Bug: _is_binary_stream should recognize TextIOWrapper as non-binary, escaped \r\n should be removed

CHANGELOG.md

@@ -20,6 +20,8 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 - Fix `.paint_path` logic for handling single line segments and extracting point-on-curve positions of Beziér path commands ([#530](https://github.com/pdfminer/pdfminer.six/pull/530))
 - Raising `UnboundLocalError` when a bad `--output-type`  is used ([#610](https://github.com/pdfminer/pdfminer.six/pull/610))
 - `TypeError` when using `TagExtractor` with non-string or non-bytes tag values ([#610](https://github.com/pdfminer/pdfminer.six/pull/610))
+- Using `io.TextIOBase` as the file to write to ([#616](https://github.com/pdfminer/pdfminer.six/pull/616))
+- Parsing \r\n after the escape character in a literal string ([#616](https://github.com/pdfminer/pdfminer.six/pull/616))
 
 ## Removed
 - Support for Python 3.4 and 3.5 ([#522](https://github.com/pdfminer/pdfminer.six/pull/522))

pdfminer/converter.py

@@ -181,6 +181,8 @@ def _is_binary_stream(outfp):
             return True
         elif isinstance(outfp, io.StringIO):
             return False
+        elif isinstance(outfp, io.TextIOBase):
+            return False
 
         return True
 

pdfminer/psparser.py

@@ -444,16 +444,29 @@ def _parse_string(self, s, i):
         return j+1
 
     def _parse_string_1(self, s, i):
+        """Parse literal strings
+
+        PDF Reference 3.2.3
+        """
         c = s[i:i+1]
         if OCT_STRING.match(c) and len(self.oct) < 3:
             self.oct += c
             return i+1
-        if self.oct:
+
+        elif self.oct:
             self._curtoken += bytes((int(self.oct, 8),))
             self._parse1 = self._parse_string
             return i
-        if c in ESC_STRING:
+
+        elif c in ESC_STRING:
             self._curtoken += bytes((ESC_STRING[c],))
+
+        elif c == b'\r' and len(s) > i+1 and s[i+1:i+2] == b'\n':
+            # If current and next character is \r\n skip both because enters
+            # after a \ are ignored
+            i += 1
+
+        # default action
         self._parse1 = self._parse_string
         return i+1
 

tests/test_converter.py

@@ -207,3 +207,6 @@ def test_binary_tmpfile(self):
 
     def test_non_file_like_object_defaults_to_binary(self):
         assert_true(PDFConverter._is_binary_stream(object()))
+
+    def test_textiowrapper(self):
+        assert_false(PDFConverter._is_binary_stream(io.TextIOBase()))