Merge branch 'develop' into https-proxy for 'bn_' modifier support

pywb/rewrite/rewrite_content.py

@@ -1,6 +1,8 @@
 #import chardet
 import pkgutil
 import yaml
+import re
+
 from chardet.universaldetector import UniversalDetector
 from io import BytesIO
 
@@ -52,11 +54,12 @@ class RewriteContent:
 
         return (rewritten_headers, stream)
 
-    def rewrite_content(self, urlrewriter, headers, stream,
+    def rewrite_content(self, wb_url, urlrewriter, headers, stream,
                         head_insert_func=None, urlkey='',
-                        sanitize_only=False, cdx=None, mod=None):
+                        cdx=None):
 
-        if sanitize_only:
+        if (wb_url.is_identity or
+            (not head_insert_func and wb_url.is_banner_only)):
             status_headers, stream = self.sanitize_content(headers, stream)
             return (status_headers, self.stream_to_gen(stream), False)
 
@@ -78,6 +81,8 @@ class RewriteContent:
 
         # see known js/css modifier specified, the context should run
         # default text_type
+        mod = wb_url.mod
+
         if mod == 'js_':
             text_type = 'js'
         elif mod == 'cs_':
@@ -118,6 +123,10 @@ class RewriteContent:
             if head_insert_func:
                 head_insert_str = head_insert_func(rule, cdx)
 
+            if wb_url.is_banner_only:
+                gen = self._head_insert_only_gen(head_insert_str, stream)
+                return (status_headers, gen, False)
+
             rewriter = rewriter_class(urlrewriter,
                                       js_rewriter_class=rule.rewriters['js'],
                                       css_rewriter_class=rule.rewriters['css'],
@@ -125,7 +134,10 @@ class RewriteContent:
                                       defmod=self.defmod)
 
         else:
-        # apply one of (js, css, xml) rewriters
+            if wb_url.is_banner_only:
+                return (status_headers, self.stream_to_gen(stream), False)
+
+            # apply one of (js, css, xml) rewriters
             rewriter = rewriter_class(urlrewriter)
 
         # Create rewriting generator
@@ -134,6 +146,32 @@ class RewriteContent:
 
         return (status_headers, gen, True)
 
+    HEAD_REGEX = re.compile(r'<\s*head\b[^>]*[>]+', re.I)
+
+    def _head_insert_only_gen(self, insert_str, stream):
+        max_len = 1024
+        buff = ''
+        while max_len > 0:
+            curr = stream.read(max_len)
+            if not curr:
+                break
+
+            max_len -= len(buff)
+            buff += curr
+
+        matcher = self.HEAD_REGEX.search(buff)
+
+        if matcher:
+            yield buff[:matcher.end()] + insert_str
+            yield buff[matcher.end():]
+        else:
+            yield insert_str
+            yield buff
+
+        for buff in self.stream_to_gen(stream):
+            yield buff
+
+
     # Create rewrite stream,  may even be chunked by front-end
     def _rewriting_stream_gen(self, rewriter, encoding,
                               stream, first_buff=None):

pywb/rewrite/rewrite_live.py

@@ -14,8 +14,9 @@ from pywb.utils.timeutils import datetime_to_timestamp
 from pywb.utils.statusandheaders import StatusAndHeaders
 from pywb.utils.canonicalize import canonicalize
 
-from pywb.rewrite.url_rewriter import UrlRewriter
+from url_rewriter import UrlRewriter
-from pywb.rewrite.rewrite_content import RewriteContent
+from wburl import WbUrl
+from rewrite_content import RewriteContent
 
 
 #=================================================================
@@ -114,15 +115,20 @@ class LiveRewriter(object):
 
         return (status_headers, stream)
 
-    def fetch_request(self, url, urlrewriter,
+    def fetch_request(self, wb_url, urlrewriter,
                       head_insert_func=None,
                       urlkey=None,
                       env=None,
                       req_headers={},
                       timestamp=None,
                       follow_redirects=False,
-                      proxies=None,
+                      proxies=None):
-                      mod=None):
+
+        if isinstance(wb_url, str):
+            url = wb_url
+            wb_url = WbUrl(url)
+        else:
+            url = wb_url.url
 
         ts_err = url.split('///')
 
