Merge pull request #1481 from lanzagar/filename

[FIX] Table names set by readers

Author: astaric

Orange/data/io.py

@@ -1,6 +1,7 @@
 import contextlib
 import csv
 import locale
+import os
 import pickle
 import re
 import subprocess
@@ -668,6 +669,14 @@ def read(self):
                 try:
                     reader = csv.reader(file, dialect=dialect)
                     data = self.data_table(reader)
+
+                    # TODO: Name can be set unconditionally when/if
+                    # self.filename will always be a string with the file name.
+                    # Currently, some tests pass StringIO instead of
+                    # the file name to a reader.
+                    if isinstance(self.filename, str):
+                        data.name = os.path.splitext(
+                            os.path.split(self.filename)[-1])[0]
                     if error and isinstance(error, UnicodeDecodeError):
                         pos, endpos = error.args[2], error.args[3]
                         warning = ('Skipped invalid byte(s) in position '
@@ -731,8 +740,10 @@ def constr_vars(inds):
         classes = constr_vars(class_indices)
         meta_attrs = constr_vars(meta_indices)
         domain = Domain(attrs, classes, meta_attrs)
-        return Table.from_numpy(
+        table = Table.from_numpy(
             domain, attrs and X, classes and Y, metas and meta_attrs)
+        table.name = os.path.splitext(os.path.split(self.filename)[-1])[0]
+        return table
 
 
 class ExcelReader(FileFormat):
@@ -767,6 +778,9 @@ def read(self):
                              for col in range(first_col, row_len)]
                             for row in range(first_row, ss.nrows)])
             table = self.data_table(cells)
+            table.name = os.path.splitext(os.path.split(self.filename)[-1])[0]
+            if self.sheet:
+                table.name = '-'.join((table.name, self.sheet))
         except Exception:
             raise IOError("Couldn't load spreadsheet from " + self.filename)
         return table

Orange/data/table.py

@@ -525,7 +525,6 @@ def from_file(cls, filename):
         if cls != data.__class__:
             data = cls(data)
 
-        data.name = os.path.splitext(os.path.split(filename)[-1])[0]
         # no need to call _init_ids as fuctions from .io already
         # construct a table with .ids
 

Orange/tests/test_basket_reader.py

@@ -89,6 +89,10 @@ def test_handles_quote(self, fname):
         table = read_basket(fname)
         self.assertEqual(len(table.domain.variables), 4)
 
+    def test_data_name(self):
+        filename = os.path.join(os.path.dirname(__file__), 'iris_basket.basket')
+        self.assertEqual(read_basket(filename).name, 'iris_basket')
+
 
 if __name__ == "__main__":
     unittest.main()

Orange/tests/test_tab_reader.py

@@ -9,9 +9,10 @@
 
 import numpy as np
 
-from Orange.data import Table, ContinuousVariable, DiscreteVariable
+from Orange.data import Table, DiscreteVariable
 from Orange.data.io import TabReader
 
+
 def read_tab_file(filename):
     return TabReader(filename).read()
 
@@ -152,3 +153,9 @@ def test_attributes_saving(self):
         table = Table(path.join(tempdir, "out.tab"))
         self.assertEqual(table.attributes[1], "test")
         shutil.rmtree(tempdir)
+
+    def test_data_name(self):
+        table1 = Table('iris')
+        table2 = TabReader(table1.__file__).read()
+        self.assertEqual(table1.name, 'iris')
+        self.assertEqual(table2.name, 'iris')

Orange/tests/test_xlsx_reader.py

@@ -6,7 +6,7 @@
 
 import numpy as np
 
-from Orange.data import io, ContinuousVariable, DiscreteVariable, StringVariable
+from Orange.data import io, ContinuousVariable, DiscreteVariable
 
 
 def get_dataset(name):
@@ -31,6 +31,7 @@ def test_read(self):
                                        np.array([[0.1, 0.5, 0.1, 21],
                                                  [0.2, 0.1, 2.5, 123],
                                                  [0, 0, 0, 0]]))
+        self.assertEqual(table.name, 'header_0')
 
 
 class TextExcelSheets(unittest.TestCase):
@@ -45,6 +46,7 @@ def test_named_sheet(self):
         self.reader.select_sheet("my_sheet")
         table = self.reader.read()
         self.assertEqual(len(table.domain.attributes), 4)
+        self.assertEqual(table.name, 'header_0_sheet-my_sheet')
 
 
 class TestExcelHeader1(unittest.TestCase):
@@ -94,6 +96,7 @@ def test_flags(self):
         np.testing.assert_almost_equal(
             table.metas[:, 1], np.array([0, 1, 2, 3] * 5 + [0, 1, 2]))
 
+
 class TestExcelHeader3(unittest.TestCase):
     def test_read(self):
         table = read_file("header_3.xlsx")
@@ -130,5 +133,6 @@ def test_read(self):
         np.testing.assert_equal(
             table.metas[:, 2], np.array(list("abcdefghijklmnopqrstuvw")))
 
+
 if __name__ == "__main__":
     unittest.main()

Orange/widgets/data/owfile.py

@@ -256,7 +256,7 @@ def load_data(self):
             try:
                 data = self.reader.read()
             except Exception as ex:
-                errors.append("An error occured:")
+                errors.append("An error occurred:")
                 errors.append(str(ex))
                 data = None
                 self.editor_model.reset()