add production domain name
add production domain name


Former-commit-id: be7a82ae478776c6067cb44055f74cb1014df8fd

--- a/admin/refreshDesignDoc.php
+++ b/admin/refreshDesignDoc.php
@@ -1,7 +1,177 @@
 <?php
 
 require_once '../include/common.inc.php';
+//function createFOIDocumentsDesignDoc() {
+
+$foidb = $server->get_db('disclosr-foidocuments');
+    $obj = new stdClass();
+    $obj->_id = "_design/" . urlencode("app");
+    $obj->language = "javascript";
+    $obj->views->all->map = "function(doc) {   emit(doc._id, doc); };";
+    $obj->views->byDate->map = "function(doc) {   emit(doc.date, doc); };";
+
+    // allow safe updates (even if slightly slower due to extra: rev-detection check).
+ $foidb->save($obj, true);
+
+
+function createDocumentsDesignDoc() {
+    /*
+    global $db;
+    $obj = new stdClass();
+    $obj->_id = "_design/" . urlencode("app");
+    $obj->language = "javascript";
+    $obj->views->all->map = "function(doc) {   emit(doc._id, doc); };";
+    $obj->views->byABN->map = "function(doc) {   emit(doc.abn, doc); };";
+ "views": {
+      "web_server": {
+      "map": "function(doc) {\n  emit(doc.web_server, 1);\n}",
+      "reduce": "function (key, values, rereduce) {\n    return sum(values);\n}"
+      },
+      "byAgency": {
+      "map": "function(doc) {\n  emit(doc.agencyID, 1);\n}",
+      "reduce": "function (key, values, rereduce) {\n    return sum(values);\n}"
+      },
+      "byURL": {
+      "map": "function(doc) {\n  emit(doc.url, doc);\n}"
+      },
+      "agency": {
+      "map": "function(doc) {\n  emit(doc.agencyID, doc);\n}"
+      },
+      "byWebServer": {
+      "map": "function(doc) {\n  emit(doc.web_server, doc);\n}"
+      },
+      "getValidationRequired": {
+      "map": "function(doc) {\nif (doc.mime_type == \"text/html\" \n&& typeof(doc.validation) == \"undefined\") {\n  emit(doc._id, doc._attachments);\n}\n}"
+      }
+      } */
+}
+
+//function createAgencyDesignDoc() {
 $db = $server->get_db('disclosr-agencies');
-createAgencyDesignDoc();
+    $obj = new stdClass();
+    $obj->_id = "_design/" . urlencode("app");
+    $obj->language = "javascript";
+    $obj->views->all->map = "function(doc) {   emit(doc._id, doc); };";
+    $obj->views->byABN->map = "function(doc) {   emit(doc.abn, doc); };";
+    $obj->views->byCanonicalName->map = "function(doc) {  
+            if (doc.parentOrg || doc.orgType == 'FMA-DepartmentOfState') {
+        emit(doc.name, doc); 
+        }
+};";
+    $obj->views->byDeptStateName->map = "function(doc) {  
+            if (doc.orgType == 'FMA-DepartmentOfState') {
+        emit(doc.name, doc._id); 
+        }
+};";
+    $obj->views->parentOrgs->map = "function(doc) {
+            if (doc.parentOrg) {
+        emit(doc._id, doc.parentOrg);
+        }
+};";
+    $obj->views->byName->map = 'function(doc) { 
+        if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") {
+        emit(doc.name, doc._id); 
+if (typeof(doc.shortName) != "undefined" && doc.shortName != doc.name) {
+       	 emit(doc.shortName, doc._id); 
+}
+ for (name in doc.otherNames) {
+if (doc.otherNames[name] != "" && doc.otherNames[name] != doc.name) {
