1 /*
2 * Copyright (c) 2016, 2019, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
54 * @param src the {@code CharSequence} to be scanned
55 * @param off offset to start looking for the next boundary in the src
56 * @param limit limit offset in the src (exclusive)
57 * @return the next possible boundary
58 */
59 static int nextBoundary(CharSequence src, int off, int limit) {
60 Objects.checkFromToIndex(off, limit, src.length());
61
62 int ch0 = Character.codePointAt(src, 0);
63 int ret = Character.charCount(ch0);
64 int ch1;
65 // indicates whether gb11 or gb12 is underway
66 int t0 = getGraphemeType(ch0);
67 int riCount = t0 == RI ? 1 : 0;
68 boolean gb11 = t0 == EXTENDED_PICTOGRAPHIC;
69 while (ret < limit) {
70 ch1 = Character.codePointAt(src, ret);
71 int t1 = getGraphemeType(ch1);
72
73 if (gb11 && t0 == ZWJ && t1 == EXTENDED_PICTOGRAPHIC) {
74 gb11 = false;
75 } else if (riCount % 2 == 1 && t0 == RI && t1 == RI) {
76 // continue for gb12
77 } else if (rules[t0][t1]) {
78 if (ret > off) {
79 break;
80 } else {
81 gb11 = t1 == EXTENDED_PICTOGRAPHIC;
82 riCount = 0;
83 }
84 }
85
86 riCount += (t1 == RI) ? 1 : 0;
87 t0 = t1;
88
89 ret += Character.charCount(ch1);
90 }
91 return ret;
92 }
93
94 // types
|
1 /*
2 * Copyright (c) 2016, 2020, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
54 * @param src the {@code CharSequence} to be scanned
55 * @param off offset to start looking for the next boundary in the src
56 * @param limit limit offset in the src (exclusive)
57 * @return the next possible boundary
58 */
59 static int nextBoundary(CharSequence src, int off, int limit) {
60 Objects.checkFromToIndex(off, limit, src.length());
61
62 int ch0 = Character.codePointAt(src, 0);
63 int ret = Character.charCount(ch0);
64 int ch1;
65 // indicates whether gb11 or gb12 is underway
66 int t0 = getGraphemeType(ch0);
67 int riCount = t0 == RI ? 1 : 0;
68 boolean gb11 = t0 == EXTENDED_PICTOGRAPHIC;
69 while (ret < limit) {
70 ch1 = Character.codePointAt(src, ret);
71 int t1 = getGraphemeType(ch1);
72
73 if (gb11 && t0 == ZWJ && t1 == EXTENDED_PICTOGRAPHIC) {
74 // continue for gb11
75 } else if (riCount % 2 == 1 && t0 == RI && t1 == RI) {
76 // continue for gb12
77 } else if (rules[t0][t1]) {
78 if (ret > off) {
79 break;
80 } else {
81 gb11 = t1 == EXTENDED_PICTOGRAPHIC;
82 riCount = 0;
83 }
84 }
85
86 riCount += (t1 == RI) ? 1 : 0;
87 t0 = t1;
88
89 ret += Character.charCount(ch1);
90 }
91 return ret;
92 }
93
94 // types
|