Add public ranking listing, link charts better
Add public ranking listing, link charts better


Former-commit-id: 889d2d51a7712e7454f582b671b6142d619ad672

file:a/about.php -> file:b/about.php
--- a/about.php
+++ b/about.php
@@ -5,6 +5,10 @@
 <div class="foundation-header">
     <h1><a href="about.php">About/FAQ</a></h1>
 </div>
+<a href="http://thenounproject.com/noun/document-dump/">Document Dump icon designed by  Iconathon,  2013</a>
+Contact us: maxious@lambdacomplex.org
+
+Exports: <a href="admin/exportAll.csv.php">All Agencies</a> <a href="admin/exportEmployees.csv.php">Agency Employee Headcounts</a>
 <h2> Attributions </h2>
 National Archives of Australia, Australian Governments’ Interactive Functions Thesaurus, 2nd edition, September 2005, published at http://www.naa.gov.au/recordkeeping/thesaurus/index.htm <br/>
 data.gov.au http://data.gov.au/dataset/directory-gov-au-full-data-export/ <br/>

--- a/admin/refreshDesignDoc.php
+++ b/admin/refreshDesignDoc.php
@@ -42,6 +42,7 @@
 $obj->views->byWebServer->map = "function(doc) {\n  emit(doc.web_server, doc);\n}";
 
 $obj->views->datasets->map = "function(doc) {\nif (doc.fieldName == \"data\") {\n  emit(doc._id, doc);\n}\n}";
+$obj->views->datasetGroups->map = "function(doc) {\nif (doc.fieldName == \"data\") {\n  doc.metadata[\"data.gov.au Category\"] && doc.metadata[\"data.gov.au Category\"].forEach(function(tag) {\n emit(tag, doc.url); \n  });\n}\n}";
 $obj->views->getValidationRequired->map = "function(doc) {\nif (doc.mime_type == \"text/html\" \n&& typeof(doc.validation) == \"undefined\") {\n  emit(doc._id, doc._attachments);\n}\n}";
 $docdb->save($obj, true);
 

file:a/charts.php (deleted)
--- a/charts.php
+++ /dev/null
@@ -1,133 +1,1 @@
-<?php
-include_once('include/common.inc.php');
-include_header('Charts');
-$db = $server->get_db('disclosr-agencies');
-?>
-<div class="foundation-header">
-    <h1><a href="about.php">Charts</a></h1>
-    <h4 class="subheader">Lorem ipsum.</h4>
-</div>
-<div id="scores" style="width:900px;height:500px;"></div>
-<div id="employees" style="width:1000px;height:900px;"></div>
-<script id="source">
-    window.onload = function() {
-        $(document).ready(function() {
-            var d1 = [];
-            var scorelabels = [];
-    <?php
-    try {
-        $rows = $db->get_view("app", "scoreHas?group=true", null, true)->rows;
 
-
-        $dataValues = Array();
-        foreach ($rows as $row) {
-            $dataValues[$row->value] = $row->key;
-        }
-        $i = 0;
-        ksort($dataValues);
-        foreach ($dataValues as $value => $key) {
-
-            echo "       d1.push([$i, $value]);" . PHP_EOL;
-            echo "        scorelabels.push('$key');" . PHP_EOL;
-            $i++;
-        }
-    } catch (SetteeRestClientException $e) {
-        setteErrorHandler($e);
-    }
-    ?>
-                function scoretrackformatter(obj) {
-                    if (scorelabels[Math.floor(obj.x)]) {
-                        return (scorelabels[Math.floor(obj.x)])+"="+obj.y;
-                     
-                    } else {
-                        return "";
-                    }
-                }
-                function scoretickformatter(val, axis) {
-                    if (scorelabels[Math.floor(val)]) {
-                        return '<p style="margin-top:8em;-webkit-transform:rotate(-90deg);">'+(scorelabels[Math.floor(val)])+"</b>";
-                     
-                    } else {
-                        return "";
-                    }
-                }
-                Flotr.draw(document.getElementById("scores"), [ {data: d1}], {
-                    HtmlText: true,
-                    bars : {
-                        show : true
-                    },
-                    mouse : {
-                        track : true,
-                        relative : true,
-                        trackFormatter: scoretrackformatter
-                    },yaxis: {
-                        autoscaling: true
-                    },
-                    xaxis: {
-                    autoscaling: true,
-                        minorTickFreq: 0.6,
-                        noTicks : scorelabels.length,
-                        tickFormatter: scoretickformatter
-                    }
-                });
-                
-                
-                
-                
-                
-                
-                
-                
-var emplabels = [];
-function emptrackformatter(obj) {
-                   
-                        return (obj.series.label)+" = "+obj.y+" in "+emplabels[Math.floor(obj.x)];
-                     
-                }
-                function emptickformatter(val, axis) {
-                    if (emplabels[Math.floor(val)]) {
-                        return '<p style="margin-top:8em;-webkit-transform:rotate(-90deg);">'+(emplabels[Math.floor(val)])+"</b>";
-                     
-                    } else {
-                        return "";
-                    }
-                }
-function onDataReceived(series) {
-    emplabels = series.labels;
-                       Flotr.draw(document.getElementById("employees"), series.data, {
-                    mouse : {
-                        track : true,
-                        relative : true,
-                    trackFormatter: emptrackformatter
-                    },yaxis: {
-                        max: 10000,
-                        scaling: 'logarithmic'
-                    },
-                    xaxis: {
-                    minorTickFreq: 1,
-                    noTicks: emplabels.length,
-                    showMinorLabels: true,
-                        tickFormatter: emptickformatter
-                    },
-                    legend: {
-                        show: false
-                    }
-                });
-                }
-        
-                $.ajax({
-                    url: "admin/exportEmployees.csv.php?format=json",
-                    method: 'GET',
-                    dataType: 'json',
-                    success: onDataReceived
-                });
-
-    
-            });
-        };
- 
-</script>
-
-<?php
-include_footer();
-?>

file:b/disclosr.iml (new)
--- /dev/null
+++ b/disclosr.iml
@@ -1,1 +1,16 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="WEB_MODULE" version="4">
+  <component name="FacetManager">
+    <facet type="Python" name="Python">
+      <configuration sdkName="" />
+    </facet>
+  </component>
+  <component name="NewModuleRootManager" inherit-compiler-output="true">
+    <exclude-output />
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>
 
+

--- a/documents/charts.php
+++ b/documents/charts.php
@@ -13,10 +13,10 @@
 ?>
 <div class="foundation-header">
     <h1><a href="about.php">Charts</a></h1>
-    <h4 class="subheader">Lorem ipsum.</h4>
+    <h4 class="subheader"></h4>
 </div>
 <div id="bydate" style="width:1000px;height:300px;"></div>
-<div id="byagency" style="width:1200px;height:300px;"></div>
+<div id="byagency" style="width:1200px;height:800px;"></div>
 <script id="source">
     window.onload = function () {
         $(document).ready(function () {
@@ -59,7 +59,7 @@
                     mode: 'x'
                 },
                 HtmlText: false,
-                title: 'Time'
+                title: 'Disclosure Log entries added by Date'
             };
 
             // Draw graph with default options, overwriting with passed options
@@ -98,12 +98,12 @@
     var agencylabels = [];
     function agencytrackformatter(obj) {
 
-        return agencylabels[Math.floor(obj.x)] + " = " + obj.y;
+        return agencylabels[Math.floor(obj.y)] + " = " + obj.x;
 
     }
     function agencytickformatter(val, axis) {
         if (agencylabels[Math.floor(val)]) {
-            return '<p style="margin-top:8em;-webkit-transform:rotate(-90deg);">' + (agencylabels[Math.floor(val)]) + "</b>";
+            return  (agencylabels[Math.floor(val)]) ;
 
         } else {
             return "";
@@ -117,7 +117,7 @@
             $dataValues = Array();
             $i = 0;
             foreach ($rows as $row) {
-                echo "       d2.push([".$i.", $row->value]);" . PHP_EOL;
+                echo "       d2.push([ $row->value,$i]);" . PHP_EOL;
                 echo "       agencylabels.push(['".str_replace("'","",$idtoname[$row->key])."']);" . PHP_EOL;
 
                 $i++;
@@ -131,9 +131,10 @@
         document.getElementById("byagency"),
         [d2],
         {
+            title: "Disclosure Log entries by Agency",
             bars: {
                 show: true,
-                horizontal: false,
+                horizontal: true,
                 shadowSize: 0,
                 barWidth: 0.5
             },
@@ -143,14 +144,14 @@
                 trackFormatter: agencytrackformatter
             },
             yaxis: {
-                min: 0,
-                autoscaleMargin: 1
-            },
-            xaxis: {
                 minorTickFreq: 1,
                 noTicks: agencylabels.length,
                 showMinorLabels: true,
                 tickFormatter: agencytickformatter
+            },
+            xaxis: {
+                min: 0,
+                autoscaleMargin: 1
             },
             legend: {
                 show: false

--- /dev/null
+++ b/documents/datagov-export-groups.py
@@ -1,1 +1,81 @@
+import ckanclient
+import couchdb
+from ckanclient import CkanApiError
+import re
 
+
+class LoaderError(Exception):
+    pass
+
+# Instantiate the CKAN client.
+#ckan = ckanclient.CkanClient(base_location='http://localhost:5000/api',    api_key='b47b24cd-591d-40c1-8677-d73101d56d1b')
+api_key = 'ff34526e-f794-4068-8235-fcbba38cd8bc'
+ckan = ckanclient.CkanClient(base_location='http://data.disclosurelo.gs/api',
+                             api_key=api_key)
+couch = couchdb.Server('http://127.0.0.1:5984/')
+#couch = couchdb.Server('http://192.168.1.113:5984/')
+
+# https://github.com/okfn/ckanext-importlib
+def munge(name):
+    # convert spaces to underscores
+    name = re.sub(' ', '_', name).lower()
+    # convert symbols to dashes
+    name = re.sub('[:]', '_-', name).lower()
+    name = re.sub('[/]', '-', name).lower()
+    # take out not-allowed characters
+    name = re.sub('[^a-zA-Z0-9-_]', '', name).lower()
+    # remove double underscores
+    name = re.sub('__', '_', name).lower()
+    return name
+
+
+def name_munge(input_name):
+    return munge(input_name.replace(' ', '').replace('.', '_').replace('&', 'and'))
+
+
+docsdb = couch['disclosr-documents']
+
+if __name__ == "__main__":
+    groups = {}
+    for doc in docsdb.view('app/datasetGroups'):
+            group_name = doc.key
+            if group_name != "Not specified":
+                pkg_name = filter(lambda x: x in '0123456789abcdefghijklmnopqrstuvwxyz-_',
+                                  doc.value.replace("http://data.gov.au/dataset/", '').replace('/', '')[:100]);
+                if group_name in groups.keys():
+                    groups[group_name] = list(set(groups[group_name] + [pkg_name]))
+                else:
+                    groups[group_name] = [pkg_name]
+
+    # add dataset to group(s)
+    for group_name in groups.keys():
+        if group_name != "Not specified":
+            group_url = name_munge(group_name[:100])
+            print group_name
+            print groups[group_name]
+            try:
+                # Update the group details
+                group_entity = ckan.group_entity_get(group_url)
+                print "group "+group_name+" exists"
+                if 'packages' in group_entity.keys():
+                    group_entity['packages'] = list(set(group_entity['packages'] + groups[group_name]))
+                else:
+                    group_entity['packages'] = groups[group_name]
+                ckan.group_entity_put(group_entity)
+            except CkanApiError, e:
+                if ckan.last_status == 404:
+                    print "group "+group_name+" does not exist, creating"
+                    group_entity = {
+                        'name': group_url,
+                        'title': group_name,
+                        'description': group_name,
+                        'packages': groups[group_name]
+                    }
+                    #print group_entity
+                    ckan.group_register_post(group_entity)
+                elif ckan.last_status == 409:
+                    print "group already exists"
+                else:
+                    raise LoaderError('Unexpected status %s adding to group under \'%s\': %r' % (
+                        ckan.last_status, pkg_name, e.args))
+

--- a/documents/datagov-export.py
+++ b/documents/datagov-export.py
@@ -1,19 +1,92 @@
+# coding=utf-8
 import ckanclient
 import couchdb
 from ckanclient import CkanApiError
 import re
 import html2text # aaronsw :(
+import ckanapi # https://github.com/open-data/ckanapi
+import scrape
+import datetime, os, hashlib
 
