du/pl ; wildcards

thesaurus-linguae-aegyptiae · Sep 20, 2022 · 7bcdf23 · 7bcdf23
2 parents 38c7239 + 6e00692
commit 7bcdf23
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 15 deletions.
diff --git a/src/main/java/tla/backend/es/query/LemmaSearchQueryBuilder.java b/src/main/java/tla/backend/es/query/LemmaSearchQueryBuilder.java
@@ -146,14 +146,17 @@ public String maskRegExTranscription(String transcription) {
             transcription = transcription.replace("⸮", ""); 
             // "?", "[" , and "]" are part of allowed RegEx syntax
 
-            // BTS wildcards (any sign)
+            // leagacy TLA wildcards
             transcription = transcription.replace("§", "."); // "§" in legacyTLA 
-            transcription = transcription.replace("*", "."); // "*" new in newTLA 
+
+            // Usual wildcards
+            transcription = transcription.replace("_", "."); // any sigle sign 
+            transcription = transcription.replace("*", ".*"); // zero or more signs
 
             // treatment of right end
 			if (transcription.endsWith("$")) { // "$": wirkliches String-Ende
 				transcription = transcription.replace("$", ""); // remove "$" (all, just to be sure)
-			} else {
+			} else if (!transcription.endsWith(".*")) { // redundant if already ends with ".*"
 				transcription = transcription + ".*"; // right: any signs may follow
 			}
 

diff --git a/src/main/resources/elasticsearch/settings/indices/lemma.json b/src/main/resources/elasticsearch/settings/indices/lemma.json
@@ -63,18 +63,6 @@
         "transcription_suffix_filter": {
           "type": "mapping",
           "mappings": [
-            ".t.pl => .wt",
-            ".t:pl => .wt",
-            ".tpl => .wt",
-            "t.du => .tj",
-            "t:du => .tj",
-            ".tdu => .tj",
-            ",t,pl => ,wt",
-            ",tpl => ,wt",
-            "t,du => ,tj",
-            ",tdu => ,tj",
-            "du => wj",
-            "pl => w",
             ",  => ."
           ]
         },