neuron-technologies/el
3
0
Fork 0
Code Issues 4 Pull Requests Actions Packages Projects Releases 5 Wiki Activity

fix(runtime): handle multi-byte UTF-8 in JSON string escaping

Browse Source 
Validate UTF-8 continuation bytes in jb_emit_escaped; pass valid
sequences through and escape orphaned/invalid start bytes as \u00xx.
Pre-existing change found uncommitted in the working tree; committed
here so it is reviewable rather than lost.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Tim Lingo
2026-06-09 08:02:46 -05:00
parent 2ed6b26dde
commit 2b8062c55f
1 changed files with 36 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lang/el-compiler/runtime/el_runtime.c
+36 -10
View File
@@ -3135,23 +3135,49 @@ static void jb_puts(JsonBuf* b, const char* s) {
static void jb_emit_escaped(JsonBuf* b, const char* s) { static void jb_emit_escaped(JsonBuf* b, const char* s) {
jb_putc(b, '"'); jb_putc(b, '"');
for (; *s; s++) { const unsigned char* p = (const unsigned char*)s;
unsigned char c = (unsigned char)*s; while (*p) {
unsigned char c = *p;
switch (c) { switch (c) {
case '"': jb_puts(b, "\\\""); break; case '"': jb_puts(b, "\\\""); p++; break;
case '\\': jb_puts(b, "\\\\"); break; case '\\': jb_puts(b, "\\\\"); p++; break;
case '\b': jb_puts(b, "\\b"); break; case '\b': jb_puts(b, "\\b"); p++; break;
case '\f': jb_puts(b, "\\f"); break; case '\f': jb_puts(b, "\\f"); p++; break;
case '\n': jb_puts(b, "\\n"); break; case '\n': jb_puts(b, "\\n"); p++; break;
case '\r': jb_puts(b, "\\r"); break; case '\r': jb_puts(b, "\\r"); p++; break;
case '\t': jb_puts(b, "\\t"); break; case '\t': jb_puts(b, "\\t"); p++; break;
default: default:
if (c < 0x20) { if (c < 0x20) {
char tmp[8]; char tmp[8];
snprintf(tmp, sizeof(tmp), "\\u%04x", c); snprintf(tmp, sizeof(tmp), "\\u%04x", c);
jb_puts(b, tmp); jb_puts(b, tmp);
} else { p++;
} else if (c < 0x80) {
jb_putc(b, (char)c); jb_putc(b, (char)c);
p++;
} else {
/* Multi-byte UTF-8: validate sequence, pass through if valid,
* escape as \u00xx if the start byte is invalid/orphaned. */
int seq_len = 0;
if ((c & 0xE0) == 0xC0) seq_len = 2;
else if ((c & 0xF0) == 0xE0) seq_len = 3;
else if ((c & 0xF8) == 0xF0) seq_len = 4;
if (seq_len >= 2) {
int valid = 1;
for (int i = 1; i < seq_len; i++) {
if ((p[i] & 0xC0) != 0x80) { valid = 0; break; }
}
if (valid) {
for (int i = 0; i < seq_len; i++) jb_putc(b, (char)p[i]);
p += seq_len;
break;
}
}
/* Invalid start byte or truncated sequence — escape it */
char tmp[8];
snprintf(tmp, sizeof(tmp), "\\u%04x", c);
jb_puts(b, tmp);
p++;
} }
break; break;
} }