Files
OCRmyPDF/pipeline.svg
T
James R. Barlow 62728205b6 Implement image+text merging in other cases
5 failed, 28 passed

failures:
test_oversample[hocr], test_skip_ocr, test_skip_big, test_maximum_options[hocr],
test_blank_input_pdf,
2016-01-15 15:38:08 -08:00

267 lines
18 KiB
XML

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
<!-- Generated by graphviz version 2.38.0 (20140413.2041)
-->
<!-- Title: Pipeline: Pages: 1 -->
<svg width="1132pt" height="708pt"
viewBox="0.00 0.00 1132.00 708.08" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 704.083)">
<title>Pipeline:</title>
<polygon fill="white" stroke="none" points="-4,4 -4,-704.083 1128,-704.083 1128,4 -4,4"/>
<g id="clust1" class="cluster"><title>clustertasks</title>
<polygon fill="none" stroke="black" points="8,-8 8,-692.083 1116,-692.083 1116,-8 8,-8"/>
<text text-anchor="middle" x="562" y="-664.083" font-family="Times,serif" font-size="30.00" fill="#ff3232">Pipeline:</text>
</g>
<!-- t0 -->
<g id="node1" class="node"><title>t0</title>
<polygon fill="#efa03b" stroke="black" points="936.535,-646.083 713.465,-646.083 709.465,-642.083 709.465,-610.083 932.535,-610.083 936.535,-614.083 936.535,-646.083"/>
<polyline fill="none" stroke="black" points="932.535,-642.083 709.465,-642.083 "/>
<polyline fill="none" stroke="black" points="932.535,-642.083 932.535,-610.083 "/>
<polyline fill="none" stroke="black" points="932.535,-642.083 936.535,-646.083 "/>
<text text-anchor="middle" x="823" y="-622.083" font-family="Times,serif" font-size="20.00">repair_pdf</text>
</g>
<!-- t1 -->
<g id="node2" class="node"><title>t1</title>
<polygon fill="#efa03b" stroke="black" points="914.112,-567.155 710,-584.057 505.888,-567.155 506.078,-539.806 913.922,-539.806 914.112,-567.155"/>
<polygon fill="none" stroke="black" points="918.134,-570.834 710,-588.069 501.866,-570.834 502.11,-535.808 917.89,-535.808 918.134,-570.834"/>
<text text-anchor="middle" x="710" y="-553.596" font-family="Times,serif" font-size="20.00">split_pages</text>
</g>
<!-- t0&#45;&gt;t1 -->
<g id="edge1" class="edge"><title>t0&#45;&gt;t1</title>
<path fill="none" stroke="#0044a0" d="M793.9,-609.961C783.582,-603.89 771.656,-596.873 760.092,-590.069"/>
<polygon fill="#0044a0" stroke="#0044a0" points="761.747,-586.982 751.353,-584.927 758.197,-593.015 761.747,-586.982"/>
</g>
<!-- t12 -->
<g id="node14" class="node"><title>t12</title>
<polygon fill="#efa03b" stroke="black" points="1108.08,-509.109 769.918,-509.109 765.918,-505.109 765.918,-473.109 1104.08,-473.109 1108.08,-477.109 1108.08,-509.109"/>
<polyline fill="none" stroke="black" points="1104.08,-505.109 765.918,-505.109 "/>
<polyline fill="none" stroke="black" points="1104.08,-505.109 1104.08,-473.109 "/>
<polyline fill="none" stroke="black" points="1104.08,-505.109 1108.08,-509.109 "/>
<text text-anchor="middle" x="937" y="-485.109" font-family="Times,serif" font-size="20.00">generate_postscript_stub</text>
</g>
<!-- t0&#45;&gt;t12 -->
<g id="edge19" class="edge"><title>t0&#45;&gt;t12</title>
<path fill="none" stroke="#0044a0" d="M899.32,-610.004C909.979,-604.592 919.748,-597.466 927,-588.083 941.916,-568.78 943.099,-540.385 941.345,-519.486"/>
