fix(filenames): fixed how spaces in filenames are handled (#1236) (#1318

)

* fix(filenames): fixed how spaces in filenames are handled.  filenames with spaces in them now are read correctly from the package files and are written to the package file in quotes (#1236)

* fix(filenames): test cases now include filenames with spaces in them

autotest/t505_test.py

@@ -403,7 +403,7 @@ def test_array():
         delc=5000.0,
         top=100.0,
         botm=[50.0, 0.0, -50.0, -100.0],
-        filename="{}.dis".format(model_name),
+        filename=f"{model_name} 1.dis",
     )
     ic_package = mf6.ModflowGwfic(
         model, strt=90.0, filename=f"{model_name}.ic"
@@ -526,9 +526,11 @@ def test_array():
         write_headers=False,
     )
     model = test_sim.get_model()
+    dis = model.get_package("dis")
     rcha = model.get_package("rcha")
     wel = model.get_package("wel")
     drn = model.get_package("drn")
+    assert os.path.split(dis.filename)[1] == f"{model_name} 1.dis"
     # do same tests as above
     val_irch = rcha.irch.array.sum(axis=(1, 2, 3))
     assert val_irch[0] == 4
@@ -767,8 +769,8 @@ def test_np001():
 
     oc_package = ModflowGwfoc(
         model,
-        budget_filerecord=[("np001_mod.cbc",)],
-        head_filerecord=[("np001_mod.hds",)],
+        budget_filerecord=[("np001_mod 1.cbc",)],
+        head_filerecord=[("np001_mod 1.hds",)],
         saverecord={
             0: [("HEAD", "ALL"), ("BUDGET", "ALL")],
             1: [],
@@ -803,7 +805,7 @@ def test_np001():
     # test saving a binary file with list data
     well_spd = {
         0: {
-            "filename": "wel0.bin",
+            "filename": "wel 0.bin",
             "binary": True,
             "data": [(0, 0, 4, -2000.0), (0, 0, 7, -2.0)],
         },
@@ -933,7 +935,7 @@ def test_np001():
         )
 
         # compare output to expected results
-        head_new = os.path.join(run_folder, "np001_mod.hds")
+        head_new = os.path.join(run_folder, "np001_mod 1.hds")
         outfile = os.path.join(run_folder, "head_compare.dat")
         assert pymake.compare_heads(
             None,
@@ -982,7 +984,7 @@ def test_np001():
         )
 
         # compare output to expected results
-        head_new = os.path.join(run_folder_new, "np001_mod.hds")
+        head_new = os.path.join(run_folder_new, "np001_mod 1.hds")
         outfile = os.path.join(run_folder_new, "head_compare.dat")
         assert pymake.compare_heads(
             None,
@@ -1217,13 +1219,13 @@ def test_np002():
     sim.register_ims_package(ims_package, [model.name])
 
     # get rid of top_data.txt so that a later test does not automatically pass
-    top_data_file = os.path.join(run_folder, "top_data.txt")
+    top_data_file = os.path.join(run_folder, "top data.txt")
     if os.path.isfile(top_data_file):
         os.remove(top_data_file)
     # test loading data to be stored in a file and loading data from a file
     # using the "dictionary" input format
     top = {
-        "filename": "top_data.txt",
+        "filename": "top data.txt",
         "factor": 1.0,
         "data": [
             100.0,

flopy/mf6/data/mfdata.py

@@ -10,6 +10,7 @@
 from ..data.mfstructure import DatumType
 from ..coordinates.modeldimensions import DataDimensions, DiscretizationType
 from ...datbase import DataInterface, DataType
+from ...utils import datautil
 from .mfdatastorage import DataStructureType
 from .mfdatautil import to_string
 from ...mbase import ModelInterface
@@ -598,7 +599,7 @@ def _get_external_formatting_string(self, layer, ext_file_action):
         ext_file_path = file_mgmt.get_updated_path(
             layer_storage.fname, model_name, ext_file_action
         )
-        layer_storage.fname = ext_file_path
+        layer_storage.fname = datautil.clean_filename(ext_file_path)
         ext_format = ["OPEN/CLOSE", f"'{ext_file_path}'"]
         if storage.data_structure_type != DataStructureType.recarray:
             if layer_storage.factor is not None:

