Merge pull request #633 from dota17/issue616

fix issue 616: support the surrogate pair in split file.

4 files changed, 113 insertions, 35 deletions

diff --git a/json_tokener.c b/json_tokener.c
index 9aa86a9..2a73ce2 100644
--- a/json_tokener.c
+++ b/json_tokener.c
@@ -630,8 +630,6 @@ struct json_object *json_tokener_parse_ex(struct json_tokener *tok, const char *
 
 		case json_tokener_state_escape_unicode:
 		{
-			unsigned int got_hi_surrogate = 0;
-
 			/* Handle a 4-byte sequence, or two sequences if a surrogate pair */
 			while (1)
 			{
@@ -643,14 +641,24 @@ struct json_object *json_tokener_parse_ex(struct json_tokener *tok, const char *
 					{
 						unsigned char unescaped_utf[4];
 
-						if (got_hi_surrogate)
+						if (tok->got_hi_surrogate)
 						{
 							if (IS_LOW_SURROGATE(tok->ucs_char))
 							{
+								/* remove the utf8_replacement_char */
+								/* which may generate during */
+								/* parsing the high surrogate pair. */
+								if (!strcmp(
+								        tok->pb->buf,
+								        (char *)
+								            utf8_replacement_char))
+								{
+									printbuf_reset(tok->pb);
+								}
 								/* Recalculate the ucs_char, then fall thru to process normally */
 								tok->ucs_char =
 								    DECODE_SURROGATE_PAIR(
-								        got_hi_surrogate,
+								        tok->got_hi_surrogate,
 								        tok->ucs_char);
 							}
 							else
@@ -662,7 +670,7 @@ struct json_object *json_tokener_parse_ex(struct json_tokener *tok, const char *
 								    (char *)utf8_replacement_char,
 								    3);
 							}
-							got_hi_surrogate = 0;
+							tok->got_hi_surrogate = 0;
 						}
 
 						if (tok->ucs_char < 0x80)
@@ -686,7 +694,7 @@ struct json_object *json_tokener_parse_ex(struct json_tokener *tok, const char *
 							 * the beginning of another sequence, which
 							 * should be the low surrogate.
 							 */
-							got_hi_surrogate = tok->ucs_char;
+							tok->got_hi_surrogate = tok->ucs_char;
 							/* Not at end, and the next two chars should be "\u" */
 							if ((len == -1 ||
 							     len > (tok->char_offset + 2)) &&
@@ -717,6 +725,8 @@ struct json_object *json_tokener_parse_ex(struct json_tokener *tok, const char *
 									    (char *)
 									        utf8_replacement_char,
 									    3);
+									tok->ucs_char = 0;
+									tok->st_pos = 0;
 									goto out;
 								}
 								tok->ucs_char = 0;
@@ -786,7 +796,8 @@ struct json_object *json_tokener_parse_ex(struct json_tokener *tok, const char *
 				if (!ADVANCE_CHAR(str, tok) || !PEEK_CHAR(c, tok))
 				{
 					/* Clean up any pending chars */
-					if (got_hi_surrogate)
+					if (tok->got_hi_surrogate &&
+					    strcmp(tok->pb->buf, (char *)utf8_replacement_char))
 						printbuf_memappend_fast(
 						    tok->pb, (char *)utf8_replacement_char, 3);
 					goto out;
diff --git a/json_tokener.h b/json_tokener.h
index ea49ad8..8afa6ec 100644
--- a/json_tokener.h
+++ b/json_tokener.h
@@ -111,7 +111,7 @@ struct json_tokener
 	 * @deprecated See json_tokener_get_error() instead.
 	 */
 	enum json_tokener_error err;
-	unsigned int ucs_char;
+	unsigned int ucs_char, got_hi_surrogate;
 	char quote_char;
 	struct json_tokener_srec *stack;
 	int flags;
diff --git a/tests/test_parse.c b/tests/test_parse.c
index 6014ac1..42b2fdf 100644
--- a/tests/test_parse.c
+++ b/tests/test_parse.c
@@ -224,6 +224,35 @@ struct incremental_step
     {"\": {\"bar", -1, -1, json_tokener_continue, 0},
     {"\":13}}", -1, -1, json_tokener_success, 1},
 