<polygon fill="#0044a0" stroke="#0044a0" points="944.8,-518.881 940.218,-509.328 937.843,-519.653 944.8,-518.881"/>
</g>
<!-- t2 -->
<g id="node3" class="node"><title>t2</title>
<polygon fill="#efa03b" stroke="black" points="592.299,-509.109 241.701,-509.109 237.701,-505.109 237.701,-473.109 588.299,-473.109 592.299,-477.109 592.299,-509.109"/>
<polyline fill="none" stroke="black" points="588.299,-505.109 237.701,-505.109 "/>
<polyline fill="none" stroke="black" points="588.299,-505.109 588.299,-473.109 "/>
<polyline fill="none" stroke="black" points="588.299,-505.109 592.299,-509.109 "/>
<text text-anchor="middle" x="415" y="-485.109" font-family="Times,serif" font-size="20.00">rasterize_with_ghostscript</text>
</g>
<!-- t1&#45;&gt;t2 -->
<g id="edge2" class="edge"><title>t1&#45;&gt;t2</title>
<path fill="none" stroke="#0044a0" d="M608.89,-535.808C573.672,-527.87 534.524,-519.048 500.679,-511.42"/>
<polygon fill="#0044a0" stroke="#0044a0" points="501.345,-507.982 490.82,-509.198 499.806,-514.811 501.345,-507.982"/>
</g>
<!-- t7 -->
<g id="node9" class="node"><title>t7</title>
<polygon fill="#efa03b" stroke="black" points="314.109,-277.109 19.8906,-277.109 15.8906,-273.109 15.8906,-241.109 310.109,-241.109 314.109,-245.109 314.109,-277.109"/>
<polyline fill="none" stroke="black" points="310.109,-273.109 15.8906,-273.109 "/>
<polyline fill="none" stroke="black" points="310.109,-273.109 310.109,-241.109 "/>
<polyline fill="none" stroke="black" points="310.109,-273.109 314.109,-277.109 "/>
<text text-anchor="middle" x="165" y="-253.109" font-family="Times,serif" font-size="20.00">select_image_layer</text>
</g>
<!-- t1&#45;&gt;t7 -->
<g id="edge11" class="edge"><title>t1&#45;&gt;t7</title>
<path fill="none" stroke="#0044a0" d="M501.985,-548.028C416.651,-540.897 317.351,-528.985 229,-509.109 131.492,-487.174 17,-534.054 17,-434.109 17,-434.109 17,-434.109 17,-374.109 17,-340.481 4.97908,-324.525 27,-299.109 32.8004,-292.415 39.6539,-286.828 47.1559,-282.17"/>
<polygon fill="#0044a0" stroke="#0044a0" points="49.1993,-285.038 56.2361,-277.118 45.7959,-278.921 49.1993,-285.038"/>
</g>
<!-- t13 -->
<g id="node12" class="node"><title>t13</title>
<polygon fill="#efa03b" stroke="black" points="1029.34,-451.109 808.662,-451.109 804.662,-447.109 804.662,-415.109 1025.34,-415.109 1029.34,-419.109 1029.34,-451.109"/>
<polyline fill="none" stroke="black" points="1025.34,-447.109 804.662,-447.109 "/>
<polyline fill="none" stroke="black" points="1025.34,-447.109 1025.34,-415.109 "/>
<polyline fill="none" stroke="black" points="1025.34,-447.109 1029.34,-451.109 "/>
<text text-anchor="middle" x="917" y="-427.109" font-family="Times,serif" font-size="20.00">skip_page</text>
</g>
<!-- t1&#45;&gt;t13 -->
<g id="edge16" class="edge"><title>t1&#45;&gt;t13</title>
<path fill="none" stroke="#0044a0" d="M716.849,-535.484C723.825,-515.965 736.562,-488.763 757,-473.109 768.342,-464.422 781.352,-457.641 794.947,-452.352"/>
<polygon fill="#0044a0" stroke="#0044a0" points="796.223,-455.612 804.44,-448.923 793.845,-449.029 796.223,-455.612"/>
</g>
