Add bool dtype support for PLY files (#321)

Author: nicholas-mitchell

pyntcloud/core_class.py

@@ -195,7 +195,7 @@ def to_instance(self, library, **kwargs):
         library = library.upper()
         if library not in TO_INSTANCE:
             raise ValueError(
-                "Unsupported library; supported linraries are: {}".format(list(TO_INSTANCE)))
+                "Unsupported library; supported libraries are: {}".format(list(TO_INSTANCE)))
 
         return TO_INSTANCE[library](self, **kwargs)
 

pyntcloud/io/ply.py

@@ -31,22 +31,28 @@
                  'binary_little_endian': '<'}
 
 
-def read_ply(filename):
-    """ Read a .ply (binary or ascii) file and store the elements in pandas DataFrame
+def read_ply(filename, allow_bool=False):
+    """ Read a .ply (binary or ascii) file and store the elements in pandas DataFrame.
+
     Parameters
     ----------
     filename: str
         Path to the filename
+    allow_bool: bool
+        flag to allow bool as a valid PLY dtype. False by default to mirror original PLY specification.
+
     Returns
     -------
     data: dict
         Elements as pandas DataFrames; comments and ob_info as list of string
     """
+    if allow_bool:
+        ply_dtypes[b'bool'] = '?'
 
     with open(filename, 'rb') as ply:
 
         if b'ply' not in ply.readline():
-            raise ValueError('The file does not start whith the word ply')
+            raise ValueError('The file does not start with the word ply')
         # get binary_little/big or ascii
         fmt = ply.readline().split()[1].decode()
         # get extension for building the numpy dtypes
@@ -165,7 +171,7 @@ def read_ply(filename):
 
 
 def write_ply(filename, points=None, mesh=None, as_text=False, comments=None):
-    """
+    """Write a PLY file populated with the given fields.
 
     Parameters
     ----------
@@ -242,7 +248,7 @@ def describe_element(name, df):
     -------
     element: list[str]
     """
-    property_formats = {'f': 'float', 'u': 'uchar', 'i': 'int'}
+    property_formats = {'f': 'float', 'u': 'uchar', 'i': 'int', 'b': 'bool'}
     element = ['element ' + name + ' ' + str(len(df))]
 
     if name == 'face':

tests/data/diamond_with_bool.ply

@@ -85,3 +85,15 @@ def test_obj_issue_vn(data_path):
 
     assert len(cloud.xyz) == 3
     assert len(cloud.mesh) == 1
+
+
+def test_ply_with_bool(data_path):
+    """Expectation: a PLY file that contains bool types can be read into a PyntCloud object."""
+    TEST_PLY = str(data_path / "diamond_with_bool.ply")
+
+    with pytest.raises(KeyError, match="bool"):
+        cloud = PyntCloud.from_file(TEST_PLY)
+
+    cloud = PyntCloud.from_file(filename=TEST_PLY, allow_bool=True)
+    assert "is_green" in cloud.points.columns, "Failed to find expected Boolean column: 'is_green'"
+    assert cloud.points.is_green.dtype == bool, "Boolean column no loaded as bool dtype"

tests/integration/io/test_from_file.py

@@ -37,4 +37,28 @@ def test_to_file(tmpdir, diamond, extension, color, mesh, comments):
 
 def test_to_bin_raises_ValueError_if_invalid_kwargs(tmpdir, diamond):
     with pytest.raises(ValueError):
-        diamond.to_file(str(tmpdir.join("written.bin")), also_save=["mesh"])
+        diamond.to_file(str(tmpdir.join("written.bin")), also_save=["mesh"])
+
+
+def test_write_ply_with_bool(plane_pyntcloud, tmp_path):
+    """Expectation: a PyntCloud class holding Boolean column within `points` can be written and re-read as a PLY file.
+
+    After adding the new column, we have the following DataFrame under plane_pyntcloud.points:
+
+        x    y    z  bool_col
+    0  0.0  0.0  0.0      True
+    1  1.0  1.0  0.0      True
+    2  2.0  2.0  0.0     False
+    3  1.0  2.0  0.0      True
+    4  0.1  0.2  0.3      True
+    """
+    # Insert the additional column of dtype: bool.
+    plane_pyntcloud.points["bool_col"] = plane_pyntcloud.points.x < 2
+
+    # Write the DataFrame containing Boolean data.
+    ply_out = (tmp_path / "test_file.ply").as_posix()
+    plane_pyntcloud.to_file(ply_out)
+
+    # Reload the test file and compare it is exactly as it was before writing.
+    new_pyntcloud = PyntCloud.from_file(ply_out, allow_bool=True)
+    assert new_pyntcloud.points.equals(plane_pyntcloud.points), "Re-read pyntcloud is not identical to before writing"