summaryrefslogtreecommitdiff
path: root/src
diff options
context:
space:
mode:
Diffstat (limited to 'src')
-rw-r--r--src/bin/psql/common.c28
-rw-r--r--src/bin/psql/psqlscanslash.l4
-rw-r--r--src/bin/psql/stringutils.c8
-rw-r--r--src/bin/psql/tab-complete.c4
-rw-r--r--src/bin/scripts/common.c4
-rw-r--r--src/common/jsonapi.c6
-rw-r--r--src/common/wchar.c15
-rw-r--r--src/fe_utils/print.c3
-rw-r--r--src/include/mb/pg_wchar.h1
-rw-r--r--src/interfaces/libpq/fe-print.c3
-rw-r--r--src/interfaces/libpq/fe-protocol3.c6
11 files changed, 57 insertions, 25 deletions
diff --git a/src/bin/psql/common.c b/src/bin/psql/common.c
index 10314288499..94d5d60f879 100644
--- a/src/bin/psql/common.c
+++ b/src/bin/psql/common.c
@@ -29,6 +29,8 @@
#include "portability/instr_time.h"
#include "settings.h"
+#define PQmblenBounded(s, e) strnlen(s, PQmblen(s, e))
+
static bool DescribeQuery(const char *query, double *elapsed_msec);
static bool ExecQueryUsingCursor(const char *query, double *elapsed_msec);
static bool command_no_begin(const char *query);
@@ -1842,7 +1844,7 @@ skip_white_space(const char *query)
while (*query)
{
- int mblen = PQmblen(query, pset.encoding);
+ int mblen = PQmblenBounded(query, pset.encoding);
/*
* Note: we assume the encoding is a superset of ASCII, so that for
@@ -1879,7 +1881,7 @@ skip_white_space(const char *query)
query++;
break;
}
- query += PQmblen(query, pset.encoding);
+ query += PQmblenBounded(query, pset.encoding);
}
}
else if (cnestlevel > 0)
@@ -1914,7 +1916,7 @@ command_no_begin(const char *query)
*/
wordlen = 0;
while (isalpha((unsigned char) query[wordlen]))
- wordlen += PQmblen(&query[wordlen], pset.encoding);
+ wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
/*
* Transaction control commands. These should include every keyword that
@@ -1945,7 +1947,7 @@ command_no_begin(const char *query)
wordlen = 0;
while (isalpha((unsigned char) query[wordlen]))
- wordlen += PQmblen(&query[wordlen], pset.encoding);
+ wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
if (wordlen == 11 && pg_strncasecmp(query, "transaction", 11) == 0)
return true;
@@ -1979,7 +1981,7 @@ command_no_begin(const char *query)
wordlen = 0;
while (isalpha((unsigned char) query[wordlen]))
- wordlen += PQmblen(&query[wordlen], pset.encoding);
+ wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
if (wordlen == 8 && pg_strncasecmp(query, "database", 8) == 0)
return true;
@@ -1995,7 +1997,7 @@ command_no_begin(const char *query)
wordlen = 0;
while (isalpha((unsigned char) query[wordlen]))
- wordlen += PQmblen(&query[wordlen], pset.encoding);
+ wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
}
if (wordlen == 5 && pg_strncasecmp(query, "index", 5) == 0)
@@ -2006,7 +2008,7 @@ command_no_begin(const char *query)
wordlen = 0;
while (isalpha((unsigned char) query[wordlen]))
- wordlen += PQmblen(&query[wordlen], pset.encoding);
+ wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
if (wordlen == 12 && pg_strncasecmp(query, "concurrently", 12) == 0)
return true;
@@ -2023,7 +2025,7 @@ command_no_begin(const char *query)
wordlen = 0;
while (isalpha((unsigned char) query[wordlen]))
- wordlen += PQmblen(&query[wordlen], pset.encoding);
+ wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