 
 class LoaderError(Exception):
     pass
 
+
+def add_package_resource_cachedurl(ckan, package_name, url, name, format, size, **kwargs):
+    # fileupload
+    ts = datetime.datetime.isoformat(datetime.datetime.now()).replace(':', '').split('.')[0]
+
+    file_key = os.path.join(ts, name)
+
+    auth_dict = ckan.storage_auth_get('/form/' + file_key, {})
+
+    fields = [(kv['name'].encode('ascii'), kv['value'].encode('ascii'))
+              for kv in auth_dict['fields']]
+    (url, mime_type, content) = scrape.fetchURL(scrape.docsdb,
+                                                url, "dataset_resource", "AGIMO", False)
+
+    files = [('file', os.path.basename(file_key), content)]
+
+    errcode, body = ckan._post_multipart(auth_dict['action'].encode('ascii'), fields, files)
+
+    if errcode == 200:
+        file_metadata = ckan.storage_metadata_get(file_key)
+        (url, msg) = file_metadata['_location'], ''
+    else:
+        (url, msg) = '', body
+        # fileupload done
+
+    if url == '':
+        raise CkanApiError(msg)
+    m = hashlib.sha1(msg)
+    #todo mime-type dectection based on content
+    r = dict(name=name,
+             mimetype=mime_type,
+             hash=m.hexdigest(), size=size, url=url)
+
+    r.update(kwargs)
+    if not r.has_key('name'): r['name'] = url
+
+    p = ckan.package_entity_get(package_name)
+    p['resources'].append(r)
+    return ckan.package_entity_put(p)
+
+
 # Instantiate the CKAN client.
-#ckan = ckanclient.CkanClient(base_location='http://localhost:5000/api',    api_key='b47b24cd-591d-40c1-8677-d73101d56d1b')
-ckan = ckanclient.CkanClient(base_location='http://data.disclosurelo.gs/api',
-    api_key='482a9dd2-a976-4adf-ac77-d71d92a98a52')
-#couch = couchdb.Server('http://127.0.0.1:5984/')
-couch = couchdb.Server('http://192.168.1.113:5984/')
+api_key = 'ff34526e-f794-4068-8235-fcbba38cd8bc'
+server = 'data.disclosurelo.gs'
+
+ckan = ckanclient.CkanClient(base_location='http://' + server + '/api',
+                             api_key=api_key)
+ckandirect = ckanapi.RemoteCKAN('http://' + server, api_key=api_key)
+couch = couchdb.Server('http://127.0.0.1:5984/')
+#couch = couchdb.Server('http://192.168.1.113:5984/')
+
+import urllib
+import urlparse
+
+
+def url_fix(s, charset='utf-8'):
+    """Sometimes you get an URL by a user that just isn't a real
+    URL because it contains unsafe characters like ' ' and so on.  This
+    function can fix some of the problems in a similar way browsers
+    handle data entered by the user:
+
+    >>> url_fix(u'http://de.wikipedia.org/wiki/Elf (Begriffsklärung)')
+    'http://de.wikipedia.org/wiki/Elf%20%28Begriffskl%C3%A4rung%29'
+
+    :param charset: The target charset for the URL if the url was
+                    given as unicode string.
+    """
+    if isinstance(s, unicode):
+        s = s.encode(charset, 'ignore')
+    if not urlparse.urlparse(s).scheme:
+        s = "http://" + s
+    scheme, netloc, path, qs, anchor = urlparse.urlsplit(s)
+    path = urllib.quote(path, '/%')
+    qs = urllib.quote_plus(qs, ':&=')
+    return urlparse.urlunsplit((scheme, netloc, path, qs, anchor))
 
 # http://code.activestate.com/recipes/578019-bytes-to-human-human-to-bytes-converter/
 SYMBOLS = {
@@ -24,6 +97,7 @@
     'iec_ext': ('byte', 'kibi', 'mebi', 'gibi', 'tebi', 'pebi', 'exbi',
                 'zebi', 'yobi'),
 }
+
 
 def human2bytes(s):
     """
@@ -53,6 +127,9 @@
           ...
       ValueError: can't interpret '12 foo'
     """
+    if s == None:
+        return 0
+    s = s.replace(',', '')
     init = s
     num = ""
     while s and s[0:1].isdigit() or s[0:1] == '.':
@@ -91,7 +168,6 @@
 
 def name_munge(input_name):
     return munge(input_name.replace(' ', '').replace('.', '_').replace('&', 'and'))
-    #return input_name.replace(' ', '').replace('.', '_').replace('&', 'and')
 
 
 def get_licence_id(licencename):
@@ -112,108 +188,142 @@
         raise Exception(licencename + " not found");
     return map[licencename];
 
