ingestr 0.13.28__tar.gz → 0.13.30__tar.gz

{ingestr-0.13.28 → ingestr-0.13.30}/.gitignore

@@ -20,4 +20,5 @@ node_modules
 *.db
 *.db.wal
 *.sql
-ingest.sh
+ingest.sh
+test.env

{ingestr-0.13.28 → ingestr-0.13.30}/Makefile

@@ -22,13 +22,13 @@ deps-ci:
 	uv pip install --system -r requirements-dev.txt
 
 test-ci:
-	TESTCONTAINERS_RYUK_DISABLED=true pytest -n auto -x -rP -vv --tb=short --durations=10 --cov=ingestr --no-cov-on-fail
+	set -a; source test.env; set +a; TESTCONTAINERS_RYUK_DISABLED=true pytest -n auto -x -rP -vv --tb=short --durations=10 --cov=ingestr --no-cov-on-fail
 
 test : venv lock-deps
 	. venv/bin/activate; $(MAKE) test-ci
 
 test-specific: venv lock-deps
-	. venv/bin/activate; TESTCONTAINERS_RYUK_DISABLED=true pytest -n auto  -rP -vv --tb=short --capture=no -k $(test)
+	. venv/bin/activate; set -a; source test.env; set +a; TESTCONTAINERS_RYUK_DISABLED=true pytest -n auto  -rP -vv --tb=short --capture=no -k $(test)
 
 lint-ci:
 	ruff format ingestr && ruff check ingestr --fix

{ingestr-0.13.28 → ingestr-0.13.30}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ingestr
-Version: 0.13.28
+Version: 0.13.30
 Summary: ingestr is a command-line application that ingests data from various sources and stores them in any database.
 Project-URL: Homepage, https://github.com/bruin-data/ingestr
 Project-URL: Issues, https://github.com/bruin-data/ingestr/issues

{ingestr-0.13.28 → ingestr-0.13.30}/docs/.vitepress/config.mjs

@@ -29,6 +29,9 @@ export default defineConfig({
       { text: "Getting started", link: "/getting-started/quickstart.md" },
     ],
     outline: "deep",
+    search: {
+      provider: 'local'
+    },
 
     sidebar: [
       {

ingestr-0.13.30/docs/supported-sources/appsflyer.md

@@ -0,0 +1,58 @@
+# AppsFlyer
+
+[AppsFlyer](https://www.appsflyer.com/) is a mobile marketing analytics and attribution platform that helps businesses track, measure, and optimize their app marketing efforts across various channels.
+
+ingestr supports AppsFlyer as a source.
+
+> [!WARNING]
+> AppsFlyer uses different names for input dimensions vs their name in the output schema. For instance, in order to obtain campaign information, you need to use the `c` dimension; however, in the output schema, the resulting column will be called `campaign`.
+
+
+## URI Format
+
+The URI format for AppsFlyer is as follows:
+
+```plaintext
+appsflyer://?api_key=<api-key>
+```
+
+An API token is required to retrieve reports from the AppsFlyer API, please [follow the guide to obtain an API key](https://support.appsflyer.com/hc/en-us/articles/360004562377-Managing-AppsFlyer-tokens)
+
+Let's say your API key is `ey123`, here's a sample command that will copy the data from AppsFlyer into a DuckDB database:
+
+```bash
+ingestr ingest 
+    --source-uri 'appsflyer://?api_key=ey123' 
+    --source-table 'campaigns' 
+    --dest-uri duckdb:///appsflyer.duckdb 
+    --dest-table 'appsflyer.output'
+```
+
+The result of this command will be a table in the `appsflyer.duckdb` database.
+
+## Supported Tables
+
+ingestr integrates with the [Master Report API](https://dev.appsflyer.com/hc/reference/master_api_get) of AppsFlyer, which allows you to retrieve data for the following tables:
+
+- `campaigns`: Retrieves data for campaigns, detailing the app's costs, loyal users, total installs, and revenue over multiple days.
+- `creatives`: Retrieves data for a creative asset, including revenue and cost.
+- `custom:<dimensions>:<metrics>`: Retrieves data for custom tables, which can be specified by the user.
+
+Use these as `--source-table` parameter in the `ingestr ingest` command.
+
+### Custom Tables
+
+You can also ingest custom tables by providing a list of dimensions and metrics.
+
+The table format is as follows:
+
+```plaintext
+custom:<dimension1>,<dimension2>,<metric1>,<metric2>
+```
+
+This will automatically generate a table with the dimensions and metrics you provided.
+
+For custom tables, ingestr will use the given dimensions as the primary key to deduplicate the data.
+
+> [!NOTE]
+> ingestr will add `install_time` as the primary key to the table by default if it is not provided as one of the dimensions.

