dd update
Former-commit-id: 829f1f8df6ecfceaaa0652e73201ea2875745c72
--- a/.gitmodules
+++ b/.gitmodules
@@ -1,9 +1,6 @@
[submodule "couchdb/couchdb-lucene"]
path = couchdb/couchdb-lucene
url = https://github.com/rnewson/couchdb-lucene.git
-[submodule "couchdb/settee"]
- path = couchdb/settee
- url = https://github.com/inadarei/settee.git
[submodule "lib/php-diff"]
path = lib/php-diff
url = https://github.com/chrisboulton/php-diff.git
--- a/admin/exportEmployees.csv.php
+++ b/admin/exportEmployees.csv.php
@@ -4,7 +4,8 @@
$format = "csv";
//$format = "json";
-if (isset($_REQUEST['format'])) $format = $_REQUEST['format'];
+if (isset($_REQUEST['format']))
+ $format = $_REQUEST['format'];
setlocale(LC_CTYPE, 'C');
if ($format == "csv") {
$headers = Array("name");
@@ -21,7 +22,6 @@
if (isset($row->value->statistics->employees)) {
$headers = array_unique(array_merge($headers, array_keys(object_to_array($row->value->statistics->employees))));
-
}
}
} catch (SetteeRestClientException $e) {
@@ -40,15 +40,14 @@
fputcsv($fp, $headers);
} else if ($format == "json") {
echo '{
- "labels" : ["' . implode('","', $headers) . '"],'.PHP_EOL;
+ "labels" : ["' . implode('","', $headers) . '"],' . PHP_EOL;
}
try {
$agencies = $db->get_view("app", "all", null, true)->rows;
//print_r($agencies);
$first = true;
if ($format == "json") {
- echo '"data" : ['.PHP_EOL;
-
+ echo '"data" : [' . PHP_EOL;
}
foreach ($agencies as $agency) {
@@ -56,25 +55,35 @@
$row = Array();
$agencyEmployeesArray = object_to_array($agency->value->statistics->employees);
foreach ($headers as $i => $fieldName) {
+ if ($format == "csv") {
+ if (isset($agencyEmployeesArray[$fieldName])) {
+ $row[] = $agencyEmployeesArray[$fieldName]["value"] ;
+ } else if ($i == 0) {
+ $row[] = $agency->value->name;
+ } else {
+ $row[] = 0;
+ }
+ } else if ($format == "json") {
if (isset($agencyEmployeesArray[$fieldName])) {
- $row[] = '['.$i.','.$agencyEmployeesArray[$fieldName]["value"].']';
+ $row[] = '[' . $i . ',' . $agencyEmployeesArray[$fieldName]["value"] . ']';
} else {
- $row[] = '['.$i.',0]';
+ $row[] = '[' . $i . ',0]';
}
+ }
}
if ($format == "csv") {
fputcsv($fp, array_values($row));
} else if ($format == "json") {
- if (!$first) echo ",";
- echo '{"data" : [' . implode(",", array_values($row)) . '], "label": "'.$agency->value->name.'", "lines" : { "show" : true }, "points" : { "show" : true }}'.PHP_EOL;
+ if (!$first)
+ echo ",";
+ echo '{"data" : [' . implode(",", array_values($row)) . '], "label": "' . $agency->value->name . '", "lines" : { "show" : true }, "points" : { "show" : true }}' . PHP_EOL;
$first = false;
}
}
}
if ($format == "json") {
- echo ']
- }'.PHP_EOL;
-
+ echo ']
+ }' . PHP_EOL;
}
} catch (SetteeRestClientException $e) {
setteErrorHandler($e);
--- a/admin/importAPSCEmployees.php
+++ b/admin/importAPSCEmployees.php
@@ -47,13 +47,17 @@
$changed = false;
if (!isset($doc->statistics)) {
$changed = true;
- $doc->statistics = Array();
+ $doc->statistics = new stdClass();
+ }
+ if (!isset($doc->statistics->employees)) {
+ $changed = true;
+ $doc->statistics->employees = new stdClass();
}
foreach ($sum as $timePeriod => $value) {
if (!isset($doc->statistics->employees->$timePeriod->value)
|| $doc->statistics->employees->$timePeriod->value != $value) {
$changed = true;
- $doc->statistics["employees"][$timePeriod] = Array("value" => $value, "source" => "http://apsc.gov.au/stateoftheservice/");
+ $doc->statistics->employees->$timePeriod = Array("value" => $value, "source" => "http://apsc.gov.au/stateoftheservice/");
}
}
if ($changed) {
--- /dev/null
+++ b/admin/importAPSCEmployees2012.php
@@ -1,1 +1,86 @@
+<?php
+require_once '../include/common.inc.php';
+require($basePath . 'lib/phpquery/phpQuery/phpQuery.php');
+$db = $server->get_db('disclosr-agencies');
+$rows = $db->get_view("app", "byName")->rows;
+$nametoid = Array();
+$sums = Array();
+$functions = Array();
+foreach ($rows as $row) {
+ $nametoid[trim($row->key)] = $row->value;
+}
+
+
+$request = Requests::get("http://www.apsc.gov.au/publications-and-media/parliamentary/state-of-the-service/new-sosr/appendix-2-aps-agencies");
+$doc = phpQuery::newDocumentHTML($request->body);
+phpQuery::selectDocument($doc);
+foreach (pq('tr')->elements as $tr) {
+ //echo $tr->nodeValue.PHP_EOL;
+ $agency = "";
+ $employees = "";
+ $function = "";
+ $i = 0;
+ foreach ($tr->childNodes as $td) {
+ //echo $td->nodeValue." $i <br>";
+ if ($i == 0)
+ $agency = $td->nodeValue;
+ if ($i == 2) {
+ $employees = trim(str_replace(",", "", $td->nodeValue));
+ }
+ if ($i == 4) {
+ $function = $td->nodeValue;
+ }
+ $i++;
+ }
+ if ($agency != "" && $employees != "" && $function != "") {
+ $name = trim(str_replace('2','',$agency));
+ //echo "$name<br><bR>" . PHP_EOL;
+ if (isset($nametoid[$name])) {
+ $id = $nametoid[$name];
+ //echo $id . "<br>" . PHP_EOL;
+ @$sums[$id]["2011-2012"] += $employees;
+ $functions[$id] = $function;
+ } else if ($agency != "Agency"){
+ echo "<br>ERROR NAME '$agency' MISSING FROM ID LIST<br><bR>" . PHP_EOL;
+
+ die();
+ }
+ } else {
+ echo "skipped $agency";
+ }
+}
+//print_r($sums);
+foreach ($sums as $id => $sum) {
+ echo $id . "<br>" . PHP_EOL;
+ $doc = $db->get($id);
+ echo $doc->name . "<br>" . PHP_EOL;
+ // print_r($doc);
+ $changed = false;
+ if (!isset($doc->statistics)) {
+ $changed = true;
+ $doc->statistics = new stdClass();
+ }
+ if (!isset($doc->statistics->employees)) {
+ $changed = true;
+ $doc->statistics->employees = new stdClass();
+ }
+ foreach ($sum as $timePeriod => $value) {
+ if (!isset($doc->statistics->employees->$timePeriod->value)
+ || $doc->statistics->employees->$timePeriod->value != $value) {
+ $changed = true;
+ $doc->statistics->employees->$timePeriod = Array("value" => $value, "source" => "http://apsc.gov.au/stateoftheservice/");
+ $doc->employees = $value;
+ $doc->functionClassification = $functions[$id];
+ }
+ }
+
+ if ($changed) {
+ $db->save($doc);
+ } else {
+ echo "not changed" . "<br>" . PHP_EOL;
+ }
+}
+// employees: timeperiod, source = apsc state of service, value
+?>
+
--- a/admin/refreshDesignDoc.php
+++ b/admin/refreshDesignDoc.php
@@ -4,74 +4,61 @@
//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); };";
- $obj->views->byDate->reduce = "_count";
- $obj->views->byAgencyID->map = "function(doc) { emit(doc.agencyID, doc); };";
- $obj->views->byAgencyID->reduce = "_count";
+$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); };";
+$obj->views->byDateMonthYear->map = "function(doc) { emit(doc.date, doc); };";
+$obj->views->byDateMonthYear->reduce = "_count";
+$obj->views->byAgencyID->map = "function(doc) { emit(doc.agencyID, doc); };";
+$obj->views->byAgencyID->reduce = "_count";
- // allow safe updates (even if slightly slower due to extra: rev-detection check).
- $foidb->save($obj, true);
+// 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); };";
- $obj->views->byABN->map = "function(doc) { emit(doc.abn, doc); };";
- "views": {
- "web_server": {
- "map": "function(doc) {\n emit(doc.web_server, 1);\n}",
- "reduce": "function (key, values, rereduce) {\n return sum(values);\n}"
- },
- "byAgency": {
- "map": "function(doc) {\n emit(doc.agencyID, 1);\n}",
- "reduce": "function (key, values, rereduce) {\n return sum(values);\n}"
- },
- "byURL": {
- "map": "function(doc) {\n emit(doc.url, doc);\n}"
- },
- "agency": {
- "map": "function(doc) {\n emit(doc.agencyID, doc);\n}"
- },
- "byWebServer": {
- "map": "function(doc) {\n emit(doc.web_server, doc);\n}"
- },
- "getValidationRequired": {
- "map": "function(doc) {\nif (doc.mime_type == \"text/html\" \n&& typeof(doc.validation) == \"undefined\") {\n emit(doc._id, doc._attachments);\n}\n}"
- }
- } */
-}
+//function createDocumentsDesignDoc() {
+$docdb = $server->get_db('disclosr-documents');
+
+$obj = new stdClass();
+$obj->_id = "_design/" . urlencode("app");
+$obj->language = "javascript";
+$obj->views->web_server->map = "function(doc) {\n emit(doc.web_server, 1);\n}";
+$obj->views->web_server->reduce = "function (key, values, rereduce) {\n return sum(values);\n}";
+$obj->views->byAgency->map = "function(doc) {\n emit(doc.agencyID, 1);\n}";
+$obj->views->byAgency->reduce = "function (key, values, rereduce) {\n return sum(values);\n}";
+$obj->views->byURL->map = "function(doc) {\n emit(doc.url, doc);\n}";
+$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->getValidationRequired = "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');
- $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); };";
- $obj->views->byCanonicalName->map = "function(doc) {
+$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);
}
};";
- $obj->views->byDeptStateName->map = "function(doc) {
+$obj->views->byDeptStateName->map = "function(doc) {
if (doc.orgType == 'FMA-DepartmentOfState') {
emit(doc.name, doc._id);
}
};";
- $obj->views->parentOrgs->map = "function(doc) {
+$obj->views->parentOrgs->map = "function(doc) {
if (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") {
emit(doc.name, doc._id);
if (typeof(doc.shortName) != "undefined" && doc.shortName != doc.name) {
@@ -95,14 +82,14 @@
}
};';
- $obj->views->foiEmails->map = "function(doc) {
+$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); } };';
- $obj->views->getScrapeRequired->map = "function(doc) {
+$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);
@@ -113,14 +100,14 @@
}
};";
- $obj->views->showNamesABNs->map = "function(doc) { emit(doc._id, {name: doc.name, abn: doc.abn}); };";
- $obj->views->getConflicts->map = "function(doc) {
+$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
- $obj->views->score->map = 'if(!String.prototype.startsWith){
+// http://stackoverflow.com/questions/646628/javascript-startswith
+$obj->views->score->map = 'if(!String.prototype.startsWith){
String.prototype.startsWith = function (str) {
return !this.indexOf(str);
}
@@ -144,7 +131,7 @@
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) {
return !this.indexOf(str);
}
@@ -164,22 +151,20 @@
emit("total", 1);
}
}';
- $obj->views->scoreHas->reduce = 'function (key, values, rereduce) {
+$obj->views->scoreHas->reduce = 'function (key, values, rereduce) {
return sum(values);
}';
- $obj->views->fieldNames->map = '
+$obj->views->fieldNames->map = '
function(doc) {
for(var propName in doc) {
emit(propName, doc._id);
}
}';
- $obj->views->fieldNames->reduce = 'function (key, values, rereduce) {
+$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);
-
-
+// allow safe updates (even if slightly slower due to extra: rev-detection check).
