sfeos-helpers 6.2.1__py3-none-any.whl → 6.4.0__py3-none-any.whl

{sfeos_helpers-6.2.1.dist-info → sfeos_helpers-6.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
-Name: sfeos_helpers
-Version: 6.2.1
+Metadata-Version: 2.1
+Name: sfeos-helpers
+Version: 6.4.0
 Summary: Helper library for the Elasticsearch and Opensearch stac-fastapi backends.
 Home-page: https://github.com/stac-utils/stac-fastapi-elasticsearch-opensearch
 License: MIT
@@ -15,15 +15,7 @@ Classifier: Programming Language :: Python :: 3.13
 Classifier: License :: OSI Approved :: MIT License
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
-Requires-Dist: stac-fastapi.core==6.2.1
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: license
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
+Requires-Dist: stac-fastapi.core==6.4.0
 
 # stac-fastapi-elasticsearch-opensearch
 
@@ -63,11 +55,10 @@ SFEOS (stac-fastapi-elasticsearch-opensearch) is a high-performance, scalable AP
 - **Scale to millions of geospatial assets** with fast search performance through optimized spatial indexing and query capabilities
 - **Support OGC-compliant filtering** including spatial operations (intersects, contains, etc.) and temporal queries
 - **Perform geospatial aggregations** to analyze data distribution across space and time
+- **Enhanced collection search capabilities** with support for sorting and field selection
 
 This implementation builds on the STAC-FastAPI framework, providing a production-ready solution specifically optimized for Elasticsearch and OpenSearch databases. It's ideal for organizations managing large geospatial data catalogs who need efficient discovery and access capabilities through standardized APIs.
 
-
-
 ## Common Deployment Patterns
 
 stac-fastapi-elasticsearch-opensearch can be deployed in several ways depending on your needs:
@@ -93,26 +84,44 @@ This project is built on the following technologies: STAC, stac-fastapi, FastAPI
 
 ## Table of Contents
 
-- [Documentation & Resources](#documentation--resources)
-- [Package Structure](#package-structure)
-- [Examples](#examples)
-- [Performance](#performance)
-- [Quick Start](#quick-start)
-  - [Installation](#installation)
-  - [Running Locally](#running-locally)
-- [Configuration reference](#configuration-reference)
-- [Interacting with the API](#interacting-with-the-api)
-- [Configure the API](#configure-the-api)
-- [Collection pagination](#collection-pagination)
-- [Ingesting Sample Data CLI Tool](#ingesting-sample-data-cli-tool)
-- [Elasticsearch Mappings](#elasticsearch-mappings)
-- [Managing Elasticsearch Indices](#managing-elasticsearch-indices)
-  - [Snapshots](#snapshots)
-  - [Reindexing](#reindexing)
-- [Auth](#auth)
-- [Aggregation](#aggregation)
-- [Rate Limiting](#rate-limiting)
-- [Datetime-Based Index Management](#datetime-based-index-management)
+- [stac-fastapi-elasticsearch-opensearch](#stac-fastapi-elasticsearch-opensearch)
+  - [Sponsors \& Supporters](#sponsors--supporters)
+  - [Project Introduction - What is SFEOS?](#project-introduction---what-is-sfeos)
+  - [Common Deployment Patterns](#common-deployment-patterns)
+  - [Technologies](#technologies)
+  - [Table of Contents](#table-of-contents)
+  - [Collection Search Extensions](#collection-search-extensions)
+  - [Documentation \& Resources](#documentation--resources)
+  - [Package Structure](#package-structure)
+  - [Examples](#examples)
+  - [Performance](#performance)
+    - [Direct Response Mode](#direct-response-mode)
+  - [Quick Start](#quick-start)
+    - [Installation](#installation)
+    - [Running Locally](#running-locally)
+      - [Using Pre-built Docker Images](#using-pre-built-docker-images)
+      - [Using Docker Compose](#using-docker-compose)
+  - [Configuration Reference](#configuration-reference)
+  - [Datetime-Based Index Management](#datetime-based-index-management)
+    - [Overview](#overview)
+    - [When to Use](#when-to-use)
+    - [Configuration](#configuration)
+      - [Enabling Datetime-Based Indexing](#enabling-datetime-based-indexing)
+    - [Related Configuration Variables](#related-configuration-variables)
+  - [How Datetime-Based Indexing Works](#how-datetime-based-indexing-works)
+    - [Index and Alias Naming Convention](#index-and-alias-naming-convention)
+    - [Index Size Management](#index-size-management)
+  - [Interacting with the API](#interacting-with-the-api)
+  - [Configure the API](#configure-the-api)
+  - [Collection Pagination](#collection-pagination)
+  - [Ingesting Sample Data CLI Tool](#ingesting-sample-data-cli-tool)
+  - [Elasticsearch Mappings](#elasticsearch-mappings)
+  - [Managing Elasticsearch Indices](#managing-elasticsearch-indices)
+    - [Snapshots](#snapshots)
+    - [Reindexing](#reindexing)
+  - [Auth](#auth)
+  - [Aggregation](#aggregation)
+  - [Rate Limiting](#rate-limiting)
 
