From 6e8a0a32a79a5d4c748787e925dfe73dbe9c755e Mon Sep 17 00:00:00 2001 From: Tom Augspurger Date: Mon, 17 Jun 2024 10:12:29 -0500 Subject: [PATCH] Document stac-geoparquet and sentinel-2-l2a workflow creation (#304) * Document how stac-geoparquet workflow was created * sentinel-2 too * Bump version * Increase chunk length --- datasets/sentinel-2/README.md | 2 +- datasets/sentinel-2/dataset.yaml | 2 +- datasets/stac-geoparquet/README.md | 10 +++++++++- 3 files changed, 11 insertions(+), 3 deletions(-) diff --git a/datasets/sentinel-2/README.md b/datasets/sentinel-2/README.md index d0aa96ef..01163fc9 100644 --- a/datasets/sentinel-2/README.md +++ b/datasets/sentinel-2/README.md @@ -19,5 +19,5 @@ az acr build -r {the registry} --subscription {the subscription} -t pctasks-sent Created with ``` -pctasks dataset process-items --is-update-workflow sentinel-2-l2a-update -d datasets/sentinel-2/dataset.yaml +pctasks dataset process-items --is-update-workflow sentinel-2-l2a-update -d datasets/sentinel-2/dataset.yaml -u ``` \ No newline at end of file diff --git a/datasets/sentinel-2/dataset.yaml b/datasets/sentinel-2/dataset.yaml index dc20ddc4..c31ebaba 100644 --- a/datasets/sentinel-2/dataset.yaml +++ b/datasets/sentinel-2/dataset.yaml @@ -36,6 +36,6 @@ collections: # But we start at depth=2 thanks to the split, so we use a depth of 5 here. min_depth: 5 max_depth: 5 - chunk_length: 5000 + chunk_length: 20000 chunk_storage: uri: blob://sentinel2l2a01/sentinel2-l2-info/pctasks-chunks/ diff --git a/datasets/stac-geoparquet/README.md b/datasets/stac-geoparquet/README.md index d0b15935..ef293a83 100644 --- a/datasets/stac-geoparquet/README.md +++ b/datasets/stac-geoparquet/README.md @@ -19,4 +19,12 @@ This requires the following permissions By default, this workflow will generate geoparquet assets for all collections. If you want to select a subset of collections, you can use either: 1. `extra_skip`: This will skip certain collections -1. `collections`: This will only generate geoparquet for the specified collection(s). \ No newline at end of file +1. `collections`: This will only generate geoparquet for the specified collection(s). + +## Updates + +The workflow used for updates was registered with + +``` +pctasks workflow update datasets/workflows/stac-geoparquet.yaml +``` \ No newline at end of file