summaryrefslogtreecommitdiff
path: root/src/utf16_be.c
diff options
context:
space:
mode:
authorJörg Frings-Fürst <debian@jff-webhosting.net>2016-05-10 05:15:59 +0200
committerJörg Frings-Fürst <debian@jff-webhosting.net>2016-05-10 05:15:59 +0200
commite706cbe5496e1829d1ddbe4d5bb0a6728204e510 (patch)
treec72d1848ac6aef07703848d0ffbe80f1336a81cd /src/utf16_be.c
parent69ab3addbc2dbbc90c311b2845cd25a2159435cd (diff)
parent5e01a4852b31d537307994248869caf38b4023cc (diff)
new upstream release
Diffstat (limited to 'src/utf16_be.c')
-rw-r--r--src/utf16_be.c228
1 files changed, 228 insertions, 0 deletions
diff --git a/src/utf16_be.c b/src/utf16_be.c
new file mode 100644
index 0000000..e93b42a
--- /dev/null
+++ b/src/utf16_be.c
@@ -0,0 +1,228 @@
+/**********************************************************************
+ utf16_be.c - Oniguruma (regular expression library)
+**********************************************************************/
+/*-
+ * Copyright (c) 2002-2016 K.Kosako <sndgk393 AT ybb DOT ne DOT jp>
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#include "regenc.h"
+
+static const int EncLen_UTF16[] = {
+ 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, 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, 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, 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, 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, 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, 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, 2, 2, 2, 2, 2, 2, 4, 4, 4, 4, 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, 2, 2, 2, 2, 2, 2
+};
+
+static int
+utf16be_mbc_enc_len(const UChar* p)
+{
+ return EncLen_UTF16[*p];
+}
+
+static int
+utf16be_is_mbc_newline(const UChar* p, const UChar* end)
+{
+ if (p + 1 < end) {
+ if (*(p+1) == 0x0a && *p == 0x00)
+ return 1;
+#ifdef USE_UNICODE_ALL_LINE_TERMINATORS
+ if ((
+#ifndef USE_CRNL_AS_LINE_TERMINATOR
+ *(p+1) == 0x0d ||
+#endif
+ *(p+1) == 0x85) && *p == 0x00)
+ return 1;
+
+ if (*p == 0x20 && (*(p+1) == 0x29 || *(p+1) == 0x28))
+ return 1;
+#endif
+ }
+ return 0;
+}
+
+static OnigCodePoint
+utf16be_mbc_to_code(const UChar* p, const UChar* end ARG_UNUSED)
+{
+ OnigCodePoint code;
+
+ if (UTF16_IS_SURROGATE_FIRST(*p)) {
+ code = ((((p[0] - 0xd8) << 2) + ((p[1] & 0xc0) >> 6) + 1) << 16)
+ + ((((p[1] & 0x3f) << 2) + (p[2] - 0xdc)) << 8)
+ + p[3];
+ }
+ else {
+ code = p[0] * 256 + p[1];
+ }
+ return code;
+}
+
+static int
+utf16be_code_to_mbclen(OnigCodePoint code)
+{
+ return (code > 0xffff ? 4 : 2);
+}
+
+static int
+utf16be_code_to_mbc(OnigCodePoint code, UChar *buf)
+{
+ UChar* p = buf;
+
+ if (code > 0xffff) {
+ unsigned int plane, high;
+
+ plane = (code >> 16) - 1;
+ *p++ = (plane >> 2) + 0xd8;
+ high = (code & 0xff00) >> 8;
+ *p++ = ((plane & 0x03) << 6) + (high >> 2);
+ *p++ = (high & 0x03) + 0xdc;
+ *p = (UChar )(code & 0xff);
+ return 4;
+ }
+ else {
+ *p++ = (UChar )((code & 0xff00) >> 8);
+ *p++ = (UChar )(code & 0xff);
+ return 2;
+ }
+}
+
+static int
+utf16be_mbc_case_fold(OnigCaseFoldType flag,
+ const UChar** pp, const UChar* end, UChar* fold)
+{
+ const UChar* p = *pp;
+
+ if (ONIGENC_IS_ASCII_CODE(*(p+1)) && *p == 0) {
+ p++;
+#ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
+ if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
+ if (*p == 0x49) {
+ *fold++ = 0x01;
+ *fold = 0x31;
+ (*pp) += 2;
+ return 2;
+ }
+ }
+#endif
+
+ *fold++ = 0;
+ *fold = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*p);
+ *pp += 2;
+ return 2;
+ }
+ else
+ return onigenc_unicode_mbc_case_fold(ONIG_ENCODING_UTF16_BE, flag,
+ pp, end, fold);
+}
+
+#if 0
+static int
+utf16be_is_mbc_ambiguous(OnigCaseFoldType flag, const UChar** pp, const UChar* end)
+{
+ const UChar* p = *pp;
+
+ (*pp) += EncLen_UTF16[*p];
+
+ if (*p == 0) {
+ int c, v;
+
+ p++;
+ if (*p == 0xdf && (flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
+ return TRUE;
+ }
+
+ c = *p;
+ v = ONIGENC_IS_UNICODE_ISO_8859_1_BIT_CTYPE(c,
+ (BIT_CTYPE_UPPER | BIT_CTYPE_LOWER));
+
+ if ((v | BIT_CTYPE_LOWER) != 0) {
+ /* 0xaa, 0xb5, 0xba are lower case letter, but can't convert. */
+ if (c >= 0xaa && c <= 0xba)
+ return FALSE;
+ else
+ return TRUE;
+ }
+ return (v != 0 ? TRUE : FALSE);
+ }
+
+ return FALSE;
+}
+#endif
+
+static UChar*
+utf16be_left_adjust_char_head(const UChar* start, const UChar* s)
+{
+ if (s <= start) return (UChar* )s;
+
+ if ((s - start) % 2 == 1) {
+ s--;
+ }
+
+ if (UTF16_IS_SURROGATE_SECOND(*s) && s > start + 1)
+ s -= 2;
+
+ return (UChar* )s;
+}
+
+static int
+utf16be_get_case_fold_codes_by_str(OnigCaseFoldType flag,
+ const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[])
+{
+ return onigenc_unicode_get_case_fold_codes_by_str(ONIG_ENCODING_UTF16_BE,
+ flag, p, end, items);
+}
+
+OnigEncodingType OnigEncodingUTF16_BE = {
+ utf16be_mbc_enc_len,
+ "UTF-16BE", /* name */
+ 4, /* max byte length */
+ 2, /* min byte length */
+ utf16be_is_mbc_newline,
+ utf16be_mbc_to_code,
+ utf16be_code_to_mbclen,
+ utf16be_code_to_mbc,
+ utf16be_mbc_case_fold,
+ onigenc_unicode_apply_all_case_fold,
+ utf16be_get_case_fold_codes_by_str,
+ onigenc_unicode_property_name_to_ctype,
+ onigenc_unicode_is_code_ctype,
+ onigenc_utf16_32_get_ctype_code_range,
+ utf16be_left_adjust_char_head,
+ onigenc_always_false_is_allowed_reverse_match,
+ NULL, /* init */
+ NULL /* is_initialized */
+};