ingestr 0.13.64__tar.gz → 0.13.66__tar.gz

{ingestr-0.13.64 → ingestr-0.13.66}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ingestr
-Version: 0.13.64
+Version: 0.13.66
 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-0.13.64 → ingestr-0.13.66}/ingestr/src/attio/__init__.py

@@ -20,13 +20,15 @@ def attio_source(
             "created_at": {"data_type": "timestamp", "partition": True},
         },
     )
+    # https://docs.attio.com/rest-api/endpoint-reference/objects/list-objects - does not support pagination
     def fetch_objects() -> Iterator[dict]:
         if len(params) != 0:
             raise ValueError("Objects table must be in the format `objects`")
 
         path = "objects"
-        yield attio_client.fetch_data(path, "get")
+        yield attio_client.fetch_all(path, "get")
 
+    # https://docs.attio.com/rest-api/endpoint-reference/records/list-records
     @dlt.resource(
         name="records",
         write_disposition="replace",
@@ -39,12 +41,12 @@ def attio_source(
             raise ValueError(
                 "Records table must be in the format `records:{object_api_slug}`"
             )
-
         object_id = params[0]
         path = f"objects/{object_id}/records/query"
 
-        yield attio_client.fetch_data(path, "post")
+        yield attio_client.fetch_paginated(path, "post")
 
+    # https://docs.attio.com/rest-api/endpoint-reference/lists/list-all-lists -- does not support pagination
     @dlt.resource(
         name="lists",
         write_disposition="replace",
@@ -54,8 +56,9 @@ def attio_source(
     )
     def fetch_lists() -> Iterator[dict]:
         path = "lists"
-        yield attio_client.fetch_data(path, "get")
+        yield attio_client.fetch_all(path, "get")
 
+    # https://docs.attio.com/rest-api/endpoint-reference/entries/list-entries
     @dlt.resource(
         name="list_entries",
         write_disposition="replace",
@@ -70,7 +73,7 @@ def attio_source(
             )
         path = f"lists/{params[0]}/entries/query"
 
-        yield attio_client.fetch_data(path, "post")
+        yield attio_client.fetch_paginated(path, "post")
 
     @dlt.resource(
         name="all_list_entries",
@@ -85,10 +88,10 @@ def attio_source(
                 "All list entries table must be in the format `all_list_entries:{object_api_slug}`"
             )
         path = "lists"
-        for lst in attio_client.fetch_data(path, "get"):
+        for lst in attio_client.fetch_all(path, "get"):
             if params[0] in lst["parent_object"]:
                 path = f"lists/{lst['id']['list_id']}/entries/query"
-                yield from attio_client.fetch_data(path, "post")
+                yield from attio_client.fetch_paginated(path, "post")
 
     return (
         fetch_objects,

{ingestr-0.13.64 → ingestr-0.13.66}/ingestr/src/attio/helpers.py

@@ -10,42 +10,53 @@ class AttioClient:
         }
         self.client = create_client()
 
-    def fetch_data(self, path: str, method: str, limit: int = 1000, params=None):
+    def fetch_paginated(self, path: str, method: str, limit: int = 1000, params=None):
         url = f"{self.base_url}/{path}"
         if params is None:
             params = {}
         offset = 0
         while True:
-            query_params = {**params, "limit": limit, "offset": offset}
+            query_params = {"limit": limit, "offset": offset, **params}
             if method == "get":
                 response = self.client.get(
                     url, headers=self.headers, params=query_params
                 )
             else:
-                response = self.client.post(
-                    url, headers=self.headers, params=query_params
-                )
+                json_body = {**params, "limit": limit, "offset": offset}
+                response = self.client.post(url, headers=self.headers, json=json_body)
 
             if response.status_code != 200:
                 raise Exception(f"HTTP {response.status_code} error: {response.text}")
 
             response_data = response.json()
             if "data" not in response_data:
-                print(f"API Response: {response_data}")
                 raise Exception(
                     "Attio API returned a response without the expected data"
                 )
 
             data = response_data["data"]
-
             for item in data:
                 flat_item = flatten_item(item)
                 yield flat_item
-
             if len(data) < limit:
                 break
+
             offset += limit
 
