From 03377a41a907cec5c95b37f9f8ba85168db959b2 Mon Sep 17 00:00:00 2001
From: Pierluigi Lenoci <pierluigi.lenoci@gmail.com>
Date: Tue, 17 Mar 2026 00:36:47 +0100
Subject: [PATCH 1/3] fix(scripts): encode residual control chars as \uXXXX
 instead of stripping

json_escape() was silently deleting control characters (U+0000-U+001F)
that were not individually handled (\n, \t, \r, \b, \f). Per RFC 8259,
these must be encoded as \uXXXX sequences to preserve data integrity.

Replace the tr -d strip with a char-by-char loop that emits proper
\uXXXX escapes for any remaining control characters.
---
 scripts/bash/common.sh | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/scripts/bash/common.sh b/scripts/bash/common.sh
index 826e740f00..2917bcc9e1 100644
--- a/scripts/bash/common.sh
+++ b/scripts/bash/common.sh
@@ -171,9 +171,21 @@ json_escape() {
     s="${s//$'\r'/\\r}"
     s="${s//$'\b'/\\b}"
     s="${s//$'\f'/\\f}"
-    # Strip remaining control characters (U+0000–U+001F) not individually escaped above
-    s=$(printf '%s' "$s" | tr -d '\000-\007\013\016-\037')
-    printf '%s' "$s"
+    # Escape any remaining U+0000-U+001F control characters as \uXXXX.
+    # Only single-byte characters can be JSON control chars; multi-byte UTF-8
+    # sequences have first-byte values >= 0xC0 and are never control characters.
+    local i char code
+    local out=""
+    for (( i=0; i<${#s}; i++ )); do
+        char="${s:$i:1}"
+        code=$(LC_ALL=C printf '%d' "'$char" 2>/dev/null || echo 256)
+        if (( code >= 0 && code <= 31 )); then
+            out+=$(printf '\\u%04x' "$code")
+        else
+            out+="$char"
+        fi
+    done
+    printf '%s' "$out"
 }
 
 check_file() { [[ -f "$1" ]] && echo "  ✓ $2" || echo "  ✗ $2"; }

From 1b7ce3bec2d6ff4c7f39020dd2b83d68c74c88d9 Mon Sep 17 00:00:00 2001
From: Pierluigi Lenoci <pierluigi.lenoci@gmail.com>
Date: Tue, 17 Mar 2026 20:18:37 +0100
Subject: [PATCH 2/3] fix(scripts): address Copilot review on json_escape
 control char loop

- Set LC_ALL=C for the entire loop (not just printf) so that ${#s} and
  ${s:$i:1} operate on bytes deterministically across locales
- Fix comment: U+0000 (NUL) cannot exist in bash strings, range is
  U+0001-U+001F; adjust code guard accordingly (code >= 1)
- Emit directly to stdout instead of accumulating in a variable,
  avoiding quadratic string concatenation on longer inputs
---
 scripts/bash/common.sh | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/scripts/bash/common.sh b/scripts/bash/common.sh
index 2917bcc9e1..644474aaeb 100644
--- a/scripts/bash/common.sh
+++ b/scripts/bash/common.sh
@@ -171,21 +171,21 @@ json_escape() {
     s="${s//$'\r'/\\r}"
     s="${s//$'\b'/\\b}"
     s="${s//$'\f'/\\f}"
-    # Escape any remaining U+0000-U+001F control characters as \uXXXX.
-    # Only single-byte characters can be JSON control chars; multi-byte UTF-8
-    # sequences have first-byte values >= 0xC0 and are never control characters.
+    # Escape any remaining U+0001-U+001F control characters as \uXXXX.
+    # (U+0000/NUL cannot appear in bash strings and is excluded.)
+    # LC_ALL=C ensures ${#s} counts bytes and ${s:$i:1} yields single bytes,
+    # so multi-byte UTF-8 sequences (first byte >= 0xC0) pass through intact.
+    local LC_ALL=C
     local i char code
-    local out=""
     for (( i=0; i<${#s}; i++ )); do
         char="${s:$i:1}"
-        code=$(LC_ALL=C printf '%d' "'$char" 2>/dev/null || echo 256)
-        if (( code >= 0 && code <= 31 )); then
-            out+=$(printf '\\u%04x' "$code")
+        code=$(printf '%d' "'$char" 2>/dev/null || echo 256)
+        if (( code >= 1 && code <= 31 )); then
+            printf '\\u%04x' "$code"
         else
-            out+="$char"
+            printf '%s' "$char"
         fi
     done
-    printf '%s' "$out"
 }
 
 check_file() { [[ -f "$1" ]] && echo "  ✓ $2" || echo "  ✗ $2"; }

From 0b1f005bb3305780e30eff9079cd029c3b2c0205 Mon Sep 17 00:00:00 2001
From: Pierluigi Lenoci <pierluigi.lenoci@gmail.com>
Date: Tue, 17 Mar 2026 22:23:27 +0100
Subject: [PATCH 3/3] perf(scripts): use printf -v to avoid subshell in
 json_escape loop

Replace code=$(printf ...) with printf -v code to assign the character
code without spawning a subshell on every byte, reducing overhead for
longer inputs.
---
 scripts/bash/common.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/bash/common.sh b/scripts/bash/common.sh
index 644474aaeb..40f1c96e7d 100644
--- a/scripts/bash/common.sh
+++ b/scripts/bash/common.sh
@@ -179,7 +179,7 @@ json_escape() {
     local i char code
     for (( i=0; i<${#s}; i++ )); do
         char="${s:$i:1}"
-        code=$(printf '%d' "'$char" 2>/dev/null || echo 256)
+        printf -v code '%d' "'$char" 2>/dev/null || code=256
         if (( code >= 1 && code <= 31 )); then
             printf '\\u%04x' "$code"
         else