Merge branch 'dk/search-improvements' into main

2022-11-24 10:29:18 +01:00 · 2022-11-24 10:29:18 +01:00 · 846cc348ff
parent 508bb42ac9 9401b677a3
commit 846cc348ff
11 changed files with 162 additions and 67 deletions
--- a/extend.php
+++ b/extend.php
@ -27,7 +27,12 @@ return [
    (new Flarum\Routes('api'))
        ->get('/blomstra/search/{type}', 'blomstra.search', Api\Controllers\SearchController::class)
        ->put('/blomstra/search/index', 'blomstra.search.index', Api\Controllers\IndexController::class),
-
-    (new Flarum\Console())
+    (new Flarum\Console)
        ->command(Commands\BuildCommand::class),
+
+    (new Flarum\Settings)
+        ->default('blomstra-search.search-discussion-subjects', true)
+        ->default('blomstra-search.search-post-bodies', true)
+        ->default('blomstra-search.match-sentences', true)
+        ->default('blomstra-search.match-words', true)
 ];
--- a/js/dist/admin.js
+++ b/js/dist/admin.js
@ -1,2 +1,2 @@
-(()=>{var a={n:e=>{var t=e&&e.__esModule?()=>e.default:()=>e;return a.d(t,{a:t}),t},d:(e,t)=>{for(var r in t)a.o(t,r)&&!a.o(e,r)&&Object.defineProperty(e,r,{enumerable:!0,get:t[r]})},o:(a,e)=>Object.prototype.hasOwnProperty.call(a,e),r:a=>{"undefined"!=typeof Symbol&&Symbol.toStringTag&&Object.defineProperty(a,Symbol.toStringTag,{value:"Module"}),Object.defineProperty(a,"__esModule",{value:!0})}},e={};(()=>{"use strict";a.r(e);const t=flarum.core.compat["admin/app"];var r=a.n(t);r().initializers.add("blomstra-search",(function(){var a=new Map;["arabic","armenian","basque","bengali","brazilian","bulgarian","catalan","cjk","czech","danish","dutch","english","estonian","finnish","french","galician","german","greek","hindi","hungarian","indonesian","irish","italian","latvian","lithuanian","norwegian","persian","portuguese","romanian","russian","sorani","spanish","swedish","turkish","thai"].forEach((function(e){a.set(e,e)})),r().extensionData.for("blomstra-search").registerSetting({setting:"blomstra-search.elastic-endpoint",label:r().translator.trans("blomstra-search.admin.elastic-endpoint"),type:"input"}).registerSetting({setting:"blomstra-search.elastic-username",label:r().translator.trans("blomstra-search.admin.elastic-username"),type:"input"}).registerSetting({setting:"blomstra-search.elastic-password",label:r().translator.trans("blomstra-search.admin.elastic-password"),type:"password"}).registerSetting({setting:"blomstra-search.elastic-index",label:r().translator.trans("blomstra-search.admin.elastic-index"),default:"flarum",type:"input"}).registerSetting({setting:"blomstra-search.analyzer-language",label:r().translator.trans("blomstra-search.admin.analyzer.label"),help:r().translator.trans("blomstra-search.admin.analyzer.help"),type:"select",options:Object.fromEntries(a.entries()),default:"english"}).registerSetting({setting:"blomstra-search.elastic-index",label:r().translator.trans("blomstra-search.admin.elastic-index"),default:"flarum",type:"input"})}))})(),module.exports=e})();
+(()=>{var a={n:t=>{var e=t&&t.__esModule?()=>t.default:()=>t;return a.d(e,{a:e}),e},d:(t,e)=>{for(var s in e)a.o(e,s)&&!a.o(t,s)&&Object.defineProperty(t,s,{enumerable:!0,get:e[s]})},o:(a,t)=>Object.prototype.hasOwnProperty.call(a,t),r:a=>{"undefined"!=typeof Symbol&&Symbol.toStringTag&&Object.defineProperty(a,Symbol.toStringTag,{value:"Module"}),Object.defineProperty(a,"__esModule",{value:!0})}},t={};(()=>{"use strict";a.r(t);const e=flarum.core.compat["admin/app"];var s=a.n(e);s().initializers.add("blomstra-search",(function(){var a=new