aboutcode-org · OctavioValdiviaMendoza · Jul 21, 2026 · Jul 22, 2026 · Jul 23, 2026 · Jul 24, 2026
diff --git a/.github/workflows/commoncode-release.yml b/.github/workflows/commoncode-release.yml
@@ -1,4 +1,4 @@
-name: Create library release archives, create a GH release and publish PyPI wheel and sdist on tag in main branch
+name: Create and release commoncode wheels on GitHub and Pypi
 
 
 # This is executed automatically on a tag in the main branch

diff --git a/.github/workflows/licensedcode-data-index-release.yml b/.github/workflows/licensedcode-data-index-release.yml
@@ -1,4 +1,4 @@
-name: Create library release archives, create a GH release and publish PyPI wheel and sdist on tag in main branch
+name: Create and release licensedcode index & data wheels on GitHub and Pypi
 
 
 # This is executed automatically on a tag in the main branch

diff --git a/AUTHORS.rst b/AUTHORS.rst
@@ -27,6 +27,7 @@ The following organizations or individuals have contributed to ScanCode:
 - Daniel Eder @daniel-eder
 - Dan Kegel @dankegel
 - Dennis Clark @DennisClark
+- Diana Galeana @diana-galeana
 - Divyansh Sharma @Divyansh2512
 - Duncan Howe @Duncan-Howe
 - Felix Kauselmann @selmf
@@ -61,6 +62,7 @@ The following organizations or individuals have contributed to ScanCode:
 - Nisha Kumar @nishakm
 - Nishchith Shetty @inishchith
 - Nitish Sharma @nitish81299
+- Octavio Valdivia Mendoza @OctavioValdiviaMendoza
 - Paul Gier @pgier
 - Philippe Ombredanne @pombredanne
 - Pi Delport @PiDelport

diff --git a/CHANGELOG.rst b/CHANGELOG.rst
@@ -8,6 +8,9 @@ Next release
   ``licensedcode-data``.
   https://github.com/aboutcode-org/scancode-toolkit/pull/5056
 
+- Add a file-level scan plugin for compiled Linux Kernel Module (``.ko``)
+  files that extracts metadata from the ELF ``.modinfo`` section.
+
 v33.0.0rc1 - 2026-05-14
 ------------------------
 

diff --git a/azure-pipelines.yml b/azure-pipelines.yml
@@ -111,8 +111,8 @@ jobs:
               # and we use the special --test-suite=plugins marker for these
               # tests
               additional_license_combined: |
-                venv/bin/pip install tests/licensedcode/data/additional_licenses/additional_plugin_1/
-                venv/bin/pip install tests/licensedcode/data/additional_licenses/additional_plugin_2/
+                venv/bin/pip install --no-deps tests/licensedcode/data/additional_licenses/additional_plugin_1/
+                venv/bin/pip install --no-deps tests/licensedcode/data/additional_licenses/additional_plugin_2/
                 venv/bin/scancode-reindex-licenses \
                   --additional-directory tests/licensedcode/data/additional_licenses/additional_dir/
                 venv/bin/pytest -vvs --test-suite=plugins \
@@ -183,6 +183,20 @@ jobs:
                   venv/bin/scancode -i --verbose samples/ -n3 --json foo.json;
                  done
 
+################################################################################
+# Tests with released commoncode instead of local editable commoncode
+################################################################################
+
+    - template: etc/ci/azure-posix.yml
+      parameters:
+          job_name: ubuntu_test_released_commocode
+          image_name: ubuntu-22.04
+          python_versions: ['3.14']
+          python_architecture: x64
+          test_suites:
+              all:
+                venv/bin/pip uninstall -y commoncode && venv/bin/pip install commoncode && venv/bin/pytest -n 2 -vvs tests/scancode/test_cli.py --reruns 2
+
 
 ################################################################################
 # Tests using a plain pip install to get the latest of all wheels

diff --git a/commoncode-CHANGELOG.rst b/commoncode-CHANGELOG.rst
@@ -1,6 +1,29 @@
 Release notes
 =============
 
