From 0076a40be8163780b6e59f47e67c8261967128d7 Mon Sep 17 00:00:00 2001
From: Alex Chen <l46983284@gmail.com>
Date: Tue, 14 Jul 2026 18:19:50 +0000
Subject: [PATCH] fix(cluecode): detect glued Author:Name C++ tags

Normalize Author:Name without a space after the colon and match
single mixed-case dotted names like Frankie.Chu.

Fixes #4229

Signed-off-by: Alex Chen <l46983284@gmail.com>
---
 src/cluecode/copyrights.py                          | 13 +++++++++++++
 .../data/authors/author_frankie_chu_cpp-tm1637.cpp  |  2 ++
 .../authors/author_frankie_chu_cpp-tm1637.cpp.yml   |  9 +++++++++
 3 files changed, 24 insertions(+)
 create mode 100644 tests/cluecode/data/authors/author_frankie_chu_cpp-tm1637.cpp
 create mode 100644 tests/cluecode/data/authors/author_frankie_chu_cpp-tm1637.cpp.yml

diff --git a/src/cluecode/copyrights.py b/src/cluecode/copyrights.py
index 6d17467acf..7dcf8e2c07 100644
--- a/src/cluecode/copyrights.py
+++ b/src/cluecode/copyrights.py
@@ -428,6 +428,9 @@ def get_tokens(numbered_lines, splitter=re.compile(r'[\t =;]+').split):
         if TRACE_TOK:
             logger_debug('  get_tokens: preped line: ' + repr(line))
 
+        # Author:Frankie.Chu -> Author: Frankie.Chu for AUTH + name tokenization
+        line = re.sub(r'(?i)\b(authors?|@authors?)(:)(?=\S)', r'\1\2 ', line)
+
         for tok in splitter(line):
             # strip trailing quotes+comma
             if tok.endswith("',"):
@@ -2227,6 +2230,10 @@ def build_detection_from_node(
     # proper noun with some separator and trailing comma
     (r'^[A-Z]+\.[A-Z][a-z]+,?$', 'NNP'),
 
+    # Mixed-case dotted name (Frankie.Chu). Not NNP: AUTHOR uses AUTH+NAME-DOT only.
+    # Exclude common org suffixes and license-prose glue tails (Assignment.This).
+    (r'^[A-Z][a-z0-9]+(?:\.(?!Org,?$|Com,?$|Net,?$|Edu,?$|Gov,?$|Inc,?$|Ltd,?$|Co,?$|This,?$|In,?$|All,?$|The,?$|Of,?$|And,?$|For,?$|By,?$|With,?$|From,?$|To,?$|As,?$|Or,?$|An,?$|At,?$|On,?$|Is,?$|Are,?$|Was,?$|Be,?$|If,?$|Not,?$|No,?$|Any,?$|Such,?$|That,?$|These,?$|Those,?$|When,?$|Where,?$|Which,?$|Who,?$|Will,?$|Shall,?$|May,?$|Can,?$|Must,?$|Should,?$|Would,?$|Could,?$|Rights,?$|Reserved,?$|Agreement,?$|Event,?$|Breach,?$|License,?$|Software,?$|Source,?$|Code,?$|File,?$|Files,?$|Notice,?$|Notices,?$|Subject,?$|Terms,?$|Conditions,?$|Section,?$|Clause,?$|Party,?$|Parties,?$)[A-Z][a-z0-9]+)+,?$', 'NAME-DOT'),
+
     # proper noun with apostrophe ': D'Orleans, D'Arcy, T'so, Ts'o
     (r"^[A-Z][a-z]?'[A-Z]?[a-z]+[,\.]?$", 'NNP'),
 
@@ -2552,6 +2559,8 @@ def build_detection_from_node(
 
     # NAME-YEAR starts or ends with a YEAR range
     NAME-YEAR: {<YR-RANGE> <NNP> <NNP>+} #350
+    NAME-YEAR: {<YR-RANGE> <NAME-DOT> <COMP|COMPANY|NNP|NN>+} #350.05
+    NAME-YEAR: {<YR-RANGE> <NAME-DOT>} #350.06
 
     COPYRIGHT: {<COPY>  <YR-RANGE>  <NNP>  <NN>  <NNP>  <NNP>  <NNP>  <EMAIL>} #350.1
 
@@ -2699,6 +2708,8 @@ def build_detection_from_node(
     # Companies
     COMPANY: {<NAME|NAME-EMAIL|NAME-YEAR|NNP>+ <OF> <NN>? <COMPANY|COMP> <NNP>?}        #770
     COMPANY: {<NNP> <COMP|COMPANY> <COMP|COMPANY>}        #780
+    # NAME-DOT + company words only (not bare NAME-DOT)
+    COMPANY: {<NAME-DOT> <COMP|COMPANY>+}        #780.1
     COMPANY: {<NN>? <COMPANY|NAME|NAME-EMAIL> <CC> <COMPANY|NAME|NAME-EMAIL>}        #790
     COMPANY: {<COMP|COMPANY|NNP> <NN> <COMPANY|COMPANY> <NNP>+}        #800
 
@@ -3475,6 +3486,8 @@ def build_detection_from_node(
     # author (Panagiotis Tsirigotis)
     AUTHOR: {<AUTH>  <NNP><NNP>+} #author Foo Bar
 
+    AUTHOR: {<AUTH> <NAME-DOT>} #author Frankie.Chu
+
     # Author: Tim (xtimor@gmail.com)
     AUTHOR: {<AUTH>  <NNP>+ <EMAIL>+} #Author Foo joe@email.com
 
diff --git a/tests/cluecode/data/authors/author_frankie_chu_cpp-tm1637.cpp b/tests/cluecode/data/authors/author_frankie_chu_cpp-tm1637.cpp
new file mode 100644
index 0000000000..5bb8b7afb3
--- /dev/null
+++ b/tests/cluecode/data/authors/author_frankie_chu_cpp-tm1637.cpp
@@ -0,0 +1,2 @@
+// Date:9 April,2012
+// Author:Frankie.Chu
diff --git a/tests/cluecode/data/authors/author_frankie_chu_cpp-tm1637.cpp.yml b/tests/cluecode/data/authors/author_frankie_chu_cpp-tm1637.cpp.yml
new file mode 100644
index 0000000000..126637455b
--- /dev/null
+++ b/tests/cluecode/data/authors/author_frankie_chu_cpp-tm1637.cpp.yml
@@ -0,0 +1,9 @@
+what:
+  - authors
+  - authors_summary
+authors:
+  - Frankie.Chu
+authors_summary:
+  - value: Frankie.Chu
+    count: 1
+notes: Detect glued C++ Author:Name tags without space after colon (issue #4229)