X-Git-Url: http://www.chiark.greenend.org.uk/ucgi/~ianmdlvl/git?a=blobdiff_plain;f=src%2Fshared%2Futf8.c;h=c559c13678d62b7cd275f05721febe73b5205924;hb=dc92e62c6c34f242aa54aa187e50a94ed7695c51;hp=732f0f00ca20d2003cd3c96122cf0099abec15bf;hpb=7991ac34ab08421415b907e42775c5539a4a5bbb;p=elogind.git

diff --git a/src/shared/utf8.c b/src/shared/utf8.c
index 732f0f00c..c559c1367 100644
--- a/src/shared/utf8.c
+++ b/src/shared/utf8.c
@@ -3,6 +3,7 @@
 /***
   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
@@ -19,7 +20,7 @@
   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.
@@ -97,7 +98,7 @@ static int utf8_encoded_expected_len(const char *str) {
 }
 
 /* decode one unicode char */
-static int utf8_encoded_to_unichar(const char *str) {
+int utf8_encoded_to_unichar(const char *str) {
         int unichar;
         int len;
         int i;
@@ -135,19 +136,21 @@ static int utf8_encoded_to_unichar(const char *str) {
         return unichar;
 }
 
-bool utf8_is_printable(const char* str, size_t length) {
+bool utf8_is_printable_newline(const char* str, size_t length, bool newline) {
         const uint8_t *p;
 
         assert(str);
 
-        for (p = (const uint8_t*) str; length; p++) {
+        for (p = (const uint8_t*) str; length;) {
                 int encoded_len = utf8_encoded_valid_unichar((const char *)p);
-                int32_t val = utf8_encoded_to_unichar((const char*)p);
+                int val = utf8_encoded_to_unichar((const char*)p);
 
-                if (encoded_len < 0 || val < 0 || is_unicode_control(val))
+                if (encoded_len < 0 || val < 0 || is_unicode_control(val) ||
+                    (!newline && val == '\n'))
                         return false;
 
                 length -= encoded_len;
+                p += encoded_len;
         }
 
         return true;
@@ -159,7 +162,9 @@ const char *utf8_is_valid(const char *str) {
         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;
@@ -170,37 +175,42 @@ const char *utf8_is_valid(const char *str) {
         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;
 
-char *ascii_filter(const char *str) {
-        const char *s;
-        char *r, *d;
-        size_t l;
+                len = utf8_encoded_valid_unichar(str);
+                if (len > 0) {
+                        s = mempcpy(s, str, len);
+                        str += len;
+                } else {
+                        s = mempcpy(s, UTF8_REPLACEMENT_CHARACTER, strlen(UTF8_REPLACEMENT_CHARACTER));
+                        str += 1;
+                }
+        }
+        *s = '\0';
 
-        assert(str);
+        return p;
+}
 
-        l = strlen(str);
-        r = malloc(l + 1);
-        if (!r)
-                return NULL;
+char *ascii_is_valid(const char *str) {
+        const char *p;
 
-        for (s = str, d = r; *s; s++)
-                if ((unsigned char) *s < 128)
-                        *(d++) = *s;
+        assert(str);
 
-        *d = 0;
+        for (p = str; *p; p++)
+                if ((unsigned char) *p >= 128)
+                        return NULL;
 
-        return r;
+        return (char*) str;
 }
 
 char *utf16_to_utf8(const void *s, size_t length) {
@@ -285,49 +295,3 @@ int utf8_encoded_valid_unichar(const char *str) {
 
         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;
-}