AppPkg/Applications/Python/Python-2.7.10: Initial Checkin part 4/5.

[mirror_edk2.git] / AppPkg / Applications / Python / Python-2.7.10 / Lib / encodings / utf_8_sig.py

diff --git a/AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/utf_8_sig.py b/AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/utf_8_sig.py
new file mode 100644 (file)
index 0000000..8cafef7
--- /dev/null
+++ b/AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/utf_8_sig.py
@@ -0,0 +1,117 @@
+""" Python 'utf-8-sig' Codec\r
+This work similar to UTF-8 with the following changes:\r
+\r
+* On encoding/writing a UTF-8 encoded BOM will be prepended/written as the\r
+  first three bytes.\r
+\r
+* On decoding/reading if the first three bytes are a UTF-8 encoded BOM, these\r
+  bytes will be skipped.\r
+"""\r
+import codecs\r
+\r
+### Codec APIs\r
+\r
+def encode(input, errors='strict'):\r
+    return (codecs.BOM_UTF8 + codecs.utf_8_encode(input, errors)[0], len(input))\r
+\r
+def decode(input, errors='strict'):\r
+    prefix = 0\r
+    if input[:3] == codecs.BOM_UTF8:\r
+        input = input[3:]\r
+        prefix = 3\r
+    (output, consumed) = codecs.utf_8_decode(input, errors, True)\r
+    return (output, consumed+prefix)\r
+\r
+class IncrementalEncoder(codecs.IncrementalEncoder):\r
+    def __init__(self, errors='strict'):\r
+        codecs.IncrementalEncoder.__init__(self, errors)\r
+        self.first = 1\r
+\r
+    def encode(self, input, final=False):\r
+        if self.first:\r
+            self.first = 0\r
+            return codecs.BOM_UTF8 + codecs.utf_8_encode(input, self.errors)[0]\r
+        else:\r
+            return codecs.utf_8_encode(input, self.errors)[0]\r
+\r
+    def reset(self):\r
+        codecs.IncrementalEncoder.reset(self)\r
+        self.first = 1\r
+\r
+    def getstate(self):\r
+        return self.first\r
+\r
+    def setstate(self, state):\r
+        self.first = state\r
+\r
+class IncrementalDecoder(codecs.BufferedIncrementalDecoder):\r
+    def __init__(self, errors='strict'):\r
+        codecs.BufferedIncrementalDecoder.__init__(self, errors)\r
+        self.first = True\r
+\r
+    def _buffer_decode(self, input, errors, final):\r
+        if self.first:\r
+            if len(input) < 3:\r
+                if codecs.BOM_UTF8.startswith(input):\r
+                    # not enough data to decide if this really is a BOM\r
+                    # => try again on the next call\r
+                    return (u"", 0)\r
+                else:\r
+                    self.first = None\r
+            else:\r
+                self.first = None\r
+                if input[:3] == codecs.BOM_UTF8:\r
+                    (output, consumed) = codecs.utf_8_decode(input[3:], errors, final)\r
+                    return (output, consumed+3)\r
+        return codecs.utf_8_decode(input, errors, final)\r
+\r
+    def reset(self):\r
+        codecs.BufferedIncrementalDecoder.reset(self)\r
+        self.first = True\r
+\r
+class StreamWriter(codecs.StreamWriter):\r
+    def reset(self):\r
+        codecs.StreamWriter.reset(self)\r
+        try:\r
+            del self.encode\r
+        except AttributeError:\r
+            pass\r
+\r
+    def encode(self, input, errors='strict'):\r
+        self.encode = codecs.utf_8_encode\r
+        return encode(input, errors)\r
+\r
+class StreamReader(codecs.StreamReader):\r
+    def reset(self):\r
+        codecs.StreamReader.reset(self)\r
+        try:\r
+            del self.decode\r
+        except AttributeError:\r
+            pass\r
+\r
+    def decode(self, input, errors='strict'):\r
+        if len(input) < 3:\r
+            if codecs.BOM_UTF8.startswith(input):\r
+                # not enough data to decide if this is a BOM\r
+                # => try again on the next call\r
+                return (u"", 0)\r
+        elif input[:3] == codecs.BOM_UTF8:\r
+            self.decode = codecs.utf_8_decode\r
+            (output, consumed) = codecs.utf_8_decode(input[3:],errors)\r
+            return (output, consumed+3)\r
+        # (else) no BOM present\r
+        self.decode = codecs.utf_8_decode\r
+        return codecs.utf_8_decode(input, errors)\r
+\r
+### encodings module API\r
+\r
+def getregentry():\r
+    return codecs.CodecInfo(\r
+        name='utf-8-sig',\r
+        encode=encode,\r
+        decode=decode,\r
+        incrementalencoder=IncrementalEncoder,\r
+        incrementaldecoder=IncrementalDecoder,\r
+        streamreader=StreamReader,\r
+        streamwriter=StreamWriter,\r
+    )\r