From f03657e5c48152d4a86a68c680131d5203c8e804 Mon Sep 17 00:00:00 2001
From: estshorter <1430311+estshorter@users.noreply.github.com>
Date: Fri, 18 Sep 2020 04:29:00 +0900
Subject: [PATCH] Allow a pathlib.PurePath object as a input to open_filename
 (#492)

* open_filename accepts a pathlib.PurePath object

* Add test for open_filename with pathlib

* Fix a wrong function name

* Cast a pathlib object to string for py3.4/3.5

* Add link to the PR

* Raise an exception when open_filename gets an unsupported type

* Add tests for open_filename

* Update CHANGELOG.md

* Documentation

Co-authored-by: Pieter Marsman <pietermarsman@gmail.com>
---
 CHANGELOG.md        |  3 +++
 pdfminer/utils.py   | 11 +++++++++--
 tests/test_utils.py | 27 +++++++++++++++++++++++++--
 3 files changed, 37 insertions(+), 4 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index dc0df88..b2386d7 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -5,6 +5,9 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 ## [Unreleased]
 
+### Added
+- Support for `pathlib.PurePath` in `open_filename` ([#491](https://github.com/pdfminer/pdfminer.six/issues/491))
+
 ### Fixed
 - Pass caching parameter to PDFResourceManager in `high_level` functions ([#475](https://github.com/pdfminer/pdfminer.six/pull/475))
 
diff --git a/pdfminer/utils.py b/pdfminer/utils.py
index 8531f79..0c67ff1 100644
--- a/pdfminer/utils.py
+++ b/pdfminer/utils.py
@@ -1,6 +1,8 @@
 """
 Miscellaneous Routines.
 """
+import io
+import pathlib
 import struct
 from html import escape
 
@@ -13,16 +15,21 @@ INF = (1 << 31) - 1
 
 class open_filename(object):
     """
-    Context manager that allows opening a filename and closes it on exit,
+    Context manager that allows opening a filename
+    (str or pathlib.PurePath type is supported) and closes it on exit,
     (just like `open`), but does nothing for file-like objects.
     """
     def __init__(self, filename, *args, **kwargs):
+        if isinstance(filename, pathlib.PurePath):
+            filename = str(filename)
         if isinstance(filename, str):
             self.file_handler = open(filename, *args, **kwargs)
             self.closing = True
-        else:
+        elif isinstance(filename, io.IOBase):
             self.file_handler = filename
             self.closing = False
+        else:
+            raise TypeError('Unsupported input type: %s' % type(filename))
 
     def __enter__(self):
         return self.file_handler
diff --git a/tests/test_utils.py b/tests/test_utils.py
index b0c7bac..dca99a6 100644
--- a/tests/test_utils.py
+++ b/tests/test_utils.py
@@ -1,7 +1,30 @@
-from nose.tools import assert_equal
+from nose.tools import assert_equal, assert_raises
+import pathlib
 
+from helpers import absolute_sample_path
 from pdfminer.layout import LTComponent
-from pdfminer.utils import Plane, shorten_str
+from pdfminer.utils import open_filename, Plane, shorten_str
+
+
+class TestOpenFilename:
+    def test_string_input(self):
+        filename = absolute_sample_path("simple1.pdf")
+        opened = open_filename(filename)
+        assert_equal(opened.closing, True)
+
+    def test_pathlib_input(self):
+        filename = pathlib.Path(absolute_sample_path("simple1.pdf"))
+        opened = open_filename(filename)
+        assert_equal(opened.closing, True)
+
+    def test_file_input(self):
+        filename = absolute_sample_path("simple1.pdf")
+        with open(filename, "rb") as in_file:
+            opened = open_filename(in_file)
+            assert_equal(opened.file_handler, in_file)
+
+    def test_unsupported_input(self):
+        assert_raises(TypeError, open_filename, 0)
 
 
 class TestPlane: