Modified to collect visit instead of visitors.
[ckanext-ga-report.git] / ckanext / ga_report / controller.py
blob:a/ckanext/ga_report/controller.py -> blob:b/ckanext/ga_report/controller.py
--- a/ckanext/ga_report/controller.py
+++ b/ckanext/ga_report/controller.py
@@ -9,7 +9,7 @@
 import sqlalchemy
 from sqlalchemy import func, cast, Integer
 import ckan.model as model
-from ga_model import GA_Url, GA_Stat, GA_ReferralStat
+from ga_model import GA_Url, GA_Stat, GA_ReferralStat, GA_Publisher
 
 log = logging.getLogger('ckanext.ga-report')
 
@@ -22,11 +22,29 @@
 
 
 def _month_details(cls):
+    '''
+    Returns a list of all the periods for which we have data, unfortunately
+    knows too much about the type of the cls being passed as GA_Url has a
+    more complex query
+
+    This may need extending if we add a period_name to the stats
+    '''
     months = []
-    vals = model.Session.query(cls.period_name).distinct().all()
+    day = None
+
+    vals = model.Session.query(cls.period_name,cls.period_complete_day)\
+        .filter(cls.period_name!='All').distinct(cls.period_name)\
+        .order_by("period_name desc").all()
+    if vals and vals[0][1]:
+        day = int(vals[0][1])
+        ordinal = 'th' if 11 <= day <= 13 \
+            else {1:'st',2:'nd',3:'rd'}.get(day % 10, 'th')
+        day = "{day}{ordinal}".format(day=day, ordinal=ordinal)
+
     for m in vals:
         months.append( (m[0], _get_month_name(m[0])))
-    return sorted(months, key=operator.itemgetter(0), reverse=True)
+
+    return months, day
 
 
 class GaReport(BaseController):
@@ -34,7 +52,7 @@
     def csv(self, month):
         import csv
 
-        q = model.Session.query(GA_Stat)
+        q = model.Session.query(GA_Stat).filter(GA_Stat.stat_name!='Downloads')
         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()
@@ -51,11 +69,31 @@
                              entry.key.encode('utf-8'),
                              entry.value.encode('utf-8')])
 
+    def csv_downloads(self, month):
+        import csv
+
+        q = model.Session.query(GA_Stat).filter(GA_Stat.stat_name=='Downloads')
+        if month != 'all':
+            q = q.filter(GA_Stat.period_name==month)
+        entries = q.order_by('GA_Stat.period_name, GA_Stat.key').all()
+
+        response.headers['Content-Type'] = "text/csv; charset=utf-8"
+        response.headers['Content-Disposition'] = str('attachment; filename=downloads_%s.csv' % (month,))
+
+        writer = csv.writer(response)
+        writer.writerow(["Period", "Resource URL", "Count"])
+
+        for entry in entries:
+            writer.writerow([entry.period_name.encode('utf-8'),
+                             entry.key.encode('utf-8'),
+                             entry.value.encode('utf-8')])
+
+
     def index(self):
 
         # Get the month details by fetching distinct values and determining the
         # month names from the values.
-        c.months = _month_details(GA_Stat)
+        c.months, c.day = _month_details(GA_Stat)
 
         # Work out which month to show, based on query params of the first item
         c.month_desc = 'all months'
@@ -70,13 +108,13 @@
         entries = q.order_by('ga_stat.key').all()
 
         def clean_key(key, val):
-            if key in ['Average time on site', 'Pages per visit', 'New visits', 'Bounces']:
+            if key in ['Average time on site', 'Pages per visit', 'New visits', 'Bounce rate (home page)']:
                 val =  "%.2f" % round(float(val), 2)
                 if key == 'Average time on site':
                     mins, secs = divmod(float(val), 60)
                     hours, mins = divmod(mins, 60)
                     val = '%02d:%02d:%02d (%s seconds) ' % (hours, mins, secs, val)
-                if key in ['New visits','Bounces']:
+                if key in ['New visits','Bounce rate (home page)']:
                     val = "%s%%" % val
             if key in ['Total page views', 'Total visits']:
                 val = int(val)
@@ -96,7 +134,7 @@
                 if k in ['Total page views', 'Total visits']:
                     v = sum(v)
                 else:
-                    v = float(sum(v))/len(v)
+                    v = float(sum(v))/float(len(v))
                 key, val = clean_key(k,v)
 
                 c.global_totals.append((key, val))
@@ -161,6 +199,35 @@
 
         return render('ga_report/site/index.html')
 
