[Cherry-Pick-Main][Server][SDL-5812] Updating project to allow locking/unlocking the schema. Adds support for a timestamp column (#56)

mkaliberda · web-flow · commit cb549a1500bc · 2025-01-15T18:11:26.000-08:00
diff --git a/src/server/datamanager/migrations/0087_lock_schema.py b/src/server/datamanager/migrations/0087_lock_schema.py
@@ -0,0 +1,18 @@
+# Generated by Django 3.2.12 on 2024-11-08 04:55
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("datamanager", "0086_label_info"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="project",
+            name="lock_schema",
+            field=models.BooleanField(default=False),
+        ),
+    ]
diff --git a/src/server/datamanager/models.py b/src/server/datamanager/models.py
@@ -248,6 +248,7 @@ class Project(models.Model):
     image_file_name = models.CharField(
         max_length=1100, null=True, unique=True, default=None
     )
+    lock_schema = models.BooleanField(default=False)
     last_modified = models.DateTimeField(auto_now=True)
 
     def __unicode__(self):
diff --git a/src/server/datamanager/query.py b/src/server/datamanager/query.py
@@ -311,7 +311,12 @@ def get_capture_file(project_uuid: str, capture_file: str, ext: str) -> DataFram
         datastore.get("{}".format(os.path.basename(capture_file)), capture_file)
 
     if ext == ".csv":
-        tmp_df = read_csv(capture_file, index_col="sequence")
+        cols = list(read_csv(capture_file, nrows=1))
+        tmp_df = read_csv(
+            capture_file,
+            index_col="sequence",
+            usecols=[col for col in cols if col != "timestamp"],
+        )
     elif ext == ".wav":
         with wave.open(capture_file, "rb") as wave_reader:
             waveFrames = wave_reader.readframes(wave_reader.getnframes())
diff --git a/src/server/datamanager/serializers/capture.py b/src/server/datamanager/serializers/capture.py
@@ -79,19 +79,16 @@ def validate_capture_file(capture, tmp_name):
         for index, (key, item) in enumerate(
             capture.project.capture_sample_schema.items()
         ):
-            if item.get("index") is None:
-                item["index"] = index
+            if item.get("index"):
+                item.pop("index")
                 update_capture_sample_schema = True
 
         for key in reader.schema.keys():
             if key not in capture.project.capture_sample_schema:
                 capture.project.capture_sample_schema[key] = reader.schema[key]
                 update_capture_sample_schema = True
 
-        if (
-            not settings.ALLOW_UPDATE_PROJECT_SCHEMA
-            and capture.project.capture_sample_schema
-        ):
+        if capture.project.lock_schema:
             project_columns = sorted(list(capture.project.capture_sample_schema.keys()))
             capture_columns = sorted(list(reader.schema.keys()))
             if project_columns != capture_columns:
diff --git a/src/server/datamanager/serializers/serializers.py b/src/server/datamanager/serializers/serializers.py
@@ -300,6 +300,7 @@ class Meta:
             "created_at",
             "active_pipelines",
             "description",
+            "lock_schema",
             "last_modified",
         )
         read_only_fields = (
diff --git a/src/server/datamanager/tests/utils/test_file_reader.py b/src/server/datamanager/tests/utils/test_file_reader.py
@@ -114,36 +114,36 @@ def test_csv_reader_data_mixed(filereader_mixed_int_float):
 def test_csv_reader_schema_int_float(filereader_mixed_int_float):
     schema = filereader_mixed_int_float.schema
     assert {
-        "AccelerometerX": {"type": "int", "index": 0},
-        "AccelerometerY": {"type": "float", "index": 1},
-        "GyroscopeZ": {"type": "float", "index": 2},
+        "AccelerometerX": {"type": "int"},
+        "AccelerometerY": {"type": "float"},
+        "GyroscopeZ": {"type": "float"},
     } == schema
 
 
 def test_csv_reader_schema_float(filereader_float):
     schema = filereader_float.schema
     assert {
-        "AccelerometerX": {"type": "float", "index": 0},
-        "AccelerometerY": {"type": "float", "index": 1},
-        "GyroscopeZ": {"type": "float", "index": 2},
+        "AccelerometerX": {"type": "float"},
+        "AccelerometerY": {"type": "float"},
+        "GyroscopeZ": {"type": "float"},
     } == schema
 