+    /* Check the UTF-16 surrogate pair */
+    /* parse one char at every time */
+    {"\"\\", -1, -1, json_tokener_continue, 0},
+    {"u", -1, -1, json_tokener_continue, 0},
+    {"d", -1, -1, json_tokener_continue, 0},
+    {"8", -1, -1, json_tokener_continue, 0},
+    {"3", -1, -1, json_tokener_continue, 0},
+    {"4", -1, -1, json_tokener_continue, 0},
+    {"\\", -1, -1, json_tokener_continue, 0},
+    {"u", -1, -1, json_tokener_continue, 0},
+    {"d", -1, -1, json_tokener_continue, 0},
+    {"d", -1, -1, json_tokener_continue, 0},
+    {"1", -1, -1, json_tokener_continue, 0},
+    {"e\"", -1, -1, json_tokener_success, 1},
+    /* parse two char at every time */
+    {"\"\\u", -1, -1, json_tokener_continue, 0},
+    {"d8", -1, -1, json_tokener_continue, 0},
+    {"34", -1, -1, json_tokener_continue, 0},
+    {"\\u", -1, -1, json_tokener_continue, 0},
+    {"dd", -1, -1, json_tokener_continue, 0},
+    {"1e\"", -1, -1, json_tokener_success, 1},
+    /* check the low surrogate pair */
+    {"\"\\ud834", -1, -1, json_tokener_continue, 0},
+    {"\\udd1e\"", -1, -1, json_tokener_success, 1},
+    {"\"\\ud834\\", -1, -1, json_tokener_continue, 0},
+    {"udd1e\"", -1, -1, json_tokener_success, 1},
+    {"\"\\ud834\\u", -1, -1, json_tokener_continue, 0},
+    {"dd1e\"", -1, -1, json_tokener_success, 1},
+
     /* Check that json_tokener_reset actually resets */
     {"{ \"foo", -1, -1, json_tokener_continue, 1},
     {": \"bar\"}", -1, 0, json_tokener_error_parse_unexpected, 1},
@@ -239,11 +268,13 @@ struct incremental_step
     {"\"Y\"", -1, -1, json_tokener_success, 1},
 
     /* Trailing characters should cause a failure in strict mode */
-    {"{\"foo\":9}{\"bar\":8}", -1, 9, json_tokener_error_parse_unexpected, 1, JSON_TOKENER_STRICT },
+    {"{\"foo\":9}{\"bar\":8}", -1, 9, json_tokener_error_parse_unexpected, 1, JSON_TOKENER_STRICT},
 
     /* ... unless explicitly allowed. */
-    {"{\"foo\":9}{\"bar\":8}", -1, 9, json_tokener_success, 0, JSON_TOKENER_STRICT|JSON_TOKENER_ALLOW_TRAILING_CHARS },
-    {"{\"b\":8}ignored garbage", -1, 7, json_tokener_success, 1, JSON_TOKENER_STRICT|JSON_TOKENER_ALLOW_TRAILING_CHARS },
+    {"{\"foo\":9}{\"bar\":8}", -1, 9, json_tokener_success, 0,
+     JSON_TOKENER_STRICT | JSON_TOKENER_ALLOW_TRAILING_CHARS},
+    {"{\"b\":8}ignored garbage", -1, 7, json_tokener_success, 1,
+     JSON_TOKENER_STRICT | JSON_TOKENER_ALLOW_TRAILING_CHARS},
 
     /* To stop parsing a number we need to reach a non-digit, e.g. a \0 */
     {"1", 1, 1, json_tokener_continue, 0},
@@ -251,7 +282,7 @@ struct incremental_step
     {"2", 2, 1, json_tokener_success, 0},
     {"12{", 3, 2, json_tokener_success, 1},
     /* Parse number in strict model */
-    {"[02]", -1, 3, json_tokener_error_parse_number, 1, JSON_TOKENER_STRICT },
+    {"[02]", -1, 3, json_tokener_error_parse_number, 1, JSON_TOKENER_STRICT},
 
