Merge branch 'master' for 0.7.8 into develop

CHANGES.rst

@@ -1,6 +1,21 @@
 pywb 0.8.0 changelist
 ~~~~~~~~~~~~~~~~~~~~~
 
+pywb 0.7.8 changelist
+~~~~~~~~~~~~~~~~~~~~~
+
+* live rewrite fix: When forwarding ``X-Forwarded-Proto`` header, set scheme to actual url scheme to avoid possible redirect loops (#57)
+
+
+pywb 0.7.7 changelist
+~~~~~~~~~~~~~~~~~~~~~
+
+* client-side rewrite: improved rewriting of all style changes using mutation observers
+
+* rules: fix YT rewrite rule, add rule for wikimedia
+
+* cdx-indexer: minor cleanup, add support for custom writer for batched cdx (write_multi_cdx_index)
+
 
 pywb 0.7.6 changelist
 ~~~~~~~~~~~~~~~~~~~~~

pywb/rewrite/rewrite_live.py

@@ -75,6 +75,10 @@ class LiveRewriter(object):
             elif name == 'HTTP_REFERER':
                 continue
 
+            elif name == 'HTTP_X_FORWARDED_PROTO':
+                name = 'X-Forwarded-Proto'
+                value = splits.scheme
+
             elif name == 'HTTP_COOKIE':
                 name = 'Cookie'
                 value = self._req_cookie_rewrite(urlkey, value)
@@ -89,7 +93,7 @@ class LiveRewriter(object):
             elif name == 'REL_REFERER':
                 name = 'Referer'
             else:
-                continue
+                value = None
 
             if value:
                 headers[name] = value

pywb/rewrite/test/test_rewrite_live.py

@@ -26,6 +26,14 @@ def test_csrf_token_headers():
 
     assert req_headers == {'X-CSRFToken': 'foobar', 'Cookie': 'csrftoken=foobar'}
 
+def test_forwarded_scheme():
+    rewriter = LiveRewriter()
+    env = {'HTTP_X_FORWARDED_PROTO': 'https', 'Other': 'Value'}
+
+    req_headers = rewriter.translate_headers('http://example.com/', 'com,example)/', env)
+
+    assert req_headers == {'X-Forwarded-Proto': 'http'}
+
 def test_req_cookie_rewrite_1():
     rewriter = LiveRewriter()
     env = {'HTTP_COOKIE': 'A=B'}

pywb/rules.yaml

@@ -65,7 +65,7 @@ rules:
       fuzzy_lookup: '()'
 
 
-    # instagram rules
+    # wikimedia rules
     #=================================================================
     - url_prefix: 'org,wikimedia,meta)/'
 
@@ -144,7 +144,7 @@ rules:
         js_regexs:
             - match: 'window.location'
               replace: 'WB_wombat_location'
-  
+
     # youtube rules
     #=================================================================
 
@@ -213,7 +213,7 @@ rules:
             - match: 'ytplayer.load\(\);'
               replace: 'ytplayer.config.args.dash = "0"; ytplayer.config.args.dashmpd = ""; {0}'
 
-            - match: 'yt\.setConfig.*PLAYER_CONFIG.*args": {'
+            - match: 'yt\.setConfig.*PLAYER_CONFIG.*args":\s*{'
               replace: '{0} "dash": "0", dashmpd: "", '
 
         req_cookie_rewrite:

pywb/static/wombat.js

@@ -626,6 +626,36 @@ _WBWombat = (function() {
         window.Worker = undefined;
     }
 
+
+    //============================================
+    function init_mutation_obs() {
+        if (!window.MutationObserver) {
+            return;
+        }
+
+        var m = new MutationObserver(function(records, observer)
+        {
+            for (var i = 0; i < records.length; i++) {
+                var r = records[i];
+                if (r.type == "attributes" && r.attributeName == "style") {
+                    var style = r.target.style.cssText;
+                    if (style.indexOf("url(") > 0) {
+                        var new_style = rewrite_style(style);
+                        if (new_style != style) {
+                            r.target.style.cssText = new_style;
+                        }
+                    }
+                }
+            }
+        });
+
+        m.observe(document.documentElement, {childList: false,
+                                  attributes: true,
+                                  subtree: true,
+                                  //attributeOldValue: true,
+                                  attributeFilter: ["style"]});
+    }
+
     //============================================
     function rewrite_attr(elem, name, func) {
         if (!elem || !elem.getAttribute) {
@@ -988,6 +1018,9 @@ _WBWombat = (function() {
         init_ajax_rewrite();
         init_worker_override();
 
+        // Init mutation observer (for style only)
+        init_mutation_obs();
+
         // setAttribute
         init_setAttribute_override();
 

pywb/warc/cdxindexer.py

@@ -107,6 +107,19 @@ def cdx_filename(filename):
     return remove_ext(filename) + '.cdx'
 
 
+#=================================================================
+def get_cdx_writer_cls(options):
+    writer_cls = options.get('writer_cls')
+
+    if not writer_cls:
+        if options.get('sort'):
+            writer_cls = SortedCDXWriter
+        else:
+            writer_cls = CDXWriter
+
+    return writer_cls
+
+
 #=================================================================
 def write_multi_cdx_index(output, inputs, **options):
     # write one cdx per dir
@@ -117,7 +130,7 @@ def write_multi_cdx_index(output, inputs, **options):
 
             with open(outpath, 'wb') as outfile:
                 with open(fullpath, 'rb') as infile:
-                    write_cdx_index(outfile, infile, filename, **options)
+                    return write_cdx_index(outfile, infile, filename, **options)
 
     # write to one cdx file
     else:
@@ -126,10 +139,7 @@ def write_multi_cdx_index(output, inputs, **options):
         else:
             outfile = open(output, 'wb')
 
-        if options.get('sort'):
+        writer_cls = get_cdx_writer_cls(options)
-            writer_cls = SortedCDXWriter
-        else:
-            writer_cls = CDXWriter
 
         with writer_cls(outfile, options.get('cdx09')) as writer:
             for fullpath, filename in iter_file_or_dir(inputs):
@@ -139,20 +149,15 @@ def write_multi_cdx_index(output, inputs, **options):
                     for entry in entry_iter:
                         writer.write(entry, filename)
 
+        return writer
+
 
 #=================================================================
 def write_cdx_index(outfile, infile, filename, **options):
-    writer_cls = options.get('writer_cls')
-
     if type(filename) is unicode:
         filename = filename.encode(sys.getfilesystemencoding())
 
-    if writer_cls:
+    writer_cls = get_cdx_writer_cls(options)
-        pass
-    elif options.get('sort'):
-        writer_cls = SortedCDXWriter
-    else:
-        writer_cls = CDXWriter
 
     with writer_cls(outfile, options.get('cdx09')) as writer:
         entry_iter = create_index_iter(infile, **options)