menekis/OCRmyPDF
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Implement “tesstop” (tesseract v4 text-only pages - working name)

Browse Source
This commit is contained in:
James R. Barlow
2017-01-20 17:16:01 -08:00
parent 7acfaf6d34
commit ac40426971
3 changed files with 356 additions and 242 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ocrmypdf/__main__.py
+1 -1
View File
@@ -222,7 +222,7 @@ advanced.add_argument(
"3 - default.")
)
advanced.add_argument(
'--pdf-renderer', choices=['auto', 'tesseract', 'hocr'], default='auto',
'--pdf-renderer', choices=['auto', 'tesseract', 'hocr', 'tesstop'], default='auto',
help="choose OCR PDF renderer - the default option is to let OCRmyPDF "
"choose. The 'tesseract' PDF renderer is more accurate and does a "
"better job and document structure such as recognizing columns. It "
ocrmypdf/pipeline.py
+65 -5
View File
@@ -467,6 +467,19 @@ def preprocess_clean(
unpaper.clean(input_file, output_file, dpi, log)
def select_ocr_image(
infiles,
output_file,
log,
contenxt):
"""Select the image we send for OCR. May not be the same as the display
image depending on preprocessing."""
# For the moment this is always the .pp-clean.png image
image = infiles[0]
re_symlink(image, output_file, log)
def ocr_tesseract_hocr(
input_file,
output_file,
@@ -593,7 +606,7 @@ def combine_layers(
output_file,
log,
context):
text = next(ii for ii in infiles if ii.endswith('.hocr.pdf'))
text = next(ii for ii in infiles if ii.endswith('.text.pdf'))
image = next(ii for ii in infiles if ii.endswith('.image-layer.pdf'))
pdf_text = pypdf.PdfFileReader(open(text, "rb"))
@@ -677,6 +690,31 @@ def ocr_tesseract_and_render_pdf(
output_pdf=output_file,
language=options.language,
engine_mode=options.tesseract_oem,
text_only=False,
tessconfig=options.tesseract_config,
timeout=options.tesseract_timeout,
pagesegmode=options.tesseract_pagesegmode,
log=log)
def ocr_tesseract_textonly_pdf(
infiles,
output_file,
log,
context):
options = context.get_options()
input_image = next((ii for ii in infiles if ii.endswith('.ocr.png')), '')
if not input_image:
raise ValueError("No image rendered?")
skip_pdf = next((ii for ii in infiles if ii.endswith('.pdf')))
tesseract.generate_pdf(
input_image=input_image,
skip_pdf=skip_pdf,
output_pdf=output_file,
language=options.language,
engine_mode=options.tesseract_oem,
text_only=True,
tessconfig=options.tesseract_config,
timeout=options.tesseract_timeout,
pagesegmode=options.tesseract_pagesegmode,
@@ -892,11 +930,19 @@ def build_pipeline(options, work_folder, log, context):
output=".pp-clean.png",
extras=[log, context])
task_select_ocr_image = main_pipeline.collate(
task_func=select_ocr_image,
input=[task_preprocess_clean],
filter=regex(r".*/(\d{6})(?:\.page|\.pp-.*)\.png"),
output=os.path.join(work_folder, r"\1.ocr.png"),
extras=[log, context])
# HOCR OCR
task_ocr_tesseract_hocr = main_pipeline.transform(
task_func=ocr_tesseract_hocr,
input=task_preprocess_clean,
filter=suffix(".pp-clean.png"),
input=task_select_ocr_image,
filter=suffix(".ocr.png"),
output=".hocr",
extras=[log, context])
task_ocr_tesseract_hocr.graphviz(fillcolor='"#00cc66"')
@@ -923,13 +969,14 @@ def build_pipeline(options, work_folder, log, context):
extras=[log, context])
task_select_image_layer.graphviz(
fillcolor='"#00cc66"', shape='diamond')
task_select_image_layer.active_if(options.pdf_renderer == 'hocr')
task_select_image_layer.active_if(
options.pdf_renderer == 'hocr' or options.pdf_renderer == 'tesstop')
task_render_hocr_page = main_pipeline.transform(
task_func=render_hocr_page,
input=task_ocr_tesseract_hocr,
filter=suffix('.hocr'),
output='.hocr.pdf',
output='.text.pdf',
extras=[log, context])
task_render_hocr_page.graphviz(fillcolor='"#00cc66"')
task_render_hocr_page.active_if(options.pdf_renderer == 'hocr')
@@ -944,9 +991,22 @@ def build_pipeline(options, work_folder, log, context):
task_render_hocr_debug_page.active_if(options.pdf_renderer == 'hocr')
task_render_hocr_debug_page.active_if(options.debug_rendering)
# Tesseract OCR + text only PDF
task_ocr_tesseract_textonly_pdf = main_pipeline.collate(
task_func=ocr_tesseract_textonly_pdf,
input=[task_select_ocr_image, task_orient_page],
filter=regex(r".*/(\d{6})(?:\.ocr.png|\.ocr\.oriented\.pdf)"),
output=os.path.join(work_folder, r'\1.text.pdf'),
extras=[log, context])
task_ocr_tesseract_textonly_pdf.graphviz(fillcolor='"#ff69b4"')
task_ocr_tesseract_textonly_pdf.active_if(options.pdf_renderer == 'tesstop')
if tesseract.v4():
task_ocr_tesseract_textonly_pdf.jobs_limit(1)
task_combine_layers = main_pipeline.collate(
task_func=combine_layers,
input=[task_render_hocr_page,
task_ocr_tesseract_textonly_pdf,
task_select_image_layer],
filter=regex(r".*/(\d{6})(?:\.text\.pdf|\.image-layer\.pdf)"),
output=os.path.join(work_folder, r'\1.rendered.pdf'),
pipeline.svg
+290 -236
View File
@@ -4,335 +4,389 @@
<!-- Generated by graphviz version 2.38.0 (20140413.2041)
-->
<!-- Title: Pipeline: Pages: 1 -->
<svg width="1444pt" height="973pt"
viewBox="0.00 0.00 1444.00 973.18" 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(4 969.181)">
<svg width="1544pt" height="1089pt"
viewBox="0.00 0.00 1544.00 1089.14" 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 1085.14)">
<title>Pipeline:</title>
<polygon fill="white" stroke="none" points="-4,4 -4,-969.181 1440,-969.181 1440,4 -4,4"/>
<polygon fill="white" stroke="none" points="-4,4 -4,-1085.14 1540,-1085.14 1540,4 -4,4"/>
<g id="clust1" class="cluster"><title>clustertasks</title>
<polygon fill="none" stroke="black" points="8,-8 8,-957.181 1428,-957.181 1428,-8 8,-8"/>
<text text-anchor="middle" x="718" y="-929.181" font-family="Times,serif" font-size="30.00" fill="#ff3232">Pipeline:</text>
<polygon fill="none" stroke="black" points="8,-8 8,-1073.14 1528,-1073.14 1528,-8 8,-8"/>
<text text-anchor="middle" x="768" y="-1045.14" 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="1219.77,-911.181 1034.23,-911.181 1030.23,-907.181 1030.23,-875.181 1215.77,-875.181 1219.77,-879.181 1219.77,-911.181"/>
<polyline fill="none" stroke="black" points="1215.77,-907.181 1030.23,-907.181 "/>
<polyline fill="none" stroke="black" points="1215.77,-907.181 1215.77,-875.181 "/>
<polyline fill="none" stroke="black" points="1215.77,-907.181 1219.77,-911.181 "/>
<text text-anchor="middle" x="1125" y="-887.181" font-family="Times,serif" font-size="20.00">triage</text>
<polygon fill="#efa03b" stroke="black" points="750.705,-1027.14 541.295,-1027.14 537.295,-1023.14 537.295,-991.141 746.705,-991.141 750.705,-995.141 750.705,-1027.14"/>
<polyline fill="none" stroke="black" points="746.705,-1023.14 537.295,-1023.14 "/>
<polyline fill="none" stroke="black" points="746.705,-1023.14 746.705,-991.141 "/>
<polyline fill="none" stroke="black" points="746.705,-1023.14 750.705,-1027.14 "/>