 
 def test_csv_reader_schema_int(filereader_int):
     schema = filereader_int.schema
     assert {
-        "AccelerometerX": {"type": "int", "index": 0},
-        "AccelerometerY": {"type": "int", "index": 1},
-        "GyroscopeZ": {"type": "int", "index": 2},
+        "AccelerometerX": {"type": "int"},
+        "AccelerometerY": {"type": "int"},
+        "GyroscopeZ": {"type": "int"},
     } == schema
 
 
 def test_csv_reader_schema_int_space_fields(filereader_int_name_space_fields):
     schema = filereader_int_name_space_fields.schema
     assert {
-        "Accelerometer_X": {"type": "int", "index": 0},
-        "AccelerometerY": {"type": "int", "index": 1},
-        "GyroscopeZ": {"type": "int", "index": 2},
+        "Accelerometer_X": {"type": "int"},
+        "AccelerometerY": {"type": "int"},
+        "GyroscopeZ": {"type": "int"},
     } == schema
 
 
diff --git a/src/server/datamanager/tests/views/data/packet_loss_with_timestamp.csv b/src/server/datamanager/tests/views/data/packet_loss_with_timestamp.csv
@@ -0,0 +1,100 @@
+timestamp,sequence,AccelerometerX,AccelerometerY,AccelerometerZ,GyroscopeX,GyroscopeY,GyroscopeZ
+r,1000,-158,313,4173,0,-2,-226
+r,1001,-146,368,4192,15,-5,-332
+r,1002,-282,278,4120,-93,56,-408
+r,1003,-332,179,4159,-19,14,-333
+r,1004,-181,170,4166,29,-13,-153
+r,1005,-148,154,4175,12,0,-51
+r,1006,-197,234,4166,9,-1,-8
+r,1007,-225,263,4160,10,-3,1
+r,1008,-218,252,4154,10,-2,-1
+r,1009,-215,254,4159,10,-3,-1
+r,1010,-221,248,4180,9,-2,-1
+r,1011,-217,250,4166,10,-4,-4
+r,1012,-215,255,4165,9,-3,-3
+r,1013,-217,256,4169,9,-2,-2
+r,1014,-215,262,4163,10,-3,-2
+r,1015,-213,264,4177,11,-2,-2
+r,1016,-214,255,4161,10,-2,-2
+r,1017,-213,248,4163,10,-2,-1
+r,1018,-218,250,4172,10,-3,-1
+r,1019,-211,254,4169,11,-4,-1
+r,1020,-213,256,4169,10,-2,-3
+r,1021,-220,250,4158,10,-3,-2
+r,1022,-212,258,4168,10,-3,-2
+r,1023,-202,257,4169,9,-2,-2
+r,1024,-210,258,4161,9,-3,-2
+r,1025,-215,256,4165,10,-4,-3
+r,1026,-213,256,4163,11,-1,-2
+r,1027,-210,256,4169,10,-2,-1
+r,1028,-216,257,4164,9,-2,-1
+r,1029,-217,253,4167,10,-1,-3
+r,1030,-215,260,4171,11,-1,-2
+r,1031,-213,255,4174,11,-3,0
+r,1032,-214,256,4164,9,-3,-1
+r,1033,-211,253,4169,8,-3,-2
+r,1034,-209,253,4163,9,-2,-2
+r,1035,-215,253,4159,9,-2,-2
+r,1036,-215,253,4166,10,-4,-2
+r,1037,-214,258,4161,11,-4,-2
+r,1038,-213,256,4163,10,-3,-1
+r,1039,-211,256,4163,10,-3,-2
+r,1040,-212,255,4164,9,-2,-1
+r,1041,-218,256,4172,9,-3,0
+r,1042,-215,253,4171,10,-4,0
+r,1043,-211,253,4164,10,-1,-1
+r,1044,-215,260,4158,11,-2,-2
+r,1045,-212,248,4169,10,-3,-3
+r,1046,-213,256,4162,11,-2,-1
+r,1047,-214,259,4160,10,-3,-1
+r,1048,-217,256,4161,10,-4,-1
+r,1049,-217,254,4175,11,-4,-2
+r,1050,-210,256,4172,11,-4,-3
+r,1051,-211,264,4162,10,-4,-3
+r,1052,-210,259,4163,10,-3,-1
+r,1053,-205,253,4168,9,-3,0
+r,1054,-221,250,4164,10,-2,-2
+r,1055,-221,255,4156,10,-3,-3
+r,1056,-213,259,4162,10,-2,-1
+r,1057,-218,254,4176,10,-2,-1
+r,1058,-216,250,4167,9,-2,-1
+r,1059,-206,257,4165,9,-2,-3
+r,1060,-212,255,4161,10,-1,-1
+r,1061,-214,252,4173,10,-2,-2
+r,1062,-217,255,4188,10,-2,-2
+r,1063,-224,255,4191,10,-2,-1
+r,1064,-218,258,4180,9,-2,-3
+r,1065,-221,256,4157,9,-3,-1
+r,1066,-208,258,4147,10,-4,-1
+r,1067,-211,257,4157,10,-2,-1
+r,1068,-214,257,4166,10,-2,-2
+r,1069,-209,253,4181,10,-2,-2
+r,1070,-213,256,4179,12,-1,-2
+r,1071,-212,257,4168,11,-3,-2
+r,1072,-205,255,4155,9,-3,-1
+r,1073,-215,261,4162,11,-2,-1
+r,1074,-223,261,4168,10,-2,-2
+r,1075,-212,264,4175,10,-2,-1
+r,1076,-217,257,4187,9,-2,-2
+r,1077,-214,258,4184,10,-4,-2
+r,1078,-220,264,4171,9,-3,-2
+r,1079,-211,284,4164,10,-2,-11
+r,1080,-206,268,4163,11,-2,-58
+r,1081,-222,233,4155,10,-4,-66
+r,1082,-217,252,4164,11,-3,-17
+r,1083,-214,261,4173,10,-3,3
+r,1084,-217,258,4181,10,-3,-2
+r,1086,-210,258,4171,10,-3,-2
+r,1087,-203,253,4158,9,-2,-2
+r,1088,-209,249,4167,10,-3,-2
+r,1089,-215,252,4173,10,-2,-1
+r,1090,-219,263,4172,10,-3,-1
+r,1092,-205,258,4184,11,-4,0
+r,1093,-211,261,4163,10,-3,-1
+r,1094,-219,258,4166,10,-4,-2
+r,1095,-217,251,4162,10,-3,-3
+r,1096,-213,257,4164,10,-3,-2
+r,1097,-210,254,4168,9,-4,-3
+r,1098,-224,252,4169,10,-2,-2
+r,1099,-219,261,4173,11,-3,-2
+r,1120,-212,263,4167,10,-3,-3
diff --git a/src/server/datamanager/tests/views/test_capture.py b/src/server/datamanager/tests/views/test_capture.py
@@ -190,6 +190,62 @@ def test_create_csv_with_packet_loss(self, client, project):
         assert r["name"] == "test_packet.csv"
         assert r["file_size"] == 2943
 
