fix: deduplicate time values in add_location instead of raising ValueError

Fixes #1478. EK80 data commonly has duplicate timestamps in Platform
time dimensions (e.g., from multiple NMEA sentences — GGA, GLL, RMC —
at the same timestamp). Previously add_location() raised a ValueError,
requiring manual deduplication before use.

Now duplicate time values are automatically removed (keeping the first
occurrence) with a UserWarning, and interpolation proceeds normally.

- loc_utils.py: check_loc_time_dim_duplicates returns deduplicated array
- api.py: use returned array for downstream interpolation
- test: updated to verify warning + successful location addition

Author: beatfactor

echopype/consolidate/api.py

@@ -316,8 +316,9 @@ def add_location(
             datagram_type=datagram_type,
         )
 
-        # Check if there are duplicates in time_dim_name for this NMEA subset
-        check_loc_time_dim_duplicates(loc_var, time_dim_name)
+        # Deduplicate time dimension if needed (e.g. multiple NMEA sentences
+        # at the same timestamp); required for downstream interpolation.
+        loc_var = check_loc_time_dim_duplicates(loc_var, time_dim_name)
 
         interp_ds[interp_loc_name] = align_to_ping_time(
             loc_var, time_dim_name, ds["ping_time"], "linear"

echopype/consolidate/loc_utils.py

@@ -1,3 +1,4 @@
+import warnings
 from typing import Union
 
 import numpy as np
@@ -107,13 +108,24 @@ def check_loc_vars_validity(
             logger.warning(output_message)
 
 
-def check_loc_time_dim_duplicates(da: xr.DataArray, time_dim_name: str) -> None:
-    """Check if there are duplicates in time_dim_name"""
-    if len(np.unique(da[time_dim_name].data)) != len(da[time_dim_name].data):
-        raise ValueError(
-            f'Data contains duplicate time values in time_dim_name "{time_dim_name}". '
-            "Downstream interpolation on the position variables requires unique time values."
+def check_loc_time_dim_duplicates(da: xr.DataArray, time_dim_name: str) -> xr.DataArray:
+    """Check for and remove duplicates in time_dim_name.
+
+    If duplicate time values are found, they are removed (keeping the first
+    occurrence) and a warning is logged. The deduplicated DataArray is returned.
+    """
+    time_vals = da[time_dim_name].data
+    if len(np.unique(time_vals)) != len(time_vals):
+        n_total = len(time_vals)
+        n_unique = len(np.unique(time_vals))
+        warnings.warn(
+            f'Dropped {n_total - n_unique} duplicate value(s) in "{time_dim_name}".',
+            UserWarning,
+            stacklevel=2,
         )
+        _, unique_idx = np.unique(time_vals, return_index=True)
+        da = da.isel({time_dim_name: np.sort(unique_idx)})
+    return da
 
 
 def sel_nmea(

echopype/tests/consolidate/test_add_location.py

@@ -234,10 +234,10 @@ def _tests(ds_test, location_type, nmea_sentence=None):
         ),
     ],
 )
-def test_add_location_time_duplicates_value_error(
+def test_add_location_time_duplicates_warning(
     ek80_path, raw_path, sonar_model, datagram_type, parse_idx, time_dim_name, compute_Sv_kwargs,
 ):   
-    """Tests for duplicate time value error in ``add_location``.""" 
+    """Tests that duplicate time values are handled with a warning, not an error.""" 
     # Open raw and compute the Sv dataset
     if parse_idx:
         ed = ep.open_raw(ek80_path / raw_path, include_idx=True, sonar_model=sonar_model)
@@ -255,16 +255,15 @@ def test_add_location_time_duplicates_value_error(
     vals[0] = vals[1]
     ed["Platform"] = ed["Platform"].assign_coords({time_dim_name: (da.dims, vals)})
 
-    # Check if the expected error is logged
-    with pytest.raises(ValueError) as exc_info:
-        # Run add location with duplicated time
-        ep.consolidate.add_location(ds=ds, echodata=ed, datagram_type=datagram_type)
+    # Should succeed with a warning instead of raising ValueError
+    with pytest.warns(UserWarning, match="Dropped 1 duplicate value"):
+        ds_loc = ep.consolidate.add_location(
+            ds=ds, echodata=ed, datagram_type=datagram_type
+        )
 
-    # Check if the specific error message is in the logs
-    assert (
-        f'Data contains duplicate time values in time_dim_name "{time_dim_name}". '
-        "Downstream interpolation on the position variables requires unique time values."
-    ) == str(exc_info.value)
+    # Verify location was successfully added
+    assert "latitude" in ds_loc
+    assert "longitude" in ds_loc
 
 
 @pytest.mark.integration