💾 Archived View for gemini.thededem.de › lc19 › src › src › util.c captured on 2024-07-08 at 23:39:28.

View Raw

More Information

⬅️ Previous capture (2021-12-03)

-=-=-=-=-=-=-

/* Copyright 2020, 2021 Lukas Wedeking
 *
 * This file is part of LC19.
 *
 * LC19 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 3 of the License, or
 * (at your option) any later version.
 *
 * LC19 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 LC19.  If not, see <https://www.gnu.org/licenses/>.
 */

#include "../include/util.h"

#include<assert.h>
#include<stdarg.h>
#include<stdio.h>
#include<stdlib.h>
#include<string.h>
#include<time.h>

size_t
util_utf8_get_codepoint(const char *s, size_t max_length,
		unsigned char codepoint[3])
{
	assert(codepoint != NULL);

	size_t length = 0;
	codepoint[0] = 0x0;
	codepoint[1] = 0x0;
	codepoint[2] = 0x0;

	/*
	 * Check for one, two, three and four byte UTF-8 character. The first
	 * byte of a UTF-8 character signifies the length of the character:
	 *     0b0xxxxxxx: 1 byte (ascii)
	 *     0b110xxxxx: 2 bytes
	 *     0b1110xxxx: 3 bytes
	 *     0b11110xxx: 4 bytes
	 *
	 * The following bytes in a multi-byte UTF-8 character all have the
	 * form:
	 *     0b10xxxxxx
	 *
	 * To check, whether a byte is the start of a mutlti-byte UTF-8
	 * character, we use the bitwise & operator with the byte and the values
	 *     0b10000000
	 *     0b11100000
	 *     0b11110000
	 *     0b11111000
	 * and check that the results are
	 *     0b00000000
	 *     0b11000000
	 *     0b11100000
	 *     0b11110000
	 * respectively.
	 */
	if (max_length >= 1 && (s[0] & 0x80) == 0x0) {
		length = 1;
		codepoint[2] = s[0];
	} else if (max_length >= 2 && (s[0] & 0xe0) == 0xc0
			&& (s[1] & 0xc0) == 0x80) {
		length = 2;
		codepoint[1] = (s[0] & 0x1f) >> 2;
		codepoint[2] = (s[0] & 0x1f) << 6;
		codepoint[2] |= s[1] & 0x3f;
	} else if (max_length >= 3 && (s[0] & 0xf0) == 0xe0
			&& (s[1] & 0xc0) == 0x80
			&& (s[1] & 0xc0) == 0x80) {
		length = 3;
		codepoint[1] = (s[0] & 0xf) << 4;
		codepoint[1] |= (s[1] & 0x3f) >> 2;
		codepoint[2] = (s[1] & 0x3f) << 6;
		codepoint[2] |= s[2] & 0x3f;
	} else if (max_length >= 4 && (s[0] & 0xf8) == 0xf0
			&& (s[1] & 0xc0) == 0x80
			&& (s[1] & 0xc0) == 0x80
			&& (s[1] & 0xc0) == 0x80) {
		length = 4;
		codepoint[0] = (s[0] & 0x7) << 2;
		codepoint[0] |= (s[1] & 0x3f) >> 4;
		codepoint[1] = (s[1] & 0x3f) << 4;
		codepoint[1] |= (s[2] & 0x3f) >> 2;
		codepoint[2] = (s[2] & 0x3f) << 6;
		codepoint[2] |= s[3] & 0x3f;
	}
	return length;
}

void
log_msg(enum Loglevel level, const char *fmt, ...) {
	extern enum Loglevel loglevel;
	if (level > loglevel) {
		return;
	}

	time_t now_stamp = time(NULL);
	if (now_stamp >= 0) {
		struct tm *now_struct = localtime(&now_stamp);
		fprintf(stderr, "%d-%.2d-%.2dT%.2d:%.2d:%.2d ",
				now_struct->tm_year + 1900,
				now_struct->tm_mon + 1, now_struct->tm_mday,
				now_struct->tm_hour, now_struct->tm_min,
				now_struct->tm_sec);
	}

	switch (level) {
	case LOGLEVEL_ERROR:
		fprintf(stderr, "ERROR ");
		break;
	case LOGLEVEL_INFO:
		fprintf(stderr, "INFO ");
		break;
	case LOGLEVEL_DEBUG:
		fprintf(stderr, "DEBUG ");
		break;
	}

	/*
	 * Add a newline at the end of fmt.
	 */
	size_t fmt_len = strlen(fmt);
	char *fmt_nl = calloc(fmt_len + 2, sizeof(char));
	strcpy(fmt_nl, fmt);
	fmt_nl[fmt_len] = '\n';

	va_list args;
	va_start(args, fmt);
	vfprintf(stderr, fmt_nl, args);
	va_end(args);

	free(fmt_nl);
	fflush(stderr);
}

size_t
util_strcpy(char *dest, const char *src, size_t max)
{
	size_t i = 0;
	while (i < max && src[i] != 0x0) {
		dest[i] = src[i];
		i++;
	}
	if (i+1 < max) {
		dest[i+1] = 0x0;
	} else {
		dest[i] = 0x0;
		i--;
	}
	return i;
}

size_t
util_mime_type(const char *mime_str, char *dest, size_t size)
{
	size_t len = 0;
	while (len < size && mime_str[len] != 0x0 && mime_str[len] != ';'
			&& mime_str[len] != ' ') {
		len++;
	}
	strncpy(dest, mime_str, len);
	return len;
}

size_t
util_mime_next_param(const char *param_str, char *dest, size_t size)
{
	size_t w = 0;
	for (size_t i = 0; param_str[i] != 0x0 && param_str[i] != ';'
			&& param_str[i] != '=' && w < size - 1; i++) {
		if (param_str[i] == ' ') {
			continue;
		} else {
			dest[w] = param_str[i];
			w++;
		}
	}
	dest[w] = 0x0;
	return w;
}