Merge branch 'master' of gitea:museum-digital/MDNodaHelpers

Close #35

src/NodaBlacklistedTerms.php

@@ -13,7 +13,7 @@ final class NodaBlacklistedTerms {
     /**
      * A blacklist of disallowed tags. All entries are listed in full lowercase.
      */
-    const TAG_BLACKLIST = [
+    public const TAG_BLACKLIST = [
         'de' => [
             'andere',
             'anderes',
@@ -33,16 +33,35 @@ final class NodaBlacklistedTerms {
             'ding',
             'dinge',
             'aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa',
+            'Aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa',
+            'aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa',
+            'nichtmünzliches',
+            'unbestimmt',
+            'AA',
+            'BB',
+            'CC',
+            'DD',
+            'EE',
+            'FF',
+            'GG',
+            'HH',
+            'LL',
+            '-',
+            '?',
         ],
         'en' => [
             'other',
             'others',
             'unknown',
             'various',
+            '-',
+            '?',
         ],
         'hu' => [
             'ism.',
             'ismeretlen',
+            '-',
+            '?',
         ],
     ];
 

src/NodaConsolidatedNamesAbstract.php

@@ -10,7 +10,6 @@ declare(strict_types = 1);
  * Abstract class to be inherited by classes for writing consolidated vocabulary names.
  */
 abstract class NodaConsolidatedNamesAbstract {
-
     /**
      * This function sanitizes a string.
      *

src/NodaConsolidatedNamesForPersinst.php

@@ -79,17 +79,18 @@ final class NodaConsolidatedNamesForPersinst extends NodaConsolidatedNamesAbstra
         if (count($parts) !== 2) return [];
 
         $nameOnly = trim($parts[0]);
-        $dateString = rtrim($parts[1], ')'); //
+        $dateString = trim(rtrim($parts[1], ')')); //
 
         if (!empty($dates = NodaTimeSplitter::is_timespan($dateString))
-            && $dates[0] !== '?'
-            && $dates[1] !== '?'
-            && intval($dates[1]) - intval($dates[0]) < 150
+            && $dates->start_year !== '?'
+            && $dates->end_year !== '?'
+            && $dates->start_year !== $dates->end_year
+            && intval($dates->end_year) - intval($dates->start_year) < 150
         ) {
             return [
                 'name' => $nameOnly,
-                'birth' => $dates[0],
-                'death' => $dates[1],
+                'birth' => $dates->start_year,
+                'death' => $dates->end_year,
             ];
         }
 
@@ -120,5 +121,4 @@ final class NodaConsolidatedNamesForPersinst extends NodaConsolidatedNamesAbstra
         return \trim($name, " ;.\t" . PHP_EOL);
 
     }
-
 }

src/NodaConsolidatedNamesForPlaces.php

@@ -93,7 +93,7 @@ final class NodaConsolidatedNamesForPlaces extends NodaConsolidatedNamesAbstract
      *
      * @return string
      */
-    private static function _rewrite_narrower_broader_pairs_to_brackets(string $name, string $indicator, $separator = ', '):string {
+    private static function _rewrite_narrower_broader_pairs_to_brackets(string $name, string $indicator, string $separator = ', '):string {
 
         if (str_contains($name, $indicator)
             && substr_count($name, $indicator) === 1
@@ -105,8 +105,7 @@ final class NodaConsolidatedNamesForPlaces extends NodaConsolidatedNamesAbstract
 
             // Skip entries like "Vaci utca 12 Budapest, Vaci utca"
             $indicatorTrimmed = trim($indicator);
-            if (
-                (str_ends_with($parts[0], $indicatorTrimmed) && str_contains($parts[1], $indicatorTrimmed))
+            if ((str_ends_with($parts[0], $indicatorTrimmed) && str_contains($parts[1], $indicatorTrimmed))
                 || (str_ends_with($parts[1], $indicatorTrimmed) && str_contains($parts[0], $indicatorTrimmed))
             ) {
                 return $name;
@@ -133,10 +132,8 @@ final class NodaConsolidatedNamesForPlaces extends NodaConsolidatedNamesAbstract
 
             }
 
-
         }
 
-
         return $name;
 
     }
@@ -226,7 +223,7 @@ final class NodaConsolidatedNamesForPlaces extends NodaConsolidatedNamesAbstract
      *
      * @return string
      */
-    private static function _rewrite_ukrainian_names_by_hierarchy($name):string {
+    private static function _rewrite_ukrainian_names_by_hierarchy(string $name):string {
 
         $identifiersByLevel = [
             'state' => [' РСР', 'РСР ', ' АРСР', 'АРСР ', ' губернія', 'губернія '],
@@ -328,13 +325,14 @@ final class NodaConsolidatedNamesForPlaces extends NodaConsolidatedNamesAbstract
         }
 
         $output = $main_name;
-        if (!empty($specifiers)) $output .= ' (' . implode(', ', $specifiers) . ')';
+        if (!empty($specifiers)) {
+            $output .= ' (' . implode(', ', $specifiers) . ')';
+        }
 
         return $output;
 
     }
 
-
     /**
      * Cleans and consolidates name parts appearing regularly in Ukrainian place names.
      *
@@ -427,15 +425,12 @@ final class NodaConsolidatedNamesForPlaces extends NodaConsolidatedNamesAbstract
 
             // If one of the parts is a blacklisted term or a cardinal directions, skip this
 
-            if (
-                (in_array($parts[0], self::_COUNTRY_REWRITE_BLACKLISTED_TERMS, true)
-                    || in_array($parts[0], $cardinal_directions, true)
-                    || in_array(strtolower($parts[0]), $cardinal_directions, true)
-                )
+            if ((in_array($parts[0], self::_COUNTRY_REWRITE_BLACKLISTED_TERMS, true)
+                || in_array($parts[0], $cardinal_directions, true)
+                || in_array(strtolower($parts[0]), $cardinal_directions, true))
                 || (in_array($parts[1], self::_COUNTRY_REWRITE_BLACKLISTED_TERMS, true)
-                    || in_array($parts[1], $cardinal_directions, true)
-                    || in_array(strtolower($parts[1]), $cardinal_directions, true)
-                )
+                || in_array($parts[1], $cardinal_directions, true)
+                || in_array(strtolower($parts[1]), $cardinal_directions, true))
             ) {
                 return $name;
             }

src/NodaCountingTimeIndicator.php

@@ -0,0 +1,74 @@
+<?PHP
+/**
+ * Represents a time indicator (CE / BCE).
+ *
+ * @author Joshua Ramon Enslin <joshua@museum-digital.de>
+ */
+declare(strict_types = 1);
+
+/**
+ * Represents a time indicator (CE / BCE).
+ */
+enum NodaCountingTimeIndicator implements JsonSerializable {
+
+    case ce;
+    case bce;
+
+    /**
+     * Returns a value of this type based on a string.
+     *
+     * @param string $input Input to get a value from.
+     *
+     * @return NodaCountingTimeIndicator
+     */
+    public static function fromString(string $input):NodaCountingTimeIndicator {
+
+        return match($input) {
+            '+' => self::ce,
+            '-' => self::bce,
+            'ce' => self::ce,
+            'bce' => self::bce,
+            default => throw new MDpageParameterNotFromListException("Unknown counting time indicator (bc / bce)"),
+        };
+
+    }
+
+    /**
+     * Returns a canonical string representation.
+     *
+     * @return string
+     */
+    public function toString():string {
+
+        return match($this) {
+            self::ce  => '+',
+            self::bce => '-',
+        };
+
+    }
+
+    /**
+     * Returns a canonical string representation.
+     *
+     * @return string
+     */
+    public function toGerman():string {
+
+        return match($this) {
+            self::ce  => ' n. Chr.',
+            self::bce => ' v. Chr.',
+        };
+
+    }
+
+    /**
+     * Provides the option to serialize as a string during json_encode().
+     *
+     * @return string
+     */
+    public function jsonSerialize():string {
+
+        return $this->toString();
+
+    }
+}

src/NodaDistinctlyTypedStrings.php

@@ -10,7 +10,6 @@ declare(strict_types = 1);
  * contains a string.
  */
 final class NodaDistinctlyTypedStrings {
-
     /**
      * Checks the vocabulary database whether it contains a given string.
      *
@@ -40,5 +39,4 @@ final class NodaDistinctlyTypedStrings {
         return $cur[0];
 
     }
-
 }

src/NodaGroup.php

@@ -44,6 +44,32 @@ final class NodaGroup {
 
     }
 
+    /**
+     * Returns basic description of a group.
+     *
+     * @param integer $group_id Group ID.
+     *
+     * @return array{name: string, comment: string}
+     */
+    public function getDescription(int $group_id):array {
+
+        $result = $this->_mysqli_noda->query_by_stmt("SELECT `group_name`, `comment`
+            FROM `group`
+            WHERE `group_id` = ?", "i", $group_id);
+
+        if (!($cur = $result->fetch_row())) {
+            $result->close();
+            throw new MDmainEntityNotExistentException("This group does not seem to exist");
+        }
+        $result->close();
+
+        return [
+            'name' => $cur[0],
+            'comment' => $cur[1],
+        ];
+
+    }
+
     /**
      * Adds a group.
      *
@@ -54,6 +80,10 @@ final class NodaGroup {
      */
     public function insert(string $name, string $comment = ''):int {
 
+        if (empty($name)) {
+            throw new MDpageParameterMissingException("Name cannot be empty when adding groups.");
+        }
+
         $insertStmt = $this->_mysqli_noda->do_prepare("INSERT INTO `group`
             (`group_name`, `comment`)
             VALUES
@@ -68,6 +98,55 @@ final class NodaGroup {
 
     }
 
+    /**
+     * Updates a group.
+     *
+     * @param integer $group_id ID of the group to update.
+     * @param string  $name     Name of the group.
+     * @param string  $comment  Optional: Comment for the group.
+     *
+     * @return void
+     */
+    public function update(int $group_id, string $name, string $comment = ''):void {
+
+        if (empty($name)) {
+            throw new MDpageParameterMissingException("Name cannot be empty when adding groups.");
+        }
+
+        $insertStmt = $this->_mysqli_noda->do_prepare("UPDATE `group`
+            SET `group_name` = ?,
+                `comment` = ?
+            WHERE `group_id` = ?");
+
+        $insertStmt->bind_param("ssi", $name, $comment, $group_id);
+        $insertStmt->execute();
+        $insertStmt->close();
+
+    }
+
+    /**
+     * Deletes a group.
+     *
+     * @param integer $group_id ID of the group to delete.
+     *
+     * @return void
+     */
+    public function delete(int $group_id):void {
+
+        $this->_mysqli_noda->update_query_by_stmt("DELETE FROM `v_group_persinst`
+            WHERE `group_id` = ?", "i", $group_id);
+        $this->_mysqli_noda->update_query_by_stmt("DELETE FROM `v_group_orte`
+            WHERE `group_id` = ?", "i", $group_id);
+        $this->_mysqli_noda->update_query_by_stmt("DELETE FROM `v_group_zeiten`
+            WHERE `group_id` = ?", "i", $group_id);
+        $this->_mysqli_noda->update_query_by_stmt("DELETE FROM `v_group_tag`
+            WHERE `group_id` = ?", "i", $group_id);
+
+        $this->_mysqli_noda->update_query_by_stmt("DELETE FROM `group`
+            WHERE `group_id` = ?", "i", $group_id);
+
+    }
+
     /**
      * Adds actors to a nodac group.
      *

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 +136,53 @@ 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 0;
 
-        return $output;
+    }
+
+    /**
+     * Returns persinst ID by entry in persinst translations table,
+     * irrespective of language.
+     *
+     * @param MDMysqli $mysqli_noda Database connection.
+     * @param string   $name        Name of the persinst to search for.
+     *
+     * @return integer
+     */
+    public static function getPersinstIDByAnyTransName(MDMysqli $mysqli_noda, string $name):int {
+
+        if (empty($name)) return 0;
+
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `persinst_id`, `trans_name`
+            FROM `persinst_translation`
+            WHERE `trans_name` = ?
+            LIMIT 2", "s", $name);
+
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($cur[1], $name)) {
+                $result->close();
+                return (int)$cur[0];
+            }
+        }
+        $result->close();
+
+        return 0;
 
     }
 
@@ -145,8 +202,8 @@ 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 +212,15 @@ 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 +236,23 @@ 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 +270,8 @@ 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 +282,15 @@ 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 +344,23 @@ 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 +406,22 @@ 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 +437,21 @@ 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 +468,53 @@ 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 0;
 
-        return $output;
+    }
+
+    /**
+     * Returns place ID by entry in place translations table, irrespective of
+     * language.
+     *
+     * @param MDMysqli $mysqli_noda Database connection.
+     * @param string   $name        Name of the place to search for.
+     *
+     * @return integer
+     */
+    public static function getPlaceIDByAnyTransName(MDMysqli $mysqli_noda, string $name):int {
+
+        if (empty($name)) return 0;
+
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `ort_id`, `trans_name`
+            FROM `ort_translation`
+            WHERE `trans_name` = ?
+            LIMIT 2", "s", $name);
+
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($cur[1], $name)) {
+                $result->close();
+                return (int)$cur[0];
+            }
+        }
+        $result->close();
+
+        return 0;
 
     }
 
@@ -470,22 +565,23 @@ 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 +629,19 @@ 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 +659,21 @@ 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 +690,53 @@ 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 0;
 
-        return $output;
+    }
+
+    /**
+     * Returns tag ID by entry in tag translations table,
+     * irrespective of language.
+     *
+     * @param MDMysqli $mysqli_noda Database connection.
+     * @param string   $name        Name of the tag to search for.
+     *
+     * @return integer
+     */
+    public static function getTagIDByAnyTransName(MDMysqli $mysqli_noda, string $name):int {
+
+        if (empty($name)) return 0;
+
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `tag_id`, `trans_name`
+            FROM `tag_translation`
+            WHERE `trans_name` = ?
+            LIMIT 2", "s", $name);
+
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($name, $cur[1])) {
+                $result->close();
+                return (int)$cur[0];
+            }
+        }
+        $result->close();
+
+        return 0;
 
     }
 
@@ -656,22 +787,23 @@ 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 +851,21 @@ 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 +881,21 @@ 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 +912,52 @@ 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 0;
 
-        return $output;
+    }
+
+    /**
+     * Returns time ID by entry in time translations table.
+     *
+     * @param MDMysqli $mysqli_noda Database connection.
+     * @param string   $name        Name of the time to search for.
+     *
+     * @return integer
+     */
+    public static function getTimeIDByAnyTransName(MDMysqli $mysqli_noda, string $name):int {
+
+        if (empty($name)) return 0;
+
+        $result = $mysqli_noda->query_by_stmt("
+            SELECT `zeit_id`, `trans_name`
+            FROM `zeit_translation`
+            WHERE `trans_name` = ?
+            LIMIT 2", "s", $name);
+
+        while ($cur = $result->fetch_row()) {
+            if (self::_stri_matches($name, $cur[1])) {
+                $result->close();
+                return (int)$cur[0];
+            }
+        }
+        $result->close();
+
+        return 0;
 
     }
 
@@ -810,22 +975,23 @@ 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;
 
     }
 
@@ -956,4 +1122,79 @@ final class NodaIDGetter {
         return 0;
 
