raphael/minishell
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Added: Stdme as dependency

Browse source
This commit is contained in:
Maieul BOYER 2024-04-28 17:07:05 +02:00
parent e1659508c6
commit 78f0707574
No known key found for this signature in database
11 changed files with 11 additions and 447 deletions
Download patch file Download diff file Expand all files Collapse all files

6
.gitmodules vendored
View file

@ -1,3 +1,3 @@
[submodule "stdme"] [submodule "shcat_c/stdme"]
path = stdme path = shcat_c/stdme
url = git@github.com:maix0/stdme.git url = git@github.com:Maix0/stdme.git

1
rust/parser/.gitignore vendored
View file

@ -1 +0,0 @@
/target

7
rust/parser/Cargo.lock generated
View file

@ -1,7 +0,0 @@
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
version = 3
[[package]]
name = "parser-rs"
version = "0.1.0"

8
rust/parser/Cargo.toml
View file

@ -1,8 +0,0 @@
[package]
name = "parser-rs"
version = "0.1.0"
edition = "2021"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies]

31
rust/parser/src/adapt_in_c/includes/enum.h
View file

@ -1,31 +0,0 @@
/* ************************************************************************** */
/* */
/* ::: :::::::: */
/* enum.h :+: :+: :+: */
/* +:+ +:+ +:+ */
/* By: rparodi <rparodi@student.42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2024/03/28 12:44:05 by rparodi #+# #+# */
/* Updated: 2024/03/28 13:09:06 by rparodi ### ########.fr */
/* */
/* ************************************************************************** */
#ifndef ENUM_H
#define ENUM_H
#include "./rust_type.h"
enum e_separator_op
{
Semi,
Fork,
};
enum e_pipeline_kind
{
Or,
And,
};
#endif

33
rust/parser/src/adapt_in_c/includes/rust_type.h
View file

@ -1,33 +0,0 @@
/* ************************************************************************** */
/* */
/* ::: :::::::: */
/* rust_type.h :+: :+: :+: */
/* +:+ +:+ +:+ */
/* By: rparodi <rparodi@student.42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2024/03/28 12:50:51 by rparodi #+# #+# */
/* Updated: 2024/03/28 12:52:53 by rparodi ### ########.fr */
/* */
/* ************************************************************************** */
#ifndef RUST_TYPE_H
#define RUST_TYPE_H
# define bool int
# define true 1
# define false 0
# define u8 unsigned char
# define u16 unsigned short
# define u32 unsigned int
# define u64 unsigned long long
# define i8 char
# define i16 short
# define i32 int
# define i64 long long
# define usize size_t
# define isize ssize_t
# define f32 float
# define f64 double
#endif

29
rust/parser/src/adapt_in_c/includes/shcat.h
View file

@ -1,29 +0,0 @@
/* ************************************************************************** */
/* */
/* ::: :::::::: */
/* shcat.h :+: :+: :+: */
/* +:+ +:+ +:+ */
/* By: rparodi <rparodi@student.42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2024/03/28 12:42:55 by rparodi #+# #+# */
/* Updated: 2024/03/28 12:53:50 by rparodi ### ########.fr */
/* */
/* ************************************************************************** */
#ifndef SHCAT_H
#define SHCAT_H
# include <unistd.h>
# include <fcntl.h>
# include <stdlib.h>
# include <stdio.h>
# include <string.h>
# include <sys/types.h>
# include <sys/wait.h>
# include <stdlib.h>
# include <stdarg.h>
# include <stddef.h>
# include "./enum.h"
# include "./rust_type.h"
#endif

