mirror of
https://github.com/ocrmypdf/OCRmyPDF.git
synced 2026-05-18 11:36:26 -04:00
Fix numerous documentation build problems
This commit is contained in:
James R. Barlow
@@ -244,34 +244,34 @@ As of June 2024, the Tesseract page segmentation modes are:
|
||||
+-----+----------------------------------------------------------------------------------+
|
||||
| ID | Description |
|
||||
+=====+==================================================================================+
|
||||
| 0 | Orientation and script detection (OSD) only. |
|
||||
| 0 | Orientation and script detection (OSD) only. |
|
||||
+-----+----------------------------------------------------------------------------------+
|
||||
| 1 | Automatic page segmentation with OSD. |
|
||||
| 1 | Automatic page segmentation with OSD. |
|
||||
+-----+----------------------------------------------------------------------------------+
|
||||
| 2 | Automatic page segmentation, but no OSD, or OCR. (not implemented) |
|
||||
+-----+----------------------------------------------------------------------------------+
|
||||
| 3 | Fully automatic page segmentation, but no OSD. (Default) |
|
||||
+-----+----------------------------------------------------------------------------------+
|
||||
| 4 | Assume a single column of text of variable sizes. |
|
||||
| 4 | Assume a single column of text of variable sizes. |
|
||||
+-----+----------------------------------------------------------------------------------+
|
||||
| 5 | Assume a single uniform block of vertically aligned text. |
|
||||
| 5 | Assume a single uniform block of vertically aligned text. |
|
||||
+-----+----------------------------------------------------------------------------------+
|
||||
| 6 | Assume a single uniform block of text. |
|
||||
| 6 | Assume a single uniform block of text. |
|
||||
+-----+----------------------------------------------------------------------------------+
|
||||
| 7 | Treat the image as a single text line. |
|
||||
| 7 | Treat the image as a single text line. |
|
||||
+-----+----------------------------------------------------------------------------------+
|
||||
| 8 | Treat the image as a single word. |
|
||||
| 8 | Treat the image as a single word. |
|
||||
+-----+----------------------------------------------------------------------------------+
|
||||
| 9 | Treat the image as a single word in a circle. |
|
||||
| 9 | Treat the image as a single word in a circle. |
|
||||
+-----+----------------------------------------------------------------------------------+
|
||||
| 10 | Treat the image as a single character. |
|
||||
| 10 | Treat the image as a single character. |
|
||||
+-----+----------------------------------------------------------------------------------+
|
||||
| 11 | Sparse text. Find as much text as possible in no particular order. |
|
||||
| 11 | Sparse text. Find as much text as possible in no particular order. |
|
||||
+-----+----------------------------------------------------------------------------------+
|
||||
| 12 | Sparse text with OSD. |
|
||||
+-----+----------------------------------------------------------------------------------+
|
||||
| 13 | Raw line. Treat the image as a single text line, bypassing hacks that are |
|
||||
| | Tesseract-specific. |
|
||||
| | Tesseract-specific. |
|
||||
+-----+----------------------------------------------------------------------------------+
|
||||
|
||||
Modes 0, 1, 2, and 12 (all of those that enable orientation and script detection)
|
||||
|
||||
@@ -9,27 +9,12 @@ API reference
|
||||
This page summarizes the rest of the public API. Generally speaking this
|
||||
should be mainly of interest to plugin developers.
|
||||
|
||||
ocrmypdf
|
||||
========
|
||||
ocrmypdf.api
|
||||
============
|
||||
|
||||
.. autoclass:: ocrmypdf.PageContext
|
||||
.. automodule:: ocrmypdf.api
|
||||
:members:
|
||||
|
||||
.. autoclass:: ocrmypdf.PdfContext
|
||||
:members:
|
||||
|
||||
.. autoclass:: ocrmypdf.Verbosity
|
||||
:members:
|
||||
:undoc-members:
|
||||
|
||||
.. autofunction:: ocrmypdf.configure_logging
|
||||
|
||||
.. autofunction:: ocrmypdf.ocr
|
||||
|
||||
.. autofunction:: ocrmypdf.pdf_to_hocr
|
||||
|
||||
.. autofunction:: ocrmypdf.hocr_to_ocr_pdf
|
||||
|
||||
ocrmypdf.exceptions
|
||||
===================
|
||||
|
||||
|
||||
10
docs/conf.py
10
docs/conf.py
@@ -92,6 +92,7 @@ if on_rtd:
|
||||
|
||||
MOCK_MODULES = [
|
||||
'pikepdf',
|
||||
'pikepdf.canvas',
|
||||
'pikepdf.models',
|
||||
'pikepdf.models.metadata',
|
||||
]
|
||||
@@ -108,7 +109,7 @@ version = '.'.join(release.split('.')[:2])
|
||||
#
|
||||
# This is also used if you do content translation via gettext catalogs.
|
||||
# Usually you set "language" from the command line for these cases.
|
||||
language = None
|
||||
language = 'en'
|
||||
|
||||
# There are two options for replacing |today|: either, you set today to some
|
||||
# non-false value, then it is used:
|
||||
@@ -158,19 +159,18 @@ todo_include_todos = False
|
||||
|
||||
# -- Options for HTML output ----------------------------------------------
|
||||
|
||||
import sphinx_rtd_theme
|
||||
import sphinx_rtd_theme # noqa: F401
|
||||
|
||||
# The theme to use for HTML and HTML Help pages. See the documentation for
|
||||
# a list of builtin themes.
|
||||
#
|
||||
html_theme = 'sphinx_rtd_theme'
|
||||
html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
|
||||
|
||||
# Theme options are theme-specific and customize the look and feel of a theme
|
||||
# further. For a list of options available for each theme, see the
|
||||
# documentation.
|
||||
#
|
||||
html_theme_options = {'display_version': False}
|
||||
html_theme_options = {}
|
||||
|
||||
# Add any paths that contain custom themes here, relative to this directory.
|
||||
# html_theme_path = []
|
||||
@@ -198,7 +198,7 @@ html_theme_options = {'display_version': False}
|
||||
# Add any paths that contain custom static files (such as style sheets) here,
|
||||
# relative to this directory. They are copied after the builtin static files,
|
||||
# so a file named "default.css" will overwrite the builtin "default.css".
|
||||
html_static_path = ['_static']
|
||||
# html_static_path = ['_static']
|
||||
|
||||
# Add any extra paths that contain custom files (such as robots.txt or
|
||||
# .htaccess) here, relative to this directory. These files are copied
|
||||
|
||||
@@ -35,7 +35,7 @@ execute the image:
|
||||
docker run hello-world
|
||||
|
||||
.. list-table:: Docker images
|
||||
:width: 30 20 50
|
||||
:widths: 30 20 50
|
||||
:header-rows: 1
|
||||
|
||||
* - Image
|
||||
|
||||
@@ -68,8 +68,8 @@ 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``.
|
||||
|
||||
Archlinux
|
||||
------
|
||||
Arch Linux
|
||||
----------
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
|
||||
@@ -2,6 +2,8 @@
|
||||
..
|
||||
.. SPDX-License-Identifier: CC-BY-SA-4.0
|
||||
|
||||
.. _security:
|
||||
|
||||
===================
|
||||
PDF security issues
|
||||
===================
|
||||
|
||||
Reference in New Issue
Block a user