Merge branch 'upstream-candidate-1.9.5' into upstream-master

Author: dcamper

Bundle.ecl

@@ -6,5 +6,5 @@ EXPORT Bundle := MODULE(Std.BundleBase)
     EXPORT License := 'http://www.apache.org/licenses/LICENSE-2.0';
     EXPORT Copyright := 'Copyright (C) 2024 HPCC Systems';
     EXPORT DependsOn := [];
-    EXPORT Version := '1.9.4';
+    EXPORT Version := '1.9.5';
 END;

Profile.ecl

@@ -617,7 +617,7 @@ EXPORT Profile(inFile,
         #UNIQUENAME(_MapUpperCharUni);
         LOCAL %_MapUpperCharUni%(UNICODE s) := REGEXREPLACE(u'\\p{Lu}', s, u'A');
         #UNIQUENAME(_MapLowerCharUni);
-        LOCAL %_MapLowerCharUni%(UNICODE s) := REGEXREPLACE(u'[[\\p{Ll}][\\p{Lt}][\\p{Lm}][\\p{Lo}]]', s, u'a');
+        LOCAL %_MapLowerCharUni%(UNICODE s) := REGEXREPLACE(u'[\\p{Ll}\\p{Lt}\\p{Lm}\\p{Lo}]', s, u'a');
         #UNIQUENAME(_MapDigitUni);
         LOCAL %_MapDigitUni%(UNICODE s) := REGEXREPLACE(u'[1-9]', s, u'9'); // Leave '0' as-is and replace with '9' later
         #UNIQUENAME(_MapAllUni);

README.md

@@ -103,6 +103,7 @@ level, such as within your "My Files" folder.
 |1.9.2|Security updates|
 |1.9.3|Better identify upper- and lower-case Unicode characters in text patterns; scan Unicode and UTF-8 strings to see if they can be represented with a STRING data type instead|
 |1.9.4|README fixes and updates; improve UTF-8 detection and prevent buffer overruns during character scans; use short form of Unicode property names in regex|
+|1.9.5|Correct Unicode regex regression introduced in 1.9.4|
 </details>
 
 ---