Skip to content

Add allow_control_characters parsing option #917

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

Merged
byroot merged 1 commit into from
Dec 11, 2025
+143 −100
Merged

Add allow_control_characters parsing option #917

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 2 additions & 0 deletions CHANGES.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,8 @@

### Unreleased

* Add `:allow_control_characters` parser options, to allow JSON strings containing unescaped ASCII control characters (e.g. newlines).

### 2025-12-04 (2.17.1)

* Fix a regression in parsing of unicode surogate pairs (`\uXX\uXX`) that could cause an invalid string to be returned.
Expand Down
36 changes: 22 additions & 14 deletions ext/json/ext/parser/parser.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ static VALUE CNaN, CInfinity, CMinusInfinity;

static ID i_new, i_try_convert, i_uminus, i_encode;

static VALUE sym_max_nesting, sym_allow_nan, sym_allow_trailing_comma, sym_symbolize_names, sym_freeze,
static VALUE sym_max_nesting, sym_allow_nan, sym_allow_trailing_comma, sym_allow_control_characters, sym_symbolize_names, sym_freeze,
sym_decimal_class, sym_on_load, sym_allow_duplicate_key;

static int binary_encindex;
Expand Down Expand Up @@ -335,6 +335,7 @@ typedef struct JSON_ParserStruct {
int max_nesting;
bool allow_nan;
bool allow_trailing_comma;
bool allow_control_characters;
bool symbolize_names;
bool freeze;
} JSON_ParserConfig;
Expand Down Expand Up @@ -752,12 +753,15 @@ NOINLINE(static) VALUE json_string_unescape(JSON_ParserState *state, JSON_Parser
break;
default:
if ((unsigned char)*pe < 0x20) {
if (*pe == '\n') {
raise_parse_error_at("Invalid unescaped newline character (\\n) in string: %s", state, pe - 1);
if (!config->allow_control_characters) {
if (*pe == '\n') {
raise_parse_error_at("Invalid unescaped newline character (\\n) in string: %s", state, pe - 1);
}
raise_parse_error_at("invalid ASCII control character in string: %s", state, pe - 1);
}
raise_parse_error_at("invalid ASCII control character in string: %s", state, pe - 1);
} else {
raise_parse_error_at("invalid escape character in string: %s", state, pe - 1);
}
raise_parse_error_at("invalid escape character in string: %s", state, pe - 1);
break;
}
}
Expand Down Expand Up @@ -1009,7 +1013,9 @@ static VALUE json_parse_escaped_string(JSON_ParserState *state, JSON_ParserConfi
break;
}
default:
raise_parse_error("invalid ASCII control character in string: %s", state);
if (!config->allow_control_characters) {
raise_parse_error("invalid ASCII control character in string: %s", state);
}
break;
}

Expand Down Expand Up @@ -1430,14 +1436,15 @@ static int parser_config_init_i(VALUE key, VALUE val, VALUE data)
{
JSON_ParserConfig *config = (JSON_ParserConfig *)data;

if (key == sym_max_nesting) { config->max_nesting = RTEST(val) ? FIX2INT(val) : 0; }
else if (key == sym_allow_nan) { config->allow_nan = RTEST(val); }
else if (key == sym_allow_trailing_comma) { config->allow_trailing_comma = RTEST(val); }
else if (key == sym_symbolize_names) { config->symbolize_names = RTEST(val); }
else if (key == sym_freeze) { config->freeze = RTEST(val); }
else if (key == sym_on_load) { config->on_load_proc = RTEST(val) ? val : Qfalse; }
else if (key == sym_allow_duplicate_key) { config->on_duplicate_key = RTEST(val) ? JSON_IGNORE : JSON_RAISE; }
else if (key == sym_decimal_class) {
if (key == sym_max_nesting) { config->max_nesting = RTEST(val) ? FIX2INT(val) : 0; }
else if (key == sym_allow_nan) { config->allow_nan = RTEST(val); }
else if (key == sym_allow_trailing_comma) { config->allow_trailing_comma = RTEST(val); }
else if (key == sym_allow_control_characters) { config->allow_control_characters = RTEST(val); }
else if (key == sym_symbolize_names) { config->symbolize_names = RTEST(val); }
else if (key == sym_freeze) { config->freeze = RTEST(val); }
else if (key == sym_on_load) { config->on_load_proc = RTEST(val) ? val : Qfalse; }
else if (key == sym_allow_duplicate_key) { config->on_duplicate_key = RTEST(val) ? JSON_IGNORE : JSON_RAISE; }
else if (key == sym_decimal_class) {
if (RTEST(val)) {
if (rb_respond_to(val, i_try_convert)) {
config->decimal_class = val;
Expand Down Expand Up @@ -1650,6 +1657,7 @@ void Init_parser(void)
sym_max_nesting = ID2SYM(rb_intern("max_nesting"));
sym_allow_nan = ID2SYM(rb_intern("allow_nan"));
sym_allow_trailing_comma = ID2SYM(rb_intern("allow_trailing_comma"));
sym_allow_control_characters = ID2SYM(rb_intern("allow_control_characters"));
sym_symbolize_names = ID2SYM(rb_intern("symbolize_names"));
sym_freeze = ID2SYM(rb_intern("freeze"));
sym_on_load = ID2SYM(rb_intern("on_load"));
Expand Down
Loading