Merge remote-tracking branch 'origin/topic/bbannier/integer-conversion-error-handling'

* origin/topic/bbannier/integer-conversion-error-handling:
  Also trim trailing spaces in `to_count`/`to_int` inputs
  Align error handling in `to_int` with existing behavior of `to_count`
  Baseline handling of leading/trailing spaces in `to_count`/`to_int`.
  Add error messages to `to_count`/`to_int` baselines

CHANGES

@@ -1,3 +1,38 @@
+7.2.0-dev.210 | 2025-02-20 15:35:21 -0700
+
+  * Also trim trailing spaces in `to_count`/`to_int` inputs (Benjamin Bannier, Corelight)
+
+    Previously we would already trim leading spaces in inputs to `to_count`
+    and `to_int`, effectively by just passing the behavior of the low-level
+    functions used in their implementations to the user. While this was
+    useful it was also inconsistent in that we did not allow trailing
+    spaces which we enable with this patch.
+
+  * Align error handling in `to_int` with existing behavior of `to_count` (Benjamin Bannier, Corelight)
+
+    Previously `to_int` would silently ignore invalid inputs and simply
+    return `0` while `to_count` would return an error; this patch changes
+    `to_int` to behave like `to_count`.
+
+    This introduces a breaking change in that `to_int` now raises an error
+    for trailing spaces (but still accepts leading spaces) where it
+    previously would have silently accepted it. This is consistent with
+    the behavior of `to_count`, but one could also argue that both of
+    these should only accept properly trimmed input; I did not go that route
+    since that would introduce breaking changes for both these functions
+    instead of for just one of them.
+
+  * Baseline handling of leading/trailing spaces in `to_count`/`to_int`. (Benjamin Bannier, Corelight)
+
+    Currently `to_count` reports an error for trailing spaces (but not for
+    leading ones) while `to_int` silently accepts them. This patch adds
+    baselines capture the current behavior.
+
+  * Add error messages to `to_count`/`to_int` baselines (Benjamin Bannier, Corelight)
+
+    This captures error messages produced by `to_count`, but will also
+    baseline future error messages from `to_int` once we introduce them.
+
 7.2.0-dev.203 | 2025-02-18 08:51:23 -0700
 
   * cirrus: Bump FreeBSD 14 task to 14.2 (Arne Welzel, Corelight)

VERSION

@@ -1 +1 @@
-7.2.0-dev.205
+7.2.0-dev.210

src/zeek.bif

@@ -7,14 +7,16 @@
 ##! You'll find most of Zeek's built-in functions that aren't protocol-specific
 ##! in this file.
 
-%%{ // C segment
-#include <cmath>
-#include <vector>
+%%{ // C++ segment
+#include <sys/stat.h>
+
 #include <algorithm>
 #include <cmath>
-#include <sys/stat.h>
+#include <cmath>
 #include <cstdio>
+#include <cstring>
 #include <ctime>
+#include <vector>
 
 #include "zeek/digest.h"
 #include "zeek/Reporter.h"
@@ -2613,12 +2615,11 @@ function to_int%(str: string%): int
 
 	zeek_int_t i = strtoll(s, &end_s, 10);
 
-#if 0
-	// Not clear we should complain.  For example, is " 205 "
-	// a legal conversion?
-	if ( s[0] == '\0' || end_s[0] != '\0' )
+	if ( s[0] == '\0' || std::any_of(static_cast<const char*>(end_s), s + ::strlen(s),
+	                                 [](char c) { return ! (c == '\0' || ::isspace(c)); }) )
+		{
 		zeek::emit_builtin_error("bad conversion to integer", @ARG@[0]);
-#endif
+		}
 
 	return zeek::val_mgr->Int(i);
 	%}
@@ -2680,9 +2681,10 @@ function to_count%(str: string%): count
 	const char* s = str->CheckString();
 	char* end_s;
 
-	uint64_t u = (uint64_t) strtoull(s, &end_s, 10);
+	uint64_t u = static_cast<uint64_t>(strtoull(s, &end_s, 10));
 
-	if ( s[0] == '\0' || end_s[0] != '\0' )
+	if ( s[0] == '\0' || std::any_of(static_cast<const char*>(end_s), s + ::strlen(s),
+	                                 [](char c) { return ! (c == '\0' || ::isspace(c)); }) )
 		{
 		zeek::emit_builtin_error("bad conversion to count", @ARG@[0]);
 		u = 0;

testing/btest/Baseline/bifs.to_count/err

@@ -0,0 +1,4 @@
+### BTest baseline data generated by btest-diff. Do not edit. Use "btest -U/-u" to update. Requires BTest >= 0.63.
+error in <...>/to_count.zeek, line 8: bad conversion to count (int_to_count(a) and -2)
+error in <...>/to_count.zeek, line 20: bad conversion to count (to_count() and )
+error in <...>/to_count.zeek, line 25: bad conversion to count (to_count(not a count) and not a count)

testing/btest/Baseline/bifs.to_count/out

@@ -6,6 +6,8 @@
 7
 0
 18446744073709551611
+205
+206
 0
 123
 9223372036854775808 and 9223372036854775808 are the same

testing/btest/Baseline/bifs.to_int/err

@@ -0,0 +1,2 @@
+### BTest baseline data generated by btest-diff. Do not edit. Use "btest -U/-u" to update. Requires BTest >= 0.63.
+error in <...>/to_int.zeek, line 10: bad conversion to integer (to_int(not an int) and not an int)

testing/btest/Baseline/bifs.to_int/out

@@ -3,6 +3,8 @@
 -1
 4294967296
 0
+205
+206
 3
 4
 -3

testing/btest/bifs/to_count.zeek

@@ -1,6 +1,6 @@
-#
-# @TEST-EXEC: zeek -b %INPUT >out
+# @TEST-EXEC: zeek -b %INPUT 1>out 2>err
 # @TEST-EXEC: btest-diff out
+# @TEST-EXEC: TEST_DIFF_CANONIFIER=${SCRIPTS}/diff-remove-abspath btest-diff err
 
 event zeek_init()
 	{
@@ -19,6 +19,9 @@ event zeek_init()
 	print to_count("7");
 	print to_count("");
 	print to_count("-5");
+	# We automatically trim leading, but not trailing whitespace.
+	print to_count(" 205"); # Okay.
+	print to_count("206 "); # Error.
 	print to_count("not a count");
 
 	local e: port = 123/tcp;

testing/btest/bifs/to_int.zeek

@@ -1,6 +1,6 @@
-#
-# @TEST-EXEC: zeek -b %INPUT >out
+# @TEST-EXEC: zeek -b %INPUT 1>out 2>err
 # @TEST-EXEC: btest-diff out
+# @TEST-EXEC: TEST_DIFF_CANONIFIER=${SCRIPTS}/diff-remove-abspath btest-diff err
 
 event zeek_init()
 	{
@@ -8,6 +8,9 @@ event zeek_init()
 	print to_int("-1");
 	print to_int("4294967296");
 	print to_int("not an int");
+	# We automatically trim leading, but not trailing whitespace.
+	print to_int(" 205"); # Okay.
+	print to_int("206 "); # Error.
 
 	local a: double = 3.14;
 	print double_to_int(a);