refactor repository and unit tests

.gitignore

@@ -0,0 +1,3 @@
+
+# ignore files created by `pip install -e .`
+*.egg-info

Makefile

@@ -1,10 +1,7 @@
 
-test: pdftitle.py test.sh test_max2.sh test_eliot.sh testc.sh
-	pylint pdftitle.py
-	bash test.sh
-	bash test_max2.sh
-	bash test_eliot.sh
-	bash testc.sh
+test: tests/__init__.py
+	pylint src/pdftitle/pdftitle.py
+	python -m unittest discover
 
 upload: pdftitle.py setup.py
 	rm -rf dist

setup.py

@@ -2,37 +2,48 @@
 from codecs import open
 from os import path
 
-here = path.abspath(path.dirname(__file__))
 
-with open(path.join(here, 'README.md'), encoding='utf-8') as f:
+packagename = "pdftitle"
+
+# consider the path of `setup.py` as root directory:
+PROJECTROOT = path.dirname(__file__)
+release_path = path.join(PROJECTROOT, "src", packagename, "release.py")
+with open(release_path, encoding="utf8") as release_file:
+    __version__ = release_file.read().split('__version__ = "', 1)[1].split('"', 1)[0]
+
+
+with open("requirements.txt") as requirements_file:
+    requirements = requirements_file.read()
+
+
+with open(path.join(PROJECTROOT, "README.md"), encoding="utf-8") as f:
     long_description = f.read()
 
 setup(
-    name='pdftitle',
-    version='0.11',
-    description='pdftitle is a small utility to extract the title from a PDF file.',
+    name=packagename,
+    version=__version__,
+    description="pdftitle is a small utility to extract the title from a PDF file.",
     long_description=long_description,
-    long_description_content_type='text/markdown',
-    url='https://github.com/metebalci/pdftitle',
-    author='Mete Balci',
-    author_email='[email protected]',
-    license='GPLv3',
+    long_description_content_type="text/markdown",
+    url="https://github.com/metebalci/pdftitle",
+    author="Mete Balci",
+    author_email="[email protected]",
+    license="GPLv3",
     classifiers=[
-        'Development Status :: 3 - Alpha',
-	'Environment :: Console',
-	'Intended Audience :: Science/Research',
-	'License :: OSI Approved :: GNU General Public License v3 (GPLv3)',
-	'Topic :: Utilities',
-        'Programming Language :: Python :: 3.6',
+        "Development Status :: 3 - Alpha",
+        "Environment :: Console",
+        "Intended Audience :: Science/Research",
+        "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
+        "Topic :: Utilities",
+        "Programming Language :: Python :: 3.6",
     ],
-
-    keywords='pdf text extract',
-    py_modules=['pdftitle'],
-    install_requires=['pdfminer.six>=20201018'],
-
+    keywords="pdf text extract",
+    packages=find_packages("src"),
+    package_dir={"": "src"},
+    install_requires=requirements,
     entry_points={
-        'console_scripts': [
-            'pdftitle=pdftitle:run',
+        "console_scripts": [
+            "pdftitle=pdftitle:run",
         ],
     },
 )

src/pdftitle/__init__.py

@@ -0,0 +1,2 @@
+# this allows `import pdftitle` instead of `import pdftitle.pdftitle`
+from .pdftitle import *

src/pdftitle/release.py

@@ -0,0 +1 @@
+__version__ = "0.11.0"

tests/test_cli.py

@@ -0,0 +1,103 @@
+import unittest
+import os
+import subprocess
+from subprocess import PIPE
+import sys
+
+
+def command_with_output(cmd):
+
+    if isinstance(cmd, str):
+        cmd = cmd.split(" ")  # note this breaks for spaces inside args
+
+    assert isinstance(cmd, (list, tuple))
+
+
+    if sys.version_info >= (3, 7):
+        res = subprocess.run(cmd, capture_output=True)
+    else:
+        # this is old and might be dropped with support for python3.6
+        res = subprocess.run(cmd, stdout=PIPE, stderr=PIPE)
+
+    res.stdout = res.stdout.decode("utf8")
+    res.stderr = res.stderr.decode("utf8")
+    return res
+
+
+class TestCore(unittest.TestCase):
+    def setUp(self):
+
+        self.orig_path = os.path.abspath(os.curdir)
+        os.chdir(os.path.abspath(os.path.dirname(__file__)))
+
+    def tearDown(self):
+        os.chdir(self.orig_path)
+
+    def test_option_c(self):
+
+        fpath = "data/knuth65.pdf"
+
+        res = command_with_output("cp {} test.pdf".format(fpath))
+        self.assertEqual(res.returncode, 0)
+
+        res = command_with_output("pdftitle -p test.pdf -c")
+        self.assertEqual(res.returncode, 0)
+
+        title = res.stdout.strip()  # remove trailing newline
+        self.assertEqual(title, "on_the_translation_of_languages_from_left_to_right.pdf")
+        self.assertFalse(os.path.isfile("test.pdf"))
+        self.assertTrue(os.path.isfile("on_the_translation_of_languages_from_left_to_right.pdf"))
+
+        # remove the newly created
+
+        res = command_with_output("rm {}".format(title))
+        self.assertEqual(res.returncode, 0)
+
+    def test_knuth65(self):
+
+        fpath = "data/knuth65.pdf"
+
+        res = command_with_output("pdftitle -p {}".format(fpath))
+        self.assertEqual(res.returncode, 0)
+
+        title = res.stdout.strip()  # remove trailing newli
+        self.assertEqual(title, "On the Translation of Languages from Left to Right")
+
+    def test_max2(self):
+
+        fpath = "data/paran2010.pdf"
+
+        res = command_with_output("pdftitle -p {} -a max2 -t".format(fpath))
+        self.assertEqual(res.returncode, 0)
+
+        title = res.stdout.strip()  # remove trailing newli
+        self.assertEqual(
+            title,
+            "Settlement Remains From The Bronze And Iron Ages At Horbat Menorim (El-Manara), Lower Galilee",
+        )
+
+    def test_eliot(self):
+
+        fpath = "data/woo2019.pdf"
+
+        # here we must pass the arguments as list because they contain spaces
+        res = command_with_output(
+            [
+                "pdftitle",
+                "-a",
+                "eliot",
+                "--eliot-tfs",
+                "1",
+                "-p",
+                fpath,
+                "--replace-missing-char",
+                " ",
+            ]
+        )
+        self.assertEqual(res.returncode, 0)
+
+        title = res.stdout.strip()  # remove trailing newli
+        self.assertEqual(
+            title,
+            "Lactobacillus HY2782 and Bifidobacterium HY8002 Decrease Airway Hyperresponsiveness Induced by Chronic PM2.5 Inhalation in Mice",
+        )