1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
|
The Debian packaging of OCRmyPDF is maintained using dgit. For the
sake of an efficient workflow, Debian modifications to the upstream
source are squashed into a single diff, rather than a series of quilt
patches. To obtain a patch queue for package version 1.2.3-1:
# apt-get install dgit
% dgit clone ocrmypdf
% cd ocrmypdf
% git log --oneline 1.2.3..debian/1.2.3-1 -- . ':!debian'
See dgit(1), dgit(7) and dgit-maint-merge(7) for more information.
--- ocrmypdf-13.7.0+dfsg.orig/docs/conf.py
+++ ocrmypdf-13.7.0+dfsg/docs/conf.py
@@ -102,7 +102,7 @@ except ModuleNotFoundError:
from importlib.metadata import version as package_version
# The full version, including alpha/beta/rc tags.
-release = package_version('ocrmypdf')
+release = os.environ['DEB_VERSION_UPSTREAM']
version = '.'.join(release.split('.')[:2])
--- ocrmypdf-13.7.0+dfsg.orig/docs/index.rst
+++ ocrmypdf-13.7.0+dfsg/docs/index.rst
@@ -19,7 +19,6 @@ image processing and OCR to existing PDF
introduction
release_notes
- installation
optimizer
languages
jbig2
--- ocrmypdf-13.7.0+dfsg.orig/docs/languages.rst
+++ ocrmypdf-13.7.0+dfsg/docs/languages.rst
@@ -26,9 +26,6 @@ English is assumed by default unless oth
For Linux users, you can often find packages that provide language
packs:
-Debian and Ubuntu users
-=======================
-
.. code-block:: bash
# Display a list of all Tesseract language packs
@@ -39,69 +36,5 @@ Debian and Ubuntu users
You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as
to what languages it should search for. Multiple languages can be
-requested using either ``-l eng+fra`` (English and French) or
-``-l eng -l fra``.
-
-Fedora users
-============
-
-.. code-block:: bash
-
- # Display a list of all Tesseract language packs
- dnf search tesseract
-
- # Install Chinese Simplified language pack
- dnf install tesseract-langpack-chi_sim
-
-You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as
-to what languages it should search for. Multiple languages can be
-requested using either ``-l eng+fra`` (English and French) or
-``-l eng -l fra``.
-
-Gentoo users
-============
-
-On Gentoo the package ``app-text/tessdata_fast``, which ``app-text/tesseract`` depends on, handles Tesseract languages.
-It accepts USE flags to select what languages should be installed, these can be set in ``/etc/portage/package.use``.
-Alternatively one can globally set the `L10N use extension <https://wiki.gentoo.org/wiki/Localization/Guide#L10N>`__ in ``/etc/portage/make.conf``.
-This enables these languages for all packages (e.g. including aspell).
-
-.. code-block:: bash
-
- # Display a list of all Tesseract language packs
- equery uses app-text/tessdata_fast
-
- # Add English and German language support for Tesseract only
- echo 'app-text/tessdata_fast l10n_de l10n_en' >> /etc/portage/package.use
-
- # Add global English and German language support (the `l10n_` from equery has to be omited)
- echo L10N="de en" >> /etc/portage/make.conf
-
- # update system to reflect changed USE flags
- emerge --update --deep --newuse @world
-
-You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as
-to what languages it should search for. Multiple languages can be
-requested using either ``-l eng+fra`` (English and French) or
-``-l eng -l fra``.
-
-macOS users
-===========
-
-You can install additional language packs by
-:ref:`installing Tesseract using Homebrew with all language packs <macos-all-languages>`.
-
-Docker users
-============
-
-Users of the OCRmyPDF Docker image should install language packs into a
-derived Docker image as
-:ref:`described in that section <docker-lang-packs>`.
-
-Windows users
-=============
-
-The Tesseract installer provided by Chocolatey currently includes only English language.
-To install other languages, download the respective language pack (``.traineddata`` file)
-from https://github.com/tesseract-ocr/tessdata/ and place it in
-``C:\\Program Files\\Tesseract-OCR\\tessdata`` (or wherever Tesseract OCR is installed).
+requested using either ``-l eng+fre`` (English and French) or
+``-l eng -l fre``.
--- ocrmypdf-13.7.0+dfsg.orig/pyproject.toml
+++ ocrmypdf-13.7.0+dfsg/pyproject.toml
@@ -79,7 +79,6 @@ known_third_party = [
minversion = "6.0"
norecursedirs = ["lib", ".pc", ".git", "venv", "output", "cache", "resources"]
testpaths = ["tests"]
-addopts = "-n auto"
markers = ["slow"]
filterwarnings = ["ignore:.*XMLParser.*:DeprecationWarning"]
--- ocrmypdf-13.7.0+dfsg.orig/src/ocrmypdf/cli.py
+++ ocrmypdf-13.7.0+dfsg/src/ocrmypdf/cli.py
@@ -126,7 +126,7 @@ minimize the number of changes made to y
If OCRmyPDF is given an image file as input, it will attempt to convert the
image to a PDF before processing. For more control over the conversion of
-images to PDF, use the Python package img2pdf or other image to PDF software.
+images to PDF, use img2pdf, or other image to PDF software.
For example, this command uses img2pdf to convert all .png files beginning
with the 'page' prefix to a PDF, fitting each image on A4-sized paper, and
@@ -134,8 +134,9 @@ sending the result to OCRmyPDF through a
img2pdf --pagesize A4 page*.png | ocrmypdf - myfile.pdf
-Online documentation is located at:
- https://ocrmypdf.readthedocs.io/en/latest/introduction.html
+HTML documentation is located at:
+ /usr/share/doc/ocrmypdf/html/index.html
+after installing the ocrmypdf-doc package.
""",
)
|