+$db->save($obj, true);
?>
--- a/couchdb/SetteeDatabase.class.php
+++ /dev/null
@@ -1,306 +1,1 @@
-<?php
-/**
-* Databaase class.
-*/
-class SetteeDatabase {
-
- /**
- * Base URL of the CouchDB REST API
- */
- private $conn_url;
-
- /**
- * HTTP REST Client instance
- */
- protected $rest_client;
-
- /**
- * Name of the database
- */
- private $dbname;
-
- /**
- * Default constructor
- */
- function __construct($conn_url, $dbname) {
- $this->conn_url = $conn_url;
- $this->dbname = $dbname;
- $this->rest_client = SetteeRestClient::get_instance($this->conn_url);
- }
-
-
- /**
- * Get UUID from CouchDB
- *
- * @return
- * CouchDB-generated UUID string
- *
- */
- function gen_uuid() {
- $ret = $this->rest_client->http_get('_uuids');
- return $ret['decoded']->uuids[0]; // should never be empty at this point, so no checking
- }
-
- /**
- * Create or update a document database
- *
- * @param $document
- * PHP object, a PHP associative array, or a JSON String representing the document to be saved. PHP Objects and arrays are JSON-encoded automatically.
- *
- * <p>If $document has a an "_id" property set, it will be used as document's unique id (even for "create" operation).
- * If "_id" is missing, CouchDB will be used to generate a UUID.
- *
- * <p>If $document has a "_rev" property (revision), document will be updated, rather than creating a new document.
- * You have to provide "_rev" if you want to update an existing document, otherwise operation will be assumed to be
- * one of creation and you will get a duplicate document exception from CouchDB. Also, you may not provide "_rev" but
- * not provide "_id" since that is an invalid input.
- *
- * @param $allowRevAutoDetection
- * Default: false. When true and _rev is missing from the document, save() function will auto-detect latest revision
- * for a document and use it. This option is "false" by default because it involves an extra http HEAD request and
- * therefore can make save() operation slightly slower if such auto-detection is not required.
- *
- * @return
- * document object with the database id (uuid) and revision attached;
- *
- * @throws SetteeCreateDatabaseException
- */
- function save($document, $allowRevAutoDetection = false) {
- if (is_string($document)) {
- $document = json_decode($document);
- }
-
- // Allow passing of $document as an array (for syntactic simplicity and also because in JSON world it does not matter)
- if(is_array($document)) {
- $document = (object) $document;
- }
-
- if (empty($document->_id) && empty($document->_rev)) {
- $id = $this->gen_uuid();
- }
- elseif (empty($document->_id) && !empty($document->_rev)) {
- throw new SetteeWrongInputException("Error: You can not save a document with a revision provided, but missing id");
- }
- else {
- $id = $document->_id;
-
- if ($allowRevAutoDetection) {
- try {
- $rev = $this->get_rev($id);
- } catch (SetteeRestClientException $e) {
- // auto-detection may fail legitimately, if a document has never been saved before (new doc), so skipping error
- }
- if (!empty($rev)) {
- $document->_rev = $rev;
- }
- }
- }
-
- $full_uri = $this->dbname . "/" . $this->safe_urlencode($id);
- $document_json = json_encode($document, JSON_NUMERIC_CHECK);
-
- $ret = $this->rest_client->http_put($full_uri, $document_json);
-
- $document->_id = $ret['decoded']->id;
- $document->_rev = $ret['decoded']->rev;
-
- return $document;
- }
-
- /**
- * @param $doc
- * @param $name
- * @param $content
- * Content of the attachment in a string-buffer format. This function will automatically base64-encode content for
- * you, so you don't have to do it.
- * @param $mime_type
- * Optional. Will be auto-detected if not provided
- * @return void
- */
- public function add_attachment($doc, $name, $content, $mime_type = null) {
- if (empty($doc->_attachments) || !is_object($doc->_attachments)) {
- $doc->_attachments = new stdClass();
- }
-
- if (empty($mime_type)) {
- $mime_type = $this->rest_client->content_mime_type($content);
- }
-
- $doc->_attachments->$name = new stdClass();
- $doc->_attachments->$name->content_type = $mime_type;
- $doc->_attachments->$name->data = base64_encode($content);
- }
-
- /**
- * @param $doc
- * @param $name
- * @param $file
- * Full path to a file (e.g. as returned by PHP's realpath function).
- * @param $mime_type
- * Optional. Will be auto-detected if not provided
- * @return void
- */
- public function add_attachment_file($doc, $name, $file, $mime_type = null) {
- $content = file_get_contents($file);
- $this->add_attachment($doc, $name, $content, $mime_type);
- }
-
- /**
- *
- * Retrieve a document from CouchDB
- *
- * @throws SetteeWrongInputException
- *
- * @param $id
- * Unique ID (usually: UUID) of the document to be retrieved.
- * @return
- * database document in PHP object format.
- */
- function get($id) {
- if (empty($id)) {
- throw new SetteeWrongInputException("Error: Can't retrieve a document without a uuid.");
- }
-
- $full_uri = $this->dbname . "/" . $this->safe_urlencode($id);
-$full_uri = str_replace("%3Frev%3D","?rev=",$full_uri);
- $ret = $this->rest_client->http_get($full_uri);
- return $ret['decoded'];
- }
-
- /**
- *
- * Get the latest revision of a document with document id: $id in CouchDB.
- *
- * @throws SetteeWrongInputException
- *
- * @param $id
- * Unique ID (usually: UUID) of the document to be retrieved.
- * @return
- * database document in PHP object format.
- */
- function get_rev($id) {
- if (empty($id)) {
- throw new SetteeWrongInputException("Error: Can't query a document without a uuid.");
- }
-
- $full_uri = $this->dbname . "/" . $this->safe_urlencode($id);
- $headers = $this->rest_client->http_head($full_uri);
- if (empty($headers['Etag'])) {
- throw new SetteeRestClientException("Error: could not retrieve revision. Server unexpectedly returned empty Etag");
- }
- $etag = str_replace('"', '', $headers['Etag']);
- return $etag;
- }
-
- /**
- * Delete a document
- *
- * @param $document
- * a PHP object or JSON representation of the document that has _id and _rev fields.
- *
- * @return void
- */
- function delete($document) {
- if (!is_object($document)) {
- $document = json_decode($document);
- }
-
- $full_uri = $this->dbname . "/" . $this->safe_urlencode($document->_id) . "?rev=" . $document->_rev;
- $this->rest_client->http_delete($full_uri);
- }
-
-
- /*----------------- View-related functions --------------*/
-
- /**
- * Create a new view or update an existing one.
- *
- * @param $design_doc
- * @param $view_name
- * @param $map_src
- * Source code of the map function in Javascript
- * @param $reduce_src
- * Source code of the reduce function in Javascript (optional)
- * @return void
- */
- function save_view($design_doc, $view_name, $map_src, $reduce_src = null) {
- $obj = new stdClass();
- $obj->_id = "_design/" . urlencode($design_doc);
- $view_name = urlencode($view_name);
- $obj->views->$view_name->map = $map_src;
- if (!empty($reduce_src)) {
- $obj->views->$view_name->reduce = $reduce_src;
- }
-
- // allow safe updates (even if slightly slower due to extra: rev-detection check).
- return $this->save($obj, true);
- }
-
- /**
- * Create a new view or update an existing one.
- *
- * @param $design_doc
- * @param $view_name
- * @param $key
- * key parameter to a view. Can be a single value or an array (for a range). If passed an array, function assumes
- * that first element is startkey, second: endkey.
- * @param $descending
- * return results in descending order. Please don't forget that if you are using a startkey/endkey, when you change
- * order you also need to swap startkey and endkey values!
- *
- * @return void
- */
- function get_view($design_doc, $view_name, $key = null, $descending = false) {
- $id = "_design/" . urlencode($design_doc);
- $view_name = urlencode($view_name);
- $id .= "/_view/$view_name";
-
- $data = array();
- if (!empty($key)) {
- if (is_string($key)) {
- $data = "key=" . '"' . $key . '"';
- }
- elseif (is_array($key)) {
- list($startkey, $endkey) = $key;
- $data = "startkey=" . '"' . $startkey . '"&' . "endkey=" . '"' . $endkey . '"';
- }
-
- if ($descending) {
- $data .= "&descending=true";
- }
- }
-
-
-
- if (empty($id)) {
- throw new SetteeWrongInputException("Error: Can't retrieve a document without a uuid.");
- }
-
- $full_uri = $this->dbname . "/" . $this->safe_urlencode($id);
-$full_uri = str_replace("%253Fgroup%253Dtrue","?group=true",$full_uri);
- $ret = $this->rest_client->http_get($full_uri, $data);
- return $ret['decoded'];
-
- }
-
- /**
- * @param $id
- * @return
- * return a properly url-encoded id.
- */
- private function safe_urlencode($id) {
- //-- System views like _design can have "/" in their URLs.
- $id = rawurlencode($id);
- if (substr($id, 0, 1) == '_') {
- $id = str_replace('%2F', '/', $id);
- }
- return $id;
- }
-
- /** Getter for a database name */
- function get_name() {
- return $this->dbname;
- }
-
-}
--- a/couchdb/settee
+++ /dev/null
--- /dev/null
+++ b/couchdb/settee/.travis.yml
@@ -1,1 +1,6 @@
+language: php
+phps:
+ - 5.3
+ - 5.4
+before_script: cd tests/
--- /dev/null
+++ b/couchdb/settee/LICENSE.txt
@@ -1,1 +1,9 @@
+(The MIT License)
+Copyright (c) 2011 Irakli Nadareishvili
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the 'Software'), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
--- /dev/null
+++ b/couchdb/settee/README.textile
@@ -1,1 +1,60 @@
+Inspired by: "CouchRest library for Ruby":http://jchrisa.net/drl/_design/sofa/_list/post/post-page?startkey=%5B%22couchrest__restful_ruby_client_%22%5D and the "couchdb-python":http://packages.python.org/CouchDB/client.html#document library.
