Potential update for all the `--scancode` options as SCTK's output is updated AND update gen with `--scancode` option
chinyeungli opened this issue · 1 comments
chinyeungli commented
Note that SCTK's output is updated in the development branch.
Current stable structure (version 31.2.4 ):
"files": [
{
"path": "clean-text-0.3.0-mod/cleantext/isc_lic.py",
"type": "file",
"name": "isc_lic.py",
"base_name": "isc_lic",
"extension": ".py",
"size": 9593,
"date": "2020-12-04",
"sha1": "ba25c99004d422e98c7f948ce6a7cf7914c69b23",
"md5": "b64befb0e9457e941e362bbb2955e5e2",
"sha256": "a089501312bc9caed493dd7cdb76f66757d92bab45c9b5861c627e2a20887573",
"mime_type": "text/plain",
"file_type": "Python script, UTF-8 Unicode text executable",
"programming_language": "Python",
"is_binary": false,
"is_text": true,
"is_archive": false,
"is_media": false,
"is_source": true,
"is_script": true,
"licenses": [
{
"key": "isc",
"score": 99.0,
"name": "ISC License",
"short_name": "ISC License",
"category": "Permissive",
"is_exception": false,
"owner": "ISC - Internet Systems Consortium",
"homepage_url": "https://www.isc.org/software/license",
"text_url": "http://fedoraproject.org/wiki/Licensing:MIT#Old_Style_with_legal_disclaimer_2",
"reference_url": "https://enterprise.dejacode.com/urn/urn:dje:license:isc",
"spdx_license_key": "ISC",
"spdx_url": "https://spdx.org/licenses/ISC",
"start_line": 1,
"end_line": 1,
"matched_rule": {
"identifier": "isc_22.RULE",
"license_expression": "isc",
"licenses": [
"isc"
],
"is_license_text": false,
"is_license_notice": false,
"is_license_reference": true,
"is_license_tag": false,
"matcher": "2-aho",
"rule_length": 2,
"matched_length": 2,
"match_coverage": 100.0,
"rule_relevance": 99.0
}
},
{
"key": "mit",
"score": 100.0,
"name": "MIT License",
"short_name": "MIT License",
"category": "Permissive",
"is_exception": false,
"owner": "MIT",
"homepage_url": "http://opensource.org/licenses/mit-license.php",
"text_url": "http://opensource.org/licenses/mit-license.php",
"reference_url": "https://enterprise.dejacode.com/urn/urn:dje:license:mit",
"spdx_license_key": "MIT",
"spdx_url": "https://spdx.org/licenses/MIT",
"start_line": 5,
"end_line": 15,
"matched_rule": {
"identifier": "mit.LICENSE",
"license_expression": "mit",
"licenses": [
"mit"
],
"is_license_text": true,
"is_license_notice": false,
"is_license_reference": false,
"is_license_tag": false,
"matcher": "2-aho",
"rule_length": 112,
"matched_length": 112,
"match_coverage": 100.0,
"rule_relevance": 100
}
}
],
"license_expressions": [
"isc",
"mit"
],
"percentage_of_license_text": 0.24,
"copyrights": [],
"holders": [],
"authors": [],
"packages": [],
"emails": [],
"urls": [
{
"url": "http://ftfy.readthedocs.org/",
"start_line": 43,
"end_line": 43
}
],
"files_count": 0,
"dirs_count": 0,
"size_count": 0,
"scan_errors": []
}
]
Development branch structure:
"files": [
{
"path": "js-yaml-master/dist/js-yaml.js",
"type": "file",
"package_data": [],
"for_packages": [
"pkg:npm/js-yaml@4.1.0?uuid=ad9a873f-b200-48f1-b295-e3fa877f87d1"
],
"detected_license_expression": "mit",
"detected_license_expression_spdx": "MIT",
"license_detections": [
{
"license_expression": "mit",
"detection_log": [
"not-combined"
],
"matches": [
{
"score": 100.0,
"start_line": 2,
"end_line": 2,
"matched_length": 2,
"match_coverage": 100.0,
"matcher": "2-aho",
"license_expression": "mit",
"rule_identifier": "mit_30.RULE",
"rule_url": "https://github.com/nexB/scancode-toolkit/tree/develop/src/licensedcode/data/rules/mit_30.RULE"
}
]
}
],
"license_clues": [],
"percentage_of_license_text": 0.02,
"for_license_detections": [
"mit-d023e558-35f1-ef53-5625-5f585054dde4"
],
"copyrights": [],
"holders": [],
"authors": [],
"emails": [],
"urls": [
{
