Skip to content

Whitelisting Onelake API & Workspace PL FQDNs #552

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

Closed
SmritiAgrawal04 wants to merge 6 commits into from
+104 −26
Closed

Whitelisting Onelake API & Workspace PL FQDNs #552

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
3960a7a
Whitelisting Onelake API & Workspace PL FQDNs
Nov 25, 2025
5b9dd47
Addressing comments to whitelist api-onelake fqdns and add UTs
Jan 8, 2026
4ba4321
Reverting the mistakenly modified UT
Jan 12, 2026
3826e5b
Adding validation for xy in WS-PL URL & case insensitive regex
Jan 13, 2026
897b528
Making regex an optional dependency
Jan 21, 2026
5d7a1fd
Eliminating the use of regex for ws-pl fqdn matching
Feb 5, 2026
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
130 changes: 104 additions & 26 deletions src/azure/builder.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -671,36 +671,74 @@ impl MicrosoftAzureBuilder {
self.container_name = Some(validate(parsed.username())?);
self.account_name = Some(validate(a)?);
self.use_fabric_endpoint = true.into();
} else if let Some(a) = host.strip_suffix(".blob.core.windows.net") {
self.container_name = Some(validate(parsed.username())?);
self.account_name = Some(validate(a)?);
} else if let Some(a) = host.strip_suffix(".blob.fabric.microsoft.com") {
self.container_name = Some(validate(parsed.username())?);
self.account_name = Some(validate(a)?);
self.use_fabric_endpoint = true.into();
} else {
return Err(Error::UrlNotRecognised { url: url.into() }.into());
}
}
"https" => match host.split_once('.') {
Some((a, "dfs.core.windows.net")) | Some((a, "blob.core.windows.net")) => {
self.account_name = Some(validate(a)?);
let container = parsed.path_segments().unwrap().next().expect(
"iterator always contains at least one string (which may be empty)",
);
if !container.is_empty() {
self.container_name = Some(validate(container)?);
"https" => {
// "{workspaceid}.z??.(onelake|dfs|blob).fabric.microsoft.com"
Comment thread
SmritiAgrawal04 marked this conversation as resolved.
match host.split_once('.') {

// Workspace-level Private Link detection
Some((workspaceid, rest)) if rest.starts_with('z') && rest.ends_with("fabric.microsoft.com") => {
// rest looks like: "z28.dfs.fabric.microsoft.com" / "z28.blob.fabric.microsoft.com" / etc.
// Account name for WS-PL is two labels: "{wsid}.z{xy}"
let (zone, _) = rest
.split_once('.')
.unwrap_or((rest, ""));

let wsid = validate(workspaceid)?;
let zone = validate(zone)?;

self.account_name = Some(format!("{wsid}.{zone}"));

// Attempt to infer the container name from the URL
let container = parsed.path_segments().unwrap().next()
.expect("iterator always contains at least one string (which may be empty)");

if !container.is_empty() {
self.container_name = Some(validate(container)?);
}

self.use_fabric_endpoint = true.into();
}
}
Some((a, "dfs.fabric.microsoft.com")) | Some((a, "blob.fabric.microsoft.com")) => {
self.account_name = Some(validate(a)?);
// Attempt to infer the container name from the URL
Comment thread
SmritiAgrawal04 marked this conversation as resolved.
// - https://onelake.dfs.fabric.microsoft.com/<workspaceGUID>/<itemGUID>/Files/test.csv
// - https://onelake.dfs.fabric.microsoft.com/<workspace>/<item>.<itemtype>/<path>/<fileName>
//
// See <https://learn.microsoft.com/en-us/fabric/onelake/onelake-access-api>
let workspace = parsed.path_segments().unwrap().next().expect(
"iterator always contains at least one string (which may be empty)",
);
if !workspace.is_empty() {
self.container_name = Some(workspace.to_string())

// Azure Storage public
Some((a, "dfs.core.windows.net")) | Some((a, "blob.core.windows.net")) => {
self.account_name = Some(validate(a)?);

// Attempt to infer the container name from the URL
let container = parsed.path_segments().unwrap().next()
.expect("iterator always contains at least one string (which may be empty)");

if !container.is_empty() {
self.container_name = Some(validate(container)?);
}
}
self.use_fabric_endpoint = true.into();

