[Enhancement] Fix minor code issues

backend/data_export/pipeline/catalog.py

@@ -69,11 +69,13 @@ class Options:
     @classmethod
     def filter_by_task(cls, task_name: str):
         options = cls.options[task_name]
-        return [{**format.dict(), **option.schema(), "example": example} for format, option, example in options]
+        return [
+            {**file_format.dict(), **option.schema(), "example": example} for file_format, option, example in options
+        ]
 
     @classmethod
-    def register(cls, task: str, format: Type[Format], option: Type[BaseModel], example: str):
-        cls.options[task].append((format, option, example))
+    def register(cls, task: str, file_format: Type[Format], option: Type[BaseModel], example: str):
+        cls.options[task].append((file_format, option, example))
 
 
 # Text Classification

backend/data_export/pipeline/data.py

@@ -4,9 +4,9 @@
 
 class Record:
     def __init__(
-        self, id: int, data: str, label: Union[List[Any], Dict[Any, Any]], user: str, metadata: Dict[Any, Any]
+        self, data_id: int, data: str, label: Union[List[Any], Dict[Any, Any]], user: str, metadata: Dict[Any, Any]
     ):
-        self.id = id
+        self.id = data_id
         self.data = data
         self.label = label
         self.user = user

backend/data_export/pipeline/repositories.py

@@ -31,7 +31,7 @@ def list(self, export_approved=False) -> Iterator[Record]:
                 label_per_user = self.reduce_user(label_per_user)
             for user, label in label_per_user.items():
                 yield Record(
-                    id=example.id,
+                    data_id=example.id,
                     data=str(example.filename).split("/")[-1],
                     label=label,
                     user=user,
@@ -45,7 +45,7 @@ def list(self, export_approved=False) -> Iterator[Record]:
             # This means I will allow each user to be able to approve the doc.
             if len(label_per_user) == 0:
                 yield Record(
-                    id=example.id, data=str(example.filename).split("/")[-1], label=[], user="unknown", metadata={}
+                    data_id=example.id, data=str(example.filename).split("/")[-1], label=[], user="unknown", metadata={}
                 )
 
     def label_per_user(self, example) -> Dict:
@@ -82,15 +82,15 @@ def list(self, export_approved=False):
             if self.project.collaborative_annotation:
                 label_per_user = self.reduce_user(label_per_user)
             for user, label in label_per_user.items():
-                yield Record(id=doc.id, data=doc.text, label=label, user=user, metadata=doc.meta)
+                yield Record(data_id=doc.id, data=doc.text, label=label, user=user, metadata=doc.meta)
             # todo:
             # If there is no label, export the doc with `unknown` user.
             # This is a quick solution.
             # In the future, the doc without label will be exported
             # with the user who approved the doc.
             # This means I will allow each user to be able to approve the doc.
             if len(label_per_user) == 0:
-                yield Record(id=doc.id, data=doc.text, label=[], user="unknown", metadata={})
+                yield Record(data_id=doc.id, data=doc.text, label=[], user="unknown", metadata={})
 
     @abc.abstractmethod
     def label_per_user(self, doc) -> Dict:

backend/data_export/tests/test_writer.py

@@ -9,9 +9,9 @@
 class TestCSVWriter(unittest.TestCase):
     def setUp(self):
         self.records = [
-            Record(id=0, data="exampleA", label=["labelA"], user="admin", metadata={"hidden": "secretA"}),
-            Record(id=1, data="exampleB", label=["labelB"], user="admin", metadata={"hidden": "secretB"}),
-            Record(id=2, data="exampleC", label=["labelC"], user="admin", metadata={"meta": "secretC"}),
+            Record(data_id=0, data="exampleA", label=["labelA"], user="admin", metadata={"hidden": "secretA"}),
+            Record(data_id=1, data="exampleB", label=["labelB"], user="admin", metadata={"hidden": "secretB"}),
+            Record(data_id=2, data="exampleC", label=["labelC"], user="admin", metadata={"meta": "secretC"}),
         ]
 
     def test_create_header(self):
@@ -29,8 +29,8 @@ def test_create_line(self):
 
     def test_label_order(self):
         writer = CsvWriter(".")
-        record1 = Record(id=0, data="", label=["labelA", "labelB"], user="", metadata={})
-        record2 = Record(id=0, data="", label=["labelB", "labelA"], user="", metadata={})
+        record1 = Record(data_id=0, data="", label=["labelA", "labelB"], user="", metadata={})
+        record2 = Record(data_id=0, data="", label=["labelB", "labelA"], user="", metadata={})
         line1 = writer.create_line(record1)
         line2 = writer.create_line(record2)
         expected = "labelA#labelB"
@@ -61,7 +61,11 @@ def test_dump(self, mock_open_file, csv_io, zip_io, mock_remove_file):
 class TestIntentWriter(unittest.TestCase):
     def setUp(self):
         self.record = Record(
-            id=0, data="exampleA", label={"cats": ["positive"], "entities": [(0, 1, "LOC")]}, user="admin", metadata={}
+            data_id=0,
+            data="exampleA",
+            label={"cats": ["positive"], "entities": [(0, 1, "LOC")]},
+            user="admin",
+            metadata={},
         )
 
     def test_create_line(self):

backend/data_import/pipeline/parsers.py

@@ -151,7 +151,7 @@ def parse(self, filename: str) -> Iterator[Dict[Any, Any]]:
         encoding = decide_encoding(filename, self.encoding)
         with open(filename, encoding=encoding) as f:
             reader = csv.DictReader(f, delimiter=self.delimiter)
-            for line_num, row in enumerate(reader, start=2):
+            for row in reader:
                 yield row
 
 
@@ -171,7 +171,7 @@ def parse(self, filename: str) -> Iterator[Dict[Any, Any]]:
         with open(filename, encoding=encoding) as f:
             try:
                 rows = json.load(f)
-                for line_num, row in enumerate(rows, start=1):
+                for row in rows:
                     yield row
             except json.decoder.JSONDecodeError as e:
                 error = FileParseException(filename, line_num=1, message=str(e))
@@ -246,7 +246,7 @@ def __init__(self, encoding: str = DEFAULT_ENCODING, label: str = "__label__", *
 
     def parse(self, filename: str) -> Iterator[Dict[Any, Any]]:
         reader = LineReader(filename, self.encoding)
-        for line_num, line in enumerate(reader, start=1):
+        for line in reader:
             labels = []
             tokens = []
             for token in line.rstrip().split(" "):

backend/label_types/tests/test_models.py

@@ -51,6 +51,6 @@ def test_can_add_label_suffix_key_with_prefix_key(self):
 
 class TestGeneratedColor(TestCase):
     def test_length(self):
-        for i in range(100):
+        for _ in range(100):
             color = generate_random_hex_color()
             self.assertEqual(len(color), 7)

backend/labels/migrations/0008_auto_20220222_0630.py

@@ -22,7 +22,7 @@ def delete_new_relation(apps, schema_editor):
     RelationOld = apps.get_model("labels", "RelationOld")
     RelationTypeOld = apps.get_model("label_types", "RelationTypeOld")
     for relation in RelationNew.objects.all():
-        relation_type, created = RelationTypeOld.objects.get_or_create(
+        relation_type, _ = RelationTypeOld.objects.get_or_create(
             project=relation.type.project, name=relation.type.text, color=relation.type.background_color
         )
         RelationOld(