Merge branch 'fix-unknown-occupancy'

* make unknonwn CIF occupancy default to 1.
* use unix line ends in all test CIF files.

Resolve #24.

Author: pavoljuhas

src/diffpy/structure/parsers/p_cif.py

@@ -156,7 +156,7 @@ def _tr_atom_site_adp_type(a, value):
     _tr_atom_site_thermal_displace_type = _tr_atom_site_adp_type
 
     def _tr_atom_site_occupancy(a, value):
-        a.occupancy = leading_float(value)
+        a.occupancy = leading_float(value, 1.0)
     _tr_atom_site_occupancy = staticmethod(_tr_atom_site_occupancy)
 
     def _tr_atom_site_aniso_U_11(a, value):
@@ -622,19 +622,36 @@ def toLines(self, stru):
 # constant regular expression for leading_float()
 rx_float = re.compile(r'[-+]?(\d+(\.\d*)?|\.\d+)([eE][-+]?\d+)?')
 
-def leading_float(s):
-    """Obtain first float from a string and ignore any trailing characters.
+def leading_float(s, d=0.0):
+    """Extract the first float from a string and ignore trailing characters.
+
     Useful for extracting values from "value(std)" syntax.
 
-    Return float.
+    Parameters
+    ----------
+    s : str
+        The string to be scanned for floating point value.
+    d : float, optional
+        The default value when `s` is "." or "?", which in CIF
+        format stands for inapplicable and unknown, respectively.
+
+    Returns
+    -------
+    float
+        The extracted floating point value.
+
+    Raises
+    ------
+    ValueError
+        When string does not start with a float.
     """
     sbare = s.strip()
     mx = rx_float.match(sbare)
     if mx:
         rv = float(mx.group())
     elif sbare == '.' or sbare == '?':
         # CIF files may contain "." or "?" for unknown values
-        rv = 0.0
+        rv = d
     else:
         rv = float(sbare)
     return rv

src/diffpy/structure/tests/testdata/LiCl-bad.cif

@@ -11,8 +11,8 @@ _cell_length_a                            5.12952
 _cell_length_b                            5.12952 
 _cell_length_c                            5.12952 
 _cell_volume                              134.968 
-_cgraph_comments                         'Praezisionsbestimmung von Gitterkonstanten hygroskopischer 
-     Verbindungen (Li Cl. Na Br).
+_cgraph_comments                         'Praezisionsbestimmung von Gitterkonstanten hygroskopischer
+     Verbindungen (Li Cl. Na Br).
 '
 _cgraph_title                            'Lithium Chloride'
 _chemical_formula_sum                    'Li Cl'

src/diffpy/structure/tests/testdata/TeI-unkocc.cif

@@ -0,0 +1,37 @@
+data_TeI
+_audit_creation_date            2011-02-15
+
+_symmetry_space_group_name_H-M  'C 1 2/m 1'
+
+_cell_length_a                  15.383
+_cell_length_b                  4.182
+_cell_length_c                  11.999
+_cell_angle_alpha               90
+_cell_angle_beta                128.09
+_cell_angle_gamma               90
+
+loop_
+  _atom_site_label
+  _atom_site_type_symbol
+  _atom_site_fract_x
+  _atom_site_fract_y
+  _atom_site_fract_z
+  _atom_site_U_iso_or_equiv
+  _atom_site_adp_type
+  _atom_site_occupancy
+  Te1   Te1+   0.306590    0.000000    0.185920    0.019227 Uani  ?
+  Te2   Te1+   0.429170    0.500000    0.168170    0.019784 Uani  ?
+  I1    I1-    0.153740    0.500000    0.182510    0.024813 Uani  ?
+  I2    I1-    0.610730    0.500000    0.448390    0.026878 Uani  ?
+loop_
+  _atom_site_aniso_label
+  _atom_site_aniso_U_11
+  _atom_site_aniso_U_22
+  _atom_site_aniso_U_33
+  _atom_site_aniso_U_12
+  _atom_site_aniso_U_13
+  _atom_site_aniso_U_23
+  Te1    0.021100  0.019500  0.016000  0.000000  0.010900  0.000000
+  Te2    0.022300  0.018000  0.025400  0.000000  0.017900  0.000000
+  I1     0.025000  0.023400  0.034500  0.000000  0.022600  0.000000
+  I2     0.023400  0.029500  0.025300  0.000000  0.013800  0.000000