     /* Similar tests for other kinds of objects: */
     /* These could all return success immediately, since regardless of
@@ -267,8 +298,8 @@ struct incremental_step
     {"Infinity", 9, 8, json_tokener_success, 1},
     {"infinity", 9, 8, json_tokener_success, 1},
     {"-infinity", 10, 9, json_tokener_success, 1},
-    {"infinity", 9, 0, json_tokener_error_parse_unexpected, 1, JSON_TOKENER_STRICT },
-    {"-infinity", 10, 1, json_tokener_error_parse_unexpected, 1, JSON_TOKENER_STRICT },
+    {"infinity", 9, 0, json_tokener_error_parse_unexpected, 1, JSON_TOKENER_STRICT},
+    {"-infinity", 10, 1, json_tokener_error_parse_unexpected, 1, JSON_TOKENER_STRICT},
 
     {"inf", 3, 3, json_tokener_continue, 0},
     {"inity", 6, 5, json_tokener_success, 1},
@@ -350,7 +381,7 @@ struct incremental_step
     {"\"\\a\"", -1, 2, json_tokener_error_parse_string, 1},
 
     /* Check '\'' in strict model */
-    {"\'foo\'", -1, 0, json_tokener_error_parse_unexpected, 1, JSON_TOKENER_STRICT },
+    {"\'foo\'", -1, 0, json_tokener_error_parse_unexpected, 1, JSON_TOKENER_STRICT},
 
     /* Parse array/object */
     {"[1,2,3]", -1, -1, json_tokener_success, 0},
@@ -372,42 +403,54 @@ struct incremental_step
     {"[1,2,3,]", -1, -1, json_tokener_success, 0},
     {"[1,2,,3,]", -1, 5, json_tokener_error_parse_unexpected, 0},
 
-    {"[1,2,3,]", -1, 7, json_tokener_error_parse_unexpected, 1, JSON_TOKENER_STRICT },
-    {"{\"a\":1,}", -1, 7, json_tokener_error_parse_unexpected, 1, JSON_TOKENER_STRICT },
+    {"[1,2,3,]", -1, 7, json_tokener_error_parse_unexpected, 1, JSON_TOKENER_STRICT},
+    {"{\"a\":1,}", -1, 7, json_tokener_error_parse_unexpected, 1, JSON_TOKENER_STRICT},
 