     }
+
+    /**
+     * Checks each string in a list of strings for its existence as a tag name.
+     *
+     * @param MDMysqli                $mysqli_noda Database connection.
+     * @param string                  $lang        Language to check in.
+     * @param non-empty-array<string> $phrases     List of phrases to check.
+     *
+     * @return array{count: int, tag: integer[], actor: integer[], time: integer[], place: integer[]}
+     */
+    public static function searchEntryNamesByList(MDMysqli $mysqli_noda, string $lang, array $phrases):array {
+
+        $output = [
+            'count' => 0,
+            'tag' => [],
+            'actor' => [],
+            'time' => [],
+            'place' => [],
+        ];
+
+        foreach ($phrases as $phrase) {
+
+            if (($tag_id = NodaIDGetter::getTagIDByNamesAndRewrites($mysqli_noda, $lang, $phrase)) !== 0 && !in_array($tag_id, $output['tag'], true)) {
+                $output['tag'][] = $tag_id;
+                ++$output['count'];
+            }
+            else if (($tag_id_by_tl = NodaIDGetter::getTagIDByAnyTransName($mysqli_noda, $phrase)) !== 0 && !in_array($tag_id_by_tl, $output['tag'], true)) {
+                $output['tag'][] = $tag_id_by_tl;
+                ++$output['count'];
+            }
+            else if (($place_id = NodaIDGetter::getPlaceIDByNamesAndRewrites($mysqli_noda, $lang, $phrase)) !== 0 && !in_array($place_id, $output['place'], true)) {
+                $output['place'][] = $place_id;
+                ++$output['count'];
+            }
+            else if (($place_id = NodaIDGetter::getPlaceIDByAnyTransName($mysqli_noda, $phrase)) !== 0 && !in_array($place_id, $output['place'], true)) {
+                $output['place'][] = $place_id;
+                ++$output['count'];
+            }
+            else if (($persinst_id = NodaIDGetter::getPersinstIDByNamesAndRewrites($mysqli_noda, $lang, $phrase, '', '')) !== 0 && !in_array($persinst_id, $output['actor'], true)) {
+                $output['actor'][] = $persinst_id;
+                ++$output['count'];
+            }
+            else if (($persinst_id = NodaIDGetter::getPersinstIDByAnyTransName($mysqli_noda, $phrase)) !== 0 && !in_array($persinst_id, $output['actor'], true)) {
+                $output['actor'][] = $persinst_id;
+                ++$output['count'];
+            }
+            else if (($time_id = NodaIDGetter::getTimeIDByNamesAndRewrites($mysqli_noda, $lang, $phrase)) !== 0 && !in_array($time_id, $output['time'], true)) {
+                $output['time'][] = $time_id;
+                ++$output['count'];
+            }
+            else if (($time_id = NodaIDGetter::getTimeIDByAnyTransName($mysqli_noda, $phrase)) !== 0 && !in_array($time_id, $output['time'], true)) {
+                $output['time'][] = $time_id;
+                ++$output['count'];
+            }
+
+        }
+
+        if (count($phrases) !== $output['count']) {
+            return [
+                'count' => 0,
+                'tag' => [],
+                'actor' => [],
+                'time' => [],
+                'place' => [],
+            ];
+        }
+
+        if (!empty($output['tag'])) sort($output['tag']);
+        if (!empty($output['actor'])) sort($output['actor']);
+        if (!empty($output['time'])) sort($output['time']);
+        if (!empty($output['place'])) sort($output['place']);
+
+        return $output;
+
+    }
 }

src/NodaImportLogger.php

@@ -32,8 +32,12 @@ final class NodaImportLogger {
         $logStmt = $mysqli_noda->do_prepare("INSERT INTO `persinst_logged_imports`
             (`instance`, `institution_id`, `input_string`, `persinst_id`)
             VALUES (?, ?, ?, ?)");
-        $logStmt->bind_param("sisi", $instance, $institution_id, $loggedName, $persinst_id);
-        $logStmt->execute();
+        try {
+            $logStmt->bind_param("sisi", $instance, $institution_id, $loggedName, $persinst_id);
+            $logStmt->execute();
+        }
+        catch (MDMysqliDuplicateKeysError $e) {
+        }
         $logStmt->close();
 
     }
@@ -54,8 +58,12 @@ final class NodaImportLogger {
         $logStmt = $mysqli_noda->do_prepare("INSERT INTO `orte_logged_imports`
             (`instance`, `institution_id`, `input_string`, `ort_id`)
             VALUES (?, ?, ?, ?)");
-        $logStmt->bind_param("sisi", $instance, $institution_id, $name, $ort_id);
-        $logStmt->execute();
+        try {
+            $logStmt->bind_param("sisi", $instance, $institution_id, $name, $ort_id);
+            $logStmt->execute();
+        }
+        catch (MDMysqliDuplicateKeysError $e) {
+        }
         $logStmt->close();
 
     }
@@ -76,8 +84,12 @@ final class NodaImportLogger {
         $logStmt = $mysqli_noda->do_prepare("INSERT INTO `zeiten_logged_imports`
             (`instance`, `institution_id`, `input_string`, `zeit_id`)
             VALUES (?, ?, ?, ?)");
-        $logStmt->bind_param("sisi", $instance, $institution_id, $name, $zeit_id);
-        $logStmt->execute();
+        try {
+            $logStmt->bind_param("sisi", $instance, $institution_id, $name, $zeit_id);
+            $logStmt->execute();
+        }
+        catch (MDMysqliDuplicateKeysError $e) {
+        }
         $logStmt->close();
 
     }
@@ -98,8 +110,12 @@ final class NodaImportLogger {
         $logStmt = $mysqli_noda->do_prepare("INSERT INTO `tag_logged_imports`
             (`instance`, `institution_id`, `input_string`, `tag_id`)
             VALUES (?, ?, ?, ?)");
-        $logStmt->bind_param("sisi", $instance, $institution_id, $name, $tag_id);
-        $logStmt->execute();
+        try {
+            $logStmt->bind_param("sisi", $instance, $institution_id, $name, $tag_id);
+            $logStmt->execute();
+        }
+        catch (MDMysqliDuplicateKeysError $e) {
+        }
         $logStmt->close();
 
     }

src/NodaLogEdit.php

@@ -19,6 +19,7 @@ final class NodaLogEdit {
 
     const SECTION_WHITELIST = [
         'base',
+        'addition',
         'noda_link',
         'name_variant',
         'logged_import_concordances',

src/NodaMailChecker.php

@@ -107,4 +107,26 @@ final class NodaMailChecker {
         return self::validateMailDomainAccessibilityCached($mysqli, $domain);
 
     }
+
+    /**
+     * Validates mail address, throwing an exception if the mail address is not valid.
+     *
+     * @param MDMysqli $mysqli       DB connection.
+     * @param string   $mail_address Address.
+     *
+     * @return string
+     */
+    public static function validateMail(MDMysqli $mysqli, string $mail_address):string {
+
+        if (empty($mail_address)) return $mail_address;
+
+        $mail_address = MD_STD_IN::sanitize_email($mail_address);
+
+        if (self::validateMailByDomainAccessibilityCached($mysqli, $mail_address) === false) {
+            throw new MDInvalidEmail("The host name of the entered mail address is invalid");
+        }
+
+        return $mail_address;
+
+    }
 }

src/NodaNameGetter.php

@@ -143,6 +143,54 @@ final class NodaNameGetter {
 
     }
 
+    /**
+     * Static function for getting persinst names in bulk.
+     *
+     * @param MDMysqli       $mysqli_noda  DB connection.
+     * @param string         $lang         Language.
+     * @param array<integer> $persinst_ids Persinst IDs.
+     *
+     * @return array<int, string>
+     */
+    public static function getBatchPersinstNamesWithLifeDates(MDMysqli $mysqli_noda, string $lang, array $persinst_ids):array {
+
+        $output = [];
+
+        // Get translations
+        $result = $mysqli_noda->do_read_query("SELECT `persinst`.`persinst_id`, `trans_name`, `persinst_geburtsjahr`, `persinst_sterbejahr`
+            FROM `persinst_translation`, `persinst`
+            WHERE `trans_language` = '" . $mysqli_noda->escape_string($lang) . "'
+                AND `persinst`.`persinst_id` = `persinst_translation`.`persinst_id`
+                AND `persinst`.`persinst_id` IN (" . implode(', ', $persinst_ids) . ")");
+
+        while ($cur = $result->fetch_row()) {
+            $name = (string)$cur[1];
+            if (!empty($cur[2]) || !empty($cur[3])) {
+                $name .= ' (' . $cur[2] . '-' . $cur[3] . ')';
+            }
+            $output[(int)$cur[0]] = $name;
+        }
+        $result->close();
+
+        if (!empty($persinst_ids_left = array_diff($persinst_ids, array_keys($output)))) {
+            $result = $mysqli_noda->do_read_query("SELECT `persinst_id`, `persinst_anzeigename`
+                FROM `persinst`
+                WHERE `persinst_id` IN (" . implode(', ', $persinst_ids_left) . ")");
+
+            while ($cur = $result->fetch_row()) {
+                $output[(int)$cur[0]] = (string)$cur[1];
+            }
+            $result->close();
+        }
+
+        if (count($output) > 1) {
+            asort($output);
+        }
+
+        return $output;
+
+    }
+
     /**
      * Static function for getting time names in bulk.
      *

src/NodaSplitTime.php

@@ -0,0 +1,407 @@
+<?PHP
+/**
+ * Describes a time after splitting / transfer object.
+ *
+ * @author Joshua Ramon Enslin <joshua@museum-digital.de>
+ */
+declare(strict_types = 1);
+
+/**
+ * Describes a time after splitting / transfer object.
+ */
+final class NodaSplitTime {
+
+    public const DEFAULT_DATE = '0001-01-01';
+
+    public readonly string $start_year;
+    public readonly string $end_year;
+
+    public readonly string $counting_time_month;
+    public readonly string $counting_time_day;
+
+    public readonly NodaCountingTimeIndicator $counting_time_indicator;
+    public readonly NodaTimeBeforeAfterIndicator $before_after_indicator;
+
+    public string $start_date;
+    public string $end_date;
+
+    /**
+     * Returns a single, exact date.
+     *
+     * @param string                       $year                   Year.
+     * @param string                       $month                  Month.
+     * @param string                       $day                    Day.
+     * @param NodaTimeBeforeAfterIndicator $before_after_indicator Determines if the time is exact or before / after.
+     *
+     * @return NodaSplitTime
+     */
+    public static function genExactDate(string $year, string $month, string $day, NodaTimeBeforeAfterIndicator $before_after_indicator = NodaTimeBeforeAfterIndicator::none):NodaSplitTime {
+
+        $start_year = $end_year = $year;
+        $start_date = $end_date = $year . '-' . $month . '-' . $day;
+
+        if ($before_after_indicator === NodaTimeBeforeAfterIndicator::before
+            || $before_after_indicator === NodaTimeBeforeAfterIndicator::until
+        ) {
+            $start_year = $start_date = '?';
+        }
+        if ($before_after_indicator === NodaTimeBeforeAfterIndicator::after
+            || $before_after_indicator === NodaTimeBeforeAfterIndicator::since
+        ) {
+            $end_year = $end_date = '?';
+        }
+
+        return new NodaSplitTime($start_year, $end_year, $month, $day, start_date: $start_date, end_date: $end_date);
+
+    }
+
+    /**
+     * Validates the entered start year.
+     *
+     * @param string $input Input to validate.
+     *
+     * @return void
+     */
+    private function _validateStartYear(string $input):void {
+
+        if (strlen($input) > 6) {
+            throw new MDgenericInvalidInputsException("Time statement longer than 6 characters is impossible");
+        }
+
+        if (($this->before_after_indicator === NodaTimeBeforeAfterIndicator::before
+            || $this->before_after_indicator === NodaTimeBeforeAfterIndicator::until)
+            && $input !== '?'
+        ) {
+            throw new MDgenericInvalidInputsException("Times with no certain start need to have a question mark (?) entered as a start date");
+        }
+
+    }
+
+    /**
+     * Validates the entered end year.
+     *
+     * @param string $input Input to validate.
+     *
+     * @return void
+     */
+    private function _validateEndYear(string $input):void {
+
+        if (strlen($input) > 6) {
+            throw new MDgenericInvalidInputsException("Time statement longer than 6 characters is impossible");
+        }
+
+        if (($this->before_after_indicator === NodaTimeBeforeAfterIndicator::after
+            || $this->before_after_indicator === NodaTimeBeforeAfterIndicator::since)
+            && $input !== '?'
+        ) {
+            throw new MDgenericInvalidInputsException("Times with no certain end need to have a question mark (?) entered as a end date");
+        }
+
+    }
+
+    /**
+     * Pads to four digits. E.g. 2 > 02.
+     *
+     * @param string $input Input string.
+     *
+     * @return string
+     */
+    public static function pad_to_two(string $input):string {
+
+        return \substr("00" . $input, -2);
+
+    }
+
+    /**
+     * Validates the entered month string.
+     *
+     * @param string $input Input to validate.
+     *
+     * @return string
+     */
+    private function _validateCountingTimeMonth(string $input):string {
+
+        if (strlen($input) > 2) throw new MDgenericInvalidInputsException("Input too long");
+
+        if ($input === '00') {
+            return $input;
+        }
+
+        if (($parsedInt = filter_var(ltrim($input, "0"), FILTER_VALIDATE_INT)) === false) {
+            throw new MDgenericInvalidInputsException("Input value is not numeric");
+        }
+        if ($parsedInt > 12) {
+            throw new MDgenericInvalidInputsException("Attempted to set a month number beyond 12");
+        }
+
+        return self::pad_to_two($input);
+
+    }
+
+    /**
+     * Validates the entered day string.
+     *
+     * @param string $input Input to validate.
+     *
+     * @return string
+     */
+    private function _validateCountingTimeDay(string $input):string {
+
+        if (strlen($input) > 2) throw new MDgenericInvalidInputsException("Input too long");
+
+        if ($input === '00') {
+            return $input;
+        }
+
+        if (($parsedInt = filter_var(ltrim($input, "0"), FILTER_VALIDATE_INT)) === false) {
+            throw new MDgenericInvalidInputsException("Input value is not numeric");
+        }
+        if ($parsedInt > 31) {
+            throw new MDgenericInvalidInputsException("Attempted to set a day number beyond 31");
+        }
+
+        return self::pad_to_two($input);
+
+    }
+
+    /**
+     * Returns a date time for the start of the time.
+     *
+     * @return DateTime
+     */
+    public function startToDateTime():DateTime {
+
+        if ($this->counting_time_indicator === NodaCountingTimeIndicator::bce) {
+            return new DateTime('-' . $this->start_date);
+        }
+        else {
+            return new DateTime($this->start_date);
+        }
+
+    }
+
+    /**
+     * Returns a date time for the end of the time.
+     *
+     * @return DateTime
+     */
+    public function endToDateTime():DateTime {
+
+        if ($this->counting_time_indicator === NodaCountingTimeIndicator::bce) {
+            return new DateTime('-' . $this->end_date);
+        }
+        else {
+            return new DateTime($this->end_date);
+        }
+
+    }
+
+    /**
+     * Generates a time name based on the current entry.
+     *
+     * @return string
+     */
+    public function toTimeName():string {
+
+        $prefix = $this->before_after_indicator->toString();
+        if (!empty($prefix)) $prefix .= ' ';
+
+        // Determine start and end for display
+        if ($this->start_year === '?') {
+            $start = (int)$this->end_year;
+        }
+        else $start = (int)$this->start_year;
+
+        if ($this->end_year === '?') {
+            $end = (int)$this->start_year;
+        }
+        else $end = (int)$this->end_year;
+
+        if ($this->before_after_indicator === NodaTimeBeforeAfterIndicator::before && $this->counting_time_month === '00') {
+            $start++;
+            $end++;
+        }
+        else if ($this->before_after_indicator === NodaTimeBeforeAfterIndicator::after && $this->counting_time_month === '00') {
+            $start--;
+            $end--;
+        }
+
+        // Determine suffix
+        if ($start < 0 && $end < 0) {
+            $suffix = " v. Chr.";
+        }
+        else if ($end < 1000) {
+            $suffix = " n. Chr.";
+        }
+        else $suffix = "";
+
+        $start = \abs($start);
+        $end = \abs($end);
+
+        if ($start !== $end) {
+            return "{$prefix}{$start}-{$end}{$suffix}";
+        }
+
+        // A single day of a given month of a given (single) year
+        else if (\intval($this->counting_time_month) !== 0 and \intval($this->counting_time_day) !== 0) {
+            return "{$prefix}{$this->counting_time_day}.{$this->counting_time_month}.{$start}{$suffix}";
+        }
+
+        // A single year
+        else if ($start === $end && trim((string)$this->counting_time_month, " 0") === "" && trim((string)$this->counting_time_day, " 0") === "") {
+            return "{$prefix}{$start}{$suffix}";
+        }
+
+        // Single month of a given year
+        else if ($start === $end && trim((string)$this->counting_time_month, " 0") !== "" && trim((string)$this->counting_time_day, " 0") === "") {
+
+            $fmt = new IntlDateFormatter(
+                'de-DE',
+                IntlDateFormatter::FULL,
+                IntlDateFormatter::FULL,
+                null,
+                IntlDateFormatter::GREGORIAN,
+                'MMMM Y'
+            );
+
+            try {
+                return $prefix . $fmt->format(MD_STD::strtotime("{$start}-{$this->counting_time_month}-15 01:01:01")) . $suffix;
+            }
+            catch (MDInvalidInputDate $e) {
+                return "";
+            }
+        }
+
+        return "";
+
+    }
+
+    /**
+     * Returns an array in the old time splitter format (array with sex values).
+     *
+     * @return array<string>
+     */
+    public function toOldFormat():array {
+
+        return [
+            $this->start_year,
+            $this->end_year,
+            $this->counting_time_month,
+            $this->counting_time_day,
+            $this->counting_time_indicator->toString(),
+            $this->before_after_indicator->toString(),
+        ];
+
+    }
+
+    /**
+     * Constructor.
+     *
+     * @param string                       $start_year              Year.
+     * @param string                       $end_year                Year.
+     * @param string                       $counting_time_month     Month.
+     * @param string                       $counting_time_day       Day.
+     * @param NodaCountingTimeIndicator    $counting_time_indicator Determines if the time is BCE or CCE.
+     * @param NodaTimeBeforeAfterIndicator $before_after_indicator  Determines if the time is inexact to one direction.
+     * @param false|string                 $start_date              Start date.
+     * @param false|string                 $end_date                End date.
+     *
+     * @return void
+     */
+    public function __construct(string $start_year, string $end_year,
+        string $counting_time_month = "00", string $counting_time_day = "00",
+        NodaCountingTimeIndicator $counting_time_indicator = NodaCountingTimeIndicator::ce,
+        NodaTimeBeforeAfterIndicator $before_after_indicator = NodaTimeBeforeAfterIndicator::none,
+        false|string $start_date = false,
+        false|string $end_date = false,
+    ) {
+
+        if (substr($start_year, 0, 1) === '-') {
+            if (strlen($start_year) > 5) $start_year = '-' . str_pad(trim($start_year, '-'), 4, '-', STR_PAD_LEFT);
+        }
+        if ($start_date !== false && str_starts_with($start_date, '-')) {
+            $parts = explode('-', trim($start_date, '-'));
+            $parts[0] = str_pad($parts[0], 4, '0', STR_PAD_LEFT);
+            $start_date = '-' . implode('-', $parts);
+        }
+        if (substr($end_year, 0, 1) === '-') {
+            if (strlen($end_year) > 5) $end_year = '-' . str_pad(trim($end_year, '-'), 4, '-', STR_PAD_LEFT);
+        }
+        if ($end_date !== false && str_starts_with($end_date, '-')) {
+            $parts = explode('-', trim($end_date, '-'));
+            $parts[0] = str_pad($parts[0], 4, '0', STR_PAD_LEFT);
+            $end_date = '-' . implode('-', $parts);
+        }
+
+        $this->counting_time_indicator = $counting_time_indicator;
+        $this->before_after_indicator = $before_after_indicator;
+
+        $this->_validateStartYear($start_year);
+        $this->start_year = $start_year;
+
+        $this->_validateEndYear($end_year);
+        $this->end_year = $end_year;
+
+        $this->counting_time_month = $this->_validateCountingTimeMonth($counting_time_month);
+        $this->counting_time_day = $this->_validateCountingTimeDay($counting_time_day);
+
+        // Calculate start date and end date
+        if (($this->before_after_indicator === NodaTimeBeforeAfterIndicator::before
+            || $this->before_after_indicator === NodaTimeBeforeAfterIndicator::until)
+            || $start_date === '?'
+        ) {
+            $this->start_date = '-9999-12-31';
+        }
+        if (($this->before_after_indicator === NodaTimeBeforeAfterIndicator::after
+            || $this->before_after_indicator === NodaTimeBeforeAfterIndicator::since)
+            || $end_date === '?'
+        ) {
+            $this->end_date = '9999-12-31';
+        }
+
+        if (!isset($this->start_date) && false !== $start_date) {
+            $this->start_date = date("Y-m-d", MD_STD::strtotime($start_date));
+        }
+        if (!isset($this->end_date) && false !== $end_date) {
+            $this->end_date = date("Y-m-d", MD_STD::strtotime($end_date));
+        }
+
+        if (!isset($this->start_date)) {
+            if ($this->counting_time_month === "00") {
+                $this->start_date = $this->start_year . '-01-01';
+            }
+            else if ($this->counting_time_day === "00") {
+                $this->start_date = $this->start_year . '-' . $this->counting_time_month . '-01';
+            }
+            else {
+                throw new MDgenericInvalidInputsException("Cannot identify start date automatically");
+            }
+        }
+        if (!isset($this->end_date)) {
+            if ($this->counting_time_month === "00") {
+                $this->end_date = $this->end_year . '-12-31';
+            }
+            else if ($this->counting_time_day === "00") {
+                $this->end_date = $this->end_year . '-' . $this->counting_time_month . '-31';
+            }
+            else {
+                throw new MDgenericInvalidInputsException("Cannot identify end date automatically");
+            }
+        }
+
+        // Validate
+        $startDateTime = MD_STD::strtotime("2000-" . substr($this->start_date, -5));
+        if (checkdate((int)date('m', $startDateTime), (int)date('d', $startDateTime), (int)date('Y', $startDateTime)) === false) {
+            throw new MDgenericInvalidInputsException("Invalid start date: " . $this->start_date);
+        }
+
+        if (!empty((int)$this->counting_time_day)) {
+            // The year 2000 is used here as it is a leap year and lots of years accepted in md are not accepted
+            // by checkdate.
+            if (checkdate((int)$this->counting_time_month, (int)$this->counting_time_day, 2000) === false) {
+                throw new MDgenericInvalidInputsException("Invalid date formed by counting time: " . $this->counting_time_month . ' -- ' . $this->counting_time_day);
+            }
+        }
+
+    }
+}

