more refactoring: seperate top-level handlers (WBHandler) from

views (html, text)
Add CDXHandler for interfacing with cdx server directly, #12

pywb/handlers.py

@@ -0,0 +1,72 @@
+import views
+import utils
+import urlparse
+
+#=================================================================
+# Standard WB Handler
+#=================================================================
+class WBHandler:
+    def __init__(self, cdx_reader, replay, html_view = None):
+        self.cdx_reader = cdx_reader
+        self.replay = replay
+        self.html_view = html_view
+        self.text_view = views.TextQueryView()
+
+    def __call__(self, wbrequest):
+        with utils.PerfTimer(wbrequest.env.get('X_PERF'), 'query') as t:
+            cdx_lines = self.cdx_reader.load_for_request(wbrequest, parsed_cdx = True)
+
+        # new special modifier to always show cdx index
+        if wbrequest.wb_url.mod == 'cdx_':
+            return self.text_view(wbrequest, cdx_lines)
+
+        if (wbrequest.wb_url.type == wbrequest.wb_url.QUERY) or (wbrequest.wb_url.type == wbrequest.wb_url.URL_QUERY):
+            if not self.html_view:
+                return self.text_view(wbrequest, cdx_lines)
+            else:
+                return self.html_view(wbrequest, cdx_lines)
+
+        with utils.PerfTimer(wbrequest.env.get('X_PERF'), 'replay') as t:
+            return self.replay(wbrequest, cdx_lines, self.cdx_reader)
+
+
+
+#=================================================================
+# CDX-Server Handler -- pass all params to cdx server
+#=================================================================
+class CDXHandler:
+    def __init__(self, cdx_reader, view = None):
+        self.cdx_reader = cdx_reader
+        self.view = view if view else views.TextQueryView()
+
+    def __call__(self, wbrequest):
+        url = wbrequest.wb_url.url
+
+        # use url= param to get actual url
+        params = urlparse.parse_qs(wbrequest.env['QUERY_STRING'])
+
+        url = params.get('url')
+        if not url:
+            raise Exception('Must specify a url= param to query cdx server')
+
+        url = url[0]
+
+        cdx_lines = self.cdx_reader.load_cdx(url, params, parsed_cdx = False)
+
+        return self.view(wbrequest, cdx_lines)
+
+
+#=================================================================
+# Debug Handlers
+#=================================================================
+class DebugEchoEnvHandler:
+    def __call__(self, wbrequest):
+        return wbrequestresponse.WbResponse.text_response(str(wbrequest.env))
+
+#=================================================================
+class DebugEchoHandler:
+    def __call__(self, wbrequest):
+        return wbrequestresponse.WbResponse.text_response(str(wbrequest))
+
+
+

pywb/pywb_init.py

@@ -1,7 +1,8 @@
 import archiveloader
 import views
+import handlers
 import indexreader
-import replay
+import replay_views
 import replay_resolvers
 import cdxserve
 from archivalrouter import ArchivalRequestRouter, Route
@@ -24,19 +25,23 @@ def pywb_config(head_insert = ''):
     prefixes = [replay_resolvers.PrefixResolver(test_dir)]
 
     # Create rewriting replay handler to rewrite records
-    replayer = replay.RewritingReplayHandler(resolvers = prefixes, archiveloader = aloader, headInsert = head_insert, buffer_response = True)
+    replayer = replay_views.RewritingReplayView(resolvers = prefixes, archiveloader = aloader, headInsert = head_insert, buffer_response = True)
 
     # Create Jinja2 based html query view
     html_view = views.J2QueryView('./ui/', 'query.html')
 
     # WB handler which uses the index reader, replayer, and html_view
-    wb_handler = replay.WBHandler(indexs, replayer, html_view)
+    wb_handler = handlers.WBHandler(indexs, replayer, html_view)
+
+    # cdx handler
+    cdx_handler = handlers.CDXHandler(indexs)
 
