Hello community,
here is the log from the commit of package python-pytesseract for
openSUSE:Factory checked in at 2019-07-22 17:20:24
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Comparing /work/SRC/openSUSE:Factory/python-pytesseract (Old)
and /work/SRC/openSUSE:Factory/.python-pytesseract.new.4126 (New)
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "python-pytesseract"
Mon Jul 22 17:20:24 2019 rev:5 rq:717602 version:0.2.7
Changes:
--------
--- /work/SRC/openSUSE:Factory/python-pytesseract/python-pytesseract.changes
2019-05-16 22:07:10.954441639 +0200
+++
/work/SRC/openSUSE:Factory/.python-pytesseract.new.4126/python-pytesseract.changes
2019-07-22 17:20:25.721893847 +0200
@@ -1,0 +2,6 @@
+Mon Jul 22 13:31:45 UTC 2019 - Tomáš Chvátal <tchva...@suse.com>
+
+- Update to 0.2.7:
+ * no upstream changelog
+
+-------------------------------------------------------------------
Old:
----
LICENSE
pytesseract-0.2.6.tar.gz
New:
----
pytesseract-0.2.7.tar.gz
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Other differences:
------------------
++++++ python-pytesseract.spec ++++++
--- /var/tmp/diff_new_pack.3vYOXk/_old 2019-07-22 17:20:26.249893703 +0200
+++ /var/tmp/diff_new_pack.3vYOXk/_new 2019-07-22 17:20:26.249893703 +0200
@@ -18,14 +18,13 @@
%{?!python_module:%define python_module() python-%{**} python3-%{**}}
Name: python-pytesseract
-Version: 0.2.6
+Version: 0.2.7
Release: 0
Summary: Python wrapper for Google's Tesseract-OCR
License: GPL-3.0-only
Group: Development/Languages/Python
URL: https://github.com/madmaze/python-tesseract
Source:
https://files.pythonhosted.org/packages/source/p/pytesseract/pytesseract-%{version}.tar.gz
-Source10:
https://raw.githubusercontent.com/madmaze/pytesseract/v%{version}/LICENSE
BuildRequires: %{python_module setuptools}
BuildRequires: fdupes
BuildRequires: python-rpm-macros
@@ -57,7 +56,6 @@
%prep
%setup -q -n pytesseract-%{version}
sed -i -e '/^#!\//, 1d' src/pytesseract.py
-cp %{SOURCE10} .
%build
%python_build
++++++ pytesseract-0.2.6.tar.gz -> pytesseract-0.2.7.tar.gz ++++++
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/pytesseract-0.2.6/PKG-INFO
new/pytesseract-0.2.7/PKG-INFO
--- old/pytesseract-0.2.6/PKG-INFO 2018-12-16 03:37:50.000000000 +0100
+++ new/pytesseract-0.2.7/PKG-INFO 2019-06-19 04:40:12.000000000 +0200
@@ -1,6 +1,6 @@
Metadata-Version: 1.1
Name: pytesseract
-Version: 0.2.6
+Version: 0.2.7
Summary: Python-tesseract is a python wrapper for Google's Tesseract-OCR
Home-page: https://github.com/madmaze/python-tesseract
Author: Matthias Lee
@@ -55,6 +55,13 @@
# French text image to string
print(pytesseract.image_to_string(Image.open('test-european.jpg'),
lang='fra'))
+ # In order to bypass the image conversions of pytesseract, just
use relative or absolute image path
+ # NOTE: In this case you should provide tesseract supported images
or tesseract will return error
+ print(pytesseract.image_to_string('test.png'))
+
+ # Batch processing with a single file containing the list of
multiple image file paths
+ print(pytesseract.image_to_string('images.txt'))
+
# Get bounding box estimates
print(pytesseract.image_to_boxes(Image.open('test.png')))
@@ -64,14 +71,10 @@
# Get information about orientation and script detection
print(pytesseract.image_to_osd(Image.open('test.png')))
- # In order to bypass the internal image conversions, just use
relative or absolute image path
- # NOTE: If you don't use supported images, tesseract will return
error
- print(pytesseract.image_to_string('test.png'))
-
- # get a searchable PDF
+ # Get a searchable PDF
pdf = pytesseract.image_to_pdf_or_hocr('test.png', extension='pdf')
- # get HOCR output
+ # Get HOCR output
hocr = pytesseract.image_to_pdf_or_hocr('test.png',
extension='hocr')
Support for OpenCV image/NumPy array objects
@@ -89,13 +92,11 @@
.. code-block:: python
- tessdata_dir_config = r'--tessdata-dir
"<replace_with_your_tessdata_dir_path>"'
# Example config: r'--tessdata-dir "C:\Program Files
(x86)\Tesseract-OCR\tessdata"'
# It's important to add double quotes around the dir path.
-
+ tessdata_dir_config = r'--tessdata-dir
"<replace_with_your_tessdata_dir_path>"'
pytesseract.image_to_string(image, lang='chi_sim',
config=tessdata_dir_config)
-
**Functions**
* **get_tesseract_version** Returns the Tesseract version installed in
the system.
