Fix compatibility with Jython

This patch was taken from
#369 (comment),
authored by Pekka Klärck <peke@iki.fi>.

In short, Jython doesn't support lone surrogates, so importing yaml (and
in particular, loading `reader.py`) caused a UnicodeDecodeError. This
patch works around this through a clever use of `eval` to defer
evaluation of the string containing the lone surrogates, only doing it
on non-Jython platforms.

This is only done in `lib/yaml/reader.py` and not `lib3/yaml/reader.py`
because Jython does not support Python 3.

With this patch, Jython's behavior with respect to Unicode code points
over 0xFFFF becomes as it was before
0716ae2. It still does not pass all the
unit tests on Jython (passes 1275, fails 3, errors on 1); all the
failing tests are related to unicode. Still, this is better than simply
crashing upon `import yaml`.

With this patch, all tests continue to pass on Python 2 / Python 3.

Author: anishathalye

lib/yaml/reader.py

@@ -137,9 +137,14 @@ def determine_encoding(self):
         self.update(1)
 
     if has_ucs4:
-        NON_PRINTABLE = re.compile(u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD\U00010000-\U0010ffff]')
+        NON_PRINTABLE = u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD\U00010000-\U0010ffff]'
+    elif sys.platform.startswith('java'):
+        # Jython doesn't support lone surrogates https://bugs.jython.org/issue2048 
+        NON_PRINTABLE = u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD]'
     else:
-        NON_PRINTABLE = re.compile(u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uFFFD]|(?:^|[^\uD800-\uDBFF])[\uDC00-\uDFFF]|[\uD800-\uDBFF](?:[^\uDC00-\uDFFF]|$)')
+        # Need to use eval here due to the above Jython issue
+        NON_PRINTABLE = eval(r"u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uFFFD]|(?:^|[^\uD800-\uDBFF])[\uDC00-\uDFFF]|[\uD800-\uDBFF](?:[^\uDC00-\uDFFF]|$)'")
+    NON_PRINTABLE = re.compile(NON_PRINTABLE)
     def check_printable(self, data):
         match = self.NON_PRINTABLE.search(data)
         if match: