refactor(datafile): ignore "text" parameter, add attributes from file

Author: mwtoews

autotest/test_binaryfile.py

@@ -3,6 +3,7 @@
 See also test_cellbudgetfile.py for similar tests.
 """
 
+import warnings
 from itertools import repeat
 
 import numpy as np
@@ -104,6 +105,8 @@ def test_headfile_build_index(example_data_path):
     assert hds.ncol == 20
     assert hds.nlay == 3
     assert not hasattr(hds, "nper")
+    assert hds.text == "head"
+    assert hds.text_bytes == b"HEAD".rjust(16)
     assert hds.totalbytes == 10_676_004
     assert len(hds.recordarray) == 3291
     assert type(hds.recordarray) == np.ndarray
@@ -150,7 +153,80 @@ def test_headfile_build_index(example_data_path):
     )
 
 
-def test_concentration_build_index(example_data_path):
+@pytest.mark.parametrize(
+    "pth, expected",
+    [
+        pytest.param(
+            "mf6-freyberg/freyberg.hds",
+            {
+                "precision": "double",
+                "nlay, nrow, ncol": (1, 40, 20),
+                "text": "head",
+                "text_bytes": b"HEAD".ljust(16),
+                "len(obj)": 1,
+            },
+            id="freyberg.hds",
+        ),
+        pytest.param(
+            "mf6/create_tests/test_transport/expected_output/gwt_mst03.ucn",
+            {
+                "precision": "double",
+                "nlay, nrow, ncol": (1, 1, 1),
+                "text": "concentration",
+                "text_bytes": b"CONCENTRATION".ljust(16),
+                "len(obj)": 28,
+            },
+            id="gwt_mst03.ucn",
+        ),
+        pytest.param(
+            "mfusg_test/03A_conduit_unconfined/output/ex3A.cln.hds",
+            {
+                "precision": "single",
+                "nlay, nrow, ncol": (1, 1, 2),
+                "text": "cln_heads",
+                "text_bytes": b"CLN HEADS".rjust(16),
+                "len(obj)": 1,
+            },
+            id="ex3A.cln.hds",
+        ),
+        pytest.param(
+            "mfusg_test/03A_conduit_unconfined/output/ex3A.ddn",
+            {
+                "precision": "single",
+                "nlay, nrow, ncol": (2, 100, 100),
+                "text": "drawdown",
+                "text_bytes": b"DRAWDOWN".rjust(16),
+                "len(obj)": 2,
+            },
+            id="ex3A.ddn",
+        ),
+    ],
+)
+def test_headfile_examples(example_data_path, pth, expected):
+    with HeadFile(example_data_path / pth) as obj:
+        assert obj.precision == expected["precision"]
+        assert (obj.nlay, obj.nrow, obj.ncol) == expected["nlay, nrow, ncol"]
+        assert obj.text == expected["text"]
+        assert obj.text_bytes == expected["text_bytes"]
+        assert len(obj) == expected["len(obj)"]
+
+
+@pytest.mark.parametrize(
+    "pth",
+    [
+        "mt3d_test/mf96mt3d/P01/case1b/MT3D001.UCN",
+        "unstructured/headu.githds",
+    ],
+)
+def test_not_headfile(example_data_path, pth):
+    # These examples pass get_headfile_precision, but are not HeadFiles
+    with pytest.raises(ValueError, match="cannot read file with HeadFile"):
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore")
+            HeadFile(example_data_path / pth)
+
+
+def test_ucnfile_build_index(example_data_path):
     # test low-level BinaryLayerFile._build_index() method with UCN file
     pth = example_data_path / "mt3d_test/mf2005mt3d/P07/MT3D001.UCN"
     with UcnFile(pth) as ucn:
@@ -159,6 +235,8 @@ def test_concentration_build_index(example_data_path):
     assert ucn.ncol == 21
     assert ucn.nlay == 8
     assert not hasattr(ucn, "nper")
+    assert ucn.text == "concentration"
+    assert ucn.text_bytes == b"CONCENTRATION".ljust(16)
     assert ucn.totalbytes == 10_432
     assert len(ucn.recordarray) == 8
     assert type(ucn.recordarray) == np.ndarray
@@ -296,6 +374,8 @@ def test_headu_file_data(function_tmpdir, example_data_path):
     headobj = HeadUFile(fname)
     assert isinstance(headobj, HeadUFile)
     assert headobj.nlay == 3
+    assert headobj.text == "headu"
+    assert headobj.text_bytes == b"HEADU".rjust(16)
 