{ingestr-0.13.28 → ingestr-0.13.30}/ingestr/main.py

@@ -302,6 +302,13 @@ def ingest(
             envvar=["COLUMNS", "INGESTR_COLUMNS"],
         ),
     ] = None,  # type: ignore
+    yield_limit: Annotated[
+        Optional[int],
+        typer.Option(
+            help="Limit the number of pages yielded from the source",
+            envvar=["YIELD_LIMIT", "INGESTR_YIELD_LIMIT"],
+        ),
+    ] = None,  # type: ignore
 ):
     import hashlib
     import tempfile
@@ -556,6 +563,9 @@ def ingest(
         if factory.source_scheme.startswith("mysql"):
             resource.for_each(dlt_source, lambda x: x.add_map(handle_mysql_empty_dates))
 
+        if yield_limit:
+            resource.for_each(dlt_source, lambda x: x.add_limit(yield_limit))
+
         def col_h(x):
             if column_hints:
                 x.apply_hints(columns=column_hints)

ingestr-0.13.30/ingestr/src/appsflyer/__init__.py

@@ -0,0 +1,325 @@
+from typing import Iterable
+
+import dlt
+import pendulum
+from dlt.common.typing import TDataItem
+from dlt.sources import DltResource
+
+from ingestr.src.appsflyer.client import AppsflyerClient
+
+DIMENSION_RESPONSE_MAPPING = {
+    "c": "campaign",
+    "af_adset_id": "adset_id",
+    "af_adset": "adset",
+    "af_ad_id": "ad_id",
+}
+HINTS = {
+    "app_id": {
+        "data_type": "text",
+        "nullable": False,
+    },
+    "campaign": {
+        "data_type": "text",
+        "nullable": False,
+    },
+    "geo": {
+        "data_type": "text",
+        "nullable": False,
+    },
+    "cost": {
+        "data_type": "decimal",
+        "precision": 30,
+        "scale": 5,
+        "nullable": False,
+    },
+    "clicks": {
+        "data_type": "bigint",
+        "nullable": False,
+    },
+    "impressions": {
+        "data_type": "bigint",
+        "nullable": False,
+    },
+    "average_ecpi": {
+        "data_type": "decimal",
+        "precision": 30,
+        "scale": 5,
+        "nullable": False,
+    },
+    "installs": {
+        "data_type": "bigint",
+        "nullable": False,
+    },
+    "retention_day_7": {
+        "data_type": "decimal",
+        "precision": 30,
+        "scale": 5,
+        "nullable": False,
+    },
+    "retention_day_14": {
+        "data_type": "decimal",
+        "precision": 30,
+        "scale": 5,
+        "nullable": False,
+    },
+    "cohort_day_1_revenue_per_user": {
+        "data_type": "decimal",
+        "precision": 30,
+        "scale": 5,
+        "nullable": True,
+    },
+    "cohort_day_1_total_revenue_per_user": {
+        "data_type": "decimal",
+        "precision": 30,
+        "scale": 5,
+        "nullable": True,
+    },
+    "cohort_day_3_revenue_per_user": {
+        "data_type": "decimal",
+        "precision": 30,
+        "scale": 5,
+        "nullable": True,
+    },
+    "cohort_day_3_total_revenue_per_user": {
+        "data_type": "decimal",
+        "precision": 30,
+        "scale": 5,
+        "nullable": True,
+    },
+    "cohort_day_7_revenue_per_user": {
+        "data_type": "decimal",
+        "precision": 30,
+        "scale": 5,
+        "nullable": True,
+    },
+    "cohort_day_7_total_revenue_per_user": {
+        "data_type": "decimal",
+        "precision": 30,
+        "scale": 5,
+        "nullable": True,
+    },
+    "cohort_day_14_revenue_per_user": {
+        "data_type": "decimal",
+        "precision": 30,
+        "scale": 5,
+        "nullable": True,
+    },
+    "cohort_day_14_total_revenue_per_user": {
+        "data_type": "decimal",
+        "precision": 30,
+        "scale": 5,
+        "nullable": True,
+    },
+    "cohort_day_21_revenue_per_user": {
+        "data_type": "decimal",
+        "precision": 30,
+        "scale": 5,
+        "nullable": True,
+    },
+    "cohort_day_21_total_revenue_per_user": {
+        "data_type": "decimal",
+        "precision": 30,
+        "scale": 5,
+        "nullable": True,
+    },
+    "install_time": {
+        "data_type": "date",
+        "nullable": False,
+    },
+    "loyal_users": {
+        "data_type": "bigint",
+        "nullable": False,
+    },
+    "revenue": {
+        "data_type": "decimal",
+        "precision": 30,
+        "scale": 5,
+        "nullable": True,
+    },
+    "roi": {
+        "data_type": "decimal",
+        "precision": 30,
+        "scale": 5,
+        "nullable": True,
+    },
+    "uninstalls": {
+        "data_type": "bigint",
+        "nullable": True,
+    },
+}
+
+CAMPAIGNS_DIMENSIONS = ["c", "geo", "app_id", "install_time"]
+CAMPAIGNS_METRICS = [
+    "average_ecpi",
+    "clicks",
+    "cohort_day_1_revenue_per_user",
+    "cohort_day_1_total_revenue_per_user",
