a large commit

biotorrents · Jun 6, 2024 · 9a7201d · 9a7201d
1 parent df072bb
commit 9a7201d
Show file tree

Hide file tree

Showing 70 changed files with 2,870 additions and 3,293 deletions.
diff --git a/README.md b/README.md
@@ -18,20 +18,19 @@ If you want to scale horizontally, the software supports both [Redis clusters](a
 Please note that Redis clusters expect at least three nodes.
 This lower limit is inherent to Redis' [cluster implementation](https://redis.io/docs/management/scaling/).
 
-### Universal database id's
-
-BioGazelle is in the process of migrating to [UUID v7 primary keys](https://uuid.ramsey.dev/en/stable/rfc4122/version7.html) to enable useful content-agnostic operations such as tagging and AI integration.
-This will consolidate the database and allow for powerful cross-object association.
-The UUIDs are stored as binary strings for index speed and to minimize disk usage.
-By the way, *all* binary data is transparently converted by the [database wrapper](app/Database.php).
-
-## Full stack search engine rewrite
+## Deeply indexed and programmatically enhanced
 
 Data indexing is important, so BioGazelle has upgraded to [Manticore Search](https://manticoresearch.com), the successor to Sphinx.
 This upgrade also involved a [rewrite of the search configuration](utilities/config/manticore.conf) from scratch, based on AnimeBytes' example.
 The Gazelle frontend itself uses a [rewritten browse.php controller](sections/torrents/browse.php) and a [brand new Twig template](templates/torrents/search.twig).
 Oh yeah, the [PHP backend class](app/Manticore.php) is also completely rewritten, replacing at least four legacy classes.
 
+### Universal database id's
+
+BioGazelle is in the process of migrating to [short UUID primary keys](https://mariadb.com/kb/en/uuid_short/) to enable useful content-agnostic operations such as tagging and AI integration.
+This will consolidate the database and allow for powerful cross-object association.
+
+
 ## Secure authentication system
 
 The user handling, including registration, logins, etc., has been rewritten into a unified system in the [Auth class](app/Auth.php).
@@ -65,12 +64,6 @@ But we took it up a notch by upgrading this system to use the [modern WebAuthn s
 use a hardware key, a smartphone fingerprint or QR code reader, or just generate a key in the browser.
 The underlying library is the canonical [web-auth/webauthn-lib](https://github.com/web-auth/webauthn-lib).
 
-## OpenAI integration
-
-One of BioGazelle's goals is to place data in context using [OpenAI's completions API](app/OpenAI.php) to generate tl;dr summaries and tags from content descriptions.
-Just paste your abstract into the torrent group description and get a succinct natural language summary with tags.
-It's possible to disable AI content display in the user settings.
-
 ## Twig template system
 
 [BioGazelle's Twig interface](app/Twig.php) takes cues from OPS's extended filters and functions.
@@ -94,6 +87,12 @@ BioGazelle uses [Starboard Notebook](https://starboard.gg) to support [Jupyter N
 This lets users document technical topics such as data processing workflows complete with executable code examples and Latex expressions.
 Our secure implementation leverages sanboxed iframes on a dedicated subdomain to ensure no cookie or local storage leaks.
 
+### OpenAI integration
+
+One of BioGazelle's goals is to place data in context using [OpenAI's completions API](app/OpenAI.php) to generate tl;dr summaries and tags from content descriptions.
+Just paste your abstract into the torrent group description and get a succinct natural language summary with tags.
+It's possible to disable AI content display in the user settings.
+
 ### Good typography
 
 BioGazelle supports an array of [unobtrusive fonts](resources/scss/assets/fonts.scss) with the appropriate glyphs for bold, italic, and monospace.

diff --git a/app/Auth.php b/app/Auth.php
@@ -782,7 +782,7 @@ public function resendConfirmation(int|string $identifier)
 
         # try to resolve the email address
         $identifier = \Gazelle\Escape::string($identifier);
-        $column = $app->dbNew->determineIdentifier($identifier);
+        $column = $app->dbNew->determineId($identifier);
 
