Merge pull request #296 from jpweytjens/min_python_version

Sphinx only supports python 3.5+

.travis.yml

@@ -1,10 +1,10 @@
 sudo: required
-dist: trusty
+dist: bionic
 
 language: python
 python:
   - "2.7"
-  - "3.4"
+  - "3.7"
 
 # install system dependencies here with apt-get.
 before_install:
@@ -13,15 +13,24 @@ before_install:
 # install python dependencies including this package in the travis
 # virtualenv
 install:
-  - ./provision/python.sh
-  - pip install .
+
+  - if [[ $TRAVIS_PYTHON_VERSION == 3.7 ]];
+        then ./provision/python3.sh;
+        fi
+  - if [[ $TRAVIS_PYTHON_VERSION == 2.7 ]];
+        then ./provision/python2.sh;
+        fi
+  - pip install .[pocketsphinx]
 
 # commands to run the testing suite. if any of these fail, travic lets us know
 script:
   - cd tests && make && cd -
   - nosetests --with-coverage --cover-package=textract
-  - pep8 textract/ bin/textract
-  - cd docs && make html && cd -
+  - cd tests && pytest && cd -
+  - pycodestyle textract/ bin/textract
+  - if [[ $TRAVIS_PYTHON_VERSION == 3.7 ]];
+        then cd docs && make html && cd -;
+        fi
 
 # commands to run after the tests successfully complete
 after_success:

README.rst

@@ -24,8 +24,8 @@ Extract text from any document. No muss. No fuss.
 .. |Downloads| image:: https://img.shields.io/pypi/dm/textract.svg
    :target: https://warehouse.python.org/project/textract/
 
-.. |Test Coverage| image:: https://coveralls.io/repos/deanmalmgren/textract/badge.png
-   :target: https://coveralls.io/r/deanmalmgren/textract
+.. |Test Coverage| image:: https://coveralls.io/repos/github/deanmalmgren/textract/badge.svg?branch=master
+    :target: https://coveralls.io/github/deanmalmgren/textract?branch=master
 
 .. |Documentation Status| image:: https://readthedocs.org/projects/textract/badge/?version=latest
    :target: https://readthedocs.org/projects/textract/?badge=latest

bin/textract

@@ -29,4 +29,5 @@ def main():
     else:
         args.output.write(output)
 
+
 main()

docs/conf.py

@@ -58,7 +58,7 @@
 # built documents.
 #
 # The short X.Y version.
-release = version = "1.6.1"
+release = version = "1.6.3"
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
@@ -132,7 +132,7 @@
 # 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 = []
 
 # Add any extra paths that contain custom files (such as robots.txt or
 # .htaccess) here, relative to this directory. These files are copied

docs/index.rst

@@ -74,7 +74,7 @@ file types by either mentioning them on the `issue tracker
 
 * ``.pptx`` via `python-pptx`_
 
-* ``.ps`` via `ps2text`_
+* ``.ps`` via `ps2ascii`_
 
 * ``.rtf`` via `unrtf`_
 
@@ -96,7 +96,7 @@ file types by either mentioning them on the `issue tracker
 .. _pdfminer.six: https://github.com/goulu/pdfminer
 .. _pdftotext: http://poppler.freedesktop.org/
 .. _pocketsphinx: https://github.com/cmusphinx/pocketsphinx/
-.. _ps2text: http://pages.cs.wisc.edu/~ghost/doc/pstotext.htm
+.. _ps2ascii: https://www.ghostscript.com/doc/current/Use.htm
 .. _python-docx2txt: https://github.com/ankushshah89/python-docx2txt
 .. _python-pptx: https://python-pptx.readthedocs.org/en/latest/
 .. _SpeechRecognition: https://pypi.python.org/pypi/SpeechRecognition/

provision/python.sh → provision/python2.sh

@@ -12,4 +12,4 @@ fi
 pip install -U pip
 
 # Install the requirements for this package as well as this module.
-pip install -r requirements/python-dev
+pip install -r requirements/python-dev2