/* ALTER SYSTEM isn't allowed in xacts */
if (wordlen == 6 && pg_strncasecmp(query, "system", 6) == 0)
@@ -2046,7 +2048,7 @@ command_no_begin(const char *query)
wordlen = 0;
while (isalpha((unsigned char) query[wordlen]))
- wordlen += PQmblen(&query[wordlen], pset.encoding);
+ wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
if (wordlen == 8 && pg_strncasecmp(query, "database", 8) == 0)
return true;
@@ -2061,7 +2063,7 @@ command_no_begin(const char *query)
query = skip_white_space(query);
wordlen = 0;
while (isalpha((unsigned char) query[wordlen]))
- wordlen += PQmblen(&query[wordlen], pset.encoding);
+ wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
/*
* REINDEX [ TABLE | INDEX ] CONCURRENTLY are not allowed in
@@ -2080,7 +2082,7 @@ command_no_begin(const char *query)
wordlen = 0;
while (isalpha((unsigned char) query[wordlen]))
- wordlen += PQmblen(&query[wordlen], pset.encoding);
+ wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
if (wordlen == 12 && pg_strncasecmp(query, "concurrently", 12) == 0)
return true;
@@ -2100,7 +2102,7 @@ command_no_begin(const char *query)
wordlen = 0;
while (isalpha((unsigned char) query[wordlen]))
- wordlen += PQmblen(&query[wordlen], pset.encoding);
+ wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
if (wordlen == 3 && pg_strncasecmp(query, "all", 3) == 0)
return true;
@@ -2136,7 +2138,7 @@ is_select_command(const char *query)
*/
wordlen = 0;
while (isalpha((unsigned char) query[wordlen]))
- wordlen += PQmblen(&query[wordlen], pset.encoding);
+ wordlen += PQmblenBounded(&query[wordlen], pset.encoding);
if (wordlen == 6 && pg_strncasecmp(query, "select", 6) == 0)
return true;
diff --git a/src/bin/psql/psqlscanslash.l b/src/bin/psql/psqlscanslash.l
index 4dff84d6271..390dc6c5c90 100644
--- a/src/bin/psql/psqlscanslash.l
+++ b/src/bin/psql/psqlscanslash.l
@@ -28,6 +28,8 @@
%{
#include "fe_utils/psqlscan_int.h"
+#define PQmblenBounded(s, e) strnlen(s, PQmblen(s, e))
+
/*
* We must have a typedef YYSTYPE for yylex's first argument, but this lexer
* doesn't presently make use of that argument, so just declare it as int.
@@ -753,7 +755,7 @@ dequote_downcase_identifier(char *str, bool downcase, int encoding)
{
if (downcase && !inquotes)
*cp = pg_tolower((unsigned char) *cp);
- cp += PQmblen(cp, encoding);
+ cp += PQmblenBounded(cp, encoding);
}
}
}
diff --git a/src/bin/psql/stringutils.c b/src/bin/psql/stringutils.c
index c521749661c..c96b2fe1965 100644
--- a/src/bin/psql/stringutils.c
+++ b/src/bin/psql/stringutils.c
@@ -12,6 +12,8 @@
#include "common.h"
#include "stringutils.h"
+#define PQmblenBounded(s, e) strnlen(s, PQmblen(s, e))
+
/*
* Replacement for strtok() (a.k.a. poor man's flex)
@@ -143,7 +145,7 @@ strtokx(const char *s,
/* okay, we have a quoted token, now scan for the closer */
char thisquote = *p++;
- for (; *p; p += PQmblen(p, encoding))
+ for (; *p; p += PQmblenBounded(p, encoding))
{
if (*p == escape && p[1] != '\0')
p++; /* process escaped anything */
@@ -262,7 +264,7 @@ strip_quotes(char *source, char quote, char escape, int encoding)
else if (c == escape && src[1] != '\0')
src++; /* process escaped character */
- i = PQmblen(src, encoding);
+ i = PQmblenBounded(src, encoding);
