database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-06-16 06:01:02 +03:00
Code Activity

Fix unescaping of JSON Unicode escapes, especially for non-UTF8.

Browse Source 
Per discussion  on -hackers. We treat Unicode escapes when unescaping
them similarly to the way we treat them in PostgreSQL string literals.
Escapes in the ASCII range are always accepted, no matter what the
database encoding. Escapes for higher code points are only processed in
UTF8 databases, and attempts to process them in other databases will
result in an error. \u0000 is never unescaped, since it would result in
an impermissible null byte.
This commit is contained in:
Andrew Dunstan
2013-06-12 13:35:24 -04:00
parent c1d729b419
commit 78ed8e03c6
5 changed files with 1033 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
src/backend/utils/adt/json.c
View File

@ -717,7 +717,6 @@ json_lex_string(JsonLexContext *lex)
{
char utf8str[5];
int utf8len;
char *converted;
if (ch >= 0xd800 && ch <= 0xdbff)
{
@ -749,13 +748,40 @@ json_lex_string(JsonLexContext *lex)
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';
converted = pg_any_to_server(utf8str, utf8len, PG_UTF8);
appendStringInfoString(lex->strval, converted);
if (converted != utf8str)
pfree(converted);
/*
* For UTF8, replace the escape sequence by the actual utf8
* character in lex->strval. Do this also for other encodings
* if the escape designates an ASCII character, otherwise
* raise an error. We don't ever unescape a \u0000, since that
* would result in an impermissible nul byte.
*/
if (ch == 0)
{
appendStringInfoString(lex->strval, "\\u0000");
}
else if (GetDatabaseEncoding() == PG_UTF8)
{
unicode_to_utf8(ch, (unsigned char *) utf8str);
utf8len = pg_utf_mblen((unsigned char *) utf8str);
appendBinaryStringInfo(lex->strval, utf8str, utf8len);
}
else if (ch <= 0x007f)
{
/*
* This is the only way to designate things like a form feed
* character in JSON, so it's useful in all encodings.
*/
appendStringInfoChar(lex->strval, (char) ch);
}
else
{
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid input syntax for type json"),
errdetail("Unicode escape for code points higher than U+007F not permitted in non-UTF8 encoding"),
report_json_context(lex)));
}
}
}