Issue #2175: SAX parsers now support a character stream of InputSource object.

3 files changed, 16 insertions, 6 deletions

diff --git a/Lib/xml/sax/expatreader.py b/Lib/xml/sax/expatreader.py
index a227cdab572..65ac7e30434 100644
--- a/Lib/xml/sax/expatreader.py
+++ b/Lib/xml/sax/expatreader.py
@@ -219,9 +219,14 @@ class ExpatParser(xmlreader.IncrementalParser, xmlreader.Locator):
         self._parsing = 0
         # break cycle created by expat handlers pointing to our methods
         self._parser = None
-        bs = self._source.getByteStream()
-        if bs is not None:
-            bs.close()
+        try:
+            file = self._source.getCharacterStream()
+            if file is not None:
+                file.close()
+        finally:
+            file = self._source.getByteStream()
+            if file is not None:
+                file.close()
 
     def _reset_cont_handler(self):
         self._parser.ProcessingInstructionHandler = \
diff --git a/Lib/xml/sax/saxutils.py b/Lib/xml/sax/saxutils.py
index 1d3d0ecc5f9..a69c7f76217 100644
--- a/Lib/xml/sax/saxutils.py
+++ b/Lib/xml/sax/saxutils.py
@@ -345,11 +345,14 @@ def prepare_input_source(source, base=""):
     elif hasattr(source, "read"):
         f = source
         source = xmlreader.InputSource()
-        source.setByteStream(f)
+        if isinstance(f.read(0), str):
+            source.setCharacterStream(f)
+        else:
+            source.setByteStream(f)
         if hasattr(f, "name") and isinstance(f.name, str):
             source.setSystemId(f.name)
 
-    if source.getByteStream() is None:
+    if source.getCharacterStream() is None and source.getByteStream() is None:
         sysid = source.getSystemId()
         basehead = os.path.dirname(os.path.normpath(base))
         sysidfilename = os.path.join(basehead, sysid)
diff --git a/Lib/xml/sax/xmlreader.py b/Lib/xml/sax/xmlreader.py
index 7ef497f94fe..716f2284041 100644
--- a/Lib/xml/sax/xmlreader.py
+++ b/Lib/xml/sax/xmlreader.py
@@ -117,7 +117,9 @@ class IncrementalParser(XMLReader):
         source = saxutils.prepare_input_source(source)
 
         self.prepareParser(source)
-        file = source.getByteStream()
+        file = source.getCharacterStream()
+        if file is None:
+            file = source.getByteStream()
         buffer = file.read(self._bufsize)
         while buffer:
             self.feed(buffer)