Merge pull request #4425 from aboutcode-org/add-git-sha1

Return `sha1_git` checksum for all files as info

Author: JonoYang

CHANGELOG.rst

@@ -46,6 +46,9 @@ v33.0.0 (next next, roadmap)
 - Update ABOUT files to adapt the ABOUT File Specification.
   See https://github.com/aboutcode-org/scancode-toolkit/issues/4181
 
+- Also return sha1_git checksums for each files with ``--info`` plugin.
+  https://github.com/aboutcode-org/scancode-toolkit/issues/624
+
 
 v32.3.3 - 2025-03-06
 --------------------

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

@@ -141,6 +141,7 @@ following options.
           "date": "2019-02-12",
           "sha1": "fca4540d490fff36bb90fd801cf9cd8fc695bb17",
           "md5": "a980b61c1e8be68d5cdb1236ba6b43e7",
+          "sha1_git": "d9a10c0d8e868ebf8da0b3dc95bb0be634c34bfe",
           "mime_type": "text/x-c++",
           "file_type": "C++ source, ASCII text",
           "programming_language": "C++",
@@ -481,6 +482,7 @@ Comparing Different ``json`` Output Formats
         - size,
         - sha1,
         - md5,
+        - sha1_git,
         - files_count,
         - mime_type,
         - file_type,

docs/source/cli-reference/scan-options-post.rst

@@ -1060,6 +1060,7 @@ To see all plugins available via command line help, use ``--plugins``.
             "sha1": null,
             "md5": null,
             "sha256": null,
+            "sha1_git": null,
             "mime_type": null,
             "file_type": null,
             "programming_language": null,

docs/source/cli-reference/synopsis.rst

@@ -156,6 +156,7 @@ A sample JSON output file structure will look like::
           "date": "2019-02-12",
           "sha1": "2e07e32c52d607204fad196052d70e3d18fb8636",
           "md5": "effc6856ef85a9250fb1a470792b3f38",
+          "sha1_git": "d9a10c0d8e868ebf8da0b3dc95bb0be634c34bfe",
           "mime_type": "text/plain",
           "file_type": "ASCII text",
           "programming_language": null,

src/scancode/api.py

@@ -330,10 +330,14 @@ def get_file_info(location, **kwargs):
     result['date'] = get_last_modified_date(location) or None
     result['size'] = getsize(location) or 0
 
-    sha1, md5, sha256 = multi_checksums(location, ('sha1', 'md5', 'sha256')).values()
+    sha1, md5, sha256, sha1_git = multi_checksums(
+        location=location,
+        checksum_names=('sha1', 'md5', 'sha256', 'sha1_git')
+    ).values()
     result['sha1'] = sha1
     result['md5'] = md5
     result['sha256'] = sha256
+    result['sha1_git'] = sha1_git
 
     collector = get_type(location)
     result['mime_type'] = collector.mimetype_file or None

src/scancode/plugin_info.py

@@ -27,6 +27,7 @@ class InfoScanner(ScanPlugin):
         ('sha1', attr.ib(default=None, repr=False)),
         ('md5', attr.ib(default=None, repr=False)),
         ('sha256', attr.ib(default=None, repr=False)),
+        ('sha1_git', attr.ib(default=None, repr=False)),
         ('mime_type', attr.ib(default=None, repr=False)),
         ('file_type', attr.ib(default=None, repr=False)),
         ('programming_language', attr.ib(default=None, repr=False)),

tests/cluecode/data/plugin_filter_clues/filtered-expected.json

@@ -34,6 +34,7 @@
       "sha1": "c4d6f133413f1ea9d3c436fb797f9060c8640c04",
       "md5": "55a970437979ffe95e7b8ee6e51abb0c",
       "sha256": "ebdef41bf0f5bd7d378e4f76052e02156ce1c80ce67f89209b018a3fca8a071c",
+      "sha1_git": "c6cc3f85376fd76bdebcc4fee6e9137e80bd8691",
       "mime_type": "text/plain",
       "file_type": "ASCII text",
       "programming_language": null,

tests/cluecode/data/plugin_filter_clues/filtered-expected2.json

@@ -34,6 +34,7 @@
       "sha1": "c43ffed01990c30300e07231790ace9f103ff7d7",
       "md5": "9946f7dcaf5066f2fb17e682e0326090",
       "sha256": "58416604a57e2e2625b802ac8c751c61763ae3d279c9c75d7c3bb55a3782cc6c",
+      "sha1_git": "9956de3f204ca2d5c46b77e70c4c6bf9509f6dd8",
       "mime_type": "text/plain",
       "file_type": "ASCII text",
       "programming_language": null,

tests/cluecode/data/plugin_filter_clues/filtered-expected3.json

@@ -34,6 +34,7 @@
       "sha1": "9db841f62fdb2372f5f474bb75366140a00c62ca",
       "md5": "3fdbe85d79aa58aaeab119505f2007b6",
       "sha256": "408dfe8f9a70ea7bc9feaa9f77fb731ada0c26dc39008fdc5ead52d0442c656f",
+      "sha1_git": "3ed0b925a62cbabad29cda7743c513d2ed557dc2",
       "mime_type": "text/plain",
       "file_type": "ASCII text",
       "programming_language": "verilog",

tests/cluecode/data/plugin_filter_clues/filtered-expected4.json

@@ -146,6 +146,7 @@
       "sha1": "8a2e40b4eb23cc05a0b78330d919a7ffacde7a9a",
       "md5": "d5d03e14130735213e0532277df33cab",
       "sha256": "e4bd79e88b577d66d351597c0d4114b9ee2e31f0544795e87a88ca1b0dd38383",
+      "sha1_git": "e7c0b65bcdb17888027d0b53a1f65ad61b238245",
       "mime_type": "text/plain",
       "file_type": "ASCII text",
       "programming_language": null,