+       	 emit(doc.otherNames[name], doc._id); 
+}
+        }
+ for (name in doc.foiBodies) {
+if (doc.foiBodies[name] != "" && doc.foiBodies[name] != doc.name) {
+       	 emit(doc.foiBodies[name], doc._id); 
+}
+        }
+        }
+};';
+
+    $obj->views->foiEmails->map = "function(doc) {  
+        emit(doc._id, doc.foiEmail);
+};";
+
+    $obj->views->byLastModified->map = "function(doc) {   emit(doc.metadata.lastModified, doc); }";
+    $obj->views->getActive->map = 'function(doc) { if (doc.status == "active") {  emit(doc._id, doc); } };';
+    $obj->views->getSuspended->map = 'function(doc) { if (doc.status == "suspended") {  emit(doc._id, doc); } };';
+    $obj->views->getScrapeRequired->map = "function(doc) {   
+
+var lastScrape = Date.parse(doc.metadata.lastScraped);
+
+var today = new Date();
+
+if (!lastScrape || lastScrape.getTime() + 1000 != today.getTime()) {
+ emit(doc._id, doc); 
+}
+
+};";
+    $obj->views->showNamesABNs->map = "function(doc) {   emit(doc._id, {name: doc.name, abn: doc.abn}); };";
+    $obj->views->getConflicts->map = "function(doc) {
+  if (doc._conflicts) {
+    emit(null, [doc._rev].concat(doc._conflicts));
+  }
+}";
+    // http://stackoverflow.com/questions/646628/javascript-startswith
+    $obj->views->score->map = 'if(!String.prototype.startsWith){
+    String.prototype.startsWith = function (str) {
+        return !this.indexOf(str);
+    }
+}
+
+function(doc) {
+    count = 0;
+    if (doc["status"] != "suspended") {
+        for(var propName in doc) {
+            if(typeof(doc[propName]) != "undefined" && doc[propName] != "") {
+                count++;
+            }
+        }
+        portfolio = doc.parentOrg;
+        if (doc.orgType == "FMA-DepartmentOfState") {
+            portfolio = doc._id;
+        }
+        if (doc.orgType == "Court-Commonwealth" || doc.orgType == "FMA-DepartmentOfParliament") {
+            portfolio = doc.orgType;
+        }
+        emit(count+doc._id, {id:doc._id, name: doc.name, score:count, orgType: doc.orgType, portfolio:portfolio});
+    }
+}';
+    $obj->views->scoreHas->map = 'if(!String.prototype.startsWith){
+    String.prototype.startsWith = function (str) {
+        return !this.indexOf(str);
+    }
+}
+if(!String.prototype.endsWith){
+	String.prototype.endsWith = function(suffix) {
+	    return this.indexOf(suffix, this.length - suffix.length) !== -1;
+	};
+}
+function(doc) {
+if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") {
+for(var propName in doc) {
+      if(typeof(doc[propName]) != "undefined" && (propName.startsWith("has") || propName.endsWith("URL"))) {
+  	emit(propName, 1);
+	}
+}
+  emit("total", 1);
+  }
+}';
+    $obj->views->scoreHas->reduce = 'function (key, values, rereduce) {
+    return sum(values);
+}';
+    $obj->views->fieldNames->map = '
+function(doc) {
+for(var propName in doc) {
+     	emit(propName, doc._id);
+	}
+  
+}';
+    $obj->views->fieldNames->reduce = 'function (key, values, rereduce) {
+    return values.length;
+}';
+    // allow safe updates (even if slightly slower due to extra: rev-detection check).
+ $db->save($obj, true);
+
+
 ?>
 

