sfeos-helpers 6.5.1__py3-none-any.whl → 6.6.0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- sfeos_helpers-6.6.0.dist-info/METADATA +43 -0
- {sfeos_helpers-6.5.1.dist-info → sfeos_helpers-6.6.0.dist-info}/RECORD +11 -9
- {sfeos_helpers-6.5.1.dist-info → sfeos_helpers-6.6.0.dist-info}/WHEEL +1 -2
- stac_fastapi/sfeos_helpers/aggregation/README.md +57 -0
- stac_fastapi/sfeos_helpers/database/README.md +61 -0
- stac_fastapi/sfeos_helpers/database/__init__.py +6 -1
- stac_fastapi/sfeos_helpers/database/query.py +136 -1
- stac_fastapi/sfeos_helpers/database/utils.py +80 -2
- stac_fastapi/sfeos_helpers/filter/README.md +27 -0
- stac_fastapi/sfeos_helpers/mappings.py +1 -1
- stac_fastapi/sfeos_helpers/version.py +1 -1
- sfeos_helpers-6.5.1.dist-info/METADATA +0 -714
- sfeos_helpers-6.5.1.dist-info/top_level.txt +0 -1
|
@@ -0,0 +1,43 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: sfeos_helpers
|
|
3
|
+
Version: 6.6.0
|
|
4
|
+
Summary: Helper library for the Elasticsearch and Opensearch stac-fastapi backends.
|
|
5
|
+
Project-URL: Homepage, https://github.com/stac-utils/stac-fastapi-elasticsearch-opensearch
|
|
6
|
+
License: MIT
|
|
7
|
+
Keywords: Elasticsearch,FastAPI,Opensearch,STAC,STAC-API,stac-fastapi
|
|
8
|
+
Classifier: Intended Audience :: Developers
|
|
9
|
+
Classifier: Intended Audience :: Information Technology
|
|
10
|
+
Classifier: Intended Audience :: Science/Research
|
|
11
|
+
Classifier: License :: OSI Approved :: MIT License
|
|
12
|
+
Classifier: Programming Language :: Python :: 3.9
|
|
13
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
14
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
15
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
16
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
17
|
+
Classifier: Programming Language :: Python :: 3.14
|
|
18
|
+
Requires-Python: >=3.9
|
|
19
|
+
Requires-Dist: stac-fastapi-core==6.6.0
|
|
20
|
+
Description-Content-Type: text/markdown
|
|
21
|
+
|
|
22
|
+
# sfeos-helpers
|
|
23
|
+
|
|
24
|
+
Helper utilities for the stac-fastapi project. For full documentation, please see the [main README](https://github.com/stac-utils/stac-fastapi-elasticsearch-opensearch/blob/main/README.md).
|
|
25
|
+
|
|
26
|
+
## Package Information
|
|
27
|
+
|
|
28
|
+
- **Package name**: sfeos-helpers
|
|
29
|
+
- **Description**: Helper utilities for the stac-fastapi project.
|
|
30
|
+
- **Documentation**: [https://stac-utils.github.io/stac-fastapi-elasticsearch-opensearch/](https://stac-utils.github.io/stac-fastapi-elasticsearch-opensearch/)
|
|
31
|
+
- **Source**: [GitHub Repository](https://github.com/stac-utils/stac-fastapi-elasticsearch-opensearch/)
|
|
32
|
+
|
|
33
|
+
## Installation
|
|
34
|
+
|
|
35
|
+
This package is a dependency of stac-fastapi-elasticsearch and stac-fastapi-opensearch and is typically installed automatically.
|
|
36
|
+
|
|
37
|
+
```bash
|
|
38
|
+
pip install stac-fastapi-elasticsearch # or stac-fastapi-opensearch
|
|
39
|
+
```
|
|
40
|
+
|
|
41
|
+
## Quick Start
|
|
42
|
+
|
|
43
|
+
For detailed usage and examples, please refer to the [main documentation](https://stac-utils.github.io/stac-fastapi-elasticsearch-opensearch/).
|
|
@@ -1,15 +1,18 @@
|
|
|
1
|
-
stac_fastapi/sfeos_helpers/mappings.py,sha256=
|
|
2
|
-
stac_fastapi/sfeos_helpers/version.py,sha256=
|
|
1
|
+
stac_fastapi/sfeos_helpers/mappings.py,sha256=IqYd0tQUG-FnWVg6Fp1MU9audntF_-pMGm-BUTGbZMM,8596
|
|
2
|
+
stac_fastapi/sfeos_helpers/version.py,sha256=zPQp-GtLh4R45hT8V_KAWzwZcP4-jyw7Xjms_eNMZBc,45
|
|
3
|
+
stac_fastapi/sfeos_helpers/aggregation/README.md,sha256=SDlvCOpKyaJrlJvx84T2RzCnGALe_PK51zNeo3RP9ac,2122
|
|
3
4
|
stac_fastapi/sfeos_helpers/aggregation/__init__.py,sha256=Mym17lFh90by1GnoQgMyIKAqRNJnvCgVSXDYzjBiPQk,1210
|
|
4
5
|
stac_fastapi/sfeos_helpers/aggregation/client.py,sha256=PPUk0kAZnms46FlLGrR5w8wa52vG-dT6BG37896R5CY,17939
|
|
5
6
|
stac_fastapi/sfeos_helpers/aggregation/format.py,sha256=qUW1jjh2EEjy-V7riliFR77grpi-AgsTmP76z60K5Lo,2011
|
|
6
|
-
stac_fastapi/sfeos_helpers/database/
|
|
7
|
+
stac_fastapi/sfeos_helpers/database/README.md,sha256=TVYFDD4PqDD57ZsWBv4i4LawaL_DAEIOjM6OQuqwLAU,4049
|
|
8
|
+
stac_fastapi/sfeos_helpers/database/__init__.py,sha256=Kvnz8hpXq_sSz8K5OW3PoPsvh9864Vv1zWhI5hxgd4o,2891
|
|
7
9
|
stac_fastapi/sfeos_helpers/database/datetime.py,sha256=XMyi9Q09cuP_hj97qbGbHFtelq7WQVPdehUfzqNZFV4,4040
|
|
8
10
|
stac_fastapi/sfeos_helpers/database/document.py,sha256=LtjX15gvaOuZC_k2t_oQhys_c-zRTLN5rwX0hNJkHnM,1725
|
|
9
11
|
stac_fastapi/sfeos_helpers/database/index.py,sha256=g7_sKfd5XUwq4IhdKRNiasejk045dKlullsdeDSZTq8,6585
|
|
10
12
|
stac_fastapi/sfeos_helpers/database/mapping.py,sha256=4-MSd4xH5wg7yoC4aPjzYMDSEvP026bw4k2TfffMT5E,1387
|
|
11
|
-
stac_fastapi/sfeos_helpers/database/query.py,sha256=
|
|
12
|
-
stac_fastapi/sfeos_helpers/database/utils.py,sha256=
|
|
13
|
+
stac_fastapi/sfeos_helpers/database/query.py,sha256=bbSYe0cLC7oFbhkHR5WTKCF7Ca9iZI3fdanD90KYN98,9476
|
|
14
|
+
stac_fastapi/sfeos_helpers/database/utils.py,sha256=CLtZgoUT37oklc9MsExXsxDviv4bzK-ZP7oxAOXS32Y,11780
|
|
15
|
+
stac_fastapi/sfeos_helpers/filter/README.md,sha256=HT8h7RN7iYgUb-Tf3kOrS2C7_I7dHBZCw1CV1_XVMr4,1947
|
|
13
16
|
stac_fastapi/sfeos_helpers/filter/__init__.py,sha256=n3zL_MhEGOoxMz1KeijyK_UKiZ0MKPl90zHtYI5RAy8,1557
|
|
14
17
|
stac_fastapi/sfeos_helpers/filter/client.py,sha256=QQ6gnUEMqzS_qG8G5QHcX9x3LNk5JvCp1rRJltMTmM4,4414
|
|
15
18
|
stac_fastapi/sfeos_helpers/filter/cql2.py,sha256=Cg9kRYD9CVkVSyRqOyB5oVXmlyteSn2bw88sqklGpUM,955
|
|
@@ -26,7 +29,6 @@ stac_fastapi/sfeos_helpers/search_engine/selection/base.py,sha256=106c4FK50cgMmT
|
|
|
26
29
|
stac_fastapi/sfeos_helpers/search_engine/selection/cache_manager.py,sha256=5yrgf9JA4mgRNMPDKih6xySF8mD724lEWnXhWud7m2c,4039
|
|
27
30
|
stac_fastapi/sfeos_helpers/search_engine/selection/factory.py,sha256=vbgNVCUW2lviePqzpgsPLxp6IEqcX3GHiahqN2oVObA,1305
|
|
28
31
|
stac_fastapi/sfeos_helpers/search_engine/selection/selectors.py,sha256=q83nfCfNfLUqtkHpORwNHNRU9Pa-heeaDIPO0RlHb-8,4779
|
|
29
|
-
sfeos_helpers-6.
|
|
30
|
-
sfeos_helpers-6.
|
|
31
|
-
sfeos_helpers-6.
|
|
32
|
-
sfeos_helpers-6.5.1.dist-info/RECORD,,
|
|
32
|
+
sfeos_helpers-6.6.0.dist-info/METADATA,sha256=g9JGbrU5C9k4Tem68ICmSHSJbd1gsHRFCvO--USKuWc,1911
|
|
33
|
+
sfeos_helpers-6.6.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
|
|
34
|
+
sfeos_helpers-6.6.0.dist-info/RECORD,,
|
|
@@ -0,0 +1,57 @@
|
|
|
1
|
+
# STAC FastAPI Aggregation Package
|
|
2
|
+
|
|
3
|
+
This package contains shared aggregation functionality used by both the Elasticsearch and OpenSearch implementations of STAC FastAPI. It helps reduce code duplication and ensures consistent behavior between the two implementations.
|
|
4
|
+
|
|
5
|
+
## Package Structure
|
|
6
|
+
|
|
7
|
+
The aggregation package is organized into three main modules:
|
|
8
|
+
|
|
9
|
+
- **client.py**: Contains the base aggregation client implementation
|
|
10
|
+
- `EsAsyncBaseAggregationClient`: The main class that implements the STAC aggregation extension for Elasticsearch/OpenSearch
|
|
11
|
+
- Methods for handling aggregation requests, validating parameters, and formatting responses
|
|
12
|
+
|
|
13
|
+
- **format.py**: Contains functions for formatting aggregation responses
|
|
14
|
+
- `frequency_agg`: Formats frequency distribution aggregation responses
|
|
15
|
+
- `metric_agg`: Formats metric aggregation responses
|
|
16
|
+
|
|
17
|
+
- **__init__.py**: Package initialization and exports
|
|
18
|
+
- Exports the main classes and functions for use by other modules
|
|
19
|
+
|
|
20
|
+
## Features
|
|
21
|
+
|
|
22
|
+
The aggregation package provides the following features:
|
|
23
|
+
|
|
24
|
+
- Support for various aggregation types:
|
|
25
|
+
- Datetime frequency
|
|
26
|
+
- Collection frequency
|
|
27
|
+
- Property frequency
|
|
28
|
+
- Geospatial grid aggregations (geohash, geohex, geotile)
|
|
29
|
+
- Metric aggregations (min, max, etc.)