+h3. Server Functions
+
+# Specify a server:
+@$server = new SetteeServer('http://127.0.0.1:5984');@
+# Database API
+## Create a database:
+@$ret = $server->create_db('irakli_test');@
+## Drop a database:
+@$ret = $server->drop_db('irakli_test');@
+## List all databases:
+@$ret = $server->list_dbs();@
+## Get a database object
+@$db = $server->get_db('irakli_test');@
+# Document API
+## Create/Update a document:
+@$ret = $db->save($doc);@
+## Retrieve a document:
+@$db_doc = $db->get($id);@
+## Determine the latest revision_id for a document:
+@$rev = $db->get_rev($id);@
+## Delete a document:
+@$db_doc = $db->delete($doc);@
+# Attachments API
+## Add content as attachment:
+@$db->add_attachment($doc, "foo.txt", "Some text that will be base64 encoded", "text/plain");@
+## Add a file path to be attached:
+@$db->add_attachment_file($doc, "foo.pdf", $file_path, "application/pdf");@
+## Add a file path to be attached (mime-type is auto-detected):
+@$db->add_attachment_file($doc, "foo.pdf", $file_path);@
+## Full attachment saving example:
+ $doc = new stdClass();
+ $doc->_id = "attachment_doc";
+ $file_path = dirname(__FILE__) . "/resources/couch-logo.pdf";
+ $this->db->add_attachment_file($doc, "foo.pdf", $file_path, "application/pdf");
+ $db_doc = $this->db->save($doc);
+## ATTENTION: there is no "load_attachments" method, because when you load a document, all its attachments get loaded with it, as well.
+# Views API
+## Create a new view or save a view:
+@$view = $db->save_view("some_design_document_id", "a_view_name", $map_src);@
+@$view = $db->save_view("some_design_document_id", "a_view_name", $map_src, $reduce_src);@
+## Get a view (run query and get results):
+@$view = $db->get_view("some_design_document_id", "a_view_name");@
+## Parametrized view:
+@$view = $db->get_view("some_design_document_id", "a_view_name", "2009/02/17 21:13:39");@
+## Parametrized view with key range:
+@$view = $db->get_view("some_design_document_id", "a_view_name", array("2009/01/30 18:04:11", "2009/02/17 21:13:39"));@
+## Parametrized view with key range, ordered descending:
+@$view = $db->get_view("some_design_document_id", "a_view_name", array("2009/01/30 18:04:11", "2009/02/17 21:13:39"), true);@
+
+
+h3. Requirements
+# PHP 5.2 or newer
+
+h3. Recommended
+# PHP 5.3 or newer. With PHP 5.2 following functionality will not work:
+## Some unit-tests
+## Mime type auto-detection.
+# pecl_http
--- /dev/null
+++ b/couchdb/settee/examples/db.ops.php
@@ -1,1 +1,50 @@
+#!/usr/bin/env php
+<?php
+
+require (realpath(dirname(__FILE__) . '/../src/settee.php'));
+
+$server = new SetteeServer('http://127.0.0.1:5984');
+
+
+$dbs = array (
+ 1 => "settee_test_perf_01",
+ 2 => "settee_test_perf_02",
+ 3 => "settee_test_perf_03",
+);
+
+print ("creating databases: \n");
+
+foreach ($dbs as $db) {
+ $start = microtime(true);
+ try {
+ $ret = $server->create_db($db);
+ } catch (Exception $e) {
+ //-- re-throw. this is just for demo
+ throw $e;
+ }
+ $elapsed = microtime(true) - $start;
+ print("Time elapsed: $elapsed \n");
+}
+
+$ret = $server->list_dbs();
+print_r($ret);
+print ("\n");
+
+print ("dropping databases: \n");
+
+foreach ($dbs as $db) {
+ $start = microtime(true);
+ try {
+ $ret = $server->drop_db($db);
+ } catch (Exception $e) {
+ //-- re-throw. this is just for demo
+ throw $e;
+ }
+ $elapsed = microtime(true) - $start;
+ print("Time elapsed: $elapsed \n");
+}
+
+$ret = $server->list_dbs();
+print_r($ret);
+
--- /dev/null
+++ b/couchdb/settee/examples/doc.ops.php
@@ -1,1 +1,40 @@
+#!/usr/bin/env php
+<?php
+
+require (realpath(dirname(__FILE__) . '/../src/settee.php'));
+
+$server = new SetteeServer('http://127.0.0.1:5984');
+$dname = 'irakli';
+$db = $server->get_db('irakli');
+
+try {
+ $server->create_db($db);
+} catch (Exception $e) {
+ print_r("database irakli already exists! \n");
+}
+
+$doc = new StdClass();
+$doc->firstName = "Irakli";
+$doc->lastName = "Nadareishvili";
+$doc->IQ = 200;
+$doc->hobbies = array("skiing", "swimming");
+$doc->pets = array ("whitey" => "labrador", "mikey" => "pug");
+
+// Should work with json string as well:
+//$doc = '{"firstName":"irakli","lastName":"Nadareishvili","IQ":200,"hobbies":["skiing","swimming"],"pets":{"whitey":"labrador","mikey":"pug"}}';
+
+$doc = $db->save($doc);
+print_r($doc);
+
+$doc = $db->get($doc->_id);
+print_r($doc);
+
+$doc->firstName = "Ika";
+$doc = $db->save($doc);
+print_r($doc);
+
+$db->delete($doc);
+
+
+
--- /dev/null
+++ b/couchdb/settee/src/classes/SetteeDatabase.class.php
@@ -1,1 +1,310 @@
-
+<?php
+
+/**
+* Databaase class.
+*/
+class SetteeDatabase {
+
+ /**
+ * Base URL of the CouchDB REST API
+ */
+ private $conn_url;
+
+ /**
+ * HTTP REST Client instance
+ */
+ protected $rest_client;
+
+ /**
+ * Name of the database
+ */
+ private $dbname;
+
+ /**
+ * Default constructor
+ */
+ function __construct($conn_url, $dbname) {
+ $this->conn_url = $conn_url;
+ $this->dbname = $dbname;
+ $this->rest_client = SetteeRestClient::get_instance($this->conn_url);
+ }
+
+
+ /**
+ * Get UUID from CouchDB
+ *
+ * @return
+ * CouchDB-generated UUID string
+ *
+ */
+ function gen_uuid() {
+ $ret = $this->rest_client->http_get('_uuids');
+ return $ret['decoded']->uuids[0]; // should never be empty at this point, so no checking
+ }
+
+ /**
+ * Create or update a document database
+ *
+ * @param $document
+ * PHP object, a PHP associative array, or a JSON String representing the document to be saved. PHP Objects and arrays are JSON-encoded automatically.
+ *
+ * <p>If $document has a an "_id" property set, it will be used as document's unique id (even for "create" operation).
+ * If "_id" is missing, CouchDB will be used to generate a UUID.
+ *
+ * <p>If $document has a "_rev" property (revision), document will be updated, rather than creating a new document.
+ * You have to provide "_rev" if you want to update an existing document, otherwise operation will be assumed to be
+ * one of creation and you will get a duplicate document exception from CouchDB. Also, you may not provide "_rev" but
+ * not provide "_id" since that is an invalid input.
+ *
+ * @param $allowRevAutoDetection
+ * Default: false. When true and _rev is missing from the document, save() function will auto-detect latest revision
+ * for a document and use it. This option is "false" by default because it involves an extra http HEAD request and
+ * therefore can make save() operation slightly slower if such auto-detection is not required.
+ *
+ * @return
+ * document object with the database id (uuid) and revision attached;
+ *
+ * @throws SetteeCreateDatabaseException
+ */
+ function save($document, $allowRevAutoDetection = false) {
+ if (is_string($document)) {
+ $document = json_decode($document);
+ }
+
+ // Allow passing of $document as an array (for syntactic simplicity and also because in JSON world it does not matter)
+ if(is_array($document)) {
+ $document = (object) $document;
+ }
+
+ if (empty($document->_id) && empty($document->_rev)) {
+ $id = $this->gen_uuid();
+ }
+ elseif (empty($document->_id) && !empty($document->_rev)) {
+ throw new SetteeWrongInputException("Error: You can not save a document with a revision provided, but missing id");
+ }
+ else {
+ $id = $document->_id;
+
+ if ($allowRevAutoDetection) {
+ try {
+ $rev = $this->get_rev($id);
+ } catch (SetteeRestClientException $e) {
+ // auto-detection may fail legitimately, if a document has never been saved before (new doc), so skipping error
+ }
+ if (!empty($rev)) {
+ $document->_rev = $rev;
+ }
+ }
+ }
+
+ $full_uri = $this->dbname . "/" . $this->safe_urlencode($id);
+ $document_json = json_encode($document, JSON_NUMERIC_CHECK);
+
+ $ret = $this->rest_client->http_put($full_uri, $document_json);
+
+ $document->_id = $ret['decoded']->id;
+ $document->_rev = $ret['decoded']->rev;
+
+ return $document;
+ }
+
+ /**
+ * @param $doc
+ * @param $name
+ * @param $content
+ * Content of the attachment in a string-buffer format. This function will automatically base64-encode content for
+ * you, so you don't have to do it.
+ * @param $mime_type
+ * Optional. Will be auto-detected if not provided
+ * @return void
+ */
+ public function add_attachment($doc, $name, $content, $mime_type = null) {
+ if (empty($doc->_attachments) || !is_object($doc->_attachments)) {
+ $doc->_attachments = new stdClass();
+ }
+
+ if (empty($mime_type)) {
+ $mime_type = $this->rest_client->content_mime_type($content);
+ }
+
+ $doc->_attachments->$name = new stdClass();
+ $doc->_attachments->$name->content_type = $mime_type;
+ $doc->_attachments->$name->data = base64_encode($content);
+ }
+
+ /**
+ * @param $doc
+ * @param $name
+ * @param $file
+ * Full path to a file (e.g. as returned by PHP's realpath function).
+ * @param $mime_type
+ * Optional. Will be auto-detected if not provided
+ * @return void
+ */
+ public function add_attachment_file($doc, $name, $file, $mime_type = null) {
+ $content = file_get_contents($file);
+ $this->add_attachment($doc, $name, $content, $mime_type);
+ }
+
+ /**
+ *
+ * Retrieve a document from CouchDB
+ *
+ * @throws SetteeWrongInputException
+ *
+ * @param $id
+ * Unique ID (usually: UUID) of the document to be retrieved.
+ * @return
+ * database document in PHP object format.
+ */
+ function get($id) {
+ if (empty($id)) {
+ throw new SetteeWrongInputException("Error: Can't retrieve a document without a uuid.");
+ }
+
+ $full_uri = $this->dbname . "/" . $this->safe_urlencode($id);
+$full_uri = str_replace("%3Frev%3D","?rev=",$full_uri);
+ $ret = $this->rest_client->http_get($full_uri);
+ return $ret['decoded'];
+ }
+
+ /**
+ *
+ * Get the latest revision of a document with document id: $id in CouchDB.
+ *
+ * @throws SetteeWrongInputException
+ *
+ * @param $id
+ * Unique ID (usually: UUID) of the document to be retrieved.
+ * @return
+ * database document in PHP object format.
+ */
+ function get_rev($id) {
+ if (empty($id)) {
+ throw new SetteeWrongInputException("Error: Can't query a document without a uuid.");
+ }
+
+ $full_uri = $this->dbname . "/" . $this->safe_urlencode($id);
+ $headers = $this->rest_client->http_head($full_uri);
+ if (empty($headers['Etag'])) {
+ throw new SetteeRestClientException("Error: could not retrieve revision. Server unexpectedly returned empty Etag");
+ }
+ $etag = str_replace('"', '', $headers['Etag']);
+ return $etag;
+ }
+
+ /**
+ * Delete a document
+ *
+ * @param $document
+ * a PHP object or JSON representation of the document that has _id and _rev fields.