+    "cohort_day_14_revenue_per_user",
+    "cohort_day_14_total_revenue_per_user",
+    "cohort_day_21_revenue_per_user",
+    "cohort_day_21_total_revenue_per_user",
+    "cohort_day_3_revenue_per_user",
+    "cohort_day_3_total_revenue_per_user",
+    "cohort_day_7_revenue_per_user",
+    "cohort_day_7_total_revenue_per_user",
+    "cost",
+    "impressions",
+    "installs",
+    "loyal_users",
+    "retention_day_7",
+    "revenue",
+    "roi",
+    "uninstalls",
+]
+
+CREATIVES_DIMENSIONS = [
+    "c",
+    "geo",
+    "app_id",
+    "install_time",
+    "af_adset_id",
+    "af_adset",
+    "af_ad_id",
+]
+CREATIVES_METRICS = [
+    "impressions",
+    "clicks",
+    "installs",
+    "cost",
+    "revenue",
+    "average_ecpi",
+    "loyal_users",
+    "uninstalls",
+    "roi",
+]
+
+
+@dlt.source(max_table_nesting=0)
+def appsflyer_source(
+    api_key: str,
+    start_date: str,
+    end_date: str,
+    dimensions: list[str],
+    metrics: list[str],
+) -> Iterable[DltResource]:
+    client = AppsflyerClient(api_key)
+
+    @dlt.resource(
+        write_disposition="merge",
+        merge_key="install_time",
+        columns=make_hints(CAMPAIGNS_DIMENSIONS, CAMPAIGNS_METRICS),
+    )
+    def campaigns(
+        datetime=dlt.sources.incremental(
+            "install_time",
+            initial_value=(
+                start_date
+                if start_date
+                else pendulum.today().subtract(days=30).format("YYYY-MM-DD")
+            ),
+            end_value=end_date,
+            range_end="closed",
+            range_start="closed",
+        ),
+    ) -> Iterable[TDataItem]:
+        end = (
+            datetime.end_value
+            if datetime.end_value
+            else pendulum.now().format("YYYY-MM-DD")
+        )
+
+        yield from client._fetch_data(
+            from_date=datetime.last_value,
+            to_date=end,
+            dimensions=CAMPAIGNS_DIMENSIONS,
+            metrics=CAMPAIGNS_METRICS,
+        )
+
+    @dlt.resource(
+        write_disposition="merge",
+        merge_key="install_time",
+        columns=make_hints(CREATIVES_DIMENSIONS, CREATIVES_METRICS),
+    )
+    def creatives(
+        datetime=dlt.sources.incremental(
+            "install_time",
+            initial_value=(
+                start_date
+                if start_date
+                else pendulum.today().subtract(days=30).format("YYYY-MM-DD")
+            ),
+            end_value=end_date,
+            range_end="closed",
+            range_start="closed",
+        ),
+    ) -> Iterable[TDataItem]:
+        end = (
+            datetime.end_value
+            if datetime.end_value
+            else pendulum.now().format("YYYY-MM-DD")
+        )
+        yield from client._fetch_data(
+            datetime.last_value,
+            end,
+            dimensions=CREATIVES_DIMENSIONS,
+            metrics=CREATIVES_METRICS,
+        )
+
+    primary_keys = []
+    if "install_time" not in dimensions:
+        dimensions.append("install_time")
+        primary_keys.append("install_time")
+
+    for dimension in dimensions:
+        if dimension in DIMENSION_RESPONSE_MAPPING:
+            primary_keys.append(DIMENSION_RESPONSE_MAPPING[dimension])
+        else:
+            primary_keys.append(dimension)
+
+    @dlt.resource(
+        write_disposition="merge",
+        primary_key=primary_keys,
+        columns=make_hints(dimensions, metrics),
+    )
+    def custom(
+        datetime=dlt.sources.incremental(
+            "install_time",
+            initial_value=(
+                start_date
+                if start_date
+                else pendulum.today().subtract(days=30).format("YYYY-MM-DD")
+            ),
+            end_value=end_date,
+        ),
+    ):
+        end = (
+            datetime.end_value
+            if datetime.end_value
+            else pendulum.now().format("YYYY-MM-DD")
+        )
+        res = client._fetch_data(
+            from_date=datetime.last_value,
+            to_date=end,
+            dimensions=dimensions,
+            metrics=metrics,
+        )
+        yield from res
+
+    return campaigns, creatives, custom
+
+
+def make_hints(dimensions: list[str], metrics: list[str]):
+    campaign_hints = {}
+    for dimension in dimensions:
+        resp_key = dimension
+        if dimension in DIMENSION_RESPONSE_MAPPING:
+            resp_key = DIMENSION_RESPONSE_MAPPING[dimension]
+
+        if resp_key in HINTS:
+            campaign_hints[resp_key] = HINTS[resp_key]
+
+    for metric in metrics:
+        if metric in HINTS:
+            campaign_hints[metric] = HINTS[metric]
+
+    return campaign_hints