@@ -155,13 +161,13 @@ class LiveRewriter(object):
               }
 
         result = (self.rewriter.
-                  rewrite_content(urlrewriter,
+                  rewrite_content(wb_url,
+                                  urlrewriter,
                                   status_headers,
                                   stream,
                                   head_insert_func=head_insert_func,
                                   urlkey=urlkey,
-                                  cdx=cdx,
+                                  cdx=cdx))
-                                  mod=mod))
 
         return result
 
@@ -174,41 +180,3 @@ class LiveRewriter(object):
         buff = ''.join(gen)
 
         return (status_headers, buff)
-
-
-#=================================================================
-def main():  # pragma: no cover
-    import sys
-
-    if len(sys.argv) < 2:
-        msg = 'Usage: {0} url-to-fetch [wb-url-target] [extra-prefix]'
-        print msg.format(sys.argv[0])
-        return 1
-    else:
-        url = sys.argv[1]
-
-    if len(sys.argv) >= 3:
-        wburl_str = sys.argv[2]
-        if wburl_str.startswith('/'):
-            wburl_str = wburl_str[1:]
-
-        prefix, wburl_str = wburl_str.split('/', 1)
-        prefix = '/' + prefix + '/'
-    else:
-        wburl_str = (datetime_to_timestamp(datetime.datetime.now()) +
-                     '/http://example.com/path/sample.html')
-        prefix = '/pywb_rewrite/'
-
-    urlrewriter = UrlRewriter(wburl_str, prefix)
-
-    liverewriter = LiveRewriter()
-
-    status_headers, buff = liverewriter.get_rewritten(url, urlrewriter)
-
-    sys.stdout.write(buff)
-    return 0
-
-
-#=================================================================
-if __name__ == "__main__":
-    exit(main())

pywb/rewrite/wburl.py

@@ -196,8 +196,11 @@ class WbUrl(BaseWbUrl):
     @property
     def is_embed(self):
         return (self.mod and
-                self.mod != 'id_' and
+                self.mod not in ('id_', 'mp_', 'bn_'))
-                self.mod != 'mp_')
+
+    @property
+    def is_banner_only(self):
+        return (self.mod == 'bn_')
 
     @property
     def is_identity(self):

pywb/ui/head_insert.html

@@ -1,5 +1,5 @@
 <!-- WB Insert -->
-{% if rule.js_rewrite_location %}
+{% if rule.js_rewrite_location and include_wombat %}
 <script src='{{ wbrequest.host_prefix }}/{{ static_path }}/wombat.js'> </script>
 <script>
   {% set urlsplit = cdx['original'] | urlsplit %}
@@ -16,9 +16,10 @@
   wbinfo.capture_str = "{{ cdx.timestamp | format_ts }}";
   wbinfo.prefix = "{{ wbrequest.wb_prefix }}";
   wbinfo.is_embed = {{"true" if wbrequest.wb_url.is_embed else "false"}};
-  wbinfo.is_frame_mp = {{"true" if wbrequest.wb_url.mod == 'mp_' else "false"}}
+  wbinfo.is_frame_mp = {{"true" if wbrequest.wb_url.mod == 'mp_' else "false"}};
   wbinfo.canon_url = "{{ canon_url }}";
   wbinfo.is_live = {{ "true" if cdx.is_live else "false" }};
+  wbinfo.is_proxy_mode = {{ "true" if wbrequest.options.is_proxy else "false" }};
 </script>
 <script src='{{ wbrequest.host_prefix }}/{{ static_path }}/wb.js'> </script>
 <link rel='stylesheet' href='{{ wbrequest.host_prefix }}/{{ static_path }}/wb.css'/>

pywb/webapp/handlers.py

@@ -115,6 +115,14 @@ class StaticHandler(BaseHandler):
         try:
             data = self.block_loader.load(full_path)
 