+
+gooddata = ["afl-in-victoria", "annual-budget-initiatives-by-suburb-brisbane-city-council"]
+#athletics-in-victoria-gfyl,bicycle-racks-mosman-municipal-council,boat-ramps-brisbane-city-council,brisbane-access-ratings-database,bus-stops-brisbane-city-council,cemeteries-brisbane-city-council,cfa-locations,citycycle-stations-brisbane-city-council,community-gardens-brisbane-city-council,community-halls-brisbane-city-council,cooking-classes-gfyl,court-locations-victoria,customer-service-centres-brisbane-city-council,dance-in-victoria-gfyl,disability-activity-gfyl,dog-parks-brisbane-city-council,ferry-terminals-brisbane-city-council,fishing-club-in-victoria-gfyl,fitness-centres-in-victoria-gfyl,gardens-reserves-gfyl,golf-courses-brisbane-city-council,gymnastics-in-victoria-gfyl,historic-cemeteries-brisbane-city-council,ice-skating-centres-gfyl,immunisation-clinics-brisbane-city-council,libraries-brisbane-city-council,licenced-venues-victoria,lifesaving-locations-victoria,loading-zones-brisbane-city-council,major-projects-victoria,markets-in-victoria,martial-arts-in-victoria-gfyl,melbourne-water-use-by-postcode,members-of-parliament-both-houses-nsw,members-of-the-legislative-assembly-nsw,members-of-the-legislative-council-nsw,mfb-locations-vic,ministers-of-the-nsw-parliament,mosman-local-government-area,mosman-rider-route,mosman-wwii-honour-roll,neighbourhood-houses-gfyl,news-feeds-mosman-municipal-council,off-street-car-parks-mosman-municipal-council,orienteering-clubs-gfyl,parking-meter-areas-brisbane-city-council,parks-and-reserves-mosman-municipal-council,parks-brisbane-city-council,personal-training-gfyl,picnic-areas-brisbane-city-council,playgrounds-brisbane-city-council,playgrounds-mosman-municipal-council,police-region-crime-statistics-victoria,police-service-area-crime-statistics-victoria,pony-clubs-in-victoria-gfyl,prison-locations-victoria,public-amenities-maintained-by-mosman-council,public-art-brisbane-city-council,public-internet-locations-vic,public-toilets-brisbane-city-council,racecourse-locations-victoria,recent-development-applications-mosman-municipal-council,recreation-groups-gfyl,recreational-fishing-spots,regional-business-centres-brisbane-city-council,reports-of-swooping-birds-mosman-municipal-council,restricted-parking-areas-brisbane-city-council,rollerskating-centres-in-victoria-gfyl,sailing-clubs-gfyl,school-locations-victoria,shadow-ministers-of-the-nsw-parliament,skate-parks-gfyl,sporting-clubs-and-organisations-gfyl,stakeboard-parks-brisbane-city-council,state-bodies-gfyl,street-names-brisbane-city-council,suburbs-and-adjoining-suburbs-brisbane-city-council,swimming-pools-brisbane-city-council,swimming-pools-gfyl,tennis-courts-brisbane-city-council,top-40-book-club-reads-brisbane-city-council,tracks-and-trails-gfyl,triathlon-clubs-gfyl,urban-water-restrictions-victoria,veterinary-services-in-mosman,victorian-microbreweries,volunteering-centres-services-and-groups-victoria,walking-groups-gfyl,ward-offices-brisbane-city-council,waste-collection-days-brisbane-city-council,waste-transfer-stations-brisbane-city-council,water-consumption-in-melbourne,water-sports-in-victoria-gfyl,wifi-hot-spots-brisbane-city-council,yoga-pilates-and-tai-chi-in-victoria-gfyl,2809cycling-in-new-south-wales-what-the-data-tells-us2809-and-related-data,act-barbecue-bbq-locations,act-tafe-locations,ausindustry-locations,austender-contract-notice-export,austender-contract-notice-export,austender-contract-notice-export,austender-contract-notice-export,austender-contract-notice-export,austender-contract-notice-export,austender-contract-notice-export,austender-contract-notice-export,australian-gas-light-company-maps,australian-gas-light-company-maps,australian-ports,australian-public-service-statistical-bulletin-2011-12,australian-public-service-statistical-bulletin-snapshot-at-december-31-2011,australian-public-service-statistical-bulletin-tables-0910,austrics-timetable-set,capital-works-call-tender-schedule,collection-item-usage-state-library-of-victoria,country-and-commodity-trade-data-spreadsheet,country-and-commodity-trade-data-spreadsheet-2,country-by-level-of-processing-trade-data-spreadsheet,crime-incident-type-and-frequency-by-capital-city-and-nationally,csiro-locations,data-from-the-oaic-public-sector-information-survey-2012,data-from-the-oaic-public-sector-information-survey-2012,data-from-the-oaic-public-sector-information-survey-2012,department-of-finance-and-deregulation-office-locations,digitised-maps,diisr-division-locations-excluding-ausindustry-enterprise-connect-and-nmi,diisr-locations,diisr-portfolio-agency-locations-excluding-csiro,distance-to-legal-service-providers-from-disadvantaged-suburbs,enterprise-connect-locations,fire-insurance-maps-sydney-block-plans-1919-1940,fire-insurance-maps-sydney-block-plans-1919-1940,first-fleet-collection,first-fleet-collection,first-fleet-maps,first-fleet-maps,freedom-of-information-annual-estimated-costs-and-staff-time-statistical-data-2011-12,freedom-of-information-quarterly-request-and-review-statistical-data-2011-12,freedom-of-information-requests-estimated-costs-and-charges-collected-1982-83-to-2011-12,higher-education-course-completions,higher-education-enrolments,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,historical-australian-government-contract-data,journey-planner-data-nt,library-catalogue-search-terms-state-library-of-victoria,location-of-act-schools,location-of-centrelink-offices,location-of-european-wasps-nests,location-of-lawyers-and-legal-service-providers-by-town,location-of-legal-assistance-service-providers,location-of-medicare-offices,location-of-medicare-offices,maps-of-the-southern-hemisphere-16th-18th-centuries,maps-of-the-southern-hemisphere-16th-18th-centuries,music-queensland,national-measurement-institute-locations,new-south-wales-officers-and-men-of-the-australian-imperial-force-a-i-f-and-the-australian-naval-for,new-south-wales-officers-and-men-of-the-australian-imperial-force-a-i-f-and-the-australian-naval-for,photographs-of-nsw-life-pre-1955,photographs-of-nsw-life-pre-1955,photographs-of-sydney-before-1885,photographs-of-sydney-before-1885,picture-queensland,plgr-28093-playgrounds-act,police-station-locations,queensland-public-libraries,rare-printed-books,rare-printed-books,real-estate-maps,regional-australia-funding-projects,sa-memory-state-library-of-south-australia,search-engine-terms-state-library-of-victoria,south-australian-photographs-state-library-of-south-australia,south-australian-sheet-music-state-library-of-south-australia,sydney-bond-store-maps-1894,sydney-bond-store-maps-1894,sydney-maps-1917,sydney-maps-1917,tafe-institute-locations-victoria,tafe-sa-campus-locations,tolt-public-toilets-act,victorian-public-library-branches-state-library-of-victoria,western-australia-public-library-network,world-war-one-photographs-by-frank-hurley,world-war-one-photographs-by-frank-hurley,citycat-timetables-brisbane-city-council,cityferry-timetables-brisbane-city-council,cost-of-salinity-to-local-infrastructure-1996-97-summary-of-component-costs-of-salinity-by-reporting,cost-of-salinity-to-local-infrastructure-1996-97-summary-of-component-costs-of-salinity-by-reporting,downstream-cost-calculator-model-and-data-for-199697-or-2001-prices,economics-of-australian-soil-conditions-199697-limiting-factor-or-relative-yield-min-of-ry_salt2000-,geographical-names-register-gnr-of-nsw,victorian-dryland-salinity-assessment-2000-d01cac_ramsar_final-xls,victorian-dryland-salinity-assessment-2000-d02cac_fauna_final-xls,victorian-dryland-salinity-assessment-2000-d03cac_fauna_dist_final-xls,victorian-dryland-salinity-assessment-2000-dc04cac_hydrol_final-xls,victorian-dryland-salinity-assessment-2000-dc05cac_wetland_final-xls,victorian-dryland-salinity-assessment-2000-dc06cac_util_final-xls,victorian-dryland-salinity-assessment-2000-dc07cac_road_final-xls,victorian-dryland-salinity-assessment-2000-dc08cac_towns_final-xls,victorian-dryland-salinity-assessment-2000-dc09cac_flora_final-xls,victorian-dryland-salinity-assessment-2000-dc10cac_flora_dist_final