Merge pull request #12 from silverstripe-big-o/pull/custom-source-paths

ENHANCEMENT Configurable source paths for Solr config

code/solr/Solr.php

@@ -10,6 +10,12 @@ class Solr  {
 	 * port (default: 8983) - The port Solr is listening on
 	 * path (default: /solr) - The suburl the solr service is available on
 	 *
+	 * Optional fields:
+	 * extraspath (default: <basefolder>/fulltextsearch/conf/extras/) - Absolute path to 
+	 *   the folder containing templates which are used for generating the schema and field definitions.
+	 * templates (default: <basefolder>/fulltextsearch/conf/templates/) - Absolute path to 
+	 *   the configuration default files, e.g. solrconfig.xml.
+	 *
 	 * indexstore => an array with
 	 *
 	 *   mode - 'file' or 'webdav'
@@ -29,7 +35,9 @@ class Solr  {
 		self::$solr_options = array_merge(array(
 			'host' => 'localhost',
 			'port' => 8983,
-			'path' => '/solr'
+			'path' => '/solr',
+			'extraspath' => Director::baseFolder().'/fulltextsearch/conf/extras/',
+			'templatespath' => Director::baseFolder().'/fulltextsearch/conf/templates/',
 		), self::$solr_options, $options);
 	}
 
@@ -92,14 +100,17 @@ class Solr_Configure extends BuildTask {
 				$remote = isset($index['remotepath']) ? $index['remotepath'] : $local;
 				
 				foreach (Solr::get_indexes() as $index => $instance) {
-					$confdir = "$local/$index/conf";
-					if (!is_dir($confdir)) mkdir($confdir, 0770, true);
+					$sourceDir = $instance->getExtrasPath();
+					$targetDir = "$local/$index/conf";
+					if (!is_dir($targetDir)) mkdir($targetDir, 0770, true);
 
-					file_put_contents("$confdir/schema.xml", $instance->generateSchema());
+					file_put_contents("$targetDir/schema.xml", $instance->generateSchema());
 
-					foreach (glob(Director::baseFolder().'/fulltextsearch/conf/extras/*') as $file) {
-						if (is_file($file)) copy($file, $confdir.'/'.basename($file));
+					echo sprintf("Copying %s to %s...", $sourceDir, $targetDir);
+					foreach (glob($sourceDir . '/*') as $file) {
+						if (is_file($file)) copy($file, $targetDir.'/'.basename($file));
 					}
+					echo "done\n";
 				}
 					
 				break;
@@ -118,14 +129,17 @@ class Solr_Configure extends BuildTask {
 					$indexdir = "$url/$index";
 					if (!WebDAV::exists($indexdir)) WebDAV::mkdir($indexdir);
 
-					$confdir = "$url/$index/conf";
-					if (!WebDAV::exists($confdir)) WebDAV::mkdir($confdir);
+					$sourceDir = $instance->getExtrasPath();
+					$targetDir = "$url/$index/conf";
+					if (!WebDAV::exists($targetDir)) WebDAV::mkdir($targetDir);
 
-					WebDAV::upload_from_string($instance->generateSchema(), "$confdir/schema.xml");
+					WebDAV::upload_from_string($instance->generateSchema(), "$targetDir/schema.xml");
 
-					foreach (glob(Director::baseFolder().'/fulltextsearch/conf/extras/*') as $file) {
-						if (is_file($file)) WebDAV::upload_from_file($file, $confdir.'/'.basename($file));
+					echo sprintf("Copying %s to %s (via WebDAV)...", $sourceDir, $targetDir);
+					foreach (glob($sourceDir . '/*') as $file) {
+						if (is_file($file)) WebDAV::upload_from_file($file, $targetDir.'/'.basename($file));
 					}
+					echo "done\n";
 				}
 					
 				break;

code/solr/SolrIndex.php

@@ -24,8 +24,27 @@ abstract class SolrIndex extends SearchIndex {
 
 	static $sortTypeMap = array();
 
