From a9c506497ce2bedaff5202a8a19d929fbdcd4088 Mon Sep 17 00:00:00 2001
From: Joshua Ramon Enslin <joshua@museum-digital.de>
Date: Thu, 10 Oct 2024 09:51:28 +0200
Subject: [PATCH] Respect diacritics when looking up tag, actor, .. IDs

---
 src/NodaIDGetter.php       | 325 ++++++++++++++++------------
 tests/NodaIDGetterTest.php | 433 +++++++++++++++++++++++++++++++++++++
 tests/bootstrap.php        |  12 +-
 3 files changed, 628 insertions(+), 142 deletions(-)
 create mode 100644 tests/NodaIDGetterTest.php

diff --git a/src/NodaIDGetter.php b/src/NodaIDGetter.php
index 6742a59..a826be4 100644
--- a/src/NodaIDGetter.php
+++ b/src/NodaIDGetter.php
@@ -10,6 +10,30 @@ declare(strict_types = 1);
  * Contains static functions for getting IDs for noda entries by various means.
  */
 final class NodaIDGetter {
+    /**
+     * Comparison operation that allows for equality but also returns true
+     * if capitalization differs. If diacritics are available in one case
+     * and not in the other, there will be no match.
+     * This is needed to identify sufficiently exact matches despite a table
+     * collation of *_ci in MySQL.
+     *
+     * @param string $string_one First string in comparison.
+     * @param string $string_two Second string in comparison.
+     *
+     * @return boolean
+     */
+    private static function _stri_matches(string $string_one, string $string_two):bool {
+
+        if ($string_one === $string_two) {
+            return true;
+        }
+        if (\strtolower($string_one) === \strtolower($string_two)) {
+            return true;
+        }
+
+        return false;
+
+    }
 
     //
     // Actors
@@ -80,21 +104,22 @@ final class NodaIDGetter {
 
         if (empty($name)) return 0;
 
-        $persinstRewriteResult = $mysqli_noda->query_by_stmt("
-            SELECT `persinst_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `persinst_id`, `input_name`
             FROM `persinst_rewriting`
             WHERE `language` = ?
                 AND `input_name` = ?
             LIMIT 1", "ss", $lang, $name);
 
-        if ($persinstRewriteData = $persinstRewriteResult->fetch_row()) {
-            $output = $persinstRewriteData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($cur[1], $name)) {
+                $result->close();
+                return (int)$cur[0];
+            }
         }
-        else $output = 0;
+        $result->close();
 
-        $persinstRewriteResult->close();
-
-        return $output;
+        return 0;
 
     }
 
@@ -111,21 +136,22 @@ final class NodaIDGetter {
 
         if (empty($name)) return 0;
 
-        $persinstByTLNameResult = $mysqli_noda->query_by_stmt("
-            SELECT `persinst_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `persinst_id`, `trans_name`
             FROM `persinst_translation`
             WHERE `trans_name` = ?
                 AND `trans_language` = ?
             LIMIT 2", "ss", $name, $lang);
 
-        if ($persinstByTlData = $persinstByTLNameResult->fetch_row()) {
-            $output = $persinstByTlData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($cur[1], $name)) {
+                $result->close();
+                return (int)$cur[0];
+            }
         }
-        else $output = 0;
+        $result->close();
 
-        $persinstByTLNameResult->close();
-
-        return $output;
+        return 0;
 
     }
 
@@ -145,8 +171,8 @@ final class NodaIDGetter {
 
         if (empty($name)) return 0;
 
-        $persinstByTLNameResult = $mysqli_noda->query_by_stmt("
-            SELECT `persinst_translation`.`persinst_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `persinst_translation`.`persinst_id`, `trans_name`
             FROM `persinst_translation`, `persinst`
             WHERE `persinst_translation`.`persinst_id` = `persinst`.`persinst_id`
                 AND `trans_name` = ?
@@ -155,14 +181,15 @@ final class NodaIDGetter {
                 AND `persinst_sterbejahr` = ?
             LIMIT 2", "ssss", $name, $lang, $birth, $death);
 
-        if ($persinstByTlData = $persinstByTLNameResult->fetch_row()) {
-            $output = $persinstByTlData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($cur[1], $name)) {
+                $result->close();
+                return (int)$cur[0];
+            }
         }
-        else $output = 0;
+        $result->close();
 