+Version 32.5.2 - (2026-06-11)
+-----------------------------
+
+- Bump version properly.
+
+Version 32.5.1 - (2026-06-11)
+-----------------------------
+
+- Minor fix in pyproject.toml to release wheels
+  to pypi properly.
+
+Version 32.5.0 - (2026-06-11)
+-----------------------------
+
+- Merge commoncode back into scancode-toolkit
+  https://github.com/aboutcode-org/scancode-toolkit/pull/5116
+
+- Add support to create codebase from multiple input paths by
+  starting codebase walk from these inputs and then ignoring
+  based on path patterns. Improves codebase and resource
+  collection and creation performance for multi-path scan inputs
+  https://github.com/aboutcode-org/scancode-toolkit/pull/5055
+
 Version 32.4.2 - (2025-01-08)
 -----------------------------
 

diff --git a/configure b/configure
@@ -256,6 +256,15 @@ install_packages() {
         $1
 }
 
+install_packages_with_local() {
+    # commoncode is present as dependencies of dependencies and so
+    # we need to install commoncode from local source first so this
+    # is tested and not the released commoncode
+    "$CFG_BIN_DIR/flot" --pyproject pyproject-commoncode.toml
+    "$CFG_BIN_DIR/pip" install ./dist/commoncode*.whl
+    install_packages "$CFG_REQUIREMENTS"
+}
+
 
 ################################
 cli_help() {
@@ -313,7 +322,7 @@ PIP_EXTRA_ARGS="$PIP_EXTRA_ARGS"
 find_python
 create_virtualenv "$VIRTUALENV_DIR"
 install_packages "$FLOT_REQUIREMENTS"
-install_packages "$CFG_REQUIREMENTS"
+install_packages_with_local
 . "$CFG_BIN_DIR/activate"
 "$CFG_BIN_DIR/scancode-train-gibberish-model"
 

diff --git a/configure.bat b/configure.bat
@@ -162,6 +162,9 @@ if %ERRORLEVEL% neq 0 (
     %PIP_EXTRA_ARGS% ^
     %FLOT_REQUIREMENTS%
 
+"%CFG_BIN_DIR%\flot" --pyproject pyproject-commoncode.toml
+"%CFG_BIN_DIR%\pip" install --force-reinstall ./dist/commoncode-32.5.2-py3-none-any.whl
+
 "%CFG_BIN_DIR%\pip" install ^
     --upgrade ^
     %CFG_QUIET% ^

diff --git a/docs/source/reference/scancode-cli/cli-core-options.rst b/docs/source/reference/scancode-cli/cli-core-options.rst
@@ -145,3 +145,98 @@ Comparing progress message options
 
