From 83e8ec587f56a88980c55204ee8433e2f50419cc Mon Sep 17 00:00:00 2001
From: Joel Nothman <joel.nothman@gmail.com>
Date: Tue, 8 Sep 2015 12:51:42 +1000
Subject: [PATCH] utf8bytelength: count UTF8 string bytelength

[Builtin name changed, and it only works on string inputs. -Nico]
---
 docs/content/3.manual/manual.yml | 12 ++++++++++++
 src/builtin.c                    |  7 +++++++
 tests/jq.test                    |  9 +++++++++
 3 files changed, 28 insertions(+)

diff --git a/docs/content/3.manual/manual.yml b/docs/content/3.manual/manual.yml
index ced5f8d0..0fe4b64b 100644
--- a/docs/content/3.manual/manual.yml
+++ b/docs/content/3.manual/manual.yml
@@ -662,6 +662,18 @@ sections:
             input: '[[1,2], "string", {"a":2}, null]'
             output: [2, 6, 1, 0]
 
+
+      - title: "`utf8bytelength`"
+        body: |
+
+          The builtin function `utf8bytelength` outputs the number of
+          bytes used to encode a string in UTF-8.
+
+        examples:
+          - program: 'utf8bytelength'
+            input: '"\u03bc"'
+            output: [2]
+
       - title: "`keys`, `keys_unsorted`"
         body: |
 
diff --git a/src/builtin.c b/src/builtin.c
index 990e24a9..3b920973 100644
--- a/src/builtin.c
+++ b/src/builtin.c
@@ -367,6 +367,12 @@ static jv f_tostring(jq_state *jq, jv input) {
   }
 }
 
+static jv f_utf8bytelength(jq_state *jq, jv input) {
+  if (jv_get_kind(input) != JV_KIND_STRING)
+    return type_error(input, "only strings have UTF-8 byte length");
+  return jv_number(jv_string_length_bytes(input));
+}
+
 #define CHARS_ALPHANUM "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789"
 
 static jv escape_string(jv input, const char* escapings) {
@@ -1273,6 +1279,7 @@ static const struct cfunction function_list[] = {
   {(cfunction_ptr)f_greatereq, "_greatereq", 3},
   {(cfunction_ptr)f_contains, "contains", 2},
   {(cfunction_ptr)f_length, "length", 1},
+  {(cfunction_ptr)f_utf8bytelength, "utf8bytelength", 1},
   {(cfunction_ptr)f_type, "type", 1},
   {(cfunction_ptr)f_isinfinite, "isinfinite", 1},
   {(cfunction_ptr)f_isnan, "isnan", 1},
diff --git a/tests/jq.test b/tests/jq.test
index 021253d8..1f4e4b11 100644
--- a/tests/jq.test
+++ b/tests/jq.test
@@ -525,6 +525,15 @@ null
 [[], {}, [1,2], {"a":42}, "asdf", "\u03bc"]
 [0, 0, 2, 1, 4, 1]
 
+utf8bytelength
+"asdf\u03bc"
+6
+
+[.[] | try utf8bytelength catch .]
+[[], {}, [1,2], 55, true, false]
+["array ([]) only strings have UTF-8 byte length","object ({}) only strings have UTF-8 byte length","array ([1,2]) only strings have UTF-8 byte length","number (55) only strings have UTF-8 byte length","boolean (true) only strings have UTF-8 byte length","boolean (false) only strings have UTF-8 byte length"]
+
+
 map(keys)
 [{}, {"abcd":1,"abc":2,"abcde":3}, {"x":1, "z": 3, "y":2}]
 [[], ["abc","abcd","abcde"], ["x","y","z"]]