flopy/mf6/data/mfdatascalar.py

@@ -4,6 +4,7 @@
 from ..data import mfdata
 from ..mfbase import ExtFileAction, MFDataException
 from ...datbase import DataType
+from ...utils.datautil import clean_filename
 from .mfdatautil import convert_data, to_string
 from .mffileaccess import MFFileAccessScalar
 from .mfdatastorage import DataStorage, DataStructureType, DataStorageType
@@ -164,7 +165,11 @@ def set_data(self, data):
                         data = [data]
         else:
             if isinstance(data, str):
-                data = data.strip().split()[-1]
+                if self.structure.file_data or self.structure.nam_file_data:
+                    # clean up file name data
+                    data = clean_filename(data)
+                else:
+                    data = data.strip().split()[-1]
             else:
                 while (
                     isinstance(data, list)

flopy/mf6/data/mfdatastorage.py

@@ -16,6 +16,7 @@
     PyListUtil,
     ArrayIndexIter,
     MultiList,
+    clean_filename,
 )
 from .mfdatautil import convert_data, MFComment
 from .mffileaccess import MFFileAccessArray, MFFileAccessList, MFFileAccess
@@ -2065,9 +2066,9 @@ def process_open_close_line(self, arr_line, layer, store=True):
                     layer,
                 )
             if arr_line[0].lower() == "open/close":
-                data_file = arr_line[1]
+                data_file = clean_filename(arr_line[1])
             else:
-                data_file = arr_line[0]
+                data_file = clean_filename(arr_line[0])
         elif isinstance(arr_line, dict):
             for key, value in arr_line.items():
                 if key.lower() == "factor":
@@ -2104,7 +2105,7 @@ def process_open_close_line(self, arr_line, layer, store=True):
                 if key.lower() == "data":
                     data = value
             if "filename" in arr_line:
-                data_file = arr_line["filename"]
+                data_file = clean_filename(arr_line["filename"])
 
         if data_file is None:
             message = (

flopy/mf6/data/mffileaccess.py

@@ -2164,6 +2164,13 @@ def _append_data_list(
                         data_item,
                         sub_amt=sub_amt,
                     )
+                    if (
+                        data_item.indicates_file_name()
+                        or data_item.file_nam_in_nam_file()
+                    ):
+                        data_converted = datautil.clean_filename(
+                            data_converted
+                        )
                     if add_to_last_line:
                         self._last_line_info[-1].append(
                             [data_index, data_item.type, 0]

flopy/mf6/data/mfstructure.py

@@ -891,7 +891,8 @@ class MFDataItemStructure:
 
     def __init__(self):
         self.file_name_keywords = {"filein": False, "fileout": False}
-        self.contained_keywords = {"file_name": True}
+        self.file_name_key_seq = {"fname": True}
+        self.contained_keywords = {"fname": True, "file": True, "tdis6": True}
         self.block_name = None
         self.name = None
         self.display_name = None
@@ -1151,11 +1152,16 @@ def get_keystring_desc(self, line_size, initial_indent, level_indent):
             )
         return description
 
+    def file_nam_in_nam_file(self):
+        for key, item in self.contained_keywords.items():
+            if self.name.lower().find(key) != -1:
+                return True
+
     def indicates_file_name(self):
         if self.name.lower() in self.file_name_keywords:
             return True
-        for key, item in self.contained_keywords.items():
-            if self.name.lower().find(key) != -1:
+        for key in self.file_name_key_seq.keys():
+            if key in self.name.lower():
                 return True
         return False
 
@@ -1415,6 +1421,7 @@ def __init__(self, data_item, model_data, package_type, dfn_list):
         self.num_data_items = len(data_item.data_items)
         self.record_within_record = False
         self.file_data = False
+        self.nam_file_data = False
         self.block_type = data_item.block_type
         self.block_variable = data_item.block_variable
         self.model_data = model_data
@@ -1545,6 +1552,9 @@ def add_item(self, item, record=False, dfn_list=None):
                             self.path,
                         )
                     if isinstance(item, MFDataItemStructure):
+                        self.nam_file_data = (
+                            self.nam_file_data or item.file_nam_in_nam_file()
+                        )
                         self.file_data = (
                             self.file_data or item.indicates_file_name()
                         )
@@ -1558,6 +1568,9 @@ def add_item(self, item, record=False, dfn_list=None):
                     # insert placeholder in array
                     self.data_item_structures.append(None)
                 if isinstance(item, MFDataItemStructure):
+                    self.nam_file_data = (
+                        self.nam_file_data or item.file_nam_in_nam_file()
+                    )
                     self.file_data = (
                         self.file_data or item.indicates_file_name()
                     )

flopy/mf6/mfbase.py

@@ -431,6 +431,10 @@ def resolve_path(
         else:
             file_path = path
 