+    def test_create_csv_with_timestamp(self, client, project):
+        project.save()
+        settings.DEBUG = True
+
+        capture_list_url = reverse(
+            "capture-list",
+            kwargs={"project_uuid": project.uuid},
+        )
+
+        dirname = os.path.dirname(__file__)
+
+        template_path = os.path.join(dirname, "data/packet_loss_with_timestamp.csv")
+        with open(template_path, "rb") as f:
+            response = client.post(
+                capture_list_url,
+                format="multipart",
+                data={"file": f, "name": "test_packet.csv"},
+            )
+
+        assert response.status_code == status.HTTP_201_CREATED
+
+        r = response.json()
+
+        assert r["max_sequence"] == 1120
+        assert r["number_samples"] == 99
+        assert r["name"] == "test_packet.csv"
+        assert r["file_size"] == 3151
+
+        from datamanager.query import get_capture_file
+
+        capture = Capture.objects.get(name="test_packet.csv")
+        capture_df = get_capture_file(project.uuid, capture.file, ".csv")
+        assert "timestamp" not in capture_df.columns
+
+        from engine.base import pipeline_utils
+        from datamanager.models import TeamMember
+
+        user = TeamMember.objects.get(email="unittest@sensiml.com").user
+        capture_df_pipeline_utils, _, _ = pipeline_utils.get_capturefile(
+            user, project.uuid, capture.name
+        )
+
+        assert "timestamp" not in capture_df_pipeline_utils.columns
+
+        capture_list_url = reverse(
+            "capture-file",
+            kwargs={"project_uuid": project.uuid, "uuid": capture.uuid},
+        )
+
+        response = client.get(capture_list_url)
+
+        assert (
+            response.data
+            == b"timestamp,sequence,AccelerometerX,AccelerometerY,AccelerometerZ,GyroscopeX,GyroscopeY,GyroscopeZ\r\nr,1000,-158,313,4173,0,-2,-226\r\nr,1001,-146,368,4192,15,-5,-332\r\nr,1002,-282,278,4120,-93,56,-408\r\nr,1003,-332,179,4159,-19,14,-333\r\nr,1004,-181,170,4166,29,-13,-153\r\nr,1005,-148,154,4175,12,0,-51\r\nr,1006,-197,234,4166,9,-1,-8\r\nr,1007,-225,263,4160,10,-3,1\r\nr,1008,-218,252,4154,10,-2,-1\r\nr,1009,-215,254,4159,10,-3,-1\r\nr,1010,-221,248,4180,9,-2,-1\r\nr,1011,-217,250,4166,10,-4,-4\r\nr,1012,-215,255,4165,9,-3,-3\r\nr,1013,-217,256,4169,9,-2,-2\r\nr,1014,-215,262,4163,10,-3,-2\r\nr,1015,-213,264,4177,11,-2,-2\r\nr,1016,-214,255,4161,10,-2,-2\r\nr,1017,-213,248,4163,10,-2,-1\r\nr,1018,-218,250,4172,10,-3,-1\r\nr,1019,-211,254,4169,11,-4,-1\r\nr,1020,-213,256,4169,10,-2,-3\r\nr,1021,-220,250,4158,10,-3,-2\r\nr,1022,-212,258,4168,10,-3,-2\r\nr,1023,-202,257,4169,9,-2,-2\r\nr,1024,-210,258,4161,9,-3,-2\r\nr,1025,-215,256,4165,10,-4,-3\r\nr,1026,-213,256,4163,11,-1,-2\r\nr,1027,-210,256,4169,10,-2,-1\r\nr,1028,-216,257,4164,9,-2,-1\r\nr,1029,-217,253,4167,10,-1,-3\r\nr,1030,-215,260,4171,11,-1,-2\r\nr,1031,-213,255,4174,11,-3,0\r\nr,1032,-214,256,4164,9,-3,-1\r\nr,1033,-211,253,4169,8,-3,-2\r\nr,1034,-209,253,4163,9,-2,-2\r\nr,1035,-215,253,4159,9,-2,-2\r\nr,1036,-215,253,4166,10,-4,-2\r\nr,1037,-214,258,4161,11,-4,-2\r\nr,1038,-213,256,4163,10,-3,-1\r\nr,1039,-211,256,4163,10,-3,-2\r\nr,1040,-212,255,4164,9,-2,-1\r\nr,1041,-218,256,4172,9,-3,0\r\nr,1042,-215,253,4171,10,-4,0\r\nr,1043,-211,253,4164,10,-1,-1\r\nr,1044,-215,260,4158,11,-2,-2\r\nr,1045,-212,248,4169,10,-3,-3\r\nr,1046,-213,256,4162,11,-2,-1\r\nr,1047,-214,259,4160,10,-3,-1\r\nr,1048,-217,256,4161,10,-4,-1\r\nr,1049,-217,254,4175,11,-4,-2\r\nr,1050,-210,256,4172,11,-4,-3\r\nr,1051,-211,264,4162,10,-4,-3\r\nr,1052,-210,259,4163,10,-3,-1\r\nr,1053,-205,253,4168,9,-3,0\r\nr,1054,-221,250,4164,10,-2,-2\r\nr,1055,-221,255,4156,10,-3,-3\r\nr,1056,-213,259,4162,10,-2,-1\r\nr,1057,-218,254,4176,10,-2,-1\r\nr,1058,-216,250,4167,9,-2,-1\r\nr,1059,-206,257,4165,9,-2,-3\r\nr,1060,-212,255,4161,10,-1,-1\r\nr,1061,-214,252,4173,10,-2,-2\r\nr,1062,-217,255,4188,10,-2,-2\r\nr,1063,-224,255,4191,10,-2,-1\r\nr,1064,-218,258,4180,9,-2,-3\r\nr,1065,-221,256,4157,9,-3,-1\r\nr,1066,-208,258,4147,10,-4,-1\r\nr,1067,-211,257,4157,10,-2,-1\r\nr,1068,-214,257,4166,10,-2,-2\r\nr,1069,-209,253,4181,10,-2,-2\r\nr,1070,-213,256,4179,12,-1,-2\r\nr,1071,-212,257,4168,11,-3,-2\r\nr,1072,-205,255,4155,9,-3,-1\r\nr,1073,-215,261,4162,11,-2,-1\r\nr,1074,-223,261,4168,10,-2,-2\r\nr,1075,-212,264,4175,10,-2,-1\r\nr,1076,-217,257,4187,9,-2,-2\r\nr,1077,-214,258,4184,10,-4,-2\r\nr,1078,-220,264,4171,9,-3,-2\r\nr,1079,-211,284,4164,10,-2,-11\r\nr,1080,-206,268,4163,11,-2,-58\r\nr,1081,-222,233,4155,10,-4,-66\r\nr,1082,-217,252,4164,11,-3,-17\r\nr,1083,-214,261,4173,10,-3,3\r\nr,1084,-217,258,4181,10,-3,-2\r\nr,1086,-210,258,4171,10,-3,-2\r\nr,1087,-203,253,4158,9,-2,-2\r\nr,1088,-209,249,4167,10,-3,-2\r\nr,1089,-215,252,4173,10,-2,-1\r\nr,1090,-219,263,4172,10,-3,-1\r\nr,1092,-205,258,4184,11,-4,0\r\nr,1093,-211,261,4163,10,-3,-1\r\nr,1094,-219,258,4166,10,-4,-2\r\nr,1095,-217,251,4162,10,-3,-3\r\nr,1096,-213,257,4164,10,-3,-2\r\nr,1097,-210,254,4168,9,-4,-3\r\nr,1098,-224,252,4169,10,-2,-2\r\nr,1099,-219,261,4173,11,-3,-2\r\nr,1120,-212,263,4167,10,-3,-3"
+        )
+
     def test_create_csv_then_upload_wave(self, client, project):
         project.save()
         settings.DEBUG = True
@@ -210,8 +266,6 @@ def test_create_csv_then_upload_wave(self, client, project):
             )
         assert response.status_code == status.HTTP_201_CREATED
 
