Merge branch 'master' into update_ciworkflow_ghidrathon

.github/workflows/changelog.yml

@@ -7,7 +7,8 @@ on:
   pull_request_target:
     types: [opened, edited, synchronize]
 
-permissions: read-all
+permissions:
+  pull-requests: write
 
 jobs:
   check_changelog:
@@ -29,14 +30,14 @@ jobs:
         echo $FILES | grep -qF 'CHANGELOG.md' || echo $PR_BODY | grep -qiF "$NO_CHANGELOG"
     - name: Reject pull request if no CHANGELOG update
       if: ${{ always() && steps.changelog_updated.outcome == 'failure' }}
-      uses: Ana06/automatic-pull-request-review@0cf4e8a17ba79344ed3fdd7fed6dd0311d08a9d4 # v0.1.0
+      uses: Ana06/automatic-pull-request-review@76aaf9b15b116a54e1da7a28a46f91fe089600bf # v0.2.0
       with:
         repo-token: ${{ secrets.GITHUB_TOKEN }}
         event: REQUEST_CHANGES
         body: "Please add bug fixes, new features, breaking changes and anything else you think is worthwhile mentioning to the `master (unreleased)` section of CHANGELOG.md. If no CHANGELOG update is needed add the following to the PR description: `${{ env.NO_CHANGELOG }}`"
         allow_duplicate: false
     - name: Dismiss previous review if CHANGELOG update
-      uses: Ana06/automatic-pull-request-review@0cf4e8a17ba79344ed3fdd7fed6dd0311d08a9d4 # v0.1.0
+      uses: Ana06/automatic-pull-request-review@76aaf9b15b116a54e1da7a28a46f91fe089600bf # v0.2.0
       with:
         repo-token: ${{ secrets.GITHUB_TOKEN }}
         event: DISMISS

CHANGELOG.md

@@ -4,6 +4,7 @@
 
 ### New Features
 
+- add function in capa/helpers to load plain and compressed JSON reports #1883 @Rohit1123
 
 ### Breaking Changes
 
@@ -27,6 +28,7 @@
 
 ### Development
 
+- ci: Fix PR review in the changelog check GH action #2004 @Ana06
 - ci: update github workflows to use latest version for depricated actions (checkout, setup-python, upload-artifact, download-artifact) #1967 @sjha2048
 - ci: use rules number badge stored in our bot gist and generated using `schneegans/dynamic-badges-action` #2001 capa-rules#882 @Ana06
 

capa/helpers.py

@@ -6,6 +6,7 @@
 #  is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and limitations under the License.
 import sys
+import gzip
 import json
 import inspect
 import logging
@@ -30,7 +31,7 @@
 
 EXTENSIONS_SHELLCODE_32 = ("sc32", "raw32")
 EXTENSIONS_SHELLCODE_64 = ("sc64", "raw64")
-EXTENSIONS_DYNAMIC = ("json", "json_")
+EXTENSIONS_DYNAMIC = ("json", "json_", "json.gz")
 EXTENSIONS_ELF = "elf_"
 EXTENSIONS_FREEZE = "frz"
 
@@ -70,9 +71,19 @@ def assert_never(value) -> NoReturn:
     assert False, f"Unhandled value: {value} ({type(value).__name__})"  # noqa: B011
 
 
-def get_format_from_report(sample: Path) -> str:
-    report = json.load(sample.open(encoding="utf-8"))
+def load_json_from_path(json_path: Path):
+    with gzip.open(json_path, "r") as compressed_report:
+        try:
+            report_json = compressed_report.read()
+        except gzip.BadGzipFile:
+            report = json.load(json_path.open(encoding="utf-8"))
+        else:
+            report = json.loads(report_json)
+    return report
 
+
+def get_format_from_report(sample: Path) -> str:
+    report = load_json_from_path(sample)
     if "CAPE" in report:
         return FORMAT_CAPE
 

capa/loader.py

@@ -6,7 +6,6 @@
 #  is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and limitations under the License.
 import sys
-import json
 import logging
 import datetime
 from typing import Set, Dict, List, Optional
@@ -180,7 +179,7 @@ def get_extractor(
     if backend == BACKEND_CAPE:
         import capa.features.extractors.cape.extractor
 
-        report = json.loads(input_path.read_text(encoding="utf-8"))
+        report = capa.helpers.load_json_from_path(input_path)
         return capa.features.extractors.cape.extractor.CapeExtractor.from_report(report)
 
     elif backend == BACKEND_DOTNET:
@@ -297,7 +296,7 @@ def get_file_extractors(input_file: Path, input_format: str) -> List[FeatureExtr
     elif input_format == FORMAT_CAPE:
         import capa.features.extractors.cape.extractor
 
-        report = json.loads(input_file.read_text(encoding="utf-8"))
+        report = capa.helpers.load_json_from_path(input_file)
         file_extractors.append(capa.features.extractors.cape.extractor.CapeExtractor.from_report(report))
 
     return file_extractors

tests/fixtures.py

@@ -191,14 +191,10 @@ def get_binja_extractor(path: Path):
 
 @lru_cache(maxsize=1)
 def get_cape_extractor(path):
-    import gzip
-    import json
-
+    from capa.helpers import load_json_from_path
     from capa.features.extractors.cape.extractor import CapeExtractor
 
-    with gzip.open(path, "r") as compressed_report:
-        report_json = compressed_report.read()
-        report = json.loads(report_json)
+    report = load_json_from_path(path)
 
     return CapeExtractor.from_report(report)
 

tests/test_main.py

@@ -356,3 +356,9 @@ def test_main_cape1(tmp_path):
     assert capa.main.main([str(path), "-j", "-r", str(rules)]) == 0
     assert capa.main.main([str(path), "-v", "-r", str(rules)]) == 0
     assert capa.main.main([str(path), "-vv", "-r", str(rules)]) == 0
+
+
+def test_main_cape_gzip():
+    # tests successful execution of .json.gz
+    path = str(fixtures.get_data_path_by_name("0000a657"))
+    assert capa.main.main([path]) == 0