Add compact JSON output for scancode

CHANGELOG.rst

@@ -26,6 +26,9 @@ Next release
   ``ValueError: did not find any 'pre_scan' hooks``.
   https://github.com/aboutcode-org/scancode-toolkit/issues/5363
 
+- Add a new CLI option for a compact JSON output with ``--compact-json``
+  https://github.com/aboutcode-org/scancode-toolkit/issues/4555
+
 v33.0.0rc1 - 2026-05-14
 ------------------------
 

configure

@@ -161,7 +161,7 @@ FLOT_REQUIREMENTS="etc/thirdparty/flot-0.7.3-py3-none-any.whl"
 VIRTUALENV_DIR=venv
 
 # Cleanable files and directories to delete with the --clean option
-CLEANABLE="build dist venv .cache .eggs *.egg-info docs/_build/ pip-selfcheck.json"
+CLEANABLE="build tmp dist venv .cache .eggs *.egg-info docs/_build/ pip-selfcheck.json .pytest_cache .ruff_cache src/scancode_toolkit.egg-info"
 
 
 # the URL to download virtualenv.pyz if needed

docs/source/reference/scancode-cli/cli-output-format-options.rst

@@ -221,6 +221,89 @@ Quick reference
 
 ----
 
+.. _cli-compact-json-option:
+
+``--compact-json FILE``
+-----------------------
+
+    ``--compact-json`` is an output format option which outputs the resusts in the most
+    compact manner possible. To make the output results compact:
+
+    * duplicate data is removed so we only have unique detection results only once
+    * only the most important data attributes are kept and the rest is removed
+    * longer text fields are either removed or CLI options adding longer/diangostic text
+      fields are made incompatible with the compact option
+    * empty data attributes are removed
+
+    The following code performs a scan on the samples directory, and publishes the results in
+    ``compact-json`` format
+
+    .. code-block:: shell
+
+        scancode -clpieu --compact-json output.json samples
+
+    **Example**
+
+    .. code-block:: json
+
+        {
+          "path": "samples/JGroups/LICENSE",
+          "type": "file",
+          "size": 26430,
+          "date": "2022-04-20",
+          "sha1": "e60c2e780886f95df9c9ee36992b8edabec00bcc",
+          "md5": "7fbc338309ac38fefcd64b04bb903e34",
+          "sha256": "a190dc9c8043755d90f8b0a75fa66b9e42d4af4c980bf5ddc633f0124db3cee7",
+          "sha1_git": "b1e3f5a2638797271cbc9b91b856c05ed6942c8f",
+          "mime_type": "text/plain",
+          "file_type": "ASCII text",
+          "is_text": true,
+          "detected_license_expression_spdx": "LGPL-2.1-only",
+          "percentage_of_license_text": 100.0,
+          "copyrights": [
+            {
+              "copyright": "Copyright (c) 1991, 1999 Free Software Foundation, Inc.",
+              "start_line": 4,
+              "end_line": 4
+            },
+            {
+              "copyright": "copyrighted by the Free Software Foundation",
+              "start_line": 429,
+              "end_line": 429
+            }
+          ],
+          "holders": [
+            {
+              "holder": "Free Software Foundation, Inc.",
+              "start_line": 4,
+              "end_line": 4
+            },
+            {
+              "holder": "the Free Software Foundation",
+              "start_line": 429,
+              "end_line": 429
+            }
+          ],
+          "license_detections": [
+            {
+              "identifier": "lgpl_2_1-64dbac63-7b61-7151-023f-321235aeef62"
+            }
+          ]
+        },
+        {
+          "path": "samples/JGroups/licenses",
+          "type": "directory",
+          "files_count": 5,
+          "size_count": 54552
+        }
+
+
+    This is the recommended output option if you want the output filesize to be as minimal as possible
+    while retaining the most important information in ScanCode-Toolkit.
+
+
+---
+
 .. _cli-json-lines-option:
 
 ``--json-lines FILE``

docs/source/rst-snippets/cli-output-format-options.rst

@@ -1,7 +1,14 @@
 **Output formats**
 ------------------
 
---json FILE             Write scan output as compact JSON to FILE.
+--json FILE             Write scan output as standard JSON to FILE.
+
+--compact-json FILE     Write scan output as compact JSON to FILE.
+                        This output format only keeps the information
+                        in scans which are most important parts,
+                        removes any redundant information or empty
+                        attributes to make the output as compact as
+                        possible.
 