+	protected $extrasPath = null;
+
+	protected $templatesPath = null;
+	/**
+	 * @return String Absolute path to the folder containing
+	 * templates which are used for generating the schema and field definitions.
+	 */
+	function getTemplatesPath() {
+		return $this->templatesPath ? $this->templatesPath : Solr::$solr_options['templatespath'];
+	}
+
+	/**
+	 * @return String Absolute path to the configuration default files,
+	 * e.g. solrconfig.xml.
+	 */
+	function getExtrasPath() {
+		return $this->extrasPath ? $this->extrasPath : Solr::$solr_options['extraspath'];
+	}
+
 	function generateSchema() {
-		return $this->renderWith(Director::baseFolder() . '/fulltextsearch/conf/templates/schema.ss');
+		return $this->renderWith($this->getTemplatesPath() . '/schema.ss');
 	}
 
 	function getIndexName() {
@@ -33,7 +52,7 @@ abstract class SolrIndex extends SearchIndex {
 	}
 
 	function getTypes() {
-		return $this->renderWith(Director::baseFolder() . '/fulltextsearch/conf/templates/types.ss');
+		return $this->renderWith($this->getTemplatesPath() . '/types.ss');
 	}
 
 	function getFieldDefinitions() {

docs/Solr.md

@@ -32,10 +32,16 @@ by the user the Solr search server is started with (see below).
 		'host' => 'localhost',
 		'indexstore' => array(
 			'mode' => 'file',
-			'path' => BASE_PATH . '/fulltextsearch/thirdparty/fulltextsearch/server/solr'
+			'path' => BASE_PATH . '/.solr'
 		)
 	));
 
+Note: We recommend to put the `indexstore.path` directory outside of the webroot.
+If you place it inside of the webroot (as shown in the example),
+please ensure its contents are not accessible through the webserver.
+This can be achieved by server configuration, or (in most configurations)
+also by marking the folder as hidden via a "dot" prefix.
+
 Create an index
 
 	// File: mysite/code/MyIndex.php:
@@ -56,6 +62,16 @@ Initialize the configuration (via CLI)
 
 	sake dev/tasks/Solr_configure
 
+Based on the sample configuration above, this command will do the following:
+
+- Create a <BASE_PATH>/.solr/MyIndex` folder
+- Copy configuration files from `fulltextsearch/conf/extras/` to `<BASE_PATH>/.solr/MyIndex/conf`
+- Generate a `schema.xml`, and place it it in `<BASE_PATH>/.solr/MyIndex/conf`
+
+If you call the `Solr_configure` task with an existing index folder,
+it will overwrite all files from their default locations, 
+regenerate the `schema.xml`, and ask Solr to reload the configuration.
+
 ## Usage
 
 After configuring Solr, you have the option to add your existing
@@ -63,7 +79,14 @@ content to its indices. Run the following command:
 
 	sake dev/tasks/Solr_reindex
 
-This will rebuild all indices. You can narrow down the operation with the following options:
+This will delete and rebuild all indices. Depending on your data,
+this can take anywhere from minutes to hours.
+Keep in mind that the normal mode of updating indices is
+based on ORM manipulations of the underlying data.
+For example, calling `$myPage->write()` will automatically
+update the index entry for this record (and all its variants).
+
+You can narrow down the operation with the following options:
 
  - `index`: PHP class name of an index
  - `class`: PHP model class to reindex
@@ -72,9 +95,31 @@ This will rebuild all indices. You can narrow down the operation with the follow
  - `verbose`: Debug information
 
 Note: The Solr indexes will be stored as binary files inside your SilverStripe project. 
-You can also copy the `thirdparty/`solr directory somewhere else,
-just set the path value in `mysite/_config.php` to point to the new location.
-And of course run `java -jar start.jar` from the new directory.
+You can also copy the `thirdparty/` solr directory somewhere else,
+just set the `path` value in `mysite/_config.php` to point to the new location.
+
+### File-based configuration (solrconfig.xml etc)
+
+Many aspects of Solr are configured outside of the `schema.xml` file
+which SilverStripe generates based on the index PHP file.
+For example, stopwords are placed in their own `stopwords.txt` file,
+and spell checks are configured in `solrconfig.xml`.
+
+By default, these files are copied from the `fulltextsearch/conf/extras/`
+directory over to the new index location. In order to use your own files,
+copy these files into a location of your choosing (for example `mysite/data/solr/`),
+and tell Solr to use this folder with the `extraspath` configuration setting.
+	
+	// mysite/_config.php
+	Solr::configure_server(array(
+		// ...
+		'extraspath' => Director::baseFolder() . '/mysite/data/solr/',
+	));
+
+Please run the `Solr_configure` task for the changes to take effect.
+
+Note: You can also define those on an index-by-index basis by
+implementing `SolrIndex->getExtrasPath()`.
 
 ### Custom Types