     # ensure recordarray is has correct data
     ra = headobj.recordarray

autotest/test_formattedfile.py

@@ -21,6 +21,7 @@ def test_headfile_build_index(example_data_path):
     assert hds.ncol == 10
     assert hds.nlay == 1
     assert not hasattr(hds, "nper")
+    assert hds.text == "head"
     assert hds.totalbytes == 1613
     assert len(hds.recordarray) == 1
     assert type(hds.recordarray) == np.ndarray

flopy/export/utils.py

@@ -179,7 +179,7 @@ def _add_output_nc_variable(
                     else:
                         a = out_obj.get_data(totim=t)
                 except Exception as e:
-                    nme = var_name + text.decode().strip().lower()
+                    nme = var_name + text
                     estr = f"error getting data for {nme} at time {t}:{e!s}"
                     if logger:
                         logger.warn(estr)
@@ -191,7 +191,7 @@ def _add_output_nc_variable(
                 try:
                     array[i, :, :, :] = a.astype(np.float32)
                 except Exception as e:
-                    nme = var_name + text.decode().strip().lower()
+                    nme = var_name + text
                     estr = f"error assigning {nme} data to array for time {t}:{e!s}"
                     if logger:
                         logger.warn(estr)
@@ -209,7 +209,7 @@ def _add_output_nc_variable(
 
     if isinstance(nc, dict):
         if text:
-            var_name = text.decode().strip().lower()
+            var_name = text
         nc[var_name] = array
         return nc
 
@@ -219,7 +219,7 @@ def _add_output_nc_variable(
     precision_str = "f4"
 
     if text:
-        var_name = text.decode().strip().lower()
+        var_name = text
     attribs = {"long_name": var_name}
     attribs["coordinates"] = "time layer latitude longitude"
     attribs["min"] = mn
@@ -434,7 +434,7 @@ def output_helper(
                     times,
                     shape3d,
                     out_obj,
-                    "concentration",
+                    out_obj.text,
                     logger=logger,
                     mask_vals=mask_vals,
                     mask_array3d=mask_array3d,
@@ -446,7 +446,7 @@ def output_helper(
                     times,
                     shape3d,
                     out_obj,
-                    out_obj.text.decode(),
+                    out_obj.text,
                     logger=logger,
                     mask_vals=mask_vals,
                     mask_array3d=mask_array3d,

flopy/export/vtk.py

@@ -1228,14 +1228,12 @@ def add_heads(self, hds, kstpkper=None, masked_values=None):
         kstpkpers = hds.get_kstpkper()
         self._totim = {ki: time for (ki, time) in zip(kstpkpers, times)}
 
-        text = hds.text.decode()
-
         d = dict()
         for ki in kstpkper:
             d[ki] = hds.get_data(ki)
 
         self.__transient_output_data = False
-        self.add_transient_array(d, name=text, masked_values=masked_values)
+        self.add_transient_array(d, name=hds.text, masked_values=masked_values)
         self.__transient_output_data = True
 
     def add_cell_budget(

flopy/mf6/utils/binaryfile_utils.py

@@ -192,7 +192,7 @@ def _get_binary_file_object(self, path, bintype, key):
 
         elif bintype == "DDN":
             try:
-                return bf.HeadFile(path, text="drawdown", precision="double")
+                return bf.HeadFile(path, precision="double")
             except AssertionError:
                 raise AssertionError(f"{self.dataDict[key]} does not exist")
 
@@ -333,9 +333,7 @@ def _setbinarykeys(self, binarypathdict):
 
             elif key[1] == "DDN":
                 try:
-                    readddn = bf.HeadFile(
-                        path, text="drawdown", precision="double"
-                    )
+                    readddn = bf.HeadFile(path, precision="double")
                     self.dataDict[(key[0], key[1], "DRAWDOWN")] = path
                     readddn.close()
 

flopy/utils/binaryfile.py

@@ -470,6 +470,10 @@ def _build_index(self):
         header = self._get_header()
         self.nrow = header["nrow"]
         self.ncol = header["ncol"]
+        self.text_bytes = header["text"]
+        self.text = (
+            self.text_bytes.decode("ascii").strip().lower().replace(" ", "_")
+        )
         if header["ilay"] > self.nlay:
             self.nlay = header["ilay"]
 
@@ -488,8 +492,12 @@ def _build_index(self):
         while ipos < self.totalbytes:
             header = self._get_header()
             self.recordarray.append(header)
-            if self.text.upper() not in header["text"]:
-                continue
+            if header["text"] != self.text_bytes:
+                warnings.warn(
+                    "inconsistent text headers changing from "
+                    f"{self.text_bytes!r} to {header['text']!r}",
+                    UserWarning,
+                )
             if ipos == 0:
                 self.times.append(header["totim"])
                 self.kstpkper.append((header["kstp"], header["kper"]))
@@ -501,6 +509,8 @@ def _build_index(self):
             ipos = self.file.tell()
             self.iposarray.append(ipos)
             databytes = self.get_databytes(header)
+            if ipos + databytes > self.totalbytes:
+                raise EOFError(f"attempting to seek {ipos + databytes}")
             self.file.seek(databytes, 1)
             ipos = self.file.tell()
 