 ## Documentation & Resources
 
@@ -123,6 +132,37 @@ This project is built on the following technologies: STAC, stac-fastapi, FastAPI
   - [Gitter Chat](https://app.gitter.im/#/room/#stac-fastapi-elasticsearch_community:gitter.im) - For real-time discussions
   - [GitHub Discussions](https://github.com/stac-utils/stac-fastapi-elasticsearch-opensearch/discussions) - For longer-form questions and answers
 
+## Collection Search Extensions
+
+SFEOS implements extended capabilities for the `/collections` endpoint, allowing for more powerful collection discovery:
+
+- **Sorting**: Sort collections by sortable fields using the `sortby` parameter
+  - Example: `/collections?sortby=+id` (ascending sort by ID)
+  - Example: `/collections?sortby=-id` (descending sort by ID)
+  - Example: `/collections?sortby=-temporal` (descending sort by temporal extent)
+
+- **Field Selection**: Request only specific fields to be returned using the `fields` parameter
+  - Example: `/collections?fields=id,title,description`
+  - This helps reduce payload size when only certain fields are needed
+
+- **Free Text Search**: Search across collection text fields using the `q` parameter
+  - Example: `/collections?q=landsat`
+  - Searches across multiple text fields including title, description, and keywords
+  - Supports partial word matching and relevance-based sorting
+
+These extensions make it easier to build user interfaces that display and navigate through collections efficiently.
+
+> **Configuration**: Collection search extensions can be disabled by setting the `ENABLE_COLLECTIONS_SEARCH` environment variable to `false`. By default, these extensions are enabled.
+
+> **Note**: Sorting is only available on fields that are indexed for sorting in Elasticsearch/OpenSearch. With the default mappings, you can sort on:
+> - `id` (keyword field)
+> - `extent.temporal.interval` (date field)
+> - `temporal` (alias to extent.temporal.interval)
+>
+> Text fields like `title` and `description` are not sortable by default as they use text analysis for better search capabilities. Attempting to sort on these fields will result in a user-friendly error message explaining which fields are sortable and how to make additional fields sortable by updating the mappings.
+>
+> **Important**: Adding keyword fields to make text fields sortable can significantly increase the index size, especially for large text fields. Consider the storage implications when deciding which fields to make sortable.
+
 ## Package Structure
 