+ *
+ * @return void
+ */
+ function delete($document) {
+ if (!is_object($document)) {
+ $document = json_decode($document);
+ }
+
+ $full_uri = $this->dbname . "/" . $this->safe_urlencode($document->_id) . "?rev=" . $document->_rev;
+ $this->rest_client->http_delete($full_uri);
+ }
+
+
+ /*----------------- View-related functions --------------*/
+
+ /**
+ * Create a new view or update an existing one.
+ *
+ * @param $design_doc
+ * @param $view_name
+ * @param $map_src
+ * Source code of the map function in Javascript
+ * @param $reduce_src
+ * Source code of the reduce function in Javascript (optional)
+ * @return void
+ */
+ function save_view($design_doc, $view_name, $map_src, $reduce_src = null) {
+ $obj = new stdClass();
+ $obj->_id = "_design/" . urlencode($design_doc);
+ $view_name = urlencode($view_name);
+ $obj->views->$view_name->map = $map_src;
+ if (!empty($reduce_src)) {
+ $obj->views->$view_name->reduce = $reduce_src;
+ }
+
+ // allow safe updates (even if slightly slower due to extra: rev-detection check).
+ return $this->save($obj, true);
+ }
+
+ /**
+ * Create a new view or update an existing one.
+ *
+ * @param $design_doc
+ * @param $view_name
+ * @param $key
+ * key parameter to a view. Can be a single value or an array (for a range). If passed an array, function assumes
+ * that first element is startkey, second: endkey.
+ * @param $descending
+ * return results in descending order. Please don't forget that if you are using a startkey/endkey, when you change
+ * order you also need to swap startkey and endkey values!
+ *
+ * @return void
+ */
+ function get_view($design_doc, $view_name, $key = null, $descending = false, $limit = false) {
+ $id = "_design/" . urlencode($design_doc);
+ $view_name = urlencode($view_name);
+ $id .= "/_view/$view_name";
+
+ $data = array();
+ if (!empty($key)) {
+ if (is_string($key)) {
+ $data = "key=" . '"' . $key . '"';
+ }
+ elseif (is_array($key)) {
+ list($startkey, $endkey) = $key;
+ $data = "startkey=" . '"' . $startkey . '"&' . "endkey=" . '"' . $endkey . '"';
+ }
+
+ if ($descending) {
+ $data .= "&descending=true";
+ }
+ if ($limit) {
+ $data .= "&limit=".$limit;
+ }
+ }
+
+
+
+ if (empty($id)) {
+ throw new SetteeWrongInputException("Error: Can't retrieve a document without a uuid.");
+ }
+
+ $full_uri = $this->dbname . "/" . $this->safe_urlencode($id);
+$full_uri = str_replace("%253Fgroup%253D","?group=",$full_uri);
+$full_uri = str_replace("%253Flimit%253D","?limit=",$full_uri);
+ $ret = $this->rest_client->http_get($full_uri, $data);
+ return $ret['decoded'];
+
+ }
+
+ /**
+ * @param $id
+ * @return
+ * return a properly url-encoded id.
+ */
+ private function safe_urlencode($id) {
+ //-- System views like _design can have "/" in their URLs.
+ $id = rawurlencode($id);
+ if (substr($id, 0, 1) == '_') {
+ $id = str_replace('%2F', '/', $id);
+ }
+ return $id;
+ }
+
+ /** Getter for a database name */
+ function get_name() {
+ return $this->dbname;
+ }
+
+}
--- /dev/null
+++ b/couchdb/settee/src/classes/SetteeRestClient.class.php
@@ -1,1 +1,246 @@
-
+<?php
+
+/**
+* HTTP REST Client for CouchDB API
+*/
+class SetteeRestClient {
+
+ /**
+ * HTTP Timeout in Milliseconds
+ */
+ const HTTP_TIMEOUT = 2000;
+
+ private $base_url;
+ private $curl;
+
+ private static $curl_workers = array();
+
+ /**
+ * Singleton factory method
+ */
+ static function get_instance($base_url) {
+
+ if (empty(self::$curl_workers[$base_url])) {
+ self::$curl_workers[$base_url] = new SetteeRestClient($base_url);
+ }
+
+ return self::$curl_workers[$base_url];
+ }
+
+ /**
+ * Class constructor
+ */
+ private function __construct($base_url) {
+ $this->base_url = $base_url;
+
+ $curl = curl_init();
+ curl_setopt($curl, CURLOPT_USERAGENT, "Settee CouchDB Client/1.0");
+ curl_setopt($curl, CURLOPT_HTTPHEADER, array('Content-Type: application/json'));
+ curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
+ curl_setopt($curl, CURLOPT_HEADER, 0);
+ curl_setopt($curl, CURLOPT_FOLLOWLOCATION, 1);
+ curl_setopt($curl, CURLOPT_TIMEOUT_MS, self::HTTP_TIMEOUT);
+ curl_setopt($curl, CURLOPT_FORBID_REUSE, false); // Connection-pool for CURL
+
+ $this->curl = $curl;
+
+ }
+
+ /**
+ * Class destructor cleans up any resources
+ */
+ function __destruct() {
+ curl_close($this->curl);
+ }
+
+ /**
+ * HTTP HEAD
+ *
+ * @return
+ * Raw HTTP Headers of the response.
+ *
+ * @see: http://www.php.net/manual/en/context.params.php
+ *
+ */
+ function http_head($uri) {
+ curl_setopt($this->curl, CURLOPT_HEADER, 1);
+
+ $full_url = $this->get_full_url($uri);
+ curl_setopt($this->curl, CURLOPT_URL, $full_url);
+ curl_setopt($this->curl, CURLOPT_CUSTOMREQUEST, 'HEAD');
+ curl_setopt($this->curl, CURLOPT_NOBODY, true);
+
+
+ $response = curl_exec($this->curl);
+ // Restore default values
+ curl_setopt($this->curl, CURLOPT_NOBODY, false);
+ curl_setopt($this->curl, CURLOPT_HEADER, false);
+
+ $resp_code = curl_getinfo($this->curl, CURLINFO_HTTP_CODE);
+ if ($resp_code == 404 ) {
+ throw new SetteeRestClientException("Couch document not found at: '$full_url'");
+ }
+
+ if (function_exists('http_parse_headers')) {
+ $headers = http_parse_headers($response);
+ }
+ else {
+ $headers = $this->_http_parse_headers($response);
+ }
+
+ return $headers;
+ }
+
+ /**
+ * Backup PHP impl. for when PECL http_parse_headers() function is not available
+ *
+ * @param $header
+ * @return array
+ * @source http://www.php.net/manual/en/function.http-parse-headers.php#77241
+ */
+ private function _http_parse_headers( $header ) {
+ $retVal = array();
+ $fields = explode("\r\n", preg_replace('/\x0D\x0A[\x09\x20]+/', ' ', $header));
+ foreach( $fields as $field ) {
+ if( preg_match('/([^:]+): (.+)/m', $field, $match) ) {
+ $match[1] = preg_replace('/(?<=^|[\x09\x20\x2D])./e', 'strtoupper("\0")', strtolower(trim($match[1])));
+ if( isset($retVal[$match[1]]) ) {
+ $retVal[$match[1]] = array($retVal[$match[1]], $match[2]);
+ } else {
+ $retVal[$match[1]] = trim($match[2]);
+ }
+ }
+ }
+ return $retVal;
+ }
+
+ /**
+ * HTTP GET
+ */
+ function http_get($uri, $data = array()) {
+ $data = (is_array($data)) ? http_build_query($data) : $data;
+ if (!empty($data)) {
+ $uri .= "?$data";
+ }
+ return $this->http_request('GET', $uri);
+ }
+
+ /**
+ * HTTP PUT
+ */
+ function http_put($uri, $data = array()) {
+ return $this->http_request('PUT', $uri, $data);
+ }
+
+ /**
+ * HTTP DELETE
+ */
+ function http_delete($uri, $data = array()) {
+ return $this->http_request('DELETE', $uri, $data);
+ }
+
+ /**
+ * Generic implementation of a HTTP Request.
+ *
+ * @param $http_method
+ * @param $uri
+ * @param array $data
+ * @return
+ * an array containing json and decoded versions of the response.
+ */
+ private function http_request($http_method, $uri, $data = array()) {
+ $data = (is_array($data)) ? http_build_query($data) : $data;
+
+ if (!empty($data)) {
+ curl_setopt($this->curl, CURLOPT_HTTPHEADER, array('Content-Length: ' . strlen($data)));
+ curl_setopt($this->curl, CURLOPT_POSTFIELDS, $data);
+ }
+
+ curl_setopt($this->curl, CURLOPT_URL, $this->get_full_url($uri));
+ curl_setopt($this->curl, CURLOPT_CUSTOMREQUEST, $http_method);
+
+ $response = curl_exec($this->curl);
+ $response_decoded = $this->decode_response($response);
+ $response = array('json' => $response, 'decoded'=>$response_decoded);
+
+ $this->check_status($response,$uri);
+
+ return $response;
+ }
+
+ /**
+ * Check http status for safe return codes
+ *
+ * @throws SetteeRestClientException
+ */
+ private function check_status($response,$uri) {
+ $resp_code = curl_getinfo($this->curl, CURLINFO_HTTP_CODE);
+
+ if ($resp_code < 199 || $resp_code > 399 || !empty($response['decoded']->error)) {
+ $msg = "CouchDB returned: \"HTTP 1.1. $resp_code\". ERROR: " . $response['json'] . $uri;
+ throw new SetteeRestClientException($msg);
+ }
+ }
+
+ /**
+ * @param $path
+ * Full path to a file (e.g. as returned by PHP's realpath function).
+ * @return void
+ */
+ public function file_mime_type ($path) {
+ $ftype = 'application/octet-stream';
+
+ if (function_exists("finfo_file")) {
+ $finfo = new finfo(FILEINFO_MIME_TYPE | FILEINFO_SYMLINK);
+ $fres = $finfo->file($path);
+ if (is_string($fres) && !empty($fres)) {
+ $ftype = $fres;
+ }
+ }
+
+ return $ftype;
+ }
+
+ /**
+ * @param $content
+ * content of a file in a string buffer format.
+ * @return void
+ */
+ public function content_mime_type ($content) {
+ $ftype = 'application/octet-stream';
+
+ if (function_exists("finfo_file")) {
+ $finfo = new finfo(FILEINFO_MIME_TYPE | FILEINFO_SYMLINK);
+ $fres = $finfo->buffer($content);
+ if (is_string($fres) && !empty($fres)) {
+ $ftype = $fres;
+ }
+ }
+
+ return $ftype;
+ }
+
+
+ /**
+ *
+ * @param $json
+ * json-encoded response from CouchDB
+ *
+ * @return
+ * decoded PHP object
+ */
+ private function decode_response($json) {
+ return json_decode($json);
+ }
+
+ /**
+ * Get full URL from a partial one
+ */
+ private function get_full_url($uri) {
+ // We do not want "/", "?", "&" and "=" separators to be encoded!!!
+ $uri = str_replace(array('%2F', '%3F', '%3D', '%26'), array('/', '?', '=', '&'), urlencode($uri));
+ return $this->base_url . '/' . $uri;
+ }
+}
+
+class SetteeRestClientException extends Exception {}
--- /dev/null
+++ b/couchdb/settee/src/classes/SetteeServer.class.php
@@ -1,1 +1,106 @@
+<?php
+/**
+* CouchDB Server Manager
+*/
+class SetteeServer {
+
+ /**
+ * Base URL of the CouchDB REST API
+ */
+ private $conn_url;
+
+ /**
+ * HTTP REST Client instance
+ */
+ protected $rest_client;
+
+
+ /**
+ * Class constructor
+ *
+ * @param $conn_url
+ * (optional) URL of the CouchDB server to connect to. Default value: http://127.0.0.1:5984
+ */
+ function __construct($conn_url = "http://127.0.0.1:5984") {
+ $this->conn_url = rtrim($conn_url, ' /');
+ $this->rest_client = SetteeRestClient::get_instance($this->conn_url);
+ }
+
+ /**
+ * Create database
+ *
+ * @param $db
+ * Either a database object or a String name of the database.
