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

Update release notes so far

Browse Source
This commit is contained in:
Jim Barlow
2015-07-25 18:18:37 -07:00
parent 7b255b575a
commit c270f1ba5f
2 changed files with 240 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
RELEASE_NOTES.md
+28
View File
@@ -5,6 +5,34 @@ Please always read this file before installing the package
Download software here: https://github.com/fritz-hh/OCRmyPDF/tags
v3.0-rc1:
=======
Changes
-------
- New, robust Python 3.4+ implementation based on ruffus pipelines
- All "tasks" in the pipeline can be executed in parallel on any available CPUs
- Removed dependencies on several packages:
- parallel
- ImageMagick
- Python 2.7
- shell
- Updated dependencies
- Ghostscript 9.14
- Unpaper 6.1 (now optional)
- Tesseract 3.02 and 3.03
- Python's reportlab 3
- Unpaper 6.1 is now an optional dependency
Fixes
-----
- Document metadata from the source PDF is copied to the output PDF (Title, Author, etc.)
v2.1-stable (2014-09-20):
=======
pipeline.svg
+212
View File
@@ -0,0 +1,212 @@
<?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="520pt" height="651pt"
viewBox="0.00 0.00 520.00 650.53" 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(4 646.53)">
<title>Pipeline:</title>
<polygon fill="white" stroke="none" points="-4,4 -4,-646.53 516,-646.53 516,4 -4,4"/>
<g id="clust1" class="cluster"><title>clustertasks</title>
<polygon fill="none" stroke="black" points="8,-8 8,-634.53 504,-634.53 504,-8 8,-8"/>
<text text-anchor="middle" x="256" y="-606.53" 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="#006000" points="257.791,-588.53 162.209,-588.53 158.209,-584.53 158.209,-552.53 253.791,-552.53 257.791,-556.53 257.791,-588.53"/>
<polyline fill="none" stroke="#006000" points="253.791,-584.53 158.209,-584.53 "/>
<polyline fill="none" stroke="#006000" points="253.791,-584.53 253.791,-552.53 "/>
<polyline fill="none" stroke="#006000" points="253.791,-584.53 257.791,-588.53 "/>
<text text-anchor="middle" x="208" y="-564.53" font-family="Times,serif" font-size="20.00" fill="#006000">repair_pdf</text>
</g>
<!-- t1 -->
<g id="node2" class="node"><title>t1</title>
<polygon fill="#efa03b" stroke="black" points="242.782,-509.564 150,-526.497 57.2177,-509.564 57.3043,-482.165 242.696,-482.165 242.782,-509.564"/>
<polygon fill="none" stroke="black" points="246.799,-512.902 150,-530.569 53.2009,-512.902 53.3107,-478.159 246.689,-478.159 246.799,-512.902"/>
<text text-anchor="middle" x="150" y="-495.991" 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="gray" d="M193.064,-552.394C188.296,-546.925 182.86,-540.689 177.493,-534.532"/>
<polygon fill="gray" stroke="gray" points="179.996,-532.077 170.787,-526.838 174.719,-536.676 179.996,-532.077"/>
</g>
<!-- t9 -->
<g id="node11" class="node"><title>t9</title>
<polygon fill="#efa03b" stroke="#006000" points="496.338,-451.452 285.662,-451.452 281.662,-447.452 281.662,-415.452 492.338,-415.452 496.338,-419.452 496.338,-451.452"/>
<polyline fill="none" stroke="#006000" points="492.338,-447.452 281.662,-447.452 "/>
<polyline fill="none" stroke="#006000" points="492.338,-447.452 492.338,-415.452 "/>
<polyline fill="none" stroke="#006000" points="492.338,-447.452 496.338,-451.452 "/>
<text text-anchor="middle" x="389" y="-427.452" font-family="Times,serif" font-size="20.00" fill="#006000">generate_postscript_stub</text>
</g>
<!-- t0&#45;&gt;t9 -->
<g id="edge14" class="edge"><title>t0&#45;&gt;t9</title>
<path fill="none" stroke="gray" d="M230.924,-552.422C263.068,-528.433 321.637,-484.724 357.75,-457.773"/>
<polygon fill="gray" stroke="gray" points="360.056,-460.42 365.977,-451.634 355.87,-454.81 360.056,-460.42"/>
