Change class names and configs

tests still passing

backdrop/admin/app.py

@@ -6,11 +6,11 @@
 
 from .. import statsd
 from ..core import cache_control, log_handler, database
-from ..core.data_set import Bucket
+from ..core.data_set import DataSet
 from ..core.errors import ParseError, ValidationError
 from ..core.repository \
-    import BucketConfigRepository, UserConfigRepository
-from ..core.flaskutils import BucketConverter
+    import DataSetConfigRepository, UserConfigRepository
+from ..core.flaskutils import DataSetConverter
 from ..core.upload import create_parser
 from .signonotron2 import Signonotron2
 from .uploaded_file import UploadedFile, FileUploadError
@@ -25,15 +25,15 @@
 
 log_handler.set_up_logging(app, GOVUK_ENV)
 
-app.url_map.converters["data_set"] = BucketConverter
+app.url_map.converters["data_set"] = DataSetConverter
 
 db = database.Database(
     app.config['MONGO_HOSTS'],
     app.config['MONGO_PORT'],
     app.config['DATABASE_NAME']
 )
 
-data_set_repository = BucketConfigRepository(
+data_set_repository = DataSetConfigRepository(
     app.config['STAGECRAFT_URL'],
     app.config['STAGECRAFT_DATA_SET_QUERY_TOKEN'])
 
@@ -202,7 +202,7 @@ def upload(data_set_name):
 
 def _store_data(data_set_config):
     parse_file = create_parser(data_set_config)
-    data_set = Bucket(db, data_set_config)
+    data_set = DataSet(db, data_set_config)
     expected_errors = (FileUploadError, ParseError, ValidationError)
 
     try:

backdrop/admin/templates/upload_file.html

@@ -4,7 +4,7 @@
 
 {% block body %}
     <h1>Upload {{ upload_format }} data to the Performance Platform</h1>
-    <h2>Bucket: {{ data_set_name }}</h2>
+    <h2>DataSet: {{ data_set_name }}</h2>
     <p>You can upload data to Performance Platform from your {{ upload_format }} files. For
         each row in a {{ upload_format }} file a document will be added to your data_set. You need
         to make sure they match our expected format (see example below). </p>

backdrop/core/data_set.py

@@ -11,7 +11,7 @@
 log = logging.getLogger(__name__)
 
 
-class Bucket(object):
+class DataSet(object):
 
     def __init__(self, db, config):
         self.name = config.name
@@ -75,26 +75,26 @@ def _generate_id(self, datum):
         return b64encode(".".join([datum[key] for key in self.auto_id_keys]))
 
 
-_BucketConfig = namedtuple(
-    "_BucketConfig",
+_DataSetConfig = namedtuple(
+    "_DataSetConfig",
     "name data_group data_type raw_queries_allowed bearer_token upload_format "
     "upload_filters auto_ids queryable realtime capped_size max_age_expected")
 
 
-class BucketConfig(_BucketConfig):
+class DataSetConfig(_DataSetConfig):
 
     def __new__(cls, name, data_group, data_type, raw_queries_allowed=False,
                 bearer_token=None, upload_format="csv", upload_filters=None,
                 auto_ids=None, queryable=True, realtime=False,
                 capped_size=5040, max_age_expected=2678400):
         if not data_set_is_valid(name):
-            raise ValueError("Bucket name is not valid: '{}'".format(name))
+            raise ValueError("DataSet name is not valid: '{}'".format(name))
 
         if upload_filters is None:
             upload_filters = [
                 "backdrop.core.upload.filters.first_sheet_filter"]
 
-        return super(BucketConfig, cls).__new__(cls, name, data_group,
+        return super(DataSetConfig, cls).__new__(cls, name, data_group,
                                                 data_type,
                                                 raw_queries_allowed,
                                                 bearer_token, upload_format,

backdrop/core/flaskutils.py

@@ -2,7 +2,7 @@
 from backdrop.core.validation import data_set_is_valid
 
 
-class BucketConverter(BaseConverter):
+class DataSetConverter(BaseConverter):
     def to_python(self, value):
         if not data_set_is_valid(value):
             raise ValidationError()

backdrop/core/repository.py

@@ -4,7 +4,7 @@
 
 import requests
 
-from backdrop.core.data_set import BucketConfig
+from backdrop.core.data_set import DataSetConfig
 from backdrop.core.user import UserConfig
 
 logger = logging.getLogger(__name__)
@@ -48,7 +48,7 @@ def _create_model(self, doc):
         return self.model_cls(**doc)
 