+ *
+ * @return
+ * json string from the server.
+ *
+ * @throws SetteeCreateDatabaseException
+ */
+ function create_db($db) {
+ if ($db instanceof SetteeDatabase) {
+ $db = $db->get_name();
+ }
+ $ret = $this->rest_client->http_put($db);
+ if (!empty($ret['decoded']->error)) {
+ throw new SetteeDatabaseException("Could not create database: " . $ret["json"]);
+ }
+ return $ret['decoded'];
+ }
+
+ /**
+ * Drop database
+ *
+ * @param $db
+ * Either a database object or a String name of the database.
+ *
+ * @return
+ * json string from the server.
+ *
+ * @throws SetteeDropDatabaseException
+ */
+ function drop_db($db) {
+ if ($db instanceof SetteeDatabase) {
+ $db = $db->get_name();
+ }
+ $ret = $this->rest_client->http_delete($db);
+ if (!empty($ret['decoded']->error)) {
+ throw new SetteeDatabaseException("Could not create database: " . $ret["json"]);
+ }
+ return $ret['decoded'];
+ }
+
+ /**
+ * Instantiate a database object
+ *
+ * @param $dbname
+ * name of the newly created database
+ *
+ * @return SetteeDatabase
+ * new SetteeDatabase instance.
+ */
+ function get_db($dbname) {
+ return new SetteeDatabase($this->conn_url, $dbname);
+ }
+
+
+ /**
+ * Return an array containing all databases
+ *
+ * @return Array
+ * an array of database names in the CouchDB instance
+ */
+ function list_dbs() {
+ $ret = $this->rest_client->http_get('_all_dbs');
+ if (!empty($ret['decoded']["error"])) {
+ throw new SetteeDatabaseException("Could not get list of databases: " . $ret["json"]);
+ }
+ return $ret['decoded'];
+ }
+
+}
+
+class SetteeServerErrorException extends Exception {}
+class SetteeDatabaseException extends Exception {}
+class SetteeWrongInputException extends Exception {}
--- /dev/null
+++ b/couchdb/settee/src/settee.php
@@ -1,1 +1,6 @@
+<?php
+require(dirname(__FILE__) . '/classes/SetteeRestClient.class.php');
+
+require(dirname(__FILE__) . '/classes/SetteeServer.class.php');
+require(dirname(__FILE__) . '/classes/SetteeDatabase.class.php');
--- /dev/null
+++ b/couchdb/settee/tests/README
@@ -1,1 +1,10 @@
+1. Make sure you have latest PEAR PHPUnit installed:
+ > sudo upgrade pear
+ > sudo pear channel-discover pear.phpunit.de
+ > sudo pear install phpunit/PHPUnit
+2. You need PHP 5.3.2 or later to run some tests that deal with private or protected methods. If you use an earlier
+ version of PHP, these tests will be skipped.
+
+3. Run all tests with:
+ > phpunit .
--- /dev/null
+++ b/couchdb/settee/tests/SetteeDatabaseTest.php
@@ -1,1 +1,281 @@
-
+<?php
+
+require_once (realpath(dirname(__FILE__) . '/../src/settee.php'));
+require_once (dirname(__FILE__) . '/SetteeTestCase.class.php');
+
+class SetteeDatabaseTest extends SetteeTestCase {
+
+ private $db;
+
+ public function setUp() {
+ parent::setUp();
+ $dbname = "settee_tests_" . md5(microtime(true));
+ $this->db = $this->server->get_db($dbname);
+ $this->server->create_db($this->db);
+ }
+
+ public function test_document_lifecycle_objectbased() {
+ $doc = new StdClass();
+ $doc->firstName = "Irakli";
+ $doc->lastName = "Nadareishvili";
+ $doc->IQ = 200;
+ $doc->hobbies = array("skiing", "swimming");
+ $doc->pets = array ("whitey" => "labrador", "mikey" => "pug");
+
+ $doc = $this->db->save($doc);
+ $this->assertTrue(!empty($doc->_id) && !empty($doc->_rev), "Document creation success [object-based]");
+
+ $_rev = $doc->_rev;
+ $doc = $this->db->get($doc->_id);
+ $this->assertEquals($_rev, $doc->_rev, "Document retrieval success [object-based] test");
+
+ $doc->firstName = "Ika";
+ $db_doc = $this->db->save($doc);
+ $this->assertEquals($doc->firstName, $db_doc->firstName, "Document update success [object-based]");
+
+ $this->db->delete($doc);
+
+
+ try {
+ $doc = $this->db->get($doc->_id);
+ } catch (SetteeRestClientException $e) {
+ // we expect exception to fire, so this is good.
+ return;
+ }
+
+ $this->fail('Document still available for retrieval after being deleted. [object-based]');
+ }
+
+ // Should work with json string as well:
+ //
+
+
+ public function test_document_lifecycle_jsonbased() {
+ $doc = '{"firstName":"Irakli","lastName":"Nadareishvili","IQ":200,"hobbies":["skiing","swimming"],"pets":{"whitey":"labrador","mikey":"pug"}}';
+
+ $doc = $this->db->save($doc);
+ $this->assertTrue(!empty($doc->_id) && !empty($doc->_rev), "Document creation success [json-based]");
+
+ $_rev = $doc->_rev;
+
+ $db_doc = $this->db->get($doc->_id);
+ $this->assertEquals($_rev, $db_doc->_rev, "Document retrieval success [json-based] test");
+
+ $doc = '{';
+ $doc .= '"_id":"' . $db_doc->_id . '",';
+ $doc .= '"_rev":"' . $db_doc->_rev . '",';
+ $doc .= '"firstName":"Ika","lastName":"Nadareishvili","IQ":200,"hobbies":["skiing","swimming"],"pets":{"whitey":"labrador","mikey":"pug"}}';
+
+ $orig_doc = json_decode($doc);
+ $db_doc = $this->db->save($doc);
+ $this->assertEquals($orig_doc->firstName, $db_doc->firstName, "Document update success [json-based]");
+
+ $doc = '{';
+ $doc .= '"_id":"' . $db_doc->_id . '",';
+ $doc .= '"_rev":"' . $db_doc->_rev . '",';
+ $doc .= '"firstName":"Ika","lastName":"Nadareishvili","IQ":200,"hobbies":["skiing","swimming"],"pets":{"whitey":"labrador","mikey":"pug"}}';
+
+ $this->db->delete($doc);
+
+ try {
+ $doc = $this->db->get($db_doc->_id);
+ } catch (SetteeRestClientException $e) {
+ // we expect exception to fire, so this is good.
+ return;
+ }
+
+ $this->fail('Document still available for retrieval after being deleted. [object-based]');
+ }
+
+ public function test_invalid_document() {
+ $doc = 12345;
+ try {
+ $doc = $this->db->save($doc);
+ } catch (SetteeRestClientException $e) {
+ // we expect exception to fire, so this is good.
+ return;
+ }
+
+ $this->fail('Document saved with invalid format');
+ }
+
+ public function test_get_rev() {
+ $doc = new stdClass();
+ $doc->_id = "some_fixed_id";
+ $doc = $this->db->save($doc);
+
+ $_rev = $doc->_rev;
+
+ $db_rev = $this->db->get_rev($doc->_id);
+ $this->assertEquals($_rev, $db_rev, "Document Revision retrieval success");
+
+ // _rev is now attached to this object due to last ->save() call
+ $doc->_id = "some_fixed_id";
+ $doc->title = "Some Fixed ID";
+ $doc = $this->db->save($doc);
+
+ $_rev = $doc->_rev;
+
+ $db_rev = $this->db->get_rev($doc->_id);
+ $this->assertEquals($_rev, $db_rev, "Document Revision retrieval success after re-save");
+
+ }
+
+ public function test_save_auto_revision_detection() {
+ $doc = new stdClass();
+ $doc->_id = "some_fixed_id";
+ $this->db->save($doc);
+
+ $doc = new stdClass();
+ $doc->_id = "some_fixed_id";
+ $doc->extra_field = "some other value";
+
+ $new_doc = $this->db->save($doc, true);
+ $this->assertEquals ($new_doc->extra_field, "some other value", "Testing auto-rev detection by save method");
+ }
+
+ public function test_inline_attachment_json() {
+ $doc = '{
+ "_id":"attachment_doc",
+ "_attachments":
+ {
+ "foo.txt":
+ {
+ "content_type":"text\/plain",
+ "data": "VGhpcyBpcyBhIGJhc2U2NCBlbmNvZGVkIHRleHQ="
+ }
+ }
+ }';
+ $db_doc = $this->db->save($doc);
+ $this->assertTrue(is_object($db_doc->_attachments), "Inline attachment save successful [json-based]");
+ }
+
+ public function test_inline_attachment_obj_content() {
+ $doc = new stdClass();
+ $doc->_id = "attachment_doc";
+ $this->db->add_attachment($doc, "foo.txt", "This is some text to be encoded", "text/plain");
+ $db_doc = $this->db->save($doc);
+ $this->assertTrue(is_object($db_doc->_attachments), "Inline attachment save successful [object-based]");
+
+ $doc = new stdClass();
+ $doc->_id = "attachment_doc_autodetect";
+ $this->db->add_attachment($doc, "foo.txt", "This is some other text to be encoded");
+ $db_doc = $this->db->save($doc);
+ $this->assertTrue(is_object($db_doc->_attachments), "Inline attachment save successful [object-based, mime auto-detection]");
+ }
+
+ public function test_inline_attachment_obj_file() {
+ $doc = new stdClass();
+ $doc->_id = "attachment_doc";
+ $file_path = dirname(__FILE__) . "/resources/couch-logo.pdf";
+ $this->db->add_attachment_file($doc, "foo.pdf", $file_path, "application/pdf");
+ $db_doc = $this->db->save($doc);
+ $this->assertTrue(is_object($db_doc->_attachments), "Inline attachment of file successful");
+
+ $doc = new stdClass();
+ $doc->_id = "attachment_doc_autodetect";
+ $file_path = dirname(__FILE__) . "/resources/couch-logo.pdf";
+ $this->db->add_attachment_file($doc, "foo.pdf", $file_path);
+ $db_doc = $this->db->save($doc);
+ $this->assertTrue(is_object($db_doc->_attachments), "Inline attachment of file successful w/ mime type auto-detection");
+ }
+
+ public function test_view_lifecycle() {
+ $this->_create_some_sample_docs();
+
+ $map_src = <<<VIEW
+function(doc) {
+ if(doc.date && doc.title) {
+ emit(doc.date, doc.title);
+ }
+}
+VIEW;
+
+ $view = $this->db->save_view("foo_views", "bar_view", $map_src);
+ $this->assertEquals("_design/foo_views", $view->_id, "View Creation Success");
+
+ $view = $this->db->get_view("foo_views", "bar_view");
+ $this->assertEquals(3, $view->total_rows, "Running a View Success");
+
+ $map_src = <<<VIEW
+function(doc) {
+ if(doc.date) {
+ emit(doc.date, doc);
+ }
+}
+VIEW;
+
+ $view = $this->db->save_view("foo_views", "bar_view", $map_src);
+ $this->assertEquals("_design/foo_views", $view->_id, "View Update Success");
+
+ $view = $this->db->get_view("foo_views", "bar_view");
+ $this->assertEquals("Well hello and welcome to my new blog...", $view->rows[0]->value->body, "Running a View Success (after update)");
+
+ $view = $this->db->get_view("foo_views", "bar_view", "2009/02/17 21:13:39");
+ $this->assertEquals("Bought a Cat", $view->rows[0]->value->title, "Running a Parametrized View");
+
+ $view = $this->db->get_view("foo_views", "bar_view", array("2009/01/30 18:04:11", "2009/02/17 21:13:39"));
+ $this->assertEquals("Biking", $view->rows[0]->value->title, "Running a Parametrized View with range");
+
+ $view = $this->db->get_view("foo_views", "bar_view", array("2009/02/17 21:13:39", "2009/01/30 18:04:11"), true);
+ $this->assertEquals("Bought a Cat", $view->rows[0]->value->title, "Running a Parametrized View with range, descending");
+ $this->assertEquals(2, count($view->rows), "Running a Parametrized View with range, descending [count]");
+
+}
+
+ function test_two_views_in_a_design_doc() {
+
+ $map_src = <<<VIEW
+function(doc) {
+ if(doc.date && doc.title) {
+ emit(doc.date, doc.title);
+ }
+}
+VIEW;
+
+ $view = $this->db->save_view("a_settee_design_doc", "foo_view", $map_src);
+ $this->assertTrue(isset($view->views->foo_view), "View1 Creation Success");
+
+ $view = $this->db->save_view("a_settee_design_doc", "bar_view", $map_src);
+ $this->assertTrue(isset($view->views->bar_view), "View2 Creation Success");
+ }
+
+ /**
+ * Create some sample docs for running tests on them.