 This project is organized into several packages, each with a specific purpose:
@@ -253,8 +293,12 @@ You can customize additional settings in your `.env` file:
 | `ENABLE_DIRECT_RESPONSE`     | Enable direct response for maximum performance (disables all FastAPI dependencies, including authentication, custom status codes, and validation) | `false`                  | Optional                       |
 | `RAISE_ON_BULK_ERROR`        | Controls whether bulk insert operations raise exceptions on errors. If set to `true`, the operation will stop and raise an exception when an error occurs. If set to `false`, errors will be logged, and the operation will continue. **Note:** STAC Item and ItemCollection validation errors will always raise, regardless of this flag. | `false` | Optional |
 | `DATABASE_REFRESH`           | Controls whether database operations refresh the index immediately after changes. If set to `true`, changes will be immediately searchable. If set to `false`, changes may not be immediately visible but can improve performance for bulk operations. If set to `wait_for`, changes will wait for the next refresh cycle to become visible. | `false` | Optional |
+| `ENABLE_COLLECTIONS_SEARCH`  | Enable collection search extensions (sort, fields).                                 | `true`                   | Optional                                                                                    |
 | `ENABLE_TRANSACTIONS_EXTENSIONS` | Enables or disables the Transactions and Bulk Transactions API extensions. If set to `false`, the POST `/collections` route and related transaction endpoints (including bulk transaction operations) will be unavailable in the API. This is useful for deployments where mutating the catalog via the API should be prevented. | `true` | Optional |
 | `STAC_ITEM_LIMIT` | Sets the environment variable for result limiting to SFEOS for the number of returned items and STAC collections. | `10` | Optional |
+| `STAC_INDEX_ASSETS` | Controls if Assets are indexed when added to Elasticsearch/Opensearch. This allows asset fields to be included in search queries. | `false` | Optional |
+| `ENV_MAX_LIMIT` | Configures the environment variable in SFEOS to override the default `MAX_LIMIT`, which controls the limit parameter for returned items and STAC collections. | `10,000` | Optional |
+| `USE_DATETIME` | Configures the datetime search behavior in SFEOS. When enabled, searches both datetime field and falls back to start_datetime/end_datetime range for items with null datetime. When disabled, searches only by start_datetime/end_datetime range. | True | Optional |
 
 > [!NOTE]
 > The variables `ES_HOST`, `ES_PORT`, `ES_USE_SSL`, `ES_VERIFY_CERTS` and `ES_TIMEOUT` apply to both Elasticsearch and OpenSearch backends, so there is no need to rename the key names to `OS_` even if you're using OpenSearch.
@@ -396,6 +440,10 @@ The system uses a precise naming convention:
 - **Root Path Configuration**: The application root path is the base URL by default.
   - For AWS Lambda with Gateway API: Set `STAC_FASTAPI_ROOT_PATH` to match the Gateway API stage name (e.g., `/v1`)
 
+- **Feature Configuration**: Control which features are enabled:
+  - `ENABLE_COLLECTIONS_SEARCH`: Set to `true` (default) to enable collection search extensions (sort, fields). Set to `false` to disable.
+  - `ENABLE_TRANSACTIONS_EXTENSIONS`: Set to `true` (default) to enable transaction extensions. Set to `false` to disable.
+
 