|
|
30
|
+
|
|
31
|
+
- Parameter validation:
|
|
32
|
+
- Precision validation for geospatial aggregations
|
|
33
|
+
- Interval validation for datetime aggregations
|
|
34
|
+
|
|
35
|
+
- Response formatting:
|
|
36
|
+
- Consistent response structure
|
|
37
|
+
- Proper typing and documentation
|
|
38
|
+
|
|
39
|
+
## Usage
|
|
40
|
+
|
|
41
|
+
The aggregation package is used by the Elasticsearch and OpenSearch implementations to provide aggregation functionality for STAC API. The main entry point is the `EsAsyncBaseAggregationClient` class, which is instantiated in the respective app.py files.
|
|
42
|
+
|
|
43
|
+
Example:
|
|
44
|
+
```python
|
|
45
|
+
from stac_fastapi.sfeos_helpers.aggregation import EsAsyncBaseAggregationClient
|
|
46
|
+
|
|
47
|
+
# Create an instance of the aggregation client
|
|
48
|
+
aggregation_client = EsAsyncBaseAggregationClient(database)
|
|
49
|
+
|
|
50
|
+
# Register the aggregation extension with the API
|
|
51
|
+
api = StacApi(
|
|
52
|
+
...,
|
|
53
|
+
extensions=[
|
|
54
|
+
...,
|
|
55
|
+
AggregationExtension(client=aggregation_client),
|
|
56
|
+
],
|
|
57
|
+
)
|
|
@@ -0,0 +1,61 @@
|
|
|
1
|
+
# STAC FastAPI Database Package
|
|
2
|
+
|
|
3
|
+
This package contains shared database operations used by both the Elasticsearch and OpenSearch
|
|
4
|
+
implementations of STAC FastAPI. It helps reduce code duplication and ensures consistent behavior
|
|
5
|
+
between the two implementations.
|
|
6
|
+
|
|
7
|
+
## Package Structure
|
|
8
|
+
|
|
9
|
+
The database package is organized into five main modules:
|
|
10
|
+
|
|
11
|
+
- **index.py**: Contains functions for managing indices
|
|
12
|
+
- [create_index_templates_shared](cci:1://file:///home/computer/Code/stac-fastapi-elasticsearch-opensearch/stac_fastapi/sfeos_helpers/stac_fastapi/sfeos_helpers/database_logic_helpers.py:15:0-48:33): Creates index templates for Collections and Items
|
|
13
|
+
- [delete_item_index_shared](cci:1://file:///home/computer/Code/stac-fastapi-elasticsearch-opensearch/stac_fastapi/sfeos_helpers/stac_fastapi/sfeos_helpers/database_logic_helpers.py:128:0-153:30): Deletes an item index for a collection
|
|
14
|
+
- [index_by_collection_id](cci:1://file:///home/computer/Code/stac-fastapi-elasticsearch-opensearch/stac_fastapi/sfeos_helpers/stac_fastapi/sfeos_helpers/utilities.py:86:0-100:5): Translates a collection ID into an index name
|
|
15
|
+
- [index_alias_by_collection_id](cci:1://file:///home/computer/Code/stac-fastapi-elasticsearch-opensearch/stac_fastapi/sfeos_helpers/stac_fastapi/sfeos_helpers/utilities.py:103:0-115:5): Translates a collection ID into an index alias
|
|
16
|
+
- [indices](cci:1://file:///home/computer/Code/stac-fastapi-elasticsearch-opensearch/stac_fastapi/sfeos_helpers/stac_fastapi/sfeos_helpers/utilities.py:118:0-132:5): Gets a comma-separated string of index names
|
|
17
|
+
|
|
18
|
+
- **query.py**: Contains functions for building and manipulating queries
|
|
19
|
+
- [apply_free_text_filter_shared](cci:1://file:///home/computer/Code/stac-fastapi-elasticsearch-opensearch/stac_fastapi/sfeos_helpers/stac_fastapi/sfeos_helpers/database_logic_helpers.py:51:0-74:16): Applies a free text filter to a search
|
|
20
|
+
- [apply_intersects_filter_shared](cci:1://file:///home/computer/Code/stac-fastapi-elasticsearch-opensearch/stac_fastapi/sfeos_helpers/stac_fastapi/sfeos_helpers/database_logic_helpers.py:77:0-104:5): Creates a geo_shape filter for intersecting geometry
|
|
21
|
+
- [populate_sort_shared](cci:1://file:///home/computer/Code/stac-fastapi-elasticsearch-opensearch/stac_fastapi/sfeos_helpers/stac_fastapi/sfeos_helpers/database_logic_helpers.py:107:0-125:16): Creates a sort configuration for queries
|
|
22
|
+
|
|
23
|
+
- **mapping.py**: Contains functions for working with mappings
|
|
24
|
+
- [get_queryables_mapping_shared](cci:1://file:///home/computer/Code/stac-fastapi-elasticsearch-opensearch/stac_fastapi/sfeos_helpers/stac_fastapi/sfeos_helpers/database_logic_helpers.py:156:0-185:27): Retrieves mapping of Queryables for search
|
|
25
|
+
|
|
26
|
+
- **document.py**: Contains functions for working with documents
|
|
27
|
+
- [mk_item_id](cci:1://file:///home/computer/Code/stac-fastapi-elasticsearch-opensearch/stac_fastapi/sfeos_helpers/stac_fastapi/sfeos_helpers/utilities.py:140:0-150:5): Creates a document ID for an Item
|
|
28
|
+
- [mk_actions](cci:1://file:///home/computer/Code/stac-fastapi-elasticsearch-opensearch/stac_fastapi/sfeos_helpers/stac_fastapi/sfeos_helpers/utilities.py:153:0-175:5): Creates bulk actions for indexing items
|
|
29
|
+
|
|
30
|
+
- **utils.py**: Contains utility functions for database operations
|
|
31
|
+
- [validate_refresh](cci:1://file:///home/computer/Code/stac-fastapi-elasticsearch-opensearch/stac_fastapi/sfeos_helpers/stac_fastapi/sfeos_helpers/utilities.py:41:0-78:5): Validates the refresh parameter value
|
|
32
|
+
|
|
33
|
+
## Usage
|
|
34
|
+
|
|
35
|
+
Import the necessary components from the database package:
|
|
36
|
+
|
|
37
|
+
```python
|
|
38
|
+
from stac_fastapi.sfeos_helpers.database import (
|
|
39
|
+
# Index operations
|
|
40
|
+
create_index_templates_shared,
|
|
41
|
+
delete_item_index_shared,
|
|
42
|
+
index_alias_by_collection_id,
|
|
43
|
+
index_by_collection_id,
|
|
44
|
+
indices,
|
|
45
|
+
|
|
46
|
+
# Query operations
|
|
47
|
+
apply_free_text_filter_shared,
|
|
48
|
+
apply_intersects_filter_shared,
|
|
49
|
+
populate_sort_shared,
|
|
50
|
+
|
|
51
|
+
# Mapping operations
|
|
52
|
+
get_queryables_mapping_shared,
|
|
53
|
+
|
|
54
|
+
# Document operations
|
|
55
|
+
mk_item_id,
|
|
56
|
+
mk_actions,
|
|
57
|
+
|
|
58
|
+
# Utility functions
|
|
59
|
+
validate_refresh,
|
|
60
|
+
)
|
|
61
|
+
```
|
|
@@ -42,11 +42,13 @@ from .index import (
|
|
|
42
42
|
)
|
|
43
43
|
from .mapping import get_queryables_mapping_shared
|
|
44
44
|
from .query import (
|
|
45
|
+
apply_collections_bbox_filter_shared,
|
|
46
|
+
apply_collections_datetime_filter_shared,
|
|
45
47
|
apply_free_text_filter_shared,
|
|
46
48
|
apply_intersects_filter_shared,
|
|
47
49
|
populate_sort_shared,
|
|
48
50
|
)
|
|
49
|
-
from .utils import get_bool_env, validate_refresh
|
|
51
|
+
from .utils import add_bbox_shape_to_collection, get_bool_env, validate_refresh
|
|
50
52
|
|
|
51
53
|
__all__ = [
|
|
52
54
|
# Index operations
|
|
@@ -59,6 +61,8 @@ __all__ = [
|
|
|
59
61
|
# Query operations
|
|
60
62
|
"apply_free_text_filter_shared",
|
|
61
63
|
"apply_intersects_filter_shared",
|
|
64
|
+
"apply_collections_bbox_filter_shared",
|
|
65
|
+
"apply_collections_datetime_filter_shared",
|
|
62
66
|
"populate_sort_shared",
|
|
63
67
|
# Mapping operations
|
|
64
68
|
"get_queryables_mapping_shared",
|
|
@@ -68,6 +72,7 @@ __all__ = [
|
|
|
68
72
|
# Utility functions
|
|
69
73
|
"validate_refresh",
|
|
70
74
|
"get_bool_env",
|
|
75
|
+
"add_bbox_shape_to_collection",
|
|
71
76
|
# Datetime utilities
|
|
72
77
|
"return_date",
|
|
73
78
|
"extract_date",
|
|
@@ -3,8 +3,10 @@
|
|
|
3
3
|
This module provides functions for building and manipulating Elasticsearch/OpenSearch queries.
|
|
4
4
|
"""
|
|
5
5
|
|
|
6
|
-
|
|
6
|
+
import logging
|
|
7
|
+
from typing import Any, Dict, List, Optional, Union
|
|
7
8
|
|
|
9
|
+
from stac_fastapi.core.utilities import bbox2polygon
|
|
8
10
|
from stac_fastapi.sfeos_helpers.mappings import Geometry
|
|
9
11
|
|
|
10
12
|
ES_MAX_URL_LENGTH = 4096
|
|
@@ -66,6 +68,139 @@ def apply_intersects_filter_shared(
|
|
|
66
68
|
}
|
|
67
69
|
|
|
68
70
|
|
|
71
|
+
def apply_collections_datetime_filter_shared(
|
|
72
|
+
datetime_str: Optional[str],
|
|
73
|
+
) -> Optional[Dict[str, Any]]:
|
|
74
|
+
"""Create a temporal filter for collections based on their extent.
|
|
75
|
+
|
|
76
|
+
Args:
|
|
77
|
+
datetime_str: The datetime parameter. Can be:
|
|
78
|
+
- A single datetime string (e.g., "2020-01-01T00:00:00Z")
|
|
79
|
+
- A datetime range with "/" separator (e.g., "2020-01-01T00:00:00Z/2021-01-01T00:00:00Z")
|
|
80
|
+
- Open-ended ranges using ".." (e.g., "../2021-01-01T00:00:00Z" or "2020-01-01T00:00:00Z/..")
|
|
81
|
+
- None if no datetime filter is provided
|
|
82
|
+
|
|
83
|
+
Returns:
|
|
84
|
+
Optional[Dict[str, Any]]: A dictionary containing the temporal filter configuration
|
|
85
|
+
that can be used with Elasticsearch/OpenSearch queries, or None if datetime_str is None.
