dataquery-sdk 1.2.2__tar.gz → 1.2.3__tar.gz

{dataquery_sdk-1.2.2 → dataquery_sdk-1.2.3}/CHANGELOG.md

@@ -46,5 +46,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Extraction is Zip Slip-guarded, skips current-day archives, and surfaces failures via `extraction_errors` (downgrading overall status to `partial`); date windows with no available files no longer mark a multi-window run as `partial`
 ## [1.2.2] - 2026-07-18
 - MCP: new `mcp-connect` CLI command  
+## [1.2.3] - 2026-07-23
+- Pagination: new client-driven `get_next_page_async(page)` helper — read `next_link` off any paged response and hand the page back to fetch the next one (manual counterpart to the SDK-driven `iter_pages`); next-page links are resolved against the surface the page came from and never sent off-host
+- Pagination models: `items`, `page-size`, and `info` fields, plus the `next_link` property and `get_self_link()` accessor, moved onto the shared `Paginated` mixin; `FileList` is now paginated; list fields default to empty instead of being required so partial/empty envelopes parse cleanly
+- New `APIResponseError` raised when a 2xx response carries an `errors`/`error` envelope (e.g. `498 Unrecognized Page Token`); an `info` `204` "no content" envelope now yields an empty page so pagination stops cleanly, while any other unrecognized body fails loudly
+- Exports: `Paginated`, `Link`, `APIResponseError` are now part of the public API
 
 

{dataquery_sdk-1.2.2 → dataquery_sdk-1.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataquery-sdk
-Version: 1.2.2
+Version: 1.2.3
 Summary: Python SDK for DATAQUERY Data API - Query, download, and check availability of economic data files
 Author-email: DATAQUERY SDK Team <dataquery_support@jpmorgan.com>
 Project-URL: Homepage, https://github.com/jpmorganchase/dataquery-sdk

{dataquery_sdk-1.2.2 → dataquery_sdk-1.2.3}/dataquery/__init__.py

@@ -1,20 +1,6 @@
-"""
-DATAQUERY SDK - Python SDK for DATAQUERY Data API
+"""DATAQUERY SDK - Python SDK for DATAQUERY Data API."""
 
-A high-performance Python SDK for the DATAQUERY Data API, providing seamless access
-to economic data files with advanced features like querying, downloading, availability
-checking, rate limiting, retry logic, connection pool monitoring, and comprehensive logging.
-
-Quick Start:
-    >>> from dataquery import DataQuery
-    >>> async with DataQuery() as dq:
-    ...     groups = await dq.list_groups_async()
-    ...     print(f"Found {len(groups)} groups")
-
-For more information, visit: https://github.com/jpmorganchase/dataquery-sdk
-"""
-
-__version__ = "1.2.2"
+__version__ = "1.2.3"
 __author__ = "DATAQUERY SDK Team"
 __email__ = "dataquery_support@jpmorgan.com"
 __license__ = "MIT"
@@ -34,6 +20,7 @@ from .function_registry import (
 from .sse.client import SSEClient, SSEEvent
 from .sse.subscriber import NotificationDownloadManager
 from .types.exceptions import (
+    APIResponseError,
     AuthenticationError,
     AvailabilityError,
     ConfigurationError,
@@ -45,6 +32,7 @@ from .types.exceptions import (
     GroupNotFoundError,
     NetworkError,
     NotFoundError,
+    PaginationError,
     RateLimitError,
     ValidationError,
     WorkflowError,
@@ -62,6 +50,8 @@ from .types.models import (
     FileList,
     Group,
     GroupList,
+    Link,
+    Paginated,
 )
 from .utils import download_zip_async
 
@@ -71,6 +61,8 @@ __all__ = [
     "ClientConfig",
     "Group",
     "GroupList",
+    "Paginated",
+    "Link",
     "FileInfo",
     "FileList",
     "AvailabilityInfo",
@@ -81,9 +73,11 @@ __all__ = [
     "DownloadProgress",
     "DateRange",
     "DataQueryError",
+    "APIResponseError",
     "AuthenticationError",
     "ValidationError",
     "NotFoundError",
+    "PaginationError",
     "RateLimitError",
     "NetworkError",
     "ConfigurationError",

{dataquery_sdk-1.2.2 → dataquery_sdk-1.2.3}/dataquery/cli.py

@@ -11,8 +11,6 @@ from typing import Any, Dict, List, Optional
 from dataquery import DataQuery
 from dataquery.types.exceptions import DataQueryError
 
-# ── Output helpers (legacy-CLI "summary + --- JSON ---" format) ────────────
-
 
 def _to_dict(payload: Any) -> Dict[str, Any]:
     """Normalize a Pydantic model or dict into a plain dict for JSON dump."""
@@ -204,8 +202,6 @@ def create_parser() -> argparse.ArgumentParser:
     p_fn.add_argument("--list", action="store_true", help="List all available functions")
     p_fn.add_argument("--json", action="store_true", help="Output raw JSON")
 