<text text-anchor="middle" x="644" y="-1003.14" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.triage</text>
</g>
<!-- t1 -->
<g id="node2" class="node"><title>t1</title>
<polygon fill="#efa03b" stroke="black" points="1238.54,-853.181 1015.46,-853.181 1011.46,-849.181 1011.46,-817.181 1234.54,-817.181 1238.54,-821.181 1238.54,-853.181"/>
<polyline fill="none" stroke="black" points="1234.54,-849.181 1011.46,-849.181 "/>
<polyline fill="none" stroke="black" points="1234.54,-849.181 1234.54,-817.181 "/>
<polyline fill="none" stroke="black" points="1234.54,-849.181 1238.54,-853.181 "/>
<text text-anchor="middle" x="1125" y="-829.181" font-family="Times,serif" font-size="20.00">repair_pdf</text>
<polygon fill="#efa03b" stroke="black" points="769.969,-969.141 522.031,-969.141 518.031,-965.141 518.031,-933.141 765.969,-933.141 769.969,-937.141 769.969,-969.141"/>
<polyline fill="none" stroke="black" points="765.969,-965.141 518.031,-965.141 "/>
<polyline fill="none" stroke="black" points="765.969,-965.141 765.969,-933.141 "/>
<polyline fill="none" stroke="black" points="765.969,-965.141 769.969,-969.141 "/>
<text text-anchor="middle" x="644" y="-945.141" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.repair_pdf</text>
</g>
<!-- t0&#45;&gt;t1 -->
<g id="edge1" class="edge"><title>t0&#45;&gt;t1</title>
<path fill="none" stroke="#0044a0" d="M1125,-875.075C1125,-871.384 1125,-867.394 1125,-863.424"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1128.5,-863.182 1125,-853.182 1121.5,-863.182 1128.5,-863.182"/>
<path fill="none" stroke="#0044a0" d="M644,-991.035C644,-987.344 644,-983.354 644,-979.384"/>
<polygon fill="#0044a0" stroke="#0044a0" points="647.5,-979.142 644,-969.142 640.5,-979.142 647.5,-979.142"/>
</g>
<!-- t2 -->
<g id="node3" class="node"><title>t2</title>
<polygon fill="#efa03b" stroke="black" points="1329.11,-774.253 1125,-791.156 920.888,-774.253 921.078,-746.905 1328.92,-746.905 1329.11,-774.253"/>
<polygon fill="none" stroke="black" points="1333.13,-777.932 1125,-795.167 916.866,-777.932 917.11,-742.906 1332.89,-742.906 1333.13,-777.932"/>
<text text-anchor="middle" x="1125" y="-760.694" font-family="Times,serif" font-size="20.00">split_pages</text>
<polygon fill="#efa03b" stroke="black" points="869.82,-890.215 644,-907.116 418.18,-890.215 418.391,-862.869 869.609,-862.869 869.82,-890.215"/>
<polygon fill="none" stroke="black" points="873.852,-893.922 644,-911.125 414.148,-893.922 414.419,-858.871 873.581,-858.871 873.852,-893.922"/>
<text text-anchor="middle" x="644" y="-876.657" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.split_pages</text>
</g>
<!-- t1&#45;&gt;t2 -->
<g id="edge2" class="edge"><title>t1&#45;&gt;t2</title>
<path fill="none" stroke="#0044a0" d="M1125,-817.059C1125,-813.44 1125,-809.484 1125,-805.438"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1128.5,-805.334 1125,-795.334 1121.5,-805.334 1128.5,-805.334"/>
</g>
<!-- t15 -->
<g id="node17" class="node"><title>t15</title>
<polygon fill="#efa03b" stroke="black" points="632.082,-716.208 293.918,-716.208 289.918,-712.208 289.918,-680.208 628.082,-680.208 632.082,-684.208 632.082,-716.208"/>
<polyline fill="none" stroke="black" points="628.082,-712.208 289.918,-712.208 "/>
<polyline fill="none" stroke="black" points="628.082,-712.208 628.082,-680.208 "/>
<polyline fill="none" stroke="black" points="628.082,-712.208 632.082,-716.208 "/>
<text text-anchor="middle" x="461" y="-692.208" font-family="Times,serif" font-size="20.00">generate_postscript_stub</text>
</g>
<!-- t1&#45;&gt;t15 -->
<g id="edge23" class="edge"><title>t1&#45;&gt;t15</title>
<path fill="none" stroke="#0044a0" d="M1026.3,-817.165C989.157,-810.572 946.587,-802.788 908,-795.181 781.899,-770.319 636.479,-738.51 546.633,-718.49"/>
<polygon fill="#0044a0" stroke="#0044a0" points="547.289,-715.05 536.767,-716.289 545.765,-721.882 547.289,-715.05"/>
<path fill="none" stroke="#0044a0" d="M644,-933.019C644,-929.4 644,-925.445 644,-921.399"/>
<polygon fill="#0044a0" stroke="#0044a0" points="647.5,-921.295 644,-911.295 640.5,-921.295 647.5,-921.295"/>
</g>
<!-- t18 -->
<g id="node19" class="node"><title>t18</title>
<polygon fill="#efa03b" stroke="black" points="1025.79,-156.452 1221,-129.134 1416.21,-156.452 1416.03,-200.654 1025.97,-200.654 1025.79,-156.452"/>
<polygon fill="none" stroke="black" points="1021.78,-152.971 1221,-125.091 1420.22,-152.971 1420.01,-204.657 1021.99,-204.657 1021.78,-152.971"/>
<text text-anchor="middle" x="1221" y="-162.669" font-family="Times,serif" font-size="20.00">merge_pages_qpdf</text>
<g id="node20" class="node"><title>t18</title>
<polygon fill="#efa03b" stroke="black" points="383.516,-832.173 20.4844,-832.173 16.4844,-828.173 16.4844,-796.173 379.516,-796.173 383.516,-800.173 383.516,-832.173"/>
<polyline fill="none" stroke="black" points="379.516,-828.173 16.4844,-828.173 "/>
<polyline fill="none" stroke="black" points="379.516,-828.173 379.516,-796.173 "/>
<polyline fill="none" stroke="black" points="379.516,-828.173 383.516,-832.173 "/>
<text text-anchor="middle" x="200" y="-808.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.generate_postscript_stub</text>
</g>
<!-- t1&#45;&gt;t18 -->
<g id="edge33" class="edge"><title>t1&#45;&gt;t18</title>
<path fill="none" stroke="#0044a0" d="M1238.67,-826.639C1321.4,-814.236 1419,-782.049 1419,-699.208 1419,-699.208 1419,-699.208 1419,-319.208 1419,-280.294 1424,-263.161 1398,-234.208 1389.64,-224.894 1379.82,-216.923 1369.17,-210.101"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1370.83,-207.019 1360.46,-204.872 1367.23,-213.02 1370.83,-207.019"/>
<g id="edge29" class="edge"><title>t1&#45;&gt;t18</title>
<path fill="none" stroke="#0044a0" d="M518.14,-936.259C481.198,-930.408 441.05,-922.284 405,-911.141 344.394,-892.407 278.709,-859.14 238.448,-837.118"/>
<polygon fill="#0044a0" stroke="#0044a0" points="239.963,-833.956 229.517,-832.188 236.581,-840.085 239.963,-833.956"/>
</g>
<!-- t21 -->
<g id="node22" class="node"><title>t21</title>
<polygon fill="#efa03b" stroke="black" points="751.49,-156.424 963,-129.109 1174.51,-156.424 1174.31,-200.62 751.688,-200.62 751.49,-156.424"/>
<polygon fill="none" stroke="black" points="747.474,-152.906 963,-125.073 1178.53,-152.906 1178.29,-204.623 747.705,-204.623 747.474,-152.906"/>
<text text-anchor="middle" x="963" y="-162.639" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.merge_pages_qpdf</text>
</g>
<!-- t1&#45;&gt;t21 -->
<g id="edge39" class="edge"><title>t1&#45;&gt;t21</title>
<path fill="none" stroke="#0044a0" d="M769.832,-943.539C1011.96,-929.143 1519,-890.056 1519,-815.173 1519,-815.173 1519,-815.173 1519,-309.173 1519,-237.474 1342.87,-202.283 1188.87,-185.216"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1189.08,-181.719 1178.76,-184.118 1188.32,-188.678 1189.08,-181.719"/>
</g>
<!-- t3 -->
