ingestr 0.14.4__py3-none-any.whl → 0.14.6__py3-none-any.whl

ingestr/src/buildinfo.py

@@ -1 +1 @@
-version = "v0.14.4"
+version = "v0.14.6"

ingestr/src/factory.py

@@ -52,6 +52,7 @@ from ingestr.src.sources import (
     GoogleAnalyticsSource,
     GoogleSheetsSource,
     GorgiasSource,
+    HttpSource,
     HubspotSource,
     InfluxDBSource,
     IntercomSource,
@@ -64,12 +65,14 @@ from ingestr.src.sources import (
     LinkedInAdsSource,
     LocalCsvSource,
     MixpanelSource,
+    MondaySource,
     MongoDbSource,
     NotionSource,
     PersonioSource,
     PhantombusterSource,
     PinterestSource,
     PipedriveSource,
+    PlusVibeAISource,
     QuickBooksSource,
     RevenueCatSource,
     S3Source,
@@ -155,6 +158,8 @@ class SourceDestinationFactory:
         "anthropic": AnthropicSource,
         "csv": LocalCsvSource,
         "docebo": DoceboSource,
+        "http": HttpSource,
+        "https": HttpSource,
         "mongodb": MongoDbSource,
         "mongodb+srv": MongoDbSource,
         "notion": NotionSource,
@@ -212,6 +217,8 @@ class SourceDestinationFactory:
         "clickup": ClickupSource,
         "influxdb": InfluxDBSource,
         "wise": WiseSource,
+        "plusvibeai": PlusVibeAISource,
+        "monday": MondaySource,
     }
     destinations: Dict[str, Type[DestinationProtocol]] = {
         "bigquery": BigQueryDestination,

ingestr/src/http/__init__.py

@@ -0,0 +1,35 @@
+"""HTTP source for reading CSV, JSON, and Parquet files from public URLs"""
+
+from typing import Any, Optional
+
+import dlt
+from dlt.sources import DltResource
+
+from .readers import HttpReader
+
+
+@dlt.source
+def http_source(
+    url: str,
+    file_format: Optional[str] = None,
+    **kwargs: Any,
+) -> DltResource:
+    """Source for reading files from HTTP URLs.
+
+    Supports CSV, JSON, and Parquet file formats.
+
+    Args:
+        url (str): The HTTP(S) URL to the file
+        file_format (str, optional): File format ('csv', 'json', 'parquet').
+            If not provided, will be inferred from URL extension.
+        **kwargs: Additional arguments passed to the reader functions
+
+    Returns:
+        DltResource: A dlt resource that yields the file data
+    """
+    reader = HttpReader(url, file_format)
+
+    return dlt.resource(
+        reader.read_file(**kwargs),
+        name="http_data",
+    )

