diff options
Diffstat (limited to 'src/common')
| -rw-r--r-- | src/common/jsonapi.c | 6 | ||||
| -rw-r--r-- | src/common/wchar.c | 15 |
2 files changed, 18 insertions, 3 deletions
diff --git a/src/common/jsonapi.c b/src/common/jsonapi.c index 1bf38d7b429..d376ab152d4 100644 --- a/src/common/jsonapi.c +++ b/src/common/jsonapi.c @@ -740,7 +740,7 @@ json_lex_string(JsonLexContext *lex) ch = (ch * 16) + (*s - 'A') + 10; else { - lex->token_terminator = s + pg_encoding_mblen(lex->input_encoding, s); + lex->token_terminator = s + pg_encoding_mblen_bounded(lex->input_encoding, s); return JSON_UNICODE_ESCAPE_FORMAT; } } @@ -846,7 +846,7 @@ json_lex_string(JsonLexContext *lex) default: /* Not a valid string escape, so signal error. */ lex->token_start = s; - lex->token_terminator = s + pg_encoding_mblen(lex->input_encoding, s); + lex->token_terminator = s + pg_encoding_mblen_bounded(lex->input_encoding, s); return JSON_ESCAPING_INVALID; } } @@ -860,7 +860,7 @@ json_lex_string(JsonLexContext *lex) * shown it's not a performance win. */ lex->token_start = s; - lex->token_terminator = s + pg_encoding_mblen(lex->input_encoding, s); + lex->token_terminator = s + pg_encoding_mblen_bounded(lex->input_encoding, s); return JSON_ESCAPING_INVALID; } diff --git a/src/common/wchar.c b/src/common/wchar.c index 6e7d731e020..0636b8765ba 100644 --- a/src/common/wchar.c +++ b/src/common/wchar.c @@ -1911,6 +1911,11 @@ const pg_wchar_tbl pg_wchar_table[] = { /* * Returns the byte length of a multibyte character. + * + * Caution: when dealing with text that is not certainly valid in the + * specified encoding, the result may exceed the actual remaining + * string length. Callers that are not prepared to deal with that + * should use pg_encoding_mblen_bounded() instead. */ int pg_encoding_mblen(int encoding, const char *mbstr) @@ -1921,6 +1926,16 @@ pg_encoding_mblen(int encoding, const char *mbstr) } /* + * Returns the byte length of a multibyte character; but not more than + * the distance to end of string. + */ +int +pg_encoding_mblen_bounded(int encoding, const char *mbstr) +{ + return strnlen(mbstr, pg_encoding_mblen(encoding, mbstr)); +} + +/* * Returns the display length of a multibyte character. */ int |