|
|
86
|
+
Example return value:
|
|
87
|
+
{
|
|
88
|
+
"bool": {
|
|
89
|
+
"must": [
|
|
90
|
+
{"range": {"extent.temporal.interval": {"lte": "2021-01-01T00:00:00Z"}}},
|
|
91
|
+
{"range": {"extent.temporal.interval": {"gte": "2020-01-01T00:00:00Z"}}}
|
|
92
|
+
]
|
|
93
|
+
}
|
|
94
|
+
}
|
|
95
|
+
|
|
96
|
+
Notes:
|
|
97
|
+
- This function is specifically for filtering collections by their temporal extent
|
|
98
|
+
- It queries the extent.temporal.interval field
|
|
99
|
+
- Open-ended ranges (..) are replaced with concrete dates (1800-01-01 for start, 2999-12-31 for end)
|
|
100
|
+
"""
|
|
101
|
+
if not datetime_str:
|
|
102
|
+
return None
|
|
103
|
+
|
|
104
|
+
# Parse the datetime string into start and end
|
|
105
|
+
if "/" in datetime_str:
|
|
106
|
+
start, end = datetime_str.split("/")
|
|
107
|
+
# Replace open-ended ranges with concrete dates
|
|
108
|
+
if start == "..":
|
|
109
|
+
# For open-ended start, use a very early date
|
|
110
|
+
start = "1800-01-01T00:00:00Z"
|
|
111
|
+
if end == "..":
|
|
112
|
+
# For open-ended end, use a far future date
|
|
113
|
+
end = "2999-12-31T23:59:59Z"
|
|
114
|
+
else:
|
|
115
|
+
# If it's just a single date, use it for both start and end
|
|
116
|
+
start = end = datetime_str
|
|
117
|
+
|
|
118
|
+
return {
|
|
119
|
+
"bool": {
|
|
120
|
+
"must": [
|
|
121
|
+
# Check if any date in the array is less than or equal to the query end date
|
|
122
|
+
# This will match if the collection's start date is before or equal to the query end date
|
|
123
|
+
{"range": {"extent.temporal.interval": {"lte": end}}},
|
|
124
|
+
# Check if any date in the array is greater than or equal to the query start date
|
|
125
|
+
# This will match if the collection's end date is after or equal to the query start date
|
|
126
|
+
{"range": {"extent.temporal.interval": {"gte": start}}},
|
|
127
|
+
]
|
|
128
|
+
}
|
|
129
|
+
}
|
|
130
|
+
|
|
131
|
+
|
|
132
|
+
def apply_collections_bbox_filter_shared(
|
|
133
|
+
bbox: Union[str, List[float], None]
|
|
134
|
+
) -> Optional[Dict[str, Dict]]:
|
|
135
|
+
"""Create a geo_shape filter for collections bbox search.
|
|
136
|
+
|
|
137
|
+
This function handles bbox parsing from both GET requests (string format) and POST requests
|
|
138
|
+
(list format), and constructs a geo_shape query for filtering collections by their bbox_shape field.
|
|
139
|
+
|
|
140
|
+
Args:
|
|
141
|
+
bbox: The bounding box parameter. Can be:
|
|
142
|
+
- A string of comma-separated coordinates (from GET requests)
|
|
143
|
+
- A list of floats [minx, miny, maxx, maxy] for 2D bbox
|
|
144
|
+
- None if no bbox filter is provided
|
|
145
|
+
|
|
146
|
+
Returns:
|
|
147
|
+
Optional[Dict[str, Dict]]: A dictionary containing the geo_shape filter configuration
|
|
148
|
+
that can be used with Elasticsearch/OpenSearch queries, or None if bbox is invalid.
|
|
149
|
+
Example return value:
|
|
150
|
+
{
|
|
151
|
+
"geo_shape": {
|
|
152
|
+
"bbox_shape": {
|
|
153
|
+
"shape": {
|
|
154
|
+
"type": "Polygon",
|
|
155
|
+
"coordinates": [[[minx, miny], [maxx, miny], [maxx, maxy], [minx, maxy], [minx, miny]]]
|
|
156
|
+
},
|
|
157
|
+
"relation": "intersects"
|
|
158
|
+
}
|
|
159
|
+
}
|
|
160
|
+
}
|
|
161
|
+
|
|
162
|
+
Notes:
|
|
163
|
+
- This function is specifically for filtering collections by their spatial extent
|
|
164
|
+
- It queries the bbox_shape field (not the geometry field used for items)
|
|
165
|
+
- The bbox is expected to be 2D (4 values) after any 3D to 2D conversion in the API layer
|
|
166
|
+
"""
|
|
167
|
+
logger = logging.getLogger(__name__)
|
|
168
|
+
|
|
169
|
+
if not bbox:
|
|
170
|
+
return None
|
|
171
|
+
|
|
172
|
+
# Parse bbox if it's a string (from GET requests)
|
|
173
|
+
if isinstance(bbox, str):
|
|
174
|
+
try:
|
|
175
|
+
bbox = [float(x.strip()) for x in bbox.split(",")]
|
|
176
|
+
except (ValueError, AttributeError) as e:
|
|
177
|
+
logger.error(f"Invalid bbox format: {bbox}, error: {e}")
|
|
178
|
+
return None
|
|
179
|
+
|
|
180
|
+
if not bbox or len(bbox) != 4:
|
|
181
|
+
if bbox:
|
|
182
|
+
logger.warning(
|
|
183
|
+
f"bbox has incorrect number of coordinates (length={len(bbox)}), expected 4 (2D bbox)"
|
|
184
|
+
)
|
|
185
|
+
return None
|
|
186
|
+
|
|
187
|
+
# Convert bbox to a polygon for geo_shape query
|
|
188
|
+
bbox_polygon = {
|
|
189
|
+
"type": "Polygon",
|
|
190
|
+
"coordinates": bbox2polygon(bbox[0], bbox[1], bbox[2], bbox[3]),
|
|
191
|
+
}
|
|
192
|
+
|
|
193
|
+
# Return geo_shape query for bbox_shape field
|
|
194
|
+
return {
|
|
195
|
+
"geo_shape": {
|
|
196
|
+
"bbox_shape": {
|
|
197
|
+
"shape": bbox_polygon,
|
|
198
|
+
"relation": "intersects",
|
|
199
|
+
}
|
|
200
|
+
}
|
|
201
|
+
}
|
|
202
|
+
|
|
203
|
+
|
|
69
204
|
def populate_sort_shared(sortby: List) -> Optional[Dict[str, Dict[str, str]]]:
|
|
70
205
|
"""Create a sort configuration for Elasticsearch/OpenSearch queries.
|
|
71
206
|
|
|
@@ -5,9 +5,9 @@ in Elasticsearch/OpenSearch, such as parameter validation.
|
|
|
5
5
|
"""
|
|
6
6
|
|
|
7
7
|
import logging
|
|
8
|
-
from typing import Dict, List, Union
|
|
8
|
+
from typing import Any, Dict, List, Union
|
|
9
9
|
|
|
10
|
-
from stac_fastapi.core.utilities import get_bool_env
|
|
10
|
+
from stac_fastapi.core.utilities import bbox2polygon, get_bool_env
|
|
11
11
|
from stac_fastapi.extensions.core.transaction.request import (
|
|
12
12
|
PatchAddReplaceTest,
|
|
13
13
|
PatchOperation,
|
|
@@ -15,6 +15,84 @@ from stac_fastapi.extensions.core.transaction.request import (
|
|
|
15
15
|
)
|
|
16
16
|
from stac_fastapi.sfeos_helpers.models.patch import ElasticPath, ESCommandSet
|
|
17
17
|
|
|
18
|
+
logger = logging.getLogger(__name__)
|
|
19
|
+
|
|
20
|
+
|
|
21
|
+
def add_bbox_shape_to_collection(collection: Dict[str, Any]) -> bool:
|
|
22
|
+
"""Add bbox_shape field to a collection document for spatial queries.
|
|
23
|
+
|
|
24
|
+
This function extracts the bounding box from a collection's spatial extent
|
|
25
|
+
and converts it to a GeoJSON polygon shape that can be used for geospatial
|
|
26
|
+
queries in Elasticsearch/OpenSearch.
|
|
27
|
+
|
|
28
|
+
Args:
|
|
29
|
+
collection: Collection document dictionary to modify in-place.
|
|
30
|
+
|
|
31
|
+
Returns:
|
|
32
|
+
bool: True if bbox_shape was added, False if it was skipped (already exists,
|
|
33
|
+
no spatial extent, or invalid bbox).
|
|
34
|
+
|
|
35
|
+
Notes:
|
|
36
|
+
- Modifies the collection dictionary in-place by adding a 'bbox_shape' field
|
|
37
|
+
- Handles both 2D [minx, miny, maxx, maxy] and 3D [minx, miny, minz, maxx, maxy, maxz] bboxes
|
|
38
|
+
- Uses the first bbox if multiple are present in the collection
|
|
39
|
+
- Logs warnings for collections with invalid or missing bbox data
|
|
40
|
+
"""
|
|
41
|
+
collection_id = collection.get("id", "unknown")
|
|
42
|
+
|
|
43
|
+
# Check if bbox_shape already exists
|
|
44
|
+
if "bbox_shape" in collection:
|
|
45
|
+
logger.debug(
|
|
46
|
+
f"Collection '{collection_id}' already has bbox_shape field, skipping"
|
|
47
|
+
)
|
|
48
|
+
return False
|
|
49
|
+
|
|
50
|
+
# Check if collection has spatial extent
|
|
51
|
+
if "extent" not in collection or "spatial" not in collection["extent"]:
|
|
52
|
+
logger.warning(f"Collection '{collection_id}' has no spatial extent, skipping")
|
|
53
|
+
return False
|
|
54
|
+
|
|
55
|
+
spatial_extent = collection["extent"]["spatial"]
|
|
56
|
+
if "bbox" not in spatial_extent or not spatial_extent["bbox"]:
|
|
57
|
+
logger.warning(
|
|
58
|
+
f"Collection '{collection_id}' has no bbox in spatial extent, skipping"
|
|
59
|
+
)
|
|
60
|
+
return False
|
|
61
|
+
|
|
62
|
+
# Get the first bbox (collections can have multiple bboxes, but we use the first one)
|
|
63
|
+
bbox = (
|
|
64
|
+
spatial_extent["bbox"][0]
|
|
65
|
+
if isinstance(spatial_extent["bbox"][0], list)
|
|
66
|
+
else spatial_extent["bbox"]
|
|
67
|
+
)
|
|
68
|
+
|
|
69
|
+
if len(bbox) < 4:
|
|
70
|
+
logger.warning(
|
|
71
|
+
f"Collection '{collection_id}': bbox has insufficient coordinates (length={len(bbox)}), expected at least 4"
|
|
72
|
+
)
|
|
73
|
+
return False
|
|
74
|
+
|
|
75
|
+
# Extract 2D coordinates (bbox can be 2D [minx, miny, maxx, maxy] or 3D [minx, miny, minz, maxx, maxy, maxz])
|
|
76
|
+
# For 2D polygon, we only need the x,y coordinates and discard altitude (z) values
|
|
77
|
+
minx, miny = bbox[0], bbox[1]
|
|
78
|
+
if len(bbox) == 4:
|
|
79
|
+
# 2D bbox: [minx, miny, maxx, maxy]
|
|
80
|
+
maxx, maxy = bbox[2], bbox[3]
|
|
81
|
+
else:
|
|
82
|
+
# 3D bbox: [minx, miny, minz, maxx, maxy, maxz]
|
|
83
|
+
# Extract indices 3,4 for maxx,maxy - discarding altitude at indices 2 (minz) and 5 (maxz)
|
|
84
|
+
maxx, maxy = bbox[3], bbox[4]
|
|
85
|
+
|
|
86
|
+
# Convert bbox to GeoJSON polygon
|
|
87
|
+
bbox_polygon_coords = bbox2polygon(minx, miny, maxx, maxy)
|
|
88
|
+
collection["bbox_shape"] = {
|
|
89
|
+
"type": "Polygon",
|
|
90
|
+
"coordinates": bbox_polygon_coords,
|
|
91
|
+
}
|
|
92
|
+
|
|
93
|
+
logger.debug(f"Collection '{collection_id}': Added bbox_shape field")
|
|
94
|
+
return True
|
|
95
|
+
|
|
18
96
|
|
|
19
97
|
def validate_refresh(value: Union[str, bool]) -> str:
|
|
20
98
|
"""
|
|
@@ -0,0 +1,27 @@
|
|
|
1
|
+
# STAC FastAPI Filter Package
|
|
2
|
+
|
|
3
|
+
This package contains shared filter extension functionality used by both the Elasticsearch and OpenSearch
|
|
4
|
+
implementations of STAC FastAPI. It helps reduce code duplication and ensures consistent behavior
|
|
5
|
+
between the two implementations.