src/NodaTagRelationIdentifier.php

@@ -0,0 +1,64 @@
+<?PHP
+/**
+ * Identifies the type of tag relation to an object based on known suffixes.
+ *
+ * @author Joshua Ramon Enslin <joshua@museum-digital.de>
+ */
+declare(strict_types = 1);
+
+/**
+ * Contains static functions for identifying uncertainty or blocking
+ * completely uncertain inputs for actors, times, and places.
+ */
+final class NodaTagRelationIdentifier {
+
+    private const SUFFIXES = [
+        'de' => [
+            ' (Motiv)' => MDTagRelationType::display_subject,
+            ' [Motiv]' => MDTagRelationType::display_subject,
+            ' <Motiv>' => MDTagRelationType::display_subject,
+
+            ' (Material)' => MDTagRelationType::material,
+            ' [Material]' => MDTagRelationType::material,
+            ' <Material>' => MDTagRelationType::material,
+
+            ' (Technik)' => MDTagRelationType::technique,
+            ' [Technik]' => MDTagRelationType::technique,
+            ' <Technik>' => MDTagRelationType::technique,
+        ]
+    ];
+
+    public readonly string $name;
+    public readonly MDTagRelationType|false $relation;
+
+    /**
+     * Constructor: Removes identifiers for well-known tag relations and determines cleaned name and relation type.
+     *
+     * @param string $lang         Current language.
+     * @param string $input_string Input string to clean.
+     *
+     * @return void
+     */
+    public function __construct(string $lang, string $input_string) {
+
+        if (empty(self::SUFFIXES[$lang])) {
+            $this->name = $input_string;
+            $this->relation = false;
+            return;
+        }
+
+        $relation = false;
+
+        $suffixes = self::SUFFIXES[$lang];
+        foreach (array_keys($suffixes) as $suffix) {
+            if (\mb_substr($input_string, \mb_strlen($suffix) * -1) === "$suffix") {
+                $input_string = \mb_substr($input_string, 0, \mb_strlen($suffix) * -1);
+                $relation = $suffixes[$suffix];
+            }
+        }
+
+        $this->name = $input_string;
+        $this->relation = $relation;
+
+    }
+}

src/NodaTimeAutotranslater.php

@@ -13,7 +13,7 @@ final class NodaTimeAutotranslater {
 
     // TODO: Move these to NodaTimeAutotranslaterLocales
 
-    const LANGS_SYLLABLE_CLEANING = [
+    public const LANGS_SYLLABLE_CLEANING = [
         "hu" => [
             "10-as évek" => "10-es évek",
             "40-as évek" => "40-es évek",
@@ -463,13 +463,13 @@ final class NodaTimeAutotranslater {
     }
 
     /**
-     * Gets translations for a given entry type.
+     * Prepares translations for each available language.
      *
      * @param array<integer|string> $timeInfo Time information.
      *
      * @return array<string>
      */
-    public static function getTranslations(array $timeInfo):array {
+    public static function prepareTranslations(array $timeInfo):array {
 
         if (!empty($timeInfo['zeit_name']) and strlen((string)$timeInfo['zeit_name']) > 10 and !empty($timespanDates = NodaTimeSplitter::attempt_splitting_from_till((string)$timeInfo['zeit_name']))) {
 
@@ -480,12 +480,12 @@ final class NodaTimeAutotranslater {
             }
             $startTimeInfo = [
                 "zeit_name" => $timespanDates['start_name'],
-                "zeit_beginn" => $start[0],
-                "zeit_ende" => $start[1],
+                "zeit_beginn" => $start->start_year,
+                "zeit_ende" => $start->end_year,
                 "zeit_zaehlzeit_jahr" => NodaTimeSplitter::timePartsToCountingYear($start),
-                "zeit_zaehlzeit_monat" => $start[2],
-                "zeit_zaehlzeit_tag" => $start[3],
-                "zeit_zaehlzeit_vorzeichen" => $start[4],
+                "zeit_zaehlzeit_monat" => $start->counting_time_month,
+                "zeit_zaehlzeit_tag" => $start->counting_time_day,
+                "zeit_zaehlzeit_vorzeichen" => $start->counting_time_indicator->toString(),
             ];
 
             if (empty($end = NodaTimeSplitter::attempt_splitting($timespanDates['end_name']))) {
@@ -493,19 +493,22 @@ final class NodaTimeAutotranslater {
             }
             $endTimeInfo = [
                 "zeit_name" => $timespanDates['end_name'],
-                "zeit_beginn" => $end[0],
-                "zeit_ende" => $end[1],
+                "zeit_beginn" => $end->start_year,
+                "zeit_ende" => $end->end_year,
                 "zeit_zaehlzeit_jahr" => NodaTimeSplitter::timePartsToCountingYear($end),
-                "zeit_zaehlzeit_monat" => $end[2],
-                "zeit_zaehlzeit_tag" => $end[3],
-                "zeit_zaehlzeit_vorzeichen" => $end[4],
+                "zeit_zaehlzeit_monat" => $end->counting_time_month,
+                "zeit_zaehlzeit_tag" => $end->counting_time_day,
+                "zeit_zaehlzeit_vorzeichen" => $end->counting_time_indicator->toString(),
             ];
 
             $output = [];
             $cases = NodaTimeAutotranslaterLocales::cases();
             foreach ($cases as $tLang) {
-                $start_term = self::getTranslations($startTimeInfo)[$tLang->name];
-                $end_term = self::getTranslations($endTimeInfo)[$tLang->name];
+                $startTls = self::getTranslations($startTimeInfo);
+                $endTls = self::getTranslations($endTimeInfo);
+                if (empty($startTls) || empty($endTls)) return [];
+                $start_term = $startTls[$tLang->name];
+                $end_term = $endTls[$tLang->name];
 
                 $output[$tLang->name] = \sprintf($tLang->formatYearspanForSprintf(), $start_term, $end_term);
             }
@@ -604,6 +607,78 @@ final class NodaTimeAutotranslater {
 
     }
 
+    /**
+     * Validates correctness of years in translation strings.
+     *
+     * @param string|integer        $start        Start year.
+     * @param string|integer        $end          End year.
+     * @param array<string, string> $translations Translations.
+     *
+     * @return boolean
+     */
+    public static function validateTranslations(string|int $start, string|int $end, array $translations):bool {
+
+        $start = ltrim((string)$start, ' 0-');
+        $end = ltrim((string)$end, ' 0-');
+
+        // Edge cases: Centuries and decades have special translations
+        // and can thus not be validated properly
+        // Century BCE
+        if (substr($start, -1) === "0" && substr($end, -1) === '1' && $start > $end) {
+            return true;
+        }
+        // Century CE
+        if (substr($start, -1) === "1" && substr($end, -1) === '0' && $start < $end) {
+            return true;
+        }
+        // Decade
+        if (substr($start, -1) === "0" && substr($end, -1) === '9' && $start < $end) {
+            return true;
+        }
+
+        // 1920 + ? can be both Since 1920 and After 1919, so validation
+        // is impossible there, too
+        if ($start === '?' || $end === '?') return true;
+
+        // Unset unvalidatable languages
+        unset($translations['ar'], $translations['fa']);
+
+        if ($start !== '?') {
+            foreach ($translations as $t) {
+                if (!str_contains($t, $start)) {
+                    return false;
+                }
+            }
+        }
+        if ($end !== '?' && $start !== $end) {
+            foreach ($translations as $t) {
+                if (!str_contains($t, $end)) {
+                    return false;
+                }
+            }
+        }
+
+        return true;
+
+    }
+
+    /**
+     * Gets translations for a given entry type.
+     *
+     * @param array<integer|string> $timeInfo Time information.
+     *
+     * @return array<string>
+     */
+    public static function getTranslations(array $timeInfo):array {
+
+        $output = self::prepareTranslations($timeInfo);
+
+        if (self::validateTranslations($timeInfo['zeit_beginn'], $timeInfo['zeit_ende'], $output) === false) return [];
+
+        return $output;
+
+    }
+
     /**
      * Runs autotranslater.
      *
@@ -613,7 +688,9 @@ final class NodaTimeAutotranslater {
      */
     public function translate(array $timeInfo):void {
 
-        $translations = self::getTranslations($timeInfo);
+        if (empty($translations = self::getTranslations($timeInfo))) {
+            return;
+        }
 
         $this->_mysqli_noda->autocommit(false);
 

src/NodaTimeBeforeAfterIndicator.php

@@ -0,0 +1,67 @@
+<?PHP
+/**
+ * Represents a time indicator (CE / BCE).
+ *
+ * @author Joshua Ramon Enslin <joshua@museum-digital.de>
+ */
+declare(strict_types = 1);
+
+/**
+ * Represents a time indicator (CE / BCE).
+ */
+enum NodaTimeBeforeAfterIndicator implements JsonSerializable {
+
+    case none;
+    case after;
+    case before;
+    case since;
+    case until;
+
+    /**
+     * Returns a value of this type based on a string.
+     *
+     * @param string $input Input to get a value from.
+     *
+     * @return NodaTimeBeforeAfterIndicator
+     */
+    public static function fromString(string $input):NodaTimeBeforeAfterIndicator {
+
+        return match($input) {
+            '' => self::none,
+            'Nach' => self::after,
+            'Vor' => self::before,
+            'Seit' => self::since,
+            'Bis' => self::until,
+            default => throw new MDpageParameterNotFromListException("Unknown before / after indicator"),
+        };
+
+    }
+
+    /**
+     * Returns a canonical string representation.
+     *
+     * @return string
+     */
+    public function toString():string {
+
+        return match($this) {
+            self::none  => '',
+            self::after => 'Nach',
+            self::before => 'Vor',
+            self::since => 'Seit',
+            self::until => 'Bis',
+        };
+
+    }
+
+    /**
+     * Provides the option to serialize as a string during json_encode().
+     *
+     * @return string
+     */
+    public function jsonSerialize():string {
+
+        return $this->name;
+
+    }
+}

src/NodaUncertaintyHelper.php

@@ -12,7 +12,7 @@ declare(strict_types = 1);
  */
 final class NodaUncertaintyHelper {
 
-    const PERSINST_INDICATORS_DISALLOWED = [
+    public const PERSINST_INDICATORS_DISALLOWED = [
         "Unbekannt",
         "unbekannt",
         "Anonymus",
@@ -41,7 +41,7 @@ final class NodaUncertaintyHelper {
         "Невідомий артист",     // Unknown artist
     ];
 
-    const PERSINST_UNCERTAINTY_PREFIXES = [
+    public const PERSINST_UNCERTAINTY_PREFIXES = [
         "verm. ",
         "Verm. ",
         "vermtl. ",
@@ -57,15 +57,16 @@ final class NodaUncertaintyHelper {
         "?",
     ];
 
-    const PERSINST_UNCERTAINTY_SUFFIXES = [
+    public const PERSINST_UNCERTAINTY_SUFFIXES = [
         "(?)",
         "?",
         " [vermutlich]",
+        " vermutlich",
         " [verm.]",
         " [wahrscheinlich]",
     ];
 
-        const TIME_INDICATORS_DISALLOWED = [
+    public const TIME_INDICATORS_DISALLOWED = [
         "Nachgewiesen",
         "nachgewiesen",
         "o.D.",
@@ -96,10 +97,11 @@ final class NodaUncertaintyHelper {
         "б.д.", // No dating
     ];
 
-    const TIME_UNCERTAINTY_PREFIXES = [
+    public const TIME_UNCERTAINTY_PREFIXES = [
         "c. ",
         "ca ",
         "ca. ",
+        "ca.",
         "Ca ",
         "Ca. ",
         "za. ",
@@ -132,7 +134,7 @@ final class NodaUncertaintyHelper {
         "Прибл.",     // UK: approximately
     ];
 