     // utf-8 test
     // acsll encoding
-    {"\x22\x31\x32\x33\x61\x73\x63\x24\x25\x26\x22", -1, -1, json_tokener_success, 1, JSON_TOKENER_VALIDATE_UTF8 },
+    {"\x22\x31\x32\x33\x61\x73\x63\x24\x25\x26\x22", -1, -1, json_tokener_success, 1,
+     JSON_TOKENER_VALIDATE_UTF8},
     {"\x22\x31\x32\x33\x61\x73\x63\x24\x25\x26\x22", -1, -1, json_tokener_success, 1},
     // utf-8 encoding
-    {"\x22\xe4\xb8\x96\xe7\x95\x8c\x22", -1, -1, json_tokener_success, 1, JSON_TOKENER_VALIDATE_UTF8 },
-    {"\x22\xe4\xb8", -1, 3, json_tokener_error_parse_utf8_string, 0, JSON_TOKENER_VALIDATE_UTF8 },
-    {"\x96\xe7\x95\x8c\x22", -1, 0, json_tokener_error_parse_utf8_string, 1, JSON_TOKENER_VALIDATE_UTF8 },
+    {"\x22\xe4\xb8\x96\xe7\x95\x8c\x22", -1, -1, json_tokener_success, 1,
+     JSON_TOKENER_VALIDATE_UTF8},
+    {"\x22\xe4\xb8", -1, 3, json_tokener_error_parse_utf8_string, 0, JSON_TOKENER_VALIDATE_UTF8},
+    {"\x96\xe7\x95\x8c\x22", -1, 0, json_tokener_error_parse_utf8_string, 1,
+     JSON_TOKENER_VALIDATE_UTF8},
     {"\x22\xe4\xb8\x96\xe7\x95\x8c\x22", -1, -1, json_tokener_success, 1},
-    {"\x22\xcf\x80\xcf\x86\x22", -1, -1, json_tokener_success, 1, JSON_TOKENER_VALIDATE_UTF8 },
-    {"\x22\xf0\xa5\x91\x95\x22", -1, -1, json_tokener_success, 1, JSON_TOKENER_VALIDATE_UTF8 },
+    {"\x22\xcf\x80\xcf\x86\x22", -1, -1, json_tokener_success, 1, JSON_TOKENER_VALIDATE_UTF8},
+    {"\x22\xf0\xa5\x91\x95\x22", -1, -1, json_tokener_success, 1, JSON_TOKENER_VALIDATE_UTF8},
     // wrong utf-8 encoding
-    {"\x22\xe6\x9d\x4e\x22", -1, 3, json_tokener_error_parse_utf8_string, 1, JSON_TOKENER_VALIDATE_UTF8 },
+    {"\x22\xe6\x9d\x4e\x22", -1, 3, json_tokener_error_parse_utf8_string, 1,
+     JSON_TOKENER_VALIDATE_UTF8},
     {"\x22\xe6\x9d\x4e\x22", -1, 5, json_tokener_success, 1},
     // GBK encoding
-    {"\x22\xc0\xee\xc5\xf4\x22", -1, 2, json_tokener_error_parse_utf8_string, 1, JSON_TOKENER_VALIDATE_UTF8 },
+    {"\x22\xc0\xee\xc5\xf4\x22", -1, 2, json_tokener_error_parse_utf8_string, 1,
+     JSON_TOKENER_VALIDATE_UTF8},
     {"\x22\xc0\xee\xc5\xf4\x22", -1, 6, json_tokener_success, 1},
     // char after space
-    {"\x20\x20\x22\xe4\xb8\x96\x22", -1, -1, json_tokener_success, 1, JSON_TOKENER_VALIDATE_UTF8 },
-    {"\x20\x20\x81\x22\xe4\xb8\x96\x22", -1, 2, json_tokener_error_parse_utf8_string, 1, JSON_TOKENER_VALIDATE_UTF8 },
-    {"\x5b\x20\x81\x31\x5d", -1, 2, json_tokener_error_parse_utf8_string, 1, JSON_TOKENER_VALIDATE_UTF8 },
+    {"\x20\x20\x22\xe4\xb8\x96\x22", -1, -1, json_tokener_success, 1, JSON_TOKENER_VALIDATE_UTF8},
+    {"\x20\x20\x81\x22\xe4\xb8\x96\x22", -1, 2, json_tokener_error_parse_utf8_string, 1,
+     JSON_TOKENER_VALIDATE_UTF8},
+    {"\x5b\x20\x81\x31\x5d", -1, 2, json_tokener_error_parse_utf8_string, 1,
+     JSON_TOKENER_VALIDATE_UTF8},
     // char in state inf
     {"\x49\x6e\x66\x69\x6e\x69\x74\x79", 9, 8, json_tokener_success, 1},
-    {"\x49\x6e\x66\x81\x6e\x69\x74\x79", -1, 3, json_tokener_error_parse_utf8_string, 1, JSON_TOKENER_VALIDATE_UTF8 },
+    {"\x49\x6e\x66\x81\x6e\x69\x74\x79", -1, 3, json_tokener_error_parse_utf8_string, 1,
+     JSON_TOKENER_VALIDATE_UTF8},
     // char in escape unicode
-    {"\x22\x5c\x75\x64\x38\x35\x35\x5c\x75\x64\x63\x35\x35\x22", 15, 14, json_tokener_success, 1, JSON_TOKENER_VALIDATE_UTF8 },
+    {"\x22\x5c\x75\x64\x38\x35\x35\x5c\x75\x64\x63\x35\x35\x22", 15, 14, json_tokener_success, 1,
+     JSON_TOKENER_VALIDATE_UTF8},
     {"\x22\x5c\x75\x64\x38\x35\x35\xc0\x75\x64\x63\x35\x35\x22", -1, 8,
-     json_tokener_error_parse_utf8_string, 1, JSON_TOKENER_VALIDATE_UTF8 },
-    {"\x22\x5c\x75\x64\x30\x30\x33\x31\xc0\x22", -1, 9, json_tokener_error_parse_utf8_string, 1, JSON_TOKENER_VALIDATE_UTF8 },
+     json_tokener_error_parse_utf8_string, 1, JSON_TOKENER_VALIDATE_UTF8},
+    {"\x22\x5c\x75\x64\x30\x30\x33\x31\xc0\x22", -1, 9, json_tokener_error_parse_utf8_string, 1,
+     JSON_TOKENER_VALIDATE_UTF8},
     // char in number
-    {"\x31\x31\x81\x31\x31", -1, 2, json_tokener_error_parse_utf8_string, 1, JSON_TOKENER_VALIDATE_UTF8 },
+    {"\x31\x31\x81\x31\x31", -1, 2, json_tokener_error_parse_utf8_string, 1,
+     JSON_TOKENER_VALIDATE_UTF8},
     // char in object
-    {"\x7b\x22\x31\x81\x22\x3a\x31\x7d", -1, 3, json_tokener_error_parse_utf8_string, 1, JSON_TOKENER_VALIDATE_UTF8 },
+    {"\x7b\x22\x31\x81\x22\x3a\x31\x7d", -1, 3, json_tokener_error_parse_utf8_string, 1,
+     JSON_TOKENER_VALIDATE_UTF8},
 