-        $persinstByTLNameResult->close();
-
-        return $output;
+        return 0;
 
     }
 
@@ -178,22 +205,23 @@ final class NodaIDGetter {
 
         if (empty($name)) return 0;
 
-        $persinstByBaseNameResult = $mysqli_noda->query_by_stmt("
-            SELECT `persinst_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `persinst_id`, `persinst_anzeigename`, `persinst_name`, CONCAT(`persinst_name`, ' (', `persinst_geburtsjahr`, '-', `persinst_sterbejahr`, ')')
             FROM `persinst`
             WHERE `persinst_anzeigename` = ?
                 OR `persinst_name` = ?
                 OR CONCAT(`persinst_name`, ' (', `persinst_geburtsjahr`, '-', `persinst_sterbejahr`, ')') = ?
             LIMIT 2", "sss", $name, $name, $name);
 
-        if ($persinstByBaseData = $persinstByBaseNameResult->fetch_row()) {
-            $output = $persinstByBaseData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($cur[1], $name) || self::_stri_matches($cur[2], $name) || self::_stri_matches($cur[3], $name)) {
+                $result->close();
+                return (int)$cur[0];
+            }
         }
-        else $output = 0;
+        $result->close();
 
-        $persinstByBaseNameResult->close();
-
-        return $output;
+        return 0;
 
     }
 
@@ -211,8 +239,8 @@ final class NodaIDGetter {
 
         if (empty($name)) return 0;
 
-        $persinstByBaseNameResult = $mysqli_noda->query_by_stmt("
-            SELECT `persinst_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `persinst_id`, `persinst_anzeigename`, `persinst_name`, CONCAT(`persinst_name`, ' (', `persinst_geburtsjahr`, '-', `persinst_sterbejahr`, ')')
             FROM `persinst`
             WHERE (
                     `persinst_anzeigename` = ?
@@ -223,14 +251,15 @@ final class NodaIDGetter {
                 AND `persinst_sterbejahr` = ?
             LIMIT 2", "sssss", $name, $name, $name, $birth, $death);
 
-        if ($persinstByBaseData = $persinstByBaseNameResult->fetch_row()) {
-            $output = $persinstByBaseData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($cur[1], $name) || self::_stri_matches($cur[2], $name) || self::_stri_matches($cur[3], $name)) {
+                $result->close();
+                return (int)$cur[0];
+            }
         }
-        else $output = 0;
+        $result->close();
 
-        $persinstByBaseNameResult->close();
-
-        return $output;
+        return 0;
 
     }
 
@@ -284,22 +313,23 @@ final class NodaIDGetter {
         if (empty($name)) return 0;
 
         $lookUpName = $name . $birthYear . $deathYear;
-        $persinstByImportLogResult = $mysqli_noda->query_by_stmt("
-            SELECT `persinst_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `persinst_id`, `input_string`
             FROM `persinst_logged_imports`
             WHERE `instance` = ?
                 AND `institution_id` = ?
                 AND `input_string` = ?
             LIMIT 2", "sis", $instance, $institution_id, $lookUpName);
 
-        if ($persinstByImportLogData = $persinstByImportLogResult->fetch_row()) {
-            $output = $persinstByImportLogData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($cur[1], $lookUpName)) {
+                $result->close();
+                return (int)$cur[0];
+            }
         }
-        else $output = 0;
+        $result->close();
 
-        $persinstByImportLogResult->close();
-
-        return $output;
+        return 0;
 
     }
 
@@ -345,21 +375,22 @@ final class NodaIDGetter {
 
         if (empty($name)) return 0;
 
-        $placeRewriteResult = $mysqli_noda->query_by_stmt("
-            SELECT `ort_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `ort_id`, `input_name`
             FROM `ort_rewriting`
             WHERE `language` = ?
                 AND `input_name` = ?
             LIMIT 1", "ss", $lang, $name);
 
-        if ($placeRewriteData = $placeRewriteResult->fetch_row()) {
-            $output = $placeRewriteData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($cur[1], $name)) {
+                $result->close();
+                return (int)$cur[0];
+            }
         }
-        else $output = 0;
+        $result->close();
 
