/***
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
along with systemd; If not, see <http://www.gnu.org/licenses/>.
***/
-/* This file is based on the GLIB utf8 validation functions. The
+/* Parts of this file are based on the GLIB utf8 validation functions. The
* original license text follows. */
/* gutf8.c - Operations on UTF-8 strings.
/* count of characters used to encode one unicode char */
static int utf8_encoded_expected_len(const char *str) {
- unsigned char c = (unsigned char)str[0];
+ unsigned char c;
+ assert(str);
+
+ c = (unsigned char) str[0];
if (c < 0x80)
return 1;
if ((c & 0xe0) == 0xc0)
return 5;
if ((c & 0xfe) == 0xfc)
return 6;
+
return 0;
}
/* decode one unicode char */
-static int utf8_encoded_to_unichar(const char *str) {
- int unichar;
- int len;
- int i;
+int utf8_encoded_to_unichar(const char *str) {
+ int unichar, len, i;
+
+ assert(str);
len = utf8_encoded_expected_len(str);
+
switch (len) {
case 1:
return (int)str[0];
unichar = (int)str[0] & 0x01;
break;
default:
- return -1;
+ return -EINVAL;
}
for (i = 1; i < len; i++) {
if (((int)str[i] & 0xc0) != 0x80)
- return -1;
+ return -EINVAL;
unichar <<= 6;
unichar |= (int)str[i] & 0x3f;
}
return unichar;
}
-bool utf8_is_printable(const char* str, size_t length) {
- const uint8_t *p;
+bool utf8_is_printable_newline(const char* str, size_t length, bool newline) {
+ const char *p;
assert(str);
- for (p = (const uint8_t*) str; length; p++) {
- int encoded_len = utf8_encoded_valid_unichar((const char *)p);
- int32_t val = utf8_encoded_to_unichar((const char*)p);
+ for (p = str; length;) {
+ int encoded_len, val;
+
+ encoded_len = utf8_encoded_valid_unichar(p);
+ if (encoded_len < 0 ||
+ (size_t) encoded_len > length)
+ return false;
- if (encoded_len < 0 || val < 0 || is_unicode_control(val))
+ val = utf8_encoded_to_unichar(p);
+ if (val < 0 ||
+ is_unicode_control(val) ||
+ (!newline && val == '\n'))
return false;
length -= encoded_len;
+ p += encoded_len;
}
return true;
assert(str);
for (p = (const uint8_t*) str; *p; ) {
- int len = utf8_encoded_valid_unichar((const char *)p);
+ int len;
+ len = utf8_encoded_valid_unichar((const char *)p);
if (len < 0)
return NULL;
return str;
}
-char *ascii_is_valid(const char *str) {
- const char *p;
+char *utf8_escape_invalid(const char *str) {
+ char *p, *s;
assert(str);
- for (p = str; *p; p++)
- if ((unsigned char) *p >= 128)
- return NULL;
+ p = s = malloc(strlen(str) * 4 + 1);
+ if (!p)
+ return NULL;
- return (char*) str;
+ while (*str) {
+ int len;
+
+ len = utf8_encoded_valid_unichar(str);
+ if (len > 0) {
+ s = mempcpy(s, str, len);
+ str += len;
+ } else {
+ s = stpcpy(s, UTF8_REPLACEMENT_CHARACTER);
+ str += 1;
+ }
+ }
+
+ *s = '\0';
+
+ return p;
}
-char *ascii_filter(const char *str) {
- const char *s;
- char *r, *d;
- size_t l;
+char *utf8_escape_non_printable(const char *str) {
+ char *p, *s;
assert(str);
- l = strlen(str);
- r = malloc(l + 1);
- if (!r)
+ p = s = malloc(strlen(str) * 4 + 1);
+ if (!p)
return NULL;
- for (s = str, d = r; *s; s++)
- if ((unsigned char) *s < 128)
- *(d++) = *s;
+ while (*str) {
+ int len;
+
+ len = utf8_encoded_valid_unichar(str);
+ if (len > 0) {
+ if (utf8_is_printable(str, len)) {
+ s = mempcpy(s, str, len);
+ str += len;
+ } else {
+ while (len > 0) {
+ *(s++) = '\\';
+ *(s++) = 'x';
+ *(s++) = hexchar((int) *str >> 4);
+ *(s++) = hexchar((int) *str);
+
+ str += 1;
+ len --;
+ }
+ }
+ } else {
+ s = stpcpy(s, UTF8_REPLACEMENT_CHARACTER);
+ str += 1;
+ }
+ }
+
+ *s = '\0';
- *d = 0;
+ return p;
+}
- return r;
+char *ascii_is_valid(const char *str) {
+ const char *p;
+
+ assert(str);
+
+ for (p = str; *p; p++)
+ if ((unsigned char) *p >= 128)
+ return NULL;
+
+ return (char*) str;
}
char *utf16_to_utf8(const void *s, size_t length) {
/* expected size used to encode one unicode char */
static int utf8_unichar_to_encoded_len(int unichar) {
+
if (unichar < 0x80)
return 1;
if (unichar < 0x800)
return 4;
if (unichar < 0x4000000)
return 5;
+
return 6;
}
/* validate one encoded unicode char and return its length */
int utf8_encoded_valid_unichar(const char *str) {
- int len;
- int unichar;
- int i;
+ int len, unichar, i;
+
+ assert(str);
len = utf8_encoded_expected_len(str);
if (len == 0)
- return -1;
+ return -EINVAL;
/* ascii is valid */
if (len == 1)
/* check if expected encoded chars are available */
for (i = 0; i < len; i++)
if ((str[i] & 0x80) != 0x80)
- return -1;
+ return -EINVAL;
unichar = utf8_encoded_to_unichar(str);
/* check if encoded length matches encoded value */
if (utf8_unichar_to_encoded_len(unichar) != len)
- return -1;
+ return -EINVAL;
/* check if value has valid range */
if (!is_unicode_valid(unichar))
- return -1;
+ return -EINVAL;
return len;
}
-
-int is_utf8_encoding_whitelisted(char c, const char *white) {
- if ((c >= '0' && c <= '9') ||
- (c >= 'A' && c <= 'Z') ||
- (c >= 'a' && c <= 'z') ||
- strchr("#+-.:=@_", c) != NULL ||
- (white != NULL && strchr(white, c) != NULL))
- return 1;
- return 0;
-}
-
-int udev_encode_string(const char *str, char *str_enc, size_t len) {
- size_t i, j;
-
- if (str == NULL || str_enc == NULL)
- return -1;
-
- for (i = 0, j = 0; str[i] != '\0'; i++) {
- int seqlen;
-
- seqlen = utf8_encoded_valid_unichar(&str[i]);
- if (seqlen > 1) {
- if (len-j < (size_t)seqlen)
- goto err;
- memcpy(&str_enc[j], &str[i], seqlen);
- j += seqlen;
- i += (seqlen-1);
- } else if (str[i] == '\\' || !is_utf8_encoding_whitelisted(str[i], NULL)) {
- if (len-j < 4)
- goto err;
- sprintf(&str_enc[j], "\\x%02x", (unsigned char) str[i]);
- j += 4;
- } else {
- if (len-j < 1)
- goto err;
- str_enc[j] = str[i];
- j++;
- }
- }
- if (len-j < 1)
- goto err;
- str_enc[j] = '\0';
- return 0;
-err:
- return -1;
-}
~ianmdlvl / elogind.git / blobdiff