Fix issue1753: TextIOWrapper.write writes utf BOM for every string.

Patch by Erick Tryzelaar, with slight modifications by me.

diff --git a/Lib/io.py b/Lib/io.py
index 2a5348d172076caa4474a3dbe456ceea3ce436cc..e427fe6969ab535239deef17a53652f8779a7866 100644 (file)
--- a/Lib/io.py
+++ b/Lib/io.py
@@ -1182,6 +1182,7 @@ class TextIOWrapper(TextIOBase):
         self._readnl = newline
         self._writetranslate = newline != ''
         self._writenl = newline or os.linesep
+        self._encoder = None
         self._decoder = None
         self._pending = ""
         self._snapshot = None
@@ -1240,8 +1241,9 @@ class TextIOWrapper(TextIOBase):
         haslf = (self._writetranslate or self._line_buffering) and "\n" in s
         if haslf and self._writetranslate and self._writenl != "\n":
             s = s.replace("\n", self._writenl)
+        encoder = self._encoder or self._get_encoder()
         # XXX What if we were just reading?
-        b = s.encode(self._encoding, self._errors)
+        b = encoder.encode(s)
         self.buffer.write(b)
         if self._line_buffering and (haslf or "\r" in s):
             self.flush()
@@ -1250,11 +1252,13 @@ class TextIOWrapper(TextIOBase):
             self._decoder.reset()
         return length
 
+    def _get_encoder(self):
+        make_encoder = codecs.getincrementalencoder(self._encoding)
+        self._encoder = make_encoder(self._errors)
+        return self._encoder
+
     def _get_decoder(self):
         make_decoder = codecs.getincrementaldecoder(self._encoding)
-        if make_decoder is None:
-            raise IOError("Can't find an incremental decoder for encoding %s" %
-                          self._encoding)
         decoder = make_decoder(self._errors)
         if self._readuniversal:
             decoder = IncrementalNewlineDecoder(decoder, self._readtranslate)

diff --git a/Lib/test/test_io.py b/Lib/test/test_io.py
index 33b32e0a1bbac42704c2c3b52d9c1105c02246b6..4963416ffaaae6d5a4f8b9a156bcdb272a56d9e6 100644 (file)
--- a/Lib/test/test_io.py
+++ b/Lib/test/test_io.py
@@ -765,6 +765,24 @@ class TextIOWrapperTest(unittest.TestCase):
         f.readline()
         f.tell()
 
+    def testEncodedWrites(self):
+        data = "1234567890"
+        tests = ("utf-16",
+                 "utf-16-le",
+                 "utf-16-be",
+                 "utf-32",
+                 "utf-32-le",
+                 "utf-32-be")
+        for encoding in tests:
+            buf = io.BytesIO()
+            f = io.TextIOWrapper(buf, encoding=encoding)
+            # Check if the BOM is written only once (see issue1753).
+            f.write(data)
+            f.write(data)
+            f.seek(0)
+            self.assertEquals(f.read(), data * 2)
+            self.assertEquals(buf.getvalue(), (data * 2).encode(encoding))
+
     def timingTest(self):
         timer = time.time
         enc = "utf8"