src/diffpy/structure/tests/testdata/TeI.cif

@@ -1,37 +1,37 @@
-data_TeI
-_audit_creation_date            2011-02-15
-
-_symmetry_space_group_name_H-M  'C 1 2/m 1'
-
-_cell_length_a                  15.383
-_cell_length_b                  4.182
-_cell_length_c                  11.999
-_cell_angle_alpha               90
-_cell_angle_beta                128.09
-_cell_angle_gamma               90
-
-loop_
-  _atom_site_label
-  _atom_site_type_symbol
-  _atom_site_fract_x
-  _atom_site_fract_y
-  _atom_site_fract_z
-  _atom_site_U_iso_or_equiv
-  _atom_site_adp_type
-  _atom_site_occupancy
-  Te1   Te1+   0.306590    0.000000    0.185920    0.019227 Uani  1.0000
-  Te2   Te1+   0.429170    0.500000    0.168170    0.019784 Uani  1.0000
-  I1    I1-    0.153740    0.500000    0.182510    0.024813 Uani  1.0000
-  I2    I1-    0.610730    0.500000    0.448390    0.026878 Uani  1.0000
-loop_
-  _atom_site_aniso_label
-  _atom_site_aniso_U_11
-  _atom_site_aniso_U_22
-  _atom_site_aniso_U_33
-  _atom_site_aniso_U_12
-  _atom_site_aniso_U_13
-  _atom_site_aniso_U_23
-  Te1    0.021100  0.019500  0.016000  0.000000  0.010900  0.000000
-  Te2    0.022300  0.018000  0.025400  0.000000  0.017900  0.000000
-  I1     0.025000  0.023400  0.034500  0.000000  0.022600  0.000000
-  I2     0.023400  0.029500  0.025300  0.000000  0.013800  0.000000
+data_TeI
+_audit_creation_date            2011-02-15
+
+_symmetry_space_group_name_H-M  'C 1 2/m 1'
+
+_cell_length_a                  15.383
+_cell_length_b                  4.182
+_cell_length_c                  11.999
+_cell_angle_alpha               90
+_cell_angle_beta                128.09
+_cell_angle_gamma               90
+
+loop_
+  _atom_site_label
+  _atom_site_type_symbol
+  _atom_site_fract_x
+  _atom_site_fract_y
+  _atom_site_fract_z
+  _atom_site_U_iso_or_equiv
+  _atom_site_adp_type
+  _atom_site_occupancy
+  Te1   Te1+   0.306590    0.000000    0.185920    0.019227 Uani  1.0000
+  Te2   Te1+   0.429170    0.500000    0.168170    0.019784 Uani  1.0000
+  I1    I1-    0.153740    0.500000    0.182510    0.024813 Uani  1.0000
+  I2    I1-    0.610730    0.500000    0.448390    0.026878 Uani  1.0000
+loop_
+  _atom_site_aniso_label
+  _atom_site_aniso_U_11
+  _atom_site_aniso_U_22
+  _atom_site_aniso_U_33
+  _atom_site_aniso_U_12
+  _atom_site_aniso_U_13
+  _atom_site_aniso_U_23
+  Te1    0.021100  0.019500  0.016000  0.000000  0.010900  0.000000
+  Te2    0.022300  0.018000  0.025400  0.000000  0.017900  0.000000
+  I1     0.025000  0.023400  0.034500  0.000000  0.022600  0.000000
+  I2     0.023400  0.029500  0.025300  0.000000  0.013800  0.000000

src/diffpy/structure/tests/testp_cif.py

@@ -249,6 +249,13 @@ def test_eps(self):
         return
 
 
+    def test_unknown_occupancy(self):
+        "test CIF file with unknown occupancy data"
+        stru = self.ptest.parseFile(datafile('TeI-unkocc.cif'))
+        self.assertTrue(numpy.array_equal(16 * [1], stru.occupancy))
+        return
+
+
     def test_nosites_cif(self):
         """Test reading of CIF file with no valid sites.
         """