ingestr/src/http/readers.py

@@ -0,0 +1,114 @@
+"""Readers for HTTP file sources"""
+
+import io
+from typing import Any, Iterator, Optional
+from urllib.parse import urlparse
+
+import requests
+from dlt.sources import TDataItems
+
+
+class HttpReader:
+    """Reader for HTTP-based file sources"""
+
+    def __init__(self, url: str, file_format: Optional[str] = None):
+        self.url = url
+        self.file_format = file_format or self._infer_format(url)
+
+        if self.file_format not in ["csv", "json", "parquet"]:
+            raise ValueError(
+                f"Unsupported file format: {self.file_format}. "
+                "Supported formats: csv, json, parquet"
+            )
+
+    def _infer_format(self, url: str) -> str:
+        """Infer file format from URL extension"""
+        parsed = urlparse(url)
+        path = parsed.path.lower()
+
+        if path.endswith(".csv"):
+            return "csv"
+        elif path.endswith(".json") or path.endswith(".jsonl"):
+            return "json"
+        elif path.endswith(".parquet"):
+            return "parquet"
+        else:
+            raise ValueError(
+                f"Cannot infer file format from URL: {url}. "
+                "Please specify file_format parameter."
+            )
+
+    def _download_file(self) -> bytes:
+        """Download file from URL"""
+        response = requests.get(self.url, stream=True, timeout=30)
+        response.raise_for_status()
+        return response.content
+
+    def read_file(self, **kwargs: Any) -> Iterator[TDataItems]:
+        """Read file and yield data in chunks"""
+        content = self._download_file()
+
+        if self.file_format == "csv":
+            yield from self._read_csv(content, **kwargs)
+        elif self.file_format == "json":
+            yield from self._read_json(content, **kwargs)
+        elif self.file_format == "parquet":
+            yield from self._read_parquet(content, **kwargs)
+
+    def _read_csv(
+        self, content: bytes, chunksize: int = 10000, **pandas_kwargs: Any
+    ) -> Iterator[TDataItems]:
+        """Read CSV file with Pandas chunk by chunk"""
+        import pandas as pd  # type: ignore
+
+        kwargs = {**{"header": "infer", "chunksize": chunksize}, **pandas_kwargs}
+
+        file_obj = io.BytesIO(content)
+        for df in pd.read_csv(file_obj, **kwargs):
+            yield df.to_dict(orient="records")
+
+    def _read_json(
+        self, content: bytes, chunksize: int = 1000, **kwargs: Any
+    ) -> Iterator[TDataItems]:
+        """Read JSON or JSONL file"""
+        from dlt.common import json
+
+        file_obj = io.BytesIO(content)
+        text = file_obj.read().decode("utf-8")
+
+        # Try to detect if it's JSONL format (one JSON object per line)
+        lines = text.strip().split("\n")
+
+        if len(lines) > 1:
+            # Likely JSONL format
+            lines_chunk = []
+            for line in lines:
+                if line.strip():
+                    lines_chunk.append(json.loads(line))
+                    if len(lines_chunk) >= chunksize:
+                        yield lines_chunk
+                        lines_chunk = []
+            if lines_chunk:
+                yield lines_chunk
+        else:
+            # Single JSON object or array
+            data = json.loads(text)
+            if isinstance(data, list):
+                # Chunk the list
+                for i in range(0, len(data), chunksize):
+                    yield data[i : i + chunksize]
+            else:
+                # Single object
+                yield [data]
+
+    def _read_parquet(
+        self, content: bytes, chunksize: int = 10000, **kwargs: Any
+    ) -> Iterator[TDataItems]:
+        """Read Parquet file"""
+        from pyarrow import parquet as pq  # type: ignore
+
+        file_obj = io.BytesIO(content)
+        parquet_file = pq.ParquetFile(file_obj)
+
+        for batch in parquet_file.iter_batches(batch_size=chunksize):
+            yield batch.to_pylist()

ingestr/src/jira_source/__init__.py

@@ -37,6 +37,7 @@ def jira_source() -> Any:
         resolutions,
         project_versions,
         project_components,
+        events,
     ]
 
 
@@ -65,7 +66,11 @@ def projects(
     yield from client.get_projects(expand=expand, recent=recent)
 
 
-@dlt.resource(write_disposition="merge", primary_key="id")
+@dlt.resource(
+    write_disposition="merge",
+    primary_key="id",
+    max_table_nesting=2,
+)
 def issues(
     base_url: str = dlt.secrets.value,
     email: str = dlt.secrets.value,
@@ -312,3 +317,24 @@ def project_components(
         return []
 
     return list(client.get_project_components(project_key))
+
+
+@dlt.resource(write_disposition="replace")
+def events(
+    base_url: str = dlt.secrets.value,
+    email: str = dlt.secrets.value,
+    api_token: str = dlt.secrets.value,
+) -> Iterable[TDataItem]:
+    """
+    Fetches all event types from Jira (e.g., Issue Created, Issue Updated, etc.).
+
+    Args:
+        base_url (str): Jira instance URL
+        email (str): User email for authentication
+        api_token (str): API token for authentication
+
+    Yields:
+        dict: The event data.
+    """
+    client = get_client(base_url, email, api_token)
+    yield from client.get_events()

ingestr/src/jira_source/helpers.py

@@ -98,8 +98,6 @@ class JiraClient:
 
         for attempt in range(max_retries + 1):
             try:
-                logger.debug(f"Making request to {url} (attempt {attempt + 1})")
-
                 response = requests.request(
                     method=method,
                     url=url,
@@ -214,10 +212,6 @@ class JiraClient:
         consecutive_empty_pages = 0
         max_empty_pages = 3
 
-        logger.info(
-            f"Starting paginated request to {endpoint} with page_size={page_size}"
-        )
-
         while True:
             try:
                 response = self._make_request(endpoint, params)
@@ -238,7 +232,6 @@ class JiraClient:
                     is_last = True
                 else:
                     # Single item response
-                    logger.debug(f"Received single item response from {endpoint}")
                     yield response
                     break
 