 
-class BucketConfigRepository(object):
+class DataSetConfigRepository(object):
 
     def __init__(self, stagecraft_url, stagecraft_token):
         self._stagecraft_url = stagecraft_url
@@ -107,7 +107,7 @@ def get_data_set_for_query(self, data_group, data_type):
 def _make_data_set_config(stagecraft_dict):
     if stagecraft_dict is None:
         return None
-    return BucketConfig(**stagecraft_dict)
+    return DataSetConfig(**stagecraft_dict)
 
 
 def _decode_json(string):

backdrop/read/api.py

@@ -9,9 +9,9 @@
 
 from .validation import validate_request_args
 from ..core import database, log_handler, cache_control
-from ..core.data_set import Bucket
+from ..core.data_set import DataSet
 from ..core.database import InvalidOperationError
-from ..core.repository import BucketConfigRepository
+from ..core.repository import DataSetConfigRepository
 
 
 GOVUK_ENV = getenv("GOVUK_ENV", "development")
@@ -30,7 +30,7 @@
     app.config['DATABASE_NAME']
 )
 
-data_set_repository = BucketConfigRepository(
+data_set_repository = DataSetConfigRepository(
     app.config['STAGECRAFT_URL'],
     app.config['STAGECRAFT_DATA_SET_QUERY_TOKEN'])
 
@@ -79,7 +79,7 @@ def data_set_health():
     data_set_configs = data_set_repository.get_all()
 
     for data_set_config in data_set_configs:
-        data_set = Bucket(db, data_set_config)
+        data_set = DataSet(db, data_set_config)
         if not data_set.is_recent_enough():
             failing_data_sets.append({
                 'name': data_set.name,
@@ -151,7 +151,7 @@ def fetch(data_set_config):
                 data_set_config.name, result.message,
                 400)
 
-        data_set = Bucket(db, data_set_config)
+        data_set = DataSet(db, data_set_config)
 
         try:
             query = Query.parse(request.args)

backdrop/write/api.py

@@ -4,9 +4,9 @@
 from flask import Flask, request, jsonify, g
 from flask_featureflags import FeatureFlag
 from backdrop import statsd
-from backdrop.core.data_set import Bucket
-from backdrop.core.flaskutils import BucketConverter
-from backdrop.core.repository import (BucketConfigRepository,
+from backdrop.core.data_set import DataSet
+from backdrop.core.flaskutils import DataSetConverter
+from backdrop.core.repository import (DataSetConfigRepository,
                                       UserConfigRepository)
 
 from ..core.errors import ParseError, ValidationError
@@ -31,15 +31,15 @@
     app.config['DATABASE_NAME']
 )
 
-data_set_repository = BucketConfigRepository(
+data_set_repository = DataSetConfigRepository(
     app.config['STAGECRAFT_URL'],
     app.config['STAGECRAFT_DATA_SET_QUERY_TOKEN'])
 
 user_repository = UserConfigRepository(db)
 
 log_handler.set_up_logging(app, GOVUK_ENV)
 
-app.url_map.converters["data_set"] = BucketConverter
+app.url_map.converters["data_set"] = DataSetConverter
 
 
 @app.errorhandler(500)
@@ -147,7 +147,7 @@ def _write_to_data_set(data_set_config):
     try:
         data = listify_json(request.json)
 
-        data_set = Bucket(db, data_set_config)
+        data_set = DataSet(db, data_set_config)
         data_set.parse_and_store(data)
 
         return jsonify(status='ok')

backdrop/write/config/development.py

@@ -2,7 +2,7 @@
 MONGO_HOSTS = ['localhost']
 MONGO_PORT = 27017
 LOG_LEVEL = "DEBUG"
-BUCKET_AUTO_ID_KEYS = {
+DATA_SET_AUTO_ID_KEYS = {
     "lpa_volumes": ("key", "start_at", "end_at")
 }
 

backdrop/write/config/test.py

@@ -4,7 +4,7 @@
 LOG_LEVEL = "DEBUG"
 CLIENT_ID = "it's not important here"
 CLIENT_SECRET = "it's not important here"
-BUCKET_AUTO_ID_KEYS = {
+DATA_SET_AUTO_ID_KEYS = {
     "data_set_with_auto_id": ["key", "start_at", "end_at"],
     "data_set_with_timestamp_auto_id": ["_timestamp", "key"],
     "evl_volumetrics": ["_timestamp", "service", "transaction"],

features/steps/read_api.py

@@ -19,7 +19,7 @@ def step(context):
 
 
 def ensure_data_set_exists(context, data_set_name, settings={}):
-    # these should mostly match the default BucketConfig.__new__() kwargs
+    # these should mostly match the default DataSetConfig.__new__() kwargs
     response = {
         'name': data_set_name,
         'data_group': data_set_name,

tasks.py

@@ -5,8 +5,8 @@
 from backdrop.core import database
 from backdrop.core.user import UserConfig
 from backdrop.write.api import app
-from backdrop.core.data_set import BucketConfig
-from backdrop.core.repository import BucketConfigRepository,\
+from backdrop.core.data_set import DataSetConfig
+from backdrop.core.repository import DataSetConfigRepository,\
     UserConfigRepository
 