-xls,victorian-dryland-salinity-assessment-2000-dc12cac_infrastructure-xls,victorian-dryland-salinity-assessment-2000-dc13cac_natural_envt-xls,victorian-dryland-salinity-assessment-2000-dc14cac_agriculture-xls,victorian-dryland-salinity-assessment-2000-dc16cac_agric_cost-xls,victorian-dryland-salinity-assessment-2000-dc17cac_shallow_wt-xls,victorian-dryland-salinity-assessment-2000-dc18cac_agric_cost_time-xls,victorian-dryland-salinity-assessment-2000-dc21cac_water_resources_new-xls,victorian-dryland-salinity-assessment-2000-dc22cac_risk-xls,licensed-broadcasting-transmitter-data,nsw-crime-data,recorded-crime-dataset-nsw,crime-statistics-in-nsw-by-month,2001-02-to-2007-08-local-government-survey-victoria,2009-green-light-report,annual-statistical-reports-fire-brigades-nsw-200304,annual-statistical-reports-fire-brigades-nsw-200405,annual-statistical-reports-fire-brigades-nsw-200506,annual-statistical-reports-fire-brigades-nsw-200607,arts-on-the-map,assets-and-liabilities-of-australian-located-operations,assets-of-australian-located-operations,assets-of-australian-located-operations-by-country,assets-of-financial-institutions,back-issues-of-monthly-banking-statistics,banks-assets,banks-consolidated-group-capital,banks-consolidated-group-impaired-assets,banks-consolidated-group-off-balance-sheet-business,banks-liabilities,building-societies-selected-assets-and-liabilities,byteback2842-locations-vic,cash-management-trusts,city-of-melbourne-street-furniture-database,community-services-nsw,consolidated-exposures-immediate-and-ultimate-risk-basis,consolidated-exposures-immediate-risk-basis-foreign-claims-by-country,consolidated-exposures-immediate-risk-basis-international-claims-by-country,consolidated-exposures-ultimate-risk-basis,consolidated-exposures-ultimate-risk-basis-foreign-claims-by-country,cosolidated-exposures-immediate-risk-basis,credit-unions-selected-assets-and-liabilities,daily-net-foreign-exchange-transactions,detox-your-home,education-national-assessment-program-literacy-and-numeracy-nsw,employment-data-by-nsw-regions,excise-beer-clearance-data-updated-each-month-beer-clearance-summary-data,finance-companies-and-general-financiers-selected-assets-and-liabilities,foreign-exchange-transactions-and-holdings-of-official-reserve-assets,half-yearly-life-insurance-bulletin-december-2010,health-behaviours-in-nsw,international-liabilities-by-country-of-the-australian-located-operations-of-banks-and-rfcs,liabilities-and-assets-monthly,liabilities-and-assets-weekly,liabilities-of-australian-located-operations,life-insurance-offices-statutory-funds,managed-funds,monetary-policy-changes,money-market-corporations-selected-assets-and-liabilities,monthly-airport-traffic-data-for-top-ten-airports-january-1985-to-december-2008,monthly-banking-statistics-april-2011,monthly-banking-statistics-june-2011,monthly-banking-statistics-may-2011,open-market-operations-2009-to-current,projected-households-vic-rvic-msd-2006-2056,projected-population-by-age-and-sex-vic-rvic-msd-2006-2056,public-unit-trust,quarterly-bank-performance-statistics,quarterly-general-insurance-performance-statistics-march-2011,quarterly-superannuation-performance-march-2011,recorded-crime-dataset-nsw,residential-land-bulletin,resourcesmart-retailers,resourcesmart-retailers-vic,road-fatalities-nsw,securitisation-vehicles,selected-asset-and-liabilities-of-the-private-non-financial-sectors,seperannuation-funds-outside-life-offices,solar-report-vic,towns-in-time-victoria,vif2008-projected-population-by-5-year-age-groups-and-sex-sla-lga-ssd-sd-2006-2026,vif2008-projected-population-totals-and-components-vic-rvic-msd-2006-2056,vif2008-projected-population-totals-sla-lga-ssd-sd-2006-2026,arts-festivals-victoria,arts-organisations-victoria,arts-spaces-and-places-victoria,ausgrid-average-electricity-use,collecting-institutions-victoria,indigenous-arts-organisations-victoria,latest-coastal-weather-observations-for-coolangatta-qld,top-10-fiction-books-brisbane-city-council];
+
+
 docsdb = couch['disclosr-documents']
 
