Apply SF patch #1775604: This adds three new codecs (utf-32, utf-32-le and

ut-32-be). On narrow builds the codecs combine surrogate pairs in the unicode
object into one codepoint on encoding and create surrogate pairs for
codepoints outside the BMP on decoding. Lone surrogates are passed through
unchanged in all cases.

Backport to the trunk will follow.

1 files changed, 37 insertions, 0 deletions

diff --git a/Lib/encodings/utf_32_be.py b/Lib/encodings/utf_32_be.py
new file mode 100644
index 0000000000..fe272b5faf
--- /dev/null
+++ b/Lib/encodings/utf_32_be.py
@@ -0,0 +1,37 @@
+"""
+Python 'utf-32-be' Codec
+"""
+import codecs
+
+### Codec APIs
+
+encode = codecs.utf_32_be_encode
+
+def decode(input, errors='strict'):
+    return codecs.utf_32_be_decode(input, errors, True)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+    def encode(self, input, final=False):
+        return codecs.utf_32_be_encode(input, self.errors)[0]
+
+class IncrementalDecoder(codecs.BufferedIncrementalDecoder):
+    _buffer_decode = codecs.utf_32_be_decode
+
+class StreamWriter(codecs.StreamWriter):
+    encode = codecs.utf_32_be_encode
+
+class StreamReader(codecs.StreamReader):
+    decode = codecs.utf_32_be_decode
+
+### encodings module API
+
+def getregentry():
+    return codecs.CodecInfo(
+        name='utf-32-be',
+        encode=encode,
+        decode=decode,
+        incrementalencoder=IncrementalEncoder,
+        incrementaldecoder=IncrementalDecoder,
+        streamreader=StreamReader,
+        streamwriter=StreamWriter,
+    )