 
@@ -32,12 +32,12 @@ def create_data_set(name, datagroup, datatype, rawqueries=False, token=None,
     """Create a new data_set configuration in the database."""
     db = get_database()
 
-    config = BucketConfig(name=name, data_group=datagroup, data_type=datatype,
+    config = DataSetConfig(name=name, data_group=datagroup, data_type=datatype,
                           raw_queries_allowed=rawqueries, bearer_token=token,
                           upload_format=uploadformat,
                           upload_filters=uploadfilters, auto_ids=autoids,
                           queryable=queryable, realtime=realtime)
-    repository = BucketConfigRepository(db)
+    repository = DataSetConfigRepository(db)
 
     repository.save(config)
 
@@ -70,8 +70,8 @@ def save_all(filename, repo_cls, model_cls, **save_kwargs):
             repo.save(model_cls(**item), **save_kwargs)
 
     save_all("data_set-seed.json",
-             BucketConfigRepository,
-             BucketConfig, create_data_set=False)
+             DataSetConfigRepository,
+             DataSetConfig, create_data_set=False)
     save_all("user-seed.json",
              UserConfigRepository,
              UserConfig)

tests/core/integration/test_data_set_integration.py

@@ -7,7 +7,7 @@
 from hamcrest import *
 
 from backdrop.core import database, data_set
-from backdrop.core.data_set import BucketConfig
+from backdrop.core.data_set import DataSetConfig
 from backdrop.core.records import Record
 from backdrop.core.timeseries import WEEK
 from backdrop.read.query import Query
@@ -16,16 +16,16 @@
 HOST = ['localhost']
 PORT = 27017
 DB_NAME = 'performance_platform_test'
-BUCKET = 'data_set_integration_test'
+DATA_SET = 'data_set_integration_test'
 
 
-class TestBucketIntegration(unittest.TestCase):
+class TestDataSetIntegration(unittest.TestCase):
 
     def setUp(self):
         self.db = database.Database(HOST, PORT, DB_NAME)
-        self.data_set = data_set.Bucket(
-            self.db, BucketConfig(BUCKET, data_group="group", data_type="type", max_age_expected=1000))
-        self.mongo_collection = MongoClient(HOST, PORT)[DB_NAME][BUCKET]
+        self.data_set = data_set.DataSet(
+            self.db, DataSetConfig(DATA_SET, data_group="group", data_type="type", max_age_expected=1000))
+        self.mongo_collection = MongoClient(HOST, PORT)[DB_NAME][DATA_SET]
 
     def setup__timestamp_data(self):
         self.mongo_collection.save({

tests/core/integration/test_database_integration.py

@@ -12,14 +12,14 @@
 HOST = ['localhost']
 PORT = 27017
 DB_NAME = 'performance_platform_test'
-BUCKET = 'test_repository_integration'
+DATA_SET = 'test_repository_integration'
 
 
 class TestMongoDriver(unittest.TestCase):
     def setUp(self):
-        self.mongo_driver = MongoDriver(MongoClient(HOST, PORT)[DB_NAME][BUCKET])
+        self.mongo_driver = MongoDriver(MongoClient(HOST, PORT)[DB_NAME][DATA_SET])
 
-        self.mongo_collection = MongoClient(HOST, PORT)[DB_NAME][BUCKET]
+        self.mongo_collection = MongoClient(HOST, PORT)[DB_NAME][DATA_SET]
         self.mongo_collection.drop()
 
     def test_save(self):
@@ -225,10 +225,10 @@ class RepositoryIntegrationTest(unittest.TestCase):
     __metaclass__ = ABCMeta
 
     def setUp(self):
-        mongo = MongoDriver(MongoClient(HOST, PORT)[DB_NAME][BUCKET])
+        mongo = MongoDriver(MongoClient(HOST, PORT)[DB_NAME][DATA_SET])
         self.repo = Repository(mongo)
 
-        self.mongo_collection = MongoClient(HOST, PORT)[DB_NAME][BUCKET]
+        self.mongo_collection = MongoClient(HOST, PORT)[DB_NAME][DATA_SET]
         self.mongo_collection.drop()