unicode: New mod_utf8_codepoint()

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Laszlo Ersek <lersek@redhat.com>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>

3 files changed, 104 insertions, 1 deletions

diff --git a/include/qemu-common.h b/include/qemu-common.h
index 31fff22f32..3b1873e4ef 100644
--- a/include/qemu-common.h
+++ b/include/qemu-common.h
@@ -442,6 +442,9 @@ int64_t pow2floor(int64_t value);
 int uleb128_encode_small(uint8_t *out, uint32_t n);
 int uleb128_decode_small(const uint8_t *in, uint32_t *n);
 
+/* unicode.c */
+int mod_utf8_codepoint(const char *s, size_t n, char **end);
+
 /*
  * Hexdump a buffer to a file. An optional string prefix is added to every line
  */
diff --git a/util/Makefile.objs b/util/Makefile.objs
index 557bda7a15..c5652f5260 100644
--- a/util/Makefile.objs
+++ b/util/Makefile.objs
@@ -1,4 +1,4 @@
-util-obj-y = osdep.o cutils.o qemu-timer-common.o
+util-obj-y = osdep.o cutils.o unicode.o qemu-timer-common.o
 util-obj-$(CONFIG_WIN32) += oslib-win32.o qemu-thread-win32.o event_notifier-win32.o
 util-obj-$(CONFIG_POSIX) += oslib-posix.o qemu-thread-posix.o event_notifier-posix.o
 util-obj-y += envlist.o path.o host-utils.o cache-utils.o module.o
diff --git a/util/unicode.c b/util/unicode.c
new file mode 100644
index 0000000000..d1c8658850
--- /dev/null
+++ b/util/unicode.c
@@ -0,0 +1,100 @@
+/*
+ * Dealing with Unicode
+ *
+ * Copyright (C) 2013 Red Hat, Inc.
+ *
+ * Authors:
+ *  Markus Armbruster <armbru@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * later.  See the COPYING file in the top-level directory.
+ */
+
+#include "qemu-common.h"
+
+/**
+ * mod_utf8_codepoint:
+ * @s: string encoded in modified UTF-8
+ * @n: maximum number of bytes to read from @s, if less than 6
+ * @end: set to end of sequence on return
+ *
+ * Convert the modified UTF-8 sequence at the start of @s.  Modified
+ * UTF-8 is exactly like UTF-8, except U+0000 is encoded as
+ * "\xC0\x80".
+ *
+ * If @n is zero or @s points to a zero byte, the sequence is invalid,
+ * and @end is set to @s.
+ *
+ * If @s points to an impossible byte (0xFE or 0xFF) or a continuation
+ * byte, the sequence is invalid, and @end is set to @s + 1
+ *
+ * Else, the first byte determines how many continuation bytes are
+ * expected.  If there are fewer, the sequence is invalid, and @end is
+ * set to @s + 1 + actual number of continuation bytes.  Else, the
+ * sequence is well-formed, and @end is set to @s + 1 + expected
+ * number of continuation bytes.
+ *
+ * A well-formed sequence is valid unless it encodes a codepoint
+ * outside the Unicode range U+0000..U+10FFFF, one of Unicode's 66
+ * noncharacters, a surrogate codepoint, or is overlong.  Except the
+ * overlong sequence "\xC0\x80" is valid.
+ *
+ * Conversion succeeds if and only if the sequence is valid.
+ *
+ * Returns: the Unicode codepoint on success, -1 on failure.
+ */
+int mod_utf8_codepoint(const char *s, size_t n, char **end)
+{
+    static int min_cp[5] = { 0x80, 0x800, 0x10000, 0x200000, 0x4000000 };
+    const unsigned char *p;
+    unsigned byte, mask, len, i;
+    int cp;
+
+    if (n == 0 || *s == 0) {
+        /* empty sequence */
+        *end = (char *)s;
+        return -1;
+    }
+
+    p = (const unsigned char *)s;
+    byte = *p++;
+    if (byte < 0x80) {
+        cp = byte;              /* one byte sequence */
+    } else if (byte >= 0xFE) {
+        cp = -1;                /* impossible bytes 0xFE, 0xFF */
+    } else if ((byte & 0x40) == 0) {
+        cp = -1;                /* unexpected continuation byte */
+    } else {
+        /* multi-byte sequence */
+        len = 0;
+        for (mask = 0x80; byte & mask; mask >>= 1) {
+            len++;
+        }
+        assert(len > 1 && len < 7);
+        cp = byte & (mask - 1);
+        for (i = 1; i < len; i++) {
+            byte = i < n ? *p : 0;
+            if ((byte & 0xC0) != 0x80) {
+                cp = -1;        /* continuation byte missing */
+                goto out;
+            }
+            p++;
+            cp <<= 6;
+            cp |= byte & 0x3F;
+        }
+        if (cp > 0x10FFFF) {
+            cp = -1;            /* beyond Unicode range */
+        } else if ((cp >= 0xFDD0 && cp <= 0xFDEF)
+                   || (cp & 0xFFFE) == 0xFFFE) {
+            cp = -1;            /* noncharacter */
+        } else if (cp >= 0xD800 && cp <= 0xDFFF) {
+            cp = -1;            /* surrogate code point */
+        } else if (cp < min_cp[len - 2] && !(cp == 0 && len == 2)) {
+            cp = -1;            /* overlong, not \xC0\x80 */
+        }
+    }
+
+out:
+    *end = (char *)p;
+    return cp;
+}