+    def downloads(self):
+
+        # Get the month details by fetching distinct values and determining the
+        # month names from the values.
+        c.months, c.day = _month_details(GA_Stat)
+
+        # Work out which month to show, based on query params of the first item
+        c.month_desc = 'all months'
+        c.month = request.params.get('month', '')
+        if c.month:
+            c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])
+
+        c.downloads = []
+        q = model.Session.query(GA_Stat).filter(GA_Stat.stat_name=='Downloads')
+        q = q.filter(GA_Stat.period_name==c.month) if c.month else q
+        q = q.order_by("ga_stat.value::int desc")
+
+        data = collections.defaultdict(int)
+        for entry in q.all():
+            r = model.Session.query(model.Resource).filter(model.Resource.url==entry.key).first()
+            if not r:
+                continue
+            data[r] += int(entry.value)
+
+        c.downloads = [(k,v,) for k,v in data.iteritems()]
+        c.downloads = sorted(c.downloads, key=operator.itemgetter(1), reverse=True)
+
+        return render('ga_report/site/downloads.html')
+
 
 class GaDatasetReport(BaseController):
     """
@@ -219,7 +286,7 @@
 
         # Get the month details by fetching distinct values and determining the
         # month names from the values.
-        c.months = _month_details(GA_Url)
+        c.months, c.day = _month_details(GA_Url)
 
         # Work out which month to show, based on query params of the first item
         c.month = request.params.get('month', '')
@@ -228,49 +295,29 @@
             c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])
 
         c.top_publishers = _get_top_publishers()
-
         return render('ga_report/publisher/index.html')
 
     def _get_packages(self, publisher=None, count=-1):
-        '''Returns the datasets in order of visits'''
+        '''Returns the datasets in order of views'''
         if count == -1:
             count = sys.maxint
 
-        q = model.Session.query(GA_Url)\
+        month = c.month or 'All'
+
+        q = model.Session.query(GA_Url,model.Package)\
+            .filter(model.Package.name==GA_Url.package_id)\
             .filter(GA_Url.url.like('/dataset/%'))
         if publisher:
             q = q.filter(GA_Url.department_id==publisher.name)
-        if c.month:
-            q = q.filter(GA_Url.period_name==c.month)
-        q = q.order_by('ga_url.visitors::int desc')
-
-        if c.month:
-            top_packages = []
-            for entry in q.limit(count):
-                package_name = entry.url[len('/dataset/'):]
-                p = model.Package.get(package_name)
-                if p:
-                    top_packages.append((p, entry.pageviews, entry.visitors))
-                else:
-                    log.warning('Could not find package "%s"', package_name)
-        else:
-            ds = {}
-            for entry in q.limit(count):
-                package_name = entry.url[len('/dataset/'):]
-                p = model.Package.get(package_name)
-                if p:
-                    if not p in ds:
-                        ds[p] = {'views': 0, 'visits': 0}
-                    ds[p]['views'] = ds[p]['views'] + int(entry.pageviews)
-                    ds[p]['visits'] = ds[p]['visits'] + int(entry.visitors)
-                else:
-                    log.warning('Could not find package "%s"', package_name)
-
-            results = []
-            for k, v in ds.iteritems():
-                results.append((k,v['views'],v['visits']))
-
-            top_packages = sorted(results, key=operator.itemgetter(1), reverse=True)
+        q = q.filter(GA_Url.period_name==month)
+        q = q.order_by('ga_url.pageviews::int desc')
+        top_packages = []
+        for entry,package in q.limit(count):
+            if package:
+                top_packages.append((package, entry.pageviews, entry.visits))
+            else:
+                log.warning('Could not find package associated package')
+
         return top_packages
 
     def read(self):
@@ -297,7 +344,7 @@
 
         # Get the month details by fetching distinct values and determining the
         # month names from the values.
-        c.months = _month_details(GA_Url)
+        c.months, c.day = _month_details(GA_Url)
 
         # Work out which month to show, based on query params of the first item
         c.month = request.params.get('month', '')
@@ -306,15 +353,12 @@
         else:
             c.month_desc = ''.join([m[1] for m in c.months if m[0]==c.month])
 
+        month = c.month or 'All'
         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)
+        entry = q.filter(GA_Url.period_name==c.month).first()
+        c.publisher_page_views = entry.pageviews if entry else 0
 
         c.top_packages = self._get_packages(c.publisher, 20)
 
@@ -325,38 +369,33 @@
     Returns a list of the top 20 publishers by dataset visits.
     (The number to show can be varied with 'limit')
     '''
+    month = c.month or 'All'
     connection = model.Session.connection()
     q = """
-        select department_id, sum(pageviews::int) views, sum(visitors::int) visits
+        select department_id, sum(pageviews::int) views, sum(visits::int) visits
         from ga_url
-        where department_id <> ''"""
-    if c.month:
-        q = q + """
-                and period_name=%s
-        """
-    q = q + """
-            group by department_id order by visits desc
+        where department_id <> ''
+          and package_id <> ''
+          and url like '/dataset/%%'
+          and period_name=%s
+        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/%%'
-
     top_publishers = []
-    res = connection.execute(q, c.month)
-
+    res = connection.execute(q, month)
     for row in res:
         g = model.Group.get(row[0])
         if g:
             top_publishers.append((g, row[1], row[2]))
     return top_publishers
 
+
 def _get_publishers():
     '''
     Returns a list of all publishers. Each item is a tuple:
-      (names, title)
+      (name, title)
     '''
     publishers = []
     for pub in model.Session.query(model.Group).\