</g>
<!-- t2 -->
<g id="node3" class="node"><title>t2</title>
<polygon fill="#efa03b" stroke="black" points="263.555,-451.452 40.4453,-451.452 36.4453,-447.452 36.4453,-415.452 259.555,-415.452 263.555,-419.452 263.555,-451.452"/>
<polyline fill="none" stroke="black" points="259.555,-447.452 36.4453,-447.452 "/>
<polyline fill="none" stroke="black" points="259.555,-447.452 259.555,-415.452 "/>
<polyline fill="none" stroke="black" points="259.555,-447.452 263.555,-451.452 "/>
<text text-anchor="middle" x="150" y="-427.452" 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="M150,-478.092C150,-472.777 150,-467.07 150,-461.593"/>
<polygon fill="#0044a0" stroke="#0044a0" points="153.5,-461.506 150,-451.506 146.5,-461.506 153.5,-461.506"/>
</g>
<!-- t10 -->
<g id="node10" class="node"><title>t10</title>
<polygon fill="#efa03b" stroke="black" points="113.594,-393.452 20.4062,-393.452 16.4062,-389.452 16.4062,-357.452 109.594,-357.452 113.594,-361.452 113.594,-393.452"/>
<polyline fill="none" stroke="black" points="109.594,-389.452 16.4062,-389.452 "/>
<polyline fill="none" stroke="black" points="109.594,-389.452 109.594,-357.452 "/>
<polyline fill="none" stroke="black" points="109.594,-389.452 113.594,-393.452 "/>
<text text-anchor="middle" x="65" y="-369.452" font-family="Times,serif" font-size="20.00">skip_page</text>
</g>
<!-- t1&#45;&gt;t10 -->
<g id="edge13" class="edge"><title>t1&#45;&gt;t10</title>
<path fill="none" stroke="#0044a0" d="M57.0924,-478.13C45.2322,-471.407 34.6013,-462.708 27,-451.452 18.0457,-438.192 20.9732,-430.273 27,-415.452 29.092,-410.307 32.2252,-405.47 35.8114,-401.07"/>
<polygon fill="#0044a0" stroke="#0044a0" points="38.4404,-403.381 42.629,-393.65 33.2858,-398.645 38.4404,-403.381"/>
</g>
<!-- t3 -->
<g id="node4" class="node"><title>t3</title>
<polygon fill="#efa03b" stroke="black" points="332.999,-393.452 165.001,-393.452 161.001,-389.452 161.001,-357.452 328.999,-357.452 332.999,-361.452 332.999,-393.452"/>
<polyline fill="none" stroke="black" points="328.999,-389.452 161.001,-389.452 "/>
<polyline fill="none" stroke="black" points="328.999,-389.452 328.999,-357.452 "/>
<polyline fill="none" stroke="black" points="328.999,-389.452 332.999,-393.452 "/>
<text text-anchor="middle" x="247" y="-369.452" 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="M179.63,-415.346C188.844,-410.026 199.134,-404.086 208.844,-398.48"/>
<polygon fill="#0044a0" stroke="#0044a0" points="210.641,-401.484 217.551,-393.453 207.141,-395.422 210.641,-401.484"/>
</g>
<!-- t6 -->
<g id="node6" class="node"><title>t6</title>
<polygon fill="#efa03b" stroke="black" points="239.375,-277.452 52.6246,-277.452 48.6246,-273.452 48.6246,-241.452 235.375,-241.452 239.375,-245.452 239.375,-277.452"/>
<polyline fill="none" stroke="black" points="235.375,-273.452 48.6246,-273.452 "/>
<polyline fill="none" stroke="black" points="235.375,-273.452 235.375,-241.452 "/>
<polyline fill="none" stroke="black" points="235.375,-273.452 239.375,-277.452 "/>
<text text-anchor="middle" x="144" y="-253.452" font-family="Times,serif" font-size="20.00">select_image_for_pdf</text>
</g>
<!-- t2&#45;&gt;t6 -->
<g id="edge7" class="edge"><title>t2&#45;&gt;t6</title>
<path fill="none" stroke="#0044a0" d="M149.403,-415.331C148.361,-385.453 146.202,-323.565 144.951,-287.726"/>
<polygon fill="#0044a0" stroke="#0044a0" points="148.441,-287.375 144.595,-277.504 141.446,-287.62 148.441,-287.375"/>
</g>
<!-- t4 -->
<g id="node5" class="node"><title>t4</title>
<polygon fill="#efa03b" stroke="black" points="334.705,-335.452 185.295,-335.452 181.295,-331.452 181.295,-299.452 330.705,-299.452 334.705,-303.452 334.705,-335.452"/>
