qemu/qobject/json-parser.c

592 lines
16 KiB
C
Raw Normal View History

/*
* JSON Parser
*
* Copyright IBM, Corp. 2009
*
* Authors:
* Anthony Liguori <aliguori@us.ibm.com>
*
* This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
* See the COPYING.LIB file in the top-level directory.
*
*/
#include "qemu/osdep.h"
#include "qemu/ctype.h"
#include "qemu/cutils.h"
#include "qemu/unicode.h"
2016-03-14 16:01:28 +08:00
#include "qapi/error.h"
#include "qapi/qmp/qbool.h"
#include "qapi/qmp/qdict.h"
#include "qapi/qmp/qlist.h"
#include "qapi/qmp/qnull.h"
#include "qapi/qmp/qnum.h"
#include "qapi/qmp/qstring.h"
#include "json-parser-int.h"
struct JSONToken {
JSONTokenType type;
int x;
int y;
char str[];
};
typedef struct JSONParserContext
{
Error *err;
JSONToken *current;
GQueue *buf;
va_list *ap;
} JSONParserContext;
#define BUG_ON(cond) assert(!(cond))
/**
* TODO
*
* 0) make errors meaningful again
* 1) add geometry information to tokens
* 3) should we return a parsed size?
* 4) deal with premature EOI
*/
static QObject *parse_value(JSONParserContext *ctxt);
/**
* Error handler
*/
static void GCC_FMT_ATTR(3, 4) parse_error(JSONParserContext *ctxt,
JSONToken *token, const char *msg, ...)
{
va_list ap;
char message[1024];
if (ctxt->err) {
return;
}
va_start(ap, msg);
vsnprintf(message, sizeof(message), msg, ap);
va_end(ap);
error_setg(&ctxt->err, "JSON parse error, %s", message);
}
static int cvt4hex(const char *s)
{
int cp, i;
cp = 0;
for (i = 0; i < 4; i++) {
if (!qemu_isxdigit(s[i])) {
return -1;
}
cp <<= 4;
if (s[i] >= '0' && s[i] <= '9') {
cp |= s[i] - '0';
} else if (s[i] >= 'a' && s[i] <= 'f') {
cp |= 10 + s[i] - 'a';
} else if (s[i] >= 'A' && s[i] <= 'F') {
cp |= 10 + s[i] - 'A';
} else {
return -1;
}
}
return cp;
}
/**
* parse_string(): Parse a JSON string
*
* From RFC 8259 "The JavaScript Object Notation (JSON) Data
* Interchange Format":
*
* char = unescaped /
* escape (
* %x22 / ; " quotation mark U+0022
* %x5C / ; \ reverse solidus U+005C
* %x2F / ; / solidus U+002F
* %x62 / ; b backspace U+0008
* %x66 / ; f form feed U+000C
* %x6E / ; n line feed U+000A
* %x72 / ; r carriage return U+000D
* %x74 / ; t tab U+0009
* %x75 4HEXDIG ) ; uXXXX U+XXXX
* escape = %x5C ; \
* quotation-mark = %x22 ; "
* unescaped = %x20-21 / %x23-5B / %x5D-10FFFF
*
* Extensions over RFC 8259:
* - Extra escape sequence in strings:
* 0x27 (apostrophe) is recognized after escape, too
* - Single-quoted strings:
* Like double-quoted strings, except they're delimited by %x27
* (apostrophe) instead of %x22 (quotation mark), and can't contain
* unescaped apostrophe, but can contain unescaped quotation mark.
*
* Note:
* - Encoding is modified UTF-8.
* - Invalid Unicode characters are rejected.
* - Control characters \x00..\x1F are rejected by the lexer.