ingestr-0.13.30/ingestr/src/appsflyer/client.py

@@ -0,0 +1,111 @@
+from typing import Optional
+
+import requests
+from dlt.sources.helpers.requests import Client
+from requests.exceptions import HTTPError
+
+
+class AppsflyerClient:
+    def __init__(self, api_key: str):
+        self.api_key = api_key
+        self.uri = "https://hq1.appsflyer.com/api/master-agg-data/v4/app/all"
+
+    def __get_headers(self):
+        return {
+            "Authorization": f"{self.api_key}",
+            "accept": "text/json",
+        }
+
+    def _fetch_data(
+        self,
+        from_date: str,
+        to_date: str,
+        dimensions: list[str],
+        metrics: list[str],
+        maximum_rows=1000000,
+    ):
+        excluded_metrics = exclude_metrics_for_date_range(metrics, from_date, to_date)
+        included_metrics = [
+            metric for metric in metrics if metric not in excluded_metrics
+        ]
+
+        params = {
+            "from": from_date,
+            "to": to_date,
+            "groupings": ",".join(dimensions),
+            "kpis": ",".join(included_metrics),
+            "format": "json",
+            "maximum_rows": maximum_rows,
+        }
+
+        def retry_on_limit(
+            response: Optional[requests.Response], exception: Optional[BaseException]
+        ) -> bool:
+            return (
+                isinstance(response, requests.Response) and response.status_code == 429
+            )
+
+        request_client = Client(
+            request_timeout=10.0,
+            raise_for_status=False,
+            retry_condition=retry_on_limit,
+            request_max_attempts=12,
+            request_backoff_factor=2,
+        ).session
+
+        try:
+            response = request_client.get(
+                url=self.uri, headers=self.__get_headers(), params=params
+            )
+
+            if response.status_code == 200:
+                result = response.json()
+                yield standardize_keys(result, excluded_metrics)
+            else:
+                raise HTTPError(
+                    f"Request failed with status code: {response.status_code}: {response.text}"
+                )
+
+        except requests.RequestException as e:
+            raise HTTPError(f"Request failed: {e}")
+
+
+def standardize_keys(data: list[dict], excluded_metrics: list[str]) -> list[dict]:
+    def fix_key(key: str) -> str:
+        return key.lower().replace("-", "").replace("  ", "_").replace(" ", "_")
+
+    standardized = []
+    for item in data:
+        standardized_item = {}
+        for key, value in item.items():
+            standardized_item[fix_key(key)] = value
+
+        for metric in excluded_metrics:
+            if metric not in standardized_item:
+                standardized_item[fix_key(metric)] = None
+
+        standardized.append(standardized_item)
+
+    return standardized
+
+
+def exclude_metrics_for_date_range(
+    metrics: list[str], from_date: str, to_date: str
+) -> list[str]:
+    """
+    Some of the cohort metrics are not available if there hasn't been enough time to have data for that cohort.
+    This means if you request data for yesterday with cohort day 7 metrics, you will get an error because 7 days hasn't passed yet.
+    One would expect the API to handle this gracefully, but it doesn't.
+
+    This function will exclude the metrics that are not available for the given date range.
+    """
+    import pendulum
+
+    excluded_metrics = []
+    days_between_today_and_end = (pendulum.now() - pendulum.parse(to_date)).days  # type: ignore
+    for metric in metrics:
+        if "cohort_day_" in metric:
+            day_count = int(metric.split("_")[2])
+            if days_between_today_and_end <= day_count:
+                excluded_metrics.append(metric)
+    return excluded_metrics

ingestr-0.13.30/ingestr/src/buildinfo.py

@@ -0,0 +1 @@
+version = "v0.13.30"