// Fabric endpoints
Some((a, "dfs.fabric.microsoft.com")) | Some((a, "blob.fabric.microsoft.com")) => {
self.account_name = Some(validate(a)?);

let workspace = parsed.path_segments().unwrap().next()
.expect("iterator always contains at least one string (which may be empty)");

if !workspace.is_empty() {
self.container_name = Some(workspace.to_string());
}

self.use_fabric_endpoint = true.into();
}

_ => return Err(Error::UrlNotRecognised { url: url.into() }.into()),
}
_ => return Err(Error::UrlNotRecognised { url: url.into() }.into()),
},
scheme => {
let scheme = scheme.into();
Expand Down Expand Up @@ -1165,7 +1203,7 @@ mod tests {
assert_eq!(builder.account_name, Some("account".to_string()));
assert_eq!(builder.container_name, None);
assert!(builder.use_fabric_endpoint.get().unwrap());

let mut builder = MicrosoftAzureBuilder::new();
builder
.parse_url("https://account.dfs.fabric.microsoft.com/container")
Expand All @@ -1174,6 +1212,14 @@ mod tests {
assert_eq!(builder.container_name.as_deref(), Some("container"));
assert!(builder.use_fabric_endpoint.get().unwrap());

let mut builder = MicrosoftAzureBuilder::new();
builder
.parse_url("https://onelake.dfs.fabric.microsoft.com/c047b3e3-4e89-407a-98d7-cf9949ae92a3/9f1a2b3c-4d5e-6f70-8a9b-c0d1e2f3a456.lakehouse/Files/tables/sales/data.parquet")
.unwrap();
assert_eq!(builder.account_name, Some("onelake".to_string()));
assert_eq!(builder.container_name.as_deref(), Some("c047b3e3-4e89-407a-98d7-cf9949ae92a3"));
assert!(builder.use_fabric_endpoint.get().unwrap());

let mut builder = MicrosoftAzureBuilder::new();
builder
.parse_url("https://account.blob.fabric.microsoft.com/")
Expand All @@ -1190,14 +1236,46 @@ mod tests {
assert_eq!(builder.container_name.as_deref(), Some("container"));
assert!(builder.use_fabric_endpoint.get().unwrap());

let mut builder = MicrosoftAzureBuilder::new();
builder
.parse_url("https://Ab000000000000000000000000000000.zAb.dfs.fabric.microsoft.com/")
.unwrap();
assert_eq!(builder.account_name, Some("ab000000000000000000000000000000.zab".to_string()));
Copy link
Copy Markdown
Contributor

@alamb alamb Jan 17, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

is the account name really supposed to have the ab000000000000000000000000000000 in it? It seems confusing that the container name is also ab000000000000000000000000000000

assert_eq!(builder.container_name.as_deref(), None);
assert!(builder.use_fabric_endpoint.get().unwrap());

let mut builder = MicrosoftAzureBuilder::new();
builder
.parse_url("https://ab000000000000000000000000000000.zab.dfs.fabric.microsoft.com/")
.unwrap();
assert_eq!(builder.account_name, Some("ab000000000000000000000000000000.zab".to_string()));
assert_eq!(builder.container_name.as_deref(), None);
assert!(builder.use_fabric_endpoint.get().unwrap());

let mut builder = MicrosoftAzureBuilder::new();
builder
.parse_url("https://c047b3e34e89407a98d7cf9949ae92a3.zc0.blob.fabric.microsoft.com/c047b3e3-4e89-407a-98d7-cf9949ae92a3/9f1a2b3c-4d5e-6f70-8a9b-c0d1e2f3a456/file")
.unwrap();
assert_eq!(builder.account_name, Some("c047b3e34e89407a98d7cf9949ae92a3.zc0".to_string()));
assert_eq!(builder.container_name.as_deref(), Some("c047b3e3-4e89-407a-98d7-cf9949ae92a3"));
assert!(builder.use_fabric_endpoint.get().unwrap());

let mut builder = MicrosoftAzureBuilder::new();
builder
.parse_url("https://c047b3e34e89407a98d7cf9949ae92a3.zc0.onelake.fabric.microsoft.com/c047b3e3-4e89-407a-98d7-cf9949ae92a3/9f1a2b3c-4d5e-6f70-8a9b-c0d1e2f3a456/file")
.unwrap();
assert_eq!(builder.account_name, Some("c047b3e34e89407a98d7cf9949ae92a3.zc0".to_string()));
assert_eq!(builder.container_name.as_deref(), Some("c047b3e3-4e89-407a-98d7-cf9949ae92a3"));
assert!(builder.use_fabric_endpoint.get().unwrap());

let err_cases = [
"mailto://account.blob.core.windows.net/",
"az://blob.mydomain/",
"abfs://container.foo/path",
"abfss://file_system@account.foo.dfs.core.windows.net/",
"abfss://file_system.bar@account.dfs.core.windows.net/",
"https://blob.mydomain/",
"https://blob.foo.dfs.core.windows.net/",
"https://blob.foo.dfs.core.windows.net/"
];
let mut builder = MicrosoftAzureBuilder::new();
for case in err_cases {
Expand Down Expand Up @@ -1256,4 +1334,4 @@ mod tests {
panic!("{key} not propagated as ClientConfigKey");
}
}
}
}