|
|
6
|
+
|
|
7
|
+
## Package Structure
|
|
8
|
+
|
|
9
|
+
The filter package is organized into three main modules:
|
|
10
|
+
|
|
11
|
+
- **cql2.py**: Contains functions for converting CQL2 patterns to Elasticsearch/OpenSearch compatible formats
|
|
12
|
+
- [cql2_like_to_es](cci:1://file:///home/computer/Code/stac-fastapi-elasticsearch-opensearch/stac_fastapi/sfeos_helpers/stac_fastapi/sfeos_helpers/filter.py:59:0-75:5): Converts CQL2 "LIKE" characters to Elasticsearch "wildcard" characters
|
|
13
|
+
- [_replace_like_patterns](cci:1://file:///home/computer/Code/stac-fastapi-elasticsearch-opensearch/stac_fastapi/sfeos_helpers/stac_fastapi/sfeos_helpers/filter.py:51:0-56:71): Helper function for pattern replacement
|
|
14
|
+
|
|
15
|
+
- **transform.py**: Contains functions for transforming CQL2 queries to Elasticsearch/OpenSearch query DSL
|
|
16
|
+
- [to_es_field](cci:1://file:///home/computer/Code/stac-fastapi-elasticsearch-opensearch/stac_fastapi/sfeos_helpers/stac_fastapi/sfeos_helpers/filter.py:83:0-93:47): Maps field names using queryables mapping
|
|
17
|
+
- [to_es](cci:1://file:///home/computer/Code/stac-fastapi-elasticsearch-opensearch/stac_fastapi/sfeos_helpers/stac_fastapi/sfeos_helpers/filter.py:96:0-201:13): Transforms CQL2 query structures to Elasticsearch/OpenSearch query DSL
|
|
18
|
+
|
|
19
|
+
- **client.py**: Contains the base filter client implementation
|
|
20
|
+
- [EsAsyncBaseFiltersClient](cci:2://file:///home/computer/Code/stac-fastapi-elasticsearch-opensearch/stac_fastapi/sfeos_helpers/stac_fastapi/sfeos_helpers/filter.py:209:0-293:25): Base class for implementing the STAC filter extension
|
|
21
|
+
|
|
22
|
+
## Usage
|
|
23
|
+
|
|
24
|
+
Import the necessary components from the filter package:
|
|
25
|
+
|
|
26
|
+
```python
|
|
27
|
+
from stac_fastapi.sfeos_helpers.filter import cql2_like_to_es, to_es, EsAsyncBaseFiltersClient
|
|
@@ -160,7 +160,7 @@ ES_COLLECTIONS_MAPPINGS = {
|
|
|
160
160
|
"dynamic_templates": ES_MAPPINGS_DYNAMIC_TEMPLATES,
|
|
161
161
|
"properties": {
|
|
162
162
|
"id": {"type": "keyword"},
|
|
163
|
-
"
|
|
163
|
+
"bbox_shape": {"type": "geo_shape"},
|
|
164
164
|
"extent.temporal.interval": {
|
|
165
165
|
"type": "date",
|
|
166
166
|
"format": "strict_date_optional_time||epoch_millis",
|
|
@@ -1,2 +1,2 @@
|
|
|
1
1
|
"""library version."""
|
|
2
|
-
__version__ = "6.
|
|
2
|
+
__version__ = "6.6.0"
|
|
@@ -1,714 +0,0 @@
|
|
|
1
|
-
Metadata-Version: 2.1
|
|
2
|
-
Name: sfeos-helpers
|
|
3
|
-
Version: 6.5.1
|
|
4
|
-
Summary: Helper library for the Elasticsearch and Opensearch stac-fastapi backends.
|
|
5
|
-
Home-page: https://github.com/stac-utils/stac-fastapi-elasticsearch-opensearch
|
|
6
|
-
License: MIT
|
|
7
|
-
Classifier: Intended Audience :: Developers
|
|
8
|
-
Classifier: Intended Audience :: Information Technology
|
|
9
|
-
Classifier: Intended Audience :: Science/Research
|
|
10
|
-
Classifier: Programming Language :: Python :: 3.9
|
|
11
|
-
Classifier: Programming Language :: Python :: 3.10
|
|
12
|
-
Classifier: Programming Language :: Python :: 3.11
|
|
13
|
-
Classifier: Programming Language :: Python :: 3.12
|
|
14
|
-
Classifier: Programming Language :: Python :: 3.13
|
|
15
|
-
Classifier: License :: OSI Approved :: MIT License
|
|
16
|
-
Requires-Python: >=3.9
|
|
17
|
-
Description-Content-Type: text/markdown
|
|
18
|
-
Requires-Dist: stac-fastapi.core==6.5.1
|
|
19
|
-
|
|
20
|
-
# stac-fastapi-elasticsearch-opensearch
|
|
21
|
-
|
|
22
|
-
<!-- markdownlint-disable MD033 MD041 -->
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
<p align="left">
|
|
26
|
-
<img src="https://raw.githubusercontent.com/stac-utils/stac-fastapi-elasticsearch-opensearch/refs/heads/main/assets/sfeos.png" width=1000>
|
|
27
|
-
</p>
|
|
28
|
-
|
|
29
|
-
**Jump to:** [Project Introduction](#project-introduction---what-is-sfeos) | [Quick Start](#quick-start) | [Table of Contents](#table-of-contents)
|
|
30
|
-
|
|
31
|
-
[](https://pepy.tech/project/stac-fastapi-core)
|
|
32
|
-
[](https://github.com/stac-utils/stac-fastapi-elasticsearch-opensearch/graphs/contributors)
|
|
33
|
-
[](https://github.com/stac-utils/stac-fastapi-elasticsearch-opensearch/stargazers)
|
|
34
|
-
[](https://github.com/stac-utils/stac-fastapi-elasticsearch-opensearch/network/members)
|
|
35
|
-
[](https://pypi.org/project/stac-fastapi-elasticsearch/)
|
|
36
|
-
[](https://github.com/radiantearth/stac-spec/tree/v1.1.0)
|
|
37
|
-
[](https://github.com/stac-utils/stac-fastapi)
|
|
38
|
-
|
|
39
|
-
## Sponsors & Supporters
|
|
40
|
-
|
|
41
|
-
The following organizations have contributed time and/or funding to support the development of this project:
|
|
42
|
-
|
|
43
|
-
<p align="left">
|
|
44
|
-
<a href="https://healy-hyperspatial.github.io/"><img src="https://raw.githubusercontent.com/stac-utils/stac-fastapi-elasticsearch-opensearch/refs/heads/main/assets/hh-logo-blue.png" alt="Healy Hyperspatial" height="100" hspace="20"></a>
|
|
45
|
-
<a href="https://atomicmaps.io/"><img src="https://raw.githubusercontent.com/stac-utils/stac-fastapi-elasticsearch-opensearch/refs/heads/main/assets/am-logo-black.png" alt="Atomic Maps" height="100" hspace="20"></a>
|
|
46
|
-
<a href="https://remotesensing.vito.be/"><img src="https://raw.githubusercontent.com/stac-utils/stac-fastapi-elasticsearch-opensearch/refs/heads/main/assets/VITO.png" alt="VITO Remote Sensing" height="100" hspace="20"></a>
|
|
47
|
-
</p>
|
|
48
|
-
|
|
49
|
-
## Project Introduction - What is SFEOS?
|
|
50
|
-
|
|
51
|
-
SFEOS (stac-fastapi-elasticsearch-opensearch) is a high-performance, scalable API implementation for serving SpatioTemporal Asset Catalog (STAC) data - an enhanced GeoJSON format designed specifically for geospatial assets like satellite imagery, aerial photography, and other Earth observation data. This project enables organizations to:
|
|
52
|
-
|
|
53
|
-
- **Efficiently catalog and search geospatial data** such as satellite imagery, aerial photography, DEMs, and other geospatial assets using Elasticsearch or OpenSearch as the database backend
|
|
54
|
-
- **Implement standardized STAC APIs** that support complex spatial, temporal, and property-based queries across large collections of geospatial data
|
|
55
|
-
- **Scale to millions of geospatial assets** with fast search performance through optimized spatial indexing and query capabilities
|
|
56
|
-
- **Support OGC-compliant filtering** including spatial operations (intersects, contains, etc.) and temporal queries
|
|
57
|
-
- **Perform geospatial aggregations** to analyze data distribution across space and time
|
|
58
|
-
- **Enhanced collection search capabilities** with support for sorting and field selection
|
|
59
|
-
|
|
60
|
-
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.
|
|
61
|
-
|
|
62
|
-
## Common Deployment Patterns
|
|
63
|
-
|
|
64
|
-
stac-fastapi-elasticsearch-opensearch can be deployed in several ways depending on your needs:
|
|
65
|
-
|
|
66
|
-
- **Containerized Application**: Run as a Docker container with connections to Elasticsearch/OpenSearch databases
|
|
67
|
-
- **Serverless Function**: Deploy as AWS Lambda or similar serverless function with API Gateway
|
|
68
|
-
- **Traditional Server**: Run on virtual machines or bare metal servers in your infrastructure
|
|
69
|
-
- **Kubernetes**: Deploy as part of a larger microservices architecture with container orchestration
|
|
70
|
-
|
|
71
|
-
The implementation is flexible and can scale from small local deployments to large production environments serving millions of geospatial assets.