-    const TIME_UNCERTAINTY_SUFFIXES = [
+    public const TIME_UNCERTAINTY_SUFFIXES = [
         "(?)",
         "?",
         " (ca.)",
@@ -141,8 +143,11 @@ final class NodaUncertaintyHelper {
         " [circa]",
         " (verm.)",
         " (vermutl.)",
+        " vermutlich",
         " körül",
         ", um",
+        ", ca.",
+        ", ca",
         " (um)",
         " (ок.)",
     ];
@@ -150,7 +155,7 @@ final class NodaUncertaintyHelper {
     /**
      * Substrings used to express uncertainty about the validity of a place name.
      */
-        const PLACE_INDICATORS_DISALLOWED = [
+    public const PLACE_INDICATORS_DISALLOWED = [
         "Unbekannt",
         "unbekannt",
         "Unknown",
@@ -175,7 +180,7 @@ final class NodaUncertaintyHelper {
         "невідоме", // No place
     ];
 
-    const PLACE_UNCERTAINTY_PREFIXES = [
+    public const PLACE_UNCERTAINTY_PREFIXES = [
         "ca ",
         "Ca ",
         "ca. ",
@@ -212,7 +217,7 @@ final class NodaUncertaintyHelper {
         "?",
     ];
 
-    const PLACE_UNCERTAINTY_SUFFIXES = [
+    public const PLACE_UNCERTAINTY_SUFFIXES = [
         "(?)",
         "(vermutl.)",
         "[vermutl.]",
@@ -232,8 +237,7 @@ final class NodaUncertaintyHelper {
      */
     public static function trim(string $input):string {
 
-        $input = \trim($input, ", \t\n\r\n;-:");
-        return $input;
+        return \trim($input, ", \t\n\r\n;-:");
 
     }
 
@@ -280,7 +284,7 @@ final class NodaUncertaintyHelper {
      */
     public static function guessTimeCertainty(string $zeit_name):bool {
 
-        $zeit_name = \strtolower($zeit_name);
+        $zeit_name = self::trim(strtolower($zeit_name));
 
         // Attempt to guess uncertainty based on prefixes.
         foreach (self::TIME_UNCERTAINTY_PREFIXES as $prefix) {
@@ -329,6 +333,14 @@ final class NodaUncertaintyHelper {
             }
         }
 
+        // If brackets are included in the name, try removing prefixes and suffixes
+        // from the beginning.
+        if (($bracketPos = strpos($ort_name, "(")) !== false) {
+            $start = substr($ort_name, 0, $bracketPos);
+            $end = substr($ort_name, $bracketPos);
+            $ort_name = self::cleanUncertaintyIndicatorsPlace($start) . ' ' . $end;
+        }
+
         return self::trim($ort_name);
 
     }
@@ -343,7 +355,7 @@ final class NodaUncertaintyHelper {
      */
     public static function guessPlaceCertainty(string $ort_name):bool {
 
-        $ort_name = \strtolower($ort_name);
+        $ort_name = self::trim(\strtolower($ort_name));
 
         // Attempt to guess uncertainty based on prefixes.
         foreach (NodaUncertaintyHelper::PLACE_UNCERTAINTY_PREFIXES as $prefix) {
@@ -359,6 +371,13 @@ final class NodaUncertaintyHelper {
             }
         }
 
+        // If brackets are included in the name, try the same for everything up to the
+        // first brackets.
+        if (($bracketPos = strpos($ort_name, "(")) !== false) {
+            $name = substr($ort_name, 0, $bracketPos);
+            return self::guessPlaceCertainty($name);
+        }
+
         return true; // Certain / no uncertainty found
 
     }
@@ -404,7 +423,7 @@ final class NodaUncertaintyHelper {
      */
     public static function guessPersinstCertainty(string $name):bool {
 
-        $name = \trim(\strtolower($name));
+        $name = self::trim(\strtolower($name));
 
         // Attempt to guess uncertainty based on prefixes.
         foreach (NodaUncertaintyHelper::PERSINST_UNCERTAINTY_PREFIXES as $prefix) {

src/NodaValidationHelper.php

@@ -11,7 +11,59 @@ declare(strict_types = 1);
  */
 final class NodaValidationHelper {
 
-    const ACTOR_DESCRIPTION_REQUIRED_DISTINCT_CHARS = 2;
+    const ACTOR_DESCRIPTION_REQUIRED_DISTINCT_CHARS = 3;
+
+    /**
+     * Validates an actor description for completeness. Of course, only an informed
+     * guess based on the length and character composition of the description can be
+     * made.
+     *
+     * @param string $description Input descrition.
+     * @param string $name        Names of the actor. Optional. Setting this enables
+     *                            checks e.g. to prevent duplicating the actor name
+     *                            as a description.
+     *
+     * @return void
+     */
+    public static function validateTagDescription(string $description, string $name = ""):void {
+
+        // For nodac, empty tag descriptions are to be allowed. Thus, a
+        // dedicated check for fully empty ones with a dedicated exception
+        // is needed.
+        if (empty($description)) {
+            throw new MDInvalidEmptyInputException("No tag name is provided");
+        }
+
+        // Throw error on descriptions that are too short
+        if (\mb_strlen($description) < 10) {
+            throw new MDgenericInvalidInputsException("Tag description is too short");
+        }
+
+        // Validate tag description based on character composition.
+
+        // Ensure more than 3 distinct characters are used.
+        $chars = \str_split($description);
+
+        $uniqueChars = array_unique($chars);
+        if (count($uniqueChars) <= self::ACTOR_DESCRIPTION_REQUIRED_DISTINCT_CHARS) {
+            throw new MDgenericInvalidInputsException("There need to be more than " . self::ACTOR_DESCRIPTION_REQUIRED_DISTINCT_CHARS . " distinct characters.");
+        }
+
+        // Ensure more than the actor name is used.
+        $clearedChars = ['  ' => ' ', ',' => ' ', ';' => ' ', '.' => ' '];
+
+        $uniqueNames = array_unique(array_diff(explode(' ', strtr($name, $clearedChars)), ['']));
+        sort($uniqueNames);
+
+        $descCleared = strtr($description, $clearedChars);
+        $descWords = array_unique(array_diff(explode(' ', $descCleared), ['']));
+        sort($descWords);
+
+        if ($uniqueNames === $descWords) {
+            throw new MDgenericInvalidInputsException("The tag name was simply repeated in the description. This is not enough.");
+        }
+
+    }
 
     /**
      * Validates an actor description for completeness. Of course, only an informed

src/NodaWikidataFetcherDisambiguationIsDisallowedException.php

@@ -0,0 +1,27 @@
+<?PHP
+/**
+ * This file contains an exception class to be thrown if a user attempts to load
+ * data from a Wikidata item specifically established for a disambiguation page.
+ *
+ * @file
+ *
+ * @author Joshua Ramon Enslin <joshua@museum-digital.de>
+ */
+declare(strict_types = 1);
+
+/**
+ * Exception class to be thrown if a user attempts to load
+ * data from a Wikidata item specifically established for a disambiguation page.
+ */
+final class NodaWikidataFetcherDisambiguationIsDisallowedException extends MDgenericInvalidInputsException {
+    /**
+     * Error message.
+     *
+     * @return string
+     */
+    public function errorMessage() {
+        //error message
+        return 'Attempted to load a disambiguation page. Please select the specific item you want to fetch to enrich the given entry: ' . $this->getMessage();
+
+    }
+}

src/Sync/NodaPersinstFulltextSyncManticore.php

@@ -11,7 +11,7 @@ declare(strict_types = 1);
  */
 final class NodaPersinstFulltextSyncManticore {
 
-    const FULL_SYNC_COMMIT_AFTER = 30000;
+    private const FULL_SYNC_COMMIT_AFTER = 30000;
 
     /**
      * Returns all names and descriptions in the different languages of a actor.
@@ -188,6 +188,10 @@ final class NodaPersinstFulltextSyncManticore {
 
         $mysqli_manticore->commit();
 
+        if (PHP_SAPI === 'cli' && $mysqli_noda->ping() === false) {
+            $mysqli_noda->reconnect();
+        }
+
         // Sync translations
 
         $result = $mysqli_noda->do_read_query("SELECT `persinst`.`persinst_id`, `trans_language`,

src/Sync/NodaTagFulltextSyncManticore.php

@@ -11,7 +11,7 @@ declare(strict_types = 1);
  */
 final class NodaTagFulltextSyncManticore {
 
-    const FULL_SYNC_COMMIT_AFTER = 30000;
+    private const FULL_SYNC_COMMIT_AFTER = 30000;
 
     /**
      * Returns all names and descriptions in the different languages of a tag.
@@ -139,6 +139,10 @@ final class NodaTagFulltextSyncManticore {
     /**
      * Synchronizes base entries.
      *
+     * @param MDMysqli $mysqli_noda      Connection to MySQL DB.
+     * @param MDMysqli $mysqli_manticore Connection to Manticore DB.
+     * @param string   $databasename     Name of the main noda database.
+     *
      * @return void
      */
     public static function runFullSyncForBaseEntries(MDMysqli $mysqli_noda, MDMysqli $mysqli_manticore, string $databasename):void {
@@ -189,6 +193,10 @@ final class NodaTagFulltextSyncManticore {
     /**
      * Synchronizes translated entries.
      *
+     * @param MDMysqli $mysqli_noda      Connection to MySQL DB.
+     * @param MDMysqli $mysqli_manticore Connection to Manticore DB.
+     * @param string   $databasename     Name of the main noda database.
+     *
      * @return void
      */
     public static function runFullSyncForTranslatedEntries(MDMysqli $mysqli_noda, MDMysqli $mysqli_manticore, string $databasename):void {

src/enums/NodaTimeAutotranslaterLocales.php

@@ -8,6 +8,7 @@
 
 enum NodaTimeAutotranslaterLocales {
     case ar;
+    case crh;
     case de;
     case en;
     case es;
@@ -40,6 +41,7 @@ enum NodaTimeAutotranslaterLocales {
 
         return match($lang) {
             'ar' => static::ar,
+            'crh' => static::crh,
             'de' => static::de,
             'en' => static::en,
             'es' => static::es,
@@ -73,6 +75,7 @@ enum NodaTimeAutotranslaterLocales {
 
         return match($this) {
             self::ar => 'ar_SY.utf8',
+            self::crh => 'uk_UA.utf8',
             self::de => 'de_DE.utf8',
             self::en => 'en_US.utf8',
             self::es => 'es_ES.utf8',
@@ -108,6 +111,7 @@ enum NodaTimeAutotranslaterLocales {
 
         return match($this) {
             self::ar => 'ar-SY',
+            self::crh => 'uk-UA',
             self::de => 'de-DE',
             self::en => 'en-US',
             self::es => 'es-ES',
@@ -143,6 +147,7 @@ enum NodaTimeAutotranslaterLocales {
 
         return match($this) {
             self::ar => '%s',
+            self::crh => '%s',
             self::de => '%s n. Chr.',
             self::en => '%s CE',
             self::es => '%s d.C.',
@@ -176,6 +181,7 @@ enum NodaTimeAutotranslaterLocales {
 
         return match($this) {
             self::ar => '-%s',
+            self::crh => '%s рік до нашої ери',
             self::de => '%s v. Chr.',
             self::en => '%s BC',
             self::es => '%s a.C.',
@@ -211,6 +217,7 @@ enum NodaTimeAutotranslaterLocales {
 
         return match($this) {
             self::ar => '%s',
+            self::crh => '%s',
             self::de => '%s',
             self::en => '%s',
             self::es => '%s',
@@ -244,6 +251,7 @@ enum NodaTimeAutotranslaterLocales {
 
         return match($this) {
             self::ar => '%s-%s',
+            self::crh => '%s-%s',
             self::de => '%s-%s',
             self::en => '%s-%s',
             self::es => '%s-%s',
@@ -279,6 +287,7 @@ enum NodaTimeAutotranslaterLocales {
 
         return match($this) {
             self::ar => '%s-',
+            self::crh => 'з %s року',
             self::de => 'Seit %s',
             self::en => 'Since %s',
             self::es => 'Desde %s',
@@ -315,6 +324,7 @@ enum NodaTimeAutotranslaterLocales {
 
         return match($this) {
             self::ar => '%s-',
+            self::crh => 'після %s року',
             self::de => 'Nach %s',
             self::en => 'After %s',
             self::es => 'Despues de %s',
@@ -350,6 +360,7 @@ enum NodaTimeAutotranslaterLocales {
 
         return match($this) {
             self::ar => '-%s',
+            self::crh => 'до %s року',
             self::de => 'Bis %s',
             self::en => 'Until %s',
             self::es => 'Hasta %s',
@@ -384,6 +395,7 @@ enum NodaTimeAutotranslaterLocales {
 
         return match($this) {
             self::ar => 'القرن ال %s',
+            self::crh => '%s століття',
             self::de => '%s. Jahrhundert',
             self::en => '%s. century',
             self::es => 'Siglo %s',
@@ -418,6 +430,7 @@ enum NodaTimeAutotranslaterLocales {
 
         return match($this) {
             self::ar => 'القرن ال %s-%s',
+            self::crh => '%s-%s століття',
             self::de => '%s.-%s. Jahrhundert',
             self::en => '%s.-%s. century',
             self::es => 'Siglo %s-%s',
@@ -452,6 +465,7 @@ enum NodaTimeAutotranslaterLocales {
 
         return match($this) {
             self::ar => '%s-%s',
+            self::crh => '%s-ті роки',
             self::de => '%ser Jahre',
             self::en => '%ss',
             self::es => '%s-%s',
@@ -486,6 +500,7 @@ enum NodaTimeAutotranslaterLocales {
 
         return match($this) {
             self::ar => '%s-%s',
+            self::crh => '%s-%s-ті роки',
             self::de => '%s-%ser Jahre',
             self::en => '%s-%ss',
             self::es => '%s-%s',
@@ -521,6 +536,7 @@ enum NodaTimeAutotranslaterLocales {
 
         return match($this) {
             self::ar => '-%s',
+            self::crh => 'до %s року',
             self::de => 'Vor %s',
             self::en => 'Before %s',
             self::es => 'Antes de %s',
@@ -558,6 +574,7 @@ enum NodaTimeAutotranslaterLocales {
             # self::be => '%d.%B.%Y',
             # self::bg => '%Y-%B-%d',
             # self::ca => '%d/%m/%Y',
+            self::crh => '%d.%m.%Y',
             # self::cs => '%d.%B.%Y',
             # self::da => '%d-%m-%Y',
             self::de => '%d.%m.%Y',
@@ -618,6 +635,7 @@ enum NodaTimeAutotranslaterLocales {
             # self::be => '%d.%B.%Y',
             # self::bg => '%Y-%B-%d',
             # self::ca => '%d/%m/%Y',
+            self::crh => 'dd.MM.Y',
             # self::cs => '%d.%B.%Y',
             # self::da => '%d-%m-%Y',
             self::de => 'dd.MM.Y',
@@ -679,6 +697,7 @@ enum NodaTimeAutotranslaterLocales {
             # self::bg => '%Y-%B',
             # self::ca => '%m/%Y',
             # self::cs => '%B.%Y',
+            self::crh => '%m %Y',
             # self::da => '%m-%Y',
             self::de => '%B %Y',
             # self::el => '%B %Y',
@@ -735,6 +754,7 @@ enum NodaTimeAutotranslaterLocales {
             # self::bg => 'Y-MMMM',
             # self::ca => 'MM/Y',
             # self::cs => 'MMMM.Y',
+            self::crh => 'MMMM Y',
             # self::da => 'MM-Y',
             self::de => 'MMMM Y',
             # self::el => 'MMMM Y',

tests/NodaConsolidatedNamesForPlacesTest.php

@@ -5,13 +5,16 @@
  * @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\Small;
 
 /**
  * Tests for setting uniform place names.
- *
- * @covers \NodaConsolidatedNamesForPlaces
  */
+#[small]
+#[CoversClass(\NodaConsolidatedNamesForPlaces::class)]
 final class NodaConsolidatedNamesForPlacesTest extends TestCase {
     /**
      * Test that cleanup function returns expected values.
@@ -56,7 +59,6 @@ final class NodaConsolidatedNamesForPlacesTest extends TestCase {
         self::assertEquals("Deák Ferenc utca 16-18. (Budapest, 5. kerület)", NodaConsolidatedNamesForPlaces::consolidate_name("hu", "Deák Ferenc utca 16-18. Budapest, V."));
         self::assertEquals("Deák Ferenc utca 16-18. Budapest, V. abc", NodaConsolidatedNamesForPlaces::consolidate_name("hu", "Deák Ferenc utca 16-18. Budapest, V. abc"));
 
