stats reduce view
stats reduce view


Former-commit-id: 501735ca670b5f69a7b39c250edd14003970c2ae

<?php <?php
   
include_once("../include/common.inc.php"); include_once("../include/common.inc.php");
require($basePath . 'lib/phpquery/phpQuery/phpQuery.php'); require($basePath . 'lib/phpquery/phpQuery/phpQuery.php');
   
setlocale(LC_CTYPE, 'C'); setlocale(LC_CTYPE, 'C');
   
   
$db = $server->get_db('disclosr-agencies'); $db = $server->get_db('disclosr-agencies');
  // metatags
  try {
  $agencies = $db->get_view("app", "byCanonicalName", null, true)->rows;
  //print_r($rows);
  foreach ($agencies as $agency) {
  if (isset($agency->value->scrapeDepth)) {
  unset($agency->value->scrapeDepth);
  }
   
  if (isset($agency->value->lastScraped)) {
  unset($agency->value->lastScraped);
  }
  $db->save($agency->value);
  echo "<hr>";
  flush();
  }
  } catch (SetteeRestClientException $e) {
  setteErrorHandler($e);
  }
  // metatags
try { try {
$agencies = $db->get_view("app", "byCanonicalName", null, true)->rows; $agencies = $db->get_view("app", "byCanonicalName", null, true)->rows;
//print_r($rows); //print_r($rows);
foreach ($agencies as $agency) { foreach ($agencies as $agency) {
//echo $agency->value->name . " ".$agency->value->website."<br />\n"; //echo $agency->value->name . " ".$agency->value->website."<br />\n";
// print_r($agency); // print_r($agency);
//hasRestricitiveLicence" hasRestrictiveLicense -> has Restrictive Licence //hasRestricitiveLicence" hasRestrictiveLicense -> has Restrictive Licence
// "hasYoutube" -> Tube // "hasYoutube" -> Tube
// "comment" -> "comments" // "comment" -> "comments"
if (!isset($agency->value->metaTags) && isset($agency->value->website)) { if (!isset($agency->value->metaTags) && isset($agency->value->website)) {
echo $agency->value->name . " ".$agency->value->website."<br />\n"; echo $agency->value->name . " " . $agency->value->website . "<br />\n";
$agency->value->metaTags = Array(); $agency->value->metaTags = Array();
$request = Requests::get($agency->value->website); $request = Requests::get($agency->value->website);
$html = phpQuery::newDocumentHTML($request->body); $html = phpQuery::newDocumentHTML($request->body);
phpQuery::selectDocument($html); phpQuery::selectDocument($html);
foreach (pq('meta')->elements as $meta) { foreach (pq('meta')->elements as $meta) {
$tagName = $meta->getAttribute('name');; $tagName = $meta->getAttribute('name');
  ;
$content = $meta->getAttribute('content'); $content = $meta->getAttribute('content');
if ($tagName != "") { if ($tagName != "") {
echo "$tagName == $content <br>\n"; echo "$tagName == $content <br>\n";
$agency->value->metaTags[$tagName] = $content; $agency->value->metaTags[$tagName] = $content;
} }
} }
//print_r($agency->value->metaTags); //print_r($agency->value->metaTags);
$db->save($agency->value); $db->save($agency->value);
echo "<hr>"; echo "<hr>";
flush(); flush();
} }
} }
} catch (SetteeRestClientException $e) { } catch (SetteeRestClientException $e) {
setteErrorHandler($e); setteErrorHandler($e);
} }
?> ?>
   
<?php <?php
   
require_once '../include/common.inc.php'; require_once '../include/common.inc.php';
   
$db = $server->get_db('disclosr-agencies'); $db = $server->get_db('disclosr-agencies');
$rows = $db->get_view("app", "byName")->rows; $rows = $db->get_view("app", "byName")->rows;
$nametoid = Array(); $nametoid = Array();
$accounts = Array(); $accounts = Array();
foreach ($rows as $row) { foreach ($rows as $row) {
$nametoid[trim($row->key)] = $row->value; $nametoid[trim($row->key)] = $row->value;
} }
   
