Skip to content

Fix string termination in BadPattern exception message #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fix string termination in BadPattern exception message #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c082ede
Fix unterminated string in BadPattern exception
Andrew-William-Smith Sep 23, 2024
6ec979e
Add test for string termination fix
Andrew-William-Smith Sep 23, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 7 additions & 2 deletions src/pcre2_stubs.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -248,8 +248,13 @@ static inline void raise_bad_pattern(int code, size_t pos)
CAMLparam0();
CAMLlocal1(v_msg);
value v_arg;
v_msg = caml_alloc_string(128);
pcre2_get_error_message(code, (PCRE2_UCHAR *)String_val(v_msg), 128);
PCRE2_UCHAR8 err[256];

/* We can safely assume that PCRE2's UTF-8-compatible human-intelligible error
messages do not contain NUL. */
pcre2_get_error_message_8(code, err, sizeof(err) / sizeof(err[0]));
v_msg = caml_copy_string((char *)err);

v_arg = caml_alloc_small(2, 0);
Field(v_arg, 0) = v_msg;
Field(v_arg, 1) = Val_int(pos);
Expand Down
20 changes: 18 additions & 2 deletions test/pcre2_tests.ml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,12 +9,28 @@ let simple_test ctxt =
NoGroup; Group (2, "u"); Text "ef"]
(full_split ~pat:"(x)|(u)" "abxcduef")

let marshalled_string_termination ctxt =
try
(* At the time of writing, the longest error message that can be returned by
PCRE2 is "\g is not followed by a braced, angle-bracketed, or quoted
name/number or by a plain number". *)
ignore @@ regexp "\\gg";
assert_failure "Invalid pattern must fail to compile."
with Error (BadPattern (msg, offset)) ->
let is_non_printing c =
let codepoint = Char.code c in
codepoint < (Char.code ' ') || codepoint > (Char.code '~')
in
assert_equal offset 2;
assert_bool "PCRE2 string contains non-printing character."
(not @@ String.exists is_non_printing msg)

let suite = "Test pcre" >::: [
"simple_test" >:: simple_test
"simple_test" >:: simple_test;
"marshalled_string_termination" >:: marshalled_string_termination;
]

let _ =
if not !Sys.interactive then
run_test_tt_main suite
else ()