redis-cli: Better --json Unicode support and --quoted-json (#10286)

Normally, `redis-cli` escapes non-printable data received from Redis, using a custom scheme (which is also used to handle quoted input). When using `--json` this is not desired as it is not compatible with RFC 7159, which specifies JSON strings are assumed to be Unicode and how they should be escaped.

This commit changes `--json` to follow RFC 7159, which means that properly encoded Unicode strings in Redis will result with a valid Unicode JSON.

However, this introduces a new problem with `--json` and data that is not valid Unicode (e.g., random binary data, text that follows other encoding, etc.). To address this, we add `--quoted-json` which produces JSON strings that follow the original redis-cli quoting scheme.

For example, a value that consists of only null (0x00) bytes will show up as:
* `"\u0000\u0000\u0000"` when using `--json`
* `"\\x00\\x00\\x00"` when using `--quoted-json`
This commit is contained in:
Yuta Hongo 2022-03-06 04:25:52 +09:00 committed by GitHub
parent af6d5c5932
commit e3ef73dc2a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 105 additions and 17 deletions

View File

@ -371,3 +371,28 @@ void freeCliConnInfo(cliConnInfo connInfo){
if (connInfo.auth) sdsfree(connInfo.auth);
if (connInfo.user) sdsfree(connInfo.user);
}
/*
* Escape a Unicode string for JSON output (--json), following RFC 7159:
* https://datatracker.ietf.org/doc/html/rfc7159#section-7
*/
sds escapeJsonString(sds s, const char *p, size_t len) {
s = sdscatlen(s,"\"",1);
while(len--) {
switch(*p) {
case '\\':
case '"':
s = sdscatprintf(s,"\\%c",*p);
break;
case '\n': s = sdscatlen(s,"\\n",2); break;
case '\f': s = sdscatlen(s,"\\f",2); break;
case '\r': s = sdscatlen(s,"\\r",2); break;
case '\t': s = sdscatlen(s,"\\t",2); break;
case '\b': s = sdscatlen(s,"\\b",2); break;
default:
s = sdscatprintf(s,(*p >= 0 && *p <= 0x1f) ? "\\u%04x" : "%c",*p);
}
p++;
}
return sdscatlen(s,"\"",1);
}

View File

@ -48,4 +48,7 @@ sds unquoteCString(char *str);
void parseRedisUri(const char *uri, const char* tool_name, cliConnInfo *connInfo, int *tls_flag);
void freeCliConnInfo(cliConnInfo connInfo);
sds escapeJsonString(sds s, const char *p, size_t len);
#endif /* __CLICOMMON_H */