+        # remove quote characters from file path
+        file_path = file_path.replace("'", "")
+        file_path = file_path.replace('"', "")
+
         if os.path.isabs(file_path):
             # path is an absolute path
             if move_abs_paths:

flopy/mf6/mfpackage.py

@@ -852,7 +852,8 @@ def load(self, block_header, fd, strict=True):
                             f'        opening external file "{file_name}"...'
                         )
                     external_file_info = arr_line
-                    fd_block = open(os.path.join(root_path, arr_line[1]), "r")
+                    file_name = datautil.clean_filename(arr_line[1])
+                    fd_block = open(os.path.join(root_path, file_name), "r")
                     # read first line of external file
                     line = fd_block.readline()
                     arr_line = datautil.PyListUtil.split_data_line(line)
@@ -1516,6 +1517,8 @@ class MFPackage(PackageContainer, PackageInterface):
         String defining the package type
     filename : str
         Filename of file where this package is stored
+    quoted_filename : str
+        Filename with quotes around it when there is a space in the name
     pname : str
         Package name
     loading_package : bool
@@ -1647,7 +1650,9 @@ def __init__(
                     message,
                     model_or_sim.simulation_data.debug,
                 )
-            self._filename = MFFileMgmt.string_to_file_path(filename)
+            self._filename = MFFileMgmt.string_to_file_path(
+                datautil.clean_filename(filename)
+            )
         self.path, self.structure = model_or_sim.register_package(
             self, not loading_package, pname is None, filename is None
         )
@@ -1714,6 +1719,13 @@ def filename(self):
         """Package's file name."""
         return self._filename
 
+    @property
+    def quoted_filename(self):
+        """Package's file name with quotes if there is a space."""
+        if " " in self._filename:
+            return f'"{self._filename}"'
+        return self._filename
+
     @filename.setter
     def filename(self, fname):
         """Package's file name."""
@@ -1722,6 +1734,7 @@ def filename(self, fname):
             and self.structure.file_type
             in self.parent_file._child_package_groups
         ):
+            fname = datautil.clean_filename(fname)
             try:
                 child_pkg_group = self.parent_file._child_package_groups[
                     self.structure.file_type
@@ -2164,7 +2177,9 @@ def load(self, strict=True):
         """
         # open file
         try:
-            fd_input_file = open(self.get_file_path(), "r")
+            fd_input_file = open(
+                datautil.clean_filename(self.get_file_path()), "r"
+            )
         except OSError as e:
             if e.errno == errno.ENOENT:
                 message = "File {} of type {} could not be opened.".format(

flopy/mf6/modflow/mfsimulation.py

@@ -1990,7 +1990,7 @@ def register_package(
             return path, self.structure.name_file_struct_obj
         elif package.package_type.lower() == "tdis":
             self._tdis_file = package
-            self._set_timing_block(package.filename)
+            self._set_timing_block(package.quoted_filename)
             return (
                 path,
                 self.structure.package_struct_objs[

flopy/utils/datautil.py

@@ -1,5 +1,18 @@
 import os
 import numpy as np
+import shlex
+
+
+def clean_filename(file_name):
+    if (
+        file_name[0] in PyListUtil.quote_list
+        and file_name[-1] in PyListUtil.quote_list
+    ):
+        # quoted string
+        # keep entire string and remove the quotes
+        f_name = file_name.strip('"')
+        return f_name.strip("'")
+    return file_name
 
 
 def clean_name(name):
@@ -295,7 +308,8 @@ def split_data_line(line, external_file=False, delimiter_conf_length=15):
         else:
             # compare against the default split option without comments split
             comment_split = line.split("#", 1)
-            clean_line = comment_split[0].strip().split()
+            # first try standard split preserving quotes
+            clean_line = shlex.split(comment_split[0].strip(), posix=False)
             if len(comment_split) > 1:
                 clean_line.append("#")
                 clean_line.append(comment_split[1].strip())
@@ -342,7 +356,8 @@ def split_data_line(line, external_file=False, delimiter_conf_length=15):
                 if item and item[0] in PyListUtil.quote_list:
                     # starts with a quote, handle quoted text
                     if item[-1] in PyListUtil.quote_list:
-                        arr_fixed_line.append(item[1:-1])
+                        # if quoted on both ends, keep quotes
+                        arr_fixed_line.append(item)
                     else:
                         arr_fixed_line.append(item[1:])
                         # loop until trailing quote found