--- a/documents/genericScrapers.py
+++ b/documents/genericScrapers.py
@@ -3,19 +3,64 @@
 import scrape
 from bs4 import BeautifulSoup
 import parsedatetime as pdt
+from time import mktime
+from datetime import datetime
+import feedparser
 import abc
-class GenericOAICDisclogScraper(object):
-	__metaclass__ = abc.ABCMeta
+
+class GenericDisclogScraper(object):
+        __metaclass__ = abc.ABCMeta
+	agencyID = None
+	disclogURL = None
+        def getAgencyID(self):
+                """ disclosr agency id """
+		if self.agencyID == None:
+			self.agencyID = os.path.basename(sys.argv[0]).replace(".py","")
+                return self.agencyID
+
+        def getURL(self):
+                """ disclog URL"""
+		if self.disclogURL == None:
+			agency = scrape.agencydb.get(self.getAgencyID())
+			self.disclogURL = agency['FOIDocumentsURL']
+                return self.disclogURL
+
 	@abc.abstractmethod
-	def getAgencyID(self):
-		""" disclosr agency id """
+	def doScrape(self):
+		""" do the scraping """
 		return
 
-	@abc.abstractmethod
-	def getURL(self):
-		""" disclog URL"""
+
+
+class GenericRSSDisclogScraper(GenericDisclogScraper):
+        def getDescription(self, entry, doc):
+                """ get description from rss entry"""
+                doc['description'] = entry.summary
 		return
 
+       	def doScrape(self):
+               	foidocsdb = scrape.couch['disclosr-foidocuments']
+                (url,mime_type,content) = scrape.fetchURL(scrape.docsdb, self.getURL(), "foidocuments", self.getAgencyID())
+		feed = feedparser.parse(content)		
+		for entry in feed.entries:
+			#print entry
+			print entry.id
+			hash = scrape.mkhash(entry.id)
+			#print hash
+		  	doc = foidocsdb.get(hash)
+			#print doc
+			if doc == None:
+                        	print "saving"
+				edate = datetime.fromtimestamp(mktime( entry.published_parsed)).strftime("%Y-%m-%d")
+                                doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': entry.link, 'docID': entry.id,
+                                "date": edate,"title": entry.title}
+				self.getDescription(entry, doc)
+                                foidocsdb.save(doc)
+                        else:
+                        	print "already saved"			
+
+class GenericOAICDisclogScraper(GenericDisclogScraper):
+        __metaclass__ = abc.ABCMeta
 	@abc.abstractmethod
 	def getColumns(self,columns):
 		""" rearranges columns if required """
@@ -42,7 +87,7 @@
 						doc = foidocsdb.get(hash)
 						descriptiontxt = ""
 						for string in description.stripped_strings:
-							descriptiontxt = descriptiontxt + string
+							descriptiontxt = descriptiontxt + " \n" + string
 							
 						if doc == None:
 							print "saving"

--- a/documents/index.php
+++ b/documents/index.php
@@ -10,8 +10,8 @@
 $agenciesdb = $server->get_db('disclosr-agencies');
 
 $idtoname = Array();
-foreach ($agenciesdb->get_view("app", "byName")->rows as $row) {
-    $idtoname[$row->value] = trim($row->key);
+foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) {
+    $idtoname[$row->id] = trim($row->value->name);
 }
 $foidocsdb = $server->get_db('disclosr-foidocuments');
 try {
@@ -34,3 +34,4 @@
 }
 include_footer_documents();
 ?>
+

--- a/documents/scrapers/3cd40b1240e987cbcd3f0e67054ce259.py
+++ b/documents/scrapers/3cd40b1240e987cbcd3f0e67054ce259.py
@@ -5,12 +5,6 @@
 
 #http://www.doughellmann.com/PyMOTW/abc/
 class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
-	def getAgencyID(self):
-		return "3cd40b1240e987cbcd3f0e67054ce259"
-
-	def getURL(self):
-		return "http://www.apvma.gov.au/about/foi/disclosure/index.php"
-
 	def getColumns(self,columns):
 		(id, date, description, title, notes) = columns
 		return (id, date, description, title, notes)
@@ -19,3 +13,4 @@
     print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
     print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
     ScraperImplementation().doScrape()
+

--- a/documents/scrapers/8c9421f852c441910bf1d93a57b31d64.py
+++ b/documents/scrapers/8c9421f852c441910bf1d93a57b31d64.py
@@ -5,12 +5,6 @@
 
