Skip to content

Fix a bug where dataset will not load if s3 prefix starts with a digit #3109

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
chinmaymore wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix a bug where dataset will not load if s3 prefix starts with a digit #3109

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion api/src/main/java/marquez/service/models/NodeId.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -222,7 +222,7 @@ private String[] parts(int expectedParts, String expectedType) {
return parts;
} else {
// try to avoid matching colons in URIs- e.g., scheme://authority and host:port patterns
Pattern p = Pattern.compile("(?:" + ID_DELIM + "(?!//|\\d+))");
Pattern p = Pattern.compile("(?:" + ID_DELIM + "(?!//|\\d+(?:/|$)))");
Matcher matcher = p.matcher(value);
String[] returnParts = new String[expectedParts];

Expand Down
3 changes: 3 additions & 0 deletions api/src/test/java/marquez/service/models/NodeIdTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,6 +71,7 @@ public void testJobWithVersion(String namespace, String job) {
value = {
"my-namespace$my-dataset",
"gs://bucket$/path/to/data",
"s3://mybucket$3d801.temp/table",
"postgresql://hostname:5432/database$my_table",
"my-namespace$my_struct<a:bigint,b:bigint,c:string>"
},
Expand All @@ -95,6 +96,8 @@ public void testDataset(String namespace, String dataset) {
value = {
"my-namespace$my-dataset#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
"gs://bucket$/path/to/data#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
"s3://mybucket$3d801.temp/table#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
"s3://mybucket$/3d801.temp/table#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
"postgresql://hostname:5432/database$my_table#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
"my-namespace$my_struct<a:bigint,b:bigint,c:string>#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee"
},
Expand Down
2 changes: 1 addition & 1 deletion clients/java/src/main/java/marquez/client/models/NodeId.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -150,7 +150,7 @@ private String[] parts(int expectedParts, String expectedType) {
return parts;
} else {
// try to avoid matching colons in URIs- e.g., scheme://authority and host:port patterns
Pattern p = Pattern.compile("(?:" + ID_DELIM + "(?!//|\\d+))");
Pattern p = Pattern.compile("(?:" + ID_DELIM + "(?!//|\\d+(?:/|$)))");
Matcher matcher = p.matcher(value);
String[] returnParts = new String[expectedParts];

Expand Down
11 changes: 9 additions & 2 deletions clients/java/src/test/java/marquez/client/models/NodeIdTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@ public class NodeIdTest {
value = {
"my-namespace$my-dataset",
"gs://bucket$/path/to/data",
"s3://mybucket$3d801.temp/table",
"postgresql://hostname:5432/database$my_table",
"my-namespace$my_struct<a:bigint,b:bigint,c:string>"
},
Expand All @@ -38,7 +39,9 @@ public void testDataset(String namespace, String dataset) {
value = {
"my-namespace$my-dataset$colA",
"gs://bucket$/path/to/data$colA",
"gs://bucket$/path/to/data$col_A"
"gs://bucket$/path/to/data$col_A",
"s3://mybucket$3d801.temp/table$colA",
"s3://mybucket$3d801.temp/table$col_A"
},
delimiter = '$')
public void testDatasetField(String namespace, String dataset, String field) {
Expand Down Expand Up @@ -90,6 +93,8 @@ public void testJobWithVersion(String namespace, String job) {
value = {
"my-namespace$my-dataset#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
"gs://bucket$/path/to/data#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
"s3://mybucket$3d801.temp/table#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
"s3://mybucket$/3d801.temp/table#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
"postgresql://hostname:5432/database$my_table#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
"my-namespace$my_struct<a:bigint,b:bigint,c:string>#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee"
},
Expand All @@ -113,7 +118,9 @@ public void testDatasetWithVersion(String namespace, String dataset) {
value = {
"my-namespace$my-dataset$colA#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
"gs://bucket$/path/to/data$colA#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
"gs://bucket$/path/to/data$col_A#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee"
"gs://bucket$/path/to/data$col_A#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
"s3://mybucket$3d801.temp/table$colA#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
"s3://mybucket$/3d801.temp/table$col_A#aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee"
},
delimiter = '$')
public void testDatasetFieldWithVersion(
Expand Down