<g id="node4" class="node"><title>t3</title>
<polygon fill="#efa03b" stroke="black" points="1186.88,-716.208 905.117,-716.208 901.117,-712.208 901.117,-680.208 1182.88,-680.208 1186.88,-684.208 1186.88,-716.208"/>
<polyline fill="none" stroke="black" points="1182.88,-712.208 901.117,-712.208 "/>
<polyline fill="none" stroke="black" points="1182.88,-712.208 1182.88,-680.208 "/>
<polyline fill="none" stroke="black" points="1182.88,-712.208 1186.88,-716.208 "/>
<text text-anchor="middle" x="1044" y="-692.208" font-family="Times,serif" font-size="20.00">rasterize_preview</text>
<polygon fill="#efa03b" stroke="black" points="712.317,-832.173 405.683,-832.173 401.683,-828.173 401.683,-796.173 708.317,-796.173 712.317,-800.173 712.317,-832.173"/>
<polyline fill="none" stroke="black" points="708.317,-828.173 401.683,-828.173 "/>
<polyline fill="none" stroke="black" points="708.317,-828.173 708.317,-796.173 "/>
<polyline fill="none" stroke="black" points="708.317,-828.173 712.317,-832.173 "/>
<text text-anchor="middle" x="557" y="-808.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.rasterize_preview</text>
</g>
<!-- t2&#45;&gt;t3 -->
<g id="edge3" class="edge"><title>t2&#45;&gt;t3</title>
<path fill="none" stroke="#0044a0" d="M1097.12,-742.813C1089.24,-736.345 1080.66,-729.296 1072.73,-722.788"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1074.71,-719.888 1064.76,-716.249 1070.27,-725.299 1074.71,-719.888"/>
<path fill="none" stroke="#0044a0" d="M614.06,-858.777C605.418,-852.173 595.983,-844.963 587.319,-838.342"/>
<polygon fill="#0044a0" stroke="#0044a0" points="589.37,-835.504 579.299,-832.213 585.119,-841.066 589.37,-835.504"/>
</g>
<!-- t4 -->
<g id="node5" class="node"><title>t4</title>
<polygon fill="#efa03b" stroke="black" points="1258.15,-658.208 1023.85,-658.208 1019.85,-654.208 1019.85,-622.208 1254.15,-622.208 1258.15,-626.208 1258.15,-658.208"/>
<polyline fill="none" stroke="black" points="1254.15,-654.208 1019.85,-654.208 "/>
<polyline fill="none" stroke="black" points="1254.15,-654.208 1254.15,-622.208 "/>
<polyline fill="none" stroke="black" points="1254.15,-654.208 1258.15,-658.208 "/>
<text text-anchor="middle" x="1139" y="-634.208" font-family="Times,serif" font-size="20.00">orient_page</text>
<polygon fill="#efa03b" stroke="black" points="688.082,-774.173 429.918,-774.173 425.918,-770.173 425.918,-738.173 684.082,-738.173 688.082,-742.173 688.082,-774.173"/>
<polyline fill="none" stroke="black" points="684.082,-770.173 425.918,-770.173 "/>
<polyline fill="none" stroke="black" points="684.082,-770.173 684.082,-738.173 "/>
<polyline fill="none" stroke="black" points="684.082,-770.173 688.082,-774.173 "/>
<text text-anchor="middle" x="557" y="-750.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.orient_page</text>
</g>
<!-- t2&#45;&gt;t4 -->
<g id="edge5" class="edge"><title>t2&#45;&gt;t4</title>
<path fill="none" stroke="#0044a0" d="M1171.65,-742.795C1181.42,-735.692 1190.44,-726.864 1196,-716.208 1203.4,-702.023 1203.46,-694.36 1196,-680.208 1192.84,-674.222 1188.31,-668.98 1183.15,-664.445"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1185.3,-661.676 1175.25,-658.302 1181,-667.203 1185.3,-661.676"/>
<path fill="none" stroke="#0044a0" d="M695.691,-858.661C705.833,-851.667 715.136,-842.912 721,-832.173 728.668,-818.13 730.919,-808.727 721,-796.173 714.915,-788.471 700.759,-782.127 683.18,-776.959"/>
<polygon fill="#0044a0" stroke="#0044a0" points="683.659,-773.462 673.091,-774.208 681.817,-780.216 683.659,-773.462"/>
</g>
<!-- t3&#45;&gt;t4 -->
<g id="edge4" class="edge"><title>t3&#45;&gt;t4</title>
<path fill="none" stroke="#0044a0" d="M1073.02,-680.102C1081.95,-674.836 1091.92,-668.963 1101.34,-663.407"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1103.32,-666.302 1110.16,-658.209 1099.77,-660.272 1103.32,-666.302"/>
<path fill="none" stroke="#0044a0" d="M557,-796.066C557,-792.375 557,-788.385 557,-784.415"/>
<polygon fill="#0044a0" stroke="#0044a0" points="560.5,-784.174 557,-774.174 553.5,-784.174 560.5,-784.174"/>
</g>
<!-- t5 -->
<g id="node6" class="node"><title>t5</title>
<polygon fill="#efa03b" stroke="black" points="1271.3,-600.208 920.701,-600.208 916.701,-596.208 916.701,-564.208 1267.3,-564.208 1271.3,-568.208 1271.3,-600.208"/>
<polyline fill="none" stroke="black" points="1267.3,-596.208 916.701,-596.208 "/>
<polyline fill="none" stroke="black" points="1267.3,-596.208 1267.3,-564.208 "/>
<polyline fill="none" stroke="black" points="1267.3,-596.208 1271.3,-600.208 "/>
<text text-anchor="middle" x="1094" y="-576.208" font-family="Times,serif" font-size="20.00">rasterize_with_ghostscript</text>
<polygon fill="#efa03b" stroke="black" points="1064.73,-716.173 689.268,-716.173 685.268,-712.173 685.268,-680.173 1060.73,-680.173 1064.73,-684.173 1064.73,-716.173"/>
<polyline fill="none" stroke="black" points="1060.73,-712.173 685.268,-712.173 "/>
<polyline fill="none" stroke="black" points="1060.73,-712.173 1060.73,-680.173 "/>
<polyline fill="none" stroke="black" points="1060.73,-712.173 1064.73,-716.173 "/>
<text text-anchor="middle" x="875" y="-692.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.rasterize_with_ghostscript</text>
</g>
<!-- t4&#45;&gt;t5 -->
<g id="edge6" class="edge"><title>t4&#45;&gt;t5</title>
<path fill="none" stroke="#0044a0" d="M1125.25,-622.102C1121.76,-617.759 1117.94,-613.003 1114.21,-608.353"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1116.65,-605.812 1107.66,-600.209 1111.2,-610.197 1116.65,-605.812"/>
<path fill="none" stroke="#0044a0" d="M653.706,-738.143C689.783,-731.789 730.943,-724.541 767.902,-718.033"/>
<polygon fill="#0044a0" stroke="#0044a0" points="768.965,-721.399 778.206,-716.218 767.751,-714.505 768.965,-721.399"/>
</g>
<!-- t10 -->
<g id="node12" class="node"><title>t10</title>
<polygon fill="#00cc66" stroke="black" points="334,-348.208 35.7812,-320.208 334,-292.208 632.219,-320.208 334,-348.208"/>
<text text-anchor="middle" x="334" y="-314.208" font-family="Times,serif" font-size="20.00">select_image_layer</text>
<!-- t15 -->
<g id="node13" class="node"><title>t15</title>
<polygon fill="#ff69b4" stroke="black" points="440.27,-396.173 59.7304,-396.173 55.7304,-392.173 55.7304,-360.173 436.27,-360.173 440.27,-364.173 440.27,-396.173"/>
<polyline fill="none" stroke="black" points="436.27,-392.173 55.7304,-392.173 "/>
<polyline fill="none" stroke="black" points="436.27,-392.173 436.27,-360.173 "/>
<polyline fill="none" stroke="black" points="436.27,-392.173 440.27,-396.173 "/>
<text text-anchor="middle" x="248" y="-372.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.ocr_tesseract_textonly_pdf</text>
</g>
<!-- t4&#45;&gt;t10 -->
<g id="edge15" class="edge"><title>t4&#45;&gt;t10</title>
<path fill="none" stroke="#0044a0" d="M1019.87,-634.085C799.18,-622.991 349,-592.156 349,-525.208 349,-525.208 349,-525.208 349,-465.208 349,-428.606 344.147,-387.052 339.961,-358.022"/>
