blogc: added utf8 validation

1 files changed, 88 insertions, 0 deletions

diff --git a/src/utf8.c b/src/utf8.c
new file mode 100644
index 0000000..deea46d
--- /dev/null
+++ b/src/utf8.c
@@ -0,0 +1,88 @@
+/*
+ * blogc: A blog compiler.
+ * Copyright (c) 2008-2010 Bjoern Hoehrmann <bjoern@hoehrmann.de>
+ * Copyright (c) 2016 Rafael G. Martins <rafael@rafaelmartins.eng.br>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+// Based on Bjoern Hoehrmann's algorithm.
+// See http://bjoern.hoehrmann.de/utf-8/decoder/dfa/ for details.
+
+#include <stdbool.h>
+#include <inttypes.h>
+#include "utils.h"
+
+#define UTF8_ACCEPT 0
+#define UTF8_REJECT 12
+
+
+static const uint8_t utf8d[] = {
+    // The first part of the table maps bytes to character classes that
+    // to reduce the size of the transition table and create bitmasks.
+     0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+     0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+     0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+     0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+     1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,  9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,
+     7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
+     8,8,2,2,2,2,2,2,2,2,2,2,2,2,2,2,  2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
+    10,3,3,3,3,3,3,3,3,3,3,3,3,4,3,3, 11,6,6,6,5,8,8,8,8,8,8,8,8,8,8,8,
+
+    // The second part is a transition table that maps a combination
+    // of a state of the automaton and a character class to a state.
+     0,12,24,36,60,96,84,12,12,12,48,72, 12,12,12,12,12,12,12,12,12,12,12,12,
+    12, 0,12,12,12,12,12, 0,12, 0,12,12, 12,24,12,12,12,12,12,24,12,24,12,12,
+    12,12,12,12,12,12,12,24,12,12,12,12, 12,24,12,12,12,12,12,12,12,24,12,12,
+    12,12,12,12,12,12,12,36,12,36,12,12, 12,36,12,12,12,12,12,36,12,36,12,12,
+    12,36,12,12,12,12,12,12,12,12,12,12,
+};
+
+
+static uint32_t inline
+decode(uint32_t* state, uint32_t* codep, uint32_t byte) {
+    uint32_t type = utf8d[byte];
+
+    *codep = (*state != UTF8_ACCEPT) ?
+        (byte & 0x3fu) | (*codep << 6) :
+        (0xff >> type) & (byte);
+
+    *state = utf8d[256 + *state + type];
+    return *state;
+}
+
+
+bool
+blogc_utf8_validate(const uint8_t *str, size_t len)
+{
+    uint32_t codepoint;
+    uint32_t state = 0;
+
+    for (size_t i = 0; i < len; i++)
+        decode(&state, &codepoint, str[i]);
+
+    return state == UTF8_ACCEPT;
+}
+
+
+bool
+blogc_utf8_validate_str(sb_string_t *str)
+{
+    return blogc_utf8_validate((uint8_t*) str->str, str->len);
+}