2008-09-03 19:14:52 +00:00
|
|
|
/* str_util.c
|
|
|
|
* String utility routines
|
|
|
|
*
|
|
|
|
* Wireshark - Network traffic analyzer
|
|
|
|
* By Gerald Combs <gerald@wireshark.org>
|
|
|
|
* Copyright 1998 Gerald Combs
|
|
|
|
*
|
2018-02-07 11:26:45 +00:00
|
|
|
* SPDX-License-Identifier: GPL-2.0-or-later
|
2008-09-03 19:14:52 +00:00
|
|
|
*/
|
|
|
|
|
2021-11-27 17:57:46 +00:00
|
|
|
#define _GNU_SOURCE
|
2021-10-16 09:33:34 +00:00
|
|
|
#include "config.h"
|
2008-09-03 19:14:52 +00:00
|
|
|
#include "str_util.h"
|
|
|
|
|
2021-11-27 17:57:46 +00:00
|
|
|
#include <string.h>
|
|
|
|
|
2014-01-08 00:28:13 +00:00
|
|
|
int
|
|
|
|
ws_xton(char ch)
|
|
|
|
{
|
|
|
|
switch (ch) {
|
|
|
|
case '0': return 0;
|
|
|
|
case '1': return 1;
|
|
|
|
case '2': return 2;
|
|
|
|
case '3': return 3;
|
|
|
|
case '4': return 4;
|
|
|
|
case '5': return 5;
|
|
|
|
case '6': return 6;
|
|
|
|
case '7': return 7;
|
|
|
|
case '8': return 8;
|
|
|
|
case '9': return 9;
|
|
|
|
case 'a': case 'A': return 10;
|
|
|
|
case 'b': case 'B': return 11;
|
|
|
|
case 'c': case 'C': return 12;
|
|
|
|
case 'd': case 'D': return 13;
|
|
|
|
case 'e': case 'E': return 14;
|
|
|
|
case 'f': case 'F': return 15;
|
|
|
|
default: return -1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2008-09-03 19:14:52 +00:00
|
|
|
/* Convert all ASCII letters to lower case, in place. */
|
2009-01-17 17:30:23 +00:00
|
|
|
gchar *
|
2008-09-03 19:14:52 +00:00
|
|
|
ascii_strdown_inplace(gchar *str)
|
|
|
|
{
|
|
|
|
gchar *s;
|
|
|
|
|
|
|
|
for (s = str; *s; s++)
|
2014-10-14 15:12:16 +00:00
|
|
|
/* What 'g_ascii_tolower (gchar c)' does, this should be slightly more efficient */
|
2014-05-13 16:00:25 +00:00
|
|
|
*s = g_ascii_isupper (*s) ? *s - 'A' + 'a' : *s;
|
2009-01-17 17:30:23 +00:00
|
|
|
|
2014-10-14 15:12:16 +00:00
|
|
|
return (str);
|
2008-09-03 19:14:52 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Convert all ASCII letters to upper case, in place. */
|
2009-01-17 17:30:23 +00:00
|
|
|
gchar *
|
2008-09-03 19:14:52 +00:00
|
|
|
ascii_strup_inplace(gchar *str)
|
|
|
|
{
|
|
|
|
gchar *s;
|
|
|
|
|
|
|
|
for (s = str; *s; s++)
|
2014-10-14 15:12:16 +00:00
|
|
|
/* What 'g_ascii_toupper (gchar c)' does, this should be slightly more efficient */
|
|
|
|
*s = g_ascii_islower (*s) ? *s - 'a' + 'A' : *s;
|
2009-01-17 17:30:23 +00:00
|
|
|
|
2014-10-14 15:12:16 +00:00
|
|
|
return (str);
|
2008-09-03 19:14:52 +00:00
|
|
|
}
|
2012-02-17 17:22:12 +00:00
|
|
|
|
|
|
|
/* Check if an entire string is printable. */
|
|
|
|
gboolean
|
2012-12-26 13:41:30 +00:00
|
|
|
isprint_string(const gchar *str)
|
2012-02-17 17:22:12 +00:00