<polygon fill="#0044a0" stroke="#0044a0" points="343.393,-357.303 338.46,-347.926 336.469,-358.332 343.393,-357.303"/>
<!-- t4&#45;&gt;t15 -->
<g id="edge14" class="edge"><title>t4&#45;&gt;t15</title>
<path fill="none" stroke="#0044a0" d="M425.857,-745.263C361.241,-732.425 297,-703.891 297,-641.173 297,-641.173 297,-641.173 297,-523.173 297,-480.18 277.182,-433.63 262.754,-405.436"/>
<polygon fill="#0044a0" stroke="#0044a0" points="265.677,-403.477 257.916,-396.265 259.486,-406.743 265.677,-403.477"/>
</g>
<!-- t16 -->
<g id="node15" class="node"><title>t16</title>
<polygon fill="#efa03b" stroke="black" points="1380.34,-270.208 1159.66,-270.208 1155.66,-266.208 1155.66,-234.208 1376.34,-234.208 1380.34,-238.208 1380.34,-270.208"/>
<polyline fill="none" stroke="black" points="1376.34,-266.208 1155.66,-266.208 "/>
<polyline fill="none" stroke="black" points="1376.34,-266.208 1376.34,-234.208 "/>
<polyline fill="none" stroke="black" points="1376.34,-266.208 1380.34,-270.208 "/>
<text text-anchor="middle" x="1268" y="-246.208" font-family="Times,serif" font-size="20.00">skip_page</text>
<!-- t12 -->
<g id="node15" class="node"><title>t12</title>
<polygon fill="#00cc66" stroke="black" points="781,-406.173 458.414,-378.173 781,-350.173 1103.59,-378.173 781,-406.173"/>
<text text-anchor="middle" x="781" y="-372.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.select_image_layer</text>
</g>
<!-- t4&#45;&gt;t16 -->
<g id="edge20" class="edge"><title>t4&#45;&gt;t16</title>
<path fill="none" stroke="#0044a0" d="M1258.35,-631.473C1326.7,-619.809 1399,-591.745 1399,-525.208 1399,-525.208 1399,-525.208 1399,-397.208 1399,-350.33 1418.37,-328.748 1389,-292.208 1383.58,-285.469 1376.99,-279.879 1369.71,-275.244"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1371.3,-272.123 1360.88,-270.231 1367.85,-278.211 1371.3,-272.123"/>
<!-- t4&#45;&gt;t12 -->
<g id="edge20" class="edge"><title>t4&#45;&gt;t12</title>
<path fill="none" stroke="#0044a0" d="M471.449,-738.167C421.018,-722.605 367,-693.681 367,-641.173 367,-641.173 367,-641.173 367,-523.173 367,-480.717 347.218,-458.43 377,-428.173 392.917,-412.001 494.592,-399.721 591.948,-391.499"/>
<polygon fill="#0044a0" stroke="#0044a0" points="592.284,-394.983 601.96,-390.666 591.704,-388.007 592.284,-394.983"/>
</g>
<!-- t14 -->
<g id="node16" class="node"><title>t14</title>
<polygon fill="#66ccff" stroke="black" points="1380.24,-338.208 999.76,-338.208 995.76,-334.208 995.76,-302.208 1376.24,-302.208 1380.24,-306.208 1380.24,-338.208"/>
<polyline fill="none" stroke="black" points="1376.24,-334.208 995.76,-334.208 "/>
<polyline fill="none" stroke="black" points="1376.24,-334.208 1376.24,-302.208 "/>
<polyline fill="none" stroke="black" points="1376.24,-334.208 1380.24,-338.208 "/>
<text text-anchor="middle" x="1188" y="-314.208" font-family="Times,serif" font-size="20.00">tesseract_ocr_and_render_pdf</text>
<!-- t19 -->
<g id="node18" class="node"><title>t19</title>
<polygon fill="#efa03b" stroke="black" points="323.772,-270.173 78.2284,-270.173 74.2284,-266.173 74.2284,-234.173 319.772,-234.173 323.772,-238.173 323.772,-270.173"/>
<polyline fill="none" stroke="black" points="319.772,-266.173 74.2284,-266.173 "/>
<polyline fill="none" stroke="black" points="319.772,-266.173 319.772,-234.173 "/>
<polyline fill="none" stroke="black" points="319.772,-266.173 323.772,-270.173 "/>
<text text-anchor="middle" x="199" y="-246.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.skip_page</text>
</g>
<!-- t4&#45;&gt;t14 -->
<g id="edge22" class="edge"><title>t4&#45;&gt;t14</title>
<path fill="none" stroke="#0044a0" d="M1244.5,-622.179C1297.25,-607.003 1350,-578.503 1350,-525.208 1350,-525.208 1350,-525.208 1350,-465.208 1350,-422.752 1366.76,-403.169 1340,-370.208 1330.4,-358.377 1317.91,-349.368 1304.22,-342.513"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1305.62,-339.304 1295.07,-338.313 1302.7,-345.666 1305.62,-339.304"/>
<!-- t4&#45;&gt;t19 -->
<g id="edge26" class="edge"><title>t4&#45;&gt;t19</title>
<path fill="none" stroke="#0044a0" d="M425.782,-752.078C271.736,-744.795 37,-720.655 37,-641.173 37,-641.173 37,-641.173 37,-377.173 37,-325.92 88.7624,-292.989 133.769,-274.043"/>
<polygon fill="#0044a0" stroke="#0044a0" points="135.289,-277.203 143.249,-270.211 132.666,-270.713 135.289,-277.203"/>
</g>
<!-- t17 -->
<g id="node19" class="node"><title>t17</title>
<polygon fill="#66ccff" stroke="black" points="1499.67,-328.173 1094.33,-328.173 1090.33,-324.173 1090.33,-292.173 1495.67,-292.173 1499.67,-296.173 1499.67,-328.173"/>
<polyline fill="none" stroke="black" points="1495.67,-324.173 1090.33,-324.173 "/>
<polyline fill="none" stroke="black" points="1495.67,-324.173 1495.67,-292.173 "/>
<polyline fill="none" stroke="black" points="1495.67,-324.173 1499.67,-328.173 "/>
<text text-anchor="middle" x="1295" y="-304.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.ocr_tesseract_and_render_pdf</text>
</g>
<!-- t4&#45;&gt;t17 -->
<g id="edge28" class="edge"><title>t4&#45;&gt;t17</title>
<path fill="none" stroke="#0044a0" d="M688.477,-752.611C947.521,-745.804 1499,-721.841 1499,-641.173 1499,-641.173 1499,-641.173 1499,-455.173 1499,-407.201 1508.25,-383.766 1474,-350.173 1465.98,-342.302 1448.74,-335.804 1427.99,-330.522"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1428.77,-327.11 1418.23,-328.18 1427.14,-333.917 1428.77,-327.11"/>
</g>
<!-- t6 -->
<g id="node7" class="node"><title>t6</title>
<polygon fill="#efa03b" stroke="black" points="1074.74,-542.208 779.258,-542.208 775.258,-538.208 775.258,-506.208 1070.74,-506.208 1074.74,-510.208 1074.74,-542.208"/>
<polyline fill="none" stroke="black" points="1070.74,-538.208 775.258,-538.208 "/>
<polyline fill="none" stroke="black" points="1070.74,-538.208 1070.74,-506.208 "/>
<polyline fill="none" stroke="black" points="1070.74,-538.208 1074.74,-542.208 "/>
<text text-anchor="middle" x="925" y="-518.208" font-family="Times,serif" font-size="20.00">preprocess_deskew</text>
<polygon fill="#efa03b" stroke="black" points="1089.08,-658.173 664.92,-658.173 660.92,-654.173 660.92,-622.173 1085.08,-622.173 1089.08,-626.173 1089.08,-658.173"/>
<polyline fill="none" stroke="black" points="1085.08,-654.173 660.92,-654.173 "/>
<polyline fill="none" stroke="black" points="1085.08,-654.173 1085.08,-622.173 "/>
<polyline fill="none" stroke="black" points="1085.08,-654.173 1089.08,-658.173 "/>
<text text-anchor="middle" x="875" y="-634.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.preprocess_remove_background</text>
</g>
<!-- t5&#45;&gt;t6 -->
<g id="edge7" class="edge"><title>t5&#45;&gt;t6</title>
<path fill="none" stroke="#0044a0" d="M1042.38,-564.102C1024.52,-558.185 1004.35,-551.5 985.823,-545.362"/>