-        $placeRewriteResult->close();
-
-        return $output;
+        return 0;
 
     }
 
@@ -375,20 +406,21 @@ final class NodaIDGetter {
 
         if (empty($name)) return 0;
 
-        $placeByBaseNameResult = $mysqli_noda->query_by_stmt("
-            SELECT `ort_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `ort_id`, `ort_name`
             FROM `orte`
             WHERE `ort_name` = ?
             LIMIT 2", "s", $name);
 
-        if ($placeByBaseData = $placeByBaseNameResult->fetch_row()) {
-            $output = $placeByBaseData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($cur[1], $name)) {
+                $result->close();
+                return (int)$cur[0];
+            }
         }
-        else $output = 0;
+        $result->close();
 
-        $placeByBaseNameResult->close();
-
-        return $output;
+        return 0;
 
     }
 
@@ -405,21 +437,22 @@ final class NodaIDGetter {
 
         if (empty($name)) return 0;
 
-        $placeByTLNameResult = $mysqli_noda->query_by_stmt("
-            SELECT `ort_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `ort_id`, `trans_name`
             FROM `ort_translation`
             WHERE `trans_name` = ?
                 AND `trans_language` = ?
             LIMIT 2", "ss", $name, $lang);
 
-        if ($placeByTlData = $placeByTLNameResult->fetch_row()) {
-            $output = $placeByTlData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($cur[1], $name)) {
+                $result->close();
+                return (int)$cur[0];
+            }
         }
-        else $output = 0;
+        $result->close();
 
-        $placeByTLNameResult->close();
-
-        return $output;
+        return 0;
 
     }
 
@@ -470,22 +503,23 @@ final class NodaIDGetter {
 
         if (empty($name)) return 0;
 
-        $placeByImportLogResult = $mysqli_noda->query_by_stmt("
-            SELECT `ort_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `ort_id`, `input_string`
             FROM `orte_logged_imports`
             WHERE `instance` = ?
                 AND `institution_id` = ?
                 AND `input_string` = ?
             LIMIT 2", "sis", $instance, $institution_id, $name);
 
-        if ($placeByImportLogData = $placeByImportLogResult->fetch_row()) {
-            $output = $placeByImportLogData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($cur[1], $name)) {
+                $result->close();
+                return (int)$cur[0];
+            }
         }
-        else $output = 0;
+        $result->close();
 
-        $placeByImportLogResult->close();
-
-        return $output;
+        return 0;
 
     }
 
@@ -533,17 +567,19 @@ final class NodaIDGetter {
 
         $output = [];
 
-        $tagRewriteResult = $mysqli_noda->query_by_stmt("
-            SELECT `tag_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `tag_id`, `input_name`
             FROM `tag_rewriting`
             WHERE `tag_language` = ?
                 AND `input_name` = ?", "ss", $lang, $name);
 
-        while ($tagRewriteData = $tagRewriteResult->fetch_row()) {
-            $output[] = $tagRewriteData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($name, $cur[1])) {
+                $output[] = $cur[0];
+            }
         }
 
-        $tagRewriteResult->close();
+        $result->close();
 
         return $output;
 
@@ -561,20 +597,21 @@ final class NodaIDGetter {
 
         if (empty($name)) return 0;
 
-        $tagByBaseNameResult = $mysqli_noda->query_by_stmt("
-            SELECT `tag_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `tag_id`, `tag_name`
             FROM `tag`
             WHERE `tag_name` = ?
             LIMIT 2", "s", $name);
 
-        if ($tagByBaseData = $tagByBaseNameResult->fetch_row()) {
-            $output = $tagByBaseData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($name, $cur[1])) {
+                $result->close();
+                return (int)$cur[0];
+            }
         }
-        else $output = 0;
+        $result->close();
 
-        $tagByBaseNameResult->close();
-
-        return $output;
+        return 0;
 
     }
 
@@ -591,21 +628,22 @@ final class NodaIDGetter {
 
         if (empty($name)) return 0;
 
-        $tagByTLNameResult = $mysqli_noda->query_by_stmt("
-            SELECT `tag_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `tag_id`, `trans_name`
             FROM `tag_translation`
             WHERE `trans_name` = ?
                 AND `trans_language` = ?
             LIMIT 2", "ss", $name, $lang);
 