|
|
72
|
-
|
|
73
|
-
## Technologies
|
|
74
|
-
|
|
75
|
-
This project is built on the following technologies: STAC, stac-fastapi, FastAPI, Elasticsearch, Python, OpenSearch
|
|
76
|
-
|
|
77
|
-
<p align="left">
|
|
78
|
-
<a href="https://stacspec.org/"><img src="https://raw.githubusercontent.com/stac-utils/stac-fastapi-elasticsearch-opensearch/refs/heads/main/assets/STAC-01.png" alt="STAC" height="100" hspace="10"></a>
|
|
79
|
-
<a href="https://www.python.org/"><img src="https://raw.githubusercontent.com/stac-utils/stac-fastapi-elasticsearch-opensearch/refs/heads/main/assets/python.png" alt="Python" height="80" hspace="10"></a>
|
|
80
|
-
<a href="https://fastapi.tiangolo.com/"><img src="https://raw.githubusercontent.com/stac-utils/stac-fastapi-elasticsearch-opensearch/refs/heads/main/assets/fastapi.svg" alt="FastAPI" height="80" hspace="10"></a>
|
|
81
|
-
<a href="https://www.elastic.co/"><img src="https://raw.githubusercontent.com/stac-utils/stac-fastapi-elasticsearch-opensearch/refs/heads/main/assets/elasticsearch.png" alt="Elasticsearch" height="80" hspace="10"></a>
|
|
82
|
-
<a href="https://opensearch.org/"><img src="https://raw.githubusercontent.com/stac-utils/stac-fastapi-elasticsearch-opensearch/refs/heads/main/assets/opensearch.svg" alt="OpenSearch" height="80" hspace="10"></a>
|
|
83
|
-
</p>
|
|
84
|
-
|
|
85
|
-
## Table of Contents
|
|
86
|
-
|
|
87
|
-
- [stac-fastapi-elasticsearch-opensearch](#stac-fastapi-elasticsearch-opensearch)
|
|
88
|
-
- [Sponsors & Supporters](#sponsors--supporters)
|
|
89
|
-
- [Project Introduction - What is SFEOS?](#project-introduction---what-is-sfeos)
|
|
90
|
-
- [Common Deployment Patterns](#common-deployment-patterns)
|
|
91
|
-
- [Technologies](#technologies)
|
|
92
|
-
- [Table of Contents](#table-of-contents)
|
|
93
|
-
- [Collection Search Extensions](#collection-search-extensions)
|
|
94
|
-
- [Documentation & Resources](#documentation--resources)
|
|
95
|
-
- [Package Structure](#package-structure)
|
|
96
|
-
- [Examples](#examples)
|
|
97
|
-
- [Performance](#performance)
|
|
98
|
-
- [Direct Response Mode](#direct-response-mode)
|
|
99
|
-
- [Quick Start](#quick-start)
|
|
100
|
-
- [Installation](#installation)
|
|
101
|
-
- [Running Locally](#running-locally)
|
|
102
|
-
- [Using Pre-built Docker Images](#using-pre-built-docker-images)
|
|
103
|
-
- [Using Docker Compose](#using-docker-compose)
|
|
104
|
-
- [Configuration Reference](#configuration-reference)
|
|
105
|
-
- [Datetime-Based Index Management](#datetime-based-index-management)
|
|
106
|
-
- [Overview](#overview)
|
|
107
|
-
- [When to Use](#when-to-use)
|
|
108
|
-
- [Configuration](#configuration)
|
|
109
|
-
- [Enabling Datetime-Based Indexing](#enabling-datetime-based-indexing)
|
|
110
|
-
- [Related Configuration Variables](#related-configuration-variables)
|
|
111
|
-
- [How Datetime-Based Indexing Works](#how-datetime-based-indexing-works)
|
|
112
|
-
- [Index and Alias Naming Convention](#index-and-alias-naming-convention)
|
|
113
|
-
- [Index Size Management](#index-size-management)
|
|
114
|
-
- [Interacting with the API](#interacting-with-the-api)
|
|
115
|
-
- [Configure the API](#configure-the-api)
|
|
116
|
-
- [Collection Pagination](#collection-pagination)
|
|
117
|
-
- [Ingesting Sample Data CLI Tool](#ingesting-sample-data-cli-tool)
|
|
118
|
-
- [Elasticsearch Mappings](#elasticsearch-mappings)
|
|
119
|
-
- [Managing Elasticsearch Indices](#managing-elasticsearch-indices)
|
|
120
|
-
- [Snapshots](#snapshots)
|
|
121
|
-
- [Reindexing](#reindexing)
|
|
122
|
-
- [Auth](#auth)
|
|
123
|
-
- [Aggregation](#aggregation)
|
|
124
|
-
- [Rate Limiting](#rate-limiting)
|
|
125
|
-
|
|
126
|
-
## Documentation & Resources
|
|
127
|
-
|
|
128
|
-
- **Online Documentation**: [https://stac-utils.github.io/stac-fastapi-elasticsearch-opensearch](https://stac-utils.github.io/stac-fastapi-elasticsearch-opensearch/)
|
|
129
|
-
- **Source Code**: [https://github.com/stac-utils/stac-fastapi-elasticsearch-opensearch](https://github.com/stac-utils/stac-fastapi-elasticsearch-opensearch)
|
|
130
|
-
- **API Examples**: [Postman Documentation](https://documenter.getpostman.com/view/12888943/2s8ZDSdRHA) - Examples of how to use the API endpoints
|
|
131
|
-
- **Community**:
|
|
132
|
-
- [Gitter Chat](https://app.gitter.im/#/room/#stac-fastapi-elasticsearch_community:gitter.im) - For real-time discussions
|
|
133
|
-
- [GitHub Discussions](https://github.com/stac-utils/stac-fastapi-elasticsearch-opensearch/discussions) - For longer-form questions and answers
|
|
134
|
-
|
|
135
|
-
## Collection Search Extensions
|
|
136
|
-
|
|
137
|
-
SFEOS provides enhanced collection search capabilities through two primary routes:
|
|
138
|
-
- **GET/POST `/collections`**: The standard STAC endpoint with extended query parameters
|
|
139
|
-
- **GET/POST `/collections-search`**: A custom endpoint that supports the same parameters, created to avoid conflicts with the STAC Transactions extension if enabled (which uses POST `/collections` for collection creation)
|
|
140
|
-
|
|
141
|
-
These endpoints support advanced collection discovery features including:
|
|
142
|
-
|
|
143
|
-
- **Sorting**: Sort collections by sortable fields using the `sortby` parameter
|
|
144
|
-
- Example: `/collections?sortby=+id` (ascending sort by ID)
|
|
145
|
-
- Example: `/collections?sortby=-id` (descending sort by ID)
|
|
146
|
-
- Example: `/collections?sortby=-temporal` (descending sort by temporal extent)
|
|
147
|
-
|
|
148
|
-
- **Field Selection**: Request only specific fields to be returned using the `fields` parameter
|
|
149
|
-
- Example: `/collections?fields=id,title,description`
|
|
150
|
-
- This helps reduce payload size when only certain fields are needed
|
|
151
|
-
|
|
152
|
-
- **Free Text Search**: Search across collection text fields using the `q` parameter
|
|
153
|
-
- Example: `/collections?q=landsat`
|
|
154
|
-
- Searches across multiple text fields including title, description, and keywords
|
|
155
|
-
- Supports partial word matching and relevance-based sorting
|
|
156
|
-
|
|
157
|
-
- **Structured Filtering**: Filter collections using CQL2 expressions
|
|
158
|
-
- JSON format: `/collections?filter={"op":"=","args":[{"property":"id"},"sentinel-2"]}&filter-lang=cql2-json`
|
|
159
|
-
- Text format: `/collections?filter=id='sentinel-2'&filter-lang=cql2-text` (note: string values must be quoted)
|
|
160
|
-
- Advanced text format: `/collections?filter=id LIKE '%sentinel%'&filter-lang=cql2-text` (supports LIKE, BETWEEN, etc.)
|
|
161
|
-
- Supports both CQL2 JSON and CQL2 text formats with various operators
|
|
162
|
-
- Enables precise filtering on any collection property
|
|
163
|
-
|
|
164
|
-
- **Datetime Filtering**: Filter collections by their temporal extent using the `datetime` parameter
|
|
165
|
-
- Example: `/collections?datetime=2020-01-01T00:00:00Z/2020-12-31T23:59:59Z` (finds collections with temporal extents that overlap this range)
|
|
166
|
-
- Example: `/collections?datetime=2020-06-15T12:00:00Z` (finds collections whose temporal extent includes this specific time)
|
|
167
|
-
- Example: `/collections?datetime=2020-01-01T00:00:00Z/..` (finds collections with temporal extents that extend to or beyond January 1, 2020)
|
|
168
|
-
- Example: `/collections?datetime=../2020-12-31T23:59:59Z` (finds collections with temporal extents that begin on or before December 31, 2020)
|
|
169
|
-
- Collections are matched if their temporal extent overlaps with the provided datetime parameter
|
|
170
|
-
- This allows for efficient discovery of collections based on time periods
|
|
171
|
-
|
|
172
|
-
These extensions make it easier to build user interfaces that display and navigate through collections efficiently.
|
|
173
|
-
|
|
174
|
-
> **Configuration**: Collection search extensions (sorting, field selection, free text search, structured filtering, and datetime filtering) for the `/collections` endpoint can be disabled by setting the `ENABLE_COLLECTIONS_SEARCH` environment variable to `false`. By default, these extensions are enabled.
|
|
175
|
-
>
|
|
176
|
-
> **Configuration**: The custom `/collections-search` endpoint can be enabled by setting the `ENABLE_COLLECTIONS_SEARCH_ROUTE` environment variable to `true`. By default, this endpoint is **disabled**.
|
|
177
|
-
|
|
178
|
-
> **Note**: Sorting is only available on fields that are indexed for sorting in Elasticsearch/OpenSearch. With the default mappings, you can sort on:
|
|
179
|
-
> - `id` (keyword field)
|
|
180
|
-
> - `extent.temporal.interval` (date field)
|
|
181
|
-
> - `temporal` (alias to extent.temporal.interval)
|
|
182
|
-
>
|
|
183
|
-
> 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.
|
|
184
|
-
>
|
|
185
|
-
> **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.
|
|
186
|
-
|
|
187
|
-
|
|
188
|
-
## Package Structure
|
|
189
|
-
|
|
190
|
-
This project is organized into several packages, each with a specific purpose:
|
|
191
|
-
|
|
192
|
-
- **stac_fastapi_core**: Core functionality that's database-agnostic, including API models, extensions, and shared utilities. This package provides the foundation for building STAC API implementations with any database backend. See [stac-fastapi-mongo](https://github.com/Healy-Hyperspatial/stac-fastapi-mongo) for a working example.
|
|
193
|
-
|
|
194
|
-
- **sfeos_helpers**: Shared helper functions and utilities used by both the Elasticsearch and OpenSearch backends. This package includes:
|
|
195
|
-
- `database`: Specialized modules for index, document, and database utility operations
|
|
196
|
-
- `aggregation`: Elasticsearch/OpenSearch-specific aggregation functionality
|
|
197
|
-
- Shared logic and utilities that improve code reuse between backends
|
|
198
|
-
|
|
199
|
-
- **stac_fastapi_elasticsearch**: Complete implementation of the STAC API using Elasticsearch as the backend database. This package depends on both `stac_fastapi_core` and `sfeos_helpers`.