<polygon fill="#0044a0" stroke="#0044a0" points="986.901,-542.032 976.308,-542.209 984.699,-548.677 986.901,-542.032"/>
<path fill="none" stroke="#0044a0" d="M875,-680.066C875,-676.375 875,-672.385 875,-668.415"/>
<polygon fill="#0044a0" stroke="#0044a0" points="878.5,-668.174 875,-658.174 871.5,-668.174 878.5,-668.174"/>
</g>
<!-- t9 -->
<g id="node11" class="node"><title>t9</title>
<polygon fill="#efa03b" stroke="black" points="1013,-426.208 694.762,-398.208 1013,-370.208 1331.24,-398.208 1013,-426.208"/>
<text text-anchor="middle" x="1013" y="-392.208" font-family="Times,serif" font-size="20.00">select_image_for_pdf</text>
<!-- t11 -->
<g id="node14" class="node"><title>t11</title>
<polygon fill="#efa03b" stroke="black" points="1096,-484.173 712.187,-456.173 1096,-428.173 1479.81,-456.173 1096,-484.173"/>
<text text-anchor="middle" x="1096" y="-450.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.select_visible_page_image</text>
</g>
<!-- t5&#45;&gt;t9 -->
<g id="edge13" class="edge"><title>t5&#45;&gt;t9</title>
<path fill="none" stroke="#0044a0" d="M1093.89,-563.996C1093.29,-548.44 1091.11,-525.146 1084,-506.208 1073.94,-479.426 1056.13,-452.609 1040.86,-432.521"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1043.62,-430.369 1034.72,-424.619 1038.09,-434.663 1043.62,-430.369"/>
<!-- t5&#45;&gt;t11 -->
<g id="edge18" class="edge"><title>t5&#45;&gt;t11</title>
<path fill="none" stroke="#0044a0" d="M1051.07,-680.0px8C1072.76,-674.712 1090.1,-667.576 1098,-658.173 1136.53,-612.317 1122.5,-537.602 1109.06,-493.335"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1112.33,-492.043 1105.96,-483.573 1105.65,-494.164 1112.33,-492.043"/>
</g>
<!-- t7 -->
<g id="node8" class="node"><title>t7</title>
<polygon fill="#efa03b" stroke="black" points="993.95,-484.208 716.05,-484.208 712.05,-480.208 712.05,-448.208 989.95,-448.208 993.95,-452.208 993.95,-484.208"/>
<polyline fill="none" stroke="black" points="989.95,-480.208 712.05,-480.208 "/>
<polyline fill="none" stroke="black" points="989.95,-480.208 989.95,-448.208 "/>
<polyline fill="none" stroke="black" points="989.95,-480.208 993.95,-484.208 "/>
<text text-anchor="middle" x="853" y="-460.208" font-family="Times,serif" font-size="20.00">preprocess_clean</text>
<polygon fill="#efa03b" stroke="black" points="1039.68,-600.173 720.324,-600.173 716.324,-596.173 716.324,-564.173 1035.68,-564.173 1039.68,-568.173 1039.68,-600.173"/>
<polyline fill="none" stroke="black" points="1035.68,-596.173 716.324,-596.173 "/>
<polyline fill="none" stroke="black" points="1035.68,-596.173 1035.68,-564.173 "/>
<polyline fill="none" stroke="black" points="1035.68,-596.173 1039.68,-600.173 "/>
<text text-anchor="middle" x="878" y="-576.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.preprocess_deskew</text>
</g>
<!-- t6&#45;&gt;t7 -->
<g id="edge8" class="edge"><title>t6&#45;&gt;t7</title>
<path fill="none" stroke="#0044a0" d="M903.006,-506.102C896.726,-501.216 889.771,-495.807 883.095,-490.615"/>
<polygon fill="#0044a0" stroke="#0044a0" points="884.901,-487.586 874.859,-484.209 880.604,-493.111 884.901,-487.586"/>
<path fill="none" stroke="#0044a0" d="M875.916,-622.066C876.114,-618.375 876.328,-614.385 876.541,-610.415"/>
<polygon fill="#0044a0" stroke="#0044a0" points="880.049,-610.347 877.089,-600.174 873.059,-609.972 880.049,-610.347"/>
</g>
<!-- t6&#45;&gt;t9 -->
<g id="edge12" class="edge"><title>t6&#45;&gt;t9</title>
<path fill="none" stroke="#0044a0" d="M977.454,-506.003C987.329,-500.504 996.562,-493.377 1003,-484.208 1012.67,-470.441 1015.74,-452.229 1016.16,-436.195"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1019.66,-436.018 1016.09,-426.041 1012.66,-436.063 1019.66,-436.018"/>
<!-- t6&#45;&gt;t11 -->
<g id="edge17" class="edge"><title>t6&#45;&gt;t11</title>
<path fill="none" stroke="#0044a0" d="M990.695,-622.152C1016.54,-616.369 1039.2,-609.066 1049,-600.173 1078.78,-573.156 1089.74,-526.964 1093.74,-494.403"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1097.24,-494.666 1094.82,-484.351 1090.28,-493.924 1097.24,-494.666"/>
</g>
<!-- t8 -->
<g id="node9" class="node"><title>t8</title>
<polygon fill="#00cc66" stroke="black" points="676.666,-416.208 387.334,-416.208 383.334,-412.208 383.334,-380.208 672.666,-380.208 676.666,-384.208 676.666,-416.208"/>
<polyline fill="none" stroke="black" points="672.666,-412.208 383.334,-412.208 "/>
<polyline fill="none" stroke="black" points="672.666,-412.208 672.666,-380.208 "/>
<polyline fill="none" stroke="black" points="672.666,-412.208 676.666,-416.208 "/>
<text text-anchor="middle" x="530" y="-392.208" font-family="Times,serif" font-size="20.00">ocr_tesseract_hocr</text>
<polygon fill="#efa03b" stroke="black" points="1030.88,-542.173 729.117,-542.173 725.117,-538.173 725.117,-506.173 1026.88,-506.173 1030.88,-510.173 1030.88,-542.173"/>
<polyline fill="none" stroke="black" points="1026.88,-538.173 725.117,-538.173 "/>
<polyline fill="none" stroke="black" points="1026.88,-538.173 1026.88,-506.173 "/>
<polyline fill="none" stroke="black" points="1026.88,-538.173 1030.88,-542.173 "/>
<text text-anchor="middle" x="878" y="-518.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.preprocess_clean</text>
</g>
<!-- t7&#45;&gt;t8 -->
<g id="edge9" class="edge"><title>t7&#45;&gt;t8</title>
<path fill="none" stroke="#0044a0" d="M769.399,-448.125C724.645,-438.98 669.394,-427.691 623.252,-418.262"/>
<polygon fill="#0044a0" stroke="#0044a0" points="623.748,-414.791 613.25,-416.219 622.347,-421.65 623.748,-414.791"/>
<path fill="none" stroke="#0044a0" d="M878,-564.066C878,-560.375 878,-556.385 878,-552.415"/>
<polygon fill="#0044a0" stroke="#0044a0" points="881.5,-552.174 878,-542.174 874.5,-552.174 881.5,-552.174"/>
</g>
<!-- t7&#45;&gt;t9 -->
<g id="edge11" class="edge"><title>t7&#45;&gt;t9</title>
<path fill="none" stroke="#0044a0" d="M894.62,-448.039C911.413,-441.112 931.162,-432.966 949.666,-425.333"/>
<polygon fill="#0044a0" stroke="#0044a0" points="951.009,-428.565 958.918,-421.516 948.339,-422.094 951.009,-428.565"/>
<!-- t7&#45;&gt;t11 -->
<g id="edge16" class="edge"><title>t7&#45;&gt;t11</title>
<path fill="none" stroke="#0044a0" d="M995.441,-564.147C1011.26,-558.713 1026.62,-551.566 1040,-542.173 1057.45,-529.919 1070.89,-510.334 1080.22,-493.051"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1083.55,-494.243 1084.99,-483.747 1077.31,-491.053 1083.55,-494.243"/>
</g>
<!-- t11 -->
<g id="node10" class="node"><title>t11</title>
<polygon fill="#00cc66" stroke="black" points="938.109,-338.208 653.891,-338.208 649.891,-334.208 649.891,-302.208 934.109,-302.208 938.109,-306.208 938.109,-338.208"/>
<polyline fill="none" stroke="black" points="934.109,-334.208 649.891,-334.208 "/>
<polyline fill="none" stroke="black" points="934.109,-334.208 934.109,-302.208 "/>