function extractCSVAccounts($url, $nameField, $accountField, $filter) { function extractCSVAccounts($url, $nameField, $accountField, $filter) {
global $accounts, $nametoid; global $accounts, $nametoid;
$request = Requests::get($url); $request = Requests::get($url);
echo $url; echo $url;
$Data = str_getcsv($request->body, "\n"); //parse the rows $Data = str_getcsv($request->body, "\n"); //parse the rows
$headers = Array(); $headers = Array();
foreach ($Data as $num => $line) { foreach ($Data as $num => $line) {
$Row = str_getcsv($line, ","); $Row = str_getcsv($line, ",");
if ($num == 0) { if ($num == 0) {
$headers = $Row; $headers = $Row;
print_r($headers); print_r($headers);
} else { } else {
if (isset($Row[array_search($nameField, $headers)])) { if (isset($Row[array_search($nameField, $headers)])) {
$agencyName = $Row[array_search($nameField, $headers)]; $agencyName = $Row[array_search($nameField, $headers)];
if (!in_array(trim($agencyName), array_keys($nametoid))) { if (!in_array(trim($agencyName), array_keys($nametoid))) {
echo "$agencyName missing" . PHP_EOL; echo "$agencyName missing" . PHP_EOL;
} else { } else {
echo $Row[array_search($nameField, $headers)] . PHP_EOL; echo $Row[array_search($nameField, $headers)] . PHP_EOL;
$accounts[$nametoid[trim($agencyName)]]["rtkURLs"][$agencyName] = 'http://www.righttoknow.org.au/body/'.$Row[array_search($accountField, $headers)]; $accounts[$nametoid[trim($agencyName)]]["rtkURLs"][$agencyName] = 'http://www.righttoknow.org.au/body/'.$Row[array_search($accountField, $headers)];
  $accounts[$nametoid[trim($agencyName)]]["rtkDescriptions"][$agencyName] = $Row[array_search("Notes", $headers)];
} }
} else { } else {
echo "error finding any agency" . $line . PHP_EOL; echo "error finding any agency" . $line . PHP_EOL;
} }
} }
} }
} }
   
extractCSVAccounts("http://www.righttoknow.org.au/body/all-authorities.csv","Agency","URL name"); extractCSVAccounts("http://www.righttoknow.org.au/body/all-authorities.csv","Agency","URL name");
print_r($accounts); //print_r($accounts);
/* foreach ($accounts as $id => $accountTypes) { foreach ($accounts as $id => $allvalues) {
echo $id . "<br>" . PHP_EOL; echo $id . "<br>" . PHP_EOL;
$doc = object_to_array($db->get($id)); $doc = object_to_array($db->get($id));
// print_r($doc); // print_r($doc);
   
foreach ($accountTypes as $accountType => $accounts) { foreach ($allvalues as $valueType => $values) {
if (!isset($doc["has" . $accountType]) || !is_array($doc["has" . $accountType])) { if (!isset($doc[ $valueType]) || !is_array($doc[ $valueType])) {
$doc["has" . $accountType] = Array(); $doc[ $valueType] = Array();
} }
$doc["has" . $accountType] = array_unique(array_merge($doc["has" . $accountType], $accounts)); $doc[ $valueType] = array_unique(array_merge($doc[ $valueType], $values));
  if ( $valueType == "rtkDescriptions") {
  foreach ($values as $descriptionAgency => $descriptionValue) {
  if ($descriptionAgency == $doc->value->name) {
  $doc->value->description = $descriptionValue;
  }
  }
  }
} }
$db->save($doc); $db->save($doc);
}*/ }
?> ?>
   
<?php <?php
   
require_once '../include/common.inc.php'; require_once '../include/common.inc.php';
//function createFOIDocumentsDesignDoc() { //function createFOIDocumentsDesignDoc() {
   
$foidb = $server->get_db('disclosr-foidocuments'); $foidb = $server->get_db('disclosr-foidocuments');
$obj = new stdClass(); $obj = new stdClass();
$obj->_id = "_design/" . urlencode("app"); $obj->_id = "_design/" . urlencode("app");
$obj->language = "javascript"; $obj->language = "javascript";
$obj->views->all->map = "function(doc) { emit(doc._id, doc); };"; $obj->views->all->map = "function(doc) { emit(doc._id, doc); };";
$obj->views->byDate->map = "function(doc) { emit(doc.date, doc); };"; $obj->views->byDate->map = "function(doc) { emit(doc.date, doc); };";
$obj->views->byDateMonthYear->map = "function(doc) { emit(doc.date, doc); };"; $obj->views->byDateMonthYear->map = "function(doc) { emit(doc.date, doc); };";
$obj->views->byDateMonthYear->reduce = "_count"; $obj->views->byDateMonthYear->reduce = "_count";
$obj->views->byAgencyID->map = "function(doc) { emit(doc.agencyID, doc); };"; $obj->views->byAgencyID->map = "function(doc) { emit(doc.agencyID, doc); };";
$obj->views->byAgencyID->reduce = "_count"; $obj->views->byAgencyID->reduce = "_count";
   