-        if ($tagByTlData = $tagByTLNameResult->fetch_row()) {
-            $output = $tagByTlData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($name, $cur[1])) {
+                $result->close();
+                return (int)$cur[0];
+            }
         }
-        else $output = 0;
+        $result->close();
 
-        $tagByTLNameResult->close();
-
-        return $output;
+        return 0;
 
     }
 
@@ -656,22 +694,23 @@ final class NodaIDGetter {
 
         if (empty($name)) return 0;
 
-        $tagByImportLogResult = $mysqli_noda->query_by_stmt("
-            SELECT `tag_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `tag_id`, `input_string`
             FROM `tag_logged_imports`
             WHERE `instance` = ?
                 AND `institution_id` = ?
                 AND `input_string` = ?
             LIMIT 2", "sis", $instance, $institution_id, $name);
 
-        if ($tagByImportLogData = $tagByImportLogResult->fetch_row()) {
-            $output = $tagByImportLogData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($name, $cur[1])) {
+                $result->close();
+                return (int)$cur[0];
+            }
         }
-        else $output = 0;
+        $result->close();
 
-        $tagByImportLogResult->close();
-
-        return $output;
+        return 0;
 
     }
 
@@ -719,20 +758,21 @@ final class NodaIDGetter {
 
         $output = [];
 
-        $timeRewriteResult = $mysqli_noda->query_by_stmt("
-            SELECT `zeit_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `zeit_id`, `input_name`
             FROM `zeit_rewriting`
             WHERE `language` = ?
                 AND `input_name` = ?", "ss", $lang, $name);
 
-        if ($timeRewriteData = $timeRewriteResult->fetch_row()) {
-            $output = (int)$timeRewriteData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($name, $cur[1])) {
+                $result->close();
+                return (int)$cur[0];
+            }
         }
-        else $output = 0;
+        $result->close();
 
-        $timeRewriteResult->close();
-
-        return $output;
+        return 0;
 
     }
 
@@ -748,20 +788,21 @@ final class NodaIDGetter {
 
         if (empty($name)) return 0;
 
-        $timeByBaseNameResult = $mysqli_noda->query_by_stmt("
-            SELECT `zeit_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `zeit_id`, `zeit_name`
             FROM `zeiten`
             WHERE `zeit_name` = ?
             LIMIT 2", "s", $name);
 
-        if ($timeByBaseData = $timeByBaseNameResult->fetch_row()) {
-            $output = $timeByBaseData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($name, $cur[1])) {
+                $result->close();
+                return (int)$cur[0];
+            }
         }
-        else $output = 0;
+        $result->close();
 
-        $timeByBaseNameResult->close();
-
-        return $output;
+        return 0;
 
     }
 
@@ -778,21 +819,22 @@ final class NodaIDGetter {
 
         if (empty($name)) return 0;
 
-        $timeByTLNameResult = $mysqli_noda->query_by_stmt("
-            SELECT `zeit_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `zeit_id`, `trans_name`
             FROM `zeit_translation`
             WHERE `trans_name` = ?
                 AND `trans_language` = ?
             LIMIT 2", "ss", $name, $lang);
 
-        if ($timeByTlData = $timeByTLNameResult->fetch_row()) {
-            $output = $timeByTlData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($name, $cur[1])) {
+                $result->close();
+                return (int)$cur[0];
+            }
         }
-        else $output = 0;
+        $result->close();
 
-        $timeByTLNameResult->close();
-
-        return $output;
+        return 0;
 
     }
 
@@ -810,22 +852,23 @@ final class NodaIDGetter {
 
         if (empty($name)) return 0;
 
-        $timeByImportLogResult = $mysqli_noda->query_by_stmt("
-            SELECT `zeit_id`
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `zeit_id`, `input_string`
             FROM `zeiten_logged_imports`
             WHERE `instance` = ?
                 AND `institution_id` = ?
                 AND `input_string` = ?
             LIMIT 2", "sis", $instance, $institution_id, $name);
 
-        if ($timeByImportLogData = $timeByImportLogResult->fetch_row()) {
-            $output = $timeByImportLogData[0];
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($name, $cur[1])) {
+                $result->close();
+                return (int)$cur[0];
+            }
         }
-        else $output = 0;
+        $result->close();
 