Map;["arabic","armenian","basque","bengali","brazilian","bulgarian","catalan","cjk","czech","danish","dutch","english","estonian","finnish","french","galician","german","greek","hindi","hungarian","indonesian","irish","italian","latvian","lithuanian","norwegian","persian","portuguese","romanian","russian","sorani","spanish","swedish","turkish","thai"].forEach((function(t){a.set(t,t)})),s().extensionData.for("blomstra-search").registerSetting({setting:"blomstra-search.elastic-endpoint",label:s().translator.trans("blomstra-search.admin.elastic-endpoint"),type:"input"}).registerSetting({setting:"blomstra-search.elastic-username",label:s().translator.trans("blomstra-search.admin.elastic-username"),type:"input"}).registerSetting({setting:"blomstra-search.elastic-password",label:s().translator.trans("blomstra-search.admin.elastic-password"),type:"password"}).registerSetting({setting:"blomstra-search.elastic-index",label:s().translator.trans("blomstra-search.admin.elastic-index"),default:"flarum",type:"input"}).registerSetting({setting:"blomstra-search.analyzer-language",label:s().translator.trans("blomstra-search.admin.analyzer.label"),help:s().translator.trans("blomstra-search.admin.analyzer.help"),type:"select",options:Object.fromEntries(a.entries()),default:"english"}).registerSetting({setting:"blomstra-search.elastic-index",label:s().translator.trans("blomstra-search.admin.elastic-index"),default:"flarum",type:"input"}).registerSetting({setting:"blomstra-search.search-discussion-subjects",label:s().translator.trans("blomstra-search.admin.search-discussion-subjects"),type:"switch"}).registerSetting({setting:"blomstra-search.search-post-bodies",label:s().translator.trans("blomstra-search.admin.search-post-bodies"),type:"switch"}).registerSetting({setting:"blomstra-search.match-sentences",label:s().translator.trans("blomstra-search.admin.match-sentences"),type:"switch"}).registerSetting({setting:"blomstra-search.match-words",label:s().translator.trans("blomstra-search.admin.match-words"),type:"switch"})}))})(),module.exports=t})();
 //# sourceMappingURL=admin.js.map
--- a/js/dist/admin.js.map
+++ b/js/dist/admin.js.map
--- a/js/dist/forum.js.map
+++ b/js/dist/forum.js.map
--- a/js/src/admin/index.ts
+++ b/js/src/admin/index.ts
@ -78,5 +78,25 @@ app.initializers.add('blomstra-search', () => {
      label: app.translator.trans('blomstra-search.admin.elastic-index'),
      default: 'flarum',
      type: 'input',
+    })
+    .registerSetting({
+      setting: 'blomstra-search.search-discussion-subjects',
+      label: app.translator.trans('blomstra-search.admin.search-discussion-subjects'),
+      type: 'switch',
+    })
+    .registerSetting({
+      setting: 'blomstra-search.search-post-bodies',
+      label: app.translator.trans('blomstra-search.admin.search-post-bodies'),
+      type: 'switch',
+    })
+    .registerSetting({
+      setting: 'blomstra-search.match-sentences',
+      label: app.translator.trans('blomstra-search.admin.match-sentences'),
+      type: 'switch',
+    })
+    .registerSetting({
+      setting: 'blomstra-search.match-words',
+      label: app.translator.trans('blomstra-search.admin.match-words'),
+      type: 'switch',
    });
 });
--- a/resources/locale/en.yml
+++ b/resources/locale/en.yml
@ -9,3 +9,7 @@ blomstra-search:
            help: |
                The analyzer makes search understand stop words and undertakes language
                specific improvements for indexing.
+        search-discussion-subjects: Search inside discussion titles
+        search-post-bodies: Search inside comments
+        match-sentences: Match search term against full sentence
+        match-words: Match search term against full words
--- a/src/Api/Controllers/SearchController.php
+++ b/src/Api/Controllers/SearchController.php
@ -16,6 +16,7 @@ use Blomstra\Search\Elasticsearch\MatchPhraseQuery;
 use Blomstra\Search\Elasticsearch\MatchQuery;
 use Blomstra\Search\Elasticsearch\TermsQuery;
 use Blomstra\Search\Save\Document as ElasticDocument;
+use Blomstra\Search\Searchers\Searcher;
 use Elasticsearch\Client;
 use Flarum\Api\Controller\ListDiscussionsController;
 use Flarum\Api\Serializer\DiscussionSerializer;
@ -24,6 +25,7 @@ use Flarum\Extension\ExtensionManager;
 use Flarum\Group\Group;
 use Flarum\Http\RequestUtil;
 use Flarum\Http\UrlGenerator;
+use Flarum\Settings\SettingsRepositoryInterface;
 use Flarum\User\User;
 use Illuminate\Contracts\Container\Container;
 use Illuminate\Support\Arr;
@ -47,8 +49,23 @@ class SearchController extends ListDiscussionsController
        'commentCount' => 'comment_count',
    ];

