cscg24-guacamole

CSCG 2024 Challenge 'Guacamole Mashup'
git clone https://git.sinitax.com/sinitax/cscg24-guacamole
Log | Files | Refs | sfeed.txt

unicode.h (2844B)

      1/*
      2 * Licensed to the Apache Software Foundation (ASF) under one
      3 * or more contributor license agreements.  See the NOTICE file
      4 * distributed with this work for additional information
      5 * regarding copyright ownership.  The ASF licenses this file
      6 * to you under the Apache License, Version 2.0 (the
      7 * "License"); you may not use this file except in compliance
      8 * with the License.  You may obtain a copy of the License at
      9 *
     10 *   http://www.apache.org/licenses/LICENSE-2.0
     11 *
     12 * Unless required by applicable law or agreed to in writing,
     13 * software distributed under the License is distributed on an
     14 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
     15 * KIND, either express or implied.  See the License for the
     16 * specific language governing permissions and limitations
     17 * under the License.
     18 */
     19
     20
     21#ifndef _GUAC_UNICODE_H
     22#define _GUAC_UNICODE_H
     23
     24/**
     25 * Provides functions for manipulating Unicode strings.
     26 *
     27 * @file unicode.h
     28 */
     29
     30#include <stddef.h>
     31
     32/**
     33 * Given the initial byte of a single UTF-8 character, returns the overall
     34 * byte size of the entire character.
     35 *
     36 * @param c The initial byte of the character to check.
     37 * @return The number of bytes in the given character overall.
     38 */
     39size_t guac_utf8_charsize(unsigned char c);
     40
     41/**
     42 * Given a UTF-8-encoded string, returns the length of the string in characters
     43 * (not bytes).
     44 *
     45 * @param str The UTF-8 string to calculate the length of.
     46 * @return The length in characters of the given UTF-8 string.
     47 */
     48size_t guac_utf8_strlen(const char* str);
     49
     50/**
     51 * Given destination buffer and its length, writes the given codepoint as UTF-8
     52 * to the buffer, returning the number of bytes written. If there is not enough
     53 * space in the buffer to write the character, no bytes are written at all.
     54 *
     55 * @param codepoint The Unicode codepoint to write to the buffer.
     56 * @param utf8 The buffer to write to.
     57 * @param length The length of the buffer, in bytes.
     58 * @return The number of bytes written, which may be zero if there is not
     59 *         enough space in the buffer to write the UTF-8 character.
     60 */
     61int guac_utf8_write(int codepoint, char* utf8, int length);
     62
     63/**
     64 * Given a buffer containing UTF-8 characters, reads the first codepoint in the
     65 * buffer, returning the length of the codepoint in bytes. If no codepoint
     66 * could be read, zero is returned.
     67 *
     68 * @param utf8 A buffer containing UTF-8 characters.
     69 * @param length The length of the buffer, in bytes.
     70 * @param codepoint A pointer to an integer which will contain the codepoint
     71 *                  read, if any. If no character can be read, the integer
     72 *                  will be left untouched.
     73 * @return The number of bytes read, which may be zero if there is not enough
     74 *         space in the buffer to read a character.
     75 */
     76int guac_utf8_read(const char* utf8, int length, int* codepoint);
     77
     78#endif
     79