     {NULL, -1, -1, json_tokener_success, 0},
 };
diff --git a/tests/test_parse.expected b/tests/test_parse.expected
index 77e8be1..df74fbd 100644
--- a/tests/test_parse.expected
+++ b/tests/test_parse.expected
@@ -100,6 +100,30 @@ json_tokener_parse_ex(tok, // hello"foo",  13) ... OK: got correct error: contin
 json_tokener_parse_ex(tok, { "foo      ,   6) ... OK: got correct error: continue
 json_tokener_parse_ex(tok, ": {"bar    ,   8) ... OK: got correct error: continue
 json_tokener_parse_ex(tok, ":13}}      ,   6) ... OK: got object of type [object]: { "foo": { "bar": 13 } }
+json_tokener_parse_ex(tok, "\          ,   2) ... OK: got correct error: continue
+json_tokener_parse_ex(tok, u           ,   1) ... OK: got correct error: continue
+json_tokener_parse_ex(tok, d           ,   1) ... OK: got correct error: continue
+json_tokener_parse_ex(tok, 8           ,   1) ... OK: got correct error: continue
+json_tokener_parse_ex(tok, 3           ,   1) ... OK: got correct error: continue
+json_tokener_parse_ex(tok, 4           ,   1) ... OK: got correct error: continue
+json_tokener_parse_ex(tok, \           ,   1) ... OK: got correct error: continue
+json_tokener_parse_ex(tok, u           ,   1) ... OK: got correct error: continue
+json_tokener_parse_ex(tok, d           ,   1) ... OK: got correct error: continue
+json_tokener_parse_ex(tok, d           ,   1) ... OK: got correct error: continue
+json_tokener_parse_ex(tok, 1           ,   1) ... OK: got correct error: continue
+json_tokener_parse_ex(tok, e"          ,   2) ... OK: got object of type [string]: "�"
+json_tokener_parse_ex(tok, "\u         ,   3) ... OK: got correct error: continue
+json_tokener_parse_ex(tok, d8          ,   2) ... OK: got correct error: continue
+json_tokener_parse_ex(tok, 34          ,   2) ... OK: got correct error: continue
+json_tokener_parse_ex(tok, \u          ,   2) ... OK: got correct error: continue
+json_tokener_parse_ex(tok, dd          ,   2) ... OK: got correct error: continue
+json_tokener_parse_ex(tok, 1e"         ,   3) ... OK: got object of type [string]: "�"
+json_tokener_parse_ex(tok, "\ud834     ,   7) ... OK: got correct error: continue
+json_tokener_parse_ex(tok, \udd1e"     ,   7) ... OK: got object of type [string]: "�"
+json_tokener_parse_ex(tok, "\ud834\    ,   8) ... OK: got correct error: continue
+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, { "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
@@ -216,5 +240,5 @@ json_tokener_parse_ex(tok, "\ud855Àudc55",  14) ... OK: got correct error: inval
 json_tokener_parse_ex(tok, "\ud0031À"  ,  10) ... OK: got correct error: invalid utf-8 string
 json_tokener_parse_ex(tok, 11�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=130 ERROR=0
+End Incremental Tests OK=154 ERROR=0
 ==================================