Support Input Array

.gitignore

@@ -8,4 +8,4 @@ test/python/__pycache__/
 .Rhistory
 *.log
 *.csv
-!test/data/tranco.csv
+!test/data/*.csv

README.md

@@ -239,20 +239,20 @@ You can use this function to get the ranking of a domain:
 
 ```sql
 D SELECT get_tranco_rank('microsoft.com') as rank;
-┌───────┐
-│ rank  │
-│ int32 │
-├───────┤
-│     2 │
-└───────┘
+┌─────────┐
+│  rank   │
+│ varchar │
+├─────────┤
+│ 2       │
+└─────────┘
 
 D SELECT get_tranco_rank('cloudflare.com') as rank;
-┌───────┐
-│ rank  │
-│ int32 │
-├───────┤
-│    13 │
-└───────┘
+┌─────────┐
+│  rank   │
+│ varchar │
+├─────────┤
+│ 13      │
+└─────────┘
 ```
 
 ### Get Extension Version

src/functions/extract_domain.cpp

@@ -11,18 +11,23 @@ namespace duckdb
     {
         // Extract the input from the arguments
         auto &input_vector = args.data[0];
-        auto input         = input_vector.GetValue (0).ToString ();
+        auto result_data   = FlatVector::GetData<string_t> (result);
 
-        if (input.empty ())
+        for (idx_t i = 0; i < args.size (); i++)
         {
-            result.SetValue (0, Value (""));
-            return;
-        }
-
-        // Extract the domain using the utility function
-        auto domain = netquack::ExtractDomain (state, input);
+            auto input = input_vector.GetValue (i).ToString ();
 
-        result.SetValue (0, Value (domain));
+            try
+            {
+                // Extract the domain using the utility function
+                auto domain    = netquack::ExtractDomain (state, input);
+                result_data[i] = StringVector::AddString (result, domain);
+            }
+            catch (const std::exception &e)
+            {
+                result_data[i] = "Error extracting domain: " + std::string (e.what ());
+            }
+        }
     }
 
     namespace netquack

src/functions/extract_host.cpp

@@ -9,13 +9,23 @@ namespace duckdb
     {
         // Extract the input from the arguments
         auto &input_vector = args.data[0];
-        auto input         = input_vector.GetValue (0).ToString ();
+        auto result_data   = FlatVector::GetData<string_t> (result);
 
-        // Extract the host using the utility function
-        auto host = netquack::ExtractHost (input);
+        for (idx_t i = 0; i < args.size (); i++)
+        {
+            auto input = input_vector.GetValue (i).ToString ();
 
-        // Set the result
-        result.SetValue (0, Value (host));
+            try
+            {
+                // Extract the host using the utility function
+                auto host      = netquack::ExtractHost (input);
+                result_data[i] = StringVector::AddString (result, host);
+            }
+            catch (const std::exception &e)
+            {
+                result_data[i] = "Error extracting host: " + std::string (e.what ());
+            }
+        }
     }
 
     namespace netquack

src/functions/extract_path.cpp

@@ -9,13 +9,23 @@ namespace duckdb
     {
         // Extract the input from the arguments
         auto &input_vector = args.data[0];
-        auto input         = input_vector.GetValue (0).ToString ();
+        auto result_data   = FlatVector::GetData<string_t> (result);
 
-        // Extract the path using the utility function
-        auto path = netquack::ExtractPath (input);
+        for (idx_t i = 0; i < args.size (); i++)
+        {
+            auto input = input_vector.GetValue (i).ToString ();
 
-        // Set the result
-        result.SetValue (0, Value (path));
+            try
+            {
+                // Extract the path using the utility function
+                auto path      = netquack::ExtractPath (input);
+                result_data[i] = StringVector::AddString (result, path);
+            }
+            catch (const std::exception &e)
+            {
+                result_data[i] = "Error extracting path: " + std::string (e.what ());
+            }
+        };
     }
 