-
         // Rewriting country names in brackets
         self::assertEquals("Köln (Deutschland)", NodaConsolidatedNamesForPlaces::consolidate_name("de", "Deutschland-Köln"));
         self::assertEquals("Köln (Deutschland)", NodaConsolidatedNamesForPlaces::consolidate_name("de", "Deutschland, Köln"));

tests/NodaIDGetterTest.php

@@ -0,0 +1,615 @@
+<?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_noda_mysqli_connect();
+        $persinstByNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `persinst_name`, `persinst_id`
+            FROM `persinst`
+            WHERE INSTR(`persinst_name`, 'i')");
+        $persinstByDisplayNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `persinst_anzeigename`, `persinst_id`
+            FROM `persinst`
+            WHERE INSTR(`persinst_anzeigename`, 'i')
+                AND `persinst_sterbejahr` != ''");
+        $persinstByDisplayNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `trans_name`, `persinst_id`
+            FROM `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,
+        ];
+
+    }
+
+    /**
+     * Returns a test actor name and life dates.
+     *
+     * @return array<array{0: string, 1: integer, 2: string, 3: string}>
+     */
+    public static function persinstByNameAndLifeDatesProvider():array {
+
+        $mysqli = md_noda_mysqli_connect();
+        $result = $mysqli->do_read_query("SELECT `persinst_name_en`, `persinst_name`, `persinst_id`, `persinst_geburtsjahr`, `persinst_sterbejahr`
+            FROM `persinst`
+            WHERE INSTR(`persinst_name_en`, 'i')
+                AND `persinst_geburtsjahr` != ''
+                AND `persinst_sterbejahr` != ''
+            LIMIT 1");
+        if (!$cur = $result->fetch_row()) {
+            throw new Exception("Error");
+        }
+        $result->close();
+        $mysqli->close();
+
+        return [
+            'Persinst ID by name: ' . implode(' - ', $cur) => [
+                (string)$cur[0], (int)$cur[2], (string)$cur[3], (string)$cur[4],
+                (string)$cur[1], (int)$cur[2], (string)$cur[3], (string)$cur[4],
+            ]
+        ];
+
+    }
+
+    /**
+     * 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);
+
+    }
+
+    /**
+     * Test getting persinst by name and life dates works.
+     *
+     * @param string  $name        Name of the entry.
+     * @param integer $expected_id Expected target ID.
+     * @param string  $birth_year  Birth year.
+     * @param string  $death_year  Death year.
+     *
+     * @return void
+     */
+    #[DataProvider('persinstByNameAndLifeDatesProvider')]
+    public function testGetPersinstIdByNameAndLifeDatesWorks(string $name, int $expected_id, string $birth_year, string $death_year):void {
+
+        self::assertEquals($expected_id,
+            NodaIDGetter::getPersinstIDByNamePlusYears($this->_mysqli, "de", $name, $birth_year, $death_year),
+            "Entry " . $name . " is not matched in exact lookup. Expected ID: " . $expected_id);
+
+    }
+
+    // PersinstIDByRewrite
+
+    /**
+     * Returns a test actor name.
+     *
+     * @return array<array{0: string, 1: integer}>
+     */
+    public static function persinstByRewriteProvider():array {
+
+        $mysqli = md_noda_mysqli_connect();
+        $persinstByRewriteSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `input_name`, `persinst_id`
+            FROM `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_noda_mysqli_connect();
+        $placeByNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `ort_name`, `ort_id`
+            FROM `orte`
+            WHERE INSTR(`ort_name`, 'i')");
+        $placeByDisplayNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `trans_name`, `ort_id`
+            FROM `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);
+        $this->runRegularComparisonTests("getPlaceIDByNamesAndRewrites", $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_noda_mysqli_connect();
+        $placeByRewriteSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `input_name`, `ort_id`
+            FROM `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);
+        $this->runRegularComparisonTests("getPlaceIDByNamesAndRewrites", $name, $expected_id);
+
+    }
+
+    // TagIDByName
+
+    /**
+     * Returns a test tag name.
+     *
+     * @return array<array{0: string, 1: integer}>
+     */
+    public static function tagByNameProvider():array {
+
+        $mysqli = md_noda_mysqli_connect();
+        $tagByNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `tag_name`, `tag_id`
+            FROM `tag`
+            WHERE INSTR(`tag_name`, 'i')");
+        $tagByDisplayNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `trans_name`, `tag_id`
+            FROM `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);
+        $this->runRegularComparisonTests("getTagIDByNamesAndRewrites", $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_noda_mysqli_connect();
+        $tagByRewriteSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `input_name`, `tag_id`
+            FROM `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_noda_mysqli_connect();
+        $timeByNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `zeit_name`, `zeit_id`
+            FROM `zeiten`
+            WHERE INSTR(`zeit_name`, 'i')");
+        $timeByDisplayNameSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `trans_name`, `zeit_id`
+            FROM `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);
+        $this->runRegularComparisonTests("getTimeIDByNamesAndRewrites", $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_noda_mysqli_connect();
+        $timeByRewriteSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `input_name`, `zeit_id`
+            FROM `zeit_rewriting`
+            WHERE INSTR(`input_name`, 'i')
+                AND `language` = 'de'");
+        $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);
+        $this->runRegularComparisonTests("getTimeIDByNamesAndRewrites", $name, $expected_id);
+
+    }
+
+    // Entity getters by norm data references
+
+    /**
+     * Data provider for norm data reference for actors.
+     *
+     * @return array<array{0: MDNodaLink, 1: integer}>
+     */
+    public static function nodaRefForActorsProvider():array {
+
+        $mysqli = md_noda_mysqli_connect();
+        $nodaSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `noda_link`, `persinst_id`
+            FROM `noda`
+            WHERE `noda_source` = 'Wikidata'
+                AND `noda_link` != ''");
+        $mysqli->close();
+
+        return [
+            'Valid actor ID by norm data reference: ' . $nodaSimple[0] => [
+                new MDNodaLink(MDNodaRepository::wikidata, $nodaSimple[0]),
+                $nodaSimple[1],
+            ],
+            'Invalid, non-existing Wikidata ID' => [
+                new MDNodaLink(MDNodaRepository::wikidata, 'Q11111111111111'),
+                0,
+            ],
+        ];
+
+    }
+
+    /**
+     * Test getting actor ID by norm data reference.
+     *
+     * @param MDNodaLink $link        Noda link.
+     * @param integer    $expected_id Expected target ID.
+     *
+     * @return void
+     */
+    #[DataProvider('nodaRefForActorsProvider')]
+    public function testGetPersinstByNodaLinkWorks(MDNodaLink $link, int $expected_id):void {
+
+        self::assertEquals($expected_id, NodaIDGetter::getPersinstIDByNodaLink($this->_mysqli, $link));
+
+    }
+
+    /**
+     * Data provider for norm data reference for places.
+     *
+     * @return array<array{0: MDNodaLink, 1: integer}>
+     */
+    public static function nodaRefForPlacesProvider():array {
+
+        $mysqli = md_noda_mysqli_connect();
+        $nodaSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `noda_link`, `ort_id`
+            FROM `noda_orte`
+            WHERE `noda_source` = 'Wikidata'
+                AND `noda_link` != ''");
+        $mysqli->close();
+
+        return [
+            'Valid place ID by norm data reference: ' . $nodaSimple[0] => [
+                new MDNodaLink(MDNodaRepository::wikidata, $nodaSimple[0]),
+                $nodaSimple[1],
+            ],
+            'Invalid, non-existing Wikidata ID' => [
+                new MDNodaLink(MDNodaRepository::wikidata, 'Q11111111111111'),
+                0,
+            ],
+        ];
+
+    }
+
+    /**
+     * Test getting place ID by norm data reference.
+     *
+     * @param MDNodaLink $link        Noda link.
+     * @param integer    $expected_id Expected target ID.
+     *
+     * @return void
+     */
+    #[DataProvider('nodaRefForPlacesProvider')]
+    public function testGetPlaceByNodaLinkWorks(MDNodaLink $link, int $expected_id):void {
+
+        self::assertEquals($expected_id, NodaIDGetter::getPlaceIDByNodaLink($this->_mysqli, $link));
+
+    }
+
+    /**
+     * Data provider for norm data reference for tags.
+     *
+     * @return array<array{0: MDNodaLink, 1: integer}>
+     */
+    public static function nodaRefForTagsProvider():array {
+
+        $mysqli = md_noda_mysqli_connect();
+        $nodaSimple = self::_getNameAndIdFromDbQuery($mysqli, "SELECT `noda_link`, `tag_id`
+            FROM `noda_tag`
+            WHERE `noda_source` = 'Wikidata'
+                AND `noda_link` != ''");
+        $mysqli->close();
+
+        return [
+            'Valid tag ID by norm data reference: ' . $nodaSimple[0] => [
+                new MDNodaLink(MDNodaRepository::wikidata, $nodaSimple[0]),
+                $nodaSimple[1],
+            ],
+            'Invalid, non-existing Wikidata ID' => [
+                new MDNodaLink(MDNodaRepository::wikidata, 'Q11111111111111'),
+                0,
+            ],
+        ];
+
+    }
+
+    /**
+     * Test getting tag ID by norm data reference.
+     *
+     * @param MDNodaLink $link        Noda link.
+     * @param integer    $expected_id Expected target ID.
+     *
+     * @return void
+     */
+    #[DataProvider('nodaRefForTagsProvider')]
+    public function testGetTagByNodaLinkWorks(MDNodaLink $link, int $expected_id):void {
+
+        self::assertEquals($expected_id, NodaIDGetter::getTagIDByNodaLink($this->_mysqli, $link));
+
+    }
+}

tests/NodaNameSplitterTest.php

@@ -6,12 +6,14 @@
  */
 declare(strict_types = 1);
 use PHPUnit\Framework\TestCase;
+use PHPUnit\Framework\Attributes\CoversClass;
+use PHPUnit\Framework\Attributes\Small;
 
 /**
  * This script contains tests for the actor name splitter.
- *
- * @covers \NodaNameSplitter
  */
+#[Small]
+#[CoversClass(\NodaIDGetter::class)]
 final class NodaNameSplitterTest extends TestCase {
     /**
      * Test to check whether the HTML page is correctly generated.

tests/NodaTagRelationIdentifierTest.php

@@ -0,0 +1,50 @@
+<?PHP
+/**
+ * Tests for the identification of tag relation types to objects based on input tag 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\Small;
+use PHPUnit\Framework\Attributes\DataProvider;
+
+/**
+ * This script contains tests for the uncertainty helper.
+ */
+#[small]
+#[CoversClass(\NodaTagRelationIdentifier::class)]
+final class NodaTagRelationIdentifierTest extends TestCase {
+    /**
+     * Returns input tag names with and without known suffixes signaling the relation type.
+     *
+     * @return array<array{0: string, 1: string, 2: false|MDTagRelationType}>
+     */
+    public static function tagNameAndRelationTypeProvider():array {
+
+        return [
+            'Delfin' => ["Delfin", "Delfin", false],
+            'Delfin (Motiv)' => ["Delfin (Motiv)", "Delfin", MDTagRelationType::display_subject],
+        ];
+
+    }
+
+    /**
+     * Test to ensure times are correctly cleaned and parsed.
+     *
+     * @param string                  $term          Term to check.
+     * @param string                  $target_output Expected output name.
+     * @param false|MDTagRelationType $target_type   Expected identified relation type (or false for lack thereof).
+     *
+     * @return void
+     */
+    #[DataProvider('tagNameAndRelationTypeProvider')]
+    public function testIdentificationWorksCorrectly(string $term, string $target_output, false|MDTagRelationType $target_type):void {
+
+        $identification = new NodaTagRelationIdentifier("de", $term);
+        self::assertEquals($target_output, $identification->name);
+        self::assertEquals($target_type, $identification->relation);
+
+    }
+}

tests/NodaTimeAutotranslaterTest.php

@@ -6,12 +6,14 @@
  */
 declare(strict_types = 1);
 use PHPUnit\Framework\TestCase;
+use PHPUnit\Framework\Attributes\CoversClass;
+use PHPUnit\Framework\Attributes\Medium;
 
 /**
  * This script contains tests for the automatic translation class for time names.
- *
- * @covers \NodaTimeAutotranslater
  */
+#[Medium]
+#[CoversClass(\NodaIDGetter::class)]
 final class NodaTimeAutotranslaterTest extends TestCase {
     /**
      * Test to check whether the HTML page is correctly generated.
@@ -32,7 +34,7 @@ final class NodaTimeAutotranslaterTest extends TestCase {
             "zeit_zaehlzeit_tag"   => "01",
         ];
         $output = NodaTimeAutotranslater::getTranslations($timeInfo);
-        self::assertEquals($output["de"], "01.05.1920");
+        self::assertEquals("01.05.1920", $output["de"]);
 
     }
 
@@ -671,4 +673,23 @@ final class NodaTimeAutotranslaterTest extends TestCase {
         self::assertEquals($output["de"], "Vor 01.12.1919");
 
     }
+
+    /**
+     * Test to check whether validating works.
+     *
+     * @author Joshua Ramon Enslin <joshua@museum-digital.de>
+     * @group  ValidOutput
+     * @small
+     *
+     * @return void
+     */
+    public function testValidation():void {
+
+        $output = [
+            'de' => '1.12.1920',
+        ];
+
+        self::assertFalse(NodaTimeAutotranslater::validateTranslations("1919", "1919", $output));
+
+    }
 }

tests/NodaUncertaintyHelperTest.php

@@ -6,110 +6,124 @@
  */
 declare(strict_types = 1);
 use PHPUnit\Framework\TestCase;
+use PHPUnit\Framework\Attributes\CoversClass;
+use PHPUnit\Framework\Attributes\Small;
+use PHPUnit\Framework\Attributes\DataProvider;
 
 /**
  * This script contains tests for the uncertainty helper.
- *
- * @covers \NodaUncertaintyHelper
  */
+#[small]
+#[CoversClass(\NodaUncertaintyHelper::class)]
 final class NodaUncertaintyHelperTest extends TestCase {
     /**
-     * Removes uncertainty indicators from an time name.
+     * Returns time names with expected cleaned version and expected parsed certainty.
      *
-     * @group ValidOutput
-     * @small
-     *
-     * @return void
+     * @return array<array{0: string, 1: string, 2: boolean}>
      */
-    public function testCleanUncertaintyIndicatorsTime():void {
+    public static function uncertainTimesProvider():array {
 
-        self::assertEquals("1950", NodaUncertaintyHelper::cleanUncertaintyIndicatorsTime("wohl 1950"));
-        self::assertEquals("1950", NodaUncertaintyHelper::cleanUncertaintyIndicatorsTime("1950"));
+        return [
+            'uncertainty prefix: "wohl 1950"' => ["wohl 1950", "1950", false],
+            'uncertainty suffix: "1950?"' => ["1950?", "1950", false],
+            'uncertainty suffix and superfluous chars: "1950 ?,"' => ["1950 ?,", "1950", false],
+            'certain term with superfluous chars: "1950 ,"' => ["1950 ,", "1950", true],
+            'certain term: 1950' => ["1950", "1950", true],
+        ];
 
     }
 
     /**
-     * Attempts guessing whether time is uncertain.
+     * Returns place names with expected cleaned version and expected parsed certainty.
      *
-     * @group ValidOutput
-     * @small
-     *
-     * @return void
+     * @return array<array{0: string, 1: string, 2: boolean}>
      */
-    public function testGuessTimeCertainty():void {
+    public static function uncertainPlacesProvider():array {
 
-        self::assertFalse(NodaUncertaintyHelper::guessTimeCertainty("wohl 1950"));
-        self::assertTrue(NodaUncertaintyHelper::guessTimeCertainty("1950"));
+        return [
+
+            'uncertainty prefix: "wohl Berlin"' => ["wohl Berlin", "Berlin", false],
+            'uncertainty prefix: "vermutl. Berlin"' => ["vermutl. Berlin", "Berlin", false],
+            'uncertainty prefix and superfluous chars: "?-Berlin"' => ["?-Berlin", "Berlin", false],
+            'uncertainty suffix: "Berlin?"' => ["Berlin?", "Berlin", false],
+            'uncertainty suffix: "Berlin (?)"' => ["Berlin (?)", "Berlin", false],
+            'uncertainty suffix and superfluous chars: "Berlin ?,"' => ["Berlin ?,", "Berlin", false],
+            'certain term with superfluous chars: "Berlin ,"' => ["Berlin ,", "Berlin", true],
+            'certain term: Berlin' => ["Berlin", "Berlin", true],
+            'Berlin ? (Deutschland)' => ["Berlin ? (Deutschland)", "Berlin (Deutschland)", false],
+            'Berli?n (Deutschland)' => ["Berl?n (Deutschland)", "Berl?n (Deutschland)", true],
+
+        ];
 
