Drop python2 support

.gitignore

@@ -71,3 +71,6 @@ tests/gif/standardized_text.txt
 tests/jpg/standardized_text.txt
 tests/tiff/standardized_text.txt
 tests/pdf/ocr_text.txt
+
+# PyCharm
+.idea/

.travis.yml

@@ -3,35 +3,26 @@ os: linux
 
 language: python
 python:
-  - "2.7"
   - "3.7"
 
 # install system dependencies here with apt-get.
 before_install:
   - sudo ./provision/debian.sh
-  - python -m pip install --upgrade pip
+  - python -m pip install --upgrade pip setuptools wheel
 
 # install python dependencies including this package in the travis
 # virtualenv
 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]
+  - ./provision/python.sh
+  - pip install .
 
 # 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
   - cd tests && pytest && cd -
 #  - pycodestyle textract/ bin/textract
-  - if [[ $TRAVIS_PYTHON_VERSION == 3.7 ]];
-        then cd docs && make html && cd -;
-        fi
+  - cd docs && make html && cd -;
 
 # commands to run after the tests successfully complete
 after_success:

Vagrantfile

@@ -27,8 +27,7 @@ Vagrant.configure("2") do |config|
     vb.customize ["modifyvm", :id, "--ioapic", "on"]
     vb.customize ["modifyvm", :id, "--cpus", "2"]
     vb.customize ["modifyvm", :id, "--memory", "2048"]
-    override_config.vm.box = "trusty64"
-    override_config.vm.box_url = "https://cloud-images.ubuntu.com/vagrant/trusty/current/trusty-server-cloudimg-amd64-vagrant-disk1.box"
+    override_config.vm.box = "ubuntu/focal64"
   end
 
   # steps for provisioning so that these provisioning steps are

docs/changelog.rst

@@ -10,6 +10,11 @@ latest changes in development for next release
 ----------------------------------------------
 
 .. THANKS FOR CONTRIBUTING; ADD YOUR UNRELEASED CHANGES HERE!
+1.7.0
+-------------------
+
+* Dropped python2 support
+
 1.6.5
 -------------------
 

docs/conf.py

@@ -58,7 +58,7 @@
 # built documents.
 #
 # The short X.Y version.
-release = version = "1.6.5"
+release = version = "1.7.0"
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

docs/index.rst

@@ -86,7 +86,7 @@ file types by either mentioning them on the `issue tracker
 
 * ``.wav`` via `SpeechRecognition`_ and `pocketsphinx`_
 
-* ``.xlsx`` via `xlrd <https://pypi.python.org/pypi/xlrd>`_
+* ``.xlsx`` via `openpyxl <https://pypi.python.org/pypi/openpyxl>`_
 
 * ``.xls`` via `xlrd <https://pypi.python.org/pypi/xlrd>`_
 

provision/python3.sh → provision/python.sh

@@ -12,5 +12,5 @@ fi
 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-dev
 pip install -r requirements/python-doc

provision/travis-mock.sh

@@ -6,7 +6,7 @@
 # if its a problem.
 # http://docs.travis-ci.com/user/languages/python/#Travis-CI-Uses-Isolated-virtualenvs
 sudo apt-get update -qq
-sudo apt-get install -y python-pip python-dev build-essential
+sudo apt-get install -y python3-pip python3-dev build-essential
 
 # install pep8 and nose for testing
 sudo pip install pep8 nose

requirements/debian

@@ -9,7 +9,7 @@ make
 
 # these packages are required by python-docx, which depends on lxml
 # and requires these things
-python-dev
+python3-dev
 libxml2-dev
 libxslt1-dev
 
@@ -48,3 +48,5 @@ swig
 # libxslt1-dev for compiling lxml.
 # https://github.com/deanmalmgren/textract/issues/19
 zlib1g-dev
+
+python-is-python3

requirements/python

@@ -1,13 +1,14 @@
 # This file contains all python dependencies that are required by the textract
 # package in order for it to properly work.
 
-argcomplete~=1.10.0
-beautifulsoup4~=4.8.0
-chardet==3.*
-docx2txt~=0.8
-extract-msg<=0.29.* #Last with python2 support
-pdfminer.six==20191110 #Last with python2 support
-python-pptx~=0.6.18
-six~=1.12.0
-SpeechRecognition~=3.8.1
-xlrd~=1.2.0
+argcomplete>=1.10.0
+beautifulsoup4>=4.8.0
+chardet>=3.0
+docx2txt>=0.8
+extract-msg>=0.29.0
+pdfminer.six>=20191110
+python-pptx>=0.6.18
+six>=1.12.0
+SpeechRecognition>=3.8.1
+xlrd>=1.2.0
+openpyxl>=2.0.0

requirements/python-doc

@@ -1,5 +1,7 @@
 # this only includes packages that are needed for documentation build.
 
+jinja2<3.1
 sphinx==2.1.2
 sphinx_rtd_theme==0.4.3
 sphinx-argparse==0.2.5
+pocketsphinx==0.1.15

setup.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 1.6.5
+current_version = 1.7.0
 commit = True
 tag = True
 

setup.py

@@ -42,7 +42,7 @@ def parse_requirements(requirements_filename):
 
 setup(
     name=textract.__name__,
-    version="1.6.5",
+    version="1.7.0",
     description="extract text from any document. no muss. no fuss.",
     long_description=long_description,
     url=github_url,

