From 94e3311b97448324d67ba9a527854271373329d9 Mon Sep 17 00:00:00 2001 From: Andrew Dunstan Date: Sat, 8 Jun 2013 09:12:48 -0400 Subject: Handle Unicode surrogate pairs correctly when processing JSON. In 9.2, Unicode escape sequences are not analysed at all other than to make sure that they are in the form \uXXXX. But in 9.3 many of the new operators and functions try to turn JSON text values into text in the server encoding, and this includes de-escaping Unicode escape sequences. This processing had not taken into account the possibility that this might contain a surrogate pair to designate a character outside the BMP. That is now handled correctly. This also enforces correct use of surrogate pairs, something that is not done by the type's input routines. This fact is noted in the docs. --- src/backend/utils/adt/json.c | 52 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) (limited to 'src/backend/utils/adt/json.c') diff --git a/src/backend/utils/adt/json.c b/src/backend/utils/adt/json.c index aaf99bddf27..d8046c5b54d 100644 --- a/src/backend/utils/adt/json.c +++ b/src/backend/utils/adt/json.c @@ -646,6 +646,7 @@ json_lex_string(JsonLexContext *lex) { char *s; int len; + int hi_surrogate = -1; if (lex->strval != NULL) resetStringInfo(lex->strval); @@ -718,6 +719,36 @@ json_lex_string(JsonLexContext *lex) int utf8len; char *converted; + if (ch >= 0xd800 && ch <= 0xdbff) + { + if (hi_surrogate != -1) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type json"), + errdetail("high order surrogate must not follow a high order surrogate."), + report_json_context(lex))); + hi_surrogate = (ch & 0x3ff) << 10; + continue; + } + else if (ch >= 0xdc00 && ch <= 0xdfff) + { + if (hi_surrogate == -1) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type json"), + errdetail("low order surrogate must follow a high order surrogate."), + report_json_context(lex))); + ch = 0x10000 + hi_surrogate + (ch & 0x3ff); + hi_surrogate = -1; + } + + if (hi_surrogate != -1) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type json"), + errdetail("low order surrogate must follow a high order surrogate."), + report_json_context(lex))); + unicode_to_utf8(ch, (unsigned char *) utf8str); utf8len = pg_utf_mblen((unsigned char *) utf8str); utf8str[utf8len] = '\0'; @@ -730,6 +761,13 @@ json_lex_string(JsonLexContext *lex) } else if (lex->strval != NULL) { + if (hi_surrogate != -1) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type json"), + errdetail("low order surrogate must follow a high order surrogate."), + report_json_context(lex))); + switch (*s) { case '"': @@ -784,11 +822,25 @@ json_lex_string(JsonLexContext *lex) } else if (lex->strval != NULL) { + if (hi_surrogate != -1) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type json"), + errdetail("low order surrogate must follow a high order surrogate."), + report_json_context(lex))); + appendStringInfoChar(lex->strval, *s); } } + if (hi_surrogate != -1) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type json"), + errdetail("low order surrogate must follow a high order surrogate."), + report_json_context(lex))); + /* Hooray, we found the end of the string! */ lex->prev_token_terminator = lex->token_terminator; lex->token_terminator = s + 1; -- cgit v1.2.3