331
rust/parser/src/main.rs
View file

@ -1,331 +0,0 @@
#![allow(dead_code)]
use std::{borrow::Cow, collections::VecDeque, convert::Infallible as Never, pin::Pin};
type WORD = String;
type Rule2 = String;
type Rule3 = String;
struct SourceFile {
cmds: Vec<CompleteCommands>,
}
struct CompleteCommands {
// each Pipeline Must have a Separator, but the
// last Pipeline is optional
list: Vec<(Pipeline, Option<SeparatorOp>)>,
}
enum SeparatorOp {
Semi, /* ; */
Fork, /* & */
}
struct Pipeline {
bang: bool, // placed before the seqence
kind: Option<PipelineKind>, // placed after the seqence
seq: Vec<Commands>, // each cmd are piped into the next
}
enum PipelineKind {
Or, /* || */
And, /* && */
}
enum Commands {
Simple(SimpleCommand),
Compound(Never),
FuncDef(Never),
}
struct SimpleCommand {
prefix: Vec<CmdPrefix>,
cmd: Vec<WORD>, // First is rule 7a, then 7b
suffix: Vec<CmdSuffix>,
}
enum CmdPrefix {
IoRedirect(IoRedirect),
Assigment(Assigment),
}
enum CmdSuffix {
IoRedirect(IoRedirect),
Word(WORD),
}
struct IoRedirect {
io_file: Option<usize>,
io_kind: IoKind,
}
enum IoKind {
IoFile(IoFile),
IoHere(IoHere),
}
enum IoFile {
Less { filename: Rule2 }, /* < */
Greater { filename: Rule2 }, /* > */
LessAnd { filename: Rule2 }, /* <& */
GreaterAnd { filename: Rule2 }, /* >& */
DoubleGreater { filename: Rule2 }, /* >> */
LessGreater { filename: Rule2 }, /* <> */
Clobber { filename: Rule2 }, /* >| */
}
enum IoHere {
Dless { here_end: Rule3 }, /* << */
DlessDash { here_end: Rule3 }, /* <<- */
}
// Rule 7
struct Assigment {
key: WORD,
value: WORD,
}
#[derive(Default)]
struct TokenizerState<'input> {
current_pos: usize,
input: &'input str,
remaining: &'input str,
invalid_quote: bool,
_marker: std::marker::PhantomPinned,
}
impl<'input> TokenizerState<'input> {
fn new(input: &'input str) -> Self {
Self {
current_pos: 0,
remaining: input,
invalid_quote: false,
input,
_marker: std::marker::PhantomPinned,
}
}
}
// Cow<'input, str> is either a owned string (so it'll have to be free'd, basically it is an `String`
// or it is an borrow string, so an &'input str, which doesn't need to be free (or at least by us)
#[derive(Debug, Clone)]
enum Token<'input> {
SingleQuote {
val: Cow<'input, str>,
start_pos: usize,
},
DoubleQuote {
val: Cow<'input, str>,
start_pos: usize,
},
WhiteSpace {
val: Cow<'input, str>,
start_pos: usize,
},
Word {
val: Cow<'input, str>,
start_pos: usize,
},
}
fn tokenizer<'state, 'input: 'state>(
state: &'state mut TokenizerState<'input>,
) -> impl Iterator<Item = Token<'input>> + 'state {
state.current_pos = 0;
std::iter::from_fn(move || {
let state = &mut *state;
let mut chars = state.remaining.chars().peekable();
let mut len = 1;
let mut escaped = false;
let Some(chr) = chars.next() else {
return None;
};
match chr {
'\'' => {
while let Some(s) = chars.peek().copied() {
if s == '\'' {
break;
}
len += 1;
chars.next();
}
let skip = chars.peek() == Some(&'\'');
state.invalid_quote |= !skip;
let old_current = state.current_pos;
state.current_pos += len;
let old_remaining = state.remaining;
state.remaining = &state.remaining[(len + skip as usize)..];
return Some(Token::SingleQuote {
val: old_remaining[1..len].into(),
start_pos: old_current,
});
}
'"' => {
while let Some(s) = chars.peek().copied() {
if !escaped && s == '\"' {
break;
}
len += 1;
escaped = chars.next() == Some('\\');
}
let skip = chars.peek() == Some(&'\"');