+ *
+ * <p>This sample was taken from a wonderful book:
+ * CouchDB: The Definitive Guide (Animal Guide) by J. Chris Anderson, Jan Lehnardt and Noah Slater
+ * http://www.amazon.com/CouchDB-Definitive-Guide-Relax-Animal/dp/0596155891/ref=sr_1_1?ie=UTF8&qid=1311533443&sr=8-1
+ *
+ * @return void
+ */
+ private function _create_some_sample_docs() {
+ $doc = new stdClass();
+ $doc->_id = "biking";
+ $doc->title = "Biking";
+ $doc->body = "My biggest hobby is mountainbiking";
+ $doc->date = "2009/01/30 18:04:11";
+ $this->db->save($doc);
+
+ $doc = new stdClass();
+ $doc->_id = "bought-a-cat";
+ $doc->title = "Bought a Cat";
+ $doc->body = "I went to the the pet store earlier and brought home a little kitty...";
+ $doc->date = "2009/02/17 21:13:39";
+ $this->db->save($doc);
+
+ $doc = new stdClass();
+ $doc->_id = "hello-world";
+ $doc->title = "Hello World";
+ $doc->body = "Well hello and welcome to my new blog...";
+ $doc->date = "2009/01/15 15:52:20";
+ $this->db->save($doc);
+ }
+
+ public function tearDown() {
+ $ret = $this->server->drop_db($this->db);
+ }
+
+}
+
+
--- /dev/null
+++ b/couchdb/settee/tests/SetteeRestClientTest.php
@@ -1,1 +1,90 @@
+<?php
+require_once (realpath(dirname(__FILE__) . '/../src/settee.php'));
+require_once (dirname(__FILE__) . '/SetteeTestCase.class.php');
+
+class SetteeRestClientTest extends SetteeTestCase {
+
+ private $rest_client;
+
+ public function setUp() {
+ parent::setUp();
+ $this->rest_client = SetteeRestClient::get_instance($this->db_url);
+ }
+
+ public function test_get_full_url() {
+
+ //-- Can't run this test in PHP versions earlier than 5.3.2, which do not support ReflectionMethod class.
+ if (!class_exists('ReflectionMethod')) {
+ return;
+ }
+
+ //-- Prepare for testing the private full_url_method method.
+ $get_full_url_method = new ReflectionMethod('SetteeRestClient', 'get_full_url');
+ $get_full_url_method->setAccessible(TRUE);
+
+ $uri = 'irakli/26cede9ab9cd8fcd67895eb05200d1ea';
+ //-- Equivalent to: $calc = $this->rest_client->get_full_url($uri); but for a private method.
+ $calc = $get_full_url_method->invokeArgs($this->rest_client, array($uri));
+ //--
+ $expected = $this->db_url . '/irakli/26cede9ab9cd8fcd67895eb05200d1ea';
+ $this->assertEquals($expected, $calc, "Full URL Generation with DB and ID");
+
+ $uri = 'irakli/26cede9ab9cd8fcd67895eb05200d1ea?rev=2-21587f7dffc43b4100f40168f309a267';
+ $calc = $get_full_url_method->invokeArgs($this->rest_client, array($uri));
+ $expected = $this->db_url . '/irakli/26cede9ab9cd8fcd67895eb05200d1ea?rev=2-21587f7dffc43b4100f40168f309a267';
+ $this->assertEquals($expected, $calc, "Full URL Generation with DB, ID and Single Query Parameter");
+
+ $uri = 'irakli/26cede9ab9cd8fcd67895eb05200d1ea?rev=2-21587f7dffc43b4100f40168f309a267&second=foo';
+ $calc = $get_full_url_method->invokeArgs($this->rest_client, array($uri));
+ $expected = $this->db_url . '/irakli/26cede9ab9cd8fcd67895eb05200d1ea?rev=2-21587f7dffc43b4100f40168f309a267&second=foo';
+ $this->assertEquals($expected, $calc, "Full URL Generation with DB, ID and Two Query Parameters");
+
+ }
+
+ public function test_file_mime_type() {
+
+ $type = $this->rest_client->file_mime_type(dirname(__FILE__) . "/resources/couch-logo.jpg");
+ $this->assertEquals("image/jpeg", $type, "Jpeg Mime Type Detection");
+
+ $type = $this->rest_client->file_mime_type(dirname(__FILE__) . "/resources/couch-logo.pdf");
+ $this->assertEquals("application/pdf", $type, "PDF Mime Type Detection");
+
+
+ $type = $this->rest_client->file_mime_type(dirname(__FILE__) . "/resources/couch-logo.png");
+ $this->assertEquals("image/png", $type, "PNG Mime Type Detection");
+
+ $type = $this->rest_client->file_mime_type(dirname(__FILE__) . "/resources/couch-tag.ini");
+ $this->assertEquals("text/plain", $type, "Text Mime Type Detection");
+
+ $type = $this->rest_client->file_mime_type(dirname(__FILE__) . "/resources/couch-tag.xml");
+ $this->assertEquals("application/xml", $type, "XML Mime Type Detection");
+ }
+
+ public function test_content_mime_type() {
+ $content = file_get_contents(dirname(__FILE__) . "/resources/couch-logo.jpg");
+ $type = $this->rest_client->content_mime_type($content);
+ $this->assertEquals("image/jpeg", $type, "Jpeg Mime Type Detection");
+
+ $content = file_get_contents(dirname(__FILE__) . "/resources/couch-logo.pdf");
+ $type = $this->rest_client->content_mime_type($content);
+ $this->assertEquals("application/pdf", $type, "PDF Mime Type Detection");
+
+ $content = file_get_contents(dirname(__FILE__) . "/resources/couch-logo.png");
+ $type = $this->rest_client->content_mime_type($content);
+ $this->assertEquals("image/png", $type, "PNG Mime Type Detection");
+
+ $content = file_get_contents(dirname(__FILE__) . "/resources/couch-tag.ini");
+ $type = $this->rest_client->content_mime_type($content);
+ $this->assertEquals("text/plain", $type, "Text Mime Type Detection");
+
+ $content = file_get_contents(dirname(__FILE__) . "/resources/couch-tag.xml");
+ $type = $this->rest_client->content_mime_type($content);
+ $this->assertEquals("application/xml", $type, "XML Mime Type Detection");
+ }
+
+
+
+}
+
+
--- /dev/null
+++ b/couchdb/settee/tests/SetteeServerTest.php
@@ -1,1 +1,43 @@
+<?php
+require_once (realpath(dirname(__FILE__) . '/../src/settee.php'));
+require_once (dirname(__FILE__) . '/SetteeTestCase.class.php');
+
+class SetteeServerTest extends SetteeTestCase {
+
+ private $dbname;
+
+ public function setUp() {
+ parent::setUp();
+ $this->dbname = "settee_tests_" . md5(microtime(true));
+ }
+
+ public function test_database_lifecycle_namebased() {
+ $db = $this->server->get_db($this->dbname);
+ $ret = $this->server->create_db($this->dbname);
+ $this->assertTrue($ret->ok, "Database Creation Success Response [name-based]");
+
+ $database_list = $this->server->list_dbs();
+ $this->assertTrue(is_array($database_list) && in_array($this->dbname, $database_list),
+ "Verifying Database in the List on the Server [name-based]");
+
+ $ret = $this->server->drop_db($this->dbname);
+ $this->assertTrue($ret->ok, "Database Deletion Success Response [name-based]");
+ }
+
+ public function test_database_lifecycle_objectbased() {
+ $db = $this->server->get_db($this->dbname);
+ $ret = $this->server->create_db($db);
+ $this->assertTrue($ret->ok, "Database Creation Success Response [object-based]");
+
+ $database_list = $this->server->list_dbs();
+ $this->assertTrue(is_array($database_list) && in_array($this->dbname, $database_list),
+ "Verifying Database in the List on the Server [object-based]");
+
+ $ret = $this->server->drop_db($db);
+ $this->assertTrue($ret->ok, "Database Deletion Success Response [object-based]");
+ }
+
+}
+
+
--- /dev/null
+++ b/couchdb/settee/tests/SetteeTestCase.class.php
@@ -1,1 +1,20 @@
+<?php
+/**
+ * Abstract parent for Settee test classes.