// allow safe updates (even if slightly slower due to extra: rev-detection check). // allow safe updates (even if slightly slower due to extra: rev-detection check).
$foidb->save($obj, true); $foidb->save($obj, true);
   
   
//function createDocumentsDesignDoc() { //function createDocumentsDesignDoc() {
$docdb = $server->get_db('disclosr-documents'); $docdb = $server->get_db('disclosr-documents');
   
$obj = new stdClass(); $obj = new stdClass();
$obj->_id = "_design/" . urlencode("app"); $obj->_id = "_design/" . urlencode("app");
$obj->language = "javascript"; $obj->language = "javascript";
$obj->views->web_server->map = "function(doc) {\n emit(doc.web_server, 1);\n}"; $obj->views->web_server->map = "function(doc) {\n emit(doc.web_server, 1);\n}";
$obj->views->web_server->reduce = "function (key, values, rereduce) {\n return sum(values);\n}"; $obj->views->web_server->reduce = "_sum";
$obj->views->byAgency->map = "function(doc) {\n emit(doc.agencyID, 1);\n}"; $obj->views->byAgency->map = "function(doc) {\n emit(doc.agencyID, 1);\n}";
$obj->views->byAgency->reduce = "function (key, values, rereduce) {\n return sum(values);\n}"; $obj->views->byAgency->reduce = "_sum";
$obj->views->byURL->map = "function(doc) {\n emit(doc.url, doc);\n}"; $obj->views->byURL->map = "function(doc) {\n emit(doc.url, doc);\n}";
$obj->views->agency->map = "function(doc) {\n emit(doc.agencyID, doc);\n}"; $obj->views->agency->map = "function(doc) {\n emit(doc.agencyID, doc);\n}";
$obj->views->byWebServer->map = "function(doc) {\n emit(doc.web_server, doc);\n}"; $obj->views->byWebServer->map = "function(doc) {\n emit(doc.web_server, doc);\n}";
$obj->views->getValidationRequired = "function(doc) {\nif (doc.mime_type == \"text/html\" \n&& typeof(doc.validation) == \"undefined\") {\n emit(doc._id, doc._attachments);\n}\n}"; $obj->views->getValidationRequired = "function(doc) {\nif (doc.mime_type == \"text/html\" \n&& typeof(doc.validation) == \"undefined\") {\n emit(doc._id, doc._attachments);\n}\n}";
   
   
   
   
//function createAgencyDesignDoc() { //function createAgencyDesignDoc() {
$db = $server->get_db('disclosr-agencies'); $db = $server->get_db('disclosr-agencies');
$obj = new stdClass(); $obj = new stdClass();
$obj->_id = "_design/" . urlencode("app"); $obj->_id = "_design/" . urlencode("app");
$obj->language = "javascript"; $obj->language = "javascript";
$obj->views->all->map = "function(doc) { emit(doc._id, doc); };"; $obj->views->all->map = "function(doc) { emit(doc._id, doc); };";
$obj->views->byABN->map = "function(doc) { emit(doc.abn, doc); };"; $obj->views->byABN->map = "function(doc) { emit(doc.abn, doc); };";
$obj->views->byCanonicalName->map = "function(doc) { $obj->views->byCanonicalName->map = "function(doc) {
if (doc.parentOrg || doc.orgType == 'FMA-DepartmentOfState') { if (doc.parentOrg || doc.orgType == 'FMA-DepartmentOfState') {
emit(doc.name, doc); emit(doc.name, doc);
} }
};"; };";
$obj->views->byDeptStateName->map = "function(doc) { $obj->views->byDeptStateName->map = "function(doc) {
if (doc.orgType == 'FMA-DepartmentOfState') { if (doc.orgType == 'FMA-DepartmentOfState') {
emit(doc.name, doc._id); emit(doc.name, doc._id);
} }
};"; };";
$obj->views->parentOrgs->map = "function(doc) { $obj->views->parentOrgs->map = "function(doc) {
if (doc.parentOrg) { if (doc.parentOrg) {
emit(doc._id, doc.parentOrg); emit(doc._id, doc.parentOrg);
} }
};"; };";
$obj->views->byName->map = 'function(doc) { $obj->views->byName->map = 'function(doc) {
if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") { if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") {
emit(doc.name, doc._id); emit(doc.name, doc._id);
if (typeof(doc.shortName) != "undefined" && doc.shortName != doc.name) { if (typeof(doc.shortName) != "undefined" && doc.shortName != doc.name) {
emit(doc.shortName, doc._id); emit(doc.shortName, doc._id);
} }
for (name in doc.otherNames) { for (name in doc.otherNames) {
if (doc.otherNames[name] != "" && doc.otherNames[name] != doc.name) { if (doc.otherNames[name] != "" && doc.otherNames[name] != doc.name) {
emit(doc.otherNames[name], doc._id); emit(doc.otherNames[name], doc._id);
} }
} }
for (name in doc.foiBodies) { for (name in doc.foiBodies) {
if (doc.foiBodies[name] != "" && doc.foiBodies[name] != doc.name) { if (doc.foiBodies[name] != "" && doc.foiBodies[name] != doc.name) {
emit(doc.foiBodies[name], doc._id); emit(doc.foiBodies[name], doc._id);
} }
} }
for (name in doc.positions) { for (name in doc.positions) {
if (doc.positions[name] != "" && doc.positions[name] != doc.name) { if (doc.positions[name] != "" && doc.positions[name] != doc.name) {
emit(doc.positions[name], doc._id); emit(doc.positions[name], doc._id);
} }
} }
} }
};'; };';
   