-        $timeByImportLogResult->close();
-
-        return $output;
+        return 0;
 
     }
 
diff --git a/tests/NodaIDGetterTest.php b/tests/NodaIDGetterTest.php
new file mode 100644
index 0000000..2a3e974
--- /dev/null
+++ b/tests/NodaIDGetterTest.php
@@ -0,0 +1,433 @@
+<?PHP
+/**
+ * Test for functions for looking up entry IDs by their (exact) names.
+ *
+ * @author Joshua Ramon Enslin <joshua@museum-digital.de>
+ */
+declare(strict_types = 1);
+
+use PHPUnit\Framework\TestCase;
+use PHPUnit\Framework\Attributes\CoversClass;
+use PHPUnit\Framework\Attributes\DataProvider;
+use PHPUnit\Framework\Attributes\Medium;
+
+require_once __DIR__ . '/../../MDMysqli/test_connections.conf.php';
+
+/**
+ * Test for functions for looking up entry IDs by their (exact) names.
+ */
+#[Medium]
+#[CoversClass(\NodaIDGetter::class)]
+final class NodaIDGetterTest extends TestCase {
+
+    private MDMysqli $_mysqli;
+
+    /**
+     * Quasi-constructor connects to DB.
+     *
+     * @return void
+     */
+    protected function setUp():void {
+
+        $this->_mysqli = md_noda_mysqli_connect();
+
+    }
+
+    /**
+     * Gets string and integer value from a mysql query.
+     *
+     * @param MDMysqli $mysqli DB connection.
+     * @param string   $query  DB query.
+     *
+     * @return array{0: string, 1: integer}
+     */
+    private static function _getNameAndIdFromDbQuery(MDMysqli $mysqli, string $query):array {
+
+        $result = $mysqli->do_read_query($query . "
+            LIMIT 1");
+
+        if (!($cur = $result->fetch_row())) {
+            throw new Exception("Failed to get result for query: " . $query);
+        }
+        $result->close();
+
+        return [
+            (string)$cur[0],
+            (int)$cur[1],
+        ];
+
+    }
+
+    /**
+     * Replaces vowels in string with variants with diacritics for testing
+     * exact matching.
+     *
+     * @param string $input Input string.
+     *
+     * @return string
+     */
+    public static function _replaceVowelsWithDiacriticVariants(string $input):string {
+
+        return strtr($input, [
+            'a' => 'ä',
+            'o' => 'ö',
+            'u' => 'ü',
+            'i' => 'ï',
+            'e' => 'è',
+        ]);
+
+    }
+
+    /**
+     * Runs regular tests on the term:
+     * - Matching by exact same name works.
+     * - Matching by same name with different capitalization works.
+     * - Matching by same name with diacritics replacing non-diacritic vowels fails
+     *   (counter to MySQL's _ci-type notations rules).
+     *
+     * @param string  $function    NodaIDGetter's callback function for identification.
+     * @param string  $name        Name of the entry.
+     * @param integer $expected_id Expected target ID.
+     *
+     * @return void
+     */
+    private function runRegularComparisonTests(string $function, string $name, int $expected_id):void {
+
+        self::assertEquals($expected_id,
+            NodaIDGetter::$function($this->_mysqli, "de", $name),
+            "Entry " . $name . " is not matched in exact lookup. Expected ID: " . $expected_id);
+
+        // Ensure that different capitalization does not influence the results
+        self::assertEquals($expected_id,
+            NodaIDGetter::$function($this->_mysqli, "de", strtoupper($name)));
+        self::assertEquals($expected_id,
+            NodaIDGetter::$function($this->_mysqli, "de", strtolower($name)));
+
+        // Ensure that diacritics will stop the entry from matching
+        $nameReplaced = self::_replaceVowelsWithDiacriticVariants($name);
+        self::assertNotEquals($expected_id,
+            NodaIDGetter::$function($this->_mysqli, "de", $nameReplaced));
+
+    }
+
+    // PersinstIDByName
+
+    /**
+     * Returns a test actor name.
+     *
+     * @return array<array{0: string, 1: integer}>
+     */
+    public static function persinstByNameProvider():array {
+
+        $mysqli = md_main_mysqli_connect();