@@ -253,27 +246,18 @@ class JiraClient:
                 else:
                     consecutive_empty_pages = 0
 
-                logger.debug(
-                    f"Retrieved {len(items)} items from {endpoint} (page {params['startAt'] // page_size + 1})"
-                )
-
                 for item in items:
                     if max_results and total_returned >= max_results:
-                        logger.info(f"Reached max_results limit of {max_results}")
                         return
                     yield item
                     total_returned += 1
 
                 # Check if we've reached the end
                 if is_last or len(items) < page_size:
-                    logger.debug(f"Reached end of pagination for {endpoint}")
                     break
 
                 # Check if we've got all available items
                 if total and total_returned >= total:
-                    logger.debug(
-                        f"Retrieved all {total} available items from {endpoint}"
-                    )
                     break
 
                 # Move to next page
@@ -295,10 +279,6 @@ class JiraClient:
                 )
                 raise JiraAPIError(f"Pagination failed: {str(e)}")
 
-        logger.info(
-            f"Completed pagination for {endpoint}, returned {total_returned} items"
-        )
-
     def search_issues(
         self,
         jql: str,
@@ -327,7 +307,7 @@ class JiraClient:
             params["expand"] = expand
 
         yield from self.get_paginated(
-            "search", params=params, page_size=page_size, max_results=max_results
+            "search/jql", params=params, page_size=page_size, max_results=max_results
         )
 
     def get_projects(
@@ -433,6 +413,13 @@ class JiraClient:
         """
         yield from self.get_paginated(f"project/{project_key}/component")
 
+    def get_events(self) -> Iterator[Dict[str, Any]]:
+        """Get all events (issue events like created, updated, etc.)."""
+        response = self._make_request("events")
+        if isinstance(response, list):
+            for event in response:
+                yield event
+
 
 def get_client(
     base_url: str, email: str, api_token: str, timeout: int = REQUEST_TIMEOUT