|
|
|
{
|
|
|
|
guint pos;
|
|
|
|
|
|
|
|
/* Loop until we reach the end of the string (a null) */
|
|
|
|
for(pos = 0; str[pos] != '\0'; pos++){
|
2014-05-13 12:44:47 +00:00
|
|
|
if(!g_ascii_isprint(str[pos])){
|
2012-02-17 17:22:12 +00:00
|
|
|
/* The string contains a non-printable character */
|
|
|
|
return FALSE;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* The string contains only printable characters */
|
|
|
|
return TRUE;
|
|
|
|
}
|
|
|
|
|
2018-04-27 13:29:32 +00:00
|
|
|
/* Check if an entire UTF-8 string is printable. */
|
|
|
|
gboolean
|
|
|
|
isprint_utf8_string(const gchar *str, guint length)
|
|
|
|
{
|
|
|
|
const char *c;
|
|
|
|
|
|
|
|
if (!g_utf8_validate (str, length, NULL)) {
|
|
|
|
return FALSE;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (c = str; *c; c = g_utf8_next_char(c)) {
|
|
|
|
if (!g_unichar_isprint(g_utf8_get_char(c))) {
|
|
|
|
return FALSE;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return TRUE;
|
|
|
|
}
|
|
|
|
|
2012-02-17 17:22:12 +00:00
|
|
|
/* Check if an entire string is digits. */
|
|
|
|
gboolean
|
2018-10-24 22:27:24 +00:00
|
|
|
isdigit_string(const guchar *str)
|
2012-02-17 17:22:12 +00:00
|
|
|
{
|
|
|
|
guint pos;
|
|
|
|
|
|
|
|
/* Loop until we reach the end of the string (a null) */
|
|
|
|
for(pos = 0; str[pos] != '\0'; pos++){
|
2014-10-17 21:10:52 +00:00
|
|
|
if(!g_ascii_isdigit(str[pos])){
|
2012-02-17 17:22:12 +00:00
|
|
|
/* The string contains a non-digit character */
|
|
|
|
return FALSE;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* The string contains only digits */
|
|
|
|
return TRUE;
|
|
|
|
}
|
2012-10-10 19:17:31 +00:00
|
|
|
|
2021-11-27 17:57:46 +00:00
|
|
|
/* Return the first occurrence of needle in haystack.
|
|
|
|
* If not found, return NULL.
|
|
|
|
* If either haystack or needle has 0 length, return NULL.*/
|
|
|
|
const guint8 *
|
|
|
|
ws_memmem(const void *_haystack, size_t haystack_len,
|
|
|
|
const void *_needle, size_t needle_len)
|
|
|
|
{
|
|
|
|
#ifdef HAVE_MEMMEM
|
|
|
|
return memmem(_haystack, haystack_len, _needle, needle_len);
|
|
|
|
#else
|
|
|
|
/* Algorithm copied from GNU's glibc 2.3.2 memmem() under LGPL 2.1+ */
|
|
|
|
const guint8 *haystack = _haystack;
|
|
|
|
const guint8 *needle = _needle;
|
|
|
|
const guint8 *begin;
|
|
|
|
const guint8 *const last_possible = haystack + haystack_len - needle_len;
|
|
|
|
|
|
|
|
if (needle_len == 0) {
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (needle_len > haystack_len) {
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (begin = haystack ; begin <= last_possible; ++begin) {
|
|
|
|
if (begin[0] == needle[0] &&
|
|
|
|
!memcmp(&begin[1], needle + 1,
|
|
|
|
needle_len - 1)) {
|
|
|
|
return begin;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
#endif /* HAVE_MEMMEM */
|
|
|
|
}
|
|
|
|
|
|
|
|
const char *
|
|
|
|
ws_strcasestr(const char *haystack, const char *needle)
|
|
|
|
{
|
|
|
|
#ifdef HAVE_STRCASESTR
|
|
|
|
return strcasestr(haystack, needle);
|
|
|
|
#else
|
|
|
|
gsize hlen = strlen(haystack);
|
|
|
|
gsize nlen = strlen(needle);
|
|
|
|
|
|
|
|
while (hlen-- >= nlen) {
|
|
|
|
if (!g_ascii_strncasecmp(haystack, needle, nlen))
|
|
|
|
return haystack;
|
|
|
|
haystack++;
|
|
|
|
}
|
|
|
|
return NULL;
|
|
|
|
#endif /* HAVE_STRCASESTR */
|
|
|
|
}
|
|
|
|
|
2021-07-11 00:01:14 +00:00
|
|
|
#define FORMAT_SIZE_UNIT_MASK 0x00ff
|
|
|
|
#define FORMAT_SIZE_PFX_MASK 0xff00
|
2012-10-10 19:17:31 +00:00
|
|
|
|
2017-10-23 18:00:27 +00:00
|
|
|
static const char *thousands_grouping_fmt = NULL;
|
|
|
|
|
|
|
|
DIAG_OFF(format)
|
|
|
|
static void test_printf_thousands_grouping(void) {
|
2021-07-10 15:12:03 +00:00
|
|
|
/* test whether wmem_strbuf works with "'" flag character */
|
|
|
|
wmem_strbuf_t *buf = wmem_strbuf_new(NULL, NULL);
|
|
|
|
wmem_strbuf_append_printf(buf, "%'d", 22);
|
|
|
|
if (g_strcmp0(wmem_strbuf_get_str(buf), "22") == 0) {
|
2017-10-23 18:00:27 +00:00
|
|
|
thousands_grouping_fmt = "%'"G_GINT64_MODIFIER"d";
|
|
|
|
} else {
|
|
|
|
/* Don't use */
|
|
|
|
thousands_grouping_fmt = "%"G_GINT64_MODIFIER"d";
|
|
|
|
}
|
2021-07-10 15:12:03 +00:00
|
|
|
wmem_strbuf_destroy(buf);
|
2017-10-23 18:00:27 +00:00
|
|
|
}
|
|
|
|
DIAG_ON(format)
|
2013-03-03 19:34:58 +00:00
|
|
|
|
2012-10-10 19:17:31 +00:00
|
|
|
/* Given a size, return its value in a human-readable format */
|
2015-08-12 21:09:35 +00:00
|
|
|
/* This doesn't handle fractional values. We might want to make size a double. */
|
2014-09-04 01:57:02 +00:00
|
|
|
gchar *
|
2021-07-10 15:12:03 +00:00
|
|
|
format_size_wmem(wmem_allocator_t *allocator, gint64 size, format_size_flags_e flags)
|
2014-09-04 01:57:02 +00:00
|
|
|
{
|
2021-07-10 15:12:03 +00:00
|
|
|
wmem_strbuf_t *human_str = wmem_strbuf_new(allocator, NULL);
|
2012-10-10 19:17:31 +00:00
|
|
|
int power = 1000;
|
|
|
|
int pfx_off = 0;
|
|
|
|
gboolean is_small = FALSE;
|
2021-07-11 00:01:14 +00:00
|
|
|
static const gchar *prefix[] = {" T", " G", " M", " k", " Ti", " Gi", " Mi", " Ki"};
|
2012-10-10 19:17:31 +00:00
|
|
|
gchar *ret_val;
|
|
|
|
|
2017-10-23 18:00:27 +00:00
|
|
|
if (thousands_grouping_fmt == NULL)
|
|
|
|
test_printf_thousands_grouping();
|
|
|
|
|
2012-10-10 19:17:31 +00:00
|
|
|
if ((flags & FORMAT_SIZE_PFX_MASK) == format_size_prefix_iec) {
|
