From e616f166ae9ffaf350468e510fb21d16b36060a5 Mon Sep 17 00:00:00 2001
From: epriestley <git@epriestley.com>
Date: Wed, 13 Aug 2014 15:34:09 -0700
Subject: [PATCH] Provide a setup warning about using the default MySQL
 stopword file

Summary:
Fixes T2605.

  - Add a setup warning about the stopword file.
  - Provide a simpler stopword file.

Test Plan:
  - Hit setup warning.
  - Resolved it according to instructions.
  - Added "various" to a task, then searched for it, found the task.

Reviewers: btrahan

Reviewed By: btrahan

Subscribers: epriestley

Maniphest Tasks: T2605

Differential Revision: https://secure.phabricator.com/D10258
---
 resources/sql/stopwords.txt                   | 50 ++++++++++++++++++
 .../check/PhabricatorSetupCheckMySQL.php      | 52 +++++++++++++++++++
 ...PhabricatorDefaultSearchEngineSelector.php |  9 +++-
 3 files changed, 109 insertions(+), 2 deletions(-)
 create mode 100644 resources/sql/stopwords.txt

diff --git a/resources/sql/stopwords.txt b/resources/sql/stopwords.txt
new file mode 100644
index 0000000000..89f5d060f7
--- /dev/null
+++ b/resources/sql/stopwords.txt
@@ -0,0 +1,50 @@
+the
+be
+and
+of
+a
+in
+to
+have
+to
+it
+I
+that
+for
+you
+he
+with
+on
+do
+say
+this
+they
+at
+but
+we
+his
+from
+that
+not
+by
+or
+as
+what
+go
+their
+can
+who
+get
+if
+would
+all
+my
+will
+as
+up
+there
+so
+its
+us
+in
+on
diff --git a/src/applications/config/check/PhabricatorSetupCheckMySQL.php b/src/applications/config/check/PhabricatorSetupCheckMySQL.php
index 117cc2558e..57fe7af813 100644
--- a/src/applications/config/check/PhabricatorSetupCheckMySQL.php
+++ b/src/applications/config/check/PhabricatorSetupCheckMySQL.php
@@ -59,6 +59,58 @@ final class PhabricatorSetupCheckMySQL extends PhabricatorSetupCheck {
         ->setSummary($summary)
         ->setMessage($message);
     }
+
+    $stopword_file = queryfx_one($conn_raw, 'SELECT @@ft_stopword_file');
+    $stopword_file = $stopword_file['@@ft_stopword_file'];
+    if ($stopword_file == '(built-in)') {
+      if (!PhabricatorDefaultSearchEngineSelector::shouldUseElasticSearch()) {
+
+        $root = dirname(phutil_get_library_root('phabricator'));
+        $stopword_path = $root.'/resources/sql/stopwords.txt';
+        $stopword_path = Filesystem::resolvePath($stopword_path);
+
+        $namespace = PhabricatorEnv::getEnvConfig('storage.default-namespace');
+
+        $summary = pht(
+          'MySQL is using a default stopword file, which will prevent '.
+          'searching for many common words.');
+
+        $message = pht(
+          "Your MySQL instance is using the builtin stopword file for ".
+          "building search indexes. This can make Phabricator's search ".
+          "feature less useful.\n\n".
+          "Stopwords are common words which are not indexed and thus can not ".
+          "be searched for. The default stopword file has about 500 words, ".
+          "including various words which you are likely to wish to search ".
+          "for, such as 'various', 'likely', 'wish', and 'zero'.\n\n".
+          "To make search more useful, you can use an alternate stopword ".
+          "file with fewer words. Alternatively, if you aren't concerned ".
+          "about searching for common words, you can ignore this warning. ".
+          "If you later plan to configure ElasticSearch, you can also ignore ".
+          "this warning: this stopword file only affects MySQL fulltext ".
+          "indexes.\n\n".
+          "To choose a different stopword file, add this to your %s file ".
+          "(in the %s section) and then restart %s:\n\n".
+          "%s\n".
+          "(You can also use a different file if you prefer. The file ".
+          "suggested above has about 50 of the most common English words.)\n\n".
+          "Finally, run this command:\n\n".
+          "%s",
+          phutil_tag('tt', array(), 'my.cnf'),
+          phutil_tag('tt', array(), '[mysqld]'),
+          phutil_tag('tt', array(), 'mysqld'),
+          phutil_tag('pre', array(), 'ft_stopword_file='.$stopword_path),
+          phutil_tag(
+            'pre',
+            array(),
+            "mysql> REPAIR TABLE {$namespace}_search.search_documentfield;"));
+
+        $this->newIssue('mysql.ft_stopword_file')
+          ->setName(pht('MySQL is Using Default Stopword File'))
+          ->setSummary($summary)
+          ->setMessage($message);
+      }
+    }
   }
 
 }
diff --git a/src/applications/search/selector/PhabricatorDefaultSearchEngineSelector.php b/src/applications/search/selector/PhabricatorDefaultSearchEngineSelector.php
index aa8757ead1..2bd804ed30 100644
--- a/src/applications/search/selector/PhabricatorDefaultSearchEngineSelector.php
+++ b/src/applications/search/selector/PhabricatorDefaultSearchEngineSelector.php
@@ -4,11 +4,16 @@ final class PhabricatorDefaultSearchEngineSelector
   extends PhabricatorSearchEngineSelector {
 
   public function newEngine() {
-    $elastic_host = PhabricatorEnv::getEnvConfig('search.elastic.host');
-    if ($elastic_host) {
+    if (self::shouldUseElasticSearch()) {
+      $elastic_host = PhabricatorEnv::getEnvConfig('search.elastic.host');
       $elastic_index = PhabricatorEnv::getEnvConfig('search.elastic.namespace');
       return new PhabricatorSearchEngineElastic($elastic_host, $elastic_index);
     }
     return new PhabricatorSearchEngineMySQL();
   }
+
+  public static function shouldUseElasticSearch() {
+    return (bool)PhabricatorEnv::getEnvConfig('search.elastic.host');
+  }
+
 }