Whitelisting Onelake API & Workspace PL FQDNs

src/azure/builder.rs

@@ -25,6 +25,7 @@ use crate::client::{HttpConnector, TokenCredentialProvider, http_connector};
 use crate::config::ConfigValue;
 use crate::{ClientConfigKey, ClientOptions, Result, RetryConfig, StaticCredentialProvider};
 use percent_encoding::percent_decode_str;
+use regex::Regex;
 use serde::{Deserialize, Serialize};
 use std::str::FromStr;
 use std::sync::Arc;
@@ -657,6 +658,9 @@ impl MicrosoftAzureBuilder {
             false => Ok(s.to_string()),
         };
 
+        const DFS_FABRIC_SUFFIX: &str = "dfs.fabric.microsoft.com";
+        const BLOB_FABRIC_SUFFIX: &str = "blob.fabric.microsoft.com";
+
         match parsed.scheme() {
             "adl" | "azure" => self.container_name = Some(validate(host)?),
             "az" | "abfs" | "abfss" => {
@@ -675,32 +679,79 @@ impl MicrosoftAzureBuilder {
                     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(
+            "https" => {
+                const DFS_FABRIC_SUFFIX: &str = "dfs.fabric.microsoft.com";
+                const BLOB_FABRIC_SUFFIX: &str = "blob.fabric.microsoft.com";
+                const DFS_AZURE_SUFFIX: &str = "dfs.core.windows.net";
+                const BLOB_AZURE_SUFFIX: &str = "blob.core.windows.net";
+
+                // Regex to match WS-PL FQDN: "{workspaceid}.z??.dfs.fabric.microsoft.com"
+                // workspaceid = 32 hex chars, z?? = z + first two chars of workspaceid
+                lazy_static::lazy_static! {
+                    static ref WS_PL_REGEX: Regex = Regex::new(r"^(?P<workspaceid>[0-9a-f]{32})\.z(?P<xy>[0-9a-f]{2})\.(dfs|blob)\.fabric\.microsoft\.com$").unwrap();
+                }
+
+                if let Some(captures) = WS_PL_REGEX.captures(host) {
+                    let workspaceid = captures.name("workspaceid").unwrap().as_str();
+                    let xy = captures.name("xy").unwrap().as_str();
+
+                    // Validate z?? matches first 2 chars of workspaceid
+                    if &workspaceid[0..2] != xy {
+                        return Err(Error::UrlNotRecognised { url: url.into() }.into());
+                    }
+
+                    self.account_name = Some(validate(workspaceid)?);
+                    self.use_fabric_endpoint = true;
+
+                    let container = parsed
+                        .path_segments()
+                        .and_then(|mut s| s.next())
+                        .unwrap_or("");
+                    if !container.is_empty() {
+                        self.container_name = Some(validate(container)?);
+                    }
+
+                    return Ok(());
+                }
+
+                // Otherwise, check Fabric global / Onelake API FQDN 
+                if host.ends_with(DFS_FABRIC_SUFFIX) || host.ends_with(BLOB_FABRIC_SUFFIX) {
+                let labels: Vec<&str> = host.split('.').collect();  
+                let account_name = if labels.len() >= 2 && labels[0].contains("api") && labels[1] == "onelake" {
+                                        format!("{}-{}", labels[0], labels[1])
+                                    } else {
+                                        labels[0].to_string()
+                                    };
+
+                self.account_name = Some(validate(&account_name)?);
+                self.use_fabric_endpoint = true;
+
+                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)?);
                     }
+
+                    return Ok(());
                 }
-                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
-                    // - 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(
+
+                // Azure Storage public
+                if host.ends_with(DFS_AZURE_SUFFIX) || host.ends_with(BLOB_AZURE_SUFFIX) {
+                    let first_label = host.split('.').next().unwrap_or_default();
+                    self.account_name = Some(validate(first_label)?);
+
+                    let container = 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())
+                    if !container.is_empty() {
+                        self.container_name = Some(validate(container)?);
                     }
-                    self.use_fabric_endpoint = true.into();
+
+                    return Ok(());
                 }
-                _ => return Err(Error::UrlNotRecognised { url: url.into() }.into()),
+
+                return Err(Error::UrlNotRecognised { url: url.into() }.into());
             },
             scheme => {
                 let scheme = scheme.into();