     # Finally, create wb router
     return ArchivalRequestRouter(
         {
-            Route('echo_req', views.DebugEchoView()), # Debug ex: just echo parsed request
+            Route('echo_req', handlers.DebugEchoHandler()), # Debug ex: just echo parsed request
             Route('pywb',   wb_handler),
+            Route('cdx', cdx_handler),
         },
         # Specify hostnames that pywb will be running on
         # This will help catch occasionally missed rewrites that fall-through to the host

pywb/replay_views.py

@@ -5,7 +5,6 @@ import copy
 import itertools
 
 import archiveloader
-import views
 from wbrequestresponse import WbResponse, StatusAndHeaders
 from wbarchivalurl import ArchivalUrl
 import utils
@@ -17,34 +16,9 @@ import regex_rewriters
 
 import wbexceptions
 
-#=================================================================
-class WBHandler:
-    def __init__(self, cdx_reader, replay, html_view = None):
-        self.cdx_reader = cdx_reader
-        self.replay = replay
-        self.html_view = html_view
-        self.text_view = views.TextQueryView()
-
-    def __call__(self, wbrequest):
-        with utils.PerfTimer(wbrequest.env.get('X_PERF'), 'query') as t:
-            cdx_lines = self.cdx_reader.load_for_request(wbrequest, parsed_cdx = True)
-
-        # new special modifier to always show cdx index
-        if wbrequest.wb_url.mod == 'cdx_':
-            return self.text_view(wbrequest, cdx_lines)
-
-        if (wbrequest.wb_url.type == wbrequest.wb_url.QUERY) or (wbrequest.wb_url.type == wbrequest.wb_url.URL_QUERY):
-            if not self.html_view:
-                return self.text_view(wbrequest, cdx_lines)
-            else:
-                return self.html_view(wbrequest, cdx_lines)
-
-        with utils.PerfTimer(wbrequest.env.get('X_PERF'), 'replay') as t:
-            return self.replay(wbrequest, cdx_lines, self.cdx_reader)
-
 
 #=================================================================
-class ReplayHandler(object):
+class ReplayView:
     def __init__(self, resolvers, archiveloader):
         self.resolvers = resolvers
         self.loader = archiveloader
@@ -238,10 +212,10 @@ class ReplayHandler(object):
 
 
 #=================================================================
-class RewritingReplayHandler(ReplayHandler):
+class RewritingReplayView(ReplayView):
 
     def __init__(self, resolvers, archiveloader, headInsert = None, headerRewriter = None, redir_to_exact = True, buffer_response = False):
-        ReplayHandler.__init__(self, resolvers, archiveloader)
+        ReplayView.__init__(self, resolvers, archiveloader)
         self.headInsert = headInsert
         if not headerRewriter:
             headerRewriter = HeaderRewriter()
@@ -264,7 +238,7 @@ class RewritingReplayHandler(ReplayHandler):
         urlrewriter = ArchivalUrlRewriter(wbrequest.wb_url, wbrequest.wb_prefix)
         wbrequest.urlrewriter = urlrewriter
 
-        response = ReplayHandler.__call__(self, wbrequest, index, cdx_reader)
+        response = ReplayView.__call__(self, wbrequest, index, cdx_reader)
 
         if response and response.cdx:
             self._checkRedir(wbrequest, response.cdx)
@@ -419,7 +393,7 @@ class RewritingReplayHandler(ReplayHandler):
 
 
     def doReplay(self, cdx, wbrequest, index, failedFiles):
-        wbresponse = ReplayHandler.doReplay(self, cdx, wbrequest, index, failedFiles)
+        wbresponse = ReplayView.doReplay(self, cdx, wbrequest, index, failedFiles)
 
         # Check for self redirect
         if wbresponse.status_headers.statusline.startswith('3'):

pywb/views.py

@@ -36,14 +36,3 @@ class J2QueryView:
         return wbrequestresponse.WbResponse.text_response(str(response), content_type = 'text/html')
 
 
-#=================================================================
-class DebugEchoView:
-    def __call__(self, wbrequest):
-        return wbrequestresponse.WbResponse.text_response(str(wbrequest.env))
-
-#=================================================================
-class DebugEchoView:
-    def __call__(self, wbrequest):
-        return wbrequestresponse.WbResponse.text_response(str(wbrequest))
-
-