<!-- t11 -->
<g id="node13" class="node"><title>t11</title>
<polygon fill="#efa03b" stroke="black" points="1068.24,-335.109 687.76,-335.109 683.76,-331.109 683.76,-299.109 1064.24,-299.109 1068.24,-303.109 1068.24,-335.109"/>
<polyline fill="none" stroke="black" points="1064.24,-331.109 683.76,-331.109 "/>
<polyline fill="none" stroke="black" points="1064.24,-331.109 1064.24,-299.109 "/>
<polyline fill="none" stroke="black" points="1064.24,-331.109 1068.24,-335.109 "/>
<text text-anchor="middle" x="876" y="-311.109" font-family="Times,serif" font-size="20.00">tesseract_ocr_and_render_pdf</text>
</g>
<!-- t1&#45;&gt;t11 -->
<g id="edge18" class="edge"><title>t1&#45;&gt;t11</title>
<path fill="none" stroke="#0044a0" d="M710.717,-535.657C712.098,-517.744 715.879,-492.693 726,-473.109 754.651,-417.673 809.56,-368.731 844.403,-341.318"/>
<polygon fill="#0044a0" stroke="#0044a0" points="846.607,-344.038 852.372,-335.148 842.322,-338.503 846.607,-344.038"/>
</g>
<!-- t3 -->
<g id="node4" class="node"><title>t3</title>
<polygon fill="#efa03b" stroke="black" points="564.742,-451.109 269.258,-451.109 265.258,-447.109 265.258,-415.109 560.742,-415.109 564.742,-419.109 564.742,-451.109"/>
<polyline fill="none" stroke="black" points="560.742,-447.109 265.258,-447.109 "/>
<polyline fill="none" stroke="black" points="560.742,-447.109 560.742,-415.109 "/>
<polyline fill="none" stroke="black" points="560.742,-447.109 564.742,-451.109 "/>
<text text-anchor="middle" x="415" y="-427.109" font-family="Times,serif" font-size="20.00">preprocess_deskew</text>
</g>
<!-- t2&#45;&gt;t3 -->
<g id="edge3" class="edge"><title>t2&#45;&gt;t3</title>
<path fill="none" stroke="#0044a0" d="M415,-473.003C415,-469.312 415,-465.322 415,-461.352"/>
<polygon fill="#0044a0" stroke="#0044a0" points="418.5,-461.111 415,-451.111 411.5,-461.111 418.5,-461.111"/>
</g>
<!-- t6 -->
<g id="node8" class="node"><title>t6</title>
<polygon fill="#efa03b" stroke="black" points="354.119,-335.109 39.8808,-335.109 35.8808,-331.109 35.8808,-299.109 350.119,-299.109 354.119,-303.109 354.119,-335.109"/>
<polyline fill="none" stroke="black" points="350.119,-331.109 35.8808,-331.109 "/>
<polyline fill="none" stroke="black" points="350.119,-331.109 350.119,-299.109 "/>
<polyline fill="none" stroke="black" points="350.119,-331.109 354.119,-335.109 "/>
<text text-anchor="middle" x="195" y="-311.109" font-family="Times,serif" font-size="20.00">select_image_for_pdf</text>
</g>
<!-- t2&#45;&gt;t6 -->
<g id="edge9" class="edge"><title>t2&#45;&gt;t6</title>
<path fill="none" stroke="#0044a0" d="M294.315,-473.06C280.461,-467.585 267.283,-460.434 256,-451.109 223.245,-424.039 207.251,-375.559 200.099,-345.207"/>
<polygon fill="#0044a0" stroke="#0044a0" points="203.486,-344.31 197.925,-335.292 196.648,-345.809 203.486,-344.31"/>
</g>
<!-- t4 -->
<g id="node5" class="node"><title>t4</title>
<polygon fill="#efa03b" stroke="black" points="587.95,-393.109 310.05,-393.109 306.05,-389.109 306.05,-357.109 583.95,-357.109 587.95,-361.109 587.95,-393.109"/>
<polyline fill="none" stroke="black" points="583.95,-389.109 306.05,-389.109 "/>