+            try:
+                data.seek(0, 2)
+                size = data.tell()
+                data.seek(0)
+                headers = [('Content-Length', str(size))]
+            except IOError:
+                headers = None
+
             if 'wsgi.file_wrapper' in wbrequest.env:
                 reader = wbrequest.env['wsgi.file_wrapper'](data)
             else:
@@ -122,7 +130,9 @@ class StaticHandler(BaseHandler):
 
             content_type, _ = mimetypes.guess_type(full_path)
 
-            return WbResponse.text_stream(data, content_type=content_type)
+            return WbResponse.text_stream(data,
+                                          content_type=content_type,
+                                          headers=headers)
 
         except IOError:
             raise NotFoundException('Static File Not Found: ' +

pywb/webapp/replay_views.py

@@ -99,8 +99,8 @@ class RewriteLiveView(BaseContentView):
         if ref_wburl_str:
             wbrequest.env['REL_REFERER'] = WbUrl(ref_wburl_str).url
 
-        url = wbrequest.wb_url.url
+        wb_url = wbrequest.wb_url
-        result = self.rewriter.fetch_request(url, wbrequest.urlrewriter,
+        result = self.rewriter.fetch_request(wb_url, wbrequest.urlrewriter,
                                              head_insert_func=head_insert_func,
                                              env=wbrequest.env)
 
@@ -211,14 +211,13 @@ class ReplayView(BaseContentView):
                                 create_insert_func(wbrequest))
 
         result = (self.content_rewriter.
-                  rewrite_content(urlrewriter,
+                  rewrite_content(wbrequest.wb_url,
+                                  urlrewriter,
                                   headers=status_headers,
                                   stream=stream,
                                   head_insert_func=head_insert_func,
                                   urlkey=cdx['urlkey'],
-                                  sanitize_only=wbrequest.wb_url.is_identity,
+                                  cdx=cdx))
-                                  cdx=cdx,
-                                  mod=wbrequest.wb_url.mod))
 
         (status_headers, response_iter, is_rewritten) = result
 

pywb/webapp/views.py

@@ -121,16 +121,18 @@ def add_env_globals(glb):
 
 #=================================================================
 class HeadInsertView(J2TemplateView):
-    def create_insert_func(self, wbrequest, include_ts=True):
+    def create_insert_func(self, wbrequest,
+                           include_ts=True):
 
         canon_url = wbrequest.wb_prefix + wbrequest.wb_url.to_str(mod='')
-        include_ts = include_ts
+        include_wombat = not wbrequest.wb_url.is_banner_only
 
         def make_head_insert(rule, cdx):
             return (self.render_to_string(wbrequest=wbrequest,
                                           cdx=cdx,
                                           canon_url=canon_url,
                                           include_ts=include_ts,
+                                          include_wombat=include_wombat,
                                           rule=rule))
         return make_head_insert
 

tests/test_integration.py

@@ -98,6 +98,7 @@ class TestWb:
 
         assert 'Mon, Jan 27 2014 17:12:38' in resp.body
         assert 'wb.js' in resp.body
+        assert 'WB_wombat_init' in resp.body
         assert '/pywb/20140127171238mp_/http://www.iana.org/time-zones"' in resp.body
 
     def test_replay_non_frame_content(self):
@@ -141,6 +142,19 @@ class TestWb:
         assert lines[0].startswith('org,iana)/_css/2013.1/print.css 20140127171239')
 
 
+    def test_replay_banner_only(self):
+        resp = self.testapp.get('/pywb/20140126201054bn_/http://www.iana.org/domains/reserved')
+
+        # wb.js header insertion
+        assert 'wb.js' in resp.body
+
+        # no wombat present
+        assert 'WB_wombat_init' not in resp.body
+
+        # url not rewritten
+        #assert '"http://www.iana.org/domains/example"' in resp.body
+        assert '"/_css/2013.1/screen.css"' in resp.body
+
     def test_replay_identity_1(self):
         resp = self.testapp.get('/pywb/20140127171251id_/http://example.com')