 #http://www.doughellmann.com/PyMOTW/abc/
 class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
-        def getAgencyID(self):
-                return "8c9421f852c441910bf1d93a57b31d64"
-
-        def getURL(self):
-                return "http://www.daff.gov.au/about/foi/ips/disclosure-log"
-
         def getColumns(self,columns):
                 (id, date, title, description, notes) = columns
                 return (id, date, description, title, notes)

--- a/documents/scrapers/be9996f0ac58f71f23d074e82d44ead3.py
+++ b/documents/scrapers/be9996f0ac58f71f23d074e82d44ead3.py
@@ -1,11 +1,42 @@
 import sys,os
 sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+#RSS feed not detailed
 import scrape
-foidocsdb = scrape.couch['disclosr-foidocuments']
-
-import feedparser
-feed = feedparser.parse( "http://foi.deewr.gov.au/disclosure-log/rss")
-print feed.entries[0]
-#foreach feed.entries
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericRSSDisclogScraper):
+	def getDescription(self,entry,doc):
+		(url,mime_type,content) = scrape.fetchURL(scrape.docsdb, entry.link, "foidocuments", self.getAgencyID(), False)
+                if content != None:
+                        if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type =="application/xml":
+                        # http://www.crummy.com/software/BeautifulSoup/documentation.html
+                               	soup = BeautifulSoup(content)
+				links = []
+				description = ""
+				dldivs = soup.find('div',class_="download")
+				if dldivs != None:
+                             		for atag in dldivs.find_all("a"):
+                                		if atag.has_key('href'):
+                                        		links.append(scrape.fullurl(url,atag['href']))
+				nodldivs = soup.find('div',class_="incompleteNotification")
+				if nodldivs != None and nodldivs.stripped_strings != None:
+                                      	for text in nodldivs.stripped_strings:
+	                                        description = description + text
+                               	for row in soup.table.find_all('tr'):
+					if row != None:
+						description = description + "\n" + row.find('th').string + ": " 
+						for text in row.find('div').stripped_strings:
+							 description = description + text
+				if links != []:
+					doc.update({'links': links})
+				if description != "":
+					doc.update({ 'description': description})
 
 
+if __name__ == '__main__':
+    print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericRSSDisclogScraper)
+    print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericRSSDisclogScraper)
+    ScraperImplementation().doScrape()
+
+

--- a/documents/scrapers/e2a845e55bc9986e6c75c5ad2c508b8d.py
+++ b/documents/scrapers/e2a845e55bc9986e6c75c5ad2c508b8d.py
@@ -1,1 +1,18 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+#RSS feed not detailed
+
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericRSSDisclogScraper):
+        def getColumns(self,columns):
+                (id, date, title, description, notes) = columns
+                return (id, date, description, title, notes)
+
+if __name__ == '__main__':
+    print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericRSSDisclogScraper)
+    print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericRSSDisclogScraper)
+    ScraperImplementation().doScrape()
+
 www.finance.gov.au/foi/disclosure-log/foi-rss.xml
+

--- a/documents/scrapers/rtk.py
+++ b/documents/scrapers/rtk.py
@@ -1,1 +1,18 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+#RSS feed not detailed
+
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericRSSDisclogScraper):
+        def getColumns(self,columns):
+                (id, date, title, description, notes) = columns
+                return (id, date, description, title, notes)
+
+if __name__ == '__main__':
+    print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericRSSDisclogScraper)
+    print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericRSSDisclogScraper)
+    ScraperImplementation().doScrape()
+
 http://www.righttoknow.org.au/feed/search/%20(latest_status:successful%20OR%20latest_status:partially_successful)
+

--- a/documents/template.inc.php
+++ b/documents/template.inc.php
@@ -69,7 +69,7 @@
 
             </p>
             <ul class="nav">
-              <li class="active"><a href="#">Home</a></li>
+              <li><a href="index.php">Home</a></li>
               <li><a href="disclogsList.php">List of Disclosure Logs</a></li>
               <li><a href="about.php">About</a></li>
               
