Detect lower camel case copyright holders

AUTHORS.rst

@@ -61,6 +61,7 @@ The following organizations or individuals have contributed to ScanCode:
 - Nisha Kumar @nishakm
 - Nishchith Shetty @inishchith
 - Nitish Sharma @nitish81299
+- Wonjae Park @JustinWonjaePark
 - Paul Gier @pgier
 - Philippe Ombredanne @pombredanne
 - Pi Delport @PiDelport

CHANGELOG.rst

@@ -4,6 +4,8 @@ Changelog
 Next release
 --------------
 
+- Improve copyright holder detection for lower camel case names.
+
 - Fix the optional ``licenses`` extra dependency typo to install
   ``licensedcode-data``.
   https://github.com/aboutcode-org/scancode-toolkit/pull/5056

src/cluecode/copyrights.py

@@ -286,6 +286,17 @@ def detect(self,
         # first, POS tag each token using token regexes
         lexed_text = list(self.lexer.lex_tokens(tokens, trace=TRACE_TOK))
 
+
+        for index, token in enumerate(lexed_text):
+            if (
+                index
+                and token.label == 'JUNK'
+                and lexed_text[index - 1].label == 'YR'
+                and token.start_line == lexed_text[index - 1].start_line
+                and re.match(r'^[a-z]{2,}[A-Z][a-z]+(?:[A-Z][a-z]+)*[\.,]?$', token.value)
+            ):
+                token.label = 'MIXEDCAP'
+
         if TRACE or TRACE_DEEP:
             logger_debug(f'CopyrightDetector: lexed tokens:')
             for l in lexed_text:

tests/cluecode/data/copyrights/lower_camel_case_holder.txt

@@ -0,0 +1,2 @@
+Copyright (c) 2021, drGlennPierce
+Copyright (c) 2022, myCompany

tests/cluecode/data/copyrights/lower_camel_case_holder.txt.yml

@@ -0,0 +1,9 @@
+what:
+  - copyrights
+  - holders
+copyrights:
+  - Copyright (c) 2021, drGlennPierce
+  - Copyright (c) 2022, myCompany
+holders:
+  - drGlennPierce
+  - myCompany