 --json-pp FILE          Write scan output as pretty-printed JSON to
                         FILE. This is one of the recommended output

docs/source/rst-snippets/cli-output-to-stdout.rst

@@ -2,8 +2,8 @@ Print to ``stdout`` / terminal
 ------------------------------
 
 If you want to format the output in JSON and print it at stdout, you can replace the JSON filename
-with a "-", like ``--json-pp -`` instead of ``--json-pp output.json``.
+with a "-", like ``--compact-json -`` instead of ``--compact-json output.json``.
 
 The following command will output the scan results in JSON format to ``stdout`` (in the terminal)::
 
-    ./scancode -clpieu --json-pp - samples/
+    ./scancode -clpieu --compact-json - samples/

docs/source/tutorials/configuring-scan-output-formats.rst

@@ -15,6 +15,8 @@ The following commands will output scan results in a formatted json file:
 
 * ``scancode --json /path/to/output.json /path/to/target/dir``
 
+* ``scancode --compact-json /path/to/output.json /path/to/target/dir``
+
 * ``scancode --json-pp /path/to/output.json /path/to/target/dir``
 
 * ``scancode --json-lines /path/to/output.json /path/to/target/dir``

pyproject-scancode-toolkit-mini.toml

@@ -306,7 +306,8 @@ ignore-copyrights = "cluecode.plugin_ignore_copyrights:IgnoreCopyrights"
 [project.entry-points.scancode_output]
 html = "formattedcode.output_html:HtmlOutput"
 html-app = "formattedcode.output_html:HtmlAppOutput"
-json = "formattedcode.output_json:JsonCompactOutput"
+json = "formattedcode.output_json:JsonOutput"
+compact-json = "formattedcode.output_json:JsonCompactOutput"
 json-pp = "formattedcode.output_json:JsonPrettyOutput"
 spdx-tv = "formattedcode.output_spdx:SpdxTvOutput"
 spdx-rdf = "formattedcode.output_spdx:SpdxRdfOutput"

pyproject-scancode-toolkit.toml

@@ -307,7 +307,8 @@ ignore-copyrights = "cluecode.plugin_ignore_copyrights:IgnoreCopyrights"
 [project.entry-points.scancode_output]
 html = "formattedcode.output_html:HtmlOutput"
 html-app = "formattedcode.output_html:HtmlAppOutput"
-json = "formattedcode.output_json:JsonCompactOutput"
+json = "formattedcode.output_json:JsonOutput"
+compact-json = "formattedcode.output_json:JsonCompactOutput"
 json-pp = "formattedcode.output_json:JsonPrettyOutput"
 spdx-tv = "formattedcode.output_spdx:SpdxTvOutput"
 spdx-rdf = "formattedcode.output_spdx:SpdxRdfOutput"

pyproject.toml

@@ -311,7 +311,8 @@ ignore-copyrights = "cluecode.plugin_ignore_copyrights:IgnoreCopyrights"
 [project.entry-points.scancode_output]
 html = "formattedcode.output_html:HtmlOutput"
 html-app = "formattedcode.output_html:HtmlAppOutput"
-json = "formattedcode.output_json:JsonCompactOutput"
+json = "formattedcode.output_json:JsonOutput"
+compact-json = "formattedcode.output_json:JsonCompactOutput"
 json-pp = "formattedcode.output_json:JsonPrettyOutput"
 spdx-tv = "formattedcode.output_spdx:SpdxTvOutput"
 spdx-rdf = "formattedcode.output_spdx:SpdxRdfOutput"