Fix #290

Fixes include - correcting code to deal with the difference in unicode strings on Python 2.7 vs Python 3.4
Build the abstract when doing the indexing pass so that any references in it will be included both times through
Add the start of a unicode test file.
 - Legacy-Id: 2013

cli/tests/input/unicode.xml

@@ -0,0 +1,49 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<rfc category="info" docName="draft-sample-input-00"
+     ipr="trust200902" submissionType="IETF">
+  <front>
+    <title abbrev="Abbreviated Title">Put Your Internet Draft Title</title>
+
+    <author fullname="John Doe" initials="J." role="editor"
+            surname="Doe">
+      <organization abbrev="Company">Company</organization>
+
+       <address>
+        <postal>
+          <street></street>
+          <city>Springfield</city>
+          <region>IL</region>
+          <country>US</country>
+        </postal>
+
+        <email>jdoe@example.com</email>
+      </address>
+    </author>
+
+    <date month="December" year="2010" day="10"/>
+
+    <abstract>
+      <t>Insert an abstract: MANDATORY. This template is for creating an
+      Internet-Draft.  With some out of scope characters
+      in Chinese, by Xing Xing, 这里是中文译本
+      </t>
+    </abstract>
+  </front>
+
+  <middle>
+    <section title="Some unicode strings">
+      <t>
+        Text body needs to deal with funny characters
+      </t>
+      <t>
+        Pure out of scope 这里是中文译本
+      </t>
+      <t>
+        Some re-mapped characters are ¢ or ©
+      </t>
+      <t>
+        More re-mapped characters are ˜ and €  and &#94;
+      </t>
+    </section>
+  </middle>
+</rfc>

cli/xml2rfc/utils.py

@@ -307,7 +307,7 @@ def _replace_unicode_characters(str):
         if match.group(1) in _unicode_replacements:
             str = re.sub(match.group(1), _unicode_replacements[match.group(1)], str)
         else:
-            entity = match.group(1).encode('ascii', 'xmlcharrefreplace')
+            entity = match.group(1).encode('ascii', 'xmlcharrefreplace').decode('ascii')
             str = re.sub(match.group(1), entity, str)
             xml2rfc.log.warn('Illegal character replaced in string: ' + entity)
 

cli/xml2rfc/writers/base.py

@@ -1022,6 +1022,13 @@ def _build_index(self):
         self.eref_count = 0
         self.pis = self.xmlrfc.getpis()
 
+        # Abstract
+        abstract = self.r.find('front/abstract')
+        if abstract is not None:
+            self.write_heading('Abstract', autoAnchor='rfc.abstract')
+            for t in abstract.findall('t'):
+                self.write_t_rec(t)
+
         # Middle sections
         middle = self.r.find('middle')
         if middle is not None: