fix(cluecode): detect glued Author:Name C++ tags

- fix(cluecode): narrow Frankie.Chu author grammar to NAME-DOT
- fix(ci): stop PyPI commoncode from shadowing in-tree sources
- fix(ci): make Windows latest_from_pip uninstall sequential
- fix(cluecode): dual-home NAME-DOT for copyright holders
- fix(cluecode): reject sentence-glue NAME-DOT holders

Signed-off-by: Alex Chen <l46983284@gmail.com>

Author: alexchen-sys

azure-pipelines.yml

@@ -194,39 +194,39 @@ jobs:
           image_name: ubuntu-22.04
           python_versions: ['3.10', '3.11', '3.12', '3.13', '3.14']
           test_suites:
-              all: venv/bin/pip install --upgrade-strategy eager --force-reinstall --upgrade -e .[testing] && venv/bin/pytest -n 2 -vvs tests/scancode/test_cli.py
+              all: venv/bin/pip install --upgrade-strategy eager --force-reinstall --upgrade -e .[testing] && (venv/bin/pip uninstall -y commoncode || true) && venv/bin/pytest -n 2 -vvs tests/scancode/test_cli.py
 
     - template: etc/ci/azure-posix.yml
       parameters:
           job_name: ubuntu24_cpython_latest_from_pip
           image_name: ubuntu-24.04
           python_versions: ['3.10', '3.11', '3.12', '3.13', '3.14']
           test_suites:
-              all: venv/bin/pip install --upgrade-strategy eager --force-reinstall --upgrade -e .[testing] && venv/bin/pytest -n 2 -vvs tests/scancode/test_cli.py
+              all: venv/bin/pip install --upgrade-strategy eager --force-reinstall --upgrade -e .[testing] && (venv/bin/pip uninstall -y commoncode || true) && venv/bin/pytest -n 2 -vvs tests/scancode/test_cli.py
 
     - template: etc/ci/azure-posix.yml
       parameters:
           job_name: macos14_cpython_latest_from_pip
           image_name: macos-14
           python_versions: ['3.10', '3.11', '3.12', '3.13', '3.14']
           test_suites:
-              all: venv/bin/pip install --upgrade-strategy eager --force-reinstall --upgrade -e .[testing] && venv/bin/pytest -n 2 -vvs tests/scancode/test_cli.py
+              all: venv/bin/pip install --upgrade-strategy eager --force-reinstall --upgrade -e .[testing] && (venv/bin/pip uninstall -y commoncode || true) && venv/bin/pytest -n 2 -vvs tests/scancode/test_cli.py
 
     - template: etc/ci/azure-win.yml
       parameters:
           job_name: win2019_cpython_latest_from_pip
           image_name: windows-2025-vs2026
           python_versions: ['3.10', '3.11', '3.12', '3.13', '3.14']
           test_suites:
-              all: venv\Scripts\pip install --upgrade-strategy eager --force-reinstall --upgrade -e .[testing] &&  venv\Scripts\pytest -n 2 -vvs  tests\scancode\test_cli.py
+              all: venv\Scripts\pip install --upgrade-strategy eager --force-reinstall --upgrade -e .[testing] && (venv\Scripts\pip uninstall -y commoncode || echo.) && venv\Scripts\pytest -n 2 -vvs  tests\scancode\test_cli.py
 
     - template: etc/ci/azure-win.yml
       parameters:
           job_name: win2022_cpython_latest_from_pip
           image_name: windows-2022
           python_versions: ['3.10', '3.11', '3.12', '3.13', '3.14']
           test_suites:
-              all: venv\Scripts\pip install --upgrade-strategy eager --force-reinstall --upgrade -e .[testing] &&  venv\Scripts\pytest -n 2 -vvs  tests\scancode\test_cli.py
+              all: venv\Scripts\pip install --upgrade-strategy eager --force-reinstall --upgrade -e .[testing] && (venv\Scripts\pip uninstall -y commoncode || echo.) && venv\Scripts\pytest -n 2 -vvs  tests\scancode\test_cli.py
 
