Add "encoding" attribute to string length op, which controls how "string length" is defined:

  * BYTE: The number of bytes in each string.  (Default)
  * UTF8: The number of UTF-8 encoded Unicode code points in each string.

RELNOTES: Add option to calculate string length in Unicode characters
PiperOrigin-RevId: 214478470

2 files changed, 11 insertions, 3 deletions

diff --git a/tensorflow/core/api_def/base_api/api_def_StringLength.pbtxt b/tensorflow/core/api_def/base_api/api_def_StringLength.pbtxt
index cc21ddc815..7d2fbcd00b 100644
--- a/tensorflow/core/api_def/base_api/api_def_StringLength.pbtxt
+++ b/tensorflow/core/api_def/base_api/api_def_StringLength.pbtxt
@@ -1,5 +1,15 @@
 op {
   graph_op_name: "StringLength"
+  attr {
+    name: "unit"
+    description: <<END
+The unit that is counted to compute string length.  One of: `"BYTE"` (for
+the number of bytes in each string) or `"UTF8_CHAR"` (for the number of UTF-8
+encoded Unicode code points in each string).  Results are undefined
+if `unit=UTF8_CHAR` and the `input` strings do not contain structurally
+valid UTF-8.
+END
+  }
   in_arg {
     name: "input"
     description: <<END
diff --git a/tensorflow/core/api_def/python_api/api_def_StringLength.pbtxt b/tensorflow/core/api_def/python_api/api_def_StringLength.pbtxt
index 01c02e1f70..df012414e3 100644
--- a/tensorflow/core/api_def/python_api/api_def_StringLength.pbtxt
+++ b/tensorflow/core/api_def/python_api/api_def_StringLength.pbtxt
@@ -1,6 +1,4 @@
 op {
   graph_op_name: "StringLength"
-  endpoint {
-    name: "strings.length"
-  }
+  visibility: HIDDEN
 }