Remove supoprt for non standard output streams that are not binary by removing the try-except check that writes a unicode character to the stream (#523)

Closes #191 

* Remove supoprt for non standard output streams that are not binary by removing the try-except check that writes a unicode character to the stream

* Add docstring

* Fix flake8

CHANGELOG.md

@@ -11,6 +11,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 ## Removed
 - Support for Python 3.4 and 3.5 ([#522](https://github.com/pdfminer/pdfminer.six/pull/522))
 - Unused dependency on `sortedcontainers` package ([#525](https://github.com/pdfminer/pdfminer.six/pull/525))
+- Support for non-standard output streams that are not binary ([#523](https://github.com/pdfminer/pdfminer.six/pull/523))
 
 ## [20201018]
 

pdfminer/converter.py

@@ -1,3 +1,4 @@
+import io
 import logging
 import re
 import sys
@@ -167,24 +168,22 @@ class PDFConverter(PDFLayoutAnalyzer):
                                    laparams=laparams)
         self.outfp = outfp
         self.codec = codec
-        if hasattr(self.outfp, 'mode'):
-            if 'b' in self.outfp.mode:
-                self.outfp_binary = True
-            else:
-                self.outfp_binary = False
-        else:
-            import io
-            if isinstance(self.outfp, io.BytesIO):
-                self.outfp_binary = True
-            elif isinstance(self.outfp, io.StringIO):
-                self.outfp_binary = False
-            else:
-                try:
-                    self.outfp.write("é")
-                    self.outfp_binary = False
-                except TypeError:
-                    self.outfp_binary = True
-        return
+        self.outfp_binary = self._is_binary_stream(self.outfp)
+
+    @staticmethod
+    def _is_binary_stream(outfp):
+        """Test if an stream is binary or not"""
+        if 'b' in getattr(outfp, 'mode', ''):
+            return True
+        elif hasattr(outfp, 'mode'):
+            # output stream has a mode, but it does not contain 'b'
+            return False
+        elif isinstance(outfp, io.BytesIO):
+            return True
+        elif isinstance(outfp, io.StringIO):
+            return False
+
+        return True
 
 
 class TextConverter(PDFConverter):

tests/test_converter.py

@@ -1,6 +1,9 @@
-from nose.tools import assert_equal
+import io
+from tempfile import TemporaryFile
 
-from pdfminer.converter import PDFLayoutAnalyzer
+from nose.tools import assert_equal, assert_false, assert_true
+
+from pdfminer.converter import PDFLayoutAnalyzer, PDFConverter
 from pdfminer.layout import LTContainer, LTRect, LTCurve
 from pdfminer.pdfinterp import PDFGraphicState
 
@@ -99,3 +102,22 @@ class TestPaintPath():
         analyzer = PDFLayoutAnalyzer(None)
         analyzer.set_ctm([1, 0, 0, 1, 0, 0])
         return analyzer
+
+
+class TestBinaryDetector():
+    def test_stringio(self):
+        assert_false(PDFConverter._is_binary_stream(io.StringIO()))
+
+    def test_bytesio(self):
+        assert_true(PDFConverter._is_binary_stream(io.BytesIO()))
+
+    def test_tmpfile(self):
+        with TemporaryFile(mode='w') as f:
+            assert_false(PDFConverter._is_binary_stream(f))
+
+    def test_binary_tmpfile(self):
+        with TemporaryFile(mode='wb') as f:
+            assert_true(PDFConverter._is_binary_stream(f))
+
+    def test_non_file_like_object_defaults_to_binary(self):
+        assert_true(PDFConverter._is_binary_stream(object()))