|
|
|
pfx_off = 4;
|
|
|
|
power = 1024;
|
|
|
|
}
|
|
|
|
|
2014-10-14 15:12:16 +00:00
|
|
|
if (size / power / power / power / power >= 10) {
|
2021-07-10 15:12:03 +00:00
|
|
|
wmem_strbuf_append_printf(human_str, thousands_grouping_fmt, size / power / power / power / power);
|
|
|
|
wmem_strbuf_append(human_str, prefix[pfx_off]);
|
2012-10-10 20:19:18 +00:00
|
|
|
} else if (size / power / power / power >= 10) {
|
2021-07-10 15:12:03 +00:00
|
|
|
wmem_strbuf_append_printf(human_str, thousands_grouping_fmt, size / power / power / power);
|
|
|
|
wmem_strbuf_append(human_str, prefix[pfx_off+1]);
|
2012-10-10 20:19:18 +00:00
|
|
|
} else if (size / power / power >= 10) {
|
2021-07-10 15:12:03 +00:00
|
|
|
wmem_strbuf_append_printf(human_str, thousands_grouping_fmt, size / power / power);
|
|
|
|
wmem_strbuf_append(human_str, prefix[pfx_off+2]);
|
2012-10-10 20:19:18 +00:00
|
|
|
} else if (size / power >= 10) {
|
2021-07-10 15:12:03 +00:00
|
|
|
wmem_strbuf_append_printf(human_str, thousands_grouping_fmt, size / power);
|
|
|
|
wmem_strbuf_append(human_str, prefix[pfx_off+3]);
|
2014-10-14 15:12:16 +00:00
|
|
|
} else {
|
2021-07-10 15:12:03 +00:00
|
|
|
wmem_strbuf_append_printf(human_str, thousands_grouping_fmt, size);
|
2012-10-10 19:17:31 +00:00
|
|
|
is_small = TRUE;
|
|
|
|
}
|
2017-10-23 18:00:27 +00:00
|
|
|
|
2012-10-10 19:17:31 +00:00
|
|
|
switch (flags & FORMAT_SIZE_UNIT_MASK) {
|
|
|
|
case format_size_unit_none:
|
|
|
|
break;
|
|
|
|
case format_size_unit_bytes:
|
2021-07-10 15:12:03 +00:00
|
|
|
wmem_strbuf_append(human_str, is_small ? " bytes" : "B");
|
2012-10-10 19:17:31 +00:00
|
|
|
break;
|
|
|
|
case format_size_unit_bits:
|
2021-07-10 15:12:03 +00:00
|
|
|
wmem_strbuf_append(human_str, is_small ? " bits" : "b");
|
2012-10-10 19:17:31 +00:00
|
|
|
break;
|
|
|
|
case format_size_unit_bits_s:
|
2021-07-10 15:12:03 +00:00
|
|
|
wmem_strbuf_append(human_str, is_small ? " bits/s" : "bps");
|
2012-10-10 19:17:31 +00:00
|
|
|
break;
|
2013-02-26 06:40:25 +00:00
|
|
|
case format_size_unit_bytes_s:
|
2021-07-10 15:12:03 +00:00
|
|
|
wmem_strbuf_append(human_str, is_small ? " bytes/s" : "Bps");
|
2014-08-24 08:56:36 +00:00
|
|
|
break;
|
|
|
|
case format_size_unit_packets:
|
2021-07-10 15:12:03 +00:00
|
|
|
wmem_strbuf_append(human_str, is_small ? " packets" : "packets");
|
2014-08-24 08:56:36 +00:00
|
|
|
break;
|
|
|
|
case format_size_unit_packets_s:
|
2021-07-10 15:12:03 +00:00
|
|
|
wmem_strbuf_append(human_str, is_small ? " packets/s" : "packets/s");
|
2013-02-26 06:40:25 +00:00
|
|
|
break;
|
2012-10-10 19:17:31 +00:00
|
|
|
default:
|
2021-05-23 23:46:43 +00:00
|
|
|
