Drops Python 2 support

REP-1030

In addition to some python 2 => 3 fixes, this change bumps the scikit-learn
version to latest. The previously pinned version of scikit-learn failed trying
to compile all necessary C modules under python 3.7+ due to included header files
that weren't compatible with C the API implemented in python 3.7+.

Simultaneously, with the restrictive compatibility supported by scikit-learn,
it seemed prudent to drop python 2 support altogether. Otherwise, we'd be stuck
with python 3.4 as the newest possible version we could support.

With this change, tests are currently passing under 3.9.2.

Lastly, imports the original training data. At some point, a new version
of the training data was committed to the repo but no classifier was
trained from it. Using a classifier trained from this new data resulted
in most of the tests failing.

.build/Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.9-slim-buster AS deps
+
+RUN apt-get update && \
+    apt-get install -y build-essential git curl python3-dev libatlas3-base libatlas-base-dev liblapack-dev libxml2 libxml2-dev libffi6 libffi-dev musl-dev libxslt-dev
+
+FROM deps AS testable
+ARG REPORT_PATH
+
+VOLUME ["/var/mailgun", "/etc/mailgun/ssl", ${REPORT_PATH}]
+
+ADD . /app
+WORKDIR /app
+COPY wheel/* /wheel/
+
+RUN mkdir -p ${REPORT_PATH}
+
+RUN python ./setup.py build bdist_wheel -d /wheel && \
+    pip install --no-deps /wheel/*
+
+ENTRYPOINT ["/bin/sh", "/app/run_tests.sh"]

.gitignore

@@ -54,3 +54,6 @@ _trial_temp
 
 # OSX
 .DS_Store
+
+# vim-backup
+*.bak

MANIFEST.in

@@ -5,3 +5,10 @@ include classifier
 include LICENSE
 include MANIFEST.in
 include README.rst
+include talon/signature/data/train.data
+include talon/signature/data/classifier
+include talon/signature/data/classifier_01.npy
+include talon/signature/data/classifier_02.npy
+include talon/signature/data/classifier_03.npy
+include talon/signature/data/classifier_04.npy
+include talon/signature/data/classifier_05.npy

requirements.txt

@@ -0,0 +1,11 @@
+chardet>=1.0.1
+cchardet>=0.3.5
+cssselect
+html5lib
+joblib
+lxml>=2.3.3
+numpy
+regex>=1
+scikit-learn==0.24.1 # pickled versions of classifier, else rebuild
+scipy
+six>=1.10.0

run_tests.sh

@@ -0,0 +1,4 @@
+#!/usr/bin/env bash
+set -ex
+REPORT_PATH="${REPORT_PATH:-./}"
+nosetests --with-xunit --with-coverage --cover-xml --cover-xml-file $REPORT_PATH/coverage.xml --xunit-file=$REPORT_PATH/nosetests.xml --cover-package=talon .

setup.py

@@ -19,12 +19,12 @@ class InstallCommand(install):
         if self.no_ml:
             dist = self.distribution
             dist.packages=find_packages(exclude=[
-                'tests',
-                'tests.*',
-                'talon.signature',
-                'talon.signature.*',
+                "tests",
+                "tests.*",
+                "talon.signature",
+                "talon.signature.*",
             ])
-            for not_required in ['numpy', 'scipy', 'scikit-learn==0.16.1']:
+            for not_required in ["numpy", "scipy", "scikit-learn==0.24.1"]:
                 dist.install_requires.remove(not_required)
 
 
@@ -48,12 +48,13 @@ setup(name='talon',
           "regex>=1",
           "numpy",
           "scipy",
-          "scikit-learn==0.16.1", # pickled versions of classifier, else rebuild
-          'chardet>=1.0.1',
-          'cchardet>=0.3.5',
-          'cssselect',
-          'six>=1.10.0',
-          'html5lib'
+          "scikit-learn==0.24.1", # pickled versions of classifier, else rebuild
+          "chardet>=1.0.1",
+          "cchardet>=0.3.5",
+          "cssselect",
+          "six>=1.10.0",
+          "html5lib",
+          "joblib",
           ],
       tests_require=[
           "mock",

talon/quotations.py

@@ -457,7 +457,7 @@ def _extract_from_html(msg_body):
 
     msg_body = msg_body.replace(b'\r\n', b'\n')
 
-    msg_body = re.sub(r"\<\?xml.+\?\>|\<\!DOCTYPE.+]\>", "", msg_body)
+    msg_body = re.sub(br"\<\?xml.+\?\>|\<\!DOCTYPE.+]\>", "", msg_body)
 
     html_tree = html_document_fromstring(msg_body)
 

talon/signature/data/__init__.py

@@ -0,0 +1 @@
+

talon/signature/learning/classifier.py

@@ -8,7 +8,7 @@ body belongs to the signature.
 from __future__ import absolute_import
 
 from numpy import genfromtxt
-from sklearn.externals import joblib
+import joblib
 from sklearn.svm import LinearSVC
 
 

test-requirements.txt

@@ -0,0 +1,3 @@
+coverage
+mock
+nose>=1.2.1

tests/text_quotations_test.py

@@ -826,10 +826,10 @@ The user experience was unparallelled. Please continue production. I'm sending p
 that this line is intact."""
 
     parsed = quotations.extract_from_plain(msg_body)
-    eq_(msg_body, parsed.decode('utf8'))
+    eq_(msg_body, parsed)
 
 
-def test_appointment():
+def test_appointment_2():
     msg_body = """Invitation for an interview:
 
 Date: Wednesday 3, October 2011 
@@ -838,4 +838,4 @@ Address: 130 Fox St
 
 Please bring in your ID."""
     parsed = quotations.extract_from_plain(msg_body)
-    eq_(msg_body, parsed.decode('utf8'))
+    eq_(msg_body, parsed)