     namespace netquack
@@ -26,11 +36,12 @@ namespace duckdb
             // Explanation:
             // ^                - Start of the string
             // (?:              - Non-capturing group for the protocol and domain part
-            //   (?:(?:ftp|https?|rsync):\/\/)? - Optional ftp://, http://, https://, or rsync://
-            //   (?:[^\/\s]+)    - Domain name (any characters except '/' or whitespace)
+            //   (?:(?:ftp|https?|rsync):\/\/)? - Optional protocol (ftp://, http://, https://, or rsync://)
+            //   (?:[^\/\s]+)   - Domain name or IP address (any characters except '/' or whitespace)
             // )
-            // (\/[^?#]*)       - Capturing group for the path (starts with '/', followed by any characters except '?' or '#')
-            std::regex path_regex (R"(^(?:(?:(?:ftp|https?|rsync):\/\/)?(?:[^\/\s]+))(\/[^?#]*))");
+            // (\/[^?#]*)?      - Optional capturing group for the path (starts with '/', followed by any characters except '?' or '#')
+            //                  - The '?' at the end makes the path component optional, allowing the regex to match URLs with or without a path
+            std::regex path_regex (R"(^(?:(?:(?:ftp|https?|rsync):\/\/)?(?:[^\/\s]+))(\/[^?#]*)?)");
             std::smatch path_match;
 
             // Use regex_search to find the path component in the input string

src/functions/extract_query.cpp

@@ -7,15 +7,25 @@ namespace duckdb
     // Function to extract the query string from a URL
     void ExtractQueryStringFunction (DataChunk &args, ExpressionState &state, Vector &result)
     {
-        // Extract the URL from the input
-        auto &url_vector = args.data[0];
-        auto url         = url_vector.GetValue (0).ToString ();
+        // Extract the input from the arguments
+        auto &input_vector = args.data[0];
+        auto result_data   = FlatVector::GetData<string_t> (result);
 
-        // Extract the query string
-        auto query_string = netquack::ExtractQueryString (url);
+        for (idx_t i = 0; i < args.size (); i++)
+        {
+            auto input = input_vector.GetValue (i).ToString ();
 
-        // Set the result
-        result.SetValue (0, Value (query_string));
+            try
+            {
+                // Extract the query string using the utility function
+                auto query_string = netquack::ExtractQueryString (input);
+                result_data[i]    = StringVector::AddString (result, query_string);
+            }
+            catch (const std::exception &e)
+            {
+                result_data[i] = "Error extracting query string: " + std::string (e.what ());
+            }
+        };
     }
 
     namespace netquack

src/functions/extract_schema.cpp

@@ -9,13 +9,23 @@ namespace duckdb
     {
         // Extract the input from the arguments
         auto &input_vector = args.data[0];
-        auto input         = input_vector.GetValue (0).ToString ();
+        auto result_data   = FlatVector::GetData<string_t> (result);
 
-        // Extract the schema using the utility function
-        auto schema = netquack::ExtractSchema (input);
+        for (idx_t i = 0; i < args.size (); i++)
+        {
+            auto input = input_vector.GetValue (i).ToString ();
 
-        // Set the result
-        result.SetValue (0, Value (schema));
+            try
+            {
+                // Extract the schema using the utility function
+                auto schema    = netquack::ExtractSchema (input);
+                result_data[i] = StringVector::AddString (result, schema);
+            }
+            catch (const std::exception &e)
+            {
+                result_data[i] = "Error extracting schema: " + std::string (e.what ());
+            }
+        };
     }
 
     namespace netquack

src/functions/extract_subdomain.cpp

@@ -11,12 +11,23 @@ namespace duckdb
     {
         // Extract the input from the arguments
         auto &input_vector = args.data[0];
-        auto input         = input_vector.GetValue (0).ToString ();
+        auto result_data   = FlatVector::GetData<string_t> (result);
 
-        // Extract the sub-domain using the utility function
-        auto subdomain = netquack::ExtractSubDomain (state, input);
+        for (idx_t i = 0; i < args.size (); i++)
+        {
+            auto input = input_vector.GetValue (i).ToString ();
 
-        result.SetValue (0, Value (subdomain));
+            try
+            {
+                // Extract the subdomain using the utility function
+                auto subdomain = netquack::ExtractSubDomain (state, input);
+                result_data[i] = StringVector::AddString (result, subdomain);
+            }
+            catch (const std::exception &e)
+            {
+                result_data[i] = "Error extracting subdomain: " + std::string (e.what ());
+            }
+        }
     }
 
     namespace netquack

src/functions/extract_tld.cpp

@@ -11,13 +11,23 @@ namespace duckdb
     {
         // Extract the input from the arguments
         auto &input_vector = args.data[0];
-        auto input         = input_vector.GetValue (0).ToString ();
+        auto result_data   = FlatVector::GetData<string_t> (result);
 