<polyline fill="none" stroke="black" points="934.109,-334.208 938.109,-338.208 "/>
<text text-anchor="middle" x="794" y="-314.208" font-family="Times,serif" font-size="20.00">render_hocr_page</text>
<!-- t9 -->
<g id="node10" class="node"><title>t9</title>
<polygon fill="#efa03b" stroke="black" points="694.109,-474.173 389.891,-474.173 385.891,-470.173 385.891,-438.173 690.109,-438.173 694.109,-442.173 694.109,-474.173"/>
<polyline fill="none" stroke="black" points="690.109,-470.173 385.891,-470.173 "/>
<polyline fill="none" stroke="black" points="690.109,-470.173 690.109,-438.173 "/>
<polyline fill="none" stroke="black" points="690.109,-470.173 694.109,-474.173 "/>
<text text-anchor="middle" x="540" y="-450.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.select_ocr_image</text>
</g>
<!-- t8&#45;&gt;t9 -->
<g id="edge10" class="edge"><title>t8&#45;&gt;t9</title>
<path fill="none" stroke="#0044a0" d="M790.517,-506.09C743.487,-496.907 685.383,-485.561 636.976,-476.109"/>
<polygon fill="#0044a0" stroke="#0044a0" points="637.602,-472.665 627.116,-474.183 636.26,-479.535 637.602,-472.665"/>
</g>
<!-- t8&#45;&gt;t11 -->
<g id="edge10" class="edge"><title>t8&#45;&gt;t11</title>
<path fill="none" stroke="#0044a0" d="M589.247,-380.152C629.442,-368.58 682.727,-353.241 724.863,-341.111"/>
<polygon fill="#0044a0" stroke="#0044a0" points="725.853,-344.468 734.495,-338.338 723.917,-337.741 725.853,-344.468"/>
<g id="edge15" class="edge"><title>t8&#45;&gt;t11</title>
<path fill="none" stroke="#0044a0" d="M934.424,-506.09C958.693,-498.742 987.536,-490.01 1014.09,-481.971"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1015.2,-485.293 1023.75,-479.045 1013.17,-478.593 1015.2,-485.293"/>
</g>
<!-- t12 -->
<g id="node14" class="node"><title>t12</title>
<polygon fill="#00cc66" stroke="black" points="1118.49,-270.208 775.514,-270.208 771.514,-266.208 771.514,-234.208 1114.49,-234.208 1118.49,-238.208 1118.49,-270.208"/>
<polyline fill="none" stroke="black" points="1114.49,-266.208 771.514,-266.208 "/>
<polyline fill="none" stroke="black" points="1114.49,-266.208 1114.49,-234.208 "/>
<polyline fill="none" stroke="black" points="1114.49,-266.208 1118.49,-270.208 "/>
<text text-anchor="middle" x="945" y="-246.208" font-family="Times,serif" font-size="20.00">render_hocr_debug_page</text>
</g>
<!-- t8&#45;&gt;t12 -->
<g id="edge19" class="edge"><title>t8&#45;&gt;t12</title>
<path fill="none" stroke="#0044a0" d="M620.537,-380.161C641.947,-376.512 664.736,-372.939 686,-370.208 714.866,-366.5 927.304,-369.633 947,-348.208 963.502,-330.256 960.281,-301.363 954.611,-280.149"/>
<polygon fill="#0044a0" stroke="#0044a0" points="957.925,-279.012 951.707,-270.433 951.218,-281.017 957.925,-279.012"/>
</g>
<!-- t13 -->
<g id="node13" class="node"><title>t13</title>
<polygon fill="#00cc66" stroke="black" points="753.082,-270.208 494.918,-270.208 490.918,-266.208 490.918,-234.208 749.082,-234.208 753.082,-238.208 753.082,-270.208"/>
<polyline fill="none" stroke="black" points="749.082,-266.208 490.918,-266.208 "/>
<polyline fill="none" stroke="black" points="749.082,-266.208 749.082,-234.208 "/>
<polyline fill="none" stroke="black" points="749.082,-266.208 753.082,-270.208 "/>
<text text-anchor="middle" x="622" y="-246.208" font-family="Times,serif" font-size="20.00">add_text_layer</text>
</g>
<!-- t11&#45;&gt;t13 -->
<g id="edge16" class="edge"><title>t11&#45;&gt;t13</title>
<path fill="none" stroke="#0044a0" d="M749.258,-302.039C726.862,-293.446 699.574,-282.975 676.019,-273.936"/>
<polygon fill="#0044a0" stroke="#0044a0" points="677.108,-270.605 666.518,-270.29 674.6,-277.14 677.108,-270.605"/>
<!-- t10 -->
<g id="node11" class="node"><title>t10</title>
<polygon fill="#00cc66" stroke="black" points="1440.1,-396.173 1125.9,-396.173 1121.9,-392.173 1121.9,-360.173 1436.1,-360.173 1440.1,-364.173 1440.1,-396.173"/>
<polyline fill="none" stroke="black" points="1436.1,-392.173 1121.9,-392.173 "/>
<polyline fill="none" stroke="black" points="1436.1,-392.173 1436.1,-360.173 "/>
<polyline fill="none" stroke="black" points="1436.1,-392.173 1440.1,-396.173 "/>
<text text-anchor="middle" x="1281" y="-372.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.ocr_tesseract_hocr</text>
</g>
<!-- t9&#45;&gt;t10 -->
<g id="edge14" class="edge"><title>t9&#45;&gt;t10</title>
<path fill="none" stroke="#0044a0" d="M877.633,-382.056C761.19,-369.023 593.788,-350.286 475.578,-337.054"/>
<polygon fill="#0044a0" stroke="#0044a0" points="475.697,-333.546 465.37,-335.912 474.919,-340.503 475.697,-333.546"/>
<g id="edge11" class="edge"><title>t9&#45;&gt;t10</title>
<path fill="none" stroke="#0044a0" d="M631.992,-438.111C655.104,-434.327 679.903,-430.697 703,-428.173 884.404,-408.343 931.549,-425.567 1113,-406.173 1133.45,-403.987 1155.2,-400.994 1176.03,-397.794"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1176.83,-401.211 1186.17,-396.209 1175.75,-394.295 1176.83,-401.211"/>
</g>
<!-- t9&#45;&gt;t12 -->
<g id="edge18" class="edge"><title>t9&#45;&gt;t12</title>
<path fill="none" stroke="#0044a0" d="M998.887,-371.447C994.931,-364.003 990.702,-355.831 987,-348.208 983.822,-341.663 967.96,-305.616 956.669,-279.865"/>
<polygon fill="#0044a0" stroke="#0044a0" points="959.82,-278.337 952.601,-270.582 953.409,-281.146 959.82,-278.337"/>
<!-- t9&#45;&gt;t15 -->
<g id="edge13" class="edge"><title>t9&#45;&gt;t15</title>
<path fill="none" stroke="#0044a0" d="M474.47,-438.117C429.651,-426.452 370.0px1,-410.957 323.342,-398.782"/>
<polygon fill="#0044a0" stroke="#0044a0" points="324.123,-395.369 313.564,-396.237 322.36,-402.143 324.123,-395.369"/>
</g>
<!-- t9&#45;&gt;t14 -->
<g id="edge21" class="edge"><title>t9&#45;&gt;t14</title>
<path fill="none" stroke="#0044a0" d="M1065.03,-374.611C1088.59,-364.381 1116.27,-352.359 1139.4,-342.314"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1140.9,-345.479 1148.68,-338.285 1138.11,-339.058 1140.9,-345.479"/>
<!-- t13 -->
<g id="node12" class="node"><title>t13</title>
<polygon fill="#00cc66" stroke="black" points="683.043,-328.173 374.957,-328.173 370.957,-324.173 370.957,-292.173 679.043,-292.173 683.043,-296.173 683.043,-328.173"/>
<polyline fill="none" stroke="black" points="679.043,-324.173 370.957,-324.173 "/>
<polyline fill="none" stroke="black" points="679.043,-324.173 679.043,-292.173 "/>
<polyline fill="none" stroke="black" points="679.043,-324.173 683.043,-328.173 "/>
<text text-anchor="middle" x="527" y="-304.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.render_hocr_page</text>
</g>
<!-- t10&#45;&gt;t13 -->
<g id="edge17" class="edge"><title>t10&#45;&gt;t13</title>
<path fill="none" stroke="#0044a0" d="M417.688,-300.029C455.345,-291.399 499.718,-281.231 537.473,-272.578"/>
<polygon fill="#0044a0" stroke="#0044a0" points="538.461,-275.943 547.427,-270.297 536.898,-269.12 538.461,-275.943"/>