tests/Dockerfile

@@ -1,16 +1,15 @@
-FROM ubuntu:12.04
+FROM ubuntu:20.04
 MAINTAINER Shawn Milochik <[email protected]>
 ENV DEBIAN_FRONTEND noninteractive
-ENV REFRESHED_AT 2014-08-12b
+ENV REFRESHED_AT 2022-08-17
 RUN apt-get update
-RUN apt-get install python-pip -y
-ADD . /src
-WORKDIR /src
-RUN /bin/bash /src/provision/debian.sh
-RUN /bin/bash /src/provision/python.sh
+RUN apt-get install python3-pip -y
+ADD . /app
+WORKDIR /app
+RUN /bin/bash /app/provision/debian.sh
+RUN /bin/bash /app/provision/python.sh
 RUN adduser --disabled-password --gecos "" --home=/home/textract textract
-VOLUME ["/home/textract/src"]
 ENV PATH $PATH:/home/textract/src/bin
 ENV PYTHONPATH /home/textract/src
 USER textract
-ENTRYPOINT ["/home/textract/src/tests/run.py"]
+ENTRYPOINT ["/home/textract/src/tests/docker_entry.sh"]

tests/docker_entry.sh

@@ -3,4 +3,4 @@
 # This script gets called from within the
 # Docker container.
 
-./tests/run.py
+cd "$(dirname "$0")" && make && pytest && cd -

tests/pdf/raw_text-m=pdfminer.txt

@@ -1,59 +1,91 @@
 I	  love	  word	  documents.	  They	  are	  lovely.	  They	  make	  me	  so	  happy	  I	  could	  smile.	  And	  
 that’s	  why	  I	  wrote	  this	  package.	  
-
 
 Sample text is hard. That’s 
 where http://hipsum.co comes 
 in handy. 
 
-
-
 Semiotics church-key VHS, Truffaut cliche actually vegan. Cray Austin 
+
 pop-up disrupt letterpress, kitsch fixie Cosby sweater cliche craft beer 
+
 PBR&B. Gentrify cornhole Tonx McSweeney's, Shoreditch keffiyeh 
+
 ethnic Marfa 90's kogi American Apparel. Shabby chic distillery church-
+
 key locavore beard, food truck chillwave sartorial deep v flannel authentic 
+
 Tumblr narwhal kogi organic. Cred vegan jean shorts Banksy forage 
+
 Neutra dreamcatcher, hashtag Bushwick polaroid pork belly flannel 
+
 keytar Portland post-ironic. Cred hoodie vegan, food truck leggings 
+
 Austin pour-over banjo trust fund before they sold out cray Intelligentsia 
+
 plaid typewriter. Williamsburg XOXO plaid Carles Austin tofu. 
 
 Carles Tonx keffiyeh, leggings 90's lo-fi kogi viral semiotics Brooklyn 
+
 biodiesel tousled bespoke kitsch. Vinyl Tonx art party Thundercats retro, 
+
 viral asymmetrical artisan bicycle rights bitters master cleanse Kickstarter 
+
 YOLO. Seitan street art semiotics twee skateboard, PBR&B VHS hashtag 
+
 meh. Thundercats semiotics shabby chic forage single-origin coffee retro, 
+
 3 wolf moon iPhone mumblecore 90's trust fund Intelligentsia. Beard 
+
 gluten-free seitan, VHS sartorial pork belly gastropub meh whatever 
+
 authentic synth. Beard single-origin coffee irony fixie, before they sold 
 
+
+
 out Pitchfork kitsch readymade. Helvetica butcher wayfarers, lomo artisan 
+
 hashtag Brooklyn four loko fanny pack 90's mustache 8-bit. 
 
 Meh jean shorts selfies, crucifix selvage Helvetica Carles PBR Vice 
+
 Banksy roof party master cleanse ugh PBR&B. Lo-fi freegan salvia photo 
+
 booth, Wes Anderson skateboard Odd Future. Etsy art party Bushwick 
+
 keffiyeh. Pork belly 3 wolf moon butcher mustache. YOLO raw denim lo-
+
 fi, hoodie gentrify Schlitz 8-bit sriracha Shoreditch retro brunch. 
+
 Williamsburg farm-to-table beard, mlkshk Banksy fap kogi Etsy art party 
+
 squid semiotics. XOXO church-key Pitchfork mlkshk irony tote bag. 
 
 Farm-to-table brunch tattooed hoodie keytar, literally selvage authentic 
+
 trust fund deep v Thundercats Kickstarter narwhal locavore. Swag disrupt 
+
 chambray, leggings shabby chic gastropub YOLO plaid hoodie 
+
 Williamsburg Godard mixtape. Retro Godard keytar biodiesel, freegan 
+
 paleo Etsy you probably haven't heard of them Pitchfork Schlitz 
+
 readymade small batch cred. Pug trust fund paleo, 90's fixie typewriter 
+
 next level banjo. Banksy occupy authentic master cleanse Bushwick 
+
 fingerstache selfies, direct trade craft beer cliche +1 cray. Locavore four 
+
 loko biodiesel Neutra chia mlkshk. Fanny pack YOLO Portland, mlkshk 
+
 PBR&B single-origin coffee drinking vinegar 8-bit flannel gentrify 
+
 stumptown pop-up. 
+
 Oh. You need a little dummy text for your mockup? How quaint. 
 
 I bet you’re still using Bootstrap too… 
 
 
-
 

tests/run_docker_tests.sh

@@ -5,15 +5,10 @@
 cd $(dirname $0)/..
 base=$(pwd)
 
-image="textract/ubuntu12.04"
-
-cp tests/Dockerfile ./Dockerfile
+image="textract/ubuntu20.04"
 
 # Note: For speed, the image won't be automatically rebuilt. If the dependencies
 # change and the existing image is outdated, just delete it with:
 # docker rmi <image name>
-docker images | grep $image || docker build -t $image .
+docker images | grep $image || docker build -t $image -f tests/Dockerfile .
 docker run --rm -v $base:/home/textract/src $image
-
-rm ./Dockerfile
-