@@ -128,7 +129,7 @@
Prerequisites:
- - Python-tesseract requires python 2.6+ or python 3.x
+ - Python-tesseract requires python 2.7+ or python 3.x
- You will need the Python Imaging Library (PIL) (or the `Pillow
<https://pypi.org/project/Pillow/>`_ fork).
Under Debian/Ubuntu, this is the package **python-imaging** or
**python3-imaging**.
- Install `Google Tesseract OCR
<https://github.com/tesseract-ocr/tesseract>`_
@@ -176,5 +177,5 @@
Keywords: python-tesseract OCR Python
Platform: UNKNOWN
Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 2
+Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/pytesseract-0.2.6/README.rst
new/pytesseract-0.2.7/README.rst
--- old/pytesseract-0.2.6/README.rst 2018-10-05 03:46:37.000000000 +0200
+++ new/pytesseract-0.2.7/README.rst 2019-06-19 04:40:00.000000000 +0200
@@ -46,6 +46,13 @@
# French text image to string
print(pytesseract.image_to_string(Image.open('test-european.jpg'),
lang='fra'))
+ # In order to bypass the image conversions of pytesseract, just use
relative or absolute image path
+ # NOTE: In this case you should provide tesseract supported images or
tesseract will return error
+ print(pytesseract.image_to_string('test.png'))
+
+ # Batch processing with a single file containing the list of multiple
image file paths
+ print(pytesseract.image_to_string('images.txt'))
+
# Get bounding box estimates
print(pytesseract.image_to_boxes(Image.open('test.png')))
@@ -55,14 +62,10 @@
# Get information about orientation and script detection
print(pytesseract.image_to_osd(Image.open('test.png')))
- # In order to bypass the internal image conversions, just use relative or
absolute image path
- # NOTE: If you don't use supported images, tesseract will return error
- print(pytesseract.image_to_string('test.png'))
-
- # get a searchable PDF
+ # Get a searchable PDF
pdf = pytesseract.image_to_pdf_or_hocr('test.png', extension='pdf')
- # get HOCR output
+ # Get HOCR output
hocr = pytesseract.image_to_pdf_or_hocr('test.png', extension='hocr')
Support for OpenCV image/NumPy array objects
@@ -80,13 +83,11 @@
.. code-block:: python
- tessdata_dir_config = r'--tessdata-dir
"<replace_with_your_tessdata_dir_path>"'
# Example config: r'--tessdata-dir "C:\Program Files
(x86)\Tesseract-OCR\tessdata"'
# It's important to add double quotes around the dir path.
-
+ tessdata_dir_config = r'--tessdata-dir
"<replace_with_your_tessdata_dir_path>"'
pytesseract.image_to_string(image, lang='chi_sim',
config=tessdata_dir_config)
-
**Functions**
* **get_tesseract_version** Returns the Tesseract version installed in the
system.
@@ -119,7 +120,7 @@
Prerequisites:
-- Python-tesseract requires python 2.6+ or python 3.x
+- Python-tesseract requires python 2.7+ or python 3.x
- You will need the Python Imaging Library (PIL) (or the `Pillow
<https://pypi.org/project/Pillow/>`_ fork).
Under Debian/Ubuntu, this is the package **python-imaging** or
**python3-imaging**.
- Install `Google Tesseract OCR <https://github.com/tesseract-ocr/tesseract>`_
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/pytesseract-0.2.6/pytesseract.egg-info/PKG-INFO
new/pytesseract-0.2.7/pytesseract.egg-info/PKG-INFO
--- old/pytesseract-0.2.6/pytesseract.egg-info/PKG-INFO 2018-12-16
03:37:50.000000000 +0100
+++ new/pytesseract-0.2.7/pytesseract.egg-info/PKG-INFO 2019-06-19
04:40:12.000000000 +0200
@@ -1,6 +1,6 @@
Metadata-Version: 1.1
Name: pytesseract
-Version: 0.2.6
+Version: 0.2.7
Summary: Python-tesseract is a python wrapper for Google's Tesseract-OCR
Home-page: https://github.com/madmaze/python-tesseract
Author: Matthias Lee
@@ -55,6 +55,13 @@
# French text image to string
print(pytesseract.image_to_string(Image.open('test-european.jpg'),
lang='fra'))
+ # In order to bypass the image conversions of pytesseract, just
use relative or absolute image path
+ # NOTE: In this case you should provide tesseract supported images
or tesseract will return error
+ print(pytesseract.image_to_string('test.png'))
+
+ # Batch processing with a single file containing the list of
multiple image file paths
+ print(pytesseract.image_to_string('images.txt'))
+
# Get bounding box estimates
print(pytesseract.image_to_boxes(Image.open('test.png')))
@@ -64,14 +71,10 @@
# Get information about orientation and script detection
print(pytesseract.image_to_osd(Image.open('test.png')))
- # In order to bypass the internal image conversions, just use
relative or absolute image path
- # NOTE: If you don't use supported images, tesseract will return
error
- print(pytesseract.image_to_string('test.png'))
-
- # get a searchable PDF
+ # Get a searchable PDF
pdf = pytesseract.image_to_pdf_or_hocr('test.png', extension='pdf')
- # get HOCR output
+ # Get HOCR output
hocr = pytesseract.image_to_pdf_or_hocr('test.png',
extension='hocr')
Support for OpenCV image/NumPy array objects
@@ -89,13 +92,11 @@
.. code-block:: python
- tessdata_dir_config = r'--tessdata-dir
"<replace_with_your_tessdata_dir_path>"'
# Example config: r'--tessdata-dir "C:\Program Files
(x86)\Tesseract-OCR\tessdata"'
