[utf8] Add ability to accumulate Unicode characters from UTF-8 bytes

Signed-off-by: Michael Brown <mcb30@ipxe.org>

2 files changed, 206 insertions, 0 deletions

diff --git a/src/core/utf8.c b/src/core/utf8.c
new file mode 100644
index 0000000..4ee01ba
--- /dev/null
+++ b/src/core/utf8.c
@@ -0,0 +1,137 @@
+/*
+ * Copyright (C) 2022 Michael Brown <mbrown@fensystems.co.uk>.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or any later version.
+ *
+ * This program 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
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ *
+ * You can also choose to distribute this program under the terms of
+ * the Unmodified Binary Distribution Licence (as given in the file
+ * COPYING.UBDL), provided that you have satisfied its requirements.
+ */
+
+FILE_LICENCE ( GPL2_OR_LATER_OR_UBDL );
+
+#include <stdint.h>
+#include <assert.h>
+#include <ipxe/utf8.h>
+
+/** @file
+ *
+ * UTF-8 Unicode encoding
+ *
+ */
+
+/**
+ * Accumulate Unicode character from UTF-8 byte sequence
+ *
+ * @v utf8		UTF-8 accumulator
+ * @v byte		UTF-8 byte
+ * @ret character	Unicode character, or 0 if incomplete
+ */
+unsigned int utf8_accumulate ( struct utf8_accumulator *utf8, uint8_t byte ) {
+	static unsigned int min[] = {
+		UTF8_MIN_TWO,
+		UTF8_MIN_THREE,
+		UTF8_MIN_FOUR,
+	};
+	unsigned int shift;
+	unsigned int len;
+	uint8_t tmp;
+
+	/* Handle continuation bytes */
+	if ( UTF8_IS_CONTINUATION ( byte ) ) {
+
+		/* Fail if this is an unexpected continuation byte */
+		if ( utf8->remaining == 0 ) {
+			DBGC ( utf8, "UTF8 %p unexpected %02x\n", utf8, byte );
+			return UTF8_INVALID;
+		}
+
+		/* Apply continuation byte */
+		utf8->character <<= UTF8_CONTINUATION_BITS;
+		utf8->character |= ( byte & UTF8_CONTINUATION_MASK );
+
+		/* Return 0 if more continuation bytes are expected */
+		if ( --utf8->remaining != 0 )
+			return 0;
+
+		/* Fail if sequence is illegal */
+		if ( utf8->character < utf8->min ) {
+			DBGC ( utf8, "UTF8 %p illegal %02x\n", utf8,
+			       utf8->character );
+			return UTF8_INVALID;
+		}
+
+		/* Sanity check */
+		assert ( utf8->character != 0 );
+
+		/* Return completed character */
+		DBGC2 ( utf8, "UTF8 %p accumulated %02x\n",
+			utf8, utf8->character );
+		return utf8->character;
+	}
+
+	/* Reset state and report failure if this is an unexpected
+	 * non-continuation byte.  Do not return UTF8_INVALID since
+	 * doing so could cause us to drop a valid ASCII character.
+	 */
+	if ( utf8->remaining != 0 ) {
+		shift = ( utf8->remaining * UTF8_CONTINUATION_BITS );
+		DBGC ( utf8, "UTF8 %p unexpected %02x (partial %02x/%02x)\n",
+		       utf8, byte, ( utf8->character << shift ),
+		       ( ( 1 << shift ) - 1 ) );
+		utf8->remaining = 0;
+	}
+
+	/* Handle initial bytes */
+	if ( ! UTF8_IS_ASCII ( byte ) ) {
+
+		/* Sanity check */
+		assert ( utf8->remaining == 0 );
+
+		/* Count total number of bytes in sequence */
+		tmp = byte;
+		len = 0;
+		while ( tmp & UTF8_HIGH_BIT ) {
+			tmp <<= 1;
+			len++;
+		}
+
+		/* Check for illegal length */
+		if ( len > UTF8_MAX_LEN ) {
+			DBGC ( utf8, "UTF8 %p illegal %02x length %d\n",
+			       utf8, byte, len );
+			return UTF8_INVALID;
+		}
+
+		/* Store initial bits of character */
+		utf8->character = ( tmp >> len );
+
+		/* Store number of bytes remaining */
+		len--;
+		utf8->remaining = len;
+		assert ( utf8->remaining > 0 );
+
+		/* Store minimum legal value */
+		utf8->min = min[ len - 1 ];
+		assert ( utf8->min > 0 );
+
+		/* Await continuation bytes */
+		return 0;
+	}
+
+	/* Handle ASCII bytes */
+	return byte;
+}
diff --git a/src/include/ipxe/utf8.h b/src/include/ipxe/utf8.h
new file mode 100644
index 0000000..299c255
--- /dev/null
+++ b/src/include/ipxe/utf8.h
@@ -0,0 +1,69 @@
+#ifndef _IPXE_UTF8_H
+#define _IPXE_UTF8_H
+
+/** @file
+ *
+ * UTF-8 Unicode encoding
+ *
+ */
+
+FILE_LICENCE ( GPL2_OR_LATER_OR_UBDL );
+
+#include <stdint.h>
+
+/** Maximum length of UTF-8 sequence */
+#define UTF8_MAX_LEN 4
+
+/** Minimum legal value for two-byte UTF-8 sequence */
+#define UTF8_MIN_TWO 0x80
+
+/** Minimum legal value for three-byte UTF-8 sequence */
+#define UTF8_MIN_THREE 0x800
+
+/** Minimum legal value for four-byte UTF-8 sequence */
+#define UTF8_MIN_FOUR 0x10000
+
+/** High bit of UTF-8 bytes */
+#define UTF8_HIGH_BIT 0x80
+
+/** Number of data bits in each continuation byte */
+#define UTF8_CONTINUATION_BITS 6
+
+/** Bit mask for data bits in a continuation byte */
+#define UTF8_CONTINUATION_MASK ( ( 1 << UTF8_CONTINUATION_BITS ) - 1 )
+
+/** Non-data bits in a continuation byte */
+#define UTF8_CONTINUATION 0x80
+
+/** Check for a continuation byte
+ *
+ * @v byte		UTF-8 byte
+ * @ret is_continuation	Byte is a continuation byte
+ */
+#define UTF8_IS_CONTINUATION( byte ) \
+	( ( (byte) & ~UTF8_CONTINUATION_MASK ) == UTF8_CONTINUATION )
+
+/** Check for an ASCII byte
+ *
+ * @v byte		UTF-8 byte
+ * @ret is_ascii	Byte is an ASCII byte
+ */
+#define UTF8_IS_ASCII( byte ) ( ! ( (byte) & UTF8_HIGH_BIT ) )
+
+/** Invalid character returned when decoding fails */
+#define UTF8_INVALID 0xfffd
+
+/** A UTF-8 character accumulator */
+struct utf8_accumulator {
+	/** Character in progress */
+	unsigned int character;
+	/** Number of remaining continuation bytes */
+	unsigned int remaining;
+	/** Minimum legal character */
+	unsigned int min;
+};
+
+extern unsigned int utf8_accumulate ( struct utf8_accumulator *utf8,
+				      uint8_t byte );
+
+#endif /* _IPXE_UTF8_H */