ingestr/src/monday/__init__.py

@@ -0,0 +1,246 @@
+"""
+Monday.com source for data extraction via GraphQL API.
+
+This source provides access to Monday.com app installation data.
+"""
+
+from typing import Any, Iterable, Iterator, Optional
+
+import dlt
+from dlt.sources import DltResource
+
+from .helpers import MondayClient, normalize_dict
+
+
+@dlt.source(max_table_nesting=0, name="monday_source")
+def monday_source(
+    api_token: str,
+    params: list[str],
+    start_date: Optional[str] = None,
+    end_date: Optional[str] = None,
+) -> Iterable[DltResource]:
+    """
+    Monday.com data source.
+
+    Args:
+        api_token: Monday.com API token for authentication
+        params: Table-specific parameters in format [table_type, ...params]
+        start_date: Optional start date for date-filtered queries (YYYY-MM-DD)
+        end_date: Optional end date for date-filtered queries (YYYY-MM-DD)
+
+    Yields:
+        DltResource: Data resource for the requested table
+    """
+    monday_client = MondayClient(api_token)
+
+    @dlt.resource(
+        name="account",
+        write_disposition="replace",
+    )
+    def fetch_account() -> Iterator[dict[str, Any]]:
+        """
+        Fetch account information from Monday.com.
+
+        Table format: account (no parameters needed)
+        """
+        if len(params) != 0:
+            raise ValueError("Account table must be in the format `account`")
+
+        yield normalize_dict(monday_client.get_account())
+
+    @dlt.resource(
+        name="account_roles",
+        write_disposition="replace",
+    )
+    def fetch_account_roles() -> Iterator[dict[str, Any]]:
+        """
+        Fetch account roles from Monday.com.
+
+        Table format: account_roles (no parameters needed)
+        """
+        if len(params) != 0:
+            raise ValueError(
+                "Account roles table must be in the format `account_roles`"
+            )
+
+        yield from monday_client.get_account_roles()
+
+    @dlt.resource(
+        name="users",
+        write_disposition="replace",
+    )
+    def fetch_users() -> Iterator[dict[str, Any]]:
+        """
+        Fetch users from Monday.com.
+
+        Table format: users (no parameters needed)
+        """
+        if len(params) != 0:
+            raise ValueError("Users table must be in the format `users`")
+
+        yield from monday_client.get_users()
+
+    @dlt.resource(
+        name="boards",
+        write_disposition="merge",
+        primary_key="id",
+    )
+    def fetch_boards(
+        updated_at: dlt.sources.incremental[str] = dlt.sources.incremental(
+            "updated_at", initial_value=start_date
+        ),
+    ) -> Iterator[dict[str, Any]]:
+        """
+        Fetch boards from Monday.com.
+
+        Table format: boards (no parameters needed)
+        """
+        if len(params) != 0:
+            raise ValueError("Boards table must be in the format `boards`")
+
+        yield from monday_client.get_boards()
+
+    @dlt.resource(
+        name="workspaces",
+        write_disposition="replace",
+    )
+    def fetch_workspaces() -> Iterator[dict[str, Any]]:
+        """
+        Fetch workspaces from Monday.com.
+
+        Table format: workspaces (no parameters needed)
+        """
+        if len(params) != 0:
+            raise ValueError("Workspaces table must be in the format `workspaces`")
+
+        yield from monday_client.get_workspaces()
+
+    @dlt.resource(
+        name="webhooks",
+        write_disposition="replace",
+    )
+    def fetch_webhooks() -> Iterator[dict[str, Any]]:
+        """
+        Fetch webhooks from Monday.com.
+
+        Table format: webhooks (no parameters needed)
+        """
+        if len(params) != 0:
+            raise ValueError("Webhooks table must be in the format `webhooks`")
+
+        yield from monday_client.get_webhooks()
+
+    @dlt.resource(
+        name="updates",
+        write_disposition="merge",
+        primary_key="id",
+    )
+    def fetch_updates(
+        updated_at: dlt.sources.incremental[str] = dlt.sources.incremental(
+            "updated_at", initial_value=start_date
+        ),
+    ) -> Iterator[dict[str, Any]]:
+        """
+        Fetch updates from Monday.com.
+
+        Table format: updates (no parameters needed)
+        Requires start_date and end_date parameters
+        """
+        if len(params) != 0:
+            raise ValueError("Updates table must be in the format `updates`")
+
+        yield from monday_client.get_updates(start_date=start_date, end_date=end_date)
+
+    @dlt.resource(
+        name="teams",
+        write_disposition="replace",
+    )
+    def fetch_teams() -> Iterator[dict[str, Any]]:
+        """
+        Fetch teams from Monday.com.
+
+        Table format: teams (no parameters needed)
+        """
+        if len(params) != 0:
+            raise ValueError("Teams table must be in the format `teams`")
+
+        yield from monday_client.get_teams()
+
+    @dlt.resource(
+        name="tags",
+        write_disposition="replace",
+    )
+    def fetch_tags() -> Iterator[dict[str, Any]]:
+        """
+        Fetch tags from Monday.com.
+
+        Table format: tags (no parameters needed)
+        """
+        if len(params) != 0:
+            raise ValueError("Tags table must be in the format `tags`")
+
+        yield from monday_client.get_tags()
+
+    @dlt.resource(
+        name="custom_activities",
+        write_disposition="replace",
+    )
+    def fetch_custom_activities() -> Iterator[dict[str, Any]]:
+        """
+        Fetch custom activities from Monday.com.
+
+        Table format: custom_activities (no parameters needed)
+        """
+        if len(params) != 0:
+            raise ValueError(
+                "Custom activities table must be in the format `custom_activities`"
+            )
+
+        yield from monday_client.get_custom_activities()
+
+    @dlt.resource(
+        name="board_columns",
+        write_disposition="replace",
+    )
+    def fetch_board_columns() -> Iterator[dict[str, Any]]:
+        """
+        Fetch board columns from Monday.com.
+
+        Table format: board_columns (no parameters needed)
+        """
+        if len(params) != 0:
+            raise ValueError(
+                "Board columns table must be in the format `board_columns`"
+            )
+
+        yield from monday_client.get_board_columns()
+
+    @dlt.resource(
+        name="board_views",
+        write_disposition="replace",
+    )
+    def fetch_board_views() -> Iterator[dict[str, Any]]:
+        """
+        Fetch board views from Monday.com.
+
+        Table format: board_views (no parameters needed)
+        """
+        if len(params) != 0:
+            raise ValueError("Board views table must be in the format `board_views`")
+
+        yield from monday_client.get_board_views()
+
+    return (
+        fetch_account,
+        fetch_account_roles,
+        fetch_users,
+        fetch_boards,
+        fetch_workspaces,
+        fetch_webhooks,
+        fetch_updates,
+        fetch_teams,
+        fetch_tags,
+        fetch_custom_activities,
+        fetch_board_columns,
+        fetch_board_views,
+    )