 ## Collection Pagination
 

{sfeos_helpers-6.2.1.dist-info → sfeos_helpers-6.4.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
-stac_fastapi/sfeos_helpers/mappings.py,sha256=z6GJFJUE7bRKF9ODc8_ddkb7JCOokMtj4p2LeaQqrQQ,8237
-stac_fastapi/sfeos_helpers/version.py,sha256=TvDysD5xP1CNnI8XDtkkz5sggBM1uuxjhZCv120q3AU,45
+stac_fastapi/sfeos_helpers/mappings.py,sha256=4IrI46_DRUeyry_rim2D7LnHnwQgUvMRDMnDs0Q1q14,8512
+stac_fastapi/sfeos_helpers/version.py,sha256=1xfRb7s1Stv055oEewNJpZn9OQUUcaJvgSzCsYLHYSQ,45
 stac_fastapi/sfeos_helpers/aggregation/__init__.py,sha256=Mym17lFh90by1GnoQgMyIKAqRNJnvCgVSXDYzjBiPQk,1210
 stac_fastapi/sfeos_helpers/aggregation/client.py,sha256=PPUk0kAZnms46FlLGrR5w8wa52vG-dT6BG37896R5CY,17939
 stac_fastapi/sfeos_helpers/aggregation/format.py,sha256=qUW1jjh2EEjy-V7riliFR77grpi-AgsTmP76z60K5Lo,2011
@@ -9,9 +9,9 @@ stac_fastapi/sfeos_helpers/database/document.py,sha256=LtjX15gvaOuZC_k2t_oQhys_c
 stac_fastapi/sfeos_helpers/database/index.py,sha256=g7_sKfd5XUwq4IhdKRNiasejk045dKlullsdeDSZTq8,6585
 stac_fastapi/sfeos_helpers/database/mapping.py,sha256=4-MSd4xH5wg7yoC4aPjzYMDSEvP026bw4k2TfffMT5E,1387
 stac_fastapi/sfeos_helpers/database/query.py,sha256=g2iGdfgqpx6o8GoQJBMl3AMmqcbSf792qvKWfWipR5w,4193
-stac_fastapi/sfeos_helpers/database/utils.py,sha256=sgkvjhWtQVGwQLeEXgPR6VoWpdbuVV-WJIGFUsVxqYg,8715
+stac_fastapi/sfeos_helpers/database/utils.py,sha256=9zU9hEglZb6f-uxOhd95saSw2id9w5PR36dWtyfXTb0,8757
 stac_fastapi/sfeos_helpers/filter/__init__.py,sha256=n3zL_MhEGOoxMz1KeijyK_UKiZ0MKPl90zHtYI5RAy8,1557
-stac_fastapi/sfeos_helpers/filter/client.py,sha256=QwjYWXkevoVS7HPtoXfeSzDy-_GJnFhPJtJM49D14oU,4229
+stac_fastapi/sfeos_helpers/filter/client.py,sha256=tCfqI2IBgJKF0U_0yuxjiSDLBllCqNCMcHASP4-icsA,4348
 stac_fastapi/sfeos_helpers/filter/cql2.py,sha256=Cg9kRYD9CVkVSyRqOyB5oVXmlyteSn2bw88sqklGpUM,955
 stac_fastapi/sfeos_helpers/filter/transform.py,sha256=1GEWQSp-rbq7_1nDVv1ApDbWxt8DswJWxwaxzV85gj4,4644
 stac_fastapi/sfeos_helpers/models/patch.py,sha256=s5n85ktnH6M2SMqpqyItR8uLxliXmnSTg1WO0QLVsmI,3127
@@ -26,7 +26,7 @@ stac_fastapi/sfeos_helpers/search_engine/selection/base.py,sha256=106c4FK50cgMmT
 stac_fastapi/sfeos_helpers/search_engine/selection/cache_manager.py,sha256=5yrgf9JA4mgRNMPDKih6xySF8mD724lEWnXhWud7m2c,4039
 stac_fastapi/sfeos_helpers/search_engine/selection/factory.py,sha256=vbgNVCUW2lviePqzpgsPLxp6IEqcX3GHiahqN2oVObA,1305
 stac_fastapi/sfeos_helpers/search_engine/selection/selectors.py,sha256=q83nfCfNfLUqtkHpORwNHNRU9Pa-heeaDIPO0RlHb-8,4779
-sfeos_helpers-6.2.1.dist-info/METADATA,sha256=Q_L1-BW_owsnpv1KVGneU7O0y-eP31OA-QlcHHiIpZw,34629
-sfeos_helpers-6.2.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-sfeos_helpers-6.2.1.dist-info/top_level.txt,sha256=vqn-D9-HsRPTTxy0Vk_KkDmTiMES4owwBQ3ydSZYb2s,13
-sfeos_helpers-6.2.1.dist-info/RECORD,,
+sfeos_helpers-6.4.0.dist-info/METADATA,sha256=4sXPxujytzGybiTskfZKq3E3HO9HaZriDLuw0FUypgE,38928
+sfeos_helpers-6.4.0.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+sfeos_helpers-6.4.0.dist-info/top_level.txt,sha256=vqn-D9-HsRPTTxy0Vk_KkDmTiMES4owwBQ3ydSZYb2s,13
+sfeos_helpers-6.4.0.dist-info/RECORD,,

