\xc2\xa0",
      '¢'  => "\xc2\xa2",
      '£' => "\xc2\xa3",
      '¥'   => "\xc2\xa5",
      '©'  => "\xc2\xa9",
      '®'   => "\xc2\xae",
      '€'  => "\xe2\x82\xac",
    }
    character_entities.each {|ce, c|
      text = pdf.unhtmlentities(ce)
      text.force_encoding('ASCII-8BIT') if text.respond_to?(:force_encoding)
      assert_equal '[' + ce + ']:' + c, '[' + ce + ']:' + text
    }
  end
end