refactor: cleanup HTMLRewrtier/LXMLHTMLRewriter close path,

single close in base class delegeating to _internal_close()
Also, HTMLRewriter auto-terminates <script> and <style> tags
for consistency with lxml

pywb/rewrite/html_rewriter.py

@@ -74,8 +74,6 @@ class HTMLRewriterMixin(object):
 
         self.url_rewriter = url_rewriter
         self._wb_parse_context = None
-        #self.out = outstream if outstream else self.AccumBuff()
-        self.out = self.AccumBuff()
 
         self.js_rewriter = js_rewriter_class(url_rewriter)
         self.css_rewriter = css_rewriter_class(url_rewriter)
@@ -218,17 +216,32 @@ class HTMLRewriterMixin(object):
         self.out.write(data)
 
     def rewrite(self, string):
-        if not self.out:
+        self.out = self.AccumBuff()
-            self.out = self.AccumBuff()
 
         self.feed(string)
 
         result = self.out.getvalue()
+
         # Clear buffer to create new one for next rewrite()
         self.out = None
 
         return result
 
+    def close(self):
+        self.out = self.AccumBuff()
+
+        self._internal_close()
+
+        result = self.out.getvalue()
+
+        # Clear buffer to create new one for next rewrite()
+        self.out = None
+
+        return result
+
+    def _internal_close(self):
+        pass
+
 
 #=================================================================
 class HTMLRewriter(HTMLRewriterMixin, HTMLParser):
@@ -243,30 +256,23 @@ class HTMLRewriter(HTMLRewriterMixin, HTMLParser):
                                            js_rewriter_class,
                                            css_rewriter_class)
 
-    # HTMLParser overrides below
     def feed(self, string):
         try:
             HTMLParser.feed(self, string)
         except HTMLParseError:
             self.out.write(string)
 
-    def close(self):
+    def _internal_close(self):
         if (self._wb_parse_context):
             end_tag = '</' + self._wb_parse_context + '>'
-            result = self.rewrite(end_tag)
+            self.feed(end_tag)
-            if result.endswith(end_tag):
-                result = result[:-len(end_tag)]
             self._wb_parse_context = None
-        else:
-            result = ''
 
         try:
             HTMLParser.close(self)
         except HTMLParseError:
             pass
 
-        return result
-
     # called to unescape attrs -- do not unescape!
     def unescape(self, s):
         return s

pywb/rewrite/lxml_html_rewriter.py

@@ -36,19 +36,9 @@ class LXMLHTMLRewriter(HTMLRewriterMixin):
         #string = string.replace(u'</html>', u'')
         self.parser.feed(string)
 
-    def close(self):
+    def _internal_close(self):
-        if not self.out:
-            self.out = self.AccumBuff()
-
-        self.is_closing = True
         self.parser.close()
 
-        result = self.out.getvalue()
-        # Clear buffer to create new one for next rewrite()
-        self.out = None
-
-        return result
-
 
 #=================================================================
 class RewriterTarget(object):

pywb/rewrite/test/test_html_rewriter.py

@@ -53,9 +53,9 @@ ur"""
 >>> parse('<script>window.location = "http://example.com/a/b/c.html"</script>')
 <script>window.WB_wombat_location = "/web/20131226101010/http://example.com/a/b/c.html"</script>
 
-# Unterminated script tag, handle but don't auto-terminate
+# Unterminated script tag, handle and auto-terminate
 >>> parse('<script>window.location = "http://example.com/a/b/c.html"</sc>')
-<script>window.WB_wombat_location = "/web/20131226101010/http://example.com/a/b/c.html"</sc>
+<script>window.WB_wombat_location = "/web/20131226101010/http://example.com/a/b/c.html"</sc></script>
 
 >>> parse('<script>/*<![CDATA[*/window.location = "http://example.com/a/b/c.html;/*]]>*/"</script>')
 <script>/*<![CDATA[*/window.WB_wombat_location = "/web/20131226101010/http://example.com/a/b/c.html;/*]]>*/"</script>
@@ -66,9 +66,9 @@ ur"""
 >>> parse('<style>@import "styles.css" .a { font-face: url(\'myfont.ttf\') }</style>')
 <style>@import "/web/20131226101010/http://example.com/some/path/styles.css" .a { font-face: url('/web/20131226101010/http://example.com/some/path/myfont.ttf') }</style>
 
-# Unterminated style tag, handle but don't auto-terminate
+# Unterminated style tag, handle and auto-terminate
 >>> parse('<style>@import url(styles.css)')
-<style>@import url(/web/20131226101010/http://example.com/some/path/styles.css)
+<style>@import url(/web/20131226101010/http://example.com/some/path/styles.css)</style>
 
 # Head Insertion
 >>> parse('<html><head><script src="other.js"></script></head><body>Test</body></html>', head_insert = '<script src="cool.js"></script>')