-        settings.ALLOW_UPDATE_PROJECT_SCHEMA = True
-
         template_path = os.path.join(dirname, "data/on_4c77947d_nohash_0.wav")
         with open(template_path, "rb") as f:
             response = client.post(
@@ -231,14 +285,25 @@ def test_create_csv_then_upload_wave(self, client, project):
             },
         }
 
-        settings.ALLOW_UPDATE_PROJECT_SCHEMA = False
+        template_path = os.path.join(dirname, "data/on_4c77947d_nohash_0.wav")
+        with open(template_path, "rb") as f:
+            response = client.post(
+                capture_list_url,
+                format="multipart",
+                data={"file": f, "name": "window_test2.wav"},
+            )
+
+        assert response.status_code == status.HTTP_201_CREATED
+
+        project.lock_schema = True
+        project.save(update_fields=["lock_schema"])
 
         template_path = os.path.join(dirname, "data/on_4c77947d_nohash_0.wav")
         with open(template_path, "rb") as f:
             response = client.post(
                 capture_list_url,
                 format="multipart",
-                data={"file": f, "name": "window_test_2.wav"},
+                data={"file": f, "name": "window_test_3.wav"},
             )
 
         assert response.status_code == status.HTTP_400_BAD_REQUEST
@@ -250,14 +315,15 @@ def test_create_csv_then_upload_wave(self, client, project):
             ],
         }
 