     This would scan the file ``samples/levelone/leveltwo/file`` but ignore
     ``samples/levelone/leveltwo/levelthree/file``
+
+----
+
+.. _cli-ignore-option:
+
+``--ignore <pattern>``
+----------------------
+
+    In a scan, all files inside the directory specified as an input argument is scanned. But if
+    there are some files which you don't want to scan, the ``--ignore`` option can be used to do
+    the same.
+
+    **Example**
+
+    .. code-block:: shell
+
+        scancode --ignore "*.java" samples samples.json
+
+    Here, ScanCode ignores files ending with `.java`, and continues with other files as usual.
+
+    More information on :ref:`glob-pattern-matching`.
+
+----
+
+.. _cli-config-option:
+
+``--config-file <path>``
+------------------------
+
+    Path patterns which should be ignored in the scan can also be provided
+    through a configuration file.
+
+    **Example**
+
+    .. code-block:: shell
+
+        scancode --config-file scancode-config.yaml samples samples.json
+
+    .. code-block:: yaml
+
+        ignored_patterns:
+        - '*.java'
+        - '*/licenses/*'
+
+    Here, ScanCode ignores files ending with `.java` and the `licenses` directory,
+    and continues with other files as usual.
+
+    This is also compatible with the `scancode.io configuration file <https://scancodeio.readthedocs.io/en/latest/project-configuration.html#ignored-patterns>`_.
+
+----
+
+.. _glob-pattern-matching:
+
+Glob Pattern Matching
+---------------------
+
+    All the pre-scan options use pattern matching, so the basics of Glob Pattern Matching is
+    discussed briefly below.
+
+    Glob pattern matching is useful for matching a group of files, by using patterns in their
+    names. Then using these patterns, files are grouped and treated differently as required.
+
+    Here are some rules from the `Linux Manual <http://man7.org/linux/man-pages/man7/glob.7.html>`_
+    on glob patterns. Refer the same for more detailed information.
+
+    A string is a wildcard pattern if it contains one of the characters '?', '*' or '['.  Globbing
+    is the operation that expands a wildcard pattern into the list of pathnames matching the
+    pattern. Matching is defined by:
+
+    - A '?' (not between brackets) matches any single character.
+
+    - A '*' (not between brackets) matches any string, including the empty string.
+
+    - An expression "[...]" where the first character after the leading '[' is not an '!' matches a
+      single character, namely any of the characters enclosed by the brackets.
+
+    - There is one special convention: two characters separated by '-' denote a range.
+
+    - An expression "[!...]" matches a single character, namely any character that is not matched
+      by the expression obtained by removing the first '!' from it.
+
+    - A '/' in a pathname cannot be matched by a '?' or '*' wildcard, or by a range like "[.-0]".
+
+    Note that wildcard patterns are not regular expressions, although they are a bit similar.
+
+    For more information on glob pattern matching refer these resources:
+
+        - `Linux Manual <http://man7.org/linux/man-pages/man7/glob.7.html>`_
+        - `Wildcard Match Documentation <https://facelessuser.github.io/wcmatch/glob/>`_.
+
+    You can also import these Python Libraries to practice UNIX style pattern matching:
+
+    - `fnmatch <https://docs.python.org/2/library/fnmatch.html>`_ for File Name matching
+    - `glob <https://docs.python.org/2/library/glob.html#module-glob>`_ for File Path matching
+
diff --git a/docs/source/reference/scancode-cli/cli-help-text-options.rst b/docs/source/reference/scancode-cli/cli-help-text-options.rst
@@ -125,8 +125,6 @@ The following help text is displayed for ScanCode version 32.0.0:
                     such that all paths have a common root directory.
 
     pre-scan:
-      --ignore <pattern>         Ignore files matching <pattern>.
-      --include <pattern>        Include files matching <pattern>.
       --classify                 Classify files with flags indicating whether the file is a
                                  legal, readme, test or similar file.
       --facet <facet>=<pattern>  Add the <facet> to files with a path matching
@@ -169,11 +167,13 @@ The following help text is displayed for ScanCode version 32.0.0:
                                at the file and directory level.
 
     core:
+      --ignore <pattern>      Ignore files matching <pattern>.
       --timeout <seconds>     Stop an unfinished file scan after a timeout in
                               seconds. [default: 120 seconds]
       -n, --processes INT     Set the number of parallel processes to use. Disable
                               parallel processing if 0. Also disable threading if
                               -1. [default: (number of CPUs)-1]
+      -c, --config-file FILENAME  Path to the configuration file.
       -q, --quiet             Do not print summary or progress.
       -v, --verbose           Print progress as file-by-file path instead of a
                               progress bar. Print verbose scan counters.
@@ -512,7 +512,7 @@ for ScanCode Version 32.0.0.
   --------------------------------------------
   Plugin: scancode_post_scan:classify  class: summarycode.classify_plugin:FileClassifier
     codebase_attributes:
-    resource_attributes: is_legal, is_manifest, is_readme, is_top_level, is_key_file
+    resource_attributes: is_legal, is_manifest, is_readme, is_top_level, is_key_file, is_community
     sort_order: 4
     required_plugins:
     options:
@@ -690,6 +690,19 @@ for ScanCode Version 32.0.0.
       - packages
 
 
+  --------------------------------------------
+  Plugin: scancode_post_scan:todo  class: summarycode.todo:AmbiguousDetectionsToDoPlugin
+    codebase_attributes: todo
+    resource_attributes: for_todo
+    sort_order: 3
+    required_plugins:
+    options:
+      help_group: post-scan, name: todo: --todo
+        help: Summarize scans by providing all ambiguous detections which are todo items and needs manual review.
+    doc:
+      Summarize a scan by compiling review items of ambiguous detections.
+
+
   --------------------------------------------
   Plugin: scancode_pre_scan:facet  class: summarycode.facet:AddFacet
     codebase_attributes:
@@ -705,21 +718,6 @@ for ScanCode Version 32.0.0.
       test vs. data, etc.
 
