/*
* The next token in the input stream is known to be a string; lex it.
*/
static inline void
json_lex_string(JsonLexContext *lex)
{
char *s;
int len;
int hi_surrogate = -1;
if (lex->strval != NULL)
resetStringInfo(lex->strval);
Assert(lex->input_length > 0);
s = lex->token_start;
len = lex->token_start - lex->input;
for (;;)
{
s++;
len++;
/* Premature end of the string. */
if (len >= lex->input_length)
{
lex->token_terminator = s;
report_invalid_token(lex);
}
else if (*s == '"')
break;
else if ((unsigned char) *s < 32)
{
/* Per RFC4627, these characters MUST be escaped. */
/* Since *s isn't printable, exclude it from the context string */
lex->token_terminator = s;
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid input syntax for type json"),
errdetail("Character with value 0x%02x must be escaped.",
(unsigned char) *s),
report_json_context(lex)));
}
else if (*s == '\\')
{
/* OK, we have an escape character. */
s++;
len++;
if (len >= lex->input_length)
{
lex->token_terminator = s;
report_invalid_token(lex);
}
else if (*s == 'u')
{
int i;
int ch = 0;
for (i = 1; i <= 4; i++)
{
s++;
len++;
if (len >= lex->input_length)
{
lex->token_terminator = s;
report_invalid_token(lex);
}
else if (*s >= '0' && *s <= '9')
ch = (ch * 16) + (*s - '0');
else if (*s >= 'a' && *s <= 'f')
ch = (ch * 16) + (*s - 'a') + 10;
else if (*s >= 'A' && *s <= 'F')
ch = (ch * 16) + (*s - 'A') + 10;
else
{
lex->token_terminator = s + pg_mblen(s);
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid input syntax for type json"),
errdetail("\"\\u\" must be followed by four hexadecimal digits."),
report_json_context(lex)));
}
}
if (lex->strval != NULL)
{
char utf8str[5];
int utf8len;
if (ch >= 0xd800 && ch <= 0xdbff)
{
if (hi_surrogate != -1)
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid input syntax for type json"),
errdetail("Unicode high surrogate must not follow a high 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("Unicode low surrogate must follow a high 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("Unicode low surrogate must follow a high surrogate."),
report_json_context(lex)));
/*
* 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 values cannot be used for code point values above 007F when the server encoding is not UTF8."),
report_json_context(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("Unicode low surrogate must follow a high surrogate."),
report_json_context(lex)));
switch (*s)
{
case '"':
case '\\':
case '/':
appendStringInfoChar(lex->strval, *s);
break;
case 'b':
appendStringInfoChar(lex->strval, '\b');
break;
case 'f':
appendStringInfoChar(lex->strval, '\f');
break;
case 'n':
appendStringInfoChar(lex->strval, '\n');
break;
case 'r':
appendStringInfoChar(lex->strval, '\r');
break;
case 't':
appendStringInfoChar(lex->strval, '\t');
break;
default:
/* Not a valid string escape, so error out. */
lex->token_terminator = s + pg_mblen(s);
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid input syntax for type json"),
errdetail("Escape sequence \"\\%s\" is invalid.",
extract_mb_char(s)),
report_json_context(lex)));
}
}
else if (strchr("\"\\/bfnrt", *s) == NULL)
{
/*
* Simpler processing if we're not bothered about de-escaping
*
* It's very tempting to remove the strchr() call here and
* replace it with a switch statement, but testing so far has
* shown it's not a performance win.
*/
lex->token_terminator = s + pg_mblen(s);
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid input syntax for type json"),
errdetail("Escape sequence \"\\%s\" is invalid.",
extract_mb_char(s)),
report_json_context(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("Unicode low surrogate must follow a high 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("Unicode low surrogate must follow a high 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;
}
/*
* The next token in the input stream is known to be a string; lex it.
*/
static void
json_lex_string(JsonLexContext *lex)
{
char *s = lex->token_start + 1;
for (s = lex->token_start + 1; *s != '"'; ++s)
{
/* Per RFC4627, these characters MUST be escaped. */
if (*s < 32)
{
/* A NUL byte marks the (premature) end of the string. */
if (*s == '\0')
{
lex->token_terminator = s;
report_invalid_token(lex);
}
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid input syntax for type json"),
errdetail_internal("line %d: Character \"%c\" must be escaped.",
lex->line_number, *s)));
}
else if (*s == '\\')
{
/* OK, we have an escape character. */
++s;
if (*s == '\0')
{
lex->token_terminator = s;
report_invalid_token(lex);
}
else if (*s == 'u')
{
int i;
int ch = 0;
for (i = 1; i <= 4; ++i)
{
if (s[i] == '\0')
{
lex->token_terminator = s + i;
report_invalid_token(lex);
}
else if (s[i] >= '0' && s[i] <= '9')
ch = (ch * 16) + (s[i] - '0');
else if (s[i] >= 'a' && s[i] <= 'f')
ch = (ch * 16) + (s[i] - 'a') + 10;
else if (s[i] >= 'A' && s[i] <= 'F')
ch = (ch * 16) + (s[i] - 'A') + 10;
else
{
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid input syntax for type json"),
errdetail_internal("line %d: \"\\u\" must be followed by four hexadecimal digits.",
lex->line_number)));
}
}
/* Account for the four additional bytes we just parsed. */
s += 4;
}
else if (!strchr("\"\\/bfnrt", *s))
{
/* Error out. */
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid input syntax for type json"),
errdetail_internal("line %d: Invalid escape \"\\%s\".",
lex->line_number, extract_mb_char(s))));
}
}
}
/* Hooray, we found the end of the string! */
lex->token_terminator = s + 1;
}
/*
* The next token in the input stream is known to be a string; lex it.
*/
static void
json_lex_string(JsonLexContext *lex)
{
char *s;
for (s = lex->token_start + 1; *s != '"'; s++)
{
/* Per RFC4627, these characters MUST be escaped. */
if ((unsigned char) *s < 32)
{
/* A NUL byte marks the (premature) end of the string. */
if (*s == '\0')
{
lex->token_terminator = s;
report_invalid_token(lex);
}
/* Since *s isn't printable, exclude it from the context string */
lex->token_terminator = s;
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid input syntax for type json"),
errdetail("Character with value 0x%02x must be escaped.",
(unsigned char) *s),
report_json_context(lex)));
}
else if (*s == '\\')
{
/* OK, we have an escape character. */
s++;
if (*s == '\0')
{
lex->token_terminator = s;
report_invalid_token(lex);
}
else if (*s == 'u')
{
int i;
int ch = 0;
for (i = 1; i <= 4; i++)
{
s++;
if (*s == '\0')
{
lex->token_terminator = s;
report_invalid_token(lex);
}
else if (*s >= '0' && *s <= '9')
ch = (ch * 16) + (*s - '0');
else if (*s >= 'a' && *s <= 'f')
ch = (ch * 16) + (*s - 'a') + 10;
else if (*s >= 'A' && *s <= 'F')
ch = (ch * 16) + (*s - 'A') + 10;
else
{
lex->token_terminator = s + pg_mblen(s);
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid input syntax for type json"),
errdetail("\"\\u\" must be followed by four hexadecimal digits."),
report_json_context(lex)));
}
}
}
else if (strchr("\"\\/bfnrt", *s) == NULL)
{
/* Not a valid string escape, so error out. */
lex->token_terminator = s + pg_mblen(s);
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid input syntax for type json"),
errdetail("Escape sequence \"\\%s\" is invalid.",
extract_mb_char(s)),
report_json_context(lex)));
}
}
}
/* Hooray, we found the end of the string! */
lex->token_terminator = s + 1;
}