{sfeos_helpers-6.2.1.dist-info → sfeos_helpers-6.4.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.9.0)
+Generator: bdist_wheel (0.45.1)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

stac_fastapi/sfeos_helpers/database/utils.py

@@ -114,7 +114,7 @@ def check_commands(
                 commands.add(
                     f"if (!ctx._source{part_nest}.containsKey('{path_part}'))"
                     f"{{ctx._source{part_nest}['{path_part}'] = {value};}}"
-                    f"{'' if index == len(path.parts) - 1 else' else '}"
+                    f"{'' if index == len(path.parts) - 1 else' else '}"  # noqa: E275
                 )
 
             else:
@@ -133,12 +133,12 @@ def check_commands(
                 f" && ctx._source{path.es_nest}.size() < {abs(path.key)})"
                 f" || (!(ctx._source{path.es_nest} instanceof ArrayList)"
                 f" && !ctx._source{path.es_nest}.containsKey('{path.key}')))"
-                f"{{Debug.explain('{path.key} does not exist in {path.nest}');}}"
+                f"{{Debug.explain('{path.key} does not exist in {path.nest}');}}"  # noqa: E713
             )
         else:
             commands.add(
                 f"if (!ctx._source{path.es_nest}.containsKey('{path.key}'))"
-                f"{{Debug.explain('{path.key} does not exist in {path.nest}');}}"
+                f"{{Debug.explain('{path.key} does not exist in {path.nest}');}}"  # noqa: E713
             )
 
 

stac_fastapi/sfeos_helpers/filter/client.py

@@ -4,6 +4,7 @@ from collections import deque
 from typing import Any, Dict, Optional, Tuple
 
 import attr
+from fastapi import Request
 
 from stac_fastapi.core.base_database_logic import BaseDatabaseLogic
 from stac_fastapi.core.extensions.filter import ALL_QUERYABLES, DEFAULT_QUERYABLES
@@ -37,9 +38,11 @@ class EsAsyncBaseFiltersClient(AsyncBaseFiltersClient):
         Returns:
             Dict[str, Any]: A dictionary containing the queryables for the given collection.
         """
+        request: Optional[Request] = kwargs.get("request")
+        url_str: str = str(request.url) if request else ""
         queryables: Dict[str, Any] = {
-            "$schema": "https://json-schema.org/draft/2019-09/schema",
-            "$id": "https://stac-api.example.com/queryables",
+            "$schema": "https://json-schema.org/draft-07/schema",
+            "$id": f"{url_str}",
             "type": "object",
             "title": "Queryables for STAC API",
             "description": "Queryable names for the STAC API Item Search filter.",
@@ -49,7 +52,7 @@ class EsAsyncBaseFiltersClient(AsyncBaseFiltersClient):
         if not collection_id:
             return queryables
 
-        properties: Dict[str, Any] = queryables["properties"]
+        properties: Dict[str, Any] = queryables["properties"].copy()
         queryables.update(
             {
                 "properties": properties,

stac_fastapi/sfeos_helpers/mappings.py

@@ -28,6 +28,8 @@ Function Naming Conventions:
 import os
 from typing import Any, Dict, Literal, Protocol
 
+from stac_fastapi.core.utilities import get_bool_env
+
 
 # stac_pydantic classes extend _GeometryBase, which doesn't have a type field,
 # So create our own Protocol for typing
@@ -134,7 +136,7 @@ ES_ITEMS_MAPPINGS = {
         "id": {"type": "keyword"},
         "collection": {"type": "keyword"},
         "geometry": {"type": "geo_shape"},
-        "assets": {"type": "object", "enabled": False},
+        "assets": {"type": "object", "enabled": get_bool_env("STAC_INDEX_ASSETS")},
         "links": {"type": "object", "enabled": False},
         "properties": {
             "type": "object",
@@ -162,7 +164,9 @@ ES_COLLECTIONS_MAPPINGS = {
         "extent.temporal.interval": {"type": "date"},
         "providers": {"type": "object", "enabled": False},
         "links": {"type": "object", "enabled": False},
-        "item_assets": {"type": "object", "enabled": False},
+        "item_assets": {"type": "object", "enabled": get_bool_env("STAC_INDEX_ASSETS")},
+        # Field alias to allow sorting on 'temporal' (points to extent.temporal.interval)
+        "temporal": {"type": "alias", "path": "extent.temporal.interval"},
     },
 }
 

stac_fastapi/sfeos_helpers/version.py

@@ -1,2 +1,2 @@
 """library version."""
-__version__ = "6.2.1"
+__version__ = "6.4.0"