# It's important to add double quotes around the dir path.
-
+ tessdata_dir_config = r'--tessdata-dir
"<replace_with_your_tessdata_dir_path>"'
pytesseract.image_to_string(image, lang='chi_sim',
config=tessdata_dir_config)
-
**Functions**
* **get_tesseract_version** Returns the Tesseract version installed in
the system.
@@ -128,7 +129,7 @@
Prerequisites:
- - Python-tesseract requires python 2.6+ or python 3.x
+ - Python-tesseract requires python 2.7+ or python 3.x
- You will need the Python Imaging Library (PIL) (or the `Pillow
<https://pypi.org/project/Pillow/>`_ fork).
Under Debian/Ubuntu, this is the package **python-imaging** or
**python3-imaging**.
- Install `Google Tesseract OCR
<https://github.com/tesseract-ocr/tesseract>`_
@@ -176,5 +177,5 @@
Keywords: python-tesseract OCR Python
Platform: UNKNOWN
Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 2
+Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/pytesseract-0.2.6/setup.py
new/pytesseract-0.2.7/setup.py
--- old/pytesseract-0.2.6/setup.py 2018-12-16 03:37:30.000000000 +0100
+++ new/pytesseract-0.2.7/setup.py 2019-06-19 04:40:00.000000000 +0200
@@ -14,7 +14,7 @@
setup(
name=PACKAGE_NAME,
- version='0.2.6',
+ version='0.2.7',
author='Samuel Hoffstaetter',
author_email='sam...@hoffstaetter.com',
maintainer='Matthias Lee',
@@ -35,7 +35,7 @@
},
classifiers=[
'Programming Language :: Python',
- 'Programming Language :: Python :: 2',
+ 'Programming Language :: Python :: 2.7',
'Programming Language :: Python :: 3',
]
)
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/pytesseract-0.2.6/src/pytesseract.py
new/pytesseract-0.2.7/src/pytesseract.py
--- old/pytesseract-0.2.6/src/pytesseract.py 2018-12-16 03:37:30.000000000
+0100
+++ new/pytesseract-0.2.7/src/pytesseract.py 2019-06-19 04:40:00.000000000
+0200
@@ -145,13 +145,13 @@
'stdin': subprocess.PIPE,
'stderr': subprocess.PIPE,
'startupinfo': None,
- 'env': None
+ 'env': os.environ
}
if hasattr(subprocess, 'STARTUPINFO'):
kwargs['startupinfo'] = subprocess.STARTUPINFO()
kwargs['startupinfo'].dwFlags |= subprocess.STARTF_USESHOWWINDOW
- kwargs['env'] = os.environ
+ kwargs['startupinfo'].wShowWindow = subprocess.SW_HIDE
if include_stdout:
kwargs['stdout'] = subprocess.PIPE
@@ -177,7 +177,7 @@
cmd_args += shlex.split(config)
- if extension not in ('box', 'osd', 'tsv'):
+ if extension not in {'box', 'osd', 'tsv'}:
cmd_args.append(extension)
try:
@@ -185,15 +185,15 @@
except OSError:
raise TesseractNotFoundError()
- status_code, error_string = proc.wait(), proc.stderr.read()
- proc.stdin.close()
- proc.stdout.close()
- proc.stderr.close()
-
- if status_code:
- raise TesseractError(status_code, get_errors(error_string))
+ try:
+ _, error_string = proc.communicate()
+ finally:
+ proc.stdin.close()
+ proc.stdout.close()
+ proc.stderr.close()
- return True
+ if proc.returncode:
+ raise TesseractError(proc.returncode, get_errors(error_string))
def run_and_get_output(image,
@@ -318,7 +318,7 @@
Returns the result of a Tesseract OCR run on the provided image to pdf/hocr
'''
- if extension not in ['pdf', 'hocr']:
+ if extension not in {'pdf', 'hocr'}:
raise ValueError('Unsupported extension: {}'.format(extension))
args = [image, extension, lang, config, nice, True]