<polyline fill="none" stroke="black" points="583.95,-389.109 583.95,-357.109 "/>
<polyline fill="none" stroke="black" points="583.95,-389.109 587.95,-393.109 "/>
<text text-anchor="middle" x="447" y="-369.109" font-family="Times,serif" font-size="20.00">preprocess_clean</text>
</g>
<!-- t3&#45;&gt;t4 -->
<g id="edge4" class="edge"><title>t3&#45;&gt;t4</title>
<path fill="none" stroke="#0044a0" d="M424.775,-415.003C427.132,-410.878 429.703,-406.379 432.232,-401.952"/>
<polygon fill="#0044a0" stroke="#0044a0" points="435.362,-403.53 437.285,-393.111 429.285,-400.057 435.362,-403.53"/>
</g>
<!-- t3&#45;&gt;t6 -->
<g id="edge8" class="edge"><title>t3&#45;&gt;t6</title>
<path fill="none" stroke="#0044a0" d="M351.041,-415.02C333.086,-409.151 313.871,-401.82 297,-393.109 269.828,-379.08 242.065,-358.149 222.377,-341.96"/>
<polygon fill="#0044a0" stroke="#0044a0" points="224.378,-339.071 214.46,-335.347 219.891,-344.444 224.378,-339.071"/>
</g>
<!-- t5 -->
<g id="node6" class="node"><title>t5</title>
<polygon fill="#efa03b" stroke="black" points="665.666,-335.109 376.334,-335.109 372.334,-331.109 372.334,-299.109 661.666,-299.109 665.666,-303.109 665.666,-335.109"/>
<polyline fill="none" stroke="black" points="661.666,-331.109 372.334,-331.109 "/>
<polyline fill="none" stroke="black" points="661.666,-331.109 661.666,-299.109 "/>
<polyline fill="none" stroke="black" points="661.666,-331.109 665.666,-335.109 "/>
<text text-anchor="middle" x="519" y="-311.109" font-family="Times,serif" font-size="20.00">ocr_tesseract_hocr</text>
</g>
<!-- t4&#45;&gt;t5 -->
<g id="edge5" class="edge"><title>t4&#45;&gt;t5</title>
<path fill="none" stroke="#0044a0" d="M468.994,-357.003C475.274,-352.118 482.229,-346.709 488.905,-341.516"/>
<polygon fill="#0044a0" stroke="#0044a0" points="491.396,-344.013 497.141,-335.111 487.099,-338.487 491.396,-344.013"/>
</g>
<!-- t4&#45;&gt;t6 -->
<g id="edge7" class="edge"><title>t4&#45;&gt;t6</title>
<path fill="none" stroke="#0044a0" d="M370.365,-357.079C342.386,-350.862 310.55,-343.787 281.752,-337.388"/>
<polygon fill="#0044a0" stroke="#0044a0" points="282.225,-333.907 271.704,-335.155 280.707,-340.741 282.225,-333.907"/>
</g>
<!-- t4&#45;&gt;t11 -->
<g id="edge17" class="edge"><title>t4&#45;&gt;t11</title>
<path fill="none" stroke="#0044a0" d="M577.461,-357.079C627.38,-350.563 684.512,-343.106 735.342,-336.47"/>
<polygon fill="#0044a0" stroke="#0044a0" points="735.957,-339.92 745.42,-335.155 735.051,-332.979 735.957,-339.92"/>
</g>
<!-- t8 -->
<g id="node7" class="node"><title>t8</title>
<polygon fill="#efa03b" stroke="black" points="986.109,-277.109 701.891,-277.109 697.891,-273.109 697.891,-241.109 982.109,-241.109 986.109,-245.109 986.109,-277.109"/>
<polyline fill="none" stroke="black" points="982.109,-273.109 697.891,-273.109 "/>
<polyline fill="none" stroke="black" points="982.109,-273.109 982.109,-241.109 "/>
<polyline fill="none" stroke="black" points="982.109,-273.109 986.109,-277.109 "/>
<text text-anchor="middle" x="842" y="-253.109" font-family="Times,serif" font-size="20.00">render_hocr_page</text>
</g>
<!-- t5&#45;&gt;t8 -->