{ingestr-0.13.28 → ingestr-0.13.30}/ingestr/src/hubspot/__init__.py

@@ -169,7 +169,7 @@ def hubspot(
         api_key: str = api_key,
     ) -> Iterator[TDataItems]:
         """Hubspot schemas resource"""
-        yield from fetch_data(CRM_SCHEMAS_ENDPOINT, api_key,resource_name="schemas")
+        yield from fetch_data(CRM_SCHEMAS_ENDPOINT, api_key, resource_name="schemas")
 
     @dlt.resource(name="quotes", write_disposition="replace")
     def quotes(
@@ -192,8 +192,7 @@ def hubspot(
         api_key: str = api_key,
         custom_object_name: str = custom_object,
     ) -> Iterator[TDataItems]:
-
-        get_custom_object =  schemas(api_key)
+        get_custom_object = schemas(api_key)
         object_type_id = None
         for custom_object in get_custom_object:
             if custom_object["name"] == custom_object_name.capitalize():
@@ -201,18 +200,18 @@ def hubspot(
                 break
         if object_type_id is None:
             raise ValueError(f"There is no such custom object as {custom_object_name}")
-        custom_object_properties= f"crm/v3/properties/{object_type_id}"
-        
+        custom_object_properties = f"crm/v3/properties/{object_type_id}"
+
         props_pages = fetch_data(custom_object_properties, api_key)
         props = []
         for page in props_pages:
             props.extend([prop["name"] for prop in page])
         props = ",".join(sorted(list(set(props))))
-       
-        custom_object_endpoint= f"crm/v3/objects/{object_type_id}/?properties={props}"
-        
+
+        custom_object_endpoint = f"crm/v3/objects/{object_type_id}/?properties={props}"
+
         """Hubspot custom object details resource"""
-        yield from fetch_data(custom_object_endpoint, api_key,resource_name="custom")
+        yield from fetch_data(custom_object_endpoint, api_key, resource_name="custom")
 
     return companies, contacts, deals, tickets, products, quotes, schemas, custom
 

{ingestr-0.13.28 → ingestr-0.13.30}/ingestr/src/hubspot/helpers.py

@@ -90,7 +90,10 @@ def fetch_property_history(
 
 
 def fetch_data(
-    endpoint: str, api_key: str, params: Optional[Dict[str, Any]] = None,resource_name: str = None
+    endpoint: str,
+    api_key: str,
+    params: Optional[Dict[str, Any]] = None,
+    resource_name: str = None,
 ) -> Iterator[List[Dict[str, Any]]]:
     """
     Fetch data from HUBSPOT endpoint using a specified API key and yield the properties of each result.
@@ -133,15 +136,17 @@ def fetch_data(
             _objects: List[Dict[str, Any]] = []
             for _result in _data["results"]:
                 if resource_name == "schemas":
-                    _objects.append({
-                        "name": _result["labels"].get("singular", ""),
-                        "objectTypeId": _result.get("objectTypeId", ""),
-                        "id": _result.get("id", ""),
-                        "fullyQualifiedName": _result.get("fullyQualifiedName", ""),
-                        "properties": _result.get("properties", ""),
-                        "createdAt": _result.get("createdAt", ""),
-                        "updatedAt": _result.get("updatedAt", "")
-                    })
+                    _objects.append(
+                        {
+                            "name": _result["labels"].get("singular", ""),
+                            "objectTypeId": _result.get("objectTypeId", ""),
+                            "id": _result.get("id", ""),
+                            "fullyQualifiedName": _result.get("fullyQualifiedName", ""),
+                            "properties": _result.get("properties", ""),
+                            "createdAt": _result.get("createdAt", ""),
+                            "updatedAt": _result.get("updatedAt", ""),
+                        }
+                    )
                 elif resource_name == "custom":
                     _objects.append(
                         _result.get("properties", ""),
@@ -157,9 +162,11 @@ def fetch_data(
                                 {
                                     "value": _obj["hs_object_id"],
                                     f"{association}_id": __r["id"],
-                            }
-                            for __r in _result["associations"][association]["results"]
-                        ]
+                                }
+                                for __r in _result["associations"][association][
+                                    "results"
+                                ]
+                            ]
 
                         # remove duplicates from list of dicts
                         __values = [