feat: Add String type with Utf8Raw encoding to Bigtable API

Google APIs · copybara-github · commit 89a836483eaf · 2024-05-23T12:06:52.000-07:00
Bigtable will allow users to configure the type of a column family with string type

PiperOrigin-RevId: 636631633
diff --git a/google/bigtable/admin/v2/types.proto b/google/bigtable/admin/v2/types.proto
@@ -41,18 +41,18 @@ option ruby_package = "Google::Cloud::Bigtable::Admin::V2";
 //  * Natural sort: Does the encoded value sort consistently with the original
 //    typed value? Note that Bigtable will always sort data based on the raw
 //    encoded value, *not* the decoded type.
-//     - Example: STRING values sort in the same order as their UTF-8 encodings.
+//     - Example: BYTES values sort in the same order as their raw encodings.
 //     - Counterexample: Encoding INT64 to a fixed-width STRING does *not*
 //       preserve sort order when dealing with negative numbers.
 //       INT64(1) > INT64(-1), but STRING("-00001") > STRING("00001).
-//     - The overall encoding chain sorts naturally if *every* link does.
+//     - The overall encoding chain has this property if *every* link does.
 //  * Self-delimiting: If we concatenate two encoded values, can we always tell
 //    where the first one ends and the second one begins?
 //     - Example: If we encode INT64s to fixed-width STRINGs, the first value
 //       will always contain exactly N digits, possibly preceded by a sign.
 //     - Counterexample: If we concatenate two UTF-8 encoded STRINGs, we have
 //       no way to tell where the first one ends.
-//     - The overall encoding chain is self-delimiting if *any* link is.
+//     - The overall encoding chain has this property if *any* link does.
 //  * Compatibility: Which other systems have matching encoding schemes? For
 //    example, does this encoding have a GoogleSQL equivalent? HBase? Java?
 message Type {
@@ -78,6 +78,31 @@ message Type {
     Encoding encoding = 1;
   }
 
+  // String
+  // Values of type `String` are stored in `Value.string_value`.
+  message String {
+    // Rules used to convert to/from lower level types.
+    message Encoding {
+      // UTF-8 encoding
+      // * Natural sort? No (ASCII characters only)
+      // * Self-delimiting? No
+      // * Compatibility?
+      //    - BigQuery Federation `TEXT` encoding
+      //    - HBase `Bytes.toBytes`
+      //    - Java `String#getBytes(StandardCharsets.UTF_8)`
+      message Utf8Raw {}
+
+      // Which encoding to use.
+      oneof encoding {
+        // Use `Utf8Raw` encoding.
+        Utf8Raw utf8_raw = 1;
+      }
+    }
+
+    // The encoding to use when converting to/from lower level types.
+    Encoding encoding = 1;
+  }
+
   // Int64
   // Values of type `Int64` are stored in `Value.int_value`.
   message Int64 {
@@ -140,6 +165,9 @@ message Type {
     // Bytes
     Bytes bytes_type = 1;
 
+    // String
+    String string_type = 2;
+
     // Int64
     Int64 int64_type = 5;
 
