reset to only read in file

This commit is contained in:
acereca 2023-03-11 15:51:45 +01:00
parent f6fca262c6
commit b37eee1fe1
4 changed files with 0 additions and 141 deletions

35
Cargo.lock generated
View File

@ -2,41 +2,6 @@
# It is not intended for manual editing.
version = 3
[[package]]
name = "aho-corasick"
version = "0.7.20"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cc936419f96fa211c1b9166887b38e5e40b19958e5b895be7c1f93adec7071ac"
dependencies = [
"memchr",
]
[[package]]
name = "memchr"
version = "2.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2dffe52ecf27772e601905b7522cb4ef790d2cc203488bbd0e2fe85fcb74566d"
[[package]]
name = "regex"
version = "1.7.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "48aaa5748ba571fb95cd2c85c09f629215d3a6ece942baa100950af03a34f733"
dependencies = [
"aho-corasick",
"memchr",
"regex-syntax",
]
[[package]]
name = "regex-syntax"
version = "0.6.28"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "456c603be3e8d448b072f410900c09faf164fbce2d480456f50eea6e25f9c848"
[[package]]
name = "skill-oxide"
version = "0.1.0"
dependencies = [
"regex",
]

View File

@ -6,4 +6,3 @@ edition = "2021"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies]
regex = "1"

View File

@ -1,17 +1,8 @@
use std::{env, fs, io::Read};
use regex::Regex;
use states::Tokenizer;
mod states;
fn main() {
let args: Vec<String> = env::args().collect();
let re = Regex::new(r"((?P<comment>;)|(?P<word>\b\w+\b))").unwrap();
let mut file = fs::File::open(args[1].as_str()).expect("msg");
let mut data = String::new();
file.read_to_string(&mut data).expect("msg");
let mut tokenizer = Tokenizer::new();
tokenizer.read_in(data);
}

View File

@ -1,96 +0,0 @@
#[derive(Debug)]
pub enum CursorState {
Comment,
List,
Token,
Literal,
Operator
}
pub struct Token {
typ: CursorState,
content: Vec<Token>,
}
pub struct Tokenizer {
stateStack: Vec<CursorState>,
tokenTree: Vec<Token>,
}
impl Tokenizer {
pub fn new() -> Tokenizer {
Tokenizer {
stateStack: Vec::new(),
tokenTree: Vec::new(),
}
}
fn match_char(&mut self, c: char) {
match self.stateStack.last() {
None => match c {
c if c.is_whitespace() => {}
';' => {
self.stateStack.push(CursorState::Comment);
}
'(' => {
self.stateStack.push(CursorState::List);
}
c if c.is_alphanumeric() => {}
_ => {
println!("{}", c);
panic!("not a comment, list or symbol ");
}
},
Some(CursorState::Comment) => match c {
c if c.is_control() => {
self.stateStack.pop();
}
c if c.is_alphanumeric() => {}
c if c.is_whitespace() => {}
_ => {}
},
Some(CursorState::List) => match c {
'(' => {
self.stateStack.push(CursorState::List);
}
')' => {
self.stateStack.pop();
}
c if c.is_alphabetic() => {
self.stateStack.push(CursorState::Token);
}
c if c.is_numeric() => {
self.stateStack.push(CursorState::Literal);
}
'"' => {
self.stateStack.push(CursorState::Literal);
}
_ => {}
},
Some(CursorState::Token) => match c {
c if !c.is_alphanumeric() => {
self.stateStack.pop();
self.match_char(c);
}
_ => {}
},
Some(CursorState::Literal) => match c {
c if c.is_whitespace() => {
self.stateStack.pop();
}
'"' => {
self.stateStack.pop();
}
_ => {}
},
_ => {}
}
}
pub fn read_in(&mut self, content: String) {
for c in content.chars() {
self.match_char(c);
println!("{} -> {}: {:?}", c, self.stateStack.len(), self.stateStack.last().clone());
}
}
}