There are three character string types in this program: null-terminated (rchar) strings ala 'C' language, UTF-8 (CONSTANT_Utf8_info) strings, and Unicode (jchar)[] strings.
Copyright 2005 The Apache Software Foundation or its licensors, as applicable.
Licensed under the Apache License, Version 2.0 ("the License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and limitations under the License.
Definition in file unicode.h.
Go to the source code of this file.
Functions | |
ARCH_COPYRIGHT_APACHE (unicode, h,"$URL: https://svn.apache.org/path/name/unicode.h $ $Id: unicode.h 0 09/28/2005 dlydick $") | |
cp_info_dup * | unicode_cnv2utf (jchar *inbfr, jshort length) |
jshort | unicode_strcmp (jchar *us1, u2 l1, jchar *us2, u2 l2) |
Compare two Unicode strings of any length, s1 minus s2. |
|
|
|
< '\u0001', UTF-8 representation < '\u007f', UTF-8 representation < '\u0080', Unicode representation < '\u07ff', Unicode representation < '\u0000', Unicode representation < '\u0001', UTF-8 representation < '\u007f', UTF-8 representation < Bits 0-6 contain data (except != 0, or NUL) < '\u0080', Unicode representation < '\u07ff', Unicode representation < '\u0000', Unicode representation < Move first byte up to bits 10-6 < Bottom 5 bits contain data bits 10-6 < Top 3 bits are '110' < Bottom 6 bits contain data bits 0-5 < Top 2 bits are '10' ! Move first byte up to bits 15-12 ! Bottom 5 bits contain data bits 15-12 ! Top 4 bits are '1110' ! Move second byte up to bits 10-6 ! Bottom 6 bits contain data bits 11-6 ! Top 2 bits are '10' ! Bottom 6 bits contain data bits 5-0 ! Top 2 bits are '10' Definition at line 91 of file unicode.c. References CONSTANT_Utf8_info::bytes, CONSTANT_Utf8, HEAP_GET_DATA, CONSTANT_Utf8_info::length, PTR_THIS_CP_Utf8, rfalse, CONSTANT_Utf8_info::tag, UNICODE_DOUBLE_MAX, UNICODE_DOUBLE_MIN, UNICODE_DOUBLE_NUL, UTF8_DOUBLE_FIRST_MASK0, UTF8_DOUBLE_FIRST_SHIFT, UTF8_DOUBLE_FIRST_VAL, UTF8_DOUBLE_SECOND_MASK0, UTF8_DOUBLE_SECOND_VAL, UTF8_SINGLE_MASK0, UTF8_SINGLE_MAX, UTF8_SINGLE_MIN, UTF8_TRIPLE_FIRST_MASK0, UTF8_TRIPLE_FIRST_SHIFT, UTF8_TRIPLE_FIRST_VAL, UTF8_TRIPLE_SECOND_MASK0, UTF8_TRIPLE_SECOND_SHIFT, UTF8_TRIPLE_SECOND_VAL, UTF8_TRIPLE_THIRD_MASK0, and UTF8_TRIPLE_THIRD_VAL. |
|
Compare two Unicode strings of any length, s1 minus s2.
|