mirror/json-c
1
0
Fork 0
mirror of https://github.com/json-c/json-c.git synced 2026-03-27 08:59:07 +08:00
Code Issues Packages Projects Releases Wiki Activity

Issue #616: Change the parsing of surrogate pairs in unicode escapes so it uses a couple of additional states instead of assuming the low surrogate is already present, to ensure that we correctly handle various cases of incremental parsing.

Browse Source
This commit is contained in:
Eric Haszlakiewicz
2020-06-21 18:17:40 +00:00
parent 197e372464
commit a68566bf6a
5 changed files with 172 additions and 172 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
tests/test_parse.c
View File

@@ -68,8 +68,8 @@ static void single_incremental_parse(const char *test_string, int clear_serializ
if (strcmp(all_at_once_str, new_str) != 0)
{
printf("ERROR: failed to parse (%s) in %d byte chunks: %s != %s\n",
test_string, chunksize, all_at_once_str, new_str);
printf("ERROR: failed to parse (%s) in %d byte chunks: %s != %s\n", test_string,
chunksize, all_at_once_str, new_str);
}
json_tokener_free(tok);
}
@@ -193,8 +193,8 @@ static void test_utf8_parse()
// json_tokener_parse doesn't support checking for byte order marks.
// It's the responsibility of the caller to detect and skip a BOM.
// Both of these checks return null.
char* utf8_bom = "\xEF\xBB\xBF";
char* utf8_bom_and_chars = "\xEF\xBB\xBF{}";
char *utf8_bom = "\xEF\xBB\xBF";
char *utf8_bom_and_chars = "\xEF\xBB\xBF{}";
single_basic_parse(utf8_bom, 0);
single_basic_parse(utf8_bom_and_chars, 0);
}
@@ -245,7 +245,7 @@ struct incremental_step
int char_offset;
enum json_tokener_error expected_error;
int reset_tokener; /* Set to 1 to call json_tokener_reset() after parsing */
int tok_flags; /* JSON_TOKENER_* flags to pass to json_tokener_set_flags() */
int tok_flags; /* JSON_TOKENER_* flags to pass to json_tokener_set_flags() */
} incremental_steps[] = {
/* Check that full json messages can be parsed, both w/ and w/o a reset */
@@ -268,7 +268,11 @@ struct incremental_step
{"\": {\"bar", -1, -1, json_tokener_continue, 0},
{"\":13}}", -1, -1, json_tokener_success, 1},
/* Check the UTF-16 surrogate pair */
/* Check the UTF-16 surrogate pair handling in various ways.
* Note: \ud843\udd1e is u+1D11E, Musical Symbol G Clef
* Your terminal may not display these correctly, in particular
* PuTTY doesn't currently show this character.
*/
/* parse one char at every time */
{"\"\\", -1, -1, json_tokener_continue, 0},
{"u", -1, -1, json_tokener_continue, 0},
@@ -296,6 +300,16 @@ struct incremental_step
{"udd1e\"", -1, -1, json_tokener_success, 1},
{"\"\\ud834\\u", -1, -1, json_tokener_continue, 0},
{"dd1e\"", -1, -1, json_tokener_success, 1},
{"\"fff \\ud834\\ud", -1, -1, json_tokener_continue, 0},
{"d1e bar\"", -1, -1, json_tokener_success, 1},
{"\"fff \\ud834\\udd", -1, -1, json_tokener_continue, 0},
{"1e bar\"", -1, -1, json_tokener_success, 1},
/* \ud83d\ude00 is U+1F600, Grinning Face
* Displays fine in PuTTY, though you may need "less -r"
*/
{"\"fff \\ud83d\\ude", -1, -1, json_tokener_continue, 0},
{"00 bar\"", -1, -1, json_tokener_success, 1},
/* Check that json_tokener_reset actually resets */
{"{ \"foo", -1, -1, json_tokener_continue, 1},

8
tests/test_parse.expected
View File

@@ -124,6 +124,12 @@ json_tokener_parse_ex(tok, "\ud834\ , 8) ... OK: got correct error: continu
json_tokener_parse_ex(tok, udd1e" , 6) ... OK: got object of type [string]: "𝄞"
json_tokener_parse_ex(tok, "\ud834\u , 9) ... OK: got correct error: continue
json_tokener_parse_ex(tok, dd1e" , 5) ... OK: got object of type [string]: "𝄞"
json_tokener_parse_ex(tok, "fff \ud834\ud, 14) ... OK: got correct error: continue
json_tokener_parse_ex(tok, d1e bar" , 8) ... OK: got object of type [string]: "fff 𝄞 bar"
json_tokener_parse_ex(tok, "fff \ud834\udd, 15) ... OK: got correct error: continue
json_tokener_parse_ex(tok, 1e bar" , 7) ... OK: got object of type [string]: "fff 𝄞 bar"
json_tokener_parse_ex(tok, "fff \ud83d\ude, 15) ... OK: got correct error: continue
json_tokener_parse_ex(tok, 00 bar" , 7) ... OK: got object of type [string]: "fff 😀 bar"
json_tokener_parse_ex(tok, { "foo , 6) ... OK: got correct error: continue
json_tokener_parse_ex(tok, : "bar"} , 8) ... OK: got correct error: unexpected character
json_tokener_parse_ex(tok, { "foo , 6) ... OK: got correct error: continue
@@ -240,5 +246,5 @@ json_tokener_parse_ex(tok, "\ud855
json_tokener_parse_ex(tok, "\ud0031<33>" , 10) ... OK: got correct error: invalid utf-8 string
json_tokener_parse_ex(tok, 11<31>11 , 5) ... OK: got correct error: invalid utf-8 string
json_tokener_parse_ex(tok, {"1<>":1} , 8) ... OK: got correct error: invalid utf-8 string
End Incremental Tests OK=154 ERROR=0
End Incremental Tests OK=160 ERROR=0
==================================