"url": "https://github.com/nodeca/js-yaml",
"start_line": 2,
"end_line": 2
},
{
"url": "http://stackoverflow.com/questions/8458984",
"start_line": 75,
"end_line": 75
},
{
"url": "https://en.wikipedia.org/wiki/UTF-16#Code_points_U.2B010000_to_U.2B10FFFF",
"start_line": 1212,
"end_line": 1212
},
{
"url": "http://www.yaml.org/spec/1.2/spec.html#id2799784",
"start_line": 2567,
"end_line": 2567
},
{
"url": "https://mathiasbynens.be/notes/javascript-encoding#surrogate-formulae",
"start_line": 3118,
"end_line": 3118
}
],
"scan_errors": []
},
{
"path": "js-yaml-master/dist/js-yaml.min.js",
"type": "file",
"package_data": [],
"for_packages": [
"pkg:npm/js-yaml@4.1.0?uuid=ad9a873f-b200-48f1-b295-e3fa877f87d1"
],
"detected_license_expression": "mit",
"detected_license_expression_spdx": "MIT",
"license_detections": [
{
"license_expression": "mit",
"detection_log": [
"not-combined"
],
"matches": [
{
"score": 100.0,
"start_line": 1,
"end_line": 1,
"matched_length": 2,
"match_coverage": 100.0,
"matcher": "2-aho",
"license_expression": "mit",
"rule_identifier": "mit_30.RULE",
"rule_url": "https://github.com/nexB/scancode-toolkit/tree/develop/src/licensedcode/data/rules/mit_30.RULE"
}
]
}
],
"license_clues": [],
"percentage_of_license_text": 0.02,
"for_license_detections": [
"mit-d023e558-35f1-ef53-5625-5f585054dde4"
],
"copyrights": [],
"holders": [],
"authors": [],
"emails": [],
"urls": [
{
"url": "https://github.com/nodeca/js-yaml",
"start_line": 1,
"end_line": 1
}
],
"scan_errors": []
},
If the changes are applied, we need to update the code to work with the latest changes.
chinyeungli commented
I tried to run gen with the latest sctk input and the result doesn't look nice.
For example,
about_resource: deflate.c
name: deflate.c
type: file
base_name: deflate
extension: .c
size: 71476
date: '2023-07-19'
sha1: 7b4ace6d698c5dbbfb9a8f047f63228ca54d2e77
md5: cd7826278ce9d9d9ed5abdefef50c3e2
sha256: 565e68ddfff5af8efd55f71e122b860ad11527a7d9de40a76af2b16afef24cc0
mime_type: text/x-c
file_type: C source, ASCII text
programming_language: C
is_text: True
is_source: True
detected_license_expression: zlib
detected_license_expression_spdx: Zlib
license_detections: '[{''license_expression'': ''zlib'', ''matches'': [{''score'': 100.0, ''start_line'':
3, ''end_line'': 3, ''matched_length'': 12, ''match_coverage'': 100.0, ''matcher'': ''2-aho'',
''license_expression'': ''zlib'', ''rule_identifier'': ''zlib_5.RULE'', ''rule_relevance'':
100, ''rule_url'': ''https://github.com/nexB/scancode-toolkit/tree/develop/src/licensedcode/data/rules/zlib_5.RULE''},
{''score'': 100.0, ''start_line'': 6, ''end_line'': 23, ''matched_length'': 144, ''match_coverage'':
100.0, ''matcher'': ''2-aho'', ''license_expression'': ''zlib'', ''rule_identifier'': ''zlib_17.RULE'',
''rule_relevance'': 100, ''rule_url'': ''https://github.com/nexB/scancode-toolkit/tree/develop/src/licensedcode/data/rules/zlib_17.RULE''}],
''identifier'': ''zlib-663c0d51-510f-fca6-b163-671ecb188ff9'', ''detection_log'': [''unknown-reference-to-local-file'']}]'
percentage_of_license_text: '0.13'
copyrights: '[{''copyright'': ''Copyright (c) 1995-2013 Jean-loup Gailly and Mark Adler'', ''start_line'':
2, ''end_line'': 2}, {''copyright'': ''Copyright 1995-2013 Jean-loup Gailly and Mark Adler'',
''start_line'': 55, ''end_line'': 55}]'
holders: '[{''holder'': ''Jean-loup Gailly and Mark Adler'', ''start_line'': 2, ''end_line'':
2}, {''holder'': ''Jean-loup Gailly and Mark Adler'', ''start_line'': 55, ''end_line'': 55}]'
authors: '[{''author'': ''Leonid Broukhis'', ''start_line'': 34, ''end_line'': 34}]'
urls: '[{''url'': ''http://tools.ietf.org/html/rfc1951'', ''start_line'': 40, ''end_line'':
40}]'
We need to update the tool to have it support.