From: Maxious <maxious@lambdacomplex.org>
Date: Mon, 23 Jan 2012 04:05:18 +0000
Subject: Handling of minister/secretary names in FOI export
X-Git-Url: https://maxious.lambdacomplex.org/git/?p=disclosr.git&a=commitdiff&h=c82c38421a63b171d9ce94168ab1f4073cf349de
---
Handling of minister/secretary names in FOI export


Former-commit-id: 4d6a601bd2ae9012300836e1ddf12bc147981e10
---


--- a/alaveteli/exportAgencies.csv.php
+++ b/alaveteli/exportAgencies.csv.php
@@ -1,6 +1,21 @@
 <?php
 
 include_once("../include/common.inc.php");
+
+function shortName($name) {
+    $name = trim($name);
+    if (strstr($name,"Minister ") || strstr($name,"Treasurer") || strstr($name,"Parliamentary Secretary")) {
+        $badWords = Array ("Assisting the Prime Minister on","Assisting on"," the "," of "," for "," on "," and "," to ",","," ","'","`");
+        return str_replace($badWords,"",$name);
+    }
+            
+    else {
+    $out = Array();
+    preg_match_all('/[A-Z]/', $name, $out);
+    return implode("", $out[0]);
+    }
+}
+
 setlocale(LC_CTYPE, 'C');
 
 $headers = Array("#id", "name", "request_email", "short_name", "notes", "publication_scheme", "home_page", "tag_string");
@@ -16,6 +31,7 @@
     }
 } catch (SetteeRestClientException $e) {
     setteErrorHandler($e);
+    die();
 }
 
 $foiEmail = Array();
@@ -27,11 +43,12 @@
     }
 } catch (SetteeRestClientException $e) {
     setteErrorHandler($e);
+    die();
 }
 
 $fp = fopen('php://output', 'w');
 if ($fp && $db) {
-    header('Content-Type: text/csv');
+    header('Content-Type: text/csv; charset=utf-8');
     header('Content-Disposition: attachment; filename="export.' . date("c") . '.csv"');
     header('Pragma: no-cache');
     header('Expires: 0');
@@ -40,8 +57,8 @@
         $agencies = $db->get_view("app", "byCanonicalName", null, true)->rows;
         //print_r($rows);
         foreach ($agencies as $agency) {
-               // print_r($agency);
-               
+            // print_r($agency);
+
             if (isset($agency->value->foiEmail) && $agency->value->foiEmail != "null" && !isset($agency->value->status)) {
                 $row = Array();
                 $row["#id"] = $agency->id;
@@ -58,9 +75,7 @@
                 if (isset($agency->value->shortName)) {
                     $row["short_name"] = $agency->value->shortName;
                 } else {
-                    $out = Array();
-                    preg_match_all('/[A-Z]/', trim($agency->value->name), $out);
-                    $row["short_name"] = implode("", $out[0]);
+                    $row["short_name"] = shortName($agency->value->name);
                 }
                 $row["notes"] = "";
                 $row["publication_scheme"] = (isset($agency->value->infoPublicationSchemeURL) ? $agency->value->infoPublicationSchemeURL : "");
@@ -75,8 +90,8 @@
 
                 if (isset($agency->value->foiBodies)) {
                     foreach ($agency->value->foiBodies as $foiBody) {
-                        $row['name'] = $foiBody;
-                        $row['short_name'] = "";
+                        $row['name'] = iconv("UTF-8", "ASCII//TRANSLIT",$foiBody);
+                        $row["short_name"] = shortName($foiBody);
                         fputcsv($fp, array_values($row));
                     }
                 }

--- a/include/common.inc.php
+++ b/include/common.inc.php
@@ -62,7 +62,3 @@
      }
 }
 
-?>
-
-
-

--- a/include/couchdb.inc.php
+++ b/include/couchdb.inc.php
@@ -86,5 +86,3 @@
 function setteErrorHandler($e) {
     echo $e->getMessage() . "<br>" . PHP_EOL;
 }
-?>
-

--- a/include/template.inc.php
+++ b/include/template.inc.php
@@ -74,5 +74,3 @@
     </html>
 
 <?php }
-?>
-

--- /dev/null
+++ b/scrape.py
@@ -1,1 +1,65 @@
+#http://packages.python.org/CouchDB/client.html
+import couchdb
+import urllib2
+from BeautifulSoup import BeautifulSoup
+import re
 