+    def fetch_all(self, path: str, method: str = "get", params=None):
+        url = f"{self.base_url}/{path}"
+        params = params or {}
+
+        if method == "get":
+            response = self.client.get(url, headers=self.headers, params=params)
+        else:
+            response = self.client.post(url, headers=self.headers, json=params)
+
+        response.raise_for_status()
+        data = response.json().get("data", [])
+        for item in data:
+            yield flatten_item(item)
+
 
 def flatten_item(item: dict) -> dict:
     if "id" in item:

ingestr-0.13.66/ingestr/src/buildinfo.py

@@ -0,0 +1 @@
+version = "v0.13.66"

{ingestr-0.13.64 → ingestr-0.13.66}/ingestr/src/destinations.py

@@ -18,14 +18,6 @@ from dlt.common.storages.configuration import FileSystemCredentials
 from dlt.destinations.impl.clickhouse.configuration import (
     ClickHouseCredentials,
 )
-from dlt.destinations.impl.mssql.configuration import MsSqlClientConfiguration
-from dlt.destinations.impl.mssql.mssql import (
-    HINT_TO_MSSQL_ATTR,
-    MsSqlJobClient,
-)
-from dlt.destinations.impl.mssql.sql_client import (
-    PyOdbcMsSqlClient,
-)
 
 from ingestr.src.errors import MissingValueError
 from ingestr.src.loader import load_dlt_file
@@ -172,72 +164,90 @@ def handle_datetimeoffset(dto_value: bytes) -> datetime.datetime:
     )
 
 
-class OdbcMsSqlClient(PyOdbcMsSqlClient):
-    SQL_COPT_SS_ACCESS_TOKEN = 1256
-    SKIP_CREDENTIALS = {"PWD", "AUTHENTICATION", "UID"}
+# MSSQL_COPT_SS_ACCESS_TOKEN is a connection attribute used to pass
+# an Azure Active Directory access token to the SQL Server ODBC driver.
+MSSQL_COPT_SS_ACCESS_TOKEN = 1256
 
-    def open_connection(self):
-        cfg = self.credentials._get_odbc_dsn_dict()
-        if (
-            cfg.get("AUTHENTICATION", "").strip().lower()
-            != "activedirectoryaccesstoken"
-        ):
-            return super().open_connection()
 
-        import pyodbc  # type: ignore
+def serialize_azure_token(token):
+    # https://github.com/mkleehammer/pyodbc/issues/228#issuecomment-494773723
+    encoded = token.encode("utf_16_le")
+    return struct.pack("<i", len(encoded)) + encoded
 
-        dsn = ";".join(
-            [f"{k}={v}" for k, v in cfg.items() if k not in self.SKIP_CREDENTIALS]
-        )
 
-        self._conn = pyodbc.connect(
-            dsn,
-            timeout=self.credentials.connect_timeout,
-            attrs_before={
-                self.SQL_COPT_SS_ACCESS_TOKEN: self.serialize_token(cfg["PWD"]),
-            },
-        )
+def build_mssql_dest():
+    # https://github.com/bruin-data/ingestr/issues/293
 