provision/python3.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+# This needs to work for vagrant, Travis builds, and Docker builds.
+# in a python virtualenv. in the virtual machine provisioning,
+# we're passing the directory this should be run from. in travis-ci,
+# its run from the root of the repository.
+if [ "$#" -eq 1 ]; then
+     cd $1
+fi
+
+# upgrade pip so we can use wheel downloads
+pip install -U pip
+
+# Install the requirements for this package as well as this module.
+pip install -r requirements/python-dev3
+pip install -r requirements/python-doc

requirements/debian

@@ -1,6 +1,7 @@
 # required packages
 gcc
 libpulse-dev
+libasound2-dev
 libjpeg-dev
 build-essential
 git
@@ -9,6 +10,7 @@ make
 # these packages are required by python-docx, which depends on lxml
 # and requires these things
 python-dev
+python-pip
 libxml2-dev
 libxslt1-dev
 
@@ -19,7 +21,7 @@ antiword
 unrtf
 
 # parse image files
-tesseract-ocr=3.03\*
+tesseract-ocr
 libjpeg-dev
 
 # parse pdfs

requirements/python

@@ -2,7 +2,7 @@
 # package in order for it to properly work.
 
 argcomplete==1.10.0
-beautifulsoup4==4.7.1
+beautifulsoup4==4.8.0
 chardet==3.0.4
 docx2txt==0.8
 EbookLib==0.17.1

requirements/python-dev → requirements/python-dev2

@@ -3,14 +3,14 @@
 # documentation builds (python-doc)
 
 -r python
--r python-doc
 
 # needed for tests/run.py script to read .travis.yml file
-coveralls==1.8.1
+coveralls==1.8.2
 nose==1.3.7
-pep8==1.7.1
+pycodestyle==2.5.0
 PyYAML==5.1.1
 requests==2.22.0
+pytest==4.6
 
 # needed for managing versions
 bumpversion==0.5.3

requirements/python-dev3

@@ -0,0 +1,16 @@
+# This includes all packages that are used in development, including all
+# packages that are required by textract itself (python), packages for
+# documentation builds (python-doc)
+
+-r python
+
+# needed for tests/run.py script to read .travis.yml file
+coveralls==1.8.2
+nose==1.3.7
+pycodestyle==2.5.0
+PyYAML==5.1.1
+pytest==5.0.1
+requests==2.22.0
+
+# needed for managing versions
+bumpversion==0.5.3

setup.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 1.6.2
+current_version = 1.6.3
 commit = True
 tag = True
 

setup.py

@@ -42,7 +42,7 @@ def parse_requirements(requirements_filename):
 
 setup(
     name=textract.__name__,
-    version="1.6.2",
+    version="1.6.3",
     description="extract text from any document. no muss. no fuss.",
     long_description=long_description,
     url=github_url,

tests/Makefile

@@ -11,7 +11,8 @@ TARGETS = pdf/ocr_text.txt \
 	png/raw_text.txt png/standardized_text.txt \
 	gif/raw_text.txt gif/standardized_text.txt \
     jpg/raw_text.txt jpg/standardized_text.txt \
-    tiff/raw_text.txt tiff/standardized_text.txt
+    tiff/raw_text.txt tiff/standardized_text.txt \
+	ps/raw_text.txt
 
 all: $(TARGETS)
 
@@ -27,6 +28,9 @@ pdf/ocr_text.txt: pdf/ocr_text.pdf
 	cat pdf-ocr-text*.txt > $@
 	rm -f pdf-ocr-text*
 
+ps/raw_text.txt: ps/raw_text.ps
+	ps2ascii $< > $@
+
 # simple pattern rule for creating standard issue tesseract files for different
 # fileypes. the `g` shell variable is the path to the file without the
 # extension (e.g. g=png/raw_text)