*/
static QString *parse_string(JSONParserContext *ctxt, JSONToken *token)
{
const char *ptr = token->str;
QString *str;
char quote;
const char *beg;
int cp, trailing;
char *end;
ssize_t len;
char utf8_buf[5];
assert(*ptr == '"' || *ptr == '\'');
quote = *ptr++;
str = qstring_new();
while (*ptr != quote) {
assert(*ptr);
json: Improve safety of qobject_from_jsonf_nofail() & friends The JSON parser optionally supports interpolation. This is used to build QObjects by parsing string templates. The templates are C literals, so parse errors (such as invalid interpolation specifications) are actually programming errors. Consequently, the functions providing parsing with interpolation (qobject_from_jsonf_nofail(), qobject_from_vjsonf_nofail(), qdict_from_jsonf_nofail(), qdict_from_vjsonf_nofail()) pass &error_abort to the parser. However, there's another, more dangerous kind of programming error: since we use va_arg() to get the value to interpolate, behavior is undefined when the variable argument isn't consistent with the interpolation specification. The same problem exists with printf()-like functions, and the solution is to have the compiler check consistency. This is what GCC_FMT_ATTR() is about. To enable this type checking for interpolation as well, we carefully chose our interpolation specifications to match printf conversion specifications, and decorate functions parsing templates with GCC_FMT_ATTR(). Note that this only protects against undefined behavior due to type errors. It can't protect against use of invalid interpolation specifications that happen to be valid printf conversion specifications. However, there's still a gaping hole in the type checking: GCC recognizes '%' as start of printf conversion specification anywhere in the template, but the parser recognizes it only outside JSON strings. For instance, if someone were to pass a "{ '%s': %d }" template, GCC would require a char * and an int argument, but the parser would va_arg() only an int argument, resulting in undefined behavior. Avoid undefined behavior by catching the programming error at run time: have the parser recognize and reject '%' in JSON strings. Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-Id: <20180823164025.12553-57-armbru@redhat.com>
2018-08-24 00:40:23 +08:00
switch (*ptr) {
case '\\':
beg = ptr++;
switch (*ptr++) {
case '"':
qstring_append_chr(str, '"');
break;
case '\'':
qstring_append_chr(str, '\'');
break;
case '\\':
qstring_append_chr(str, '\\');
break;
case '/':
qstring_append_chr(str, '/');
break;
case 'b':
qstring_append_chr(str, '\b');
break;
case 'f':
qstring_append_chr(str, '\f');
break;
case 'n':
qstring_append_chr(str, '\n');
break;
case 'r':
qstring_append_chr(str, '\r');
break;
case 't':
qstring_append_chr(str, '\t');
break;
case 'u':
cp = cvt4hex(ptr);
ptr += 4;
/* handle surrogate pairs */
if (cp >= 0xD800 && cp <= 0xDBFF
&& ptr[0] == '\\' && ptr[1] == 'u') {
/* leading surrogate followed by \u */
cp = 0x10000 + ((cp & 0x3FF) << 10);
trailing = cvt4hex(ptr + 2);
if (trailing >= 0xDC00 && trailing <= 0xDFFF) {
/* followed by trailing surrogate */
cp |= trailing & 0x3FF;
ptr += 6;
} else {
cp = -1; /* invalid */
}
}
if (mod_utf8_encode(utf8_buf, sizeof(utf8_buf), cp) < 0) {
parse_error(ctxt, token,
"%.*s is not a valid Unicode character",
(int)(ptr - beg), beg);
goto out;
}
qstring_append(str, utf8_buf);
break;
default:
parse_error(ctxt, token, "invalid escape sequence in string");
goto out;
}
json: Improve safety of qobject_from_jsonf_nofail() & friends The JSON parser optionally supports interpolation. This is used to build QObjects by parsing string templates. The templates are C literals, so parse errors (such as invalid interpolation specifications) are actually programming errors. Consequently, the functions providing parsing with interpolation (qobject_from_jsonf_nofail(), qobject_from_vjsonf_nofail(), qdict_from_jsonf_nofail(), qdict_from_vjsonf_nofail()) pass &error_abort to the parser. However, there's another, more dangerous kind of programming error: since we use va_arg() to get the value to interpolate, behavior is undefined when the variable argument isn't consistent with the interpolation specification. The same problem exists with printf()-like functions, and the solution is to have the compiler check consistency. This is what GCC_FMT_ATTR() is about. To enable this type checking for interpolation as well, we carefully chose our interpolation specifications to match printf conversion specifications, and decorate functions parsing templates with GCC_FMT_ATTR(). Note that this only protects against undefined behavior due to type errors. It can't protect against use of invalid interpolation specifications that happen to be valid printf conversion specifications. However, there's still a gaping hole in the type checking: GCC recognizes '%' as start of printf conversion specification anywhere in the template, but the parser recognizes it only outside JSON strings. For instance, if someone were to pass a "{ '%s': %d }" template, GCC would require a char * and an int argument, but the parser would va_arg() only an int argument, resulting in undefined behavior. Avoid undefined behavior by catching the programming error at run time: have the parser recognize and reject '%' in JSON strings. Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-Id: <20180823164025.12553-57-armbru@redhat.com>
2018-08-24 00:40:23 +08:00
break;
case '%':
json: Fix % handling when not interpolating Commit 8bca4613 added support for %% in json strings when interpolating, but in doing so broke handling of % when not interpolating. When parse_string() is fed a string token containing '%', it skips the '%' regardless of ctxt->ap, i.e. even it's not interpolating. If the '%' is the string's last character, it fails an assertion. Else, it "merely" swallows the '%'. Fix parse_string() to handle '%' specially only when interpolating. To gauge the bug's impact, let's review non-interpolating users of this parser, i.e. code passing NULL context to json_message_parser_init(): * tests/check-qjson.c, tests/test-qobject-input-visitor.c, tests/test-visitor-serialization.c Plenty of tests, but we still failed to cover the buggy case. * monitor.c: QMP input * qga/main.c: QGA input * qobject_from_json(): - qobject-input-visitor.c: JSON command line option arguments of -display and -blockdev Reproducer: -blockdev '{"%"}' - block.c: JSON pseudo-filenames starting with "json:" Reproducer: https://bugzilla.redhat.com/show_bug.cgi?id=1668244#c3 - block/rbd.c: JSON key pairs Pseudo-filenames starting with "rbd:". Command line, QMP and QGA input are trusted. Filenames are trusted when they come from command line, QMP or HMP. They are untrusted when they come from from image file headers. Example: QCOW2 backing file name. Note that this is *not* the security boundary between host and guest. It's the boundary between host and an image file from an untrusted source. Neither failing an assertion nor skipping a character in a filename of your choice looks exploitable. Note that we don't support compiling with NDEBUG. Fixes: 8bca4613e6cddd948895b8db3def05950463495b Cc: qemu-stable@nongnu.org Signed-off-by: Christophe Fergeau <cfergeau@redhat.com> Message-Id: <20190102140535.11512-1-cfergeau@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Tested-by: Richard W.M. Jones <rjones@redhat.com> [Commit message extended to discuss impact] Signed-off-by: Markus Armbruster <armbru@redhat.com>
2019-01-02 22:05:35 +08:00
if (ctxt->ap) {
if (ptr[1] != '%') {
parse_error(ctxt, token, "can't interpolate into string");
goto out;
}
ptr++;
json: Improve safety of qobject_from_jsonf_nofail() & friends The JSON parser optionally supports interpolation. This is used to build QObjects by parsing string templates. The templates are C literals, so parse errors (such as invalid interpolation specifications) are actually programming errors. Consequently, the functions providing parsing with interpolation (qobject_from_jsonf_nofail(), qobject_from_vjsonf_nofail(), qdict_from_jsonf_nofail(), qdict_from_vjsonf_nofail()) pass &error_abort to the parser. However, there's another, more dangerous kind of programming error: since we use va_arg() to get the value to interpolate, behavior is undefined when the variable argument isn't consistent with the interpolation specification. The same problem exists with printf()-like functions, and the solution is to have the compiler check consistency. This is what GCC_FMT_ATTR() is about. To enable this type checking for interpolation as well, we carefully chose our interpolation specifications to match printf conversion specifications, and decorate functions parsing templates with GCC_FMT_ATTR(). Note that this only protects against undefined behavior due to type errors. It can't protect against use of invalid interpolation specifications that happen to be valid printf conversion specifications. However, there's still a gaping hole in the type checking: GCC recognizes '%' as start of printf conversion specification anywhere in the template, but the parser recognizes it only outside JSON strings. For instance, if someone were to pass a "{ '%s': %d }" template, GCC would require a char * and an int argument, but the parser would va_arg() only an int argument, resulting in undefined behavior. Avoid undefined behavior by catching the programming error at run time: have the parser recognize and reject '%' in JSON strings. Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-Id: <20180823164025.12553-57-armbru@redhat.com>
2018-08-24 00:40:23 +08:00
}
/* fall through */
default:
cp = mod_utf8_codepoint(ptr, 6, &end);
if (cp < 0) {
parse_error(ctxt, token, "invalid UTF-8 sequence in string");
goto out;
}
ptr = end;
len = mod_utf8_encode(utf8_buf, sizeof(utf8_buf), cp);
assert(len >= 0);
qstring_append(str, utf8_buf);
}
}
return str;
out:
qobject_unref(str);
return NULL;
}
/* Note: the token object returned by parser_context_peek_token or
* parser_context_pop_token is deleted as soon as parser_context_pop_token
* is called again.