@@ -617,14 +627,13 @@ class HeadFile(BinaryLayerFile):
     ----------
     filename : str or PathLike
         Path of the head file.
-    text : string
-        Name of the text string in the head file. Default is 'head'.
-    precision : string
-        Precision of floating point head data in the value. Accepted
-        values are 'auto', 'single' or 'double'. Default is 'auto',
-        which enables automatic detection of precision.
-    verbose : bool
-        Toggle logging output. Default is False.
+    text : str
+        Ignored.
+    precision : {'auto', 'single', 'double'}
+        Precision of floating point head data in the value. Default
+        'auto' enables automatic detection of precision.
+    verbose : bool, default False
+        Toggle logging output.
 
     Examples
     --------
@@ -634,7 +643,7 @@ class HeadFile(BinaryLayerFile):
     >>> hdobj.list_records()
     >>> rec = hdobj.get_data(kstpkper=(0, 49))
 
-    >>> ddnobj = bf.HeadFile('model.ddn', text='drawdown', precision='single')
+    >>> ddnobj = bf.HeadFile('model.ddn', precision='single')
     >>> ddnobj.list_records()
     >>> rec = ddnobj.get_data(totim=100.)
 
@@ -643,12 +652,11 @@ class HeadFile(BinaryLayerFile):
     def __init__(
         self,
         filename: Union[str, os.PathLike],
-        text="head",
+        text="head",  # noqa ARG002
         precision="auto",
         verbose=False,
         **kwargs,
     ):
-        self.text = text.encode()
         if precision == "auto":
             precision = get_headfile_precision(filename)
             if precision == "unknown":
@@ -749,14 +757,15 @@ class UcnFile(BinaryLayerFile):
 
     Parameters
     ----------
-    filename : string
-        Name of the concentration file
-    text : string
-        Name of the text string in the ucn file.  Default is 'CONCENTRATION'
-    precision : string
-        'auto', 'single' or 'double'.  Default is 'auto'.
-    verbose : bool
-        Write information to the screen.  Default is False.
+    filename : str or PathLike
+        Path of the concentration file.
+    text : str
+        Ignored.
+    precision : {'auto', 'single', 'double'}
+        Precision of floating point values. Default 'auto' enables automatic
+        detection of precision.
+    verbose : bool, default False
+        Write information to the screen.
 
     Attributes
     ----------
@@ -792,12 +801,11 @@ class UcnFile(BinaryLayerFile):
     def __init__(
         self,
         filename,
-        text="concentration",
+        text="concentration",  # noqa ARG002
         precision="auto",
         verbose=False,
         **kwargs,
     ):
-        self.text = text.encode()
         if precision == "auto":
             precision = get_headfile_precision(filename)
         if precision == "unknown":
@@ -821,14 +829,13 @@ class HeadUFile(BinaryLayerFile):
     ----------
     filename : str or PathLike
         Path of the head file
-    text : string
-        Name of the text string in the head file. Default is 'headu'.
-    precision : string
-        Precision of the floating point head data in the file. Accepted
-        values are 'auto', 'single' or 'double'. Default is 'auto', which
-        enables precision to be automatically detected.
-    verbose : bool
-        Toggle logging output. Default is False.
+    text : str
+        Ignored.
+    precision : {'auto', 'single', 'double'}
+        Precision of floating point values. Default 'auto' enables automatic
+        detection of precision.
+    verbose : bool, default False
+        Toggle logging output.
 
     Notes
     -----
@@ -859,15 +866,14 @@ class HeadUFile(BinaryLayerFile):
     def __init__(
         self,
         filename: Union[str, os.PathLike],
-        text="headu",
+        text="headu",  # noqa ARG002
         precision="auto",
         verbose=False,
         **kwargs,
     ):
         """
         Class constructor
         """
-        self.text = text.encode()
         if precision == "auto":
             precision = get_headfile_precision(filename)
             if precision == "unknown":
@@ -990,11 +996,11 @@ class CellBudgetFile:
     ----------
     filename : str or PathLike
         Path of the cell budget file.
-    precision : string
-        Precision of floating point budget data in the file. Accepted
-        values are 'single' or 'double'. Default is 'single'.
-    verbose : bool
-        Toggle logging output. Default is False.
+    precision : {'auto', 'single', 'double'}
+        Precision of floating point values. Default 'auto' enables automatic
+        detection of precision.
+    verbose : bool, default False
+        Toggle logging output.
 
     Examples
     --------
@@ -2217,7 +2223,6 @@ def reverse(self, filename: Optional[os.PathLike] = None):
 
         Parameters
         ----------
-
         filename : str or PathLike, optional
             Path of the new reversed binary cell budget file to create.
         """