From 64bd8ba3749fe473b0708f999e088dfa94d37a2c Mon Sep 17 00:00:00 2001
From: itchyny <itchyny@cybozu.co.jp>
Date: Sun, 16 Feb 2025 21:40:18 +0900
Subject: [PATCH] fix: `jv_dump_string_trunc` should not break unicode
 characters (#3249)

---
 src/jv_print.c | 19 ++++++++++---------
 tests/jq.test  | 13 +++++++++++++
 2 files changed, 23 insertions(+), 9 deletions(-)

diff --git a/src/jv_print.c b/src/jv_print.c
index ffe15234..ae17ec0a 100644
--- a/src/jv_print.c
+++ b/src/jv_print.c
@@ -381,16 +381,17 @@ jv jv_dump_string(jv x, int flags) {
 }
 
 char *jv_dump_string_trunc(jv x, char *outbuf, size_t bufsize) {
-  x = jv_dump_string(x,0);
-  const char* p = jv_string_value(x);
-  const size_t len = strlen(p);
-  strncpy(outbuf, p, bufsize);
-  outbuf[bufsize - 1] = 0;
+  x = jv_dump_string(x, 0);
+  const char *str = jv_string_value(x);
+  const size_t len = strlen(str);
+  strncpy(outbuf, str, bufsize);
   if (len > bufsize - 1 && bufsize >= 4) {
-    // Indicate truncation with '...'
-    outbuf[bufsize - 2]='.';
-    outbuf[bufsize - 3]='.';
-    outbuf[bufsize - 4]='.';
+    // Indicate truncation with '...' without breaking UTF-8.
+    const char *s = jvp_utf8_backtrack(outbuf + bufsize - 4, outbuf, NULL);
+    if (s) bufsize = s + 4 - outbuf;
+    strcpy(outbuf + bufsize - 4, "...");
+  } else {
+    outbuf[bufsize - 1] = '\0';
   }
   jv_free(x);
   return outbuf;
diff --git a/tests/jq.test b/tests/jq.test
index d8758b43..d5eb8dde 100644
--- a/tests/jq.test
+++ b/tests/jq.test
@@ -1788,6 +1788,19 @@ try -. catch .
 "very-long-string"
 "string (\"very-long-...) cannot be negated"
 
+try (.-.) catch .
+"very-long-string"
+"string (\"very-long-...) and string (\"very-long-...) cannot be subtracted"
+
+"x" * range(0; 12; 2) + "☆" * 5 | try -. catch .
+null
+"string (\"☆☆☆...) cannot be negated"
+"string (\"xx☆☆...) cannot be negated"
+"string (\"xxxx☆☆...) cannot be negated"
+"string (\"xxxxxx☆...) cannot be negated"
+"string (\"xxxxxxxx...) cannot be negated"
+"string (\"xxxxxxxxxx...) cannot be negated"
+
 join(",")
 ["1",2,true,false,3.4]
 "1,2,true,false,3.4"