*/
static JSONToken *parser_context_pop_token(JSONParserContext *ctxt)
{
g_free(ctxt->current);
ctxt->current = g_queue_pop_head(ctxt->buf);
return ctxt->current;
}
static JSONToken *parser_context_peek_token(JSONParserContext *ctxt)
{
return g_queue_peek_head(ctxt->buf);
}
/**
* Parsing rules
*/
static int parse_pair(JSONParserContext *ctxt, QDict *dict)
{
json: Fix a memleak in parse_pair() In qobject_type(), NULL is returned when the 'QObject' returned from parse_value() is not of QString type, and this 'QObject' memory will leaked. So we need to first cache the 'QObject' returned from parse_value(), and finally free 'QObject' memory at the end of the function. Also, we add a testcast about invalid dict key. The memleak stack is as follows: Direct leak of 32 byte(s) in 1 object(s) allocated from: #0 0xfffe4b3c34fb in __interceptor_malloc (/lib64/libasan.so.4+0xd34fb) #1 0xfffe4ae48aa3 in g_malloc (/lib64/libglib-2.0.so.0+0x58aa3) #2 0xaaab3557d9f7 in qnum_from_int qemu/qobject/qnum.c:25 #3 0xaaab35584d23 in parse_literal qemu/qobject/json-parser.c:511 #4 0xaaab35584d23 in parse_value qemu/qobject/json-parser.c:554 #5 0xaaab35583d77 in parse_pair qemu/qobject/json-parser.c:270 #6 0xaaab355845db in parse_object qemu/qobject/json-parser.c:327 #7 0xaaab355845db in parse_value qemu/qobject/json-parser.c:546 #8 0xaaab35585b1b in json_parser_parse qemu/qobject/json-parser.c:580 #9 0xaaab35583703 in json_message_process_token qemu/qobject/json-streamer.c:92 #10 0xaaab355ddccf in json_lexer_feed_char qemu/qobject/json-lexer.c:313 #11 0xaaab355de0eb in json_lexer_feed qemu/qobject/json-lexer.c:350 #12 0xaaab354aff67 in tcp_chr_read qemu/chardev/char-socket.c:525 #13 0xfffe4ae429db in g_main_context_dispatch (/lib64/libglib-2.0.so.0+0x529db) #14 0xfffe4ae42d8f (/lib64/libglib-2.0.so.0+0x52d8f) #15 0xfffe4ae430df in g_main_loop_run (/lib64/libglib-2.0.so.0+0x530df) #16 0xaaab34d70bff in iothread_run qemu/iothread.c:82 #17 0xaaab3559d71b in qemu_thread_start qemu/util/qemu-thread-posix.c:519 Fixes: 532fb5328473 ("qapi: Make more of qobject_to()") Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: Alex Chen <alex.chen@huawei.com> Signed-off-by: Chen Qun <kuhn.chenqun@huawei.com> Signed-off-by: Markus Armbruster <armbru@redhat.com> Message-Id: <20201113145525.85151-1-alex.chen@huawei.com> [Commit message tweaked]
2020-11-13 22:55:25 +08:00
QObject *key_obj = NULL;
QString *key;
QObject *value;
JSONToken *peek, *token;
peek = parser_context_peek_token(ctxt);
if (peek == NULL) {
parse_error(ctxt, NULL, "premature EOI");
goto out;
}
json: Fix a memleak in parse_pair() In qobject_type(), NULL is returned when the 'QObject' returned from parse_value() is not of QString type, and this 'QObject' memory will leaked. So we need to first cache the 'QObject' returned from parse_value(), and finally free 'QObject' memory at the end of the function. Also, we add a testcast about invalid dict key. The memleak stack is as follows: Direct leak of 32 byte(s) in 1 object(s) allocated from: #0 0xfffe4b3c34fb in __interceptor_malloc (/lib64/libasan.so.4+0xd34fb) #1 0xfffe4ae48aa3 in g_malloc (/lib64/libglib-2.0.so.0+0x58aa3) #2 0xaaab3557d9f7 in qnum_from_int qemu/qobject/qnum.c:25 #3 0xaaab35584d23 in parse_literal qemu/qobject/json-parser.c:511 #4 0xaaab35584d23 in parse_value qemu/qobject/json-parser.c:554 #5 0xaaab35583d77 in parse_pair qemu/qobject/json-parser.c:270 #6 0xaaab355845db