Add deduplication of overlapping Dropmate objects

Closes: #2

dropmate_py/cli.py

@@ -7,7 +7,7 @@
 from sco1_misc.prompts import prompt_for_dir, prompt_for_file
 
 from dropmate_py.audits import audit_pipeline
-from dropmate_py.parser import log_parse_pipeline
+from dropmate_py.parser import log_parse_pipeline, merge_dropmates
 
 MIN_ALT_LOSS = 200  # feet
 MIN_FIRMWARE = 5
@@ -75,17 +75,17 @@ def audit_bulk(
     log_files = list(log_dir.glob(log_pattern))
     print(f"Found {len(log_files)} log files to process.")
 
-    found_errs = []
-    for log_filepath in log_files:
-        conslidated_log = log_parse_pipeline(log_filepath)
-        found_errs.extend(
-            audit_pipeline(
-                consolidated_log=conslidated_log,
-                min_alt_loss_ft=min_alt_loss_ft,
-                min_firmware=min_firmware,
-                max_scanned_time_delta_sec=time_delta_minutes * 60,
-            )
-        )
+    compiled_logs = log_parse_pipeline(log_files[0])
+    for log_filepath in log_files[1:]:
+        compiled_logs.extend(log_parse_pipeline(log_filepath))
+
+    compiled_logs = merge_dropmates(compiled_logs)
+    found_errs = audit_pipeline(
+        consolidated_log=compiled_logs,
+        min_alt_loss_ft=min_alt_loss_ft,
+        min_firmware=min_firmware,
+        max_scanned_time_delta_sec=time_delta_minutes * 60,
+    )
 
     print(f"Found {len(found_errs)} errors.")
     if found_errs:

dropmate_py/parser.py

@@ -171,7 +171,7 @@ def __str__(self) -> str:  # pragma: no cover
         return f"UID: {self.uid}, FW: {self.firmware_version}, {len(self.drops)} drops, Scanned: {scanned_pretty} UTC"  # noqa: E501
 
 
-def _group_by_uid(drop_logs: abc.Sequence[DropRecord]) -> list[Dropmate]:
+def _group_by_uid(drop_logs: abc.Collection[DropRecord]) -> list[Dropmate]:
     # Groupby assumes logs are sorted, so we need to sort them to avoid duplicate devices
     sorted_logs = sorted(drop_logs, key=operator.attrgetter("uid", "flight_index"))
     dropmates = []
@@ -213,3 +213,12 @@ def log_parse_pipeline(log_filepath: Path) -> list[Dropmate]:
     parsed_records = _parse_raw_log(log_lines)
 
     return _group_by_uid(parsed_records)
+
+
+def merge_dropmates(dropmates: abc.Sequence[Dropmate]) -> list[Dropmate]:
+    """Merge a collection of potentially overlapping `Dropmate` devices into a new list."""
+    all_drops = set()
+    for dropmate in dropmates:
+        all_drops.update(dropmate.drops)
+
+    return _group_by_uid(all_drops)

tests/test_log_objects.py

@@ -145,3 +145,15 @@ def test_file_parse_pipeline(tmp_path: Path) -> None:
     grouped_records = parser.log_parse_pipeline(log_file)
     assert len(grouped_records) == 3
     assert [rec.uid for rec in grouped_records] == ["A1", "A2", "A3"]
+
+
+def test_merge_dropomates() -> None:
+    faux_batch_dropmates = parser._group_by_uid(
+        parser._parse_raw_log(SAMPLE_CONSOLIDATED_LOG.splitlines())
+    )
+    faux_batch_dropmates.extend(
+        parser._group_by_uid(parser._parse_raw_log(SAMPLE_CONSOLIDATED_LOG.splitlines()))
+    )
+
+    merged = parser.merge_dropmates(faux_batch_dropmates)
+    assert len(merged) == 3