<g id="edge6" class="edge"><title>t5&#45;&gt;t8</title>
<path fill="none" stroke="#0044a0" d="M617.226,-299.079C654.028,-292.699 696.036,-285.416 733.699,-278.886"/>
<polygon fill="#0044a0" stroke="#0044a0" points="734.429,-282.312 743.685,-277.155 733.234,-275.415 734.429,-282.312"/>
</g>
<!-- t9 -->
<g id="node11" class="node"><title>t9</title>
<polygon fill="#efa03b" stroke="black" points="679.486,-277.109 336.514,-277.109 332.514,-273.109 332.514,-241.109 675.486,-241.109 679.486,-245.109 679.486,-277.109"/>
<polyline fill="none" stroke="black" points="675.486,-273.109 332.514,-273.109 "/>
<polyline fill="none" stroke="black" points="675.486,-273.109 675.486,-241.109 "/>
<polyline fill="none" stroke="black" points="675.486,-273.109 679.486,-277.109 "/>
<text text-anchor="middle" x="506" y="-253.109" font-family="Times,serif" font-size="20.00">render_hocr_debug_page</text>
</g>
<!-- t5&#45;&gt;t9 -->
<g id="edge15" class="edge"><title>t5&#45;&gt;t9</title>
<path fill="none" stroke="#0044a0" d="M515.029,-299.003C514.147,-295.204 513.191,-291.087 512.243,-287.002"/>
<polygon fill="#0044a0" stroke="#0044a0" points="515.617,-286.06 509.947,-277.111 508.799,-287.643 515.617,-286.06"/>
</g>
<!-- t10 -->
<g id="node10" class="node"><title>t10</title>
<polygon fill="#efa03b" stroke="black" points="973.082,-219.109 714.918,-219.109 710.918,-215.109 710.918,-183.109 969.082,-183.109 973.082,-187.109 973.082,-219.109"/>
<polyline fill="none" stroke="black" points="969.082,-215.109 710.918,-215.109 "/>
<polyline fill="none" stroke="black" points="969.082,-215.109 969.082,-183.109 "/>
<polyline fill="none" stroke="black" points="969.082,-215.109 973.082,-219.109 "/>
<text text-anchor="middle" x="842" y="-195.109" font-family="Times,serif" font-size="20.00">add_text_layer</text>
</g>
<!-- t8&#45;&gt;t10 -->
<g id="edge12" class="edge"><title>t8&#45;&gt;t10</title>
<path fill="none" stroke="#0044a0" d="M842,-241.003C842,-237.312 842,-233.322 842,-229.352"/>
<polygon fill="#0044a0" stroke="#0044a0" points="845.5,-229.111 842,-219.111 838.5,-229.111 845.5,-229.111"/>
</g>
<!-- t6&#45;&gt;t7 -->
<g id="edge10" class="edge"><title>t6&#45;&gt;t7</title>
<path fill="none" stroke="#0044a0" d="M185.836,-299.003C183.626,-294.878 181.216,-290.379 178.845,-285.952"/>
<polygon fill="#0044a0" stroke="#0044a0" points="181.915,-284.273 174.108,-277.111 175.745,-287.578 181.915,-284.273"/>
</g>
<!-- t6&#45;&gt;t9 -->
<g id="edge14" class="edge"><title>t6&#45;&gt;t9</title>
<path fill="none" stroke="#0044a0" d="M289.577,-299.079C324.86,-292.726 365.115,-285.478 401.259,-278.969"/>
<polygon fill="#0044a0" stroke="#0044a0" points="402.116,-282.372 411.337,-277.155 400.875,-275.482 402.116,-282.372"/>
</g>
<!-- t7&#45;&gt;t10 -->
<g id="edge13" class="edge"><title>t7&#45;&gt;t10</title>
<path fill="none" stroke="#0044a0" d="M314.366,-242.002C317.606,-241.697 320.821,-241.399 324,-241.109 451.228,-229.521 596.262,-218.816 700.44,-211.565"/>
<polygon fill="#0044a0" stroke="#0044a0" points="700.976,-215.036 710.71,-210.852 700.491,-208.053 700.976,-215.036"/>
</g>
<!-- t14 -->
<g id="node15" class="node"><title>t14</title>