+couch = couchdb.Server('http://192.168.1.148:5984/')
+
+# select database
+agencydb = couch['disclosr-agencies']
+
+for row in agencydb.view('app/getScrapeRequired'): #not recently scraped agencies view?
+    agency = agencydb.get(row.id)
+    print agency['agencyName']
+
+#http://diveintopython.org/http_web_services/etags.html
+class NotModifiedHandler(urllib2.BaseHandler):  
+    def http_error_304(self, req, fp, code, message, headers):
+        addinfourl = urllib2.addinfourl(fp, headers, req.get_full_url())
+        addinfourl.code = code
+        return addinfourl
+
+def scrapeAndStore(URL, depth, agency):
+    URL = "http://www.hole.fi/jajvirta/weblog/"
+    req = urllib2.Request(URL)
+    
+    #if there is a previous version sotred in couchdb, load caching helper tags
+    if etag:
+        req.add_header("If-None-Match", etag)
+    if last_modified:
+        req.add_header("If-Modified-Since", last_modified)
+     
+    opener = urllib2.build_opener(NotModifiedHandler())
+    url_handle = opener.open(req)
+    headers = url_handle.info() # the addinfourls have the .info() too
+    etag = headers.getheader("ETag")
+    last_modified = headers.getheader("Last-Modified") 
+    web_server = headers.getheader("Server") 
+    file_size = headers.getheader("Content-Length") 
+    mime_type = headers.getheader("Content-Type") 
+     
+    if hasattr(url_handle, 'code') 
+        if url_handle.code == 304:
+            print "the web page has not been modified"
+        else: 
+            #do scraping
+            html = url_handle.read()
+            # http://www.crummy.com/software/BeautifulSoup/documentation.html
+            soup = BeautifulSoup(html)
+        links = soup.findAll('a') # soup.findAll('a', id=re.compile("^p-"))
+        for link in links:
+            print link['href']
+            #for each unique link
+            #if html mimetype
+            # go down X levels,
+            # diff with last stored attachment, store in document
+            #if not
+            #   remember to save parentURL and title (link text that lead to document)
+    
+    #store as attachment epoch-filename
+    else:
+        print "error %s in downloading %s", url_handle.code, URL
+        #record/alert error to error database
+    
+    

--- a/unimplemented/scrape.py
+++ /dev/null
@@ -1,64 +1,1 @@
-#http://packages.python.org/CouchDB/client.html
-import couchdb
-import urllib2
-from BeautifulSoup import BeautifulSoup
-import re
 
-couch = couchdb.Server() # Assuming localhost:5984
-# If your CouchDB server is running elsewhere, set it up like this:
-# couch = couchdb.Server('http://example.com:5984/')
-
-# select database
-agencydb = couch['disclosr-agencies']
-
-for row in agencydb.view('app/getScrapeRequired'): #not recently scraped agencies view?
-    agency = agencydb.get(row.id)
-    print agency['agencyName']
-
-#http://diveintopython.org/http_web_services/etags.html
-class NotModifiedHandler(urllib2.BaseHandler):  
-    def http_error_304(self, req, fp, code, message, headers):
-        addinfourl = urllib2.addinfourl(fp, headers, req.get_full_url())
-        addinfourl.code = code
-        return addinfourl
-
-def scrapeAndStore(URL, depth, agency):
-    URL = "http://www.hole.fi/jajvirta/weblog/"
-    req = urllib2.Request(URL)
-    
-    #if there is a previous version sotred in couchdb, load caching helper tags
-    if etag:
-        req.add_header("If-None-Match", etag)
-    if last_modified:
-        req.add_header("If-Modified-Since", last_modified)
-     
-    opener = urllib2.build_opener(NotModifiedHandler())
-    url_handle = opener.open(req)
-    headers = url_handle.info() # the addinfourls have the .info() too
-    etag = headers.getheader("ETag")
-    last_modified = headers.getheader("Last-Modified") 
-    web_server = headers.getheader("Server") 
-    file_size = headers.getheader("Content-Length") 
-    mime_type = headers.getheader("Content-Type") 
-     
-    if hasattr(url_handle, 'code') and url_handle.code == 304:
-        print "the web page has not been modified"
-    else:
-        print "error %s in downloading %s", url_handle.code, URL
-        #record/alert error to error database
-    
-    #do scraping
-    html = ?
-    # http://www.crummy.com/software/BeautifulSoup/documentation.html
-    soup = BeautifulSoup(html)
-links = soup.findAll('a') # soup.findAll('a', id=re.compile("^p-"))
-for link in links:
-    print link['href']
-    #for each unique link
-    #if html mimetype
-    # go down X levels,
-    # diff with last stored attachment, store in document
-    #if not
-    #   remember to save parentURL and title (link text that lead to document)
-    
-    #store as attachment epoch-filename