 
 ################################################################################

configure

@@ -314,6 +314,12 @@ find_python
 create_virtualenv "$VIRTUALENV_DIR"
 install_packages "$FLOT_REQUIREMENTS"
 install_packages "$CFG_REQUIREMENTS"
+# After commoncode was merged back (#5116), transitive deps still install PyPI
+# commoncode (e.g. 32.5.2) into site-packages. That package shadows the in-tree
+# src/commoncode from the editable install (clean_path uses rstrip on PyPI vs
+# strip in-tree), which breaks --full-root CLI tests. Drop the PyPI dist so the
+# in-tree sources on the editable path win.
+"$CFG_BIN_DIR/pip" uninstall -y commoncode >/dev/null 2>&1 || true
 . "$CFG_BIN_DIR/activate"
 "$CFG_BIN_DIR/scancode-train-gibberish-model"
 

configure.bat

@@ -168,6 +168,11 @@ if %ERRORLEVEL% neq 0 (
     %PIP_EXTRA_ARGS% ^
     %CFG_REQUIREMENTS%
 
+@rem After commoncode was merged back (#5116), transitive deps still install PyPI
+@rem commoncode into site-packages and shadow in-tree src/commoncode. Uninstall
+@rem the PyPI dist so the editable path sources win (needed for --full-root tests).
+"%CFG_BIN_DIR%\pip" uninstall -y commoncode >nul 2>&1
+
 "%CFG_BIN_DIR%\scancode-train-gibberish-model"
 
 @rem ################################

src/cluecode/copyrights.py

@@ -428,6 +428,10 @@ def get_tokens(numbered_lines, splitter=re.compile(r'[\t =;]+').split):
         if TRACE_TOK:
             logger_debug('  get_tokens: preped line: ' + repr(line))
 
+        # Split glued Author:/Authors: tags so "Author:Frankie.Chu" tokenizes as AUTH + name.
+        # Keep ordinary tokens intact; only introduce a space after the tag when missing.
+        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 +2231,16 @@ def build_detection_from_node(
     # proper noun with some separator and trailing comma
     (r'^[A-Z]+\.[A-Z][a-z]+,?$', 'NNP'),
 
+    # Mixed-case dotted personal/product name token, e.g. Frankie.Chu / Rocket.Chat.
+    # Keep this after exact NNP exceptions (Xiph.Org) and exclude common domain/org suffixes
+    # so tokens like Xiph.Org/Iotacoffee.Com still fall through to URL/NNP patterns.
+    # NAME-DOT is intentionally not NNP: AUTHOR only matches AUTH + NAME-DOT for
+    # single-token Author:Name tags, avoiding false authors from bare AUTH NNP.
+    # Also reject sentence-glue tails from missing spaces in license prose
+    # (Assignment.This, Remedies.In, Corporation.All) so dual-home copyright
+    # grammar cannot invent holders from section headers.
+    (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 +2566,9 @@ def build_detection_from_node(
 
     # NAME-YEAR starts or ends with a YEAR range
     NAME-YEAR: {<YR-RANGE> <NNP> <NNP>+} #350
+    # 2015-2020 Rocket.Chat Technologies Corp. (NAME-DOT accepted where NNP is needed)
+    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 +2716,11 @@ 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
+    # Rocket.Chat Technologies Corp. / Foo.Bar Systems Inc. (NAME-DOT + company words)
+    # Do NOT accept bare {NAME-DOT} as COMPANY: license prose like Assignment.This
+    # / Remedies.In would become fake holders. Bare Rocket.Chat still works via
+    # NAME-YEAR {YR-RANGE NAME-DOT} when a year is present.
+    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 +3497,9 @@ def build_detection_from_node(
     # author (Panagiotis Tsirigotis)
     AUTHOR: {<AUTH>  <NNP><NNP>+} #author Foo Bar
 
+    # Author:Frankie.Chu / Author: Frankie.Chu (single mixed-case dotted name token)
+    AUTHOR: {<AUTH> <NAME-DOT>} #author Frankie.Chu
+
     # Author: Tim (xtimor@gmail.com)
     AUTHOR: {<AUTH>  <NNP>+ <EMAIL>+} #Author Foo joe@email.com
 

tests/cluecode/data/authors/author_frankie_chu_cpp-tm1637.cpp

@@ -0,0 +1,2 @@
+// Date:9 April,2012
+// Author:Frankie.Chu

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)