<polyline fill="none" stroke="black" points="330.705,-331.452 181.295,-331.452 "/>
<polyline fill="none" stroke="black" points="330.705,-331.452 330.705,-299.452 "/>
<polyline fill="none" stroke="black" points="330.705,-331.452 334.705,-335.452 "/>
<text text-anchor="middle" x="258" y="-311.452" 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="M250.36,-357.346C251.106,-353.546 251.915,-349.43 252.718,-345.345"/>
<polygon fill="#0044a0" stroke="#0044a0" points="256.167,-345.94 254.66,-335.453 249.299,-344.591 256.167,-345.94"/>
</g>
<!-- t3&#45;&gt;t6 -->
<g id="edge6" class="edge"><title>t3&#45;&gt;t6</title>
<path fill="none" stroke="#0044a0" d="M201.207,-357.385C190.535,-351.706 179.974,-344.465 172,-335.452 160.103,-322.004 153.083,-303.029 149.047,-287.53"/>
<polygon fill="#0044a0" stroke="#0044a0" points="152.381,-286.414 146.707,-277.466 145.563,-287.999 152.381,-286.414"/>
</g>
<!-- t4&#45;&gt;t6 -->
<g id="edge5" class="edge"><title>t4&#45;&gt;t6</title>
<path fill="none" stroke="#0044a0" d="M223.177,-299.346C212.017,-293.864 199.513,-287.721 187.797,-281.966"/>
<polygon fill="#0044a0" stroke="#0044a0" points="189.129,-278.721 178.61,-277.453 186.042,-285.004 189.129,-278.721"/>
</g>
<!-- t5 -->
<g id="node7" class="node"><title>t5</title>
<polygon fill="#efa03b" stroke="black" points="377.385,-277.452 260.615,-277.452 256.615,-273.452 256.615,-241.452 373.385,-241.452 377.385,-245.452 377.385,-277.452"/>
<polyline fill="none" stroke="black" points="373.385,-273.452 256.615,-273.452 "/>
<polyline fill="none" stroke="black" points="373.385,-273.452 373.385,-241.452 "/>
<polyline fill="none" stroke="black" points="373.385,-273.452 377.385,-277.452 "/>
<text text-anchor="middle" x="317" y="-253.452" font-family="Times,serif" font-size="20.00">ocr_tesseract</text>
</g>
<!-- t4&#45;&gt;t5 -->
<g id="edge8" class="edge"><title>t4&#45;&gt;t5</title>
<path fill="none" stroke="#0044a0" d="M276.023,-299.346C280.941,-294.678 286.363,-289.531 291.608,-284.552"/>
<polygon fill="#0044a0" stroke="#0044a0" points="294.244,-286.876 299.088,-277.453 289.425,-281.799 294.244,-286.876"/>
</g>
<!-- t7 -->
<g id="node8" class="node"><title>t7</title>
<polygon fill="#efa03b" stroke="black" points="368.328,-219.452 257.672,-219.452 253.672,-215.452 253.672,-183.452 364.328,-183.452 368.328,-187.452 368.328,-219.452"/>
<polyline fill="none" stroke="black" points="364.328,-215.452 253.672,-215.452 "/>
<polyline fill="none" stroke="black" points="364.328,-215.452 364.328,-183.452 "/>
<polyline fill="none" stroke="black" points="364.328,-215.452 368.328,-219.452 "/>
<text text-anchor="middle" x="311" y="-195.452" font-family="Times,serif" font-size="20.00">render_page</text>
</g>
<!-- t6&#45;&gt;t7 -->
<g id="edge9" class="edge"><title>t6&#45;&gt;t7</title>
<path fill="none" stroke="#0044a0" d="M195.013,-241.346C212.575,-235.457 232.41,-228.806 250.645,-222.691"/>
<polygon fill="#0044a0" stroke="#0044a0" points="251.931,-225.951 260.299,-219.453 249.706,-219.314 251.931,-225.951"/>
</g>
<!-- t8 -->
<g id="node9" class="node"><title>t8</title>
<polygon fill="#efa03b" stroke="black" points="235.705,-219.452 66.2947,-219.452 62.2947,-215.452 62.2947,-183.452 231.705,-183.452 235.705,-187.452 235.705,-219.452"/>
<polyline fill="none" stroke="black" points="231.705,-215.452 62.2947,-215.452 "/>
<polyline fill="none" stroke="black" points="231.705,-215.452 231.705,-183.452 "/>
<polyline fill="none" stroke="black" points="231.705,-215.452 235.705,-219.452 "/>
<text text-anchor="middle" x="149" y="-195.452" font-family="Times,serif" font-size="20.00">render_debug_page</text>
</g>
<!-- t6&#45;&gt;t8 -->
