Merge branch 'main' into feat/orphan-files

Author: jayceslesar

.github/ISSUE_TEMPLATE/iceberg_bug_report.yml

@@ -28,7 +28,8 @@ body:
       description: What Apache Iceberg version are you using?
       multiple: false
       options:
-        - "0.9.0 (latest release)"
+        - "0.9.1 (latest release)"
+        - "0.9.0"
         - "0.8.1"
         - "0.8.0"
         - "0.7.1"

dev/docker-compose-integration.yml

@@ -81,7 +81,7 @@ services:
       - AWS_REGION=us-east-1
     entrypoint: >
       /bin/sh -c "
-      until (/usr/bin/mc config host add minio http://minio:9000 admin password) do echo '...waiting...' && sleep 1; done;
+      until (/usr/bin/mc alias set minio http://minio:9000 admin password) do echo '...waiting...' && sleep 1; done;
       /usr/bin/mc mb minio/warehouse;
       /usr/bin/mc policy set public minio/warehouse;
       tail -f /dev/null

dev/docker-compose.yml

@@ -38,7 +38,7 @@ services:
       - AWS_REGION=us-east-1
     entrypoint: >
       /bin/sh -c "
-      until (/usr/bin/mc config host add minio http://minio:9000 admin password) do echo '...waiting...' && sleep 1; done;
+      until (/usr/bin/mc alias set minio http://minio:9000 admin password) do echo '...waiting...' && sleep 1; done;
       /usr/bin/mc rm -r --force minio/warehouse;
       /usr/bin/mc mb minio/warehouse;
       /usr/bin/mc policy set public minio/warehouse;

mkdocs/docs/configuration.md

@@ -95,6 +95,7 @@ Iceberg works with the concept of a FileIO which is a pluggable module for readi
 - **hdfs**: `PyArrowFileIO`
 - **abfs**, **abfss**: `FsspecFileIO`
 - **oss**: `PyArrowFileIO`
+- **hf**: `FsspecFileIO`
 
 You can also set the FileIO explicitly:
 
@@ -154,6 +155,7 @@ For the FileIO there are several configuration options available:
 | adls.tenant-id         | ad667be4-b811-11ed-afa1-0242ac120002                                                      | The tenant-id                                                                                                                                                                                                                                                                          |
 | adls.client-id         | ad667be4-b811-11ed-afa1-0242ac120002                                                      | The client-id                                                                                                                                                                                                                                                                          |
 | adls.client-secret     | oCA3R6P\*ka#oa1Sms2J74z...                                                                | The client-secret                                                                                                                                                                                                                                                                      |
+| adls.account-host      | accountname1.blob.core.windows.net                                                        | The storage account host. See [AzureBlobFileSystem](https://github.com/fsspec/adlfs/blob/adb9c53b74a0d420625b86dd00fbe615b43201d2/adlfs/spec.py#L125) for reference                                                                                                                   |
 
 <!-- markdown-link-check-enable-->
 
@@ -193,6 +195,17 @@ PyIceberg uses [S3FileSystem](https://arrow.apache.org/docs/python/generated/pya
 
 <!-- markdown-link-check-enable-->
 
+### Hugging Face
+
+<!-- markdown-link-check-disable -->
+
+| Key         | Example                  | Description                                               |
+| ----------- | ------------------------ | --------------------------------------------------------- |
+| hf.endpoint | <https://huggingface.co> | Configure the endpoint for Hugging Face                   |
+| hf.token    | hf_xxx                   | The Hugging Face token to access HF Datasets repositories |
+
+<!-- markdown-link-check-enable-->
+
 ### PyArrow
 
 <!-- markdown-link-check-disable -->
@@ -332,6 +345,7 @@ catalog:
 | rest.signing-region | us-east-1                        | The region to use when SigV4 signing a request                                                     |
 | rest.signing-name   | execute-api                      | The service signing name to use when SigV4 signing a request                                       |
 | oauth2-server-uri   | <https://auth-service/cc>          | Authentication URL to use for client credentials authentication (default: uri + 'v1/oauth/tokens') |
+| snapshot-loading-mode | refs                             | The snapshots to return in the body of the metadata. Setting the value to `all` would return the full set of snapshots currently valid for the table. Setting the value to `refs` would load all snapshots referenced by branches or tags. |
 
 <!-- markdown-link-check-enable-->