ws_assert_not_reached();
|
2012-10-10 19:17:31 +00:00
|
|
|
}
|
|
|
|
|
2021-07-10 15:12:03 +00:00
|
|
|
ret_val = wmem_strbuf_finalize(human_str);
|
2014-04-29 15:10:27 +00:00
|
|
|
return g_strchomp(ret_val);
|
2012-10-10 19:17:31 +00:00
|
|
|
}
|
2014-09-04 01:57:02 +00:00
|
|
|
|
|
|
|
gchar
|
|
|
|
printable_char_or_period(gchar c)
|
|
|
|
{
|
|
|
|
return g_ascii_isprint(c) ? c : '.';
|
|
|
|
}
|
2014-10-14 15:12:16 +00:00
|
|
|
|
2021-11-29 13:52:09 +00:00
|
|
|
size_t
|
|
|
|
ws_escape_string_len(const char *string)
|
|
|
|
{
|
|
|
|
const char *p;
|
|
|
|
gchar c;
|
|
|
|
size_t repr_len;
|
|
|
|
|
|
|
|
repr_len = 0;
|
|
|
|
for (p = string; (c = *p) != '\0'; p++) {
|
|
|
|
/* Backslashes and double-quotes must
|
|
|
|
* be escaped */
|
|
|
|
if (c == '\\' || c == '"') {
|
|
|
|
repr_len += 2;
|
|
|
|
}
|
|
|
|
/* Values that can't nicely be represented
|
|
|
|
* in ASCII need to be escaped. */
|
|
|
|
else if (!g_ascii_isprint(c)) {
|
|
|
|
/* c --> \xNN */
|
|
|
|
repr_len += 4;
|
|
|
|
}
|
|
|
|
/* Other characters are just passed through. */
|
|
|
|
else {
|
|
|
|
repr_len++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return repr_len + 2; /* string plus leading and trailing quotes */
|
|
|
|
}
|
|
|
|
|
|
|
|
char *
|
|
|
|
ws_escape_string(char *buf, const char *string)
|
|
|
|
{
|
|
|
|
const gchar *p;
|
|
|
|
gchar c;
|
|
|
|
char *bufp;
|
|
|
|
char hexbuf[3];
|
|
|
|
|
|
|
|
bufp = buf;
|
|
|
|
*bufp++ = '"';
|
|
|
|
for (p = string; (c = *p) != '\0'; p++) {
|
|
|
|
/* Backslashes and double-quotes must
|
|
|
|
* be escaped. */
|
|
|
|
if (c == '\\' || c == '"') {
|
|
|
|
*bufp++ = '\\';
|
|
|
|
*bufp++ = c;
|
|
|
|
}
|
|
|
|
/* Values that can't nicely be represented
|
|
|
|
* in ASCII need to be escaped. */
|
|
|
|
else if (!g_ascii_isprint(c)) {
|
|
|
|
/* c --> \xNN */
|
|
|
|
g_snprintf(hexbuf,sizeof(hexbuf), "%02x", (unsigned char) c);
|
|
|
|
*bufp++ = '\\';
|
|
|
|
*bufp++ = 'x';
|
|
|
|
*bufp++ = hexbuf[0];
|
|
|
|
*bufp++ = hexbuf[1];
|
|
|
|
}
|
|
|
|
/* Other characters are just passed through. */
|
|
|
|
else {
|
|
|
|
*bufp++ = c;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
*bufp++ = '"';
|
|
|
|
*bufp = '\0';
|
|
|
|
return buf;
|
|
|
|
}
|
|
|
|
|
2014-10-14 15:12:16 +00:00
|
|
|
/*
|
2019-07-26 18:43:17 +00:00
|
|
|
* Editor modelines - https://www.wireshark.org/tools/modelines.html
|
2014-10-14 15:12:16 +00:00
|
|
|
*
|
|
|
|
* Local variables:
|
|
|
|
* c-basic-offset: 8
|
|
|
|
* tab-width: 8
|
|
|
|
* indent-tabs-mode: t
|
|
|
|
* End:
|
|
|
|
*
|
|
|
|
* vi: set shiftwidth=8 tabstop=8 noexpandtab:
|
|
|
|
* :indentSize=8:tabSize=8:noTabs=false:
|
|
|
|
*/
|