Changes to enable proper download
Changes to enable proper download

--- a/ckanext/ga_report/controller.py
+++ b/ckanext/ga_report/controller.py
@@ -1,4 +1,6 @@
 import re
+import csv
+import sys
 import logging
 import operator
 import collections
@@ -153,6 +155,45 @@
     Displays the pageview and visit count for specific publishers based on
     the datasets associated with the publisher.
     """
+    def csv(self, month):
+        #q = model.Session.query(GA_Stat)
+        #if month != 'all':
+        #    q = q.filter(GA_Stat.period_name==month)
+        #entries = q.order_by('GA_Stat.period_name, GA_Stat.stat_name, GA_Stat.key').all()
+        c.month = month if not month =='all' else ''
+        response.headers['Content-Type'] = "text/csv; charset=utf-8"
+
+        writer = csv.writer(response)
+        writer.writerow(["Publisher", "Views", "Visits", "Period Name"])
+
+        for publisher,view,visit in self._get_publishers(None):
+            writer.writerow([publisher.title.encode('utf-8'),
+                             view,
+                             visit,
+                             month])
+
+
+
+    def publisher_csv(self, id, month):
+
+        c.month = month if not month =='all' else ''
+        c.publisher = model.Group.get(id)
+        if not c.publisher:
+            abort(404, 'A publisher with that name could not be found')
+
+        packages = self._get_packages(c.publisher)
+        response.headers['Content-Type'] = "text/csv; charset=utf-8"
+
+        writer = csv.writer(response)
+        writer.writerow(["Publisher", "Views", "Visits", "Period Name"])
+
+        for package,view,visit in packages:
+            writer.writerow([package.title.encode('utf-8'),
+                             view,
+                             visit,
+                             month])
+
+
 
     def index(self):
 
@@ -166,6 +207,11 @@
         if c.month:
             c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])
 
+        c.top_publishers = self._get_publishers()
+
+        return render('ga_report/publisher/index.html')
+
+    def _get_publishers(self, limit=20):
         connection = model.Session.connection()
         q = """
             select department_id, sum(pageviews::int) views, sum(visitors::int) visits
@@ -176,54 +222,31 @@
                     and period_name=%s
             """
         q = q + """
-                group by department_id order by views desc limit 20;
+                group by department_id order by views desc
             """
+        if limit:
+            q = q + " limit %s;" % (limit)
 
         # Add this back (before and period_name =%s) if you want to ignore publisher
         # homepage views
         # and not url like '/publisher/%%'
 
-        c.top_publishers = []
+        top_publishers = []
         res = connection.execute(q, c.month)
 
         for row in res:
-            c.top_publishers.append((model.Group.get(row[0]), row[1], row[2]))
-
-        return render('ga_report/publisher/index.html')
-
-
-    def read(self, id):
-        count = 20
-
-        c.publisher = model.Group.get(id)
-        if not c.publisher:
-            abort(404, 'A publisher with that name could not be found')
-        c.top_packages = [] # package, dataset_views in c.top_packages
-
-        # Get the month details by fetching distinct values and determining the
-        # month names from the values.
-        c.months = _month_details(GA_Url)
-
-        # Work out which month to show, based on query params of the first item
-        c.month = request.params.get('month', '')
-        if not c.month:
-            c.month_desc = 'all time'
-        else:
-            c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])
-
-        c.publisher_page_views = 0
-        q = model.Session.query(GA_Url).\
-            filter(GA_Url.url=='/publisher/%s' % c.publisher.name)
-        if c.month:
-            entry = q.filter(GA_Url.period_name==c.month).first()
-            c.publisher_page_views = entry.pageviews if entry else 0
-        else:
-            for e in q.all():
-                c.publisher_page_views = c.publisher_page_views  + int(e.pageviews)
-
-
+            g = model.Group.get(row[0])
+            if g:
+                top_publishers.append((g, row[1], row[2]))
+        return top_publishers
+
+    def _get_packages(self, publisher, count=-1):
+        if count == -1:
+            count = sys.maxint
+
+        top_packages = []
         q =  model.Session.query(GA_Url).\
-            filter(GA_Url.department_id==c.publisher.name).\
+            filter(GA_Url.department_id==publisher.name).\
             filter(GA_Url.url.like('/dataset/%'))
         if c.month:
             q = q.filter(GA_Url.period_name==c.month)
@@ -232,7 +255,7 @@
         if c.month:
             for entry in q[:count]:
                 p = model.Package.get(entry.url[len('/dataset/'):])
-                c.top_packages.append((p,entry.pageviews,entry.visitors))
+                top_packages.append((p,entry.pageviews,entry.visitors))
         else:
             ds = {}
             for entry in q.all():
@@ -248,7 +271,40 @@
             for k, v in ds.iteritems():
                 results.append((k,v['views'],v['visits']))
 