-    # ── DataQuery API v2 endpoints (skill-facing surface) ────────────────
-
     def _ts_args(p: argparse.ArgumentParser) -> None:
         p.add_argument("--data", choices=["REFERENCE_DATA", "NO_REFERENCE_DATA", "ALL"], default=None)
         p.add_argument("--start-date", help="YYYYMMDD or TODAY-Nx (x=D/W/M/Y). Default: TODAY-1D")
@@ -518,9 +514,6 @@ async def cmd_search(args: argparse.Namespace) -> int:
     return 0
 
 
-# ── DataQuery API v2 command handlers ────────────────────────────────────
-
-
 async def cmd_groups_search(args: argparse.Namespace) -> int:
     async with DataQuery(args.env_file) as dq:
         items = await dq.search_groups_async(args.keywords, page=args.page)
@@ -732,14 +725,7 @@ def cmd_function_help(args: argparse.Namespace) -> int:
 
 
 async def cmd_mcp_connect(args: argparse.Namespace) -> int:
-    """Bridge a desktop MCP client (stdio) to a remote streamable-HTTP MCP server.
-
-    Mints an OAuth client-credentials (AuthE) token with the SDK's own
-    TokenManager from the ``DATAQUERY_*`` environment and attaches a fresh bearer
-    token to every upstream request. Launched by an MCP client as its stdio
-    ``command``; stdout carries only the MCP JSON-RPC stream, so all diagnostics
-    go to stderr.
-    """
+    """Bridge a desktop MCP client (stdio) to a remote streamable-HTTP MCP server."""
     try:
         import httpx
         from fastmcp import FastMCP
@@ -764,7 +750,7 @@ async def cmd_mcp_connect(args: argparse.Namespace) -> int:
         """Stamp a fresh AuthE bearer token (from the SDK TokenManager) per request."""
 
         async def async_auth_flow(self, request: httpx.Request) -> AsyncGenerator[httpx.Request, httpx.Response]:
-            header = await token_manager.get_valid_token()  # "Bearer <jwt>"
+            header = await token_manager.get_valid_token()
             if not header:
                 raise DataQueryError(
                     "Could not obtain an OAuth token \u2014 check DATAQUERY_CLIENT_ID, "
@@ -776,7 +762,6 @@ async def cmd_mcp_connect(args: argparse.Namespace) -> int:
 
     transport = StreamableHttpTransport(args.url, auth=_AutheAuth())
     proxy = FastMCP.as_proxy(transport, name=args.name)
-    # stdout is reserved for the MCP JSON-RPC stream; keep the banner off it.
     await proxy.run_async(transport="stdio", show_banner=False)
     return 0
 

{dataquery_sdk-1.2.2 → dataquery_sdk-1.2.3}/dataquery/config/env.py

@@ -1,15 +1,4 @@
-"""
-Environment-based configuration for the DATAQUERY SDK.
-
-Loads settings from environment variables (or a ``.env`` file) into a
-:class:`ClientConfig` Pydantic model. Field declarations live on
-``ClientConfig`` — this module only handles the env-var → field projection,
-type coercion, and cross-field validation.
-
-Single source of truth: :data:`ClientConfig.model_fields`. The
-``DEFAULTS`` table here is derived from the model at import time so the two
-cannot drift.
-"""
+"""Environment-based configuration for the DATAQUERY SDK."""
 
 from __future__ import annotations
 
@@ -57,12 +46,7 @@ def _unwrap_optional(annotation: Any) -> Any:
 
 
 def _build_defaults() -> Dict[str, Optional[str]]:
-    """Compute the ``EnvConfig.DEFAULTS`` table from the model.
-
-    Booleans become ``"true"``/``"false"`` (lowercase, matching the
-    tokens :meth:`EnvConfig.get_bool` accepts). Numeric / string defaults
-    are stringified directly. ``None`` defaults stay ``None``.
-    """
+    """Compute the ``EnvConfig.DEFAULTS`` table from the model."""
     defaults: Dict[str, Optional[str]] = {}
     for field_name, field in ClientConfig.model_fields.items():
         env_key = _env_name_for(field_name)
@@ -79,12 +63,7 @@ def _build_defaults() -> Dict[str, Optional[str]]:
 
 
 class EnvConfig:
-    """Environment-based configuration loader for the DataQuery SDK.
-
-    All methods are class methods — this class is a namespace, never
-    instantiated. Field definitions, types, and defaults all originate from
-    :class:`dataquery.types.models.ClientConfig`.
-    """
+    """Environment-based configuration loader for the DataQuery SDK."""
 