while (i--)
*dst++ = *src++;
}
@@ -324,7 +326,7 @@ quote_if_needed(const char *source, const char *entails_quote,
else if (strchr(entails_quote, c))
need_quotes = true;
- i = PQmblen(src, encoding);
+ i = PQmblenBounded(src, encoding);
while (i--)
*dst++ = *src++;
}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index eb018854a5c..4f46cd949d9 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -73,6 +73,8 @@
#define USE_FILENAME_QUOTING_FUNCTIONS 1
#endif
+#define PQmblenBounded(s, e) strnlen(s, PQmblen(s, e))
+
/* word break characters */
#define WORD_BREAKS "\t\n@$><=;|&{() "
@@ -4140,7 +4142,7 @@ _complete_from_query(const char *simple_query,
while (*pstr)
{
char_length++;
- pstr += PQmblen(pstr, pset.encoding);
+ pstr += PQmblenBounded(pstr, pset.encoding);
}
/* Free any prior result */
diff --git a/src/bin/scripts/common.c b/src/bin/scripts/common.c
index afa62e4da73..d446d7af9fa 100644
--- a/src/bin/scripts/common.c
+++ b/src/bin/scripts/common.c
@@ -25,6 +25,8 @@
#define ERRCODE_UNDEFINED_TABLE "42P01"
+#define PQmblenBounded(s, e) strnlen(s, PQmblen(s, e))
+
/*
* Provide strictly harmonized handling of --help and --version
* options.
@@ -368,7 +370,7 @@ splitTableColumnsSpec(const char *spec, int encoding,
cp++;
}
else
- cp += PQmblen(cp, encoding);
+ cp += PQmblenBounded(cp, encoding);
}
*table = pnstrdup(spec, cp - spec);
*columns = cp;
diff --git a/src/common/jsonapi.c b/src/common/jsonapi.c
index 9326f805366..6fe17a3d378 100644
--- a/src/common/jsonapi.c
+++ b/src/common/jsonapi.c
@@ -738,7 +738,7 @@ json_lex_string(JsonLexContext *lex)
ch = (ch * 16) + (*s - 'A') + 10;
else
{
- lex->token_terminator = s + pg_encoding_mblen(lex->input_encoding, s);
+ lex->token_terminator = s + pg_encoding_mblen_bounded(lex->input_encoding, s);
return JSON_UNICODE_ESCAPE_FORMAT;
}
}
@@ -844,7 +844,7 @@ json_lex_string(JsonLexContext *lex)
default:
/* Not a valid string escape, so signal error. */
lex->token_start = s;
- lex->token_terminator = s + pg_encoding_mblen(lex->input_encoding, s);
+ lex->token_terminator = s + pg_encoding_mblen_bounded(lex->input_encoding, s);
return JSON_ESCAPING_INVALID;
}
}
@@ -858,7 +858,7 @@ json_lex_string(JsonLexContext *lex)
* shown it's not a performance win.
*/
lex->token_start = s;
- lex->token_terminator = s + pg_encoding_mblen(lex->input_encoding, s);
+ lex->token_terminator = s + pg_encoding_mblen_bounded(lex->input_encoding, s);
return JSON_ESCAPING_INVALID;
}
diff --git a/src/common/wchar.c b/src/common/wchar.c
index efaf1c155bb..08734802236 100644
--- a/src/common/wchar.c
+++ b/src/common/wchar.c
@@ -1549,6 +1549,11 @@ const pg_wchar_tbl pg_wchar_table[] = {
/*
* Returns the byte length of a multibyte character.
+ *
+ * Caution: when dealing with text that is not certainly valid in the
+ * specified encoding, the result may exceed the actual remaining
+ * string length. Callers that are not prepared to deal with that
+ * should use pg_encoding_mblen_bounded() instead.
*/
int
pg_encoding_mblen(int encoding, const char *mbstr)
@@ -1559,6 +1564,16 @@ pg_encoding_mblen(int encoding, const char *mbstr)
}
/*
+ * Returns the byte length of a multibyte character; but not more than
+ * the distance to end of string.