+ */
+abstract class SetteeTestCase extends PHPUnit_Framework_TestCase {
+
+ protected $server;
+ protected $db_url;
+ protected $db_user;
+ protected $db_pass;
+
+ public function setUp() {
+ $this->db_url = isset($GLOBALS['db_url']) ? $GLOBALS['db_url'] : 'http://127.0.0.1:5984';
+ $this->db_user = isset($GLOBALS['db_user']) ? $GLOBALS['db_user'] : 'admin';
+ $this->db_pass = isset($GLOBALS['db_pass']) ? $GLOBALS['db_pass'] : 'admin';
+ $this->server = new SetteeServer($this->db_url);
+ }
+
+}
--- /dev/null
+++ b/couchdb/settee/tests/phpunitConfig.xml
@@ -1,1 +1,8 @@
+<phpunit>
+ <php>
+ <var name="db_url" value="http://127.0.0.1:5984"/>
+ <var name="db_user" value="admin"/>
+ <var name="db_pass" value="passwd"/>
+ </php>
+</phpunit>
Binary files /dev/null and b/couchdb/settee/tests/resources/couch-logo.jpg differ
Binary files /dev/null and b/couchdb/settee/tests/resources/couch-logo.pdf differ
Binary files /dev/null and b/couchdb/settee/tests/resources/couch-logo.png differ
--- /dev/null
+++ b/couchdb/settee/tests/resources/couch-tag.ini
@@ -1,1 +1,2 @@
+Couchdb=relax
--- /dev/null
+++ b/couchdb/settee/tests/resources/couch-tag.xml
@@ -1,1 +1,5 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<tagline>
+ <main>CouchDB - Relax</main>
+</tagline>
--- a/documents/disclogsList.php
+++ b/documents/disclogsList.php
@@ -12,6 +12,7 @@
$disclogs = 0;
$red = 0;
$green = 0;
+$yellow = 0;
$orange = 0;
try {
$rows = $agenciesdb->get_view("app", "byCanonicalName", null, true)->rows;
@@ -19,46 +20,56 @@
if ($rows) {
foreach ($rows as $row) {
+ if ((!isset($row->value->status) || $row->value->status != "suspended") && isset($row->value->foiEmail)) {
+ echo "<tr><td>";
+ if (isset($row->value->website)) echo "<a href='" . $row->value->website . "'>";
+ echo "<b>" . $row->value->name . "</b>";
+ if (isset($row->value->website)) echo "</a>";
+ if ($ENV == "DEV")
+ echo "<br>(" . $row->id . ")";
+ echo "</td>\n";
+ $agencies++;
- echo "<tr><td><b>" . $row->value->name . "</b>";
- if ($ENV == "DEV")
- echo "<br>(" . $row->id . ")";
- echo "</td>\n";
-$agencies++;
-
- echo "<td>";
- if (isset($row->value->FOIDocumentsURL)) {
- $disclogs++;
- echo '<a href="' . $row->value->FOIDocumentsURL . '">'
- . $row->value->FOIDocumentsURL . '</a>';
- if ($ENV == "DEV")
- echo '<br><small>(<a href="viewDocument.php?hash=' . md5($row->value->FOIDocumentsURL) . '">'
- . 'view local copy</a>)</small>';
- } else {
- echo "<font color='red'><abbr title='No'>✘</abbr></font>";
- }
- echo "</td>\n<td>";
- if (isset($row->value->FOIDocumentsURL)) {
- if (file_exists("./scrapers/" . $row->id . '.py')) {
- echo "<font color='green'><abbr title='Yes'>✔</abbr></font>";
- $green++;
- } else if (file_exists("./scrapers/" . $row->id . '.txt')) {
- echo "<font color='orange'><abbr title='Work in progress'><b>▬</b></abbr></font>";
- $orange++;
+ echo "<td>";
+ if (isset($row->value->FOIDocumentsURL)) {
+ $disclogs++;
+ echo '<a href="' . $row->value->FOIDocumentsURL . '">'
+ . $row->value->FOIDocumentsURL . '</a>';
+ if ($ENV == "DEV")
+ echo '<br><small>(<a href="viewDocument.php?hash=' . md5($row->value->FOIDocumentsURL) . '">'
+ . 'view local copy</a>)</small>';
} else {
echo "<font color='red'><abbr title='No'>✘</abbr></font>";
- $red++;
}
+ echo "</td>\n<td>";
+ if (isset($row->value->FOIDocumentsURL)) {
+ if (file_exists("./scrapers/" . $row->id . '.py')) {
+ echo "<font color='green'><abbr title='Yes'>✔</abbr></font>";
+ $green++;
+ } else if (file_exists("./scrapers/" . $row->id . '.txt')) {
+ if (trim(file_get_contents("./scrapers/" . $row->id . '.txt')) == "no disclog") {
+ echo "<font color='yellow'><abbr title='No log table exists at URL to scrape'><b>◎</b></abbr></font>";
+ $yellow++;
+ } else {
+ echo file_get_contents("./scrapers/" . $row->id . '.txt');
+ echo "<font color='orange'><abbr title='Work in progress'><b>▬</b></abbr></font>";
+ $orange++;
+ }
+ } else {
+ echo "<font color='red'><abbr title='No'>✘</abbr></font>";
+ $red++;
+ }
+ }
+ echo "</td></tr>\n";
}
- echo "</td></tr>\n";
}
}
} catch (SetteeRestClientException $e) {
setteErrorHandler($e);
}
echo "</table>";
-echo $agencies." agencies, ".round(($disclogs/$agencies)*100)."% with disclosure logs; "
-.round(($green/$disclogs)*100)."% logs with scrapers ".round(($red/$disclogs)*100)."% logs without scrapers ".round(($orange/$disclogs)*100)."% logs Work-In-Progress scrapers ";
+echo $agencies . " agencies, " . round(($disclogs / $agencies) * 100) . "% with disclosure logs; "
+ . round(($green / $disclogs) * 100) . "% logs with scrapers " . round(($red / $disclogs) * 100) . "% logs without scrapers " . round(($orange / $disclogs) * 100) . "% logs Work-In-Progress scrapers ";
include_footer_documents();
?>
--- a/documents/genericScrapers.py
+++ b/documents/genericScrapers.py
@@ -9,6 +9,7 @@
import dateutil
from dateutil.parser import *
from datetime import *
+import codecs
class GenericDisclogScraper(object):
__metaclass__ = abc.ABCMeta
@@ -92,7 +93,8 @@
return table.find_all('tr')
def getDate(self, content, entry, doc):
date = ''.join(content.stripped_strings).strip()
- date = date.replace("Octber","October")
+ (a,b,c) = date.partition("(")
+ date = self.remove_control_chars(a.replace("Octber","October"))
print date
edate = parse(date, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d")
print edate
@@ -119,7 +121,7 @@
columns = row.find_all('td')
if len(columns) == self.getColumnCount():
(id, date, title, description, notes) = self.getColumns(columns)
- print ''.join(id.stripped_strings)
+ print self.remove_control_chars(''.join(id.stripped_strings))
if id.string == None:
hash = scrape.mkhash(self.remove_control_chars(url+(''.join(date.stripped_strings))))
else:
--- a/documents/index.php
+++ b/documents/index.php
@@ -1,11 +1,11 @@
<?php
+
include('template.inc.php');
include_header_documents("");
include_once('../include/common.inc.php');
+$startkey = (isset($_REQUEST['start_key']) ? $_REQUEST['start_key'] : '9999-99-99');
?>
<?php
-
-
$agenciesdb = $server->get_db('disclosr-agencies');
@@ -15,17 +15,17 @@
}
$foidocsdb = $server->get_db('disclosr-foidocuments');
try {
- $rows = $foidocsdb->get_view("app", "byDate", Array('9999-99-99','0000-00-00'), true)->rows;
-
-
+ $rows = $foidocsdb->get_view("app", "byDate", Array($startkey, '0000-00-00'), true, 20)->rows;
if ($rows) {
- foreach ($rows as $row) {
-echo displayLogEntry($row,$idtoname);
+ foreach ($rows as $key => $row) {
+ echo displayLogEntry($row, $idtoname);
+ $endkey = $row->key;
}
}
} catch (SetteeRestClientException $e) {
setteErrorHandler($e);
}
+echo "<a href='?start_key=$endkey'>next page</a>";
include_footer_documents();
?>
--- a/documents/rss.xml.php
+++ b/documents/rss.xml.php
@@ -11,7 +11,7 @@
//Use wrapper functions for common channelelements
$TestFeed->setTitle('Last Modified - All');
$TestFeed->setLink('http://disclosurelo.gs/rss.xml.php');
-$TestFeed->setDescription('This is test of creating a RSS 2.0 feed Universal Feed Writer');
+$TestFeed->setDescription('Latest entries');
$TestFeed->setChannelElement('language', 'en-us');
$TestFeed->setChannelElement('pubDate', date(DATE_RSS, time()));
//Retriving informations from database
@@ -21,7 +21,7 @@
$idtoname[$row->id] = trim($row->value->name);
}
$foidocsdb = $server->get_db('disclosr-foidocuments');
-$rows = $foidocsdb->get_view("app", "byDate", Array('9999-99-99','0000-00-00'), true)->rows;
+$rows = $foidocsdb->get_view("app", "byDate", Array('9999-99-99','0000-00-00', 50), true)->rows;
//print_r($rows);
foreach ($rows as $row) {
//Create an empty FeedItem
@@ -38,3 +38,4 @@
//OK. Everything is done. Now genarate the feed.
