From bc2e2e040430410e7d7fb78d5b6316de2c2f25f2 Mon Sep 17 00:00:00 2001
From: He-Pin <hepin1989@gmail.com>
Date: Tue, 28 Jul 2026 02:24:13 +0800
Subject: [PATCH] fix: use codepoint count for std.format width padding
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Motivation:
`std.format("%5s", "😀")` produced 3 spaces instead of 4 because width
was computed using String.length (UTF-16 code units), counting the
surrogate pair as 2. Python's % formatting defines width as codepoint
count; go-jsonnet uses `len([]rune(str))`. Both yield 4 spaces.

Modification:
In `widen`, use `codePointCount` for non-numeric (string) paths where
supplementary characters can appear. Numeric paths (%d/%f/%g/%x/%o)
retain O(1) `.length` since their output is provably ASCII. This avoids
O(n) scans on every numeric format call while fixing the string case.

Result:
Width padding counts supplementary characters as 1 codepoint, matching
go-jsonnet and Python. Numeric formatting performance is unchanged.

References:
- Python docs: width is "minimum field width" in characters (codepoints)
- go-jsonnet: uses len([]rune(str)) for width calculation
---
 sjsonnet/src/sjsonnet/Format.scala                    |  8 +++++++-
 .../new_test_suite/format_width_codepoint.jsonnet     | 11 +++++++++++
 .../format_width_codepoint.jsonnet.golden             |  9 +++++++++
 3 files changed, 27 insertions(+), 1 deletion(-)
 create mode 100644 sjsonnet/test/resources/new_test_suite/format_width_codepoint.jsonnet
 create mode 100644 sjsonnet/test/resources/new_test_suite/format_width_codepoint.jsonnet.golden

diff --git a/sjsonnet/src/sjsonnet/Format.scala b/sjsonnet/src/sjsonnet/Format.scala
index 77377dac..c8a30990 100644
--- a/sjsonnet/src/sjsonnet/Format.scala
+++ b/sjsonnet/src/sjsonnet/Format.scala
@@ -286,7 +286,13 @@ object Format {
       else if (signedConversion && formatted.signCharacter) "+" + lhs
       else lhs
 
-    val missingWidth = formatted.widthOr(-1) - lhs2.length - mhs.length - rhs.length
+    val missingWidth =
+      if (numeric) formatted.widthOr(-1) - lhs2.length - mhs.length - rhs.length
+      else
+        formatted.widthOr(-1) -
+        lhs2.codePointCount(0, lhs2.length) -
+        mhs.codePointCount(0, mhs.length) -
+        rhs.codePointCount(0, rhs.length)
 
     if (missingWidth <= 0) {
       // Avoid unnecessary string concatenation when parts are empty
diff --git a/sjsonnet/test/resources/new_test_suite/format_width_codepoint.jsonnet b/sjsonnet/test/resources/new_test_suite/format_width_codepoint.jsonnet
new file mode 100644
index 00000000..bb469103
--- /dev/null
+++ b/sjsonnet/test/resources/new_test_suite/format_width_codepoint.jsonnet
@@ -0,0 +1,11 @@
+// Width padding must count codepoints, not UTF-16 code units.
+// Supplementary characters (surrogate pairs) count as 1 codepoint.
+[
+  std.assertEqual("%5s" % "😀", "    😀"),
+  std.assertEqual("%-5s" % "😀", "😀    "),
+  std.assertEqual("%5s" % "a😀b", "  a😀b"),
+  std.assertEqual("%3s" % "😀😀", " 😀😀"),
+  std.assertEqual("%5.1s" % "😀x", "    😀"),
+  std.assertEqual("%5s" % "hello", "hello"),
+  std.assertEqual("%10s" % "hello", "     hello"),
+]
diff --git a/sjsonnet/test/resources/new_test_suite/format_width_codepoint.jsonnet.golden b/sjsonnet/test/resources/new_test_suite/format_width_codepoint.jsonnet.golden
new file mode 100644
index 00000000..15f719b5
--- /dev/null
+++ b/sjsonnet/test/resources/new_test_suite/format_width_codepoint.jsonnet.golden
@@ -0,0 +1,9 @@
+[
+   true,
+   true,
+   true,
+   true,
+   true,
+   true,
+   true
+]