<polygon fill="#efa03b" stroke="black" points="774.472,-105.333 939,-78.005 1103.53,-105.333 1103.37,-149.551 774.625,-149.551 774.472,-105.333"/>
<polygon fill="none" stroke="black" points="770.46,-101.94 939,-73.9453 1107.54,-101.94 1107.36,-153.556 770.639,-153.556 770.46,-101.94"/>
<text text-anchor="middle" x="939" y="-111.555" font-family="Times,serif" font-size="20.00">merge_pages</text>
</g>
<!-- t10&#45;&gt;t14 -->
<g id="edge23" class="edge"><title>t10&#45;&gt;t14</title>
<path fill="none" stroke="#0044a0" d="M862.571,-182.814C870.479,-176.165 879.888,-168.254 889.356,-160.293"/>
<polygon fill="#0044a0" stroke="#0044a0" points="891.89,-162.736 897.292,-153.622 887.385,-157.378 891.89,-162.736"/>
</g>
<!-- t9&#45;&gt;t14 -->
<g id="edge24" class="edge"><title>t9&#45;&gt;t14</title>
<path fill="none" stroke="#0044a0" d="M546.87,-241.103C586.226,-225.054 647.626,-200.869 702,-183.109 730.59,-173.771 761.415,-164.679 791.074,-156.405"/>
<polygon fill="#0044a0" stroke="#0044a0" points="792.38,-159.675 801.082,-153.632 790.511,-152.93 792.38,-159.675"/>
</g>
<!-- t13&#45;&gt;t14 -->
<g id="edge20" class="edge"><title>t13&#45;&gt;t14</title>
<path fill="none" stroke="#0044a0" d="M986.636,-414.956C1033.58,-398.748 1087,-369.103 1087,-318.109 1087,-318.109 1087,-318.109 1087,-258.109 1087,-215.948 1054.81,-182.761 1020.46,-159.346"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1021.98,-156.158 1011.7,-153.604 1018.15,-162.013 1021.98,-156.158"/>
</g>
<!-- t11&#45;&gt;t14 -->
<g id="edge22" class="edge"><title>t11&#45;&gt;t14</title>
<path fill="none" stroke="#0044a0" d="M969.056,-299.033C979.177,-293.579 988.239,-286.44 995,-277.109 1020.03,-242.568 998.243,-195.803 974.929,-162.021"/>
<polygon fill="#0044a0" stroke="#0044a0" points="977.661,-159.825 968.996,-153.728 971.968,-163.897 977.661,-159.825"/>
</g>
<!-- t12&#45;&gt;t14 -->
<g id="edge21" class="edge"><title>t12&#45;&gt;t14</title>
<path fill="none" stroke="#0044a0" d="M1006.64,-472.956C1053.58,-456.748 1107,-427.103 1107,-376.109 1107,-376.109 1107,-376.109 1107,-258.109 1107,-220.742 1095.53,-209.426 1069,-183.109 1059.8,-173.988 1049.06,-165.927 1037.76,-158.869"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1039.41,-155.777 1029.03,-153.665 1035.83,-161.791 1039.41,-155.777"/>
</g>
<!-- t15 -->
<g id="node16" class="node"><title>t15</title>
<polygon fill="#efa03b" stroke="black" points="1053.18,-52 828.822,-52 824.822,-48 824.822,-16 1049.18,-16 1053.18,-20 1053.18,-52"/>
<polyline fill="none" stroke="black" points="1049.18,-48 824.822,-48 "/>
<polyline fill="none" stroke="black" points="1049.18,-48 1049.18,-16 "/>
<polyline fill="none" stroke="black" points="1049.18,-48 1053.18,-52 "/>
<text text-anchor="middle" x="939" y="-28" font-family="Times,serif" font-size="20.00">copy_final</text>
</g>
<!-- t14&#45;&gt;t15 -->
<g id="edge25" class="edge"><title>t14&#45;&gt;t15</title>
<path fill="none" stroke="#0044a0" d="M939,-73.8665C939,-69.8921 939,-65.942 939,-62.1676"/>
<polygon fill="#0044a0" stroke="#0044a0" points="942.5,-62.1213 939,-52.1214 935.5,-62.1214 942.5,-62.1213"/>
</g>
</g>
</svg>