$TestFeed->generateFeed();
?>
+
--- /dev/null
+++ b/documents/runScrapers.sh
@@ -1,1 +1,3 @@
+for f in scrapers/*.py; do echo "Processing $f file.."; python $f; done
+
--- /dev/null
+++ b/documents/scrapers/0049d35216493c545ef5f7f000e6b252.txt
@@ -1,1 +1,2 @@
+pdf
--- /dev/null
+++ b/documents/scrapers/0372b19123076338d483f624c433727b.txt
@@ -1,1 +1,2 @@
+docx
--- /dev/null
+++ b/documents/scrapers/0ae822d1a748e60d90f0b79b97d5a3e5.txt
@@ -1,1 +1,2 @@
+ACMA style
--- /dev/null
+++ b/documents/scrapers/0ced9dd2de36100c3cabdb7fd8e843a9.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/1d404c4934f74feacd00dcb434e7c10a.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "cphMain_C001_Col01").table
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/2cac2cd1f42687db2d04fa20b5b6a538.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 3
+ def getColumns(self,columns):
+ (id, title, date) = columns
+ return (id, date, title, title, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/3e2f110af49d62833a835bd257771ffb.txt
@@ -1,1 +1,2 @@
+no disclog
--- /dev/null
+++ b/documents/scrapers/4c57389dda9bd454bcb08bc1e5ed87bf.txt
@@ -1,1 +1,2 @@
+parent
--- /dev/null
+++ b/documents/scrapers/4d2af2dcc72f1703bbf04b13b03720a8.txt
@@ -1,1 +1,2 @@
+no disclog
--- /dev/null
+++ b/documents/scrapers/525c3953187da08cd702359b2fc2997f.txt
@@ -1,1 +1,2 @@
+no disclog
--- /dev/null
+++ b/documents/scrapers/54cbb3439276062b7a9f007f9f69d1f6.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 4
+ def getColumns(self,columns):
+ (id, date, title, description) = columns
+ return (id, date, title, description, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- a/documents/scrapers/627f116dfe42c9f27ad6747be0aa44e2.txt
+++ b/documents/scrapers/627f116dfe42c9f27ad6747be0aa44e2.txt
@@ -1,2 +1,1 @@
-see parent dhs
-
+no disclog
--- /dev/null
+++ b/documents/scrapers/655d4d67333536bda18d68265dfe7e80.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getTable(self,soup):
+ return soup.find(id="node-30609")
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/656f7bb1884f4b9d31ebe2a5f5f58064.txt
@@ -1,1 +1,2 @@
+list style
--- /dev/null
+++ b/documents/scrapers/65ec17101b00519e6d88c5a9f33c2c46.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 3
+ def getColumns(self,columns):
+ (id, date, description) = columns
+ return (id, date, description, description, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/69d59284ef0ccd2677394d82d3292abc.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getTable(self,soup):
+ return soup.find(id = "centercontent").table
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/6ac74a939f420c6194ae29224809734a.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/768bbbfb34115873af361af8519b38a9.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/794ea270edc9aa4f70f2a84bbc5ecc7a.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getTable(self,soup):
+ return soup.find(id = "cphMain_C001_Col01").table
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/795e7a8afb39a420360aa207b0cb1306.txt
@@ -1,1 +1,2 @@
+no disclog
--- /dev/null
+++ b/documents/scrapers/7b39ce7f362a0af9a711eaf223943eea.txt
@@ -1,1 +1,2 @@
+no disclog
--- a/documents/scrapers/7c6adc1d41cf029bf1a0959e5156477a.txt
+++ b/documents/scrapers/7c6adc1d41cf029bf1a0959e5156477a.txt
@@ -1,1 +1,1 @@
-
+acma style
--- /dev/null
+++ b/documents/scrapers/7ec28d7d97fcf493b1350acd03e3642e.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 3
+ def getColumns(self,columns):
+ (date, title, description) = columns
+ return (date, date, title, description, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/7f55a3c42ad7460254906aa043a6e324.py
@@ -1,1 +1,24 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getTitle(self, content, entry, doc):
+ doc.update({'title': content.stripped_strings.next()})
+ return
+ def getColumnCount(self):
+ return 3
+ def getColumns(self,columns):
+ (date, id, description) = columns
+ return (id, date, description, description, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/8317df630946937864d31a4728ad8ee8.txt
@@ -1,1 +1,2 @@
+pdf
--- /dev/null
+++ b/documents/scrapers/8aae1c28db7f3ce10f232a0137be6bb2.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/8e874a2fde8aa0ccdc6d14573d766540.py
@@ -1,1 +1,86 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+import codecs
+#http://www.doughellmann.com/PyMOTW/abc/
+class NewScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getDescription(self,content, entry,doc):
+ link = None
+ links = []
+ description = ""
+ for atag in entry.find_all('a'):
+ if atag.has_key('href'):
+ link = scrape.fullurl(self.getURL(),atag['href'])
+ (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, link, "foidocuments", self.getAgencyID(), False)
+ if htcontent != 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(htcontent)
+ for text in soup.find(id="divFullWidthColumn").stripped_strings:
+ description = description + text.encode('ascii', 'ignore')
+
+ for atag in soup.find(id="divFullWidthColumn").find_all("a"):
+ if atag.has_key('href'):
+ links.append(scrape.fullurl(link,atag['href']))
+ if links != []:
+ doc.update({'links': links})
+ if description != "":
+ doc.update({ 'description': description})
+
+ def getColumnCount(self):
+ return 2
+ def getTable(self,soup):
+ return soup.find(id = "TwoColumnSorting")
+ def getColumns(self,columns):
+ ( title, date) = columns
+ return (title, date, title, title, None)
+class OldScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getDescription(self,content, entry,doc):
+ link = None
+ links = []
+ description = ""
+ for atag in entry.find_all('a'):
+ if atag.has_key('href'):
+ link = scrape.fullurl(self.getURL(),atag['href'])
+ (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, link, "foidocuments", self.getAgencyID(), False)
+ if htcontent != 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(htcontent)
+ for text in soup.find(id="content-item").stripped_strings:
+ description = description + text + " \n"
+ for atag in soup.find(id="content-item").find_all("a"):
+ if atag.has_key('href'):
+ links.append(scrape.fullurl(link,atag['href']))
+ if links != []:
+ doc.update({'links': links})
+ if description != "":
+ doc.update({ 'description': description})
+
+ if links != []:
+ doc.update({'links': links})
+ if description != "":
+ doc.update({ 'description': description})
+
+ def getColumnCount(self):
+ return 2
+ def getTable(self,soup):
+ return soup.find(class_ = "doc-list")
+ def getColumns(self,columns):
+ (date, title) = columns
+ return (title, date, title, title, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(NewScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(NewScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ #NewScraperImplementation().doScrape()
+ print 'Subclass:', issubclass(OldScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(OldScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ osi = OldScraperImplementation()
+ osi.disclogURL = "http://archive.treasury.gov.au/content/foi_publications.asp?year=-1&abstract=0&classification=&=&titl=Disclosure+Log+-+Documents+Released+Under+FOI"
+ osi.doScrape()
+# old site too
+
--- a/documents/scrapers/8e874a2fde8aa0ccdc6d14573d766540.txt
+++ /dev/null
@@ -1,49 +1,1 @@
-import sys,os
-sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
-import genericScrapers
-import scrape
-from bs4 import BeautifulSoup
-#http://www.doughellmann.com/PyMOTW/abc/
-class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
- def getDescription(self,content, entry,doc):
- link = None
- links = []
- description = ""
- for atag in entry.find_all('a'):
- if atag.has_key('href'):
- link = scrape.fullurl(self.getURL(),atag['href'])
- (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, link, "foidocuments", self.getAgencyID(), False)
- if htcontent != 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(htcontent)
- for row in soup.find(class_ = "ms-rteTable-GreyAlternating").find_all('tr'):
- if row != None:
- rowtitle = row.find('th').string
- description = description + "\n" + rowtitle + ": "
- for text in row.find('td').stripped_strings:
- description = description + text
- for atag in row.find_all("a"):
- if atag.has_key('href'):
- links.append(scrape.fullurl(link,atag['href']))
-
- if links != []:
- doc.update({'links': links})
- if description != "":
- doc.update({ 'description': description})
-
- def getColumnCount(self):
- return 2
- def getTable(self,soup):
- return soup.find(class_ = "ms-rteTable-GreyAlternating")
- def getColumns(self,columns):
- (date, title) = columns
- return (title, date, title, title, None)
-
-if __name__ == '__main__':
- print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
- print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
- ScraperImplementation().doScrape()
-# old site too http://archive.treasury.gov.au/content/foi_publications.asp
-
--- /dev/null
+++ b/documents/scrapers/9282306e244040c9e4ae5705f06f9548.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 4
+ def getColumns(self,columns):
+ (id, date, title, description) = columns
+ return (id, date, title, description, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/93ce83e46f5c2c4ca1b7f199b59b4bd2.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 4
+ def getColumns(self,columns):
+ (id, date,logdate, description) = columns
+ return (id, date, description, description, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/99328d76c8efb56ff3f1da79b9d1b17f.txt
@@ -1,1 +1,2 @@
+acma style
--- /dev/null
+++ b/documents/scrapers/9961dc45e046288ad1431941653af20c.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/9f4815bfdcb918a036e4bb43a30f8d77.txt
@@ -1,1 +1,1 @@
-
+no disclog
--- /dev/null
+++ b/documents/scrapers/a1ab9c80ab473958676c62c1a25dd502.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/a43467fe82b840a353b380c4d7462a4c.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 3
+ def getColumns(self,columns):
+ (date, title, description) = columns
+ return (date, date, title, description, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/a687a9eaab9e10e9e118d3fd7cf0e13a.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getTable(self,soup):
+ return soup.find(id="ctl00_ContentPlaceHolderMainNoAjax_EdtrTD1494_2").table
+ def getColumnCount(self):
+ return 4
+ def getColumns(self,columns):
+ (blank,id, title,date) = columns
+ return (id, date, title, title, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/b91f866928eb61959dbbab56313214fc.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- a/documents/scrapers/bb96fe4065afb7e0872136dd657f9369.txt
+++ b/documents/scrapers/bb96fe4065afb7e0872136dd657f9369.txt
@@ -1,2 +1,1 @@
-# does not have any disclog entries or table
-
+no disclog
--- /dev/null
+++ b/documents/scrapers/bc91b878e2317fa231cc2c512e2027f0.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 4
+ def getColumns(self,columns):
+ (id, date, title, description) = columns
+ return (id, date, title, description, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/bf16d4ba0d306ee03e5a1d32aaba3da1.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getTable(self,soup):
+ return soup.find(summary="This table shows every FOI request to date.")
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- a/documents/scrapers/bf6e587f166040b63681cd2ff76fbfdf.txt
+++ b/documents/scrapers/bf6e587f166040b63681cd2ff76fbfdf.txt
@@ -1,1 +1,1 @@
-no disclog yet
+no disclog
--- a/documents/scrapers/cb7f40e3495b682de6eee61bf09c1cfc.txt
+++ b/documents/scrapers/cb7f40e3495b682de6eee61bf09c1cfc.txt
@@ -1,2 +1,1 @@
-no log
-
+no disclog
--- /dev/null
+++ b/documents/scrapers/cca17a34bd490474a316fe0a1ca03c25.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getTable(self,soup):
+ return soup.find(id = "ctl00_PlaceHolderMain_ctl01__ControlWrapper_RichHtmlField").table
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/cde8eb4a2e40abb18d8b28d3b85bc9b0.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getTable(self,soup):
+ return soup.find(summary="This table lists the schedule of upcoming courses.")
+ def getColumnCount(self):
+ return 7
+ def getColumns(self,columns):
+ (id, date, title, description,link,deldate,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/ce34d1e9b55911e4272d2d388821f311.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/d1296c366287f7a9faedf235c7e6df01.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ def getTable(self,soup):
+ return soup.find(id="main").table
+ def getColumnCount(self):
+ return 7
+ def getColumns(self,columns):
+ (id, date, title, description,link,deldate,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- a/documents/scrapers/d72744fb1e5d6e87af9a5ea16cc27fa5.txt
+++ b/documents/scrapers/d72744fb1e5d6e87af9a5ea16cc27fa5.txt
@@ -1,1 +1,1 @@
-
+acma style
--- /dev/null
+++ b/documents/scrapers/e0614dc3a9e25d375370ffd82f7165ac.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 6
+ def getColumns(self,columns):
+ (id, date, title, description,deldate, notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/e64c71f4986f78675a252104c5a5f359.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 5
+ def getColumns(self,columns):
+ (id, date, title, description,notes) = columns
+ return (id, date, title, description, notes)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/e770921522a49dc77de208cc724ce134.txt
@@ -1,1 +1,1 @@
-
+no disclog
--- /dev/null
+++ b/documents/scrapers/ee30aad97f0bb32e74c4587404b67ce4.py
@@ -1,1 +1,21 @@
+import sys,os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
+import genericScrapers
+import scrape
+from bs4 import BeautifulSoup
+#http://www.doughellmann.com/PyMOTW/abc/
+class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
+ #def getTable(self,soup):
+ # return soup.find(id = "ctl00_PlaceHolderMain_intro2__ControlWrapper_CerRichHtmlField").table
+ def getColumnCount(self):
+ return 4
+ def getColumns(self,columns):
+ (id, title, date, description) = columns
+ return (id, date, title, description, None)
+
+if __name__ == '__main__':
+ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
+ print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
+ ScraperImplementation().doScrape()
+
--- /dev/null
+++ b/documents/scrapers/f189459fc43f941e0d4ecfba52c666f3.txt
@@ -1,1 +1,2 @@
+no disclog
--- a/documents/template.inc.php
+++ b/documents/template.inc.php
@@ -21,7 +21,7 @@
<!-- Mobile viewport optimized: h5bp.com/viewport -->
<meta name="viewport" content="width=device-width">
-
+<link rel="alternate" type="application/rss+xml" title="Latest Disclosure Log Entries" href="rss.xml.php" />
<!-- Place favicon.ico and apple-touch-icon.png in the root directory: mathiasbynens.be/notes/touch-icons -->
<meta name="google-site-verification" content="jkknX5g2FCpQvrW030b1Nq2hyoa6mb3EDiA7kCoHNj8" />
@@ -145,7 +145,7 @@
$result .= "</ul>";
}
- $result .= "<small><A href='".$row->value->url."'>View original source...</a> ID: ".$row->value->docID."</small>";
+ $result .= "<small><A href='".$row->value->url."'>View original source...</a> ID: ".strip_tags($row->value->docID)."</small>";
$result .= "</div>";
return $result;
}