-    public function __construct(protected Client $elastic, protected UrlGenerator $uri)
+    protected Collection $searchers;
+    protected bool $matchSentences;
+    protected bool $matchWords;
+
+    public function __construct(protected Client $elastic, protected UrlGenerator $uri, Container $container, SettingsRepositoryInterface $settings)
    {
+        $this->searchers = $this->gatherSearchers($container->tagged('blomstra.search.searchers'));
+
+        $this->matchSentences = (bool) $settings->get('blomstra-search.match-sentences', true);
+        $this->matchWords = (bool) $settings->get('blomstra-search.match-words', true);
+    }
+
+    protected function gatherSearchers(iterable $searchers)
+    {
+        return collect($searchers)
+            ->map(fn ($searcher) => new $searcher)
+            ->filter(fn (Searcher $searcher) => $searcher->enabled());
    }

    protected function data(ServerRequestInterface $request, Document $document)
@ -69,14 +86,11 @@ class SearchController extends ListDiscussionsController

        $filterQuery = BoolQuery::create();

-        if (!empty($search)) {
-            $filterQuery
-                // @todo commented out to use only partial matching for now
-                ->add($this->sentenceMatch($search))
-                ->add($this->wordMatch($search, 'and'))
-                ->add($this->wordMatch($search, 'or'))
-//                ->add($this->partialMatch($search))
-;
+
+        if (! empty($search)) {
+            if ($this->matchSentences) $filterQuery->add($this->sentenceMatch($search));
+            if ($this->matchWords) $filterQuery->add($this->wordMatch($search, 'and'));
+            if ($this->matchWords) $filterQuery->add($this->wordMatch($search, 'or'));
        }

        $builder = (new Builder($this->elastic))
@ -232,70 +246,40 @@ class SearchController extends ListDiscussionsController
        return $query;
    }

+    protected function boolQuery(Query $parent, float $boost = 1): Query
+    {
+        $bool = new BoolQuery;
+
+        /** @var Searcher $searcher */
+        foreach ($this->searchers as $searcher) {
+            $searcher = new $searcher;
+
+            $bool->add(
+                BoolQuery::create()
+                    ->add(TermQuery::create('type', $searcher->type()), 'filter')
+                    ->add(clone $parent->boost($boost * $searcher->boost())),
+                'should'
+            );
+        }
+
+        return $bool;
+    }
+
    protected function sentenceMatch(string $q): Query
    {
        $query = (new MatchPhraseQuery('content', $q));

-        return BoolQuery::create()
-            // Discussion titles
-            ->add(
-                BoolQuery::create()
-                    ->add(TermQuery::create('type', 'discussions'), 'filter')
-                    ->add($query->boost(2)),
-                'should'
-            )
-            // Post bodies
-            ->add(
-                BoolQuery::create()
-                    ->add(TermQuery::create('type', 'posts'), 'filter')
-                    ->add($query->boost(1.9)),
-                'should'
-            );
+        return $this->boolQuery($query, 2);
    }

-    protected function wordMatch(string $q, string $operator = 'or')
+    protected function wordMatch(string $q, string $operator = 'or'): Query
    {
        $query = (new MatchQuery('content', $q))
            ->operator($operator);

-        $boost = $operator === 'and' ? 1 : .8;
+        $boost = $operator === 'and' ? 1.8 : .8;