-        # https://github.com/mkleehammer/pyodbc/wiki/Using-an-Output-Converter-function
-        self._conn.add_output_converter(-155, handle_datetimeoffset)
-        self._conn.autocommit = True
-        return self._conn
-
-    def serialize_token(self, token):
-        # https://github.com/mkleehammer/pyodbc/issues/228#issuecomment-494773723
-        encoded = token.encode("utf_16_le")
-        return struct.pack("<i", len(encoded)) + encoded
-
-
-class MsSqlClient(MsSqlJobClient):
-    def __init__(
-        self,
-        schema: Schema,
-        config: MsSqlClientConfiguration,
-        capabilities: DestinationCapabilitiesContext,
-    ) -> None:
-        sql_client = OdbcMsSqlClient(
-            config.normalize_dataset_name(schema),
-            config.normalize_staging_dataset_name(schema),
-            config.credentials,
-            capabilities,
-        )
-        super(MsSqlJobClient, self).__init__(schema, config, sql_client)
-        self.config: MsSqlClientConfiguration = config
-        self.sql_client = sql_client
-        self.active_hints = HINT_TO_MSSQL_ATTR if self.config.create_indexes else {}
-        self.type_mapper = capabilities.get_type_mapper()
+    from dlt.destinations.impl.mssql.configuration import MsSqlClientConfiguration
+    from dlt.destinations.impl.mssql.mssql import (
+        HINT_TO_MSSQL_ATTR,
+        MsSqlJobClient,
+    )
+    from dlt.destinations.impl.mssql.sql_client import (
+        PyOdbcMsSqlClient,
+    )
 
+    class OdbcMsSqlClient(PyOdbcMsSqlClient):
+        SKIP_CREDENTIALS = {"PWD", "AUTHENTICATION", "UID"}
 
-class MsSqlDestImpl(dlt.destinations.mssql):
-    @property
-    def client_class(self):
-        return MsSqlClient
+        def open_connection(self):
+            cfg = self.credentials._get_odbc_dsn_dict()
+            if (
+                cfg.get("AUTHENTICATION", "").strip().lower()
+                != "activedirectoryaccesstoken"
+            ):
+                return super().open_connection()
+
+            import pyodbc  # type: ignore
+
+            dsn = ";".join(
+                [f"{k}={v}" for k, v in cfg.items() if k not in self.SKIP_CREDENTIALS]
+            )
+
+            self._conn = pyodbc.connect(
+                dsn,
+                timeout=self.credentials.connect_timeout,
+                attrs_before={
+                    MSSQL_COPT_SS_ACCESS_TOKEN: serialize_azure_token(cfg["PWD"]),
+                },
+            )
+
+            # https://github.com/mkleehammer/pyodbc/wiki/Using-an-Output-Converter-function
+            self._conn.add_output_converter(-155, handle_datetimeoffset)
+            self._conn.autocommit = True
+            return self._conn
+
+    class MsSqlClient(MsSqlJobClient):
+        def __init__(
+            self,
+            schema: Schema,
+            config: MsSqlClientConfiguration,
+            capabilities: DestinationCapabilitiesContext,
+        ) -> None:
+            sql_client = OdbcMsSqlClient(
+                config.normalize_dataset_name(schema),
+                config.normalize_staging_dataset_name(schema),
+                config.credentials,
+                capabilities,
+            )
+            super(MsSqlJobClient, self).__init__(schema, config, sql_client)
+            self.config: MsSqlClientConfiguration = config
+            self.sql_client = sql_client
+            self.active_hints = HINT_TO_MSSQL_ATTR if self.config.create_indexes else {}
+            self.type_mapper = capabilities.get_type_mapper()
+
+    class MsSqlDestImpl(dlt.destinations.mssql):
+        @property
+        def client_class(self):
+            return MsSqlClient
+
+    return MsSqlDestImpl
 
 
 class MsSQLDestination(GenericSqlDestination):
     def dlt_dest(self, uri: str, **kwargs):
-        return MsSqlDestImpl(credentials=uri, **kwargs)
+        cls = build_mssql_dest()
+        return cls(credentials=uri, **kwargs)
 
 
 class DatabricksDestination(GenericSqlDestination):