     }
 
     /**
-     * Removes uncertainty indicators from an place name.
+     * Returns actor names with expected cleaned version and expected parsed certainty.
      *
-     * @group ValidOutput
-     * @small
-     *
-     * @return void
+     * @return array<array{0: string, 1: string, 2: boolean}>
      */
-    public static function testCleanUncertaintyIndicatorsPlace():void {
+    public static function uncertainPersinstProvider():array {
 
-        self::assertEquals("Berlin", NodaUncertaintyHelper::cleanUncertaintyIndicatorsPlace("wohl Berlin"));
-        self::assertEquals("Berlin", NodaUncertaintyHelper::cleanUncertaintyIndicatorsPlace("Berlin"));
-
-        // Real-life examples that previously passed unencumbered
-        self::assertEquals("Augsburg", NodaUncertaintyHelper::cleanUncertaintyIndicatorsPlace("vermutlich: Augsburg"));
-        self::assertEquals("Augsburg", NodaUncertaintyHelper::cleanUncertaintyIndicatorsPlace("vermutl. Augsburg"));
+        return [
+            'uncertainty prefix: "wohl Barbarossa"' => ["wohl Barbarossa", "Barbarossa", false],
+            'uncertainty prefix: "vermutl. Barbarossa"' => ["vermutl. Barbarossa", "Barbarossa", false],
+            'uncertainty prefix and superfluous chars: "?-Barbarossa"' => ["?-Barbarossa", "Barbarossa", false],
+            'uncertainty suffix: "Barbarossa?"' => ["Barbarossa?", "Barbarossa", false],
+            'uncertainty suffix and superfluous chars: "Barbarossa ?,"' => ["Barbarossa ?,", "Barbarossa", false],
+            'certain term with superfluous chars: "Barbarossa ,"' => ["Barbarossa ,", "Barbarossa", true],
+            'certain term: Barbarossa' => ["Barbarossa", "Barbarossa", true],
+        ];
 
     }
 
     /**
-     * Attempts guessing whether place is uncertain.
+     * Test to ensure times are correctly cleaned and parsed.
      *
-     * @group ValidOutput
-     * @small
+     * @param string  $term             Term to check.
+     * @param string  $target_output    Expected output name.
+     * @param boolean $target_certainty Expected output certainty.
      *
      * @return void
      */
-    public static function testGuessPlaceCertainty():void {
+    #[DataProvider('uncertainTimesProvider')]
+    public function testParsingUncertaintyFromTimes(string $term, string $target_output, bool $target_certainty):void {
 
-        self::assertFalse(NodaUncertaintyHelper::guessPlaceCertainty("vermutlich: Augsburg"));
-        self::assertFalse(NodaUncertaintyHelper::guessPlaceCertainty("vermutl. Augsburg"));
-
-        self::assertFalse(NodaUncertaintyHelper::guessPlaceCertainty("wohl Berlin"));
-        self::assertTrue(NodaUncertaintyHelper::guessPlaceCertainty("Berlin"));
-
-        self::assertFalse(NodaUncertaintyHelper::guessPlaceCertainty("?-Italien"));
+        self::assertEquals($target_output, NodaUncertaintyHelper::cleanUncertaintyIndicatorsTime($term));
+        self::assertEquals($target_certainty, NodaUncertaintyHelper::guessTimeCertainty($term));
 
     }
 
     /**
-     * Removes uncertainty indicators from an actor name.
+     * Test to ensure places are correctly cleaned and parsed.
      *
-     * @group ValidOutput
-     * @small
+     * @param string  $term             Term to check.
+     * @param string  $target_output    Expected output name.
+     * @param boolean $target_certainty Expected output certainty.
      *
      * @return void
      */
-    public static function testCleanUncertaintyIndicatorsPersinst():void {
+    #[DataProvider('uncertainPlacesProvider')]
+    public function testParsingUncertaintyFromPlaces(string $term, string $target_output, bool $target_certainty):void {
 
-        self::assertEquals("Barbarossa", NodaUncertaintyHelper::cleanUncertaintyIndicatorsPersinst("wohl Barbarossa"));
-        self::assertEquals("Barbarossa", NodaUncertaintyHelper::cleanUncertaintyIndicatorsPersinst("Barbarossa"));
-        self::assertEquals("Barbarossa", NodaUncertaintyHelper::cleanUncertaintyIndicatorsPersinst("?-Barbarossa"));
+        self::assertEquals($target_output, NodaUncertaintyHelper::cleanUncertaintyIndicatorsPlace($term));
+        self::assertEquals($target_certainty, NodaUncertaintyHelper::guessPlaceCertainty($term));
 
     }
 
     /**
-     * Attempts guessing whether persinst is uncertain.
+     * Test to ensure actor names are correctly cleaned and parsed.
      *
-     * @group ValidOutput
-     * @small
+     * @param string  $term             Term to check.
+     * @param string  $target_output    Expected output name.
+     * @param boolean $target_certainty Expected output certainty.
      *
      * @return void
      */
-    public static function testGuessPersinstCertainty():void {
+    #[DataProvider('uncertainPersinstProvider')]
+    public function testParsingUncertaintyFromPersinst(string $term, string $target_output, bool $target_certainty):void {
 
-        self::assertFalse(NodaUncertaintyHelper::guessPlaceCertainty("wohl Barbarossa"));
-        self::assertTrue(NodaUncertaintyHelper::guessPlaceCertainty("Barbarossa"));
+        self::assertEquals($target_output, NodaUncertaintyHelper::cleanUncertaintyIndicatorsPersinst($term));
+        self::assertEquals($target_certainty, NodaUncertaintyHelper::guessPersinstCertainty($term));
 
     }
 }

tests/NodaValidationHelperTest.php

@@ -5,19 +5,20 @@
  * @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\Small;
 
 /**
  * This script contains tests for the validation of single field contents.
- *
- * @covers \NodaValidationHelper
  */
+#[small]
+#[CoversClass(\NodaValidationHelper::class)]
 final class NodaValidationHelperTest extends TestCase {
     /**
      * Test that a specific error is thrown if no description for actors is provided.
      *
-     * @small
-     *
      * @return void
      */
     public function testActorDescriptionValidationFailsOnEmptyInput():void {
@@ -30,8 +31,6 @@ final class NodaValidationHelperTest extends TestCase {
     /**
      * Test successfully refusing too short actor descriptions.
      *
-     * @small
-     *
      * @return void
      */
     public function testActorDescriptionValidationFailsOnTooShortInput():void {
@@ -44,8 +43,6 @@ final class NodaValidationHelperTest extends TestCase {
     /**
      * Test successfully refusing actor descriptions that have too few distinct characters.
      *
-     * @small
-     *
      * @return void
      */
     public function testActorDescriptionValidationFailsOnTooFewDistinctCharacters():void {
@@ -58,8 +55,6 @@ final class NodaValidationHelperTest extends TestCase {
     /**
      * Test successfully refusing actor descriptions that simply duplicate the actor name.
      *
-     * @small
-     *
      * @return void
      */
     public function testActorDescriptionValidationFailsOnDuplicatedActorNames():void {
@@ -80,8 +75,6 @@ final class NodaValidationHelperTest extends TestCase {
     /**
      * Test that a valid description is accepted.
      *
-     * @small
-     *
      * @return void
      */
     public function testActorDescriptionValidationAcceptsValidDescription():void {
@@ -90,4 +83,68 @@ final class NodaValidationHelperTest extends TestCase {
         self::assertTrue(true);
 
     }
+
+    /**
+     * Test that a specific error is thrown if no description for tags is provided.
+     *
+     * @return void
+     */
+    public function testTagDescriptionValidationFailsOnEmptyInput():void {
+
+        $this->expectException(MDInvalidEmptyInputException::class);
+        NodaValidationHelper::validateTagDescription("");
+
+    }
+
+    /**
+     * Test successfully refusing too short tag descriptions.
+     *
+     * @return void
+     */
+    public function testTagDescriptionValidationFailsOnTooShortInput():void {
+
+        $this->expectException(MDgenericInvalidInputsException::class);
+        NodaValidationHelper::validateTagDescription("abc");
+
+    }
+
+    /**
+     * Test successfully refusing tag descriptions that have too few distinct characters.
+     *
+     * @return void
+     */
+    public function testTagDescriptionValidationFailsOnTooFewDistinctCharacters():void {
+
+        $this->expectException(MDgenericInvalidInputsException::class);
+        NodaValidationHelper::validateTagDescription("aaaaaaaaaaaa");
+
+    }
+
+    /**
+     * Test successfully refusing tag descriptions that simply duplicate the tag name.
+     *
+     * @return void
+     */
+    public function testTagDescriptionValidationFailsOnDuplicatedTagNames():void {
+
+        $this->expectException(MDgenericInvalidInputsException::class);
+        NodaValidationHelper::validateTagDescription("Richard Lepsius", "Richard Lepsius");
+        $this->expectException(MDgenericInvalidInputsException::class);
+        NodaValidationHelper::validateTagDescription("Richard Lepsius", "Lepsius Richard");
+        $this->expectException(MDgenericInvalidInputsException::class);
+        NodaValidationHelper::validateTagDescription("Lepsius, Richard", "Lepsius, Richard");
+
+    }
+
+    /**
+     * Test that a valid description is accepted.
+     *
+     * @return void
+     */
+    public function testTagDescriptionValidationAcceptsValidDescription():void {
+
+        NodaValidationHelper::validateTagDescription("Richard Lepsius war ein Forscher", "Richard Lepsius");
+        self::assertTrue(true);
+
+    }
 }

tests/NodaWikidataFetcherTest.php

@@ -6,19 +6,28 @@
  */
 declare(strict_types = 1);
 use PHPUnit\Framework\TestCase;
+use PHPUnit\Framework\Attributes\CoversClass;
+use PHPUnit\Framework\Attributes\Medium;
+use PHPUnit\Framework\Attributes\DataProvider;
+
+require_once __DIR__ . '/../../MDMysqli/test_connections.conf.php';
+require_once __DIR__ . '/../src/NodaWikidataFetcherDisambiguationIsDisallowedException.php';
 
 /**
  * This script contains tests for the Wikidata fetcher.
- *
- * @covers \NodaWikidataFetcher
  */
+#[medium]
+#[CoversClass(\NodaWikidataFetcher::class)]
 final class NodaWikidataFetcherTest extends TestCase {
+
+    // Test for getting translations: Telugu
+    public const TEST_LANG = 'te';
+
     /**
      * Test to check whether the HTML page is correctly generated.
      *
      * @author Joshua Ramon Enslin <joshua@museum-digital.de>
      * @group  ValidOutput
-     * @small
      *
      * @return void
      */
@@ -29,12 +38,39 @@ final class NodaWikidataFetcherTest extends TestCase {
 
     }
 
+    /**
+     * Data provider providing a Wikidata ID for a dedicated wikidata item for disambiguation pages.
+     *
+     * @return array<string, array{0: string}>
+     */
+    public static function disambiguationPageProvider():array {
+
+        return [
+            'Disambiguation page for "Mochi" - Q6916210' => ['Q6916210'],
+        ];
+
+    }
+
+    /**
+     * Throw error when attempting to load a dedicated wikidata entry for a disambiguation page.
+     *
+     * @param string $wikidata_id Wikidata ID.
+     *
+     * @return void
+     */
+    #[DataProvider('disambiguationPageProvider')]
+    public function testWikidataIdFromLinkFailsForDisambiguationPages(string $wikidata_id):void {
+
+        self::expectException(NodaWikidataFetcherDisambiguationIsDisallowedException::class);
+        NodaWikidataFetcher::getWikidataEntity($wikidata_id);
+
+    }
+
     /**
      * Test to check whether the HTML page is correctly generated.
      *
      * @author Joshua Ramon Enslin <joshua@museum-digital.de>
      * @group  ValidOutput
-     * @small
      *
      * @return void
      */
@@ -47,9 +83,7 @@ final class NodaWikidataFetcherTest extends TestCase {
     /**
      * Test to check whether the HTML page is correctly generated.
      *
-     * @author Joshua Ramon Enslin <joshua@museum-digital.de>
      * @group  ValidOutput
-     * @small
      *
      * @return void
      */
@@ -60,225 +94,208 @@ final class NodaWikidataFetcherTest extends TestCase {
     }
 
     /**
-     * Test for cleaning wikidata info.
+     * Data provider for an actor that has a wikidata link and a Telugu translation.
      *
-     * @author Joshua Ramon Enslin <joshua@museum-digital.de>
-     * @group  ValidOutput
-     * @small
-     *
-     * @return void
+     * @return array<string, array{0: int, 1: string}>
      */
-    public function testCleanWikidataInput():void {
+    public static function actorWithTlAndWikidataLinkProvider():array {
 
-        $testStr = '"<div class="mw-parser-output"><table class="infobox float-right toccolours toptextcells" style="margin: 0 0 1em 1em; width: 300px;" id="Vorlage_Infobox_Ort_in_der_Ukraine" summary="Infobox Ort in der Ukraine">
+        $mysqli = md_main_mysqli_connect();
 
-<tbody><tr>
-<td colspan="2" style="background-color:#AFD6FF; font-size:1.3em; font-weight:bold; text-align:center;">Werbowez (Kossiw)
-</td></tr>
-<tr>
-<td colspan="2" style="background-color:#FFC; font-size:1em; font-weight:bold; text-align:center;"><span lang="uk-Cyrl" class="Cyrl">Вербовець</span>
-</td></tr>
+        $result = $mysqli->do_read_query("SELECT `persinst_id`, `noda_nrinsource`
+            FROM `" . DATABASENAME_NODA . "`.`noda`
+            WHERE `noda_source` = 'Wikidata'
+                AND EXISTS (SELECT 1 FROM `" . DATABASENAME_NODA . "`.`persinst_translation`
+                    WHERE `persinst_translation`.`persinst_id` = `noda`.`persinst_id`
+                        AND `trans_language` = '" . $mysqli->escape_string(self::TEST_LANG) . "')");
 
+        if (!$cur = $result->fetch_row()) {
+            throw new Exception("Failed to identify an entry that has a wikidata entry and a translation for language " . self::TEST_LANG);
+        }
+        $result->close();
+        $mysqli->close();
 