-        // Extract the top-level domain using the utility function
-        auto tld = netquack::ExtractTLD (state, input);
+        for (idx_t i = 0; i < args.size (); i++)
+        {
+            auto input = input_vector.GetValue (i).ToString ();
 
-        // Set the result
-        result.SetValue (0, Value (tld));
+            try
+            {
+                // Extract the top-level domain using the utility function
+                auto tld       = netquack::ExtractTLD (state, input);
+                result_data[i] = StringVector::AddString (result, tld);
+            }
+            catch (const std::exception &e)
+            {
+                result_data[i] = "Error extracting tld: " + std::string (e.what ());
+            }
+        }
     }
 
     namespace netquack

src/functions/get_tranco.cpp

@@ -148,13 +148,28 @@ namespace duckdb
                 throw std::runtime_error ("Tranco table not found. Download it first using `SELECT update_tranco(true);`");
             }
 
-            auto &domain_vector = args.data[0];
-            auto domain         = domain_vector.GetValue (0).ToString ();
+            // Extract the input from the arguments
+            auto &input_vector = args.data[0];
+            auto result_data   = FlatVector::GetData<string_t> (result);
 
-            auto query        = "SELECT rank FROM tranco_list WHERE domain = '" + domain + "'";
-            auto query_result = con.Query (query);
+            for (idx_t i = 0; i < args.size (); i++)
+            {
+                auto input = input_vector.GetValue (i).ToString ();
+
+                try
+                {
+                    auto query = "SELECT rank FROM tranco_list WHERE domain = '" + input + "'";
+
+                    auto query_result = con.Query (query);
+                    auto rank         = query_result->RowCount () > 0 ? query_result->GetValue (0, 0) : Value ();
 
-            result.SetValue (0, query_result->RowCount () > 0 ? query_result->GetValue (0, 0) : Value ());
+                    result_data[i] = StringVector::AddString (result, rank.ToString ());
+                }
+                catch (const std::exception &e)
+                {
+                    result_data[i] = "Error extracting tranco rank: " + std::string (e.what ());
+                }
+            }
         }
     } // namespace netquack
 } // namespace duckdb

src/netquack_extension.cpp

@@ -95,7 +95,7 @@ namespace duckdb
         auto get_tranco_rank_function = ScalarFunction (
             "get_tranco_rank",
             { LogicalType::VARCHAR },
-            LogicalType::INTEGER,
+            LogicalType::VARCHAR,
             netquack::GetTrancoRankFunction);
         ExtensionUtil::RegisterFunction (instance, get_tranco_rank_function);
 

test/data/examples.csv

@@ -0,0 +1,9 @@
+example.com
+example.com.ac
+example.com.co
+a.example.com
+example.com/a
+example.com.ac/a
+https://example.com
+https://a.example.com
+http://example.com.ac/path/?a=1&b=2&

test/data/examples_tranco.csv

@@ -0,0 +1,4 @@
+microsoft.com
+googleapis.com
+gstatic.com
+apple.com

test/sql/extract_domain.test

@@ -4,6 +4,9 @@
 
 require netquack
 
+statement ok
+CREATE TABLE uri_list AS SELECT * FROM read_csv('test/data/examples.csv', header=false, columns={'uri': 'VARCHAR'});
+
 query I
 SELECT extract_domain('example.com');
 ----
@@ -172,4 +175,17 @@ SELECT extract_domain('http:/example.com.ac/path');
 query I
 SELECT extract_domain('http:/example.com.ac:443/path');
 ----
-(empty)
+(empty)
+
+query I
+SELECT extract_domain(uri) from uri_list;
+----
+example.com
+example.com.ac
+example.com.co
+example.com
+example.com
+example.com.ac
+example.com
+example.com
+example.com.ac

test/sql/extract_host.test

@@ -4,6 +4,9 @@
 
 require netquack
 
+statement ok
+CREATE TABLE uri_list AS SELECT * FROM read_csv('test/data/examples.csv', header=false, columns={'uri': 'VARCHAR'});
+
 query I
 SELECT extract_host('http://example.com.ac/path');
 ----
@@ -63,3 +66,16 @@ query I
 SELECT extract_host('rsync://rpki.example.com/path');
 ----
 rpki.example.com
+
+query I
+SELECT extract_host(uri) from uri_list;
+----
+example.com
+example.com.ac
+example.com.co
+a.example.com
+example.com
+example.com.ac
+example.com
+a.example.com
+example.com.ac