@@ -127,13 +127,21 @@
 }
 
 function displayLogEntry($row, $idtoname) {
-    echo "<div><h2>".$row->value->date.": ".$row->value->title." (".$idtoname[$row->value->agencyID].")</h2>
-    <p>".$row->value->description." <br>Note: ".$row->value->notes."</p>";
+    echo "<div><h2>".$row->value->date.": ".$row->value->title." (".$idtoname[$row->value->agencyID].")</h2> <p>".str_replace("\n","<br>",$row->value->description);
+if (isset($row->value->notes)) {
+echo " <br>Note: ".$row->value->notes;
+}
+echo "</p>";
+
+if (isset($row->value->links)){
 echo "<h3>Links/Documents</h3><ul>";
 foreach ($row->value->links as $link) {
     echo "<li><a href='$link'>".$link."</a></li>";
 }
+
         echo "</ul>";
+}
         echo "<small><A href='".$row->value->url."'>View original source...</a> ID: ".$row->value->docID."</small>";
 echo"</div>";
 }
+

--- a/include/common.inc.php
+++ b/include/common.inc.php
@@ -8,6 +8,7 @@
         || strstr($_SERVER['PHP_SELF'], "lib/")
         || strstr($_SERVER['PHP_SELF'], "include/")
         || strstr($_SERVER['PHP_SELF'], "documents/")
+	|| $_SERVER['SERVER_NAME'] == "disclosurelo.gs"
         )
     $basePath = "../";
 

--- a/include/couchdb.inc.php
+++ b/include/couchdb.inc.php
@@ -3,158 +3,6 @@
 include $basePath . "schemas/schemas.inc.php";
 