+        $persinstByNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `persinst_name`, `persinst_id`
+            FROM `" . DATABASENAME_NODA . "`.`persinst`
+            WHERE INSTR(`persinst_name`, 'i')");
+        $persinstByDisplayNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `persinst_anzeigename`, `persinst_id`
+            FROM `" . DATABASENAME_NODA . "`.`persinst`
+            WHERE INSTR(`persinst_anzeigename`, 'i')
+                AND `persinst_sterbejahr` != ''");
+        $persinstByDisplayNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `trans_name`, `persinst_id`
+            FROM `" . DATABASENAME_NODA . "`.`persinst_translation`
+            WHERE INSTR(`trans_name`, 'i')
+                AND `trans_language` = 'de'");
+        $mysqli->close();
+
+        return [
+            'Persinst ID by name: ' . $persinstByNameSimple[0] => $persinstByNameSimple,
+            'Persinst ID by display name: ' . $persinstByDisplayNameSimple[0] => $persinstByDisplayNameSimple,
+            'Persinst ID by translated name: ' . $persinstByDisplayNameSimple[0] => $persinstByDisplayNameSimple,
+        ];
+
+    }
+
+    /**
+     * Test getting persinst by name works.
+     *
+     * @param string  $name        Name of the entry.
+     * @param integer $expected_id Expected target ID.
+     *
+     * @return void
+     */
+    #[DataProvider('persinstByNameProvider')]
+    public function testGetPersinstIdByNameWorks(string $name, int $expected_id):void {
+
+        $this->runRegularComparisonTests("getPersinstIDByName", $name, $expected_id);
+
+    }
+
+    // PersinstIDByRewrite
+
+    /**
+     * Returns a test actor name.
+     *
+     * @return array<array{0: string, 1: integer}>
+     */
+    public static function persinstByRewriteProvider():array {
+
+        $mysqli = md_main_mysqli_connect();
+        $persinstByRewriteSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `input_name`, `persinst_id`
+            FROM `" . DATABASENAME_NODA . "`.`persinst_rewriting`
+            WHERE INSTR(`input_name`, 'i')");
+        $mysqli->close();
+
+        return [
+            'Persinst ID by rewrite: ' . $persinstByRewriteSimple[0] => $persinstByRewriteSimple,
+        ];
+
+    }
+
+    /**
+     * Test getting persinst by rewrite works.
+     *
+     * @param string  $name        Name of the entry.
+     * @param integer $expected_id Expected target ID.
+     *
+     * @return void
+     */
+    #[DataProvider('persinstByRewriteProvider')]
+    public function testGetPersinstIdByRewriteWorks(string $name, int $expected_id):void {
+
+        $this->runRegularComparisonTests("getPersinstIDByRewrite", $name, $expected_id);
+
+    }
+
+    // PlaceIDByName
+
+    /**
+     * Returns a test place name.
+     *
+     * @return array<array{0: string, 1: integer}>
+     */
+    public static function placeByNameProvider():array {
+
+        $mysqli = md_main_mysqli_connect();
+        $placeByNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `ort_name`, `ort_id`
+            FROM `" . DATABASENAME_NODA . "`.`orte`
+            WHERE INSTR(`ort_name`, 'i')");
+        $placeByDisplayNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `trans_name`, `ort_id`
+            FROM `" . DATABASENAME_NODA . "`.`ort_translation`
+            WHERE INSTR(`trans_name`, 'i')
+                AND `trans_language` = 'de'");
+        $mysqli->close();
+
+        return [
+            'Place ID by name: ' . $placeByNameSimple[0] => $placeByNameSimple,
+            'Place ID by translated name: ' . $placeByDisplayNameSimple[0] => $placeByDisplayNameSimple,
+        ];
+
+    }
+
+    /**
+     * Test getting persinst by name works.
+     *
+     * @param string  $name        Name of the entry.
+     * @param integer $expected_id Expected target ID.
+     *
+     * @return void
+     */
+    #[DataProvider('placeByNameProvider')]
+    public function testGetPlaceIdByNameWorks(string $name, int $expected_id):void {