 
-  --------------------------------------------
-  Plugin: scancode_pre_scan:ignore  class: scancode.plugin_ignore:ProcessIgnore
-    codebase_attributes:
-    resource_attributes:
-    sort_order: 100
-    required_plugins:
-    options:
-      help_group: pre-scan, name: ignore: --ignore
-        help: Ignore files matching <pattern>.
-      help_group: pre-scan, name: include: --include
-        help: Include files matching <pattern>.
-    doc:
-      Include or ignore files matching patterns.
-
-
   --------------------------------------------
   Plugin: scancode_scan:copyrights  class: cluecode.plugin_copyright:CopyrightScanner
     codebase_attributes:
@@ -761,10 +759,23 @@ for ScanCode Version 32.0.0.
       Tag a file as generated.
 
 
+  --------------------------------------------
+  Plugin: scancode_scan:go_symbol  class: go_inspector.plugin:GoSymbolScannerPlugin
+    codebase_attributes:
+    resource_attributes: go_symbols
+    sort_order: 100
+    required_plugins:
+    options:
+      help_group: primary scans, name: go_symbol: --go-symbol
+        help: Collect Go symbols.
+    doc:
+      Scan a Go binary for symbols using GoReSym.
+
+
   --------------------------------------------
   Plugin: scancode_scan:info  class: scancode.plugin_info:InfoScanner
     codebase_attributes:
-    resource_attributes: date, sha1, md5, sha256, mime_type, file_type, programming_language, is_binary, is_text, is_archive, is_media, is_source, is_script
+    resource_attributes: date, sha1, md5, sha256, sha1_git, mime_type, file_type, programming_language, is_binary, is_text, is_archive, is_media, is_source, is_script
     sort_order: 0
     required_plugins:
     options:
@@ -779,7 +790,7 @@ for ScanCode Version 32.0.0.
   Plugin: scancode_scan:licenses  class: licensedcode.plugin_license:LicenseScanner
     codebase_attributes: license_detections
     resource_attributes: detected_license_expression, detected_license_expression_spdx, license_detections, license_clues, percentage_of_license_text
-    sort_order: 4
+    sort_order: 5
     required_plugins:
     options:
       help_group: primary scans, name: license: -l, --license
@@ -804,13 +815,15 @@ for ScanCode Version 32.0.0.
   Plugin: scancode_scan:packages  class: packagedcode.plugin_package:PackageScanner
     codebase_attributes: packages, dependencies
     resource_attributes: package_data, for_packages
-    sort_order: 3
+    sort_order: 4
     required_plugins: scan:licenses
     options:
       help_group: primary scans, name: package: -p, --package
         help: Scan <input> for application package and dependency manifests, lockfiles and related data.
       help_group: primary scans, name: system_package: --system-package
         help: Scan <input> for installed system package databases.
+      help_group: primary scans, name: package_in_compiled: --package-in-compiled
+        help: Scan <input> for package and dependency related data in compiled binaries. Currently supported compiled binaries: Go, Rust.
       help_group: primary scans, name: package_only: --package-only
         help: Scan for system and application package data and skip license/copyright detection and top-level package creation.
       help_group: documentation, name: list_packages: --list-packages
@@ -821,6 +834,19 @@ for ScanCode Version 32.0.0.
       level.
 
 
+  --------------------------------------------
+  Plugin: scancode_scan:rust_symbol  class: rust_inspector.plugin:RustSymbolScannerPlugin
+    codebase_attributes:
+    resource_attributes: rust_symbols
+    sort_order: 100
+    required_plugins:
+    options:
+      help_group: primary scans, name: rust_symbol: --rust-symbol
+        help: Collect Rust symbols from rust binaries.
+    doc:
+      Scan a Rust binary for symbols using blint, lief and symbolic.
+
+
   --------------------------------------------
   Plugin: scancode_scan:urls  class: cluecode.plugin_url:UrlScanner
     codebase_attributes: