-/*-*- Mode: C; c-basic-offset: 8; indent-tabs-mode: nil -*-*/
-
-/***
- This file is part of systemd.
-
- Copyright 2008-2011 Kay Sievers
- Copyright 2012 Lennart Poettering
-
- systemd is free software; you can redistribute it and/or modify it
- under the terms of the GNU Lesser General Public License as published by
- the Free Software Foundation; either version 2.1 of the License, or
- (at your option) any later version.
-
- systemd is distributed in the hope that it will be useful, but
- WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- Lesser General Public License for more details.
-
- You should have received a copy of the GNU Lesser General Public License
- along with systemd; If not, see <http://www.gnu.org/licenses/>.
-***/
+/* SPDX-License-Identifier: LGPL-2.1+ */
/* Parts of this file are based on the GLIB utf8 validation functions. The
* original license text follows. */
*/
#include <errno.h>
-#include <inttypes.h>
#include <stdbool.h>
#include <stdlib.h>
#include <string.h>
#include "alloc-util.h"
+//#include "gunicode.h"
#include "hexdecoct.h"
+#include "macro.h"
#include "utf8.h"
-#include "util.h"
-bool unichar_is_valid(uint32_t ch) {
+bool unichar_is_valid(char32_t ch) {
if (ch >= 0x110000) /* End of unicode space */
return false;
return true;
}
-static bool unichar_is_control(uint32_t ch) {
+static bool unichar_is_control(char32_t ch) {
/*
0 to ' '-1 is the C0 range.
'\t' is in C0 range, but more or less harmless and commonly used.
*/
- return (ch < ' ' && ch != '\t' && ch != '\n') ||
+ return (ch < ' ' && !IN_SET(ch, '\t', '\n')) ||
(0x7F <= ch && ch <= 0x9F);
}
}
/* decode one unicode char */
-int utf8_encoded_to_unichar(const char *str) {
- int unichar, len, i;
+int utf8_encoded_to_unichar(const char *str, char32_t *ret_unichar) {
+ char32_t unichar;
+ int len, i;
assert(str);
switch (len) {
case 1:
- return (int)str[0];
+ *ret_unichar = (char32_t)str[0];
+ return 0;
case 2:
unichar = str[0] & 0x1f;
break;
case 3:
- unichar = (int)str[0] & 0x0f;
+ unichar = (char32_t)str[0] & 0x0f;
break;
case 4:
- unichar = (int)str[0] & 0x07;
+ unichar = (char32_t)str[0] & 0x07;
break;
case 5:
- unichar = (int)str[0] & 0x03;
+ unichar = (char32_t)str[0] & 0x03;
break;
case 6:
- unichar = (int)str[0] & 0x01;
+ unichar = (char32_t)str[0] & 0x01;
break;
default:
return -EINVAL;
}
for (i = 1; i < len; i++) {
- if (((int)str[i] & 0xc0) != 0x80)
+ if (((char32_t)str[i] & 0xc0) != 0x80)
return -EINVAL;
unichar <<= 6;
- unichar |= (int)str[i] & 0x3f;
+ unichar |= (char32_t)str[i] & 0x3f;
}
- return unichar;
+ *ret_unichar = unichar;
+
+ return 0;
}
bool utf8_is_printable_newline(const char* str, size_t length, bool newline) {
assert(str);
for (p = str; length;) {
- int encoded_len, val;
+ int encoded_len, r;
+ char32_t val;
encoded_len = utf8_encoded_valid_unichar(p);
if (encoded_len < 0 ||
(size_t) encoded_len > length)
return false;
- val = utf8_encoded_to_unichar(p);
- if (val < 0 ||
+ r = utf8_encoded_to_unichar(p, &val);
+ if (r < 0 ||
unichar_is_control(val) ||
(!newline && val == '\n'))
return false;
*(s++) = hexchar((int) *str);
str += 1;
- len --;
+ len--;
}
}
} else {
char *ascii_is_valid(const char *str) {
const char *p;
+ /* Check whether the string consists of valid ASCII bytes,
+ * i.e values between 0 and 127, inclusive. */
+
assert(str);
for (p = str; *p; p++)
return (char*) str;
}
+char *ascii_is_valid_n(const char *str, size_t len) {
+ size_t i;
+
+ /* Very similar to ascii_is_valid(), but checks exactly len
+ * bytes and rejects any NULs in that range. */
+
+ assert(str);
+
+ for (i = 0; i < len; i++)
+ if ((unsigned char) str[i] >= 128 || str[i] == 0)
+ return NULL;
+
+ return (char*) str;
+}
+
/**
* utf8_encode_unichar() - Encode single UCS-4 character as UTF-8
* @out_utf8: output buffer of at least 4 bytes or NULL
* Returns: The length in bytes that the UTF-8 representation does or would
* occupy.
*/
-size_t utf8_encode_unichar(char *out_utf8, uint32_t g) {
+size_t utf8_encode_unichar(char *out_utf8, char32_t g) {
if (g < (1 << 7)) {
if (out_utf8)
t = r;
while (f < (const uint8_t*) s + length) {
- uint16_t w1, w2;
+ char16_t w1, w2;
/* see RFC 2781 section 2.2 */
}
/* expected size used to encode one unicode char */
-static int utf8_unichar_to_encoded_len(int unichar) {
+static int utf8_unichar_to_encoded_len(char32_t unichar) {
if (unichar < 0x80)
return 1;
/* validate one encoded unicode char and return its length */
int utf8_encoded_valid_unichar(const char *str) {
- int len, unichar, i;
+ int len, i, r;
+ char32_t unichar;
assert(str);
if ((str[i] & 0x80) != 0x80)
return -EINVAL;
- unichar = utf8_encoded_to_unichar(str);
+ r = utf8_encoded_to_unichar(str, &unichar);
+ if (r < 0)
+ return r;
/* check if encoded length matches encoded value */
if (utf8_unichar_to_encoded_len(unichar) != len)
return len;
}
+
+size_t utf8_n_codepoints(const char *str) {
+ size_t n = 0;
+
+ /* Returns the number of UTF-8 codepoints in this string, or (size_t) -1 if the string is not valid UTF-8. */
+
+ while (*str != 0) {
+ int k;
+
+ k = utf8_encoded_valid_unichar(str);
+ if (k < 0)
+ return (size_t) -1;
+
+ str += k;
+ n++;
+ }
+
+ return n;
+}
+
+size_t utf8_console_width(const char *str) {
+ size_t n = 0;
+
+ /* Returns the approximate width a string will take on screen when printed on a character cell
+ * terminal/console. */
+
+ while (*str != 0) {
+ char32_t c;
+
+ if (utf8_encoded_to_unichar(str, &c) < 0)
+ return (size_t) -1;
+
+ str = utf8_next_char(str);
+
+ n += unichar_iswide(c) ? 2 : 1;
+ }
+
+ return n;
+}