in parse_object qemu/qobject/json-parser.c:327 #7 0xaaab355845db in parse_value qemu/qobject/json-parser.c:546 #8 0xaaab35585b1b in json_parser_parse qemu/qobject/json-parser.c:580 #9 0xaaab35583703 in json_message_process_token qemu/qobject/json-streamer.c:92 #10 0xaaab355ddccf in json_lexer_feed_char qemu/qobject/json-lexer.c:313 #11 0xaaab355de0eb in json_lexer_feed qemu/qobject/json-lexer.c:350 #12 0xaaab354aff67 in tcp_chr_read qemu/chardev/char-socket.c:525 #13 0xfffe4ae429db in g_main_context_dispatch (/lib64/libglib-2.0.so.0+0x529db) #14 0xfffe4ae42d8f (/lib64/libglib-2.0.so.0+0x52d8f) #15 0xfffe4ae430df in g_main_loop_run (/lib64/libglib-2.0.so.0+0x530df) #16 0xaaab34d70bff in iothread_run qemu/iothread.c:82 #17 0xaaab3559d71b in qemu_thread_start qemu/util/qemu-thread-posix.c:519 Fixes: 532fb5328473 ("qapi: Make more of qobject_to()") Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: Alex Chen <alex.chen@huawei.com> Signed-off-by: Chen Qun <kuhn.chenqun@huawei.com> Signed-off-by: Markus Armbruster <armbru@redhat.com> Message-Id: <20201113145525.85151-1-alex.chen@huawei.com> [Commit message tweaked]
2020-11-13 22:55:25 +08:00
key_obj = parse_value(ctxt);
key = qobject_to(QString, key_obj);
if (!key) {
parse_error(ctxt, peek, "key is not a string in object");
goto out;
}
token = parser_context_pop_token(ctxt);
if (token == NULL) {
parse_error(ctxt, NULL, "premature EOI");
goto out;
}
if (token->type != JSON_COLON) {
parse_error(ctxt, token, "missing : in object pair");
goto out;
}
value = parse_value(ctxt);
if (value == NULL) {
parse_error(ctxt, token, "Missing value in dict");
goto out;
}
if (qdict_haskey(dict, qstring_get_str(key))) {
parse_error(ctxt, token, "duplicate key");
goto out;
}
qdict_put_obj(dict, qstring_get_str(key), value);
json: Fix a memleak in parse_pair() In qobject_type(), NULL is returned when the 'QObject' returned from parse_value() is not of QString type, and this 'QObject' memory will leaked. So we need to first cache the 'QObject' returned from parse_value(), and finally free 'QObject' memory at the end of the function. Also, we add a testcast about invalid dict key. The memleak stack is as follows: Direct leak of 32 byte(s) in 1 object(s) allocated from: #0 0xfffe4b3c34fb in __interceptor_malloc (/lib64/libasan.so.4+0xd34fb) #1 0xfffe4ae48aa3 in g_malloc (/lib64/libglib-2.0.so.0+0x58aa3) #2 0xaaab3557d9f7 in qnum_from_int qemu/qobject/qnum.c:25 #3 0xaaab35584d23 in parse_literal qemu/qobject/json-parser.c:511 #4 0xaaab35584d23 in parse_value qemu/qobject/json-parser.c:554 #5 0xaaab35583d77 in parse_pair qemu/qobject/json-parser.c:270 #6 0xaaab355845db in parse_object qemu/qobject/json-parser.c:327 #7 0xaaab355845db in parse_value qemu/qobject/json-parser.c:546 #8 0xaaab35585b1b in json_parser_parse qemu/qobject/json-parser.c:580 #9 0xaaab35583703 in json_message_process_token qemu/qobject/json-streamer.c:92 #10 0xaaab355ddccf in json_lexer_feed_char qemu/qobject/json-lexer.c:313 #11 0xaaab355de0eb in json_lexer_feed qemu/qobject/json-lexer.c:350 #12 0xaaab354aff67 in tcp_chr_read qemu/chardev/char-socket.c:525 #13 0xfffe4ae429db in g_main_context_dispatch (/lib64/libglib-2.0.so.0+0x529db) #14 0xfffe4ae42d8f (/lib64/libglib-2.0.so.0+0x52d8f) #15 0xfffe4ae430df in g_main_loop_run (/lib64/libglib-2.0.so.0+0x530df) #16 0xaaab34d70bff in iothread_run qemu/iothread.c:82 #17 0xaaab3559d71b in qemu_thread_start qemu/util/qemu-thread-posix.c:519 Fixes: 532fb5328473 ("qapi: Make more of qobject_to()") Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: Alex Chen <alex.chen@huawei.com> Signed-off-by: Chen Qun <kuhn.chenqun@huawei.com> Signed-off-by: Markus Armbruster <armbru@redhat.com> Message-Id: <20201113145525.85151-1-alex.chen@huawei.com> [Commit message tweaked]