{ingestr-0.13.64 → ingestr-0.13.66}/ingestr/src/linear/__init__.py

@@ -1,38 +1,9 @@
-from typing import Any, Dict, Iterable, Iterator, Optional
+from typing import Any, Dict, Iterable, Iterator
 
 import dlt
 import pendulum
-import requests
-
-LINEAR_GRAPHQL_ENDPOINT = "https://api.linear.app/graphql"
-
-
-def _graphql(
-    api_key: str, query: str, variables: Optional[Dict[str, Any]] = None
-) -> Dict[str, Any]:
-    headers = {"Authorization": api_key, "Content-Type": "application/json"}
-    response = requests.post(
-        LINEAR_GRAPHQL_ENDPOINT,
-        json={"query": query, "variables": variables or {}},
-        headers=headers,
-    )
-    response.raise_for_status()
-    payload = response.json()
-    if "errors" in payload:
-        raise ValueError(str(payload["errors"]))
-    return payload["data"]
-
-
-def _paginate(api_key: str, query: str, root: str) -> Iterator[Dict[str, Any]]:
-    cursor: Optional[str] = None
-    while True:
-        data = _graphql(api_key, query, {"cursor": cursor})[root]
-        for item in data["nodes"]:
-            yield item
-        if not data["pageInfo"]["hasNextPage"]:
-            break
-        cursor = data["pageInfo"]["endCursor"]
 
+from .helpers import  _paginate, _normalize_issue, _normalize_team
 
 ISSUES_QUERY = """
 query Issues($cursor: String) {
@@ -43,6 +14,17 @@ query Issues($cursor: String) {
       description
       createdAt
       updatedAt
+      creator { id }
+      assignee { id}
+      state { id}
+      labels { nodes { id } }
+      cycle { id}
+      project { id }
+      subtasks: children { nodes { id title } }
+      comments(first: 250) { nodes { id body } }
+      priority
+      attachments { nodes { id } }
+      subscribers { nodes { id } }
     }
     pageInfo { hasNextPage endCursor }
   }
@@ -58,6 +40,10 @@ query Projects($cursor: String) {
       description
       createdAt
       updatedAt
+      health
+      priority
+      targetDate
+      lead { id }
     }
     pageInfo { hasNextPage endCursor }
   }
@@ -72,6 +58,11 @@ query Teams($cursor: String) {
       name
       key
       description
+      updatedAt
+      createdAt
+      memberships { nodes { id } }
+      members { nodes { id } }
+      projects { nodes { id } }
     }
     pageInfo { hasNextPage endCursor }
   }
@@ -124,7 +115,7 @@ def linear_source(
         for item in _paginate(api_key, ISSUES_QUERY, "issues"):
             if pendulum.parse(item["updatedAt"]) >= current_start_date:
                 if pendulum.parse(item["updatedAt"]) <= current_end_date:
-                    yield item
+                    yield _normalize_issue(item)
 
     @dlt.resource(name="projects", primary_key="id", write_disposition="merge")
     def projects(
@@ -152,8 +143,29 @@ def linear_source(
                     yield item
 
     @dlt.resource(name="teams", primary_key="id", write_disposition="merge")
-    def teams() -> Iterator[Dict[str, Any]]:
-        yield from _paginate(api_key, TEAMS_QUERY, "teams")
+    def teams( updated_at: dlt.sources.incremental[str] = dlt.sources.incremental(
+            "updatedAt",
+            initial_value=start_date.isoformat(),
+            end_value=end_date.isoformat() if end_date else None,
+            range_start="closed",
+            range_end="closed",
+        ),) -> Iterator[Dict[str, Any]]:
+        print(start_date)
+        if updated_at.last_value:
+            current_start_date = pendulum.parse(updated_at.last_value)
+        else:
+            current_start_date = pendulum.parse(start_date)
+        print(current_start_date)
+
+        if updated_at.end_value:
+            current_end_date = pendulum.parse(updated_at.end_value)
+        else:
+            current_end_date = pendulum.now(tz="UTC")
+
+        for item in _paginate(api_key, TEAMS_QUERY, "teams"):
+            if pendulum.parse(item["updatedAt"]) >= current_start_date:
+                if pendulum.parse(item["updatedAt"]) <= current_end_date:
+                    yield _normalize_team(item)
 