+
+        $this->runRegularComparisonTests("getPlaceIDByName", $name, $expected_id);
+
+    }
+
+    // PlaceIDByRewrite
+
+    /**
+     * Returns a test place name registered for rewriting.
+     *
+     * @return array<array{0: string, 1: integer}>
+     */
+    public static function placeByRewriteProvider():array {
+
+        $mysqli = md_main_mysqli_connect();
+        $placeByRewriteSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `input_name`, `ort_id`
+            FROM `" . DATABASENAME_NODA . "`.`ort_rewriting`
+            WHERE INSTR(`input_name`, 'i')");
+        $mysqli->close();
+
+        return [
+            'Place ID by rewrite: ' . $placeByRewriteSimple[0] => $placeByRewriteSimple,
+        ];
+
+    }
+
+    /**
+     * Test getting places by rewrite works.
+     *
+     * @param string  $name        Name of the entry.
+     * @param integer $expected_id Expected target ID.
+     *
+     * @return void
+     */
+    #[DataProvider('placeByRewriteProvider')]
+    public function testGetPlaceIdByRewriteWorks(string $name, int $expected_id):void {
+
+        $this->runRegularComparisonTests("getPlaceIDByRewrite", $name, $expected_id);
+
+    }
+
+    // TagIDByName
+
+    /**
+     * Returns a test tag name.
+     *
+     * @return array<array{0: string, 1: integer}>
+     */
+    public static function tagByNameProvider():array {
+
+        $mysqli = md_main_mysqli_connect();
+        $tagByNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `tag_name`, `tag_id`
+            FROM `" . DATABASENAME_NODA . "`.`tag`
+            WHERE INSTR(`tag_name`, 'i')");
+        $tagByDisplayNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `trans_name`, `tag_id`
+            FROM `" . DATABASENAME_NODA . "`.`tag_translation`
+            WHERE INSTR(`trans_name`, 'i')
+                AND `trans_language` = 'de'");
+        $mysqli->close();
+
+        return [
+            'Tag ID by name: ' . $tagByNameSimple[0] => $tagByNameSimple,
+            'Tag ID by translated name: ' . $tagByDisplayNameSimple[0] => $tagByDisplayNameSimple,
+        ];
+
+    }
+
+    /**
+     * Test getting tags by name works.
+     *
+     * @param string  $name        Name of the entry.
+     * @param integer $expected_id Expected target ID.
+     *
+     * @return void
+     */
+    #[DataProvider('tagByNameProvider')]
+    public function testGetTagIdByNameWorks(string $name, int $expected_id):void {
+
+        $this->runRegularComparisonTests("getTagIDByName", $name, $expected_id);
+
+    }
+
+    // TagIDByRewrite
+
+    /**
+     * Returns a test tag name registered for rewriting.
+     *
+     * @return array<array{0: string, 1: integer}>
+     */
+    public static function tagByRewriteProvider():array {
+
+        $mysqli = md_main_mysqli_connect();
+        $tagByRewriteSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `input_name`, `tag_id`
+            FROM `" . DATABASENAME_NODA . "`.`tag_rewriting`
+            WHERE INSTR(`input_name`, 'i')");
+        $mysqli->close();
+
+        return [
+            'Tag ID by rewrite: ' . $tagByRewriteSimple[0] => $tagByRewriteSimple,
+        ];
+
+    }
+
+    /**
+     * Test getting tags by rewrite works.
+     *
+     * @param string  $name        Name of the entry.
+     * @param integer $expected_id Expected target ID.
+     *
+     * @return void
+     */
+    #[DataProvider('tagByRewriteProvider')]
+    public function testGetTagIdByRewriteWorks(string $name, int $expected_id):void {
+
+        self::assertContains($expected_id, NodaIDGetter::getTagIDByRewrite($this->_mysqli, "de", $name));
+
+        // Ensure that different capitalization does not influence the results
+        self::assertContains($expected_id, NodaIDGetter::getTagIDByRewrite($this->_mysqli, "de", strtoupper($name)));
+        self::assertContains($expected_id, NodaIDGetter::getTagIDByRewrite($this->_mysqli, "de", strtolower($name)));