2020-11-13 22:55:25 +08:00
qobject_unref(key_obj);
return 0;
out:
json: Fix a memleak in parse_pair() In qobject_type(), NULL is returned when the 'QObject' returned from parse_value() is not of QString type, and this 'QObject' memory will leaked. So we need to first cache the 'QObject' returned from parse_value(), and finally free 'QObject' memory at the end of the function. Also, we add a testcast about invalid dict key. The memleak stack is as follows: Direct leak of 32 byte(s) in 1 object(s) allocated from: #0 0xfffe4b3c34fb in __interceptor_malloc (/lib64/libasan.so.4+0xd34fb) #1 0xfffe4ae48aa3 in g_malloc (/lib64/libglib-2.0.so.0+0x58aa3) #2 0xaaab3557d9f7 in qnum_from_int qemu/qobject/qnum.c:25 #3 0xaaab35584d23 in parse_literal qemu/qobject/json-parser.c:511 #4 0xaaab35584d23 in parse_value qemu/qobject/json-parser.c:554 #5 0xaaab35583d77 in parse_pair qemu/qobject/json-parser.c:270 #6 0xaaab355845db in parse_object qemu/qobject/json-parser.c:327 #7 0xaaab355845db in parse_value qemu/qobject/json-parser.c:546 #8 0xaaab35585b1b in json_parser_parse qemu/qobject/json-parser.c:580 #9 0xaaab35583703 in json_message_process_token qemu/qobject/json-streamer.c:92 #10 0xaaab355ddccf in json_lexer_feed_char qemu/qobject/json-lexer.c:313 #11 0xaaab355de0eb in json_lexer_feed qemu/qobject/json-lexer.c:350 #12 0xaaab354aff67 in tcp_chr_read qemu/chardev/char-socket.c:525 #13 0xfffe4ae429db in g_main_context_dispatch (/lib64/libglib-2.0.so.0+0x529db) #14 0xfffe4ae42d8f (/lib64/libglib-2.0.so.0+0x52d8f) #15 0xfffe4ae430df in g_main_loop_run (/lib64/libglib-2.0.so.0+0x530df) #16 0xaaab34d70bff in iothread_run qemu/iothread.c:82 #17 0xaaab3559d71b in qemu_thread_start qemu/util/qemu-thread-posix.c:519 Fixes: 532fb5328473 ("qapi: Make more of qobject_to()") Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: Alex Chen <alex.chen@huawei.com> Signed-off-by: Chen Qun <kuhn.chenqun@huawei.com> Signed-off-by: Markus Armbruster <armbru@redhat.com> Message-Id: <20201113145525.85151-1-alex.chen@huawei.com> [Commit message tweaked]
2020-11-13 22:55:25 +08:00
qobject_unref(key_obj);
return -1;
}
static QObject *parse_object(JSONParserContext *ctxt)
{
QDict *dict = NULL;
JSONToken *token, *peek;
token = parser_context_pop_token(ctxt);
assert(token && token->type == JSON_LCURLY);
dict = qdict_new();
peek = parser_context_peek_token(ctxt);
if (peek == NULL) {
parse_error(ctxt, NULL, "premature EOI");
goto out;
}
if (peek->type != JSON_RCURLY) {
if (parse_pair(ctxt, dict) == -1) {
goto out;
}
token = parser_context_pop_token(ctxt);
if (token == NULL) {
parse_error(ctxt, NULL, "premature EOI");
goto out;
}
while (token->type != JSON_RCURLY) {
if (token->type != JSON_COMMA) {
parse_error(ctxt, token, "expected separator in dict");
goto out;
}
if (parse_pair(ctxt, dict) == -1) {
goto out;
}
token = parser_context_pop_token(ctxt);
if (token == NULL) {
parse_error(ctxt, NULL, "premature EOI");
goto out;
}
}
} else {
(void)parser_context_pop_token(ctxt);
}
return QOBJECT(dict);
out:
qobject_unref(dict);
return NULL;
}
static QObject *parse_array(JSONParserContext *ctxt)