 require ($basePath . 'couchdb/settee/src/settee.php');
-
-function createDocumentsDesignDoc() {
-    /* "views": {
-      "web_server": {
-      "map": "function(doc) {\n  emit(doc.web_server, 1);\n}",
-      "reduce": "function (key, values, rereduce) {\n    return sum(values);\n}"
-      },
-      "byAgency": {
-      "map": "function(doc) {\n  emit(doc.agencyID, 1);\n}",
-      "reduce": "function (key, values, rereduce) {\n    return sum(values);\n}"
-      },
-      "byURL": {
-      "map": "function(doc) {\n  emit(doc.url, doc);\n}"
-      },
-      "agency": {
-      "map": "function(doc) {\n  emit(doc.agencyID, doc);\n}"
-      },
-      "byWebServer": {
-      "map": "function(doc) {\n  emit(doc.web_server, doc);\n}"
-      },
-      "getValidationRequired": {
-      "map": "function(doc) {\nif (doc.mime_type == \"text/html\" \n&& typeof(doc.validation) == \"undefined\") {\n  emit(doc._id, doc._attachments);\n}\n}"
-      }
-      } */
-}
-
-function createAgencyDesignDoc() {
-    global $db;
-    $obj = new stdClass();
-    $obj->_id = "_design/" . urlencode("app");
-    $obj->language = "javascript";
-    $obj->views->all->map = "function(doc) {   emit(doc._id, doc); };";
-    $obj->views->byABN->map = "function(doc) {   emit(doc.abn, doc); };";
-    $obj->views->byCanonicalName->map = "function(doc) {  
-            if (doc.parentOrg || doc.orgType == 'FMA-DepartmentOfState') {
-        emit(doc.name, doc); 
-        }
-};";
-    $obj->views->byDeptStateName->map = "function(doc) {  
-            if (doc.orgType == 'FMA-DepartmentOfState') {
-        emit(doc.name, doc._id); 
-        }
-};";
-    $obj->views->parentOrgs->map = "function(doc) {
-            if (doc.parentOrg) {
-        emit(doc._id, doc.parentOrg);
-        }
-};";
-    $obj->views->byName->map = 'function(doc) { 
-        if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") {
-        emit(doc.name, doc._id); 
-if (typeof(doc.shortName) != "undefined" && doc.shortName != doc.name) {
-       	 emit(doc.shortName, doc._id); 
-}
- for (name in doc.otherNames) {
-if (doc.otherNames[name] != "" && doc.otherNames[name] != doc.name) {
-       	 emit(doc.otherNames[name], doc._id); 
-}
-        }
- for (name in doc.foiBodies) {
-if (doc.foiBodies[name] != "" && doc.foiBodies[name] != doc.name) {
-       	 emit(doc.foiBodies[name], doc._id); 
-}
-        }
-        }
-};';
-
-    $obj->views->foiEmails->map = "function(doc) {  
-        emit(doc._id, doc.foiEmail);
-};";
-
-    $obj->views->byLastModified->map = "function(doc) {   emit(doc.metadata.lastModified, doc); }";
-    $obj->views->getActive->map = 'function(doc) { if (doc.status == "active") {  emit(doc._id, doc); } };';
-    $obj->views->getSuspended->map = 'function(doc) { if (doc.status == "suspended") {  emit(doc._id, doc); } };';
-    $obj->views->getScrapeRequired->map = "function(doc) {   
-
-var lastScrape = Date.parse(doc.metadata.lastScraped);
-
-var today = new Date();
-
-if (!lastScrape || lastScrape.getTime() + 1000 != today.getTime()) {
- emit(doc._id, doc); 
-}
-
-};";
-    $obj->views->showNamesABNs->map = "function(doc) {   emit(doc._id, {name: doc.name, abn: doc.abn}); };";
-    $obj->views->getConflicts->map = "function(doc) {
-  if (doc._conflicts) {
-    emit(null, [doc._rev].concat(doc._conflicts));
-  }
-}";
-    // http://stackoverflow.com/questions/646628/javascript-startswith
-    $obj->views->score->map = 'if(!String.prototype.startsWith){
-    String.prototype.startsWith = function (str) {
-        return !this.indexOf(str);
-    }
-}
-
-function(doc) {
-    count = 0;
-    if (doc["status"] != "suspended") {
-        for(var propName in doc) {
-            if(typeof(doc[propName]) != "undefined" && doc[propName] != "") {
-                count++;
-            }
-        }
-        portfolio = doc.parentOrg;
-        if (doc.orgType == "FMA-DepartmentOfState") {
-            portfolio = doc._id;
-        }
-        if (doc.orgType == "Court-Commonwealth" || doc.orgType == "FMA-DepartmentOfParliament") {
-            portfolio = doc.orgType;
-        }
-        emit(count+doc._id, {id:doc._id, name: doc.name, score:count, orgType: doc.orgType, portfolio:portfolio});
-    }
-}';
-    $obj->views->scoreHas->map = 'if(!String.prototype.startsWith){
-    String.prototype.startsWith = function (str) {
-        return !this.indexOf(str);
-    }
-}
-if(!String.prototype.endsWith){
-	String.prototype.endsWith = function(suffix) {
-	    return this.indexOf(suffix, this.length - suffix.length) !== -1;
-	};
-}
-function(doc) {
-if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") {
-for(var propName in doc) {
-      if(typeof(doc[propName]) != "undefined" && (propName.startsWith("has") || propName.endsWith("URL"))) {
-  	emit(propName, 1);
-	}
-}
-  emit("total", 1);
-  }
-}';
-    $obj->views->scoreHas->reduce = 'function (key, values, rereduce) {
-    return sum(values);
-}';
-    $obj->views->fieldNames->map = '
-function(doc) {
-for(var propName in doc) {
-     	emit(propName, doc._id);
-	}
-  
-}';
-    $obj->views->fieldNames->reduce = 'function (key, values, rereduce) {
-    return values.length;
-}';
-    // allow safe updates (even if slightly slower due to extra: rev-detection check).
-    return $db->save($obj, true);
-}
 
 if (php_uname('n') == "vanille") {
     $serverAddr = 'http://192.168.178.21:5984/';