-        settings.ALLOW_UPDATE_PROJECT_SCHEMA = True
+        project.lock_schema = False
+        project.save(update_fields=["lock_schema"])
 
         template_path = os.path.join(dirname, "data/on_4c77947d_nohash_0.wav")
         with open(template_path, "rb") as f:
             response = client.post(
                 capture_list_url,
                 format="multipart",
-                data={"file": f, "name": "window_test_2.wav"},
+                data={"file": f, "name": "window_test_4.wav"},
             )
 
         assert response.status_code == status.HTTP_201_CREATED
@@ -266,13 +332,13 @@ def test_create_csv_then_upload_wave(self, client, project):
 
         assert response.status_code == status.HTTP_200_OK
         assert response.json()["capture_sample_schema"] == {
-            "channel_0": {"type": "int", "index": 0},
-            "GyroscopeX": {"type": "int", "index": 3},
-            "GyroscopeY": {"type": "int", "index": 4},
-            "GyroscopeZ": {"type": "int", "index": 5},
-            "AccelerometerX": {"type": "int", "index": 0},
-            "AccelerometerY": {"type": "int", "index": 1},
-            "AccelerometerZ": {"type": "int", "index": 2},
+            "channel_0": {"type": "int"},
+            "GyroscopeX": {"type": "int"},
+            "GyroscopeY": {"type": "int"},
+            "GyroscopeZ": {"type": "int"},
+            "AccelerometerX": {"type": "int"},
+            "AccelerometerY": {"type": "int"},
+            "AccelerometerZ": {"type": "int"},
         }
 
     def test_capture_stats_api_base(
diff --git a/src/server/datamanager/utils/file_reader.py b/src/server/datamanager/utils/file_reader.py
@@ -50,18 +50,22 @@ def make_schema(dataframe):
     invalid_columns = []
     schema = {}
     for index, dtype in enumerate(dataframe.dtypes):
-        if dtype not in ["int64", "float64"]:
+        if (
+            dtype not in ["int64", "float64"]
+            and dataframe.columns[index] != "timestamp"
+        ):
             invalid_columns.append(dataframe.columns[index])
 
         column_dtype = None
         if dtype in ["int64"]:
             column_dtype = "int"
+        elif dtype in ["string"]:
+            column_dtype = "string"
         elif dtype in ["float64"]:
             column_dtype = "float"
 
         schema[dataframe.columns[index].replace(" ", "_")] = {
             "type": column_dtype,
-            "index": index,
         }
 
     if invalid_columns:
@@ -154,10 +158,7 @@ def __init__(self, file_path):
                 index="sequence"
             )
 
-            self._schema = {
-                key: {"type": "int16", "index": index}
-                for index, key in enumerate(columns)
-            }
+            self._schema = {key: {"type": "int16"} for index, key in enumerate(columns)}
 
     def to_CSVFileReader(self, tmp_file_path):
         self._dataframe.to_csv(tmp_file_path, index=None)
diff --git a/src/server/engine/base/pipeline_utils.py b/src/server/engine/base/pipeline_utils.py
diff --git a/src/server/server/settings.py b/src/server/server/settings.py

Original file line number	Diff line number	Diff line change
`@@ -248,6 +248,7 @@ class Project(models.Model):`
`248`	`248`	`image_file_name = models.CharField(`
`249`	`249`	`max_length=1100, null=True, unique=True, default=None`
`250`	`250`	`)`
	`251`	`+ lock_schema = models.BooleanField(default=False)`
`251`	`252`	`last_modified = models.DateTimeField(auto_now=True)`
`252`	`253`
`253`	`254`	`def __unicode__(self):`
Original file line number	Diff line number	Diff line change
`@@ -300,6 +300,7 @@ class Meta:`
`300`	`300`	`"created_at",`
`301`	`301`	`"active_pipelines",`
`302`	`302`	`"description",`
	`303`	`+ "lock_schema",`
`303`	`304`	`"last_modified",`
`304`	`305`	`)`
`305`	`306`	`read_only_fields = (`