{
QList *list = NULL;
JSONToken *token, *peek;
token = parser_context_pop_token(ctxt);
assert(token && token->type == JSON_LSQUARE);
list = qlist_new();
peek = parser_context_peek_token(ctxt);
if (peek == NULL) {
parse_error(ctxt, NULL, "premature EOI");
goto out;
}
if (peek->type != JSON_RSQUARE) {
QObject *obj;
obj = parse_value(ctxt);
if (obj == NULL) {
parse_error(ctxt, token, "expecting value");
goto out;
}
qlist_append_obj(list, obj);
token = parser_context_pop_token(ctxt);
if (token == NULL) {
parse_error(ctxt, NULL, "premature EOI");
goto out;
}
while (token->type != JSON_RSQUARE) {
if (token->type != JSON_COMMA) {
parse_error(ctxt, token, "expected separator in list");
goto out;
}
obj = parse_value(ctxt);
if (obj == NULL) {
parse_error(ctxt, token, "expecting value");
goto out;
}
qlist_append_obj(list, obj);
token = parser_context_pop_token(ctxt);
if (token == NULL) {
parse_error(ctxt, NULL, "premature EOI");
goto out;
}
}
} else {
(void)parser_context_pop_token(ctxt);
}
return QOBJECT(list);
out:
qobject_unref(list);
return NULL;
}
static QObject *parse_keyword(JSONParserContext *ctxt)
{
JSONToken *token;
token = parser_context_pop_token(ctxt);
assert(token && token->type == JSON_KEYWORD);
if (!strcmp(token->str, "true")) {
return QOBJECT(qbool_from_bool(true));
} else if (!strcmp(token->str, "false")) {
return QOBJECT(qbool_from_bool(false));
} else if (!strcmp(token->str, "null")) {
return QOBJECT(qnull());
}
parse_error(ctxt, token, "invalid keyword '%s'", token->str);
return NULL;
}
static QObject *parse_interpolation(JSONParserContext *ctxt)
{
JSONToken *token;
token = parser_context_pop_token(ctxt);
assert(token && token->type == JSON_INTERP);
if (!strcmp(token->str, "%p")) {
return va_arg(*ctxt->ap, QObject *);
} else if (!strcmp(token->str, "%i")) {
return QOBJECT(qbool_from_bool(va_arg(*ctxt->ap, int)));
} else if (!strcmp(token->str, "%d")) {
return QOBJECT(qnum_from_int(va_arg(*ctxt->ap, int)));
} else if (!strcmp(token->str, "%ld")) {
return QOBJECT(qnum_from_int(va_arg(*ctxt->ap, long)));
} else if (!strcmp(token->str, "%lld")) {
return QOBJECT(qnum_from_int(va_arg(*ctxt->ap, long long)));
} else if (!strcmp(token->str, "%" PRId64)) {
return QOBJECT(qnum_from_int(va_arg(*ctxt->ap, int64_t)));
} else if (!strcmp(token->str, "%u")) {
return QOBJECT(qnum_from_uint(va_arg(*ctxt->ap, unsigned int)));
} else if (!strcmp(token->str, "%lu")) {
return QOBJECT(qnum_from_uint(va_arg(*ctxt->ap, unsigned long)));
} else if (!strcmp(token->str, "%llu")) {
return QOBJECT(qnum_from_uint(va_arg(*ctxt->ap, unsigned long long)));
} else if (!strcmp(token->str, "%" PRIu64)) {
return QOBJECT(qnum_from_uint(va_arg(*ctxt->ap, uint64_t)));
} else if (!strcmp(token->str, "%s")) {
return QOBJECT(qstring_from_str(va_arg(*ctxt->ap, const char *)));
} else if (!strcmp(token->str, "%f")) {
return QOBJECT(qnum_from_double(va_arg(*ctxt->ap, double)));
}
parse_error(ctxt, token, "invalid interpolation '%s'", token->str);
return NULL;
}
static QObject *parse_literal(JSONParserContext *ctxt)
{
JSONToken *token;
token = parser_context_pop_token(ctxt);
assert(token);
switch (token->type) {
case JSON_STRING:
return QOBJECT(parse_string(ctxt, token));
case JSON_INTEGER: {
/*
* Represent JSON_INTEGER as QNUM_I64 if possible, else as
* QNUM_U64, else as QNUM_DOUBLE. Note that qemu_strtoi64()
* and qemu_strtou64() fail with ERANGE when it's not
* possible.