View File

@ -70,6 +70,7 @@
#define OUTPUT_RAW 1
#define OUTPUT_CSV 2
#define OUTPUT_JSON 3
#define OUTPUT_QUOTED_JSON 4
#define REDIS_CLI_KEEPALIVE_INTERVAL 15 /* seconds */
#define REDIS_CLI_DEFAULT_PIPE_TIMEOUT 30 /* seconds */
#define REDIS_CLI_HISTFILE_ENV "REDISCLI_HISTFILE"
@ -1486,16 +1487,39 @@ static sds cliFormatReplyCSV(redisReply *r) {
return out;
}
static sds cliFormatReplyJson(sds out, redisReply *r) {
/* Append specified buffer to out and return it, using required JSON output
* mode. */
static sds jsonStringOutput(sds out, const char *p, int len, int mode) {
if (mode == OUTPUT_JSON) {
return escapeJsonString(out, p, len);
} else if (mode == OUTPUT_QUOTED_JSON) {
/* Need to double-quote backslashes */
sds tmp = sdscatrepr(sdsempty(), p, len);
int tmplen = sdslen(tmp);
char *n = tmp;
while (tmplen--) {
if (*n == '\\') out = sdscatlen(out, "\\\\", 2);
else out = sdscatlen(out, n, 1);
n++;
}
sdsfree(tmp);
return out;
} else {
assert(0);
}
}
static sds cliFormatReplyJson(sds out, redisReply *r, int mode) {
unsigned int i;
switch (r->type) {
case REDIS_REPLY_ERROR:
out = sdscat(out,"error:");
out = sdscatrepr(out,r->str,strlen(r->str));
out = jsonStringOutput(out,r->str,strlen(r->str),mode);
break;
case REDIS_REPLY_STATUS:
out = sdscatrepr(out,r->str,r->len);
out = jsonStringOutput(out,r->str,r->len,mode);
break;
case REDIS_REPLY_INTEGER:
out = sdscatprintf(out,"%lld",r->integer);
@ -1505,7 +1529,7 @@ static sds cliFormatReplyJson(sds out, redisReply *r) {
break;
case REDIS_REPLY_STRING:
case REDIS_REPLY_VERB:
out = sdscatrepr(out,r->str,r->len);
out = jsonStringOutput(out,r->str,r->len,mode);
break;
case REDIS_REPLY_NIL:
out = sdscat(out,"null");
@ -1518,7 +1542,7 @@ static sds cliFormatReplyJson(sds out, redisReply *r) {
case REDIS_REPLY_PUSH:
out = sdscat(out,"[");
for (i = 0; i < r->elements; i++ ) {
out = cliFormatReplyJson(out, r->element[i]);
out = cliFormatReplyJson(out,r->element[i],mode);
if (i != r->elements-1) out = sdscat(out,",");
}
out = sdscat(out,"]");
@ -1527,20 +1551,25 @@ static sds cliFormatReplyJson(sds out, redisReply *r) {
out = sdscat(out,"{");
for (i = 0; i < r->elements; i += 2) {
redisReply *key = r->element[i];
if (key->type == REDIS_REPLY_STATUS ||
if (key->type == REDIS_REPLY_ERROR ||
key->type == REDIS_REPLY_STATUS ||
key->type == REDIS_REPLY_STRING ||
key->type == REDIS_REPLY_VERB) {
out = cliFormatReplyJson(out, key);
key->type == REDIS_REPLY_VERB)
{
out = cliFormatReplyJson(out,key,mode);
} else {
/* According to JSON spec, JSON map keys must be strings, */
/* and in RESP3, they can be other types. */
sds tmp = cliFormatReplyJson(sdsempty(), key);
out = sdscatrepr(out,tmp,sdslen(tmp));
sdsfree(tmp);
/* According to JSON spec, JSON map keys must be strings,
* and in RESP3, they can be other types.
* The first one(cliFormatReplyJson) is to convert non string type to string
* The Second one(escapeJsonString) is to escape the converted string */
sds keystr = cliFormatReplyJson(sdsempty(),key,mode);
if (keystr[0] == '"') out = sdscatsds(out,keystr);
else out = sdscatfmt(out,"\"%S\"",keystr);
sdsfree(keystr);
}
out = sdscat(out,":");
out = cliFormatReplyJson(out, r->element[i+1]);
out = cliFormatReplyJson(out,r->element[i+1],mode);
if (i != r->elements-2) out = sdscat(out,",");
}
out = sdscat(out,"}");
@ -1566,8 +1595,8 @@ static sds cliFormatReply(redisReply *reply, int mode, int verbatim) {
} else if (mode == OUTPUT_CSV) {
out = cliFormatReplyCSV(reply);
out = sdscatlen(out, "\n", 1);
} else if (mode == OUTPUT_JSON) {
out = cliFormatReplyJson(sdsempty(), reply);
} else if (mode == OUTPUT_JSON || mode == OUTPUT_QUOTED_JSON) {
out = cliFormatReplyJson(sdsempty(), reply, mode);
out = sdscatlen(out, "\n", 1);
} else {
fprintf(stderr, "Error: Unknown output encoding %d\n", mode);
@ -1953,11 +1982,17 @@ static int parseOptions(int argc, char **argv) {
} else if (!strcmp(argv[i],"--csv")) {
config.output = OUTPUT_CSV;
} else if (!strcmp(argv[i],"--json")) {
/* Not overwrite explicit value by -3*/
/* Not overwrite explicit value by -3 */
if (config.resp3 == 0) {
config.resp3 = 2;
}
config.output = OUTPUT_JSON;
} else if (!strcmp(argv[i],"--quoted-json")) {
/* Not overwrite explicit value by -3*/
if (config.resp3 == 0) {
config.resp3 = 2;
}
config.output = OUTPUT_QUOTED_JSON;
} else if (!strcmp(argv[i],"--latency")) {
config.latency_mode = 1;
} else if (!strcmp(argv[i],"--latency-dist")) {
@ -2289,6 +2324,7 @@ static void usage(int err) {
" --quoted-input Force input to be handled as quoted strings.\n"
" --csv Output in CSV format.\n"
" --json Output in JSON format (default RESP3, use -2 if you want to use with RESP2).\n"
" --quoted-json Same as --json, but produce ASCII-safe quoted strings, not Unicode.\n"
" --show-pushes <yn> Whether to print RESP3 PUSH messages. Enabled by default when\n"
" STDOUT is a tty but can be overridden with --show-pushes no.\n"
" --stat Print rolling stats about server: mem, clients, ...\n",version);

View File

@ -228,6 +228,30 @@ start_server {tags {"cli"}} {
file delete $tmpfile
}
test_tty_cli "Escape character in JSON mode" {
# reverse solidus
r hset solidus \/ \/
assert_equal \/ \/ [run_cli hgetall solidus]
set escaped_reverse_solidus \"\\"
assert_equal $escaped_reverse_solidus $escaped_reverse_solidus [run_cli --json hgetall \/]
# non printable (0xF0 in ISO-8859-1, not UTF-8(0xC3 0xB0))
set eth "\xf0\x65"
r hset eth test $eth
assert_equal \"\\xf0e\" [run_cli hget eth test]
assert_equal \"\xf0e\" [run_cli --json hget eth test]
assert_equal \"\\\\xf0e\" [run_cli --quoted-json hget eth test]
# control characters
r hset control test "Hello\x00\x01\x02\x03World"
assert_equal \"Hello\\u0000\\u0001\\u0002\\u0003World" [run_cli --json hget control test]
# non-string keys
r hset numkey 1 One
assert_equal \{\"1\":\"One\"\} [run_cli --json hgetall numkey]
# non-string, non-printable keys
r hset npkey "K\x00\x01ey" "V\x00\x01alue"
assert_equal \{\"K\\u0000\\u0001ey\":\"V\\u0000\\u0001alue\"\} [run_cli --json hgetall npkey]
assert_equal \{\"K\\\\x00\\\\x01ey\":\"V\\\\x00\\\\x01alue\"\} [run_cli --quoted-json hgetall npkey]
}
test_nontty_cli "Status reply" {
assert_equal "OK" [run_cli set key bar]
assert_equal "bar" [r get key]