 if __name__ == "__main__":
+    orgs_list = []
+    orgs_ids = {}
     for doc in docsdb.view('app/datasets'):
+        print "   ---   "
         print doc.id
-        if doc.value['url'] != "http://data.gov.au/data/":
+
+        if doc.value['url'] != "http://data.gov.au/data/" and doc.value['agencyID'] != "qld":
+
+
             # Collect the package metadata.
-            pkg_name = doc.value['url'].replace("http://data.gov.au/dataset/",'').replace('/','');                                                                  _
-            tags = []
-            if doc.value['agencyID'] == "AGIMO":
-                if len(doc.value['metadata']["Keywords / Tags"]) > 0:
-                    if hasattr(doc.value['metadata']["Keywords / Tags"], '__iter__'):
-                        tags = tags + doc.value['metadata']["Keywords / Tags"]
+            pkg_name = filter(lambda x: x in '0123456789abcdefghijklmnopqrstuvwxyz-_',
+                              doc.value['url'].replace("http://data.gov.au/dataset/", '').replace('/', '')[:100]);
+            print pkg_name
+            if pkg_name in gooddata:
+
+                #add to or create organization using direct API
+                agency = doc.value['metadata']["Agency"]
+                if agency == "APS":
+                    agency = "Australian Public Service Commission"
+                if agency == "Shared Services, Treasury Directorate":
+                    agency = "Shared Services Procurement, Treasury Directorate"
+                if agency == "Treasury - Shared Services":
+                    agency = "Shared Services Procurement, Treasury Directorate"
+                if agency == "Territory and Municipal Services (TAMS)":
+                    agency = "Territory and Municipal Services Directorate"
+                if agency == "State Library of NSW":
+                    agency = "State Library of New South Wales"
+                org_name = name_munge(agency[:100])
+                if org_name not in orgs_list:
+                    orgs_list = ckandirect.action.organization_list()['result']
+                    #print orgs_list
+                    if org_name not in orgs_list:
+                        try:
+                            print "org not found, creating " + org_name
+                            ckandirect.action.organization_create(name=org_name, title=agency,
+                                                                  description=agency)
+                            orgs_list.append(org_name)
+                        except ckanapi.ValidationError, e:
+                            print e
+                            raise LoaderError('Unexpected status')
                     else:
-                        tags = tags + [doc.value['metadata']["Keywords / Tags"]]
-                if 'data.gov.au Category' in doc.value['metadata'].keys() and len(doc.value['metadata']['data.gov.au Category']) > 0:
-                    if hasattr(doc.value['metadata']['data.gov.au Category'], '__iter__'):
-                        tags = tags + doc.value['metadata']['data.gov.au Category']
+                        print "org found, adding dataset to " + org_name
+
+                # cache org names -> id mapping
+                if org_name not in orgs_ids:
+                    org = ckandirect.action.organization_show(id=org_name)
+                    orgs_ids[org_name] = org["result"]["id"]
+                org_id = orgs_ids[org_name]
+                print "org id is " + org_id
+                tags = []
+                creator = doc.value['metadata']["DCTERMS.Creator"]
+                if doc.value['agencyID'] == "AGIMO":
+                    if len(doc.value['metadata']["Keywords / Tags"]) > 0:
+                        if hasattr(doc.value['metadata']["Keywords / Tags"], '__iter__'):
+                            tags = tags + doc.value['metadata']["Keywords / Tags"]
+                        else:
+                            tags = tags + [doc.value['metadata']["Keywords / Tags"]]
+
+                    tags = [re.sub('[^a-zA-Z0-9-_.]', '', tag.replace('&', 'and')).lower() for tag in tags if tag]
+                    #print tags
+                    extras = []
+
+                    for extra_key in doc.value['metadata'].keys():
+                        if extra_key not in ["Description", "Content-Language", "DCTERMS.Description",
+                                             "Keywords / Tags",
+                                             "data.gov.au Category", "Download", "Permalink", "DCTERMS.Identifier"]:
+                            if doc.value['metadata'][extra_key] != None and doc.value['metadata'][extra_key] != "":
+                                extras.append([extra_key, doc.value['metadata'][extra_key]])
+
+                    package_entity = {
+                        'name': pkg_name,
+                        'title': doc.value['metadata']['DCTERMS.Title'],
+                        'url': doc.value['metadata']['DCTERMS.Source.URI'],
+                        'tags': tags, #tags are mandatory?
+                        'author': creator,
+                        'maintainer': creator,
+                        'licence_id': get_licence_id(doc.value['metadata']['DCTERMS.License']),
+                        'notes': html2text.html2text(doc.value['metadata']['Description']),
+                        'owner_org': org_id,
+                        'extras': extras
+                    }
+
+                try:
+                    #print package_entity
+                    ckan.package_register_post(package_entity)
+                except CkanApiError, e:
+                    if ckan.last_message == "{\"name\": [\"That URL is already in use.\"]}":
+                        print "package already exists"
                     else:
-                        tags = tags + [doc.value['metadata']['data.gov.au Category']]
-                tags = [re.sub('[^a-zA-Z0-9-_.]', '', tag.replace('&', 'and')).lower() for tag in tags if tag]
-                print tags
-                package_entity = {
-                    'name': pkg_name,
-                    'title': doc.value['metadata']['DCTERMS.Title'],
-                    'url': doc.value['metadata']['DCTERMS.Source.URI'],