     PREFIX = "DATAQUERY_"
     DEFAULTS: Dict[str, Optional[str]] = _build_defaults()
@@ -146,11 +125,7 @@ class EnvConfig:
         config_data: Optional[Dict[str, Any]] = None,
         env_file: Optional[Path] = None,
     ) -> ClientConfig:
-        """Build a :class:`ClientConfig` from env vars or an explicit dict.
-
-        When ``config_data`` is provided the env-var path is skipped entirely
-        — the dict is passed straight to :class:`ClientConfig`.
-        """
+        """Build a :class:`ClientConfig` from env vars or an explicit dict."""
         if config_data is not None:
             return ClientConfig(**config_data)
 
@@ -275,11 +250,7 @@ class EnvConfig:
 
     @classmethod
     def create_env_template(cls, output_path: Optional[Path] = None) -> Path:
-        """Write a ``.env`` template listing every supported variable.
-
-        Lines are auto-generated from :data:`ClientConfig.model_fields` so a
-        new field shows up here automatically (no separate maintenance).
-        """
+        """Write a ``.env`` template listing every supported variable."""
         if output_path is None:
             output_path = Path(".env.template")
         if not isinstance(output_path, Path):

{dataquery_sdk-1.2.2 → dataquery_sdk-1.2.3}/dataquery/config/logging.py

@@ -1,9 +1,4 @@
-"""
-Enhanced logging configuration for the DATAQUERY SDK.
-
-Provides structured logging, performance metrics, request/response logging,
-and configurable log levels and formats.
-"""
+"""Enhanced logging configuration for the DATAQUERY SDK."""
 
 import logging
 from dataclasses import dataclass, field
@@ -353,21 +348,7 @@ def create_logging_config(
     enable_request_logging: bool = False,
     enable_performance_logging: bool = True,
 ) -> LoggingConfig:
-    """
-    Create logging configuration.
-
-    Args:
-        level: Log level
-        format: Log format
-        enable_console: Whether to enable console logging
-        enable_file: Whether to enable file logging
-        log_file: Path to log file
-        enable_request_logging: Whether to log HTTP requests/responses
-        enable_performance_logging: Whether to log performance metrics
-
-    Returns:
-        Logging configuration
-    """
+    """Create logging configuration."""
     return LoggingConfig(
         level=level,
         format=format,
@@ -380,13 +361,5 @@ def create_logging_config(
 
 
 def create_logging_manager(config: LoggingConfig) -> LoggingManager:
-    """
-    Create a logging manager with the specified configuration.
-
-    Args:
-        config: Logging configuration
-
-    Returns:
-        Configured logging manager
-    """
+    """Create a logging manager with the specified configuration."""
     return LoggingManager(config)

{dataquery_sdk-1.2.2 → dataquery_sdk-1.2.3}/dataquery/constants/__init__.py

@@ -1,16 +1,4 @@
-"""Internal tunable constants used across the SDK.
-
-Centralizing these values here avoids drift between code paths that must agree
-(e.g. the single-stream and parallel downloaders share thresholds) and gives a
-single place to adjust tunables. Pydantic model field defaults and validation
-bounds are intentionally NOT hoisted here — those are part of the public
-schema.
-
-Constants are organized into topical submodules; this ``__init__`` re-exports
-them so existing call sites using ``from . import constants as C`` keep
-working without change. New code may also import from a specific submodule,
-e.g. ``from dataquery.constants.api import API_GROUPS``.
-"""
+"""Internal tunable constants used across the SDK."""
 
 from __future__ import annotations
 

{dataquery_sdk-1.2.2 → dataquery_sdk-1.2.3}/dataquery/constants/api.py

@@ -1,8 +1,4 @@
-"""API endpoint paths.
-
-Paths are relative to the main API base URL (``_build_api_url``) or the files
-API base URL (``_build_files_api_url``) unless otherwise noted.
-"""
+"""API endpoint paths."""
 
 from __future__ import annotations
 

{dataquery_sdk-1.2.2 → dataquery_sdk-1.2.3}/dataquery/constants/download.py

@@ -26,15 +26,6 @@ TEMP_SUFFIX = ".part"
 MBPS_TO_BYTES_PER_SECOND = 125_000
 
 
-# Default size, in days, of each chunk when splitting a date range so that
-# the available-files endpoint is queried over a smaller window per call.
-# Used by ``split_date_range_into_chunks``. The endpoint caps each call at
-# one calendar month; smaller windows just keep responses lighter. (The old
-# group-level limits, e.g. 14 days for RESEARCH_EQUITY_ALL, were lifted
-# server-side.)
 DEFAULT_WRITTEN_RESEARCH_CHUNK_DAYS: int = 7
 
-# Error string set on the OperationReport when the available-files endpoint
-# returns nothing for a date window. Chunked workflows match on it to tell
-# a quiet window apart from a real failure.
 NO_FILES_FOUND_ERROR: str = "No available files found for date range"