-<tr style="height:120px; background-color:#FFF;">
-<td style="width: 130px; text-align:center;"><span typeof="mw:File"><a href="/wiki/Datei:Coats_of_arms_of_None.svg" class="mw-file-description" title="Wappen fehlt"><img alt="Wappen fehlt" src="//upload.wikimedia.org/wikipedia/commons/thumb/c/c1/Coats_of_arms_of_None.svg/100px-Coats_of_arms_of_None.svg.png" decoding="async" width="100" height="120" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/c/c1/Coats_of_arms_of_None.svg/150px-Coats_of_arms_of_None.svg.png 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/c/c1/Coats_of_arms_of_None.svg/200px-Coats_of_arms_of_None.svg.png 2x" data-file-width="125" data-file-height="150" /></a></span>
-</td>
-<td style="width: 170px; text-align:center;"><table class="centered" style="background-color: #f9f9f9; border: none; border-collapse: collapse; width: 1px;">
-<tbody><tr><td style="border: none; padding: 0; text-align: center;"><div style="position: relative; z-index: 0; padding: 0; display: inline-block; width: -webkit-max-content; width: -moz-max-content; width: max-content; border: none;"><figure class="mw-halign-center noviewer notpageimage" typeof="mw:File"><a href="/wiki/Datei:Ukraine_adm_location_map.svg" class="mw-file-description" title="Werbowez (Kossiw) (Ukraine)"><img alt="Werbowez (Kossiw) (Ukraine)" src="//upload.wikimedia.org/wikipedia/commons/thumb/7/78/Ukraine_adm_location_map.svg/180px-Ukraine_adm_location_map.svg.png" decoding="async" width="180" height="121" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/7/78/Ukraine_adm_location_map.svg/270px-Ukraine_adm_location_map.svg.png 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/7/78/Ukraine_adm_location_map.svg/360px-Ukraine_adm_location_map.svg.png 2x" data-file-width="1546" data-file-height="1038" /></a><figcaption>Werbowez (Kossiw) (Ukraine)</figcaption></figure><div style="position:absolute; top:50.7%; left:18.9%; height:0; width:0;"><div style="position:relative;z-index:100;left:-4px;top:-4px;width:8px;height:8px;line-height:0px;"><span typeof="mw:File"><a href="https://geohack.toolforge.org/geohack.php?pagename=Werbowez_(Kossiw)&amp;language=de&amp;params=48.342222222222_N_25.133333333333_E_dim:10000_region:UA-26_type:city(3395)&amp;title=Werbowez+%28Kossiw%29" title="Werbowez (Kossiw) (48° 20′ 32″ N, 25° 8′ 0″O)"><img alt="" src="//upload.wikimedia.org/wikipedia/commons/thumb/9/97/ButtonRed.svg/8px-ButtonRed.svg.png" decoding="async" width="8" height="8" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/9/97/ButtonRed.svg/12px-ButtonRed.svg.png 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/9/97/ButtonRed.svg/16px-ButtonRed.svg.png 2x" data-file-width="480" data-file-height="480" /></a></span></div>
-<table style="font-size:90%; border:none; background-color:transparent; border-collapse:collapse; line-height:1em; position:absolute; width:6em; margin: 0 .2em; text-align:left; left:1px; bottom:1px;"><tbody><tr><td style="border:none; vertical-align:middle;"><span style="position:relative; z-index:9; background-color:none;">Werbowez (Kossiw) </span></td></tr></tbody></table></div></div></td></tr>
-</tbody></table>
-</td></tr>
-<tr style="background-color:#AFD6FF;">
-<th colspan="2">Basisdaten
-</th></tr>
-<tr>
-<td><a href="/wiki/Liste_der_Oblaste_der_Ukraine" title="Liste der Oblaste der Ukraine">Oblast</a>:</td>
-<td><a href="/wiki/Oblast_Iwano-Frankiwsk" title="Oblast Iwano-Frankiwsk">Oblast Iwano-Frankiwsk</a>
-</td></tr>
-<tr>
-<td><a href="/wiki/Liste_der_Rajone_der_Ukraine" title="Liste der Rajone der Ukraine">Rajon</a>:</td>
-<td><a href="/wiki/Rajon_Kossiw" title="Rajon Kossiw">Rajon Kossiw</a>
-</td></tr>
-<tr>
-<td><a href="/wiki/H%C3%B6he_%C3%BCber_dem_Meeresspiegel" title="Höhe über dem Meeresspiegel">Höhe</a>:</td>
-<td>369 m
-</td></tr>
-<tr>
-<td><a href="/wiki/Fl%C3%A4cheninhalt" title="Flächeninhalt">Fläche</a>:</td>
-<td>18,77 <a href="/wiki/Quadratmeter#Quadratkilometer" title="Quadratmeter">km²</a>
-</td></tr>
-<tr>
-<td><a href="/wiki/Einwohner" title="Einwohner">Einwohner</a>:</td>
-<td>3.395 <small><i>(2001)</i></small>
-</td></tr>
-<tr>
-<td><a href="/wiki/Bev%C3%B6lkerungsdichte" title="Bevölkerungsdichte">Bevölkerungsdichte</a>:
-</td>
-<td>181 Einwohner je km²
-</td></tr>
-<tr>
-<td><a href="/wiki/Postleitzahl" title="Postleitzahl">Postleitzahlen</a>:</td>
-<td>78605
-</td></tr>
-<tr>
-<td><a href="/wiki/Telefonvorwahl" title="Telefonvorwahl">Vorwahl</a>:</td>
-<td>+380 3478
-</td></tr>
-<tr>
-<td><a href="/wiki/Geographische_Koordinaten" title="Geographische Koordinaten">Geographische Lage</a>:</td>
-<td><span id="text_coordinates" class="coordinates plainlinks-print"><a class="external text" href="https://geohack.toolforge.org/geohack.php?pagename=Werbowez_(Kossiw)&amp;language=de&amp;params=48.342222222222_N_25.133333333333_E_dim:10000_region:UA-26_type:city(3395)"><span title="Breitengrad">48°&#160;21′&#160;<abbr title="Nord">N</abbr></span>, <span title="Längengrad">25°&#160;8′&#160;<abbr title="Ost">O</abbr></span></a></span><span class="geo noexcerpt" style="display:none"><span class="body"></span><span class="latitude">48.342222222222</span><span class="longitude">25.133333333333</span><span class="elevation"></span></span><span id="coordinates" class="coordinates noprint"><span title="Koordinatensystem WGS84">Koordinaten: </span><a class="external text" href="https://geohack.toolforge.org/geohack.php?pagename=Werbowez_(Kossiw)&amp;language=de&amp;params=48.342222222222_N_25.133333333333_E_dim:10000_region:UA-26_type:city(3395)"><span title="Breitengrad">48°&#160;20′&#160;32″&#160;<abbr title="Nord">N</abbr></span>, <span title="Längengrad">25°&#160;8′&#160;0″&#160;<abbr title="Ost">O</abbr></span></a></span>
-</td></tr>
-<tr>
-<td><a href="/wiki/KATOTTH" title="KATOTTH">KATOTTH</a>:
-</td>
-<td>UA26100010030094355
-</td></tr>
-<tr>
-<td><a href="/wiki/KOATUU" title="KOATUU">KOATUU</a>:
-</td>
-<td>2623682401
-</td></tr>
-<tr>
-<td><a href="/wiki/Verwaltungsgliederung_der_Ukraine" title="Verwaltungsgliederung der Ukraine">Verwaltungsgliederung</a>:
-</td>
-<td>1 Dorf
-</td></tr>
-
-
-
-
-<tr>
-<td>Adresse:
-</td>
-<td>вул. Миру, буд. 15<br />78605 с. Вербовець
-</td></tr>
-<tr>
-<td><a href="/wiki/Website" title="Website">Website</a>:
-</td>
-<td><a rel="nofollow" class="external text" href="http://verbovets.kosiv.net/">Offizielle Webseite</a>
-</td></tr>
-<tr>
-<td colspan="2" style="padding-bottom:3px; text-align:center; border-bottom:1px solid #bbb; border-top:1px solid #bbb;"><a rel="nofollow" class="external text" href="http://w1.c1.rada.gov.ua/pls/z7503/A005?rdat1=31.08.2023&amp;rf7571=13801">Statistische Informationen</a>
-</td></tr>
-<tr>
-<td colspan="2" style="padding-bottom:3px; text-align:center; border-bottom:1px solid #bbb; border-top:1px solid #bbb;">
-<table class="centered" style="background-color: #f9f9f9; border: none; border-collapse: collapse; width: 1px;">
-<tbody><tr><td style="border: none; padding: 0; text-align: center;"><div style="position: relative; z-index: 0; padding: 0; display: inline-block; width: -webkit-max-content; width: -moz-max-content; width: max-content; border: none;"><figure class="mw-halign-center noviewer notpageimage" typeof="mw:File"><a href="/wiki/Datei:Ivano-Frankivsk_location_map.svg" class="mw-file-description" title="Werbowez (Kossiw) (Oblast Iwano-Frankiwsk)"><img alt="Werbowez (Kossiw) (Oblast Iwano-Frankiwsk)" src="//upload.wikimedia.org/wikipedia/commons/thumb/8/8e/Ivano-Frankivsk_location_map.svg/290px-Ivano-Frankivsk_location_map.svg.png" decoding="async" width="290" height="347" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/8/8e/Ivano-Frankivsk_location_map.svg/435px-Ivano-Frankivsk_location_map.svg.png 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/8/8e/Ivano-Frankivsk_location_map.svg/580px-Ivano-Frankivsk_location_map.svg.png 2x" data-file-width="533" data-file-height="637" /></a><figcaption>Werbowez (Kossiw) (Oblast Iwano-Frankiwsk)</figcaption></figure><div style="position:absolute; top:63.3%; left:74.4%; height:0; width:0;"><div style="position:relative;z-index:100;left:-4px;top:-4px;width:8px;height:8px;line-height:0px;"><span typeof="mw:File"><a href="https://geohack.toolforge.org/geohack.php?pagename=Werbowez_(Kossiw)&amp;language=de&amp;params=48.342222222222_N_25.133333333333_E_dim:10000_region:UA-26_type:city(3395)&amp;title=Werbowez+%28Kossiw%29" title="Werbowez (Kossiw) (48° 20′ 32″ N, 25° 8′ 0″O)"><img alt="" src="//upload.wikimedia.org/wikipedia/commons/thumb/9/97/ButtonRed.svg/8px-ButtonRed.svg.png" decoding="async" width="8" height="8" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/9/97/ButtonRed.svg/12px-ButtonRed.svg.png 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/9/97/ButtonRed.svg/16px-ButtonRed.svg.png 2x" data-file-width="480" data-file-height="480" /></a></span></div>
-<table style="font-size:90%; border:none; background-color:transparent; border-collapse:collapse; line-height:1em; position:absolute; width:6em; margin: 0 .2em; text-align:right; right:1px; bottom:1px;"><tbody><tr><td style="border:none; vertical-align:middle;"><span style="position:relative; z-index:9; background-color:none;">Werbowez (Kossiw) </span></td></tr></tbody></table></div></div></td></tr>
-</tbody></table><span style="display:none;"><a href="/w/index.php?title=Vorlage:Positionskarte_ISO_3166-2/Wartung/noregion&amp;action=edit&amp;redlink=1" class="new" title="Vorlage:Positionskarte ISO 3166-2/Wartung/noregion (Seite nicht vorhanden)">i1</a></span>
-</td></tr></tbody></table>
-<p><b>Werbowez</b> (<b><span style="font-style:normal;font-weight:normal"><a href="/wiki/Ukrainische_Sprache" title="Ukrainische Sprache">ukrainisch</a></span> <span lang="uk-Cyrl" class="Cyrl" style="font-style:normal">Вербовець</span></b>; <span style="font-style:normal;font-weight:normal"><a href="/wiki/Russische_Sprache" title="Russische Sprache">russisch</a></span> <span lang="ru-Cyrl" class="Cyrl" style="font-style:normal">Вербовец</span>, <a href="/wiki/Polnische_Sprache" title="Polnische Sprache">polnisch</a> <span lang="pl" style="font-style:italic;font-weight:normal">Wierzbowiec</span>; <span style="font-style:normal;font-weight:normal"><a href="/wiki/Rum%C3%A4nische_Sprache" title="Rumänische Sprache">rumänisch</a></span> <span lang="ro-Latn" style="font-style:italic">Verboveț</span>) ist ein <a href="/wiki/Dorf" title="Dorf">Dorf</a> in der <a href="/wiki/Ukraine" title="Ukraine">ukrainischen</a> <a href="/wiki/Oblast_Iwano-Frankiwsk" title="Oblast Iwano-Frankiwsk">Oblast Iwano-Frankiwsk</a> mit etwa 3400 Einwohnern (2001).<sup id="cite_ref-1" class="reference"><a href="#cite_note-1">&#91;1&#93;</a></sup> 
-</p>
-<figure class="mw-default-size mw-halign-left" typeof="mw:File/Thumb"><a href="/wiki/Datei:%D0%92%D0%B5%D1%80%D0%B1%D0%BE%D0%B2%D0%B5%D1%86%D1%8C.JPG" class="mw-file-description"><img src="//upload.wikimedia.org/wikipedia/commons/thumb/9/9d/%D0%92%D0%B5%D1%80%D0%B1%D0%BE%D0%B2%D0%B5%D1%86%D1%8C.JPG/220px-%D0%92%D0%B5%D1%80%D0%B1%D0%BE%D0%B2%D0%B5%D1%86%D1%8C.JPG" decoding="async" width="220" height="147" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/9/9d/%D0%92%D0%B5%D1%80%D0%B1%D0%BE%D0%B2%D0%B5%D1%86%D1%8C.JPG/330px-%D0%92%D0%B5%D1%80%D0%B1%D0%BE%D0%B2%D0%B5%D1%86%D1%8C.JPG 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/9/9d/%D0%92%D0%B5%D1%80%D0%B1%D0%BE%D0%B2%D0%B5%D1%86%D1%8C.JPG/440px-%D0%92%D0%B5%D1%80%D0%B1%D0%BE%D0%B2%D0%B5%D1%86%D1%8C.JPG 2x" data-file-width="5184" data-file-height="3456" /></a><figcaption>Blick auf das Dorf</figcaption></figure>
-<p>Das um 1650 erstmals schriftlich erwähnte Dorf<sup id="cite_ref-2" class="reference"><a href="#cite_note-2">&#91;2&#93;</a></sup> liegt im Osten der <a href="/wiki/Historische_Landschaft" title="Historische Landschaft">historischen Landschaft</a> <a href="/wiki/Galizien" title="Galizien">Galizien</a> am Ufer der <a href="/w/index.php?title=Rybnyzja_(Fluss)&amp;action=edit&amp;redlink=1" class="new" title="Rybnyzja (Fluss) (Seite nicht vorhanden)">Rybnyzja</a> (<span lang="uk-Cyrl" class="Cyrl">Рибниця</span>), einem 56&#160;km langen Nebenfluss des <a href="/wiki/Pruth" title="Pruth">Pruth</a> 7&#160;km nordöstlich vom Rajonzentrum <a href="/wiki/Kossiw" title="Kossiw">Kossiw</a> und 95&#160;km südlich vom Oblastzentrum <a href="/wiki/Iwano-Frankiwsk" title="Iwano-Frankiwsk">Iwano-Frankiwsk</a>. Südlich der Ortschaft verläuft die <a href="/wiki/Territorialstra%C3%9Fe" title="Territorialstraße">Territorialstraße</a> <i>T–09–09</i>.
-</p><p>Am 12. Juni 2020 wurde das Dorf ein Teil der neu gegründeten <i>Stadtgemeinde <a href="/wiki/Kossiw" title="Kossiw">Kossiw</a></i> im <a href="/wiki/Rajon_Kossiw" title="Rajon Kossiw">Rajon Kossiw</a><sup id="cite_ref-3" class="reference"><a href="#cite_note-3">&#91;3&#93;</a></sup>, bis dahin bildete es zusammen mit dem Dorf <a href="/w/index.php?title=Staryj_Kossiw&amp;action=edit&amp;redlink=1" class="new" title="Staryj Kossiw (Seite nicht vorhanden)">Staryj Kossiw</a> (<span lang="uk-Cyrl" class="Cyrl">Старий Косів</span>) die <i>Landratsgemeinde Werbowez</i> (Вербовецька сільська рада/<i>Werbowezka silska rada</i>) im Osten des Rajons.
-</p>
-<ol class="references">
-<li id="cite_note-1"><span class="mw-cite-backlink"><a href="#cite_ref-1">↑</a></span> <span class="reference-text"><a rel="nofollow" class="external text" href="http://w1.c1.rada.gov.ua/pls/z7503/A005?rf7571=13801">Ortswebseite</a> auf der offiziellen Webpräsenz der <a href="/wiki/Werchowna_Rada" title="Werchowna Rada">Werchowna Rada</a>; abgerufen am 14. November 2017 (ukrainisch)</span>
-</li>
-<li id="cite_note-2"><span class="mw-cite-backlink"><a href="#cite_ref-2">↑</a></span> <span class="reference-text"><a rel="nofollow" class="external text" href="http://ukrssr.com.ua/ifrank/kosivskiy/verbovets-kosivskiy-rayon-ivano-frankivska-oblast">Ortsgeschichte Werbowez</a> in der <a href="/wiki/Geschichte_der_St%C3%A4dte_und_D%C3%B6rfer_der_Ukrainischen_SSR" title="Geschichte der Städte und Dörfer der Ukrainischen SSR">Geschichte der Städte und Dörfer der Ukrainischen SSR</a>; abgerufen am 14. November 2017 (ukrainisch)</span>
-</li>
-<li id="cite_note-3"><span class="mw-cite-backlink"><a href="#cite_ref-3">↑</a></span> <span class="reference-text"><a rel="nofollow" class="external text" href="https://zakon.rada.gov.ua/laws/show/714-2020-%D1%80#Text">Кабінет Міністрів України Розпорядження від 12 червня 2020 р. № 714-р "Про визначення адміністративних центрів та затвердження територій територіальних громад Івано-Франківської області"</a></span>
-</li>
-</ol>
-<!-- 
-NewPP limit report
-Parsed by mw1396
-Cached time: 20230831121013
-Cache expiry: 42588
-Reduced expiry: true
-Complications: []
-CPU time usage: 0.219 seconds
-Real time usage: 0.274 seconds
-Preprocessor visited node count: 6414/1000000
-Post‐expand include size: 33611/2097152 bytes
-Template argument size: 12317/2097152 bytes
-Highest expansion depth: 34/100
-Expensive parser function count: 9/500
-Unstrip recursion depth: 0/20
-Unstrip post‐expand size: 1476/5000000 bytes
-Lua time usage: 0.080/10.000 seconds
-Lua memory usage: 3398800/52428800 bytes
-Number of Wikibase entities loaded: 0/400
--->
-<!--
-Transclusion expansion time report (%,ms,calls,template)
-100.00%  239.600      1 -total
- 93.55%  224.134      1 Vorlage:Infobox_Ort_in_der_Ukraine
- 50.81%  121.740      2 Vorlage:Positionskarte
- 49.72%  119.121      2 Vorlage:Positionskarte+
- 44.41%  106.401      2 Vorlage:Positionskarte~
- 33.28%   79.732      2 Vorlage:Positionskarte~*
- 25.69%   61.558      3 Vorlage:Lang
- 19.41%   46.499      1 Vorlage:Positionskarte_ISO_3166-2
- 16.90%   40.486     12 Vorlage:CoordinateLONG
- 14.02%   33.586     10 Vorlage:CoordinateLAT
--->
-</div>" - (de.wikipedia.org 31.08.2023)';
-
-        $output = NodaWikidataFetcher::cleanWikidataInput($testStr);
-        $expected = 'Werbowez (ukrainisch Вербовець; russisch Вербовец, polnisch Wierzbowiec; rumänisch Verboveț) ist ein Dorf in der ukrainischen Oblast Iwano-Frankiwsk mit etwa 3400 Einwohnern (2001).';
-        self::assertTrue(
-            str_starts_with($output, $expected),
-            "Start of parsed Wikipedia text should be:" . PHP_EOL . PHP_EOL . $expected . PHP_EOL . PHP_EOL . 'Real start text is: ' . PHP_EOL . PHP_EOL . substr($output, 0, 250)
-        );
-
-        $output = NodaWikidataFetcher::cleanWikidataInput('<div class="mw-parser-output"><figure class="mw-default-size mw-halign-right" typeof="mw:File/Thumb"><a href="/wiki/File:%D0%92%D0%B5%D1%80%D0%B1%D0%BE%D0%B2%D0%B5%D1%86%D1%8C.JPG" class="mw-file-description"><img src="//upload.wikimedia.org/wikipedia/commons/thumb/9/9d/%D0%92%D0%B5%D1%80%D0%B1%D0%BE%D0%B2%D0%B5%D1%86%D1%8C.JPG/220px-%D0%92%D0%B5%D1%80%D0%B1%D0%BE%D0%B2%D0%B5%D1%86%D1%8C.JPG" decoding="async" width="220" height="147" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/9/9d/%D0%92%D0%B5%D1%80%D0%B1%D0%BE%D0%B2%D0%B5%D1%86%D1%8C.JPG/330px-%D0%92%D0%B5%D1%80%D0%B1%D0%BE%D0%B2%D0%B5%D1%86%D1%8C.JPG 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/9/9d/%D0%92%D0%B5%D1%80%D0%B1%D0%BE%D0%B2%D0%B5%D1%86%D1%8C.JPG/440px-%D0%92%D0%B5%D1%80%D0%B1%D0%BE%D0%B2%D0%B5%D1%86%D1%8C.JPG 2x" data-file-width="5184" data-file-height="3456" /></a><figcaption></figcaption></figure>
-<p><span style="font-size: small;"><span id="coordinates"><a href="/wiki/%E5%9C%B0%E7%90%86%E5%9D%90%E6%A0%87" class="mw-redirect" title="地理坐标">坐标</a>：<style data-mw-deduplicate="TemplateStyles:r65292569">.mw-parser-output .geo-default,.mw-parser-output .geo-dms,.mw-parser-output .geo-dec{display:inline}.mw-parser-output .geo-nondefault,.mw-parser-output .geo-multi-punct{display:none}.mw-parser-output .longitude,.mw-parser-output .latitude{white-space:nowrap}</style><span class="plainlinks nourlexpansion"><a class="external text" href="//geohack.toolforge.org/geohack.php?language=zh&amp;pagename=%E9%9F%8B%E7%88%BE%E5%8D%9A%E9%9F%8B%E9%BD%8A_(%E7%A7%91%E7%B4%A2%E5%A4%AB%E5%8D%80)&amp;params=48_20_32_N_25_8_0_E_scale:30000"><span class="geo-default"><span class="geo-dms" title="此地的地图、航拍照片和其他数据"><span class="latitude">48°20′32″N</span> <span class="longitude">25°8′0″E</span></span></span><span class="geo-multi-punct">&#xfeff; / &#xfeff;</span><span class="geo-nondefault"><span class="geo-dec" title="此地的地图、航拍照片和其他数据">48.34222°N 25.13333°E</span><span style="display:none">&#xfeff; / <span class="geo">48.34222; 25.13333</span></span></span></a></span></span></span>
-</p><p><b>韋爾博韋齊</b>（<a href="/wiki/%E7%83%8F%E5%85%8B%E8%98%AD%E8%AA%9E" class="mw-redirect" title="烏克蘭語">烏克蘭語</a>：<span lang="uk">Вербовець</span>），是<a href="/wiki/%E7%83%8F%E5%85%8B%E8%98%AD" class="mw-redirect" title="烏克蘭">烏克蘭</a>的村落，位於該國西部<a href="/wiki/%E4%BC%8A%E4%B8%87%E8%AF%BA-%E5%BC%97%E5%85%B0%E7%A7%91%E5%A4%AB%E6%96%AF%E5%85%8B%E5%B7%9E" title="伊万诺-弗兰科夫斯克州">伊萬諾-弗蘭科夫斯克州</a>，由<a href="/wiki/%E7%A7%91%E7%B4%A2%E5%A4%AB%E5%8D%80" class="mw-redirect" title="科索夫區">科索夫區</a>負責管轄，始建於1456年，面積18.77平方公里，2001年人口3,395。
-</p>
-<!-- 
-NewPP limit report
-Parsed by mw1412
-Cached time: 20230831132208
-Cache expiry: 1814400
-Reduced expiry: false
-Complications: []
-CPU time usage: 0.147 seconds
-Real time usage: 0.186 seconds
-Preprocessor visited node count: 48/1000000
-Post‐expand include size: 2084/2097152 bytes
-Template argument size: 0/2097152 bytes
-Highest expansion depth: 3/100
-Expensive parser function count: 1/500
-Unstrip recursion depth: 0/20
-Unstrip post‐expand size: 362/5000000 bytes
-Lua time usage: 0.110/10.000 seconds
-Lua memory usage: 15402517/52428800 bytes
-Number of Wikibase entities loaded: 1/400
--->
-<!--
-Transclusion expansion time report (%,ms,calls,template)
-100.00%  152.989      1 -total
- 70.07%  107.204      1 Template:Lang-uk
- 29.62%   45.313      1 Template:Coord
--->
-</div>');
-        $expected = '韋爾博韋齊（烏克蘭語：Вербовець），是烏克蘭的村落，位於該國西部伊萬諾-弗蘭科夫斯克州，由科索夫區負責管轄，始建於1456年，面積18.77平方公里，2001年人口3,3';
-        self::assertTrue(
-            str_starts_with($output, $expected),
-            "Start of parsed Wikipedia text should be:" . PHP_EOL . PHP_EOL . $expected . PHP_EOL . PHP_EOL . 'Real start text is: ' . PHP_EOL . PHP_EOL . substr($output, 0, 250)
-        );
+        return [
+            'Actor with wikidata and translation' => [$cur[0], $cur[1]],
+        ];
 