<g id="edge11" class="edge"><title>t6&#45;&gt;t8</title>
<path fill="none" stroke="#0044a0" d="M145.527,-241.346C145.857,-237.655 146.213,-233.665 146.568,-229.695"/>
<polygon fill="#0044a0" stroke="#0044a0" points="150.079,-229.725 147.482,-219.453 143.106,-229.102 150.079,-229.725"/>
</g>
<!-- t5&#45;&gt;t7 -->
<g id="edge10" class="edge"><title>t5&#45;&gt;t7</title>
<path fill="none" stroke="#0044a0" d="M315.167,-241.346C314.772,-237.655 314.344,-233.665 313.919,-229.695"/>
<polygon fill="#0044a0" stroke="#0044a0" points="317.367,-229.024 312.822,-219.453 310.407,-229.769 317.367,-229.024"/>
</g>
<!-- t5&#45;&gt;t8 -->
<g id="edge12" class="edge"><title>t5&#45;&gt;t8</title>
<path fill="none" stroke="#0044a0" d="M265.682,-241.346C248.014,-235.457 228.061,-228.806 209.716,-222.691"/>
<polygon fill="#0044a0" stroke="#0044a0" points="210.598,-219.295 200.004,-219.453 208.384,-225.936 210.598,-219.295"/>
</g>
<!-- t11 -->
<g id="node12" class="node"><title>t11</title>
<polygon fill="#efa03b" stroke="black" points="149.845,-105.456 230,-78.0208 310.155,-105.456 310.08,-149.848 149.92,-149.848 149.845,-105.456"/>
<polygon fill="none" stroke="black" points="145.836,-102.581 230,-73.7729 314.164,-102.581 314.078,-153.869 145.922,-153.869 145.836,-102.581"/>
<text text-anchor="middle" x="230" y="-111.726" font-family="Times,serif" font-size="20.00">merge_pages</text>
</g>
<!-- t7&#45;&gt;t11 -->
<g id="edge17" class="edge"><title>t7&#45;&gt;t11</title>
<path fill="none" stroke="#0044a0" d="M293.822,-183.12C287.553,-176.794 280.152,-169.328 272.653,-161.762"/>
<polygon fill="#0044a0" stroke="#0044a0" points="274.685,-158.84 265.16,-154.201 269.713,-163.767 274.685,-158.84"/>
</g>
<!-- t8&#45;&gt;t11 -->
<g id="edge16" class="edge"><title>t8&#45;&gt;t11</title>
<path fill="none" stroke="#0044a0" d="M166.178,-183.12C172.447,-176.794 179.848,-169.328 187.347,-161.762"/>
<polygon fill="#0044a0" stroke="#0044a0" points="190.287,-163.767 194.84,-154.201 185.315,-158.84 190.287,-163.767"/>
</g>
<!-- t10&#45;&gt;t11 -->
<g id="edge15" class="edge"><title>t10&#45;&gt;t11</title>
<path fill="none" stroke="#0044a0" d="M56.8713,-357.375C40.6714,-320.554 9.49472,-233.019 53,-183.452 74.3258,-159.154 105.557,-143.971 135.87,-134.485"/>
<polygon fill="#0044a0" stroke="#0044a0" points="137.062,-137.783 145.666,-131.601 135.085,-131.068 137.062,-137.783"/>
</g>
<!-- t9&#45;&gt;t11 -->
<g id="edge19" class="edge"><title>t9&#45;&gt;t11</title>
<path fill="none" stroke="gray" d="M390.73,-415.09C392.803,-392.758 396,-352.756 396,-318.452 396,-318.452 396,-318.452 396,-258.452 396,-224.066 399.207,-209.706 377,-183.452 362.867,-166.743 343.584,-154.196 323.637,-144.829"/>
<polygon fill="gray" stroke="gray" points="325.001,-141.605 314.441,-140.745 322.16,-148.003 325.001,-141.605"/>
</g>
<!-- t12 -->
<g id="node13" class="node"><title>t12</title>
<polygon fill="#efa03b" stroke="black" points="292.338,-52 171.662,-52 167.662,-48 167.662,-16 288.338,-16 292.338,-20 292.338,-52"/>
<polyline fill="none" stroke="black" points="288.338,-48 167.662,-48 "/>
<polyline fill="none" stroke="black" points="288.338,-48 288.338,-16 "/>
<polyline fill="none" stroke="black" points="288.338,-48 292.338,-52 "/>
<text text-anchor="middle" x="230" y="-28" font-family="Times,serif" font-size="20.00">validate_pdfa</text>
</g>
<!-- t11&#45;&gt;t12 -->
<g id="edge18" class="edge"><title>t11&#45;&gt;t12</title>
<path fill="none" stroke="#0044a0" d="M230,-73.9482C230,-69.9654 230,-66.007 230,-62.2247"/>
<polygon fill="#0044a0" stroke="#0044a0" points="233.5,-62.1573 230,-52.1573 226.5,-62.1574 233.5,-62.1573"/>
</g>
</g>
</svg>
Side by Side

After

Width:  |  Height:  |  Size: 14 KiB