From e0e0e315cd557d1649077d6cae9d4d10d503c50f Mon Sep 17 00:00:00 2001
From: Anand Krishnamoorthi <anakrish@microsoft.com>
Date: Thu, 27 Aug 2026 14:55:57 -0500
Subject: [PATCH] fix(builtins): prevent panic in strings.count on empty needle

strings.count panicked when called with an empty needle because
.windows(0) is invalid. Fix three issues in strings_count:

1. Wrong param index: params[0] was used for the substring error span
   instead of params[1].
2. Panic: .windows(needle.len()) panics when needle is empty (len == 0).
3. Semantics: the byte-level .windows() approach counted overlapping
   matches; OPA uses non-overlapping match semantics (Go strings.Count).

The fix:
- Correct the param index to params[1] for the substring argument.
- Handle empty needle explicitly: return chars().count() + 1, matching
  Go's strings.Count behaviour (empty needle matches between every
  character and at both ends).
- Use str::matches() for non-overlapping count on non-empty needles.

A YAML regression test is added covering basic match, no-match,
multi-match, empty-needle (must not panic), empty-needle on empty
string, non-overlapping semantics, and multi-byte UTF-8 strings.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---
 src/builtins/strings.rs                       | 18 +++---
 .../cases/builtins/strings/strings_count.yaml | 59 +++++++++++++++++++
 2 files changed, 68 insertions(+), 9 deletions(-)
 create mode 100644 tests/interpreter/cases/builtins/strings/strings_count.yaml

diff --git a/src/builtins/strings.rs b/src/builtins/strings.rs
index fd3a2ee8b..7ca949df3 100644
--- a/src/builtins/strings.rs
+++ b/src/builtins/strings.rs
@@ -542,15 +542,15 @@ fn strings_count(
     ensure_args_count(span, name, params, args, 2)?;
 
     let search = ensure_string(name, &params[0], &args[0])?;
-    let substring = ensure_string(name, &params[0], &args[1])?;
-
-    Ok(Value::from(
-        search
-            .as_bytes()
-            .windows(substring.len())
-            .filter(|&w| w == substring.as_bytes())
-            .count(),
-    ))
+    let substring = ensure_string(name, &params[1], &args[1])?;
+
+    if substring.is_empty() {
+        // An empty needle matches between every character (and at both ends),
+        // consistent with Go's strings.Count and OPA semantics.
+        return Ok(Value::from(search.chars().count().saturating_add(1)));
+    }
+
+    Ok(Value::from(search.matches(substring.as_ref()).count()))
 }
 
 fn startswith(span: &Span, params: &[Ref<Expr>], args: &[Value], _strict: bool) -> Result<Value> {
diff --git a/tests/interpreter/cases/builtins/strings/strings_count.yaml b/tests/interpreter/cases/builtins/strings/strings_count.yaml
new file mode 100644
index 000000000..5de134629
--- /dev/null
+++ b/tests/interpreter/cases/builtins/strings/strings_count.yaml
@@ -0,0 +1,59 @@
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT License.
+
+cases:
+  - note: basic match
+    data: {}
+    modules: []
+    query: 'x := strings.count("cheese", "e")'
+    want_result:
+      x: 3
+
+  - note: no match
+    data: {}
+    modules: []
+    query: 'x := strings.count("dummy", "x")'
+    want_result:
+      x: 0
+
+  - note: multiple separate matches
+    data: {}
+    modules: []
+    query: 'x := strings.count("hello hello hello world", "hello")'
+    want_result:
+      x: 3
+
+  - note: empty needle returns char_count+1
+    data: {}
+    modules: []
+    query: 'x := strings.count("abc", "")'
+    want_result:
+      x: 4
+
+  - note: empty needle on empty string
+    data: {}
+    modules: []
+    query: 'x := strings.count("", "")'
+    want_result:
+      x: 1
+
+  - note: empty needle on single char
+    data: {}
+    modules: []
+    query: 'x := strings.count("a", "")'
+    want_result:
+      x: 2
+
+  - note: non-overlapping matches only
+    data: {}
+    modules: []
+    query: 'x := strings.count("aaaa", "aa")'
+    want_result:
+      x: 2
+
+  - note: multibyte utf8 string with empty needle
+    data: {}
+    modules: []
+    query: 'x := strings.count("\u4e16\u754c", "")'
+    want_result:
+      x: 3