-        return BoolQuery::create()
-            // Discussion titles
-            ->add(
-                BoolQuery::create()
-                    ->add(TermQuery::create('type', 'discussions'), 'filter')
-                    ->add($query->boost($boost * 1.8)),
-                'should'
-            )
-            // Post bodies
-            ->add(
-                BoolQuery::create()
-                    ->add(TermQuery::create('type', 'posts'), 'filter')
-                    ->add($query->boost($boost * 1.8)),
-                'should'
-            );
-    }
-
-    protected function partialMatch(string $q)
-    {
-        $query = (new MatchQuery('content', $q));
-
-        return BoolQuery::create()
-            // Discussion titles
-            ->add(
-                BoolQuery::create()
-                    ->add(TermQuery::create('type', 'discussions'), 'filter')
-                    ->add(clone $query->boost(1.6)),
-                'should'
-            )
-            // Post bodies
-            ->add(
-                BoolQuery::create()
-                    ->add(TermQuery::create('type', 'posts'), 'filter')
-                    ->add(clone $query->boost(1.3)),
-                'should'
-            );
+        return $this->boolQuery($query, $boost);
    }

    protected function getGroups(User $actor): Collection
--- a/src/Provider.php
+++ b/src/Provider.php
@ -15,6 +15,8 @@ namespace Blomstra\Search;
 use Blomstra\Search\Jobs\DeletingJob;
 use Blomstra\Search\Jobs\Job;
 use Blomstra\Search\Jobs\SavingJob;
+use Blomstra\Search\Searchers;
+use Blomstra\Search\Seeders;
 use Elasticsearch\Client as Elastic;
 use Elasticsearch\ClientBuilder;
 use Flarum\Api\Client;
@ -87,6 +89,11 @@ class Provider extends AbstractServiceProvider
                return new Api\Client($pipe);
            }
        );
+
+        $this->container->tag([
+            Searchers\DiscussionSearcher::class,
+            Searchers\CommentPostSearcher::class,
+        ], 'blomstra.search.searchers');
    }

    public function boot()
--- a/src/Searchers/CommentPostSearcher.php
+++ b/src/Searchers/CommentPostSearcher.php
@ -0,0 +1,17 @@
+<?php
+
+namespace Blomstra\Search\Searchers;
+
+use Blomstra\Search\Seeders\CommentSeeder;
+
+class CommentPostSearcher extends Searcher
+{
+    protected string|null $seeder = CommentSeeder::class;
+
+    public function enabled(): bool
+    {
+        $enabled = $this->setting('blomstra-search.search-post-bodies', true);
+
+        return boolval($enabled);
+    }
+}
--- a/src/Searchers/DiscussionSearcher.php
+++ b/src/Searchers/DiscussionSearcher.php
@ -0,0 +1,22 @@
+<?php
+
+namespace Blomstra\Search\Searchers;
+
+use Blomstra\Search\Seeders\DiscussionSeeder;
+
+class DiscussionSearcher extends Searcher
+{
+    protected string|null $seeder = DiscussionSeeder::class;
+
+    public function enabled(): bool
+    {
+        $enabled = $this->setting('blomstra-search.search-discussion-subjects', true);
+
+        return boolval($enabled);
+    }
+
+    public function boost(): float
+    {
+        return 1.5;
+    }
+}
--- a/src/Searchers/Searcher.php
+++ b/src/Searchers/Searcher.php
@ -0,0 +1,36 @@
+<?php
+
+namespace Blomstra\Search\Searchers;
+
+use Blomstra\Search\Seeders\Seeder;
+use Flarum\Settings\SettingsRepositoryInterface;
+
+abstract class Searcher
+{
+    protected string|null $seeder = null;
+
+    public function type(): string
+    {
+        /** @var Seeder $seeder */
+        $seeder = $this->seeder;
+
+        if (empty($seeder)) throw new \InvalidArgumentException("Implement type or add \$seeder");
+
+        return (new $seeder)->type();
+    }
+
+    public function enabled(): bool
+    {
+        return true;
+    }
+
+    public function boost(): float
+    {
+        return 1;
+    }
+
+    protected function setting(string $key, $default = null)
+    {
+        return resolve(SettingsRepositoryInterface::class)->get($key, $default);
+    }
+}