-            c.top_packages = sorted(results, key=operator.itemgetter(1), reverse=True)
+            top_packages = sorted(results, key=operator.itemgetter(1), reverse=True)
+        return top_packages
+
+
+    def read(self, id):
+        count = 20
+
+        c.publisher = model.Group.get(id)
+        if not c.publisher:
+            abort(404, 'A publisher with that name could not be found')
+        c.top_packages = [] # package, dataset_views in c.top_packages
+
+        # Get the month details by fetching distinct values and determining the
+        # month names from the values.
+        c.months = _month_details(GA_Url)
+
+        # Work out which month to show, based on query params of the first item
+        c.month = request.params.get('month', '')
+        if not c.month:
+            c.month_desc = 'all time'
+        else:
+            c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])
+
+        c.publisher_page_views = 0
+        q = model.Session.query(GA_Url).\
+            filter(GA_Url.url=='/publisher/%s' % c.publisher.name)
+        if c.month:
+            entry = q.filter(GA_Url.period_name==c.month).first()
+            c.publisher_page_views = entry.pageviews if entry else 0
+        else:
+            for e in q.all():
+                c.publisher_page_views = c.publisher_page_views  + int(e.pageviews)
+
+        c.top_packages = self._get_packages(c.publisher, 20)
 
         return render('ga_report/publisher/read.html')
 

--- a/ckanext/ga_report/plugin.py
+++ b/ckanext/ga_report/plugin.py
@@ -27,22 +27,32 @@
 
     def after_map(self, map):
         map.connect(
-            '/data/analytics/publisher',
+            '/data/site-usage/publisher',
             controller='ckanext.ga_report.controller:GaPublisherReport',
             action='index'
         )
         map.connect(
-            '/data/analytics/publisher/{id}',
+            '/data/site-usage/publisher_{month}.csv',
+            controller='ckanext.ga_report.controller:GaPublisherReport',
+            action='csv'
+        )
+        map.connect(
+            '/data/site-usage/publisher/{id}_{month}.csv',
+            controller='ckanext.ga_report.controller:GaPublisherReport',
+            action='publisher_csv'
+        )
+        map.connect(
+            '/data/site-usage/publisher/{id}',
             controller='ckanext.ga_report.controller:GaPublisherReport',
             action='read'
         )
         map.connect(
-            '/data/analytics',
+            '/data/site-usage',
             controller='ckanext.ga_report.controller:GaReport',
             action='index'
         )
         map.connect(
-            '/data/analytics/data_{month}.csv',
+            '/data/site-usage/data_{month}.csv',
             controller='ckanext.ga_report.controller:GaReport',
             action='csv'
         )

--- a/ckanext/ga_report/templates/ga_report/publisher/index.html
+++ b/ckanext/ga_report/templates/ga_report/publisher/index.html
@@ -20,7 +20,7 @@
     <li class="widget-container boxed widget_text">
       <h4>Download</h4>
       <p><center>
-          <a class="btn button" href="${h.url_for(controller='ckanext.ga_report.controller:GaReport',action='csv',month=c.month or 'all')}">Download as CSV</a></center>
+          <a class="btn button" href="${h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport',action='csv',month=c.month or 'all')}">Download as CSV</a></center>
       </p>
     </li>
   </py:match>

--- a/ckanext/ga_report/templates/ga_report/publisher/read.html
+++ b/ckanext/ga_report/templates/ga_report/publisher/read.html
@@ -21,7 +21,7 @@
     <li class="widget-container boxed widget_text">
       <h4>Download</h4>
       <p><center>
-          <a class="btn button" href="${h.url_for(controller='ckanext.ga_report.controller:GaReport',action='csv',month=c.month or 'all')}">Download as CSV</a></center>
+          <a class="btn button" href="${h.url_for(controller='ckanext.ga_report.controller:GaPublisherReport',action='publisher_csv',id=c.publisher.name,month=c.month or 'all')}">Download as CSV</a></center>
       </p>
     </li>
   </py:match>