Merge b6d8a1f into c8c0f1f

q2_types/sample_data/_format.py

@@ -7,19 +7,48 @@
 # ----------------------------------------------------------------------------
 
 import qiime2.plugin.model as model
+from qiime2.plugin import ValidationError
 
 from ..plugin_setup import plugin
 
 
 class AlphaDiversityFormat(model.TextFileFormat):
-    def sniff(self):
+    def _validate_(self, level):
         with self.open() as fh:
-            i = 0
-            for line, i in zip(fh, range(10)):
-                cells = line.split('\t')
-                if len(cells) < 2:
-                    return False
-            return i > 1
+            header = None
+            records_seen = 0
+            file_ = enumerate(fh) if level == 'min' else zip(range(10), fh)
+            for i, line in file_:
+                i = i + 1  # For easier reporting
+                if line.lstrip(' ') == '\n':
+                    continue  # Blank line
+                elif line.startswith('#'):
+                    continue  # Comment line
+                cells = [c.strip() for c in line.rstrip('\n').split('\t')]
+
+                if header is None:
+                    if len(cells) < 2:
+                        raise ValidationError(
+                            'Found header on line %d with the following '
+                            'columns: %s (length: %d), expected at least 2 '
+                            'columns.' % (i, cells, len(cells)))
+                    else:
+                        header = cells
+                else:
+                    if len(cells) != len(header):
+                        raise ValidationError(
+                            'Line %d has %s cells (%s), expected %s.'
+                            % (i, len(cells), cells, len(header)))
+
+                    records_seen += 1
+
+            if header is None:
+                raise ValidationError('No header found.')
+
+            if records_seen == 0:
+                raise ValidationError('No records found in file, only '
+                                      'observed comments, blank lines, and/or '
+                                      'a header row.')
 
 
 AlphaDiversityDirectoryFormat = model.SingleFileDirectoryFormat(

q2_types/sample_data/tests/data/alpha-diversity-jagged-rows.tsv

@@ -0,0 +1,3 @@
+	shannon	extra
+Sample1	0.9709505944546688	foo
+Sample4	0.7219280948873623

q2_types/sample_data/tests/data/alpha-diversity-one-column.tsv

@@ -0,0 +1,3 @@
+
+Sample1
+Sample4

q2_types/sample_data/tests/data/alpha-diversity-one-sample.tsv

@@ -0,0 +1,2 @@
+	shannon
+Sample1	0.9709505944546688

q2_types/sample_data/tests/test_format.py

@@ -22,22 +22,52 @@ def test_alpha_diversity_format_validate_positive(self):
         filepath = self.get_data_path('alpha-diversity.tsv')
         format = AlphaDiversityFormat(filepath, mode='r')
 
+        # Should succeed
         format.validate()
 
-    def test_alpha_diversity_format_validate_negative(self):
-        filepath = self.get_data_path('not-alpha-diversity.tsv')
-        format = AlphaDiversityFormat(filepath, mode='r')
-
-        with self.assertRaisesRegex(ValidationError, 'AlphaDiversityFormat'):
-            format.validate()
-
     def test_alpha_diversity_dir_fmt_validate_positive(self):
         filepath = self.get_data_path('alpha-diversity.tsv')
         shutil.copy(filepath, self.temp_dir.name)
         format = AlphaDiversityDirectoryFormat(self.temp_dir.name, mode='r')
 
+        # Should succeed
+        format.validate()
+
+    def test_alpha_diversity_format_validate_positive_one_sample(self):
+        filepath = self.get_data_path('alpha-diversity-one-sample.tsv')
+        format = AlphaDiversityFormat(filepath, mode='r')
+
+        # Should succeed
+        format.validate()
+
+    def test_alpha_diversity_format_validate_positive_md_columns(self):
+        filepath = self.get_data_path('alpha-diversity-with-metadata.tsv')
+        format = AlphaDiversityFormat(filepath, mode='r')
+
+        # Should succeed
         format.validate()
 
+    def test_alpha_diversity_format_validate_negative_no_records(self):
+        filepath = self.get_data_path('alpha-diversity-missing-records.tsv')
+        format = AlphaDiversityFormat(filepath, mode='r')
+
+        with self.assertRaisesRegex(ValidationError, 'No records found.*'):
+            format.validate()
+
+    def test_alpha_diversity_format_validate_negative_too_few_cols(self):
+        filepath = self.get_data_path('alpha-diversity-one-column.tsv')
+        format = AlphaDiversityFormat(filepath, mode='r')
+
+        with self.assertRaisesRegex(ValidationError, '.*Sample1.*: 1.*'):
+            format.validate()
+
+    def test_alpha_diversity_format_validate_negative_jagged_rows(self):
+        filepath = self.get_data_path('alpha-diversity-jagged-rows.tsv')
+        format = AlphaDiversityFormat(filepath, mode='r')
+
+        with self.assertRaisesRegex(ValidationError, 'Line 3.*expected 3.*'):
+            format.validate()
+
 
 if __name__ == '__main__':
     unittest.main()