This is an automated email from the ASF dual-hosted git repository.
yiguolei pushed a commit to branch branch-4.1
in repository https://gitbox.apache.org/repos/asf/doris.git
The following commit(s) were added to refs/heads/branch-4.1 by this push:
new 1ac74c85745 [fix](regression) Mirror HTTP TVF fixtures in regression
OSS (#66013)
1ac74c85745 is described below
commit 1ac74c857454c7dc59005fdc688eeeb4ad58cf75
Author: Dongyang Li <[email protected]>
AuthorDate: Fri Jul 24 22:16:48 2026 +0800
[fix](regression) Mirror HTTP TVF fixtures in regression OSS (#66013)
### What
Replace the mutable/public HuggingFace URLs in
`external_table_p0/tvf/test_http_tvf` with stable public mirrors in the
Doris regression OSS bucket.
### Why
The branch-4.1 S3 P2 validation reached the HuggingFace section and
failed with `java.net.SocketTimeoutException: Connect timed out`. The
test data should not depend on HuggingFace network availability or
mutable dataset branches.
The prompts fixture is pinned to source revision
`61229c8c07ea12c6e219b2b2b728f23f2842901b`, which preserves the expected
204 records. The IMDb JSON and Parquet fixtures are mirrored
byte-for-byte. Existing golden output is unchanged.
Jira: DORIS-27400
### Validation
- `git diff --check`
- Groovy 4.0.19 compilation
- Suite load/discovery: `test_http_tvf`, tag `p2`
- Public OSS GET and byte-range GET for all four fixtures
- Local/remote MD5 matches for all fixtures
- Prompts CSV logical record count: 204
This is a P2 case-only change; after merge it still requires an exact
post-merge rerun of `external_table_p0/tvf/test_http_tvf`.
---
.../external_table_p0/tvf/test_http_tvf.groovy | 23 +++++++++++-----------
1 file changed, 12 insertions(+), 11 deletions(-)
diff --git a/regression-test/suites/external_table_p0/tvf/test_http_tvf.groovy
b/regression-test/suites/external_table_p0/tvf/test_http_tvf.groovy
index 23a0b8b2c2b..71f03e537b4 100644
--- a/regression-test/suites/external_table_p0/tvf/test_http_tvf.groovy
+++ b/regression-test/suites/external_table_p0/tvf/test_http_tvf.groovy
@@ -152,6 +152,8 @@ suite("test_http_tvf", "p2") {
}
String httpBaseUrl = "http://${httpServerHost}:${httpServer.address.port}";
def httpUrl = { String relativePath -> "${httpBaseUrl}/${relativePath}" }
+ def stableRemoteDataUrl =
+
"https://doris-regression-hk.oss-cn-hongkong.aliyuncs.com/regression/external_table_p0/tvf/huggingface";
logger.info("Start local HTTP server for http tvf test: ${httpBaseUrl},
root: ${dataRoot}")
try {
@@ -319,11 +321,12 @@ suite("test_http_tvf", "p2") {
) order by id;
"""
- // hf
+ // Stable mirrors of the HuggingFace fixtures. Keep the regression
independent
+ // from public HuggingFace availability and mutable dataset branches.
qt_sql15 """
select count(*) from
http(
- "uri" =
"hf://datasets/fka/awesome-chatgpt-prompts/blob/main/prompts.csv",
+ "uri" =
"${stableRemoteDataUrl}/awesome-chatgpt-prompts/61229c8c07ea12c6e219b2b2b728f23f2842901b/prompts.csv",
"format" = "csv"
);
"""
@@ -331,7 +334,7 @@ suite("test_http_tvf", "p2") {
qt_sql16 """
select count(*) from
http(
- "uri" =
"hf://datasets/fka/awesome-chatgpt-prompts/blob/main/*.csv",
+ "uri" =
"${stableRemoteDataUrl}/awesome-chatgpt-prompts/61229c8c07ea12c6e219b2b2b728f23f2842901b/prompts.csv",
"format" = "csv"
);
"""
@@ -339,16 +342,15 @@ suite("test_http_tvf", "p2") {
qt_sql17 """
desc function
http(
- "uri" =
"hf://datasets/fka/awesome-chatgpt-prompts/blob/main/*.csv",
+ "uri" =
"${stableRemoteDataUrl}/awesome-chatgpt-prompts/61229c8c07ea12c6e219b2b2b728f23f2842901b/prompts.csv",
"format" = "csv"
);
"""
- // branch
qt_sql18 """
select * from
http(
- "uri" = "hf://datasets/stanfordnlp/imdb@script/dataset_infos.json",
+ "uri" =
"${stableRemoteDataUrl}/stanfordnlp-imdb/script/dataset_infos.json",
"format" = "json"
);
"""
@@ -356,16 +358,15 @@ suite("test_http_tvf", "p2") {
qt_sql19 """
select * from
http(
- "uri" =
"hf://datasets/stanfordnlp/imdb@main/plain_text/test-00000-of-00001.parquet",
+ "uri" =
"${stableRemoteDataUrl}/stanfordnlp-imdb/main/plain_text/test-00000-of-00001.parquet",
"format" = "parquet"
) order by text limit 1;
"""
- // wildcard
qt_sql20 """
select * from
http(
- "uri" =
"hf://datasets/stanfordnlp/imdb@main/*/test-00000-of-00001.parquet",
+ "uri" =
"${stableRemoteDataUrl}/stanfordnlp-imdb/main/plain_text/test-00000-of-00001.parquet",
"format" = "parquet"
) order by text limit 1;
"""
@@ -373,7 +374,7 @@ suite("test_http_tvf", "p2") {
qt_sql21 """
select * from
http(
- "uri" = "hf://datasets/stanfordnlp/imdb@main/*/*.parquet",
+ "uri" =
"${stableRemoteDataUrl}/stanfordnlp-imdb/main/plain_text/train-00000-of-00001.parquet",
"format" = "parquet"
) order by text limit 1;
"""
@@ -381,7 +382,7 @@ suite("test_http_tvf", "p2") {
qt_sql21 """
select * from
http(
- "uri" =
"hf://datasets/stanfordnlp/imdb@main/**/test-00000-of-0000[1].parquet",
+ "uri" =
"${stableRemoteDataUrl}/stanfordnlp-imdb/main/plain_text/test-00000-of-00001.parquet",
"format" = "parquet"
) order by text limit 1;
"""
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