+ */
+int
+pg_encoding_mblen_bounded(int encoding, const char *mbstr)
+{
+ return strnlen(mbstr, pg_encoding_mblen(encoding, mbstr));
+}
+
+/*
* Returns the display length of a multibyte character.
*/
int
diff --git a/src/fe_utils/print.c b/src/fe_utils/print.c
index f3c176aa555..966a7721801 100644
--- a/src/fe_utils/print.c
+++ b/src/fe_utils/print.c
@@ -3652,6 +3652,9 @@ strlen_max_width(unsigned char *str, int *target_width, int encoding)
curr_width += char_width;
str += PQmblen((char *) str, encoding);
+
+ if (str > end) /* Don't overrun invalid string */
+ str = end;
}
*target_width = curr_width;
diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h
index 494aefc7fab..b43454b64ce 100644
--- a/src/include/mb/pg_wchar.h
+++ b/src/include/mb/pg_wchar.h
@@ -553,6 +553,7 @@ extern int pg_valid_server_encoding_id(int encoding);
* earlier in this file are also available from libpgcommon.
*/
extern int pg_encoding_mblen(int encoding, const char *mbstr);
+extern int pg_encoding_mblen_bounded(int encoding, const char *mbstr);
extern int pg_encoding_dsplen(int encoding, const char *mbstr);
extern int pg_encoding_verifymb(int encoding, const char *mbstr, int len);
extern int pg_encoding_max_length(int encoding);
diff --git a/src/interfaces/libpq/fe-print.c b/src/interfaces/libpq/fe-print.c
index 784eaae48e5..61ba4e4ce7b 100644
--- a/src/interfaces/libpq/fe-print.c
+++ b/src/interfaces/libpq/fe-print.c
@@ -36,6 +36,7 @@
#include "libpq-fe.h"
#include "libpq-int.h"
+#define PQmblenBounded(s, e) strnlen(s, PQmblen(s, e))
static void do_field(const PQprintOpt *po, const PGresult *res,
const int i, const int j, const int fs_len,
@@ -365,7 +366,7 @@ do_field(const PQprintOpt *po, const PGresult *res,
/* Detect whether field contains non-numeric data */
char ch = '0';
- for (p = pval; *p; p += PQmblen(p, res->client_encoding))
+ for (p = pval; *p; p += PQmblenBounded(p, res->client_encoding))
{
ch = *p;
if (!((ch >= '0' && ch <= '9') ||
diff --git a/src/interfaces/libpq/fe-protocol3.c b/src/interfaces/libpq/fe-protocol3.c
index 686299dce91..04fd4ba874b 100644
--- a/src/interfaces/libpq/fe-protocol3.c
+++ b/src/interfaces/libpq/fe-protocol3.c
@@ -39,6 +39,8 @@
((id) == 'T' || (id) == 'D' || (id) == 'd' || (id) == 'V' || \
(id) == 'E' || (id) == 'N' || (id) == 'A')
+#define PQmblenBounded(s, e) strnlen(s, PQmblen(s, e))
+
static void handleSyncLoss(PGconn *conn, char id, int msgLength);
static int getRowDescriptions(PGconn *conn, int msgLength);
@@ -1241,7 +1243,7 @@ reportErrorPosition(PQExpBuffer msg, const char *query, int loc, int encoding)
if (w <= 0)
w = 1;
scroffset += w;
- qoffset += pg_encoding_mblen(encoding, &wquery[qoffset]);
+ qoffset += PQmblenBounded(&wquery[qoffset], encoding);
}
else
{
@@ -1309,7 +1311,7 @@ reportErrorPosition(PQExpBuffer msg, const char *query, int loc, int encoding)
* width.
*/
scroffset = 0;
- for (; i < msg->len; i += pg_encoding_mblen(encoding, &msg->data[i]))
+ for (; i < msg->len; i += PQmblenBounded(&msg->data[i], encoding))
{
int w = pg_encoding_dsplen(encoding, &msg->data[i]);
generated by cgit v1.2.3 (git 2.39.1) at 2025-07-30 03:04:13 +0000