expressions/expr.cpp
2024-08-26 18:01:03 +08:00

122 lines
3.4 KiB
C++

/***************************************************************************************
* Copyright (c) 2014-2022 Zihao Yu, Nanjing University
*
* NEMU is licensed under Mulan PSL v2.
* You can use this software according to the terms and conditions of the Mulan PSL v2.
* You may obtain a copy of Mulan PSL v2 at:
* http://license.coscl.org.cn/MulanPSL2
*
* THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND,
* EITHER EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT,
* MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.
*
* See the Mulan PSL v2 for more details.
***************************************************************************************/
// Modified by: Zhiyi Zhang in 2024.08
#include "common.h"
/* We use the POSIX regex functions to process regular expressions.
* Type 'man regex' for more information about POSIX regex functions.
*/
#include <regex>
enum {
TK_NOTYPE = 256, TK_EQ,
/* TODO: Add more token types */
};
static struct rule {
const char *regex;
int token_type;
} rules[] = {
/* TODO: Add more rules.
* Pay attention to the precedence level of different rules.
*/
{" +", TK_NOTYPE}, // spaces
{"\\+", '+'}, // plus
{"==", TK_EQ}, // equal
};
#define NR_REGEX ARRLEN(rules)
static std::regex re[NR_REGEX] = {};
/* Rules are used for many times.
* Therefore we compile them only once before any usage.
*/
void init_regex() {
for (int i = 0; i < NR_REGEX; i ++) {
try {
re[i] = std::regex(rules[i].regex, std::regex_constants::ECMAScript);
}
catch(const std::regex_error & e) {
panic("regex compilation failed: %s\n%s", e.what(), rules[i].regex);
}
}
}
typedef struct token {
int type;
char str[32];
} Token;
static Token tokens[32] __attribute__((used)) = {};
static int nr_token __attribute__((used)) = 0;
static bool make_token(char *e) {
int position = 0;
int i;
std::cmatch pmatch;
nr_token = 0;
while (e[position] != '\0') {
/* Try all rules one by one. */
for (i = 0; i < NR_REGEX; i ++) {
// if (regexec(&re[i], e + position, 1, &pmatch, 0) == 0 && pmatch.rm_so == 0) {
if (std::regex_search(e + position, pmatch, re[i], std::regex_constants::match_continuous)) {
char *substr_start = e + position;
int substr_len = pmatch.length();
Log("match rules[%d] = \"%s\" at position %d with len %d: %.*s",
i, rules[i].regex, position, substr_len, substr_len, substr_start);
position += substr_len;
/* TODO: Now a new token is recognized with rules[i]. Add codes
* to record the token in the array `tokens'. For certain types
* of tokens, some extra actions should be performed.
*/
switch (rules[i].token_type) {
default: TODO();
}
break;
}
}
if (i == NR_REGEX) {
printf("no match at position %d\n%s\n%*.s^\n", position, e, position, "");
return false;
}
}
return true;
}
uint32_t expr(char *e, bool *success) {
if (!make_token(e)) {
*success = false;
return 0;
}
/* TODO: Insert codes to evaluate the expression. */
TODO();
return 0;
}