Fix issue #143 (#145)

* Implement changes from 5.0.x branch

* that's ruff

src/yadg/dgutils/dsutils.py

@@ -2,6 +2,9 @@
 import xarray as xr
 from xarray import Dataset
 from typing import Any
+import logging
+
+logger = logging.getLogger(__name__)
 
 
 def append_dicts(
@@ -37,19 +40,24 @@ def dicts_to_dataset(
     fulldate: bool = True,
 ) -> Dataset:
     darrs = {}
-    for k, v in data.items():
+    for key, val in data.items():
         attrs = {}
-        u = units.get(k, None)
+        u = units.get(key, None)
         if u is not None:
             attrs["units"] = u
-        if k == "uts":
+        if key == "uts":
             continue
-        darrs[k] = xr.DataArray(data=v, dims=["uts"], attrs=attrs)
-        if k in meta and darrs[k].dtype.kind in {"i", "u", "f", "c", "m", "M"}:
+        if "/" in key:
+            logger.warning(f"Replacing '/' for '_' in column {key!r}.")
+            k = key.replace("/", "_")
+        else:
+            k = key
+        darrs[k] = xr.DataArray(data=val, dims=["uts"], attrs=attrs)
+        if key in meta and darrs[k].dtype.kind in {"i", "u", "f", "c", "m", "M"}:
             err = f"{k}_std_err"
             darrs[k].attrs["ancillary_variables"] = err
             attrs["standard_name"] = f"{k} standard error"
-            darrs[err] = xr.DataArray(data=meta[k], dims=["uts"], attrs=attrs)
+            darrs[err] = xr.DataArray(data=meta[key], dims=["uts"], attrs=attrs)
     if "uts" in data:
         coords = dict(uts=data.pop("uts"))
     else:

src/yadg/extractors/basic/csv.py

@@ -138,11 +138,6 @@ def extract(
     assert len(lines) >= 2
     headers = [h.strip().strip(strip) for h in lines[0].split(parameters.sep)]
 
-    for hi, header in enumerate(headers):
-        if "/" in header:
-            logger.warning("Replacing '/' for '_' in header '%s'.", header)
-            headers[hi] = header.replace("/", "_")
-
     datecolumns, datefunc, fulldate = dgutils.infer_timestamp_from(
         headers=headers, spec=parameters.timestamp, timezone=timezone
     )

tests/test_basiccsv.py

@@ -280,3 +280,24 @@ def test_datagram_from_basiccsv(input, ts, datadir):
     print(f"{ret=}")
     standard_datagram_test(ret, ts)
     pars_datagram_test(ret, ts)
+
+
+def test_issue_143(datadir):
+    input = {
+        "case": "flow_data.csv",
+        "version": "4.2",
+        "parameters": {
+            "sep": ",",
+            "timestamp": {"time": {"index": 5}},
+            "units": {
+                "DryCal smL/min": "smL/min",
+                "DryCal Avg. smL/min": "smL/min",
+                "Temp. Deg C": "degC",
+                "Pressure mBar": "mbar",
+            },
+        },
+    }
+    ver = input.pop("version", "4.0")
+    ret = datagram_from_input(input, "basiccsv", datadir, version=ver)
+    print(f"{ret=}")
+    assert ret["0"]["DryCal smL_min"].attrs["units"] == "smL/min"

tests/test_basiccsv/flow_data.csv

@@ -0,0 +1,30 @@
+Sample,DryCal smL/min ,DryCal Avg. smL/min ,Temp. Deg C,Pressure mBar ,Time,
+1,14.5840,14.5950,24.3,971.000,12:45:33,
+2,14.5780,14.5930,24.5,971.000,12:46:46,
+3,14.5750,14.5910,24.5,971.000,12:47:58,
+4,14.5710,14.5890,24.7,971.000,12:49:11,
+5,14.5210,14.5830,24.8,971.000,12:50:23,
+6,14.5540,14.5800,24.9,971.000,12:51:35,
+7,14.5680,14.5800,25.0,971.000,12:52:48,
+8,14.5930,14.5800,25.0,971.000,12:54:00,
+9,14.6120,14.5830,25.1,971.000,12:55:12,
+10,14.6300,14.5860,25.2,971.000,12:56:25,
+11,14.6460,14.5890,25.3,971.000,12:57:37,
+12,14.6770,14.5940,25.4,971.000,12:58:50,
+13,14.7170,14.6000,25.4,971.000,13:00:02,
+14,14.8320,14.6120,25.5,971.000,13:01:14,
+15,14.8080,14.6210,25.5,971.000,13:02:26,
+16,14.7990,14.6290,25.6,971.000,13:03:39,
+17,14.6950,14.6320,25.6,971.000,13:04:52,
+18,14.6590,14.6330,25.7,970.000,13:06:04,
+19,14.7030,14.6360,25.7,971.000,13:07:16,
+20,14.7070,14.6390,25.8,971.000,13:08:29,
+21,14.8240,14.6460,25.8,971.000,13:09:41,
+22,14.8650,14.6540,25.8,971.000,13:10:53,
+23,14.8480,14.6600,25.9,971.000,13:12:06,
+24,14.7570,14.6640,25.9,971.000,13:13:18,
+25,14.6870,14.6640,26.0,970.000,13:14:31,
+26,14.7380,14.6670,26.0,971.000,13:15:43,
+27,14.8070,14.6710,26.0,971.000,13:16:55,
+28,14.8740,14.6770,26.0,970.000,13:18:07,
+29,14.8480,14.6820,26.1,971.000,13:19:20,