|
|
200
|
-
|
|
201
|
-
- **stac_fastapi_opensearch**: Complete implementation of the STAC API using OpenSearch as the backend database. This package depends on both `stac_fastapi_core` and `sfeos_helpers`.
|
|
202
|
-
|
|
203
|
-
## Examples
|
|
204
|
-
|
|
205
|
-
The `/examples` directory contains several useful examples and reference implementations:
|
|
206
|
-
|
|
207
|
-
- **pip_docker**: Examples of running stac-fastapi-elasticsearch from PyPI in Docker without needing any code from the repository
|
|
208
|
-
- **auth**: Authentication examples including:
|
|
209
|
-
- Basic authentication
|
|
210
|
-
- OAuth2 with Keycloak
|
|
211
|
-
- Route dependencies configuration
|
|
212
|
-
- **rate_limit**: Example of implementing rate limiting for API requests
|
|
213
|
-
- **postman_collections**: Postman collection files you can import for testing API endpoints
|
|
214
|
-
|
|
215
|
-
These examples provide practical reference implementations for various deployment scenarios and features.
|
|
216
|
-
|
|
217
|
-
## Performance
|
|
218
|
-
|
|
219
|
-
### Direct Response Mode
|
|
220
|
-
|
|
221
|
-
- The `enable_direct_response` option is provided by the stac-fastapi core library (introduced in stac-fastapi 5.2.0) and is available in this project starting from v4.0.0.
|
|
222
|
-
- **Control via environment variable**: Set `ENABLE_DIRECT_RESPONSE=true` to enable this feature.
|
|
223
|
-
- **How it works**: When enabled, endpoints return Starlette Response objects directly, bypassing FastAPI's default serialization for improved performance.
|
|
224
|
-
- **Important limitation**: All FastAPI dependencies (including authentication, custom status codes, and validation) are disabled for all routes when this mode is enabled.
|
|
225
|
-
- **Best use case**: This mode is best suited for public or read-only APIs where authentication and custom logic are not required.
|
|
226
|
-
- **Default setting**: `false` for safety.
|
|
227
|
-
- **More information**: See [issue #347](https://github.com/stac-utils/stac-fastapi-elasticsearch-opensearch/issues/347) for background and implementation details.
|
|
228
|
-
|
|
229
|
-
## Quick Start
|
|
230
|
-
|
|
231
|
-
This section helps you get up and running with stac-fastapi-elasticsearch-opensearch quickly.
|
|
232
|
-
|
|
233
|
-
### Installation
|
|
234
|
-
|
|
235
|
-
- **For versions 4.0.0a1 and newer** (PEP 625 compliant naming):
|
|
236
|
-
```bash
|
|
237
|
-
pip install stac-fastapi-elasticsearch # Elasticsearch backend
|
|
238
|
-
pip install stac-fastapi-opensearch # Opensearch backend
|
|
239
|
-
pip install stac-fastapi-core # Core library
|
|
240
|
-
```
|
|
241
|
-
|
|
242
|
-
- **For versions 4.0.0a0 and older**:
|
|
243
|
-
```bash
|
|
244
|
-
pip install stac-fastapi.elasticsearch # Elasticsearch backend
|
|
245
|
-
pip install stac-fastapi.opensearch # Opensearch backend
|
|
246
|
-
pip install stac-fastapi.core # Core library
|
|
247
|
-
```
|
|
248
|
-
|
|
249
|
-
> **Important Note:** Starting with version 4.0.0a1, package names have changed from using periods (e.g., `stac-fastapi.core`) to using hyphens (e.g., `stac-fastapi-core`) to comply with PEP 625. The internal package structure uses underscores, but users should install with hyphens as shown above. Please update your requirements files accordingly.
|
|
250
|
-
|
|
251
|
-
### Running Locally
|
|
252
|
-
|
|
253
|
-
There are two main ways to run the API locally:
|
|
254
|
-
|
|
255
|
-
#### Using Pre-built Docker Images
|
|
256
|
-
|
|
257
|
-
- We provide ready-to-use Docker images through GitHub Container Registry:
|
|
258
|
-
- [ElasticSearch backend](https://github.com/stac-utils/stac-fastapi-elasticsearch-opensearch/pkgs/container/stac-fastapi-es)
|
|
259
|
-
- [OpenSearch backend](https://github.com/stac-utils/stac-fastapi-elasticsearch-opensearch/pkgs/container/stac-fastapi-os)
|
|
260
|
-
|
|
261
|
-
- **Pull and run the images**:
|
|
262
|
-
```shell
|
|
263
|
-
# For Elasticsearch backend
|
|
264
|
-
docker pull ghcr.io/stac-utils/stac-fastapi-es:latest
|
|
265
|
-
|
|
266
|
-
# For OpenSearch backend
|
|
267
|
-
docker pull ghcr.io/stac-utils/stac-fastapi-os:latest
|
|
268
|
-
```
|
|
269
|
-
|
|
270
|
-
#### Using Docker Compose
|
|
271
|
-
|
|
272
|
-
- **Prerequisites**: Ensure [Docker Compose](https://docs.docker.com/compose/install/) or [Podman Compose](https://podman-desktop.io/docs/compose) is installed on your machine.
|
|
273
|
-
|
|
274
|
-
- **Start the API**:
|
|
275
|
-
```shell
|
|
276
|
-
docker compose up elasticsearch app-elasticsearch
|
|
277
|
-
```
|
|
278
|
-
|
|
279
|
-
- **Configuration**: By default, Docker Compose uses Elasticsearch 8.x and OpenSearch 2.11.1. To use different versions, create a `.env` file:
|
|
280
|
-
```shell
|
|
281
|
-
ELASTICSEARCH_VERSION=8.11.0
|
|
282
|
-
OPENSEARCH_VERSION=2.11.1
|
|
283
|
-
ENABLE_DIRECT_RESPONSE=false
|
|
284
|
-
```
|
|
285
|
-
|
|
286
|
-
- **Compatibility**: The most recent Elasticsearch 7.x versions should also work. See the [opensearch-py docs](https://github.com/opensearch-project/opensearch-py/blob/main/COMPATIBILITY.md) for compatibility information.
|
|
287
|
-
|
|
288
|
-
|
|
289
|
-
|
|
290
|
-
## Configuration Reference
|
|
291
|
-
|
|
292
|
-
You can customize additional settings in your `.env` file:
|
|
293
|
-
|
|
294
|
-
| Variable | Description | Default | Required |
|
|
295
|
-
|------------------------------|--------------------------------------------------------------------------------------|--------------------------|---------------------------------------------------------------------------------------------|
|
|
296
|
-
| `ES_HOST` | Hostname for external Elasticsearch/OpenSearch. | `localhost` | Optional |
|
|
297
|
-
| `ES_PORT` | Port for Elasticsearch/OpenSearch. | `9200` (ES) / `9202` (OS)| Optional |
|
|
298
|
-
| `ES_USE_SSL` | Use SSL for connecting to Elasticsearch/OpenSearch. | `true` | Optional |
|
|
299
|
-
| `ES_VERIFY_CERTS` | Verify SSL certificates when connecting. | `true` | Optional |
|
|
300
|
-
| `ES_API_KEY` | API Key for external Elasticsearch/OpenSearch. | N/A | Optional |
|
|
301
|
-
| `ES_TIMEOUT` | Client timeout for Elasticsearch/OpenSearch. | DB client default | Optional |
|
|
302
|
-
| `STAC_FASTAPI_TITLE` | Title of the API in the documentation. | `stac-fastapi-<backend>` | Optional |
|
|
303
|
-
| `STAC_FASTAPI_DESCRIPTION` | Description of the API in the documentation. | N/A | Optional |
|
|
304
|
-
| `STAC_FASTAPI_VERSION` | API version. | `2.1` | Optional |
|
|
305
|
-
| `STAC_FASTAPI_LANDING_PAGE_ID` | Landing page ID | `stac-fastapi` | Optional |
|
|
306
|
-
| `APP_HOST` | Server bind address. | `0.0.0.0` | Optional |
|
|
307
|
-
| `APP_PORT` | Server port. | `8000` | Optional |
|
|
308
|
-
| `ENVIRONMENT` | Runtime environment. | `local` | Optional |
|
|
309
|
-
| `WEB_CONCURRENCY` | Number of worker processes. | `10` | Optional |
|
|
310
|
-
| `RELOAD` | Enable auto-reload for development. | `true` | Optional |
|
|
311
|
-
| `STAC_FASTAPI_RATE_LIMIT` | API rate limit per client. | `200/minute` | Optional |
|
|
312
|
-
| `BACKEND` | Tests-related variable | `elasticsearch` or `opensearch` based on the backend | Optional |
|
|
313
|
-
| `ELASTICSEARCH_VERSION` | Version of Elasticsearch to use. | `8.11.0` | Optional |
|
|
314
|
-
| `OPENSEARCH_VERSION` | OpenSearch version | `2.11.1` | Optional |
|
|
315
|
-
| `ENABLE_DIRECT_RESPONSE` | Enable direct response for maximum performance (disables all FastAPI dependencies, including authentication, custom status codes, and validation) | `false` | Optional |
|
|
316
|
-
| `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 |
|
|
317
|
-
| `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 |
|
|
318
|
-
| `ENABLE_COLLECTIONS_SEARCH` | Enable collection search extensions (sort, fields, free text search, structured filtering, and datetime filtering) on the core `/collections` endpoint. | `true` | Optional |
|
|
319
|
-
| `ENABLE_COLLECTIONS_SEARCH_ROUTE` | Enable the custom `/collections-search` endpoint (both GET and POST methods). When disabled, the custom endpoint will not be available, but collection search extensions will still be available on the core `/collections` endpoint if `ENABLE_COLLECTIONS_SEARCH` is true. | `false` | Optional |
|
|
320
|
-
| `ENABLE_TRANSACTIONS_EXTENSIONS` | Enables or disables the Transactions and Bulk Transactions API extensions. This is useful for deployments where mutating the catalog via the API should be prevented. If set to `true`, the POST `/collections` route for search will be unavailable in the API. | `true` | Optional |
|
|
321
|
-
| `STAC_ITEM_LIMIT` | Sets the environment variable for result limiting to SFEOS for the number of returned items and STAC collections. | `10` | Optional |
|
|
322
|
-
| `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 |
|
|
323
|
-
| `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 |
|
|
324
|
-
| `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 |
|
|
325
|
-
|
|
326
|
-
> [!NOTE]
|
|
327
|
-
> 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.
|
|
328
|
-
|
|
329
|
-
## Datetime-Based Index Management
|
|
330
|
-
|
|
331
|
-
### Overview
|
|
332
|
-
|
|
333
|
-
SFEOS supports two indexing strategies for managing STAC items:
|
|
334
|
-
|
|
335
|
-
1. **Simple Indexing** (default) - One index per collection
|
|
336
|
-
2. **Datetime-Based Indexing** - Time-partitioned indexes with automatic management
|
|
337
|
-
|
|
338
|
-
The datetime-based indexing strategy is particularly useful for large temporal datasets. When a user provides a datetime parameter in a query, the system knows exactly which index to search, providing **multiple times faster searches** and significantly **reducing database load**.
