Fix comma in link email property (#1269)

macchiati · markusicu · web-flow · commit e6a332badd9b · 2025-12-26T14:15:00.000-08:00
* Add changes for email property

* Fixed data files

* Update code for prop change, regen dev file.

* Update unicodetools/src/main/java/org/unicode/utilities/LinkUtilities.java

Co-authored-by: Markus Scherer &lt;markus.icu@gmail.com&gt;

---------

Co-authored-by: Markus Scherer &lt;markus.icu@gmail.com&gt;
diff --git a/unicodetools/data/linkification/17.0.0/LinkBracket.txt b/unicodetools/data/linkification/17.0.0/LinkBracket.txt
@@ -1,5 +1,5 @@
 # LinkBracket.txt
-# Date: 2025-12-20, 21:02:29 GMT 
+# Date: 2025-12-26, 00:24:58 GMT 
 # © 2025 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
diff --git a/unicodetools/data/linkification/17.0.0/LinkDetectionTest.txt b/unicodetools/data/linkification/17.0.0/LinkDetectionTest.txt
@@ -1,5 +1,5 @@
 # LinkDetectionTest.txt
-# Date: 2025-12-20, 21:02:29 GMT 
+# Date: 2025-12-26, 00:24:58 GMT 
 # © 2025 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
diff --git a/unicodetools/data/linkification/17.0.0/LinkEmail.txt b/unicodetools/data/linkification/17.0.0/LinkEmail.txt
@@ -1,5 +1,5 @@
 # LinkEmail.txt
-# Date: 2025-12-20, 21:02:29 GMT 
+# Date: 2025-12-26, 00:24:58 GMT 
 # © 2025 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -26,7 +26,8 @@
 # 
 0021           # 1.1       (!)  EXCLAMATION MARK
 0023..0027     # 1.1   [5] (#..')  NUMBER SIGN..APOSTROPHE
-002A..0039     # 1.1  [16] (*..9)  ASTERISK..DIGIT NINE
+002A..002B     # 1.1   [2] (*..+)  ASTERISK..PLUS SIGN
+002D..0039     # 1.1  [13] (-..9)  HYPHEN-MINUS..DIGIT NINE
 003D           # 1.1       (=)  EQUALS SIGN
 003F           # 1.1       (?)  QUESTION MARK
 0041..005A     # 1.1  [26] (A..Z)  LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z
@@ -1292,4 +1293,4 @@ FFDA..FFDC     # 1.1   [3] (ￚ..ￜ)  HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
 323B0..33479   # 17.0 [4298] (𲎰..𳑹)  CJK UNIFIED IDEOGRAPH-323B0..CJK UNIFIED IDEOGRAPH-33479
 E0100..E01EF   # 4.0 [240] (U+E0100..U+E01EF)  VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 149241
+# Total code points: 149240
diff --git a/unicodetools/data/linkification/17.0.0/LinkFormattingTest.txt b/unicodetools/data/linkification/17.0.0/LinkFormattingTest.txt
@@ -1,5 +1,5 @@
 # LinkFormattingTest.txt
-# Date: 2025-12-20, 21:02:29 GMT 
+# Date: 2025-12-26, 00:24:58 GMT 
 # © 2025 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
diff --git a/unicodetools/data/linkification/17.0.0/LinkTerm.txt b/unicodetools/data/linkification/17.0.0/LinkTerm.txt
@@ -1,5 +1,5 @@
 # LinkTerm.txt
-# Date: 2025-12-20, 21:02:29 GMT 
+# Date: 2025-12-26, 00:24:58 GMT 
 # © 2025 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
diff --git a/unicodetools/data/linkification/dev/LinkEmail.txt b/unicodetools/data/linkification/dev/LinkEmail.txt
@@ -1,5 +1,5 @@
 # LinkEmail.txt
-# Date: 2025-12-24, 02:37:15 GMT 
+# Date: 2025-12-26, 00:32:54 GMT 
 # © 2025 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use and license, see https://www.unicode.org/terms_of_use.html
@@ -26,7 +26,8 @@
 # 
 0021           # 1.1       (!)  EXCLAMATION MARK
 0023..0027     # 1.1   [5] (#..')  NUMBER SIGN..APOSTROPHE
-002A..0039     # 1.1  [16] (*..9)  ASTERISK..DIGIT NINE
+002A..002B     # 1.1   [2] (*..+)  ASTERISK..PLUS SIGN
+002D..0039     # 1.1  [13] (-..9)  HYPHEN-MINUS..DIGIT NINE
 003D           # 1.1       (=)  EQUALS SIGN
 003F           # 1.1       (?)  QUESTION MARK
 0041..005A     # 1.1  [26] (A..Z)  LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z
@@ -1331,4 +1332,4 @@ FFDA..FFDC     # 1.1   [3] (ￚ..ￜ)  HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
 3D000..3FC3F   # 18.0 [11328] (U+3D000..U+3FC3F)  SEAL CHARACTER-3D000..SEAL CHARACTER-3FC3F
 E0100..E01EF   # 4.0 [240] (U+E0100..U+E01EF)  VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 162119
+# Total code points: 162118
diff --git a/unicodetools/src/main/java/org/unicode/utilities/LinkUtilities.java b/unicodetools/src/main/java/org/unicode/utilities/LinkUtilities.java
@@ -194,17 +194,20 @@ private LinkTermination(String uset) {
         }
     }
 
-    // Note: the source standards are painful to read.
-    // https://en.wikipedia.org/wiki/Email_address#Local-part is much easier
+    // https://www.rfc-editor.org/rfc/rfc5322.html#section-3.2.3 has the full list for ASCII part
+    // See also https://en.wikipedia.org/wiki/Email_address#Local-part
+    // We add dot (ascii '.'), and then check after for the special dot constraints.
 
-    static final UnicodeSet EMAIL_EXCLUDES =
-            new UnicodeSet("[\\u0020 ; \\: \" ( ) \\[ \\] @ \\\\ < >]").freeze();
+    static final UnicodeSet EMAIL_ASCII_INCLUDES =
+            new UnicodeSet("[[a-zA-Z][0-9][_ \\- ! ? ' \\{ \\} * / \\& # % ` \\^ + = | ~ \\$]]")
+                    .add('.')
+                    .freeze();
     static final UnicodeSet validEmailLocalPart =
             new UnicodeSet(
-                            "[\\p{XID_Continue}\\p{block=basic_latin}-\\p{Cc}]",
+                            "[\\p{XID_Continue}-\\p{block=basic_latin}]",
                             new ParsePosition(0),
                             VersionedSymbolTable.frozenAt(UNICODE_VERSION))
-                    .removeAll(EMAIL_EXCLUDES)
+                    .addAll(EMAIL_ASCII_INCLUDES)
                     .freeze();
     public static final UnicodeProperty LinkEmail =
             new UnicodeSetProperty()
