Handle detection of SARIFs that have UTF-8 BOMs (#713)

Author: drdavella

src/codemodder/sarifs.py

@@ -23,7 +23,7 @@ def detect_sarif_tools(filenames: list[Path]) -> DefaultDict[str, list[str]]:
         ent.name: ent.load() for ent in entry_points().select(group="sarif_detectors")
     }
     for fname in filenames:
-        data = json.loads(fname.read_text())
+        data = json.loads(fname.read_text(encoding="utf-8-sig"))
         for name, det in detectors.items():
             # TODO: handle malformed sarif?
             for run in data["runs"]:

tests/test_sarif_processing.py

@@ -4,6 +4,7 @@
 
 import pytest
 
+from codemodder.sarifs import detect_sarif_tools
 from codemodder.semgrep import SemgrepResult, SemgrepResultSet
 
 
@@ -34,6 +35,17 @@ def test_extract_rule_id_semgrep(self):
         )
         assert rule_id == "secure-random"
 
+    def test_detect_sarif_with_bom_encoding(self, tmpdir):
+        sarif_file = Path("tests") / "samples" / "semgrep.sarif"
+        sarif_file_bom = tmpdir / "semgrep_bom.sarif"
+
+        with open(sarif_file_bom, "w") as f:
+            f.write("\ufeff")
+            f.write(sarif_file.read_text(encoding="utf-8"))
+
+        results = detect_sarif_tools([sarif_file_bom])
+        assert len(results) == 1
+
     @pytest.mark.parametrize("truncate", [True, False])
     def test_results_by_rule_id(self, truncate):
         sarif_file = Path("tests") / "samples" / "semgrep.sarif"