|
|
339
|
-
|
|
340
|
-
### When to Use
|
|
341
|
-
|
|
342
|
-
**Recommended for:**
|
|
343
|
-
- Systems with large collections containing millions of items
|
|
344
|
-
- Systems requiring high-performance temporal searching
|
|
345
|
-
|
|
346
|
-
**Pros:**
|
|
347
|
-
- Multiple times faster queries with datetime filter
|
|
348
|
-
- Reduced database load - only relevant indexes are searched
|
|
349
|
-
|
|
350
|
-
**Cons:**
|
|
351
|
-
- Slightly longer item indexing time (automatic index management)
|
|
352
|
-
- Greater management complexity
|
|
353
|
-
|
|
354
|
-
### Configuration
|
|
355
|
-
|
|
356
|
-
#### Enabling Datetime-Based Indexing
|
|
357
|
-
|
|
358
|
-
Enable datetime-based indexing by setting the following environment variable:
|
|
359
|
-
|
|
360
|
-
```bash
|
|
361
|
-
ENABLE_DATETIME_INDEX_FILTERING=true
|
|
362
|
-
```
|
|
363
|
-
|
|
364
|
-
### Related Configuration Variables
|
|
365
|
-
|
|
366
|
-
| Variable | Description | Default | Example |
|
|
367
|
-
|----------|-------------|---------|---------|
|
|
368
|
-
| `ENABLE_DATETIME_INDEX_FILTERING` | Enables time-based index partitioning | `false` | `true` |
|
|
369
|
-
| `DATETIME_INDEX_MAX_SIZE_GB` | Maximum size limit for datetime indexes (GB) - note: add +20% to target size due to ES/OS compression | `25` | `50` |
|
|
370
|
-
| `STAC_ITEMS_INDEX_PREFIX` | Prefix for item indexes | `items_` | `stac_items_` |
|
|
371
|
-
|
|
372
|
-
## How Datetime-Based Indexing Works
|
|
373
|
-
|
|
374
|
-
### Index and Alias Naming Convention
|
|
375
|
-
|
|
376
|
-
The system uses a precise naming convention:
|
|
377
|
-
|
|
378
|
-
**Physical indexes:**
|
|
379
|
-
```
|
|
380
|
-
{ITEMS_INDEX_PREFIX}{collection-id}_{uuid4}
|
|
381
|
-
```
|
|
382
|
-
|
|
383
|
-
**Aliases:**
|
|
384
|
-
```
|
|
385
|
-
{ITEMS_INDEX_PREFIX}{collection-id} # Main collection alias
|
|
386
|
-
{ITEMS_INDEX_PREFIX}{collection-id}_{start-datetime} # Temporal alias
|
|
387
|
-
{ITEMS_INDEX_PREFIX}{collection-id}_{start-datetime}_{end-datetime} # Closed index alias
|
|
388
|
-
```
|
|
389
|
-
|
|
390
|
-
**Example:**
|
|
391
|
-
|
|
392
|
-
*Physical indexes:*
|
|
393
|
-
- `items_sentinel-2-l2a_a1b2c3d4-e5f6-7890-abcd-ef1234567890`
|
|
394
|
-
|
|
395
|
-
*Aliases:*
|
|
396
|
-
- `items_sentinel-2-l2a` - main collection alias
|
|
397
|
-
- `items_sentinel-2-l2a_2024-01-01` - active alias from January 1, 2024
|
|
398
|
-
- `items_sentinel-2-l2a_2024-01-01_2024-03-15` - closed index alias (reached size limit)
|
|
399
|
-
|
|
400
|
-
### Index Size Management
|
|
401
|
-
|
|
402
|
-
**Important - Data Compression:** Elasticsearch and OpenSearch automatically compress data. The configured `DATETIME_INDEX_MAX_SIZE_GB` limit refers to the compressed size on disk. It is recommended to add +20% to the target size to account for compression overhead and metadata.
|
|
403
|
-
|
|
404
|
-
## Interacting with the API
|
|
405
|
-
|
|
406
|
-
- **Creating a Collection**:
|
|
407
|
-
```shell
|
|
408
|
-
curl -X "POST" "http://localhost:8080/collections" \
|
|
409
|
-
-H 'Content-Type: application/json; charset=utf-8' \
|
|
410
|
-
-d $'{
|
|
411
|
-
"id": "my_collection"
|
|
412
|
-
}'
|
|
413
|
-
```
|
|
414
|
-
|
|
415
|
-
- **Adding an Item to a Collection**:
|
|
416
|
-
```shell
|
|
417
|
-
curl -X "POST" "http://localhost:8080/collections/my_collection/items" \
|
|
418
|
-
-H 'Content-Type: application/json; charset=utf-8' \
|
|
419
|
-
-d @item.json
|
|
420
|
-
```
|
|
421
|
-
|
|
422
|
-
- **Searching for Items**:
|
|
423
|
-
```shell
|
|
424
|
-
curl -X "GET" "http://localhost:8080/search" \
|
|
425
|
-
-H 'Content-Type: application/json; charset=utf-8' \
|
|
426
|
-
-d $'{
|
|
427
|
-
"collections": ["my_collection"],
|
|
428
|
-
"limit": 10
|
|
429
|
-
}'
|
|
430
|
-
```
|
|
431
|
-
|
|
432
|
-
- **Filtering by Bbox**:
|
|
433
|
-
```shell
|
|
434
|
-
curl -X "GET" "http://localhost:8080/search" \
|
|
435
|
-
-H 'Content-Type: application/json; charset=utf-8' \
|
|
436
|
-
-d $'{
|
|
437
|
-
"collections": ["my_collection"],
|
|
438
|
-
"bbox": [-180, -90, 180, 90]
|
|
439
|
-
}'
|
|
440
|
-
```
|
|
441
|
-
|
|
442
|
-
- **Filtering by Datetime**:
|
|
443
|
-
```shell
|
|
444
|
-
curl -X "GET" "http://localhost:8080/search" \
|
|
445
|
-
-H 'Content-Type: application/json; charset=utf-8' \
|
|
446
|
-
-d $'{
|
|
447
|
-
"collections": ["my_collection"],
|
|
448
|
-
"datetime": "2020-01-01T00:00:00Z/2020-12-31T23:59:59Z"
|
|
449
|
-
}'
|
|
450
|
-
```
|
|
451
|
-
|
|
452
|
-
## Configure the API
|
|
453
|
-
|
|
454
|
-
- **API Title and Description**: By default set to `stac-fastapi-<backend>`. Customize these by setting:
|
|
455
|
-
- `STAC_FASTAPI_TITLE`: Changes the API title in the documentation
|
|
456
|
-
- `STAC_FASTAPI_DESCRIPTION`: Changes the API description in the documentation
|
|
457
|
-
|
|
458
|
-
- **Database Indices**: By default, the API reads from and writes to:
|
|
459
|
-
- `collections` index for collections
|
|
460
|
-
- `items_<collection name>` indices for items
|
|
461
|
-
- Customize with `STAC_COLLECTIONS_INDEX` and `STAC_ITEMS_INDEX_PREFIX` environment variables
|
|
462
|
-
|
|
463
|
-
- **Root Path Configuration**: The application root path is the base URL by default.
|
|
464
|
-
- For AWS Lambda with Gateway API: Set `STAC_FASTAPI_ROOT_PATH` to match the Gateway API stage name (e.g., `/v1`)
|
|
465
|
-
|
|
466
|
-
- **Feature Configuration**: Control which features are enabled:
|
|
467
|
-
- `ENABLE_COLLECTIONS_SEARCH`: Set to `true` (default) to enable collection search extensions (sort, fields). Set to `false` to disable.
|
|
468
|
-
- `ENABLE_TRANSACTIONS_EXTENSIONS`: Set to `true` (default) to enable transaction extensions. Set to `false` to disable.
|
|
469
|
-
|
|
470
|
-
## Collection Pagination
|
|
471
|
-
|
|
472
|
-
- **Overview**: The collections route supports pagination through optional query parameters.
|
|
473
|
-
- **Parameters**:
|
|
474
|
-
- `limit`: Controls the number of collections returned per page
|
|
475
|
-
- `token`: Used to retrieve subsequent pages of results
|
|
476
|
-
- **Response Structure**: The `links` field in the response contains a `next` link with the token for the next page of results.
|
|
477
|
-
- **Example Usage**:
|
|
478
|
-
```shell
|
|
479
|
-
curl -X "GET" "http://localhost:8080/collections?limit=1&token=example_token"
|
|
480
|
-
```
|
|
481
|
-
|
|
482
|
-
## Ingesting Sample Data CLI Tool
|
|
483
|
-
|
|
484
|
-
- **Overview**: The `data_loader.py` script provides a convenient way to load STAC items into the database.
|
|
485
|
-
|
|
486
|
-
- **Usage**:
|
|
487
|
-
```shell
|
|
488
|
-
python3 data_loader.py --base-url http://localhost:8080
|
|
489
|
-
```
|
|
490
|
-
|
|
491
|
-
- **Options**:
|
|
492
|
-
```
|
|
493
|
-
--base-url TEXT Base URL of the STAC API [required]
|
|
494
|
-
--collection-id TEXT ID of the collection to which items are added
|
|
495
|
-
--use-bulk Use bulk insert method for items
|
|
496
|
-
--data-dir PATH Directory containing collection.json and feature
|
|
497
|
-
collection file
|
|
498
|
-
--help Show this message and exit.
|
|
499
|
-
```
|
|
500
|
-
|
|
501
|
-
- **Example Workflows**:
|
|
502
|
-
- **Loading Sample Data**:
|
|
503
|
-
```shell
|
|
504
|
-
python3 data_loader.py --base-url http://localhost:8080
|
|
505
|
-
```
|
|
506
|
-
- **Loading Data to a Specific Collection**:
|
|
507
|
-
```shell
|
|
508
|
-
python3 data_loader.py --base-url http://localhost:8080 --collection-id my-collection
|
|
509
|
-
```
|
|
510
|
-
- **Using Bulk Insert for Performance**:
|
|
511
|
-
```shell
|
|
512
|
-
python3 data_loader.py --base-url http://localhost:8080 --use-bulk
|
|
513
|
-
```
|
|
514
|
-
|
|
515
|
-
## Elasticsearch Mappings
|
|
516
|
-
|
|
517
|
-
- **Overview**: Mappings apply to search index, not source data. They define how documents and their fields are stored and indexed.
|
|
518
|
-
- **Implementation**:
|
|
519
|
-
- Mappings are stored in index templates that are created on application startup
|
|
520
|
-
- These templates are automatically applied when creating new Collection and Item indices
|
|
521
|
-
- The `sfeos_helpers` package contains shared mapping definitions used by both Elasticsearch and OpenSearch backends
|
|
522
|
-
- **Customization**: Custom mappings can be defined by extending the base mapping templates.
