This file is indexed.

/usr/lib/python3/dist-packages/ocrmypdf-6.1.2.egg-info/PKG-INFO is in ocrmypdf 6.1.2-1ubuntu1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
Metadata-Version: 2.1
Name: ocrmypdf
Version: 6.1.2
Summary: OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
Home-page: https://github.com/jbarlow83/OCRmyPDF
Author: James R. Barlow
Author-email: jim@purplerock.ca
License: UNKNOWN
Description: OCRmyPDF
        ========
        
        .. image:: https://travis-ci.org/jbarlow83/OCRmyPDF.svg?branch=master
            :target: https://travis-ci.org/jbarlow83/OCRmyPDF
        
        .. image:: https://img.shields.io/pypi/v/ocrmypdf.svg   
            :target: https://pypi.org/project/ocrmypdf/
        
        .. image:: https://img.shields.io/homebrew/v/ocrmypdf.svg   
            :alt: homebrew
            :target: http://brewformulas.org/Ocrmypdf
        
        
        OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to
        be searched or copy-pasted.
        
        .. code-block:: bash
        
           ocrmypdf                      # it's a scriptable command line program
              -l eng+fra                 # it supports multiple languages
              --rotate-pages             # it can fix pages that are misrotated
              --deskew                   # it can deskew crooked PDFs!
              --title "My PDF"           # it can change output metadata
              --jobs 4                   # it uses multiple cores by default
              --output-type pdfa         # it produces PDF/A by default
              input_scanned.pdf          # takes PDF input (or images)
              output_searchable.pdf      # produces validated PDF output
        
        
        Main features
        -------------
        
        -  Generates a searchable
           `PDF/A <https://en.wikipedia.org/?title=PDF/A>`_ file from a regular PDF
        -  Places OCR text accurately below the image to ease copy / paste
        -  Keeps the exact resolution of the original embedded images
        -  When possible, inserts OCR information as a "lossless" operation without rendering vector information
        -  Keeps file size about the same
        -  If requested deskews and/or cleans the image before performing OCR
        -  Validates input and output files
        -  Provides debug mode to enable easy verification of the OCR results
        -  Processes pages in parallel when more than one CPU core is
           available
        -  Uses `Tesseract OCR <https://github.com/tesseract-ocr/tesseract>`_ engine
        -  Supports more than `100 languages <https://github.com/tesseract-ocr/tessdata>`_ recognized by Tesseract
        -  Battle-tested on thousands of PDFs, a test suite and continuous integration
        
        For details: please consult the `documentation <https://ocrmypdf.readthedocs.io/en/latest/>`_.
        
        Motivation
        ----------
        
        I searched the web for a free command line tool to OCR PDF files on
        Linux/UNIX: I found many, but none of them were really satisfying.
        
        -  Either they produced PDF files with misplaced text under the image (making copy/paste impossible) 
        -  Or they did not handle accents and multilingual characters
        -  Or they changed the resolution of the embedded images
        -  Or they generated ridiculously large PDF files
        -  Or they crashed when trying to OCR some of my PDF files
        -  Or they did not produce valid PDF files (even though they were readable with my current PDF reader)
        -  On top of that none of them produced PDF/A files (format dedicated for long time storage)
        
        ...so I decided to develop my own tool (using various existing scripts
        as an inspiration). 
        
        Installation
        ------------
        
        Linux, UNIX, and macOS are supported. Windows is not directly supported but there is a Docker image available that runs on Windows.
        
        Users of Debian 9 or later or Ubuntu 16.10 or later may simply
        
        .. code-block:: bash
        
           apt-get install ocrmypdf
        
        and macOS users with Homebrew may simply
        
        .. code-block:: bash
        
           brew install ocrmypdf
        
        For everyone else, `see our documentation <https://ocrmypdf.readthedocs.io/en/latest/installation.html>`_ for installation steps.
        
        Languages
        ---------
        
        OCRmyPDF uses Tesseract for OCR, and relies on its language packs. For Linux users,
        you can often find packages that provide language packs:
        
        .. code-block:: bash
        
           # Display a list of all Tesseract language packs
           apt-cache search tesseract-ocr
        
           # Debian/Ubuntu users
           apt-get install tesseract-ocr-chi-sim  # Example: Install Chinese Simplified language back
           
        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.
        
        Documentation and support
        -------------------------
        
        Once ocrmypdf is installed, the built-in help which explains the command syntax and options can be accessed via:
        
        .. code-block:: bash
        
           ocrmypdf --help
        
        Our `documentation is served on Read the Docs <https://ocrmypdf.readthedocs.io/en/latest/index.html>`_.
        
        If you detect an issue, please:
        
        -  Check whether your issue is already known
        -  If no problem report exists on github, please create one here:
           https://github.com/jbarlow83/OCRmyPDF/issues
        -  Describe your problem thoroughly
        -  Append the console output of the script when running the debug mode
           (``-v 1`` option)
        -  If possible provide your input PDF file as well as the content of the
           temporary folder (using a file sharing service like Dropbox)
        
        Requirements
        ------------
        
        Runs on CPython 3.6, and requires external program installations of Ghostscript, Tesseract OCR, QPDF, and Leptonica. ocrmypdf is pure Python, but uses CFFI to portably generate library bindings.
        
        Python 3.5 is also supported.
        
        Press & Media
        -------------
        
        -  `c't 1-2014, page 59 <http://heise.de/-2279695>`_:
           Detailed presentation of OCRmyPDF v1.0 in the leading German IT
           magazine c't
        -  `heise Open Source, 09/2014: Texterkennung mit
           OCRmyPDF <http://heise.de/-2356670>`_
        
        License
        -------
        
        The OCRmyPDF software is licensed under the GNU GPLv3. Certain files are covered by other licenses, as noted in their source files. 
        
        The license for each test file varies, and is noted in tests/resources/README.rst. The documentation is licensed under Creative Commons Attribution-ShareAlike 4.0 (CC-BY-SA 4.0).
        
        OCRmyPDF versions prior to 6.0 were licensed under the MIT License.
        
        Disclaimer
        ----------
        
        The software is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
        CONDITIONS OF ANY KIND, either express or implied.
        
Keywords: PDF,OCR,optical character recognition,PDF/A,scanning
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Classifier: Development Status :: 5 - Production/Stable
Classifier: Environment :: Console
Classifier: Intended Audience :: End Users/Desktop
Classifier: Intended Audience :: Science/Research
Classifier: Intended Audience :: System Administrators
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Classifier: Operating System :: MacOS :: MacOS X
Classifier: Operating System :: POSIX
Classifier: Operating System :: POSIX :: BSD
Classifier: Operating System :: POSIX :: Linux
Classifier: Topic :: Scientific/Engineering :: Image Recognition
Classifier: Topic :: Text Processing :: Indexing
Classifier: Topic :: Text Processing :: Linguistic
Requires-Python:  >= 3.5
Provides-Extra: fitz