$obj->views->foiEmails->map = "function(doc) { $obj->views->foiEmails->map = "function(doc) {
emit(doc._id, doc.foiEmail); emit(doc._id, doc.foiEmail);
};"; };";
   
$obj->views->byLastModified->map = "function(doc) { emit(doc.metadata.lastModified, doc); }"; $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->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->getSuspended->map = 'function(doc) { if (doc.status == "suspended") { emit(doc._id, doc); } };';
$obj->views->getScrapeRequired->map = "function(doc) { $obj->views->getScrapeRequired->map = "function(doc) {
   
var lastScrape = Date.parse(doc.metadata.lastScraped); var lastScrape = Date.parse(doc.metadata.lastScraped);
   
var today = new Date(); var today = new Date();
   
if (!lastScrape || lastScrape.getTime() + 1000 != today.getTime()) { if (!lastScrape || lastScrape.getTime() + 1000 != today.getTime()) {
emit(doc._id, doc); emit(doc._id, doc);
} }
   
};"; };";
$obj->views->showNamesABNs->map = "function(doc) { emit(doc._id, {name: doc.name, abn: doc.abn}); };"; $obj->views->showNamesABNs->map = "function(doc) { emit(doc._id, {name: doc.name, abn: doc.abn}); };";
$obj->views->getConflicts->map = "function(doc) { $obj->views->getConflicts->map = "function(doc) {
if (doc._conflicts) { if (doc._conflicts) {
emit(null, [doc._rev].concat(doc._conflicts)); emit(null, [doc._rev].concat(doc._conflicts));
} }
}"; }";
  $obj->views->getStatistics->map =
  "function(doc) {
  if (doc.statistics) {
  for (var statisticSet in doc.statistics) {
  for (var statisticPeriod in doc.statistics[statisticSet]) {
  emit([statisticSet,statisticPeriod], doc.statistics[statisticSet][statisticPeriod]['value']);
  }
  }
  }
  }";
  $obj->views->getStatistics->reduce = '_sum';
// http://stackoverflow.com/questions/646628/javascript-startswith // http://stackoverflow.com/questions/646628/javascript-startswith
$obj->views->score->map = 'if(!String.prototype.startsWith){ $obj->views->score->map = 'if(!String.prototype.startsWith){
String.prototype.startsWith = function (str) { String.prototype.startsWith = function (str) {
return !this.indexOf(str); return !this.indexOf(str);
} }
} }
   
function(doc) { function(doc) {
count = 0; count = 0;
if (doc["status"] != "suspended") { if (doc["status"] != "suspended") {
for(var propName in doc) { for(var propName in doc) {
if(typeof(doc[propName]) != "undefined" && doc[propName] != "") { if(typeof(doc[propName]) != "undefined" && doc[propName] != "") {
count++; count++;
} }
} }
portfolio = doc.parentOrg; portfolio = doc.parentOrg;
if (doc.orgType == "FMA-DepartmentOfState") { if (doc.orgType == "FMA-DepartmentOfState") {
portfolio = doc._id; portfolio = doc._id;
} }
if (doc.orgType == "Court-Commonwealth" || doc.orgType == "FMA-DepartmentOfParliament") { if (doc.orgType == "Court-Commonwealth" || doc.orgType == "FMA-DepartmentOfParliament") {
portfolio = doc.orgType; portfolio = doc.orgType;
} }
emit(count+doc._id, {id:doc._id, name: doc.name, score:count, orgType: doc.orgType, portfolio:portfolio}); 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){ $obj->views->scoreHas->map = 'if(!String.prototype.startsWith){
String.prototype.startsWith = function (str) { String.prototype.startsWith = function (str) {
return !this.indexOf(str); return !this.indexOf(str);
}