     }
 
     /**
-     * Test for cleaning wikidata info.
+     * Data provider for a place that has a wikidata link and a Telugu translation.
      *
-     * @author Joshua Ramon Enslin <joshua@museum-digital.de>
-     * @group  ValidOutput
-     * @small
+     * @return array<string, array{0: int, 1: string}>
+     */
+    public static function placeWithTlAndWikidataLinkProvider():array {
+
+        $mysqli = md_main_mysqli_connect();
+
+        $result = $mysqli->do_read_query("SELECT `ort_id`, `noda_nrinsource`
+            FROM `" . DATABASENAME_NODA . "`.`noda_orte`
+            WHERE `noda_source` = 'Wikidata'
+                AND EXISTS (SELECT 1 FROM `" . DATABASENAME_NODA . "`.`ort_translation`
+                    WHERE `ort_translation`.`ort_id` = `noda_orte`.`ort_id`
+                        AND `trans_language` = '" . $mysqli->escape_string(self::TEST_LANG) . "')");
+
+        if (!$cur = $result->fetch_row()) {
+            throw new Exception("Failed to identify an entry that has a wikidata entry and a translation for language " . self::TEST_LANG);
+        }
+        $result->close();
+        $mysqli->close();
+
+        return [
+            'Place with wikidata and translation' => [$cur[0], $cur[1]],
+        ];
+
+    }
+
+    /**
+     * Data provider for an tag that has a wikidata link and a Telugu translation.
+     *
+     * @return array<string, array{0: int, 1: string}>
+     */
+    public static function tagWithTlAndWikidataLinkProvider():array {
+
+        $mysqli = md_main_mysqli_connect();
+
+        $result = $mysqli->do_read_query("SELECT `tag_id`, `noda_nrinsource`
+            FROM `" . DATABASENAME_NODA . "`.`noda_tag`
+            WHERE `noda_source` = 'Wikidata'
+                AND EXISTS (SELECT 1 FROM `" . DATABASENAME_NODA . "`.`tag_translation`
+                    WHERE `tag_translation`.`tag_id` = `noda_tag`.`tag_id`
+                        AND `trans_language` = '" . $mysqli->escape_string(self::TEST_LANG) . "')");
+
+        if (!$cur = $result->fetch_row()) {
+            throw new Exception("Failed to identify an entry that has a wikidata entry and a translation for language " . self::TEST_LANG);
+        }
+        $result->close();
+        $mysqli->close();
+
+        return [
+            'Tag with wikidata and translation' => [$cur[0], $cur[1]],
+        ];
+
+    }
+
+    /**
+     * Test for fetching and recording translations for an actor.
+     *
+     * @param integer $actor_id    Actor ID.
+     * @param string  $wikidata_id Wikidata ID.
      *
      * @return void
      */
-    public function testCleanWikidataInputWithoutHtml():void {
+    #[DataProvider('actorWithTlAndWikidataLinkProvider')]
+    public function testFetchingTranslationForPersinst(int $actor_id, string $wikidata_id):void {
 
-        $output = NodaWikidataFetcher::cleanWikidataInput('Werbowez (ukrainisch Вербовець; russisch Вербовец, polnisch Wierzbowiec; rumänisch Verboveț) ist ein Dorf in der ukrainischen Oblast Iwano-Frankiwsk mit etwa 3400 Einwohnern (2001).[1]');
-        $expected = 'Werbowez (ukrainisch Вербовець; russisch Вербовец, polnisch Wierzbowiec; rumänisch Verboveț) ist ein Dorf in der ukrainischen Oblast Iwano-Frankiwsk mit etwa 3400 Einwohnern (2001).';
-        self::assertTrue(
-            str_starts_with($output, $expected),
-            "Start of parsed Wikipedia text should be:" . PHP_EOL . PHP_EOL . $expected . PHP_EOL . PHP_EOL . 'Real start text is: ' . PHP_EOL . PHP_EOL . substr($output, 0, 250)
-        );
+        $mysqli = md_main_mysqli_connect();
+
+        $mysqli->do_update_query("DELETE FROM `" . DATABASENAME_NODA . "`.`persinst_translation`
+            WHERE `persinst_id` = " . $actor_id . "
+                AND `trans_language` = '" . $mysqli->escape_string(self::TEST_LANG) . "'");
+
+        self::assertEquals(0, MDMysqliTesting::queryNumRows($mysqli, "
+            FROM `" . DATABASENAME_NODA . "`.`persinst_translation`
+            WHERE `persinst_id` = " . $actor_id . "
+                AND `trans_language` = '" . $mysqli->escape_string(self::TEST_LANG) . "'"));
+
+        $data = NodaWikidataFetcher::getWikidataEntity($wikidata_id);
+        $fetcher = new NodaWikidataFetcher($mysqli);
+        $fetcher->getWikidataTranslationsForPersinst($data, $actor_id, [self::TEST_LANG]);
+
+        self::assertEquals(1, MDMysqliTesting::queryNumRows($mysqli, "
+            FROM `" . DATABASENAME_NODA . "`.`persinst_translation`
+            WHERE `persinst_id` = " . $actor_id . "
+                AND `trans_language` = '" . $mysqli->escape_string(self::TEST_LANG) . "'"));
+
+        $mysqli->close();
+
+    }
+
+    /**
+     * Test for fetching and recording translations for an place.
+     *
+     * @param integer $place_id    Place ID.
+     * @param string  $wikidata_id Wikidata ID.
+     *
+     * @return void
+     */
+    #[DataProvider('placeWithTlAndWikidataLinkProvider')]
+    public function testFetchingTranslationForPlace(int $place_id, string $wikidata_id):void {
+
+        $mysqli = md_main_mysqli_connect();
+
+        $mysqli->do_update_query("DELETE FROM `" . DATABASENAME_NODA . "`.`ort_translation`
+            WHERE `ort_id` = " . $place_id . "
+                AND `trans_language` = '" . $mysqli->escape_string(self::TEST_LANG) . "'");
+
+        self::assertEquals(0, MDMysqliTesting::queryNumRows($mysqli, "
+            FROM `" . DATABASENAME_NODA . "`.`ort_translation`
+            WHERE `ort_id` = " . $place_id . "
+                AND `trans_language` = '" . $mysqli->escape_string(self::TEST_LANG) . "'"));
+
+        $data = NodaWikidataFetcher::getWikidataEntity($wikidata_id);
+        $fetcher = new NodaWikidataFetcher($mysqli);
+        $fetcher->getWikidataTranslationsForPlace($data, $place_id, [self::TEST_LANG]);
+
+        self::assertEquals(1, MDMysqliTesting::queryNumRows($mysqli, "
+            FROM `" . DATABASENAME_NODA . "`.`ort_translation`
+            WHERE `ort_id` = " . $place_id . "
+                AND `trans_language` = '" . $mysqli->escape_string(self::TEST_LANG) . "'"));
+
+        $mysqli->close();
+
+    }
+
+    /**
+     * Test for fetching and recording translations for an tag.
+     *
+     * @param integer $tag_id      Tag ID.
+     * @param string  $wikidata_id Wikidata ID.
+     *
+     * @return void
+     */
+    #[DataProvider('tagWithTlAndWikidataLinkProvider')]
+    public function testFetchingTranslationForTag(int $tag_id, string $wikidata_id):void {
+
+        $mysqli = md_main_mysqli_connect();
+
+        $mysqli->do_update_query("DELETE FROM `" . DATABASENAME_NODA . "`.`tag_translation`
+            WHERE `tag_id` = " . $tag_id . "
+                AND `trans_language` = '" . $mysqli->escape_string(self::TEST_LANG) . "'");
+
+        self::assertEquals(0, MDMysqliTesting::queryNumRows($mysqli, "
+            FROM `" . DATABASENAME_NODA . "`.`tag_translation`
+            WHERE `tag_id` = " . $tag_id . "
+                AND `trans_language` = '" . $mysqli->escape_string(self::TEST_LANG) . "'"));
+
+        $data = NodaWikidataFetcher::getWikidataEntity($wikidata_id);
+        $fetcher = new NodaWikidataFetcher($mysqli);
+        $fetcher->getWikidataTranslationsForTag($data, $tag_id, [self::TEST_LANG]);
+
+        self::assertEquals(1, MDMysqliTesting::queryNumRows($mysqli, "
+            FROM `" . DATABASENAME_NODA . "`.`tag_translation`
+            WHERE `tag_id` = " . $tag_id . "
+                AND `trans_language` = '" . $mysqli->escape_string(self::TEST_LANG) . "'"));
+
+        $mysqli->close();
+
+    }
+
+    /**
+     * Test that fetching translation from Wikidata returns the title of the wikipedia page,
+     * not the wikidata title.
+     *
+     * @return void
+     */
+    public function testListTranslationsFromWikidataWikipediaReturnsWikipediaTitle():void {
+
+        $data = NodaWikidataFetcher::getWikidataEntity("Q33550");
+
+        $output = NodaWikidataFetcher::listTranslationsFromWikidataWikipedia(["de"], $data);
+        self::assertNotEmpty($output['de']);
+
+        self::assertEquals("Friedrich II. (Preußen)", $output['de']['label']);
 
     }
 }

tests/bootstrap.php

@@ -12,7 +12,21 @@ 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__ . '/../../MDAllowedValueSets/src',
+        __DIR__ . '/../../MDAllowedValueSets/src/classes',
+        __DIR__ . '/../../MDAllowedValueSets/src/enums',
+        __DIR__ . '/../../MDAllowedValueSets/exceptions',
+        __DIR__ . '/../../MDMysqli/exceptions',
+    ]) as $classDir) {
 
         if (\file_exists("$classDir/$className.php")) {
             include "$classDir/$className.php";
@@ -20,6 +34,5 @@ declare(strict_types = 1);
         }
 
     }
-
 });