(#105) Adding tests to pre-processing parser and annotate parser

tests/parser/test_YAML_parser.py

@@ -1,3 +1,4 @@
+import yaml
 from hygia.parser.YAML_parser import YAMLParser
 
 class TestYamlParser():
@@ -18,7 +19,7 @@ def test_yaml_has_description(self):
         assert 'description' in self.yaml
         assert self.yaml['description'] == 'DAG de teste'
 
-    def test_yaml_has_feature_settings(self):
+    def test_yaml_has_output_folder(self):
         assert 'output_folder' in self.yaml
         assert self.yaml['output_folder'] == 'output'
 
@@ -29,12 +30,16 @@ def test_yaml_has_feature_settings(self):
 
     def test_yaml_has_nrows(self):
         assert 'nrows' in self.yaml
-
+        assert isinstance(self.yaml['nrows'], int)
+
     def test_yaml_has_engine(self):
         assert 'engine' in self.yaml
+        assert isinstance(self.yaml['engine'], str)
 
     def test_yaml_has_encoding(self):
         assert 'encoding' in self.yaml
+        assert isinstance(self.yaml['encoding'], str)
 
     def test_yaml_has_separator(self):
         assert 'separator' in self.yaml
+        assert isinstance(self.yaml['separator'], str)

tests/parser/test_annotate_parser.py

@@ -1,8 +1,7 @@
 import pytest
-
 from hygia.parser.annotate_data_parser import AnnotateDataParser
 
-class TestAnnotateParser():
+class TestAnnotateParser:
 
     def setup_method(self):
         self.model_data = [{'input': {'columns': ['street', 'phone'], 'thresholds': {'ksmash_sequence_vowels': 1.0, 'ksmash_sequence_consonants': 1.999, 'ksmash_sequence_special_characters': 2.2499, 'ksmash_numbers': 2.9, 'ksmash_char_frequence': 2.78}}}]
@@ -33,7 +32,7 @@ def test_parser_annotate_data(self):
         assert 'ksmash_sequence_vowels' in thresholds
         assert thresholds['ksmash_sequence_vowels'] == 1.0
 
-    def test_get_thresholds(self):
+    def test_get_thresholds_with_input(self):
         thresholds = self.parser.get_thresholds(self.model_data[0]['input'])
 
         assert 'ksmash_char_frequence' in thresholds
@@ -51,7 +50,7 @@ def test_get_thresholds(self):
         assert 'ksmash_sequence_vowels' in thresholds
         assert thresholds['ksmash_sequence_vowels'] == 1.0
 
-    def test_get_keyboard_smash_default_config(self):
+    def test_get_thresholds_with_input_missing_keys(self):
         thresholds = self.parser.get_thresholds({'thresholds': {'ksmash_sequence_vowels': 1.1}})
 
         assert 'ksmash_char_frequence' in thresholds
@@ -69,7 +68,7 @@ def test_get_keyboard_smash_default_config(self):
         assert 'ksmash_sequence_vowels' in thresholds
         assert thresholds['ksmash_sequence_vowels'] == 1.1
 
-    def test_get_keyboard_smash_default_config(self):
+    def test_get_thresholds_without_input(self):
         thresholds = self.parser.get_thresholds()
 
         assert 'ksmash_char_frequence' in thresholds

tests/parser/test_pre_processing_parser.py

@@ -0,0 +1,39 @@
+import pytest
+from hygia.parser.pre_processing_parser import PreProcessingParser
+
+class TestPreProcessingParser:
+
+    def setup_method(self):
+        self.columns_name = ['col1', 'col2']
+        self.parser = PreProcessingParser(self.columns_name)
+
+    def test_parse_pre_processing_configs_with_empty_data(self):
+        data = []
+        result = self.parser.parse(data)
+
+        assert result is None
+
+    def test_get_dataframe(self):
+        aliases = [{'col3': 'new_col3'}, {'col4': 'new_col4'}]
+        self.parser._get_dataframe(aliases)
+
+        assert 'col3' in self.parser.columns_name
+        assert 'col4' in self.parser.columns_name
+
+    def test_get_dataframe_with_empty_aliases(self):
+        aliases = []
+        self.parser._get_dataframe(aliases)
+
+        assert self.parser.columns_name == self.columns_name
+
+    def test_get_dataframe_with_existing_columns(self):
+        aliases = [{'new_col1': 'col1'}, {'new_col2': 'col2'}]
+        self.parser._get_dataframe(aliases)
+
+        assert self.parser.columns_name == self.columns_name
+
+    def test_get_dataframe_with_empty_aliases_and_existing_columns(self):
+        aliases = []
+        self.parser._get_dataframe(aliases)
+
+        assert self.parser.columns_name == self.columns_name