     @dlt.resource(name="users", primary_key="id", write_disposition="merge")
     def users(

ingestr-0.13.66/ingestr/src/linear/helpers.py

@@ -0,0 +1,60 @@
+import json
+from typing import Any, Dict, Iterator, Optional
+
+import requests
+
+LINEAR_GRAPHQL_ENDPOINT = "https://api.linear.app/graphql"
+
+def _graphql(
+    api_key: str, query: str, variables: Optional[Dict[str, Any]] = None
+) -> Dict[str, Any]:
+    headers = {"Authorization": api_key, "Content-Type": "application/json"}
+    response = requests.post(
+        LINEAR_GRAPHQL_ENDPOINT,
+        json={"query": query, "variables": variables or {}},
+        headers=headers,
+    )
+    response.raise_for_status()
+    payload = response.json()
+    if "errors" in payload:
+        raise ValueError(str(payload["errors"]))
+    return payload["data"]
+
+def _paginate(api_key: str, query: str, root: str) -> Iterator[Dict[str, Any]]:
+    cursor: Optional[str] = None
+    while True:
+        data = _graphql(api_key, query, {"cursor": cursor})[root]
+        for item in data["nodes"]:
+            yield item
+        if not data["pageInfo"]["hasNextPage"]:
+            break
+        cursor = data["pageInfo"]["endCursor"]
+
+def _normalize_issue(item: Dict[str, Any]) -> Dict[str, Any]:
+    field_mapping = {
+        "assignee": "assignee_id",
+        "creator": "creator_id",
+        "state": "state_id",
+        "cycle": "cycle_id",
+        "project": "project_id",
+    }
+    for key, value in field_mapping.items():
+        if item.get(key):
+            item[value] = item[key]["id"]
+            del item[key]
+        else:
+            item[value] = None
+            del item[key]
+    json_fields = ["comments", "subscribers", "attachments", "labels", "subtasks","projects", "memberships", "members"]
+    for field in json_fields:
+        if item.get(field):
+            item[f"{field}"] = item[field].get("nodes", [])
+                
+    return item
+
+def _normalize_team(item: Dict[str, Any]) -> Dict[str, Any]:
+    json_fields = ["memberships", "members", "projects"]
+    for field in json_fields:
+        if item.get(field):
+            item[f"{field}"] = item[field].get("nodes", [])
+    return item

{ingestr-0.13.64 → ingestr-0.13.66}/ingestr/src/sources.py

@@ -268,8 +268,9 @@ class SqlSource:
                 from sqlalchemy import create_engine
 
                 from ingestr.src.destinations import (
-                    OdbcMsSqlClient,
+                    MSSQL_COPT_SS_ACCESS_TOKEN,
                     handle_datetimeoffset,
+                    serialize_azure_token,
                 )
 
                 cfg = {
@@ -283,7 +284,7 @@ class SqlSource:
                     if k.lower() not in ["driver", "authentication", "connect_timeout"]:
                         cfg[k.upper()] = v[0]
 
-                token = OdbcMsSqlClient.serialize_token(None, parsed_uri.password)  # type: ignore[arg-type]
+                token = serialize_azure_token(parsed_uri.password)
                 dsn = ";".join([f"{k}={v}" for k, v in cfg.items()])
 
                 def creator():
@@ -292,7 +293,7 @@ class SqlSource:
                         autocommit=True,
                         timeout=kwargs.get("connect_timeout", 30),
                         attrs_before={
-                            OdbcMsSqlClient.SQL_COPT_SS_ACCESS_TOKEN: token,
+                            MSSQL_COPT_SS_ACCESS_TOKEN: token,
                         },
                     )
                     connection.add_output_converter(-155, handle_datetimeoffset)

ingestr-0.13.64/ingestr/src/buildinfo.py

@@ -1 +0,0 @@
-version = "v0.13.64"