|
|
523
|
-
|
|
524
|
-
## Managing Elasticsearch Indices
|
|
525
|
-
|
|
526
|
-
### Snapshots
|
|
527
|
-
|
|
528
|
-
- **Overview**: Snapshots provide a way to backup and restore your indices.
|
|
529
|
-
|
|
530
|
-
- **Creating a Snapshot Repository**:
|
|
531
|
-
```shell
|
|
532
|
-
curl -X "PUT" "http://localhost:9200/_snapshot/my_fs_backup" \
|
|
533
|
-
-H 'Content-Type: application/json; charset=utf-8' \
|
|
534
|
-
-d $'{
|
|
535
|
-
"type": "fs",
|
|
536
|
-
"settings": {
|
|
537
|
-
"location": "/usr/share/elasticsearch/snapshots/my_fs_backup"
|
|
538
|
-
}
|
|
539
|
-
}'
|
|
540
|
-
```
|
|
541
|
-
- This creates a snapshot repository that stores files in the elasticsearch/snapshots directory in this git repo clone
|
|
542
|
-
- The elasticsearch.yml and compose files create a mapping from that directory to /usr/share/elasticsearch/snapshots within the Elasticsearch container and grant permissions for using it
|
|
543
|
-
|
|
544
|
-
- **Creating a Snapshot**:
|
|
545
|
-
```shell
|
|
546
|
-
curl -X "PUT" "http://localhost:9200/_snapshot/my_fs_backup/my_snapshot_2?wait_for_completion=true" \
|
|
547
|
-
-H 'Content-Type: application/json; charset=utf-8' \
|
|
548
|
-
-d $'{
|
|
549
|
-
"metadata": {
|
|
550
|
-
"taken_because": "dump of all items",
|
|
551
|
-
"taken_by": "pvarner"
|
|
552
|
-
},
|
|
553
|
-
"include_global_state": false,
|
|
554
|
-
"ignore_unavailable": false,
|
|
555
|
-
"indices": "items_my-collection"
|
|
556
|
-
}'
|
|
557
|
-
```
|
|
558
|
-
- This creates a snapshot named my_snapshot_2 and waits for the action to be completed before returning
|
|
559
|
-
- This can also be done asynchronously by omitting the wait_for_completion parameter, and queried for status later
|
|
560
|
-
- The indices parameter determines which indices are snapshotted, and can include wildcards
|
|
561
|
-
|
|
562
|
-
- **Viewing Snapshots**:
|
|
563
|
-
```shell
|
|
564
|
-
# View a specific snapshot
|
|
565
|
-
curl http://localhost:9200/_snapshot/my_fs_backup/my_snapshot_2
|
|
566
|
-
|
|
567
|
-
# View all snapshots
|
|
568
|
-
curl http://localhost:9200/_snapshot/my_fs_backup/_all
|
|
569
|
-
```
|
|
570
|
-
- These commands allow you to check the status and details of your snapshots
|
|
571
|
-
|
|
572
|
-
- **Restoring a Snapshot**:
|
|
573
|
-
```shell
|
|
574
|
-
curl -X "POST" "http://localhost:9200/_snapshot/my_fs_backup/my_snapshot_2/_restore?wait_for_completion=true" \
|
|
575
|
-
-H 'Content-Type: application/json; charset=utf-8' \
|
|
576
|
-
-d $'{
|
|
577
|
-
"include_aliases": false,
|
|
578
|
-
"include_global_state": false,
|
|
579
|
-
"ignore_unavailable": true,
|
|
580
|
-
"rename_replacement": "items_$1-copy",
|
|
581
|
-
"indices": "items_*",
|
|
582
|
-
"rename_pattern": "items_(.+)"
|
|
583
|
-
}'
|
|
584
|
-
```
|
|
585
|
-
- This specific command will restore any indices that match items_* and rename them so that the new index name will be suffixed with -copy
|
|
586
|
-
- The rename_pattern and rename_replacement parameters allow you to restore indices under new names
|
|
587
|
-
|
|
588
|
-
- **Updating Collection References**:
|
|
589
|
-
```shell
|
|
590
|
-
curl -X "POST" "http://localhost:9200/items_my-collection-copy/_update_by_query" \
|
|
591
|
-
-H 'Content-Type: application/json; charset=utf-8' \
|
|
592
|
-
-d $'{
|
|
593
|
-
"query": {
|
|
594
|
-
"match_all": {}
|
|
595
|
-
},
|
|
596
|
-
"script": {
|
|
597
|
-
"lang": "painless",
|
|
598
|
-
"params": {
|
|
599
|
-
"collection": "my-collection-copy"
|
|
600
|
-
},
|
|
601
|
-
"source": "ctx._source.collection = params.collection"
|
|
602
|
-
}
|
|
603
|
-
}'
|
|
604
|
-
```
|
|
605
|
-
- After restoring, the item documents have been restored in the new index (e.g., my-collection-copy), but the value of the collection field in those documents is still the original value of my-collection
|
|
606
|
-
- This command updates these values to match the new collection name using Elasticsearch's Update By Query feature
|
|
607
|
-
|
|
608
|
-
- **Creating a New Collection**:
|
|
609
|
-
```shell
|
|
610
|
-
curl -X "POST" "http://localhost:8080/collections" \
|
|
611
|
-
-H 'Content-Type: application/json' \
|
|
612
|
-
-d $'{
|
|
613
|
-
"id": "my-collection-copy"
|
|
614
|
-
}'
|
|
615
|
-
```
|
|
616
|
-
- The final step is to create a new collection through the API with the new name for each of the restored indices
|
|
617
|
-
- This gives you a copy of the collection that has a resource URI (/collections/my-collection-copy) and can be correctly queried by collection name
|
|
618
|
-
|
|
619
|
-
### Reindexing
|
|
620
|
-
|
|
621
|
-
- **Overview**: Reindexing allows you to copy documents from one index to another, optionally transforming them in the process.
|
|
622
|
-
|
|
623
|
-
- **Use Cases**:
|
|
624
|
-
- Apply changes to documents
|
|
625
|
-
- Correct dynamically generated mappings
|
|
626
|
-
- Transform data (e.g., lowercase identifiers)
|
|
627
|
-
- The index templates will make sure that manually created indices will also have the correct mappings and settings
|
|
628
|
-
|
|
629
|
-
- **Example: Reindexing with Transformation**:
|
|
630
|
-
```shell
|
|
631
|
-
curl -X "POST" "http://localhost:9200/_reindex" \
|
|
632
|
-
-H 'Content-Type: application/json' \
|
|
633
|
-
-d $'{
|
|
634
|
-
"source": {
|
|
635
|
-
"index": "items_my-collection-lower_my-collection-hex-000001"
|
|
636
|
-
},
|
|
637
|
-
"dest": {
|
|
638
|
-
"index": "items_my-collection-lower_my-collection-hex-000002"
|
|
639
|
-
},
|
|
640
|
-
"script": {
|
|
641
|
-
"source": "ctx._source.id = ctx._source.id.toLowerCase()",
|
|
642
|
-
"lang": "painless"
|
|
643
|
-
}
|
|
644
|
-
}'
|
|
645
|
-
```
|
|
646
|
-
- In this example, we make a copy of an existing Item index but change the Item identifier to be lowercase
|
|
647
|
-
- The script parameter allows you to transform documents during the reindexing process
|
|
648
|
-
|
|
649
|
-
- **Updating Aliases**:
|
|
650
|
-
```shell
|
|
651
|
-
curl -X "POST" "http://localhost:9200/_aliases" \
|
|
652
|
-
-H 'Content-Type: application/json' \
|
|
653
|
-
-d $'{
|
|
654
|
-
"actions": [
|
|
655
|
-
{
|
|
656
|
-
"remove": {
|
|
657
|
-
"index": "*",
|
|
658
|
-
"alias": "items_my-collection"
|
|
659
|
-
}
|
|
660
|
-
},
|
|
661
|
-
{
|
|
662
|
-
"add": {
|
|
663
|
-
"index": "items_my-collection-lower_my-collection-hex-000002",
|
|
664
|
-
"alias": "items_my-collection"
|
|
665
|
-
}
|
|
666
|
-
}
|
|
667
|
-
]
|
|
668
|
-
}'
|
|
669
|
-
```
|
|
670
|
-
- If you are happy with the data in the newly created index, you can move the alias items_my-collection to the new index
|
|
671
|
-
- This makes the modified Items with lowercase identifiers visible to users accessing my-collection in the STAC API
|
|
672
|
-
- Using aliases allows you to switch between different index versions without changing the API endpoint
|
|
673
|
-
|
|
674
|
-
## Auth
|
|
675
|
-
|
|
676
|
-
- **Overview**: Authentication is an optional feature that can be enabled through Route Dependencies.
|
|
677
|
-
- **Implementation Options**:
|
|
678
|
-
- Basic authentication
|
|
679
|
-
- OAuth2 with Keycloak
|
|
680
|
-
- Custom route dependencies
|
|
681
|
-
- **Configuration**: Authentication can be configured using the `STAC_FASTAPI_ROUTE_DEPENDENCIES` environment variable.
|
|
682
|
-
- **Examples and Documentation**: Detailed examples and implementation guides can be found in the [examples/auth](examples/auth) directory.
|
|
683
|
-
|
|
684
|
-
## Aggregation
|
|
685
|
-
|
|
686
|
-
- **Supported Aggregations**:
|
|
687
|
-
- Spatial aggregations of points and geometries
|
|
688
|
-
- Frequency distribution aggregation of any property including dates
|
|
689
|
-
- Temporal distribution of datetime values
|
|
690
|
-
|
|
691
|
-
- **Endpoint Locations**:
|
|
692
|
-
- Root Catalog level: `/aggregations`
|
|
693
|
-
- Collection level: `/<collection_id>/aggregations`
|
|
694
|
-
|
|
695
|
-
- **Implementation Details**: The `sfeos_helpers.aggregation` package provides specialized functionality for both Elasticsearch and OpenSearch backends.
|
|
696
|
-
|
|
697
|
-
- **Documentation**: Detailed information about supported aggregations can be found in [the aggregation docs](./docs/src/aggregation.md).
|
|
698
|
-
|
|
699
|
-
|
|
700
|
-
## Rate Limiting
|
|
701
|
-
|
|
702
|
-
- **Overview**: Rate limiting is an optional security feature that controls API request frequency on a remote address basis.
|
|
703
|
-
|
|
704
|
-
- **Configuration**: Enabled by setting the `STAC_FASTAPI_RATE_LIMIT` environment variable:
|
|
705
|
-
```
|
|
706
|
-
STAC_FASTAPI_RATE_LIMIT=500/minute
|
|
707
|
-
```
|
|
708
|
-
|
|
709
|
-
- **Functionality**:
|
|
710
|
-
- Limits each client to a specified number of requests per time period (e.g., 500 requests per minute)
|
|
711
|
-
- Helps prevent API abuse and maintains system stability
|
|
712
|
-
- Ensures fair resource allocation among all clients
|
|
713
|
-
|
|
714
|
-
- **Examples**: Implementation examples are available in the [examples/rate_limit](examples/rate_limit) directory.
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
stac_fastapi
|