*
* qnum_get_int() will then work for any signed 64-bit
* JSON_INTEGER, qnum_get_uint() for any unsigned 64-bit
* integer, and qnum_get_double() both for any JSON_INTEGER
* and any JSON_FLOAT (with precision loss for integers beyond
* 53 bits)
*/
int ret;
int64_t value;
uint64_t uvalue;
ret = qemu_strtoi64(token->str, NULL, 10, &value);
if (!ret) {
return QOBJECT(qnum_from_int(value));
}
assert(ret == -ERANGE);
if (token->str[0] != '-') {
ret = qemu_strtou64(token->str, NULL, 10, &uvalue);
if (!ret) {
return QOBJECT(qnum_from_uint(uvalue));
}
assert(ret == -ERANGE);
}
}
/* fall through to JSON_FLOAT */
case JSON_FLOAT:
/* FIXME dependent on locale; a pervasive issue in QEMU */
/* FIXME our lexer matches RFC 8259 in forbidding Inf or NaN,
* but those might be useful extensions beyond JSON */
return QOBJECT(qnum_from_double(strtod(token->str, NULL)));
default:
abort();
}
}
static QObject *parse_value(JSONParserContext *ctxt)
{
JSONToken *token;
token = parser_context_peek_token(ctxt);
if (token == NULL) {
parse_error(ctxt, NULL, "premature EOI");
return NULL;
}
switch (token->type) {
case JSON_LCURLY:
return parse_object(ctxt);
case JSON_LSQUARE:
return parse_array(ctxt);
case JSON_INTERP:
return parse_interpolation(ctxt);
case JSON_INTEGER:
case JSON_FLOAT:
case JSON_STRING:
return parse_literal(ctxt);
case JSON_KEYWORD:
return parse_keyword(ctxt);
default:
parse_error(ctxt, token, "expecting value");
return NULL;
}
}
JSONToken *json_token(JSONTokenType type, int x, int y, GString *tokstr)
{
JSONToken *token = g_malloc(sizeof(JSONToken) + tokstr->len + 1);
token->type = type;
memcpy(token->str, tokstr->str, tokstr->len);
token->str[tokstr->len] = 0;
token->x = x;
token->y = y;
return token;
}
json: Redesign the callback to consume JSON values The classical way to structure parser and lexer is to have the client call the parser to get an abstract syntax tree, the parser call the lexer to get the next token, and the lexer call some function to get input characters. Another way to structure them would be to have the client feed characters to the lexer, the lexer feed tokens to the parser, and the parser feed abstract syntax trees to some callback provided by the client. This way is more easily integrated into an event loop that dispatches input characters as they arrive. Our JSON parser is kind of between the two. The lexer feeds tokens to a "streamer" instead of a real parser. The streamer accumulates tokens until it got the sequence of tokens that comprise a single JSON value (it counts curly braces and square brackets to decide). It feeds those token sequences to a callback provided by the client. The callback passes each token sequence to the parser, and gets back an abstract syntax tree. I figure it was done that way to make a straightforward recursive descent parser possible. "Get next token" becomes "pop the first token off the token sequence". Drawback: we need to store a complete token sequence. Each token eats 13 + input characters + malloc overhead bytes. Observations: 1. This is not the only way to use recursive descent. If we replaced "get next token" by a coroutine yield, we could do without a streamer. 2. The lexer reports errors by passing a JSON_ERROR token to the streamer. This communicates the offending input characters and their location, but no more. 3. The streamer reports errors by passing a null token sequence to the callback. The (already poor) lexical error information is thrown away. 4. Having the callback receive a token sequence duplicates the code to convert token sequence to abstract syntax tree in every callback. 5. Known bug: the streamer silently drops incomplete token sequences. This commit rectifies 4. by lifting the call of the parser from the callbacks into the streamer. Later commits will address 3. and 5. The lifting removes a bug from qjson.c's parse_json(): it passed a pointer to a non-null Error * in certain cases, as demonstrated by check-qjson.c. json_parser_parse() is now unused. It's a stupid wrapper around json_parser_parse_err(). Drop it, and rename json_parser_parse_err() to json_parser_parse(). Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-Id: <20180823164025.12553-35-armbru@redhat.com>
2018-08-24 00:40:01 +08:00
QObject *json_parser_parse(GQueue *tokens, va_list *ap, Error **errp)
{
JSONParserContext ctxt = { .buf = tokens, .ap = ap };
QObject *result;
result = parse_value(&ctxt);
assert(ctxt.err || g_queue_is_empty(ctxt.buf));
error_propagate(errp, ctxt.err);
while (!g_queue_is_empty(ctxt.buf)) {
parser_context_pop_token(&ctxt);
}
g_free(ctxt.current);
return result;
}