+
+        // Ensure that diacritics will stop the entry from matching
+        $nameReplaced = self::_replaceVowelsWithDiacriticVariants($name);
+        self::assertFalse(in_array($expected_id, NodaIDGetter::getTagIDByRewrite($this->_mysqli, "de", $nameReplaced), true));
+
+    }
+
+    // TimeIDByName
+
+    /**
+     * Returns a test time name.
+     *
+     * @return array<array{0: string, 1: integer}>
+     */
+    public static function timeByNameProvider():array {
+
+        $mysqli = md_main_mysqli_connect();
+        $timeByNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `zeit_name`, `zeit_id`
+            FROM `" . DATABASENAME_NODA . "`.`zeiten`
+            WHERE INSTR(`zeit_name`, 'i')");
+        $timeByDisplayNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `trans_name`, `zeit_id`
+            FROM `" . DATABASENAME_NODA . "`.`zeit_translation`
+            WHERE INSTR(`trans_name`, 'i')
+                AND `trans_language` = 'de'");
+        $mysqli->close();
+
+        return [
+            'Time ID by name: ' . $timeByNameSimple[0] => $timeByNameSimple,
+            'Time ID by translated name: ' . $timeByDisplayNameSimple[0] => $timeByDisplayNameSimple,
+        ];
+
+    }
+
+    /**
+     * Test getting persinst by name works.
+     *
+     * @param string  $name        Name of the entry.
+     * @param integer $expected_id Expected target ID.
+     *
+     * @return void
+     */
+    #[DataProvider('timeByNameProvider')]
+    public function testGetTimeIdByNameWorks(string $name, int $expected_id):void {
+
+        $this->runRegularComparisonTests("getTimeIDByName", $name, $expected_id);
+
+    }
+
+    // timeIDByRewrite
+
+    /**
+     * Returns a test time name registered for rewriting.
+     *
+     * @return array<array{0: string, 1: integer}>
+     */
+    public static function timeByRewriteProvider():array {
+
+        $mysqli = md_main_mysqli_connect();
+        $timeByRewriteSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `input_name`, `zeit_id`
+            FROM `" . DATABASENAME_NODA . "`.`zeit_rewriting`
+            WHERE INSTR(`input_name`, 'i')");
+        $mysqli->close();
+
+        return [
+            'Time ID by rewrite: ' . $timeByRewriteSimple[0] => $timeByRewriteSimple,
+        ];
+
+    }
+
+    /**
+     * Test getting times by rewrite works.
+     *
+     * @param string  $name        Name of the entry.
+     * @param integer $expected_id Expected target ID.
+     *
+     * @return void
+     */
+    #[DataProvider('timeByRewriteProvider')]
+    public function testGetTimeIdByRewriteWorks(string $name, int $expected_id):void {
+
+        $this->runRegularComparisonTests("getTimeIDByRewrite", $name, $expected_id);
+
+    }
+}
diff --git a/tests/bootstrap.php b/tests/bootstrap.php
index b1d499e..d27cbb9 100644
--- a/tests/bootstrap.php
+++ b/tests/bootstrap.php
@@ -12,7 +12,17 @@ declare(strict_types = 1);
 
     // Try using class map as defined through /scripts/buildClassMap.php
 
-    foreach (array_merge([__DIR__ . '/../tests', __DIR__ . '/../src', __DIR__ . '/../src/enums', __DIR__ . '/../../MD_STD/src', __DIR__ . '/../../MDErrorReporter', __DIR__ . '/../../MDErrorReporter/exceptions', __DIR__ . '/../../MDErrorReporter/exceptions/generic', __DIR__ . '/../../MDErrorReporter/exceptions/updates']) as $classDir) {
+    foreach (array_merge([__DIR__ . '/../tests',
+        __DIR__ . '/../src',
+        __DIR__ . '/../src/enums',
+        __DIR__ . '/../../MD_STD/src',
+        __DIR__ . '/../../MDErrorReporter',
+        __DIR__ . '/../../MDErrorReporter/exceptions',
+        __DIR__ . '/../../MDErrorReporter/exceptions/generic',
+        __DIR__ . '/../../MDErrorReporter/exceptions/updates',
+        __DIR__ . '/../../MDMysqli/src',
+        __DIR__ . '/../../MDMysqli/exceptions',
+    ]) as $classDir) {
 
         if (\file_exists("$classDir/$className.php")) {
             include "$classDir/$className.php";