<g id="edge12" class="edge"><title>t10&#45;&gt;t13</title>
<path fill="none" stroke="#0044a0" d="M1186.17,-360.113C1162.35,-356.33 1136.79,-352.699 1113,-350.173 929.956,-330.738 880.531,-342.246 693.485,-328.255"/>
<polygon fill="#0044a0" stroke="#0044a0" points="693.548,-324.75 683.311,-327.48 693.016,-331.73 693.548,-324.75"/>
</g>
<!-- t17 -->
<g id="node18" class="node"><title>t17</title>
<polygon fill="#efa03b" stroke="black" points="540.724,-156.455 770,-129.143 999.276,-156.455 999.062,-200.646 540.938,-200.646 540.724,-156.455"/>
<polygon fill="none" stroke="black" points="536.704,-152.903 770,-125.112 1003.3,-152.903 1003.05,-204.648 536.954,-204.648 536.704,-152.903"/>
<text text-anchor="middle" x="770" y="-162.669" font-family="Times,serif" font-size="20.00">merge_pages_ghostscript</text>
<!-- t14 -->
<g id="node17" class="node"><title>t14</title>
<polygon fill="#00cc66" stroke="black" points="1072.92,-328.173 705.08,-328.173 701.08,-324.173 701.08,-292.173 1068.92,-292.173 1072.92,-296.173 1072.92,-328.173"/>
<polyline fill="none" stroke="black" points="1068.92,-324.173 701.08,-324.173 "/>
<polyline fill="none" stroke="black" points="1068.92,-324.173 1068.92,-292.173 "/>
<polyline fill="none" stroke="black" points="1068.92,-324.173 1072.92,-328.173 "/>
<text text-anchor="middle" x="887" y="-304.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.render_hocr_debug_page</text>
</g>
<!-- t13&#45;&gt;t17 -->
<g id="edge27" class="edge"><title>t13&#45;&gt;t17</title>
<path fill="none" stroke="#0044a0" d="M653.026,-234.114C665.992,-226.971 681.653,-218.343 697.24,-209.755"/>
<polygon fill="#0044a0" stroke="#0044a0" points="699.319,-212.606 706.388,-204.715 695.941,-206.475 699.319,-212.606"/>
<!-- t10&#45;&gt;t14 -->
<g id="edge25" class="edge"><title>t10&#45;&gt;t14</title>
<path fill="none" stroke="#0044a0" d="M1179.28,-360.133C1124,-350.873 1055.54,-339.405 998.77,-329.896"/>
<polygon fill="#0044a0" stroke="#0044a0" points="999.118,-326.405 988.677,-328.205 997.962,-333.309 999.118,-326.405"/>
</g>
<!-- t13&#45;&gt;t18 -->
<g id="edge31" class="edge"><title>t13&#45;&gt;t18</title>
<path fill="none" stroke="#0044a0" d="M753.329,-235.235C756.584,-234.884 759.812,-234.541 763,-234.208 873.497,-222.668 902.059,-228.201 1012,-212.208 1023.74,-210.5 1035.81,-208.554 1047.95,-206.456"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1048.91,-209.84 1058.16,-204.659 1047.7,-202.946 1048.91,-209.84"/>
<!-- t16 -->
<g id="node16" class="node"><title>t16</title>
<polygon fill="#00cc66" stroke="black" points="636.299,-270.173 345.701,-270.173 341.701,-266.173 341.701,-234.173 632.299,-234.173 636.299,-238.173 636.299,-270.173"/>
<polyline fill="none" stroke="black" points="632.299,-266.173 341.701,-266.173 "/>
<polyline fill="none" stroke="black" points="632.299,-266.173 632.299,-234.173 "/>
<polyline fill="none" stroke="black" points="632.299,-266.173 636.299,-270.173 "/>
<text text-anchor="middle" x="489" y="-246.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.combine_layers</text>
</g>
<!-- t12&#45;&gt;t17 -->
<g id="edge28" class="edge"><title>t12&#45;&gt;t17</title>
<path fill="none" stroke="#0044a0" d="M908.314,-234.114C892.552,-226.77 873.424,-217.858 854.484,-209.033"/>
<polygon fill="#0044a0" stroke="#0044a0" points="855.759,-205.766 845.216,-204.715 852.803,-212.111 855.759,-205.766"/>
<!-- t13&#45;&gt;t16 -->
<g id="edge22" class="edge"><title>t13&#45;&gt;t16</title>
<path fill="none" stroke="#0044a0" d="M515.392,-292.066C512.519,-287.833 509.379,-283.205 506.299,-278.666"/>
<polygon fill="#0044a0" stroke="#0044a0" points="509.048,-276.483 500.537,-270.174 503.256,-280.414 509.048,-276.483"/>
</g>
<!-- t12&#45;&gt;t18 -->
<g id="edge32" class="edge"><title>t12&#45;&gt;t18</title>
<path fill="none" stroke="#0044a0" d="M1002.86,-234.114C1029.07,-226.37 1061.19,-216.881 1092.64,-207.59"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1093.77,-210.905 1102.37,-204.715 1091.79,-204.192 1093.77,-210.905"/>
<!-- t15&#45;&gt;t16 -->
<g id="edge21" class="edge"><title>t15&#45;&gt;t16</title>
<path fill="none" stroke="#0044a0" d="M263.466,-359.936C281.645,-340.695 313.598,-309.935 347,-292.173 361.3,-284.568 377.219,-278.339 393.079,-273.27"/>
<polygon fill="#0044a0" stroke="#0044a0" points="394.389,-276.53 402.932,-270.262 392.345,-269.835 394.389,-276.53"/>
</g>
<!-- t16&#45;&gt;t17 -->
<g id="edge24" class="edge"><title>t16&#45;&gt;t17</title>
<path fill="none" stroke="#0044a0" d="M1155.57,-234.546C1111.13,-227.821 1059.63,-219.853 1013,-212.208 1001.53,-210.326 989.752,-208.365 977.872,-206.363"/>
<polygon fill="#0044a0" stroke="#0044a0" points="978.316,-202.888 967.872,-204.672 977.149,-209.79 978.316,-202.888"/>
<!-- t11&#45;&gt;t12 -->
<g id="edge19" class="edge"><title>t11&#45;&gt;t12</title>
<path fill="none" stroke="#0044a0" d="M1009.92,-434.405C967.591,-424.191 916.524,-411.87 873.373,-401.459"/>
<polygon fill="#0044a0" stroke="#0044a0" points="873.983,-398.006 863.441,-399.063 872.341,-404.811 873.983,-398.006"/>
</g>
<!-- t16&#45;&gt;t18 -->
<g id="edge29" class="edge"><title>t16&#45;&gt;t18</title>
<path fill="none" stroke="#0044a0" d="M1258.03,-233.915C1254.58,-227.933 1250.55,-220.928 1246.43,-213.785"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1249.24,-211.645 1241.21,-204.729 1243.17,-215.141 1249.24,-211.645"/>
<!-- t11&#45;&gt;t14 -->
<g id="edge24" class="edge"><title>t11&#45;&gt;t14</title>
<path fill="none" stroke="#0044a0" d="M1334.06,-445.464C1386.49,-438.209 1431.63,-426.12 1449,-406.173 1465.34,-387.403 1466.07,-368.289 1449,-350.173 1422.45,-321.987 1153.75,-330.0px 1083.05,-328.037"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1083,-324.531 1072.85,-327.564 1082.68,-331.524 1083,-324.531"/>
</g>
<!-- t14&#45;&gt;t17 -->
<g id="edge26" class="edge"><title>t14&#45;&gt;t17</title>
<path fill="none" stroke="#0044a0" d="M1172.36,-302.154C1164.33,-293.013 1154.66,-281.362 1147,-270.208 1136.64,-255.121 1141.88,-244.862 1127,-234.208 1125.19,-232.915 1055.67,-220.232 978.45,-206.446"/>
<polygon fill="#0044a0" stroke="#0044a0" points="978.964,-202.982 968.505,-204.672 977.735,-209.874 978.964,-202.982"/>
<!-- t11&#45;&gt;t17 -->
<g id="edge27" class="edge"><title>t11&#45;&gt;t17</title>
<path fill="none" stroke="#0044a0" d="M1278.64,-441.463C1364.44,-433.122 1450.86,-421.174 1464,-406.173 1480.4,-387.448 1479.49,-369.65 1464,-350.173 1457.83,-342.418 1443.67,-336.074 1426.02,-330.926"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1426.46,-327.418 1415.89,-328.188 1424.63,-334.176 1426.46,-327.418"/>
</g>
<!-- t14&#45;&gt;t18 -->
<g id="edge30" class="edge"><title>t14&#45;&gt;t18</title>
<path fill="none" stroke="#0044a0" d="M1310.22,-302.184C1345.8,-294.579 1378.07,-284.119 1389,-270.208 1408.78,-245.028 1391.25,-224.765 1361.2,-209.211"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1362.48,-205.944 1351.96,-204.742 1359.44,-212.246 1362.48,-205.944"/>