         # todo: maybe change unresolved id or uuid to null
         # and let the backend decide which column to use?

diff --git a/app/Better.php b/app/Better.php
@@ -136,7 +136,8 @@ public static function missingCitations(bool $snatchedOnly = false): array
             from torrents_group
             {$subQuery}
             where torrents_group.id not in
-            (select distinct groupId from literature_groups)
+            (select distinct contentId from literature_links)
+            and literature_links.contentType = 'torrentGroups'
             order by rand() limit {$resultCount}
         ";
 

diff --git a/app/Crossref.php b/app/Crossref.php
@@ -0,0 +1,37 @@
+<?php
+
+declare(strict_types=1);
+
+
+/**
+ * Gazelle\Crossref
+ *
+ * @see https://api.crossref.org/swagger-ui/index.html
+ */
+
+namespace Gazelle;
+
+class Crossref
+{
+    # guzzle client
+    private \GuzzleHttp\Client $client;
+    private string $baseUri = "https://api.crossref.org";
+
+    # cache settings
+    private string $cachePrefix = "crossref:";
+    private string $cacheDuration = "1 hour";
+    private string $cacheAlgorithm = "sha3-512";
+
+
+    /**
+     * __construct
+     */
+    public function __construct()
+    {
+        # https://docs.guzzlephp.org/en/stable/quickstart.html
+        $this->client = new \GuzzleHttp\Client([
+            "base_uri" => $this->baseUri,
+            "timeout" => 2.0,
+        ]);
+    }
+} # class
diff --git a/app/Database.php b/app/Database.php
@@ -278,34 +278,71 @@ public function shortUuid(): string
     /**
      * slug
      *
-     * @param string $string
+     * @param ?string $string
      * @return string
      *
      * @see https://laravel.com/api/master/Illuminate/Support/Str.html#method_slug
      */
-    public function slug(string $string): string
+    public function slug(?string $string): string
     {
         return \Illuminate\Support\Str::slug($string);
     }
 
 
     /**
-     * determineIdentifier
+     * determineId
      *
      * Determine the identifier to use for a query.
      * Used for finding stuff by id, uuid, or slug.
      *
      * @param int|string $id
      * @return string
      */
-    public function determineIdentifier(int|string $id): string
+    public function determineId(int|string $id): string
     {
         $app = App::go();
 
+        # cast to string
+        $id = strval($id);
+
+        # openAlex
+        $good = preg_match("/{$app->env->regexOpenAlex}/", $id);
+        if ($good) {
+            return "openAlexId";
+        }
+
+        # doi
+        $good = preg_match("/{$app->env->regexDoi}/i", $id);
+        if ($good) {
+            return "doi";
+        }
+
+        # orcid
+        $good = preg_match("/{$app->env->regexOrcid}/i", $id);
+        if ($good) {
+            return "orcid";
+        }
+
+        # issn
+        $good = preg_match("/{$app->env->regexIssn}/", $id);
+        if ($good) {
+            return "issn";
+        }
+
+        # rorId
+        $good = preg_match("/{$app->env->regexRor}/", $id);
+        if ($good) {
+            return "rorId";
+        }
+
+        # normal numeric id
         if (is_int($id) || is_numeric($id)) {
             return "id";
         }
 
+        # default slug
+        return "slug";
+
         /*
         # https://ihateregex.io/expr/uuid/
         if (is_string($id) && strlen($id) === 36 && preg_match("/{$app->env->regexUuid}/iD", $id)) {
@@ -317,9 +354,6 @@ public function determineIdentifier(int|string $id): string
             return "uuid";
         }
         */
-
-        # default slug
-        return "slug";
     }
 
 
@@ -672,7 +706,7 @@ public function upsert(string $table, array $data = []): array
         # it was updated, resolve a key from the data
         foreach ($data as $key => $value) {
             if (in_array(strtolower(strval($key)), ["id", "uuid", "slug"])) {
-                $column = $this->determineIdentifier($value);
+                $column = $this->determineId($value);
                 $query = "select * from {$table} where {$column} = ?";
                 return $this->row($query, [$value], ["hostname" => "source"]);
             }

diff --git a/app/Format.php b/app/Format.php
@@ -575,4 +575,18 @@ public static function breadcrumbs()
 
         return $crumbs;
     }
+
+
+    /**
+     * tag
+     *
+     * Formats a tag for storage and display.
+     *
+     * @param ?string $string
+     * @return string
+     */
+    public static function tag(?string $string): string
+    {
+        return \Illuminate\Support\Str::slug($string);
+    }
 } # class