<!-- t12&#45;&gt;t16 -->
<g id="edge23" class="edge"><title>t12&#45;&gt;t16</title>
<path fill="none" stroke="#0044a0" d="M624.426,-363.718C509.174,-353.04 370.992,-338.277 362,-328.173 351.364,-316.22 352.491,-305.04 362,-292.173 366.819,-285.651 372.71,-280.186 379.287,-275.609"/>
<polygon fill="#0044a0" stroke="#0044a0" points="381.274,-278.496 387.956,-270.274 377.605,-272.534 381.274,-278.496"/>
</g>
<!-- t15&#45;&gt;t17 -->
<g id="edge25" class="edge"><title>t15&#45;&gt;t17</title>
<path fill="none" stroke="#0044a0" d="M289.656,-684.797C164.646,-670.853 17,-641.95 17,-583.208 17,-583.208 17,-583.208 17,-319.208 17,-213.417 306.554,-181.327 526.553,-172.213"/>
<polygon fill="#0044a0" stroke="#0044a0" points="526.794,-175.706 536.646,-171.808 526.514,-168.711 526.794,-175.706"/>
<!-- t20 -->
<g id="node21" class="node"><title>t20</title>
<polygon fill="#efa03b" stroke="black" points="234.918,-156.426 480,-129.117 725.082,-156.426 724.853,-200.614 235.147,-200.614 234.918,-156.426"/>
<polygon fill="none" stroke="black" points="230.903,-152.847 480,-125.09 729.097,-152.847 728.829,-204.616 231.171,-204.616 230.903,-152.847"/>
<text text-anchor="middle" x="480" y="-162.639" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.merge_pages_ghostscript</text>
</g>
<!-- t19 -->
<g id="node20" class="node"><title>t19</title>
<polygon fill="#efa03b" stroke="black" points="844.361,-47.3406 995,-20.006 1145.64,-47.3406 1145.5,-91.5689 844.501,-91.5689 844.361,-47.3406"/>
<polygon fill="none" stroke="black" points="840.355,-43.9965 995,-15.9349 1149.65,-43.9965 1149.48,-95.5749 840.519,-95.5749 840.355,-43.9965"/>
<text text-anchor="middle" x="995" y="-53.565" font-family="Times,serif" font-size="20.00">copy_final</text>
<!-- t16&#45;&gt;t20 -->
<g id="edge33" class="edge"><title>t16&#45;&gt;t20</title>
<path fill="none" stroke="#0044a0" d="M487.091,-233.881C486.46,-228.165 485.726,-221.515 484.974,-214.703"/>
<polygon fill="#0044a0" stroke="#0044a0" points="488.446,-214.253 483.87,-204.697 481.488,-215.021 488.446,-214.253"/>
</g>
<!-- t17&#45;&gt;t19 -->
<g id="edge35" class="edge"><title>t17&#45;&gt;t19</title>
<path fill="none" stroke="#0044a0" d="M841.81,-133.486C864.177,-122.839 889.024,-111.011 912.085,-100.034"/>
<polygon fill="#0044a0" stroke="#0044a0" points="913.64,-103.17 921.165,-95.7118 910.631,-96.8497 913.64,-103.17"/>
<!-- t16&#45;&gt;t21 -->
<g id="edge37" class="edge"><title>t16&#45;&gt;t21</title>
<path fill="none" stroke="#0044a0" d="M602.543,-234.159C645.082,-227.582 693.805,-219.809 738,-212.173 748.572,-210.346 759.416,-208.431 770.357,-206.468"/>
<polygon fill="#0044a0" stroke="#0044a0" points="771.206,-209.872 780.427,-204.653 769.964,-202.983 771.206,-209.872"/>
</g>
<!-- t18&#45;&gt;t19 -->
<g id="edge34" class="edge"><title>t18&#45;&gt;t19</title>
<path fill="none" stroke="#0044a0" d="M1151.35,-134.66C1128.23,-123.705 1102.26,-111.399 1078.23,-100.009"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1079.66,-96.8131 1069.12,-95.6933 1076.66,-103.139 1079.66,-96.8131"/>
<!-- t14&#45;&gt;t20 -->
<g id="edge34" class="edge"><title>t14&#45;&gt;t20</title>
<path fill="none" stroke="#0044a0" d="M837.094,-292.063C776.411,-271.259 672.165,-235.52 591.922,-208.01"/>
<polygon fill="#0044a0" stroke="#0044a0" points="592.855,-204.63 582.26,-204.697 590.584,-211.251 592.855,-204.63"/>
</g>
<!-- t14&#45;&gt;t21 -->
<g id="edge38" class="edge"><title>t14&#45;&gt;t21</title>
<path fill="none" stroke="#0044a0" d="M896.319,-292.063C906.85,-272.729 924.406,-240.497 938.861,-213.958"/>
<polygon fill="#0044a0" stroke="#0044a0" points="942.118,-215.294 943.828,-204.838 935.971,-211.946 942.118,-215.294"/>
</g>
<!-- t19&#45;&gt;t20 -->
<g id="edge30" class="edge"><title>t19&#45;&gt;t20</title>
<path fill="none" stroke="#0044a0" d="M257.907,-234.081C284.597,-226.336 317.298,-216.848 349.316,-207.558"/>
<polygon fill="#0044a0" stroke="#0044a0" points="350.595,-210.831 359.224,-204.683 348.645,-204.108 350.595,-210.831"/>
</g>
<!-- t19&#45;&gt;t21 -->
<g id="edge35" class="edge"><title>t19&#45;&gt;t21</title>
<path fill="none" stroke="#0044a0" d="M323.792,-235.042C326.891,-234.738 329.964,-234.447 333,-234.173 512.532,-217.929 559.043,-233.851 738,-212.173 751.869,-210.493 766.169,-208.472 780.522,-206.237"/>
<polygon fill="#0044a0" stroke="#0044a0" points="781.136,-209.683 790.462,-204.657 780.037,-202.77 781.136,-209.683"/>
</g>
<!-- t17&#45;&gt;t20 -->
<g id="edge32" class="edge"><title>t17&#45;&gt;t20</title>
<path fill="none" stroke="#0044a0" d="M1195.47,-292.133C1071.63,-270.93 856.728,-234.138 694.688,-206.395"/>
<polygon fill="#0044a0" stroke="#0044a0" points="695.028,-202.903 684.581,-204.665 693.846,-209.802 695.028,-202.903"/>
</g>
<!-- t17&#45;&gt;t21 -->
<g id="edge36" class="edge"><title>t17&#45;&gt;t21</title>
<path fill="none" stroke="#0044a0" d="M1254.29,-292.063C1205.19,-271.428 1121.13,-236.1 1055.9,-208.683"/>
<polygon fill="#0044a0" stroke="#0044a0" points="1056.99,-205.345 1046.42,-204.697 1054.28,-211.799 1056.99,-205.345"/>
</g>
<!-- t18&#45;&gt;t20 -->
<g id="edge31" class="edge"><title>t18&#45;&gt;t20</title>
<path fill="none" stroke="#0044a0" d="M120.266,-796.105C70.9512,-780.34 17,-751.202 17,-699.173 17,-699.173 17,-699.173 17,-309.173 17,-269.597 31.8505,-255.79 65,-234.173 92.9782,-215.927 154.085,-202.475 221.024,-192.724"/>
<polygon fill="#0044a0" stroke="#0044a0" points="221.533,-196.187 230.939,-191.311 220.546,-189.256 221.533,-196.187"/>
</g>
<!-- t22 -->
<g id="node23" class="node"><title>t22</title>
<polygon fill="#efa03b" stroke="black" points="554.065,-47.332 721,-20.0049 887.935,-47.332 887.779,-91.5483 554.221,-91.5483 554.065,-47.332"/>
<polygon fill="none" stroke="black" points="550.054,-43.9306 721,-15.9468 891.946,-43.9306 891.764,-95.5532 550.236,-95.5532 550.054,-43.9306"/>
<text text-anchor="middle" x="721" y="-53.5531" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.copy_final</text>
</g>
<!-- t20&#45;&gt;t22 -->
<g id="edge41" class="edge"><title>t20&#45;&gt;t22</title>
<path fill="none" stroke="#0044a0" d="M556.585,-133.609C580.784,-122.857 607.72,-110.888 632.67,-99.8018"/>
<polygon fill="#0044a0" stroke="#0044a0" points="634.408,-102.859 642.125,-95.6004 631.566,-96.4625 634.408,-102.859"/>
</g>
<!-- t21&#45;&gt;t22 -->
<g id="edge40" class="edge"><title>t21&#45;&gt;t22</title>
<path fill="none" stroke="#0044a0" d="M888.417,-134.636C863.556,-123.635 835.613,-111.27 809.783,-99.8401"/>
<polygon fill="#0044a0" stroke="#0044a0" points="810.933,-96.5216 800.372,-95.6756 808.1,-102.923 810.933,-96.5216"/>
</g>
</g>
</svg>
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 23 KiB

After

Width:  |  Height:  |  Size: 28 KiB