state.invalid_quote |= !skip;
let old_current = state.current_pos;
state.current_pos += len;
let old_remaining = state.remaining;
state.remaining = &state.remaining[(len + skip as usize)..];
return Some(Token::DoubleQuote {
val: old_remaining[1..len].into(),
start_pos: old_current,
});
}
_ => {}
}
let was_whitespace = chr.is_ascii_whitespace();
while let Some(&chr) = chars.peek() {
if chr.is_ascii_whitespace() && !escaped && !was_whitespace {
let old_current = state.current_pos;
state.current_pos += len;
let old_remaining = state.remaining;
state.remaining = &state.remaining[len..];
return Some(Token::Word {
val: old_remaining[..len].into(),
start_pos: old_current,
});
} else if !chr.is_ascii_whitespace() && was_whitespace {
let old_current = state.current_pos;
state.current_pos += len;
let old_remaining = state.remaining;
state.remaining = &state.remaining[len..];
return Some(Token::WhiteSpace {
val: old_remaining[..len].into(),
start_pos: old_current,
});
}
len += 1;
escaped = chars.next() == Some('\\');
}
let old_current = state.current_pos;
state.current_pos += len;
let old_remaining = state.remaining;
state.remaining = &state.remaining[len..];
Some(if was_whitespace {
Token::WhiteSpace {
val: old_remaining[..len].into(),
start_pos: old_current,
}
} else {
Token::Word {
val: old_remaining[..len].into(),
start_pos: old_current,
}
})
})
}
// This isn't a C thingy, it is just needed to make rust happy
struct TokenizerWrapper<'input> {
_marker: std::marker::PhantomPinned,
first_pass: TokenizerState<'input>,
iter: Box<dyn Iterator<Item = Token<'input>> + 'input>,
}
impl<'input> TokenizerWrapper<'input> {
fn new(s: TokenizerState<'input>) -> Pin<Box<Self>> {
let mut value = Box::new(std::mem::MaybeUninit::<Self>::uninit());
unsafe {
let ptr = value.as_mut_ptr();
std::ptr::write(std::ptr::addr_of_mut!((*ptr).first_pass), s);
std::ptr::write(
std::ptr::addr_of_mut!((*ptr).iter),
Box::new(tokenizer(&mut *std::ptr::addr_of_mut!((*ptr).first_pass))),
);
std::mem::transmute(Pin::new_unchecked(value))
}
}
}
impl<'input> TokenizerWrapper<'input> {
fn next(self: &mut Pin<Box<Self>>) -> Option<Token<'input>> {
unsafe { Pin::into_inner_unchecked(self.as_mut()).iter.next() }
}
}
// end of rust thingy
struct ExpenderState<'input> {
// These will be inserted when a substitution is made, like $HOME
// if it is "$HOME", then no splitting should be done, so if there is any stuff that needs to
// be pushed, then push it, otherwise get the next token from `iter`, expend if needed and
// voila
need_push: VecDeque<ExpendedToken<'input>>,
// This is because of the way I wrote the rust
// stuff, returning iterator instead of an token everytime I call a function and stuff, it
// shouldn't be reflected into the C code, as we will just call 'get_next_token(&state)' and it
// will give us the next token (or EOF if no more token are present)
tokenizer: Pin<Box<TokenizerWrapper<'input>>>,
}
#[derive(Debug, Clone)]
enum ExpendedToken<'input> {
SingleQuote {
val: Cow<'input, str>,
start_pos: usize,
},
DoubleQuote {
val: Cow<'input, str>,
start_pos: usize,
},
WhiteSpace {
val: Cow<'input, str>,
start_pos: usize,
},
Word {
val: Cow<'input, str>,
start_pos: usize,
},
}
impl<'input> ExpenderState<'input> {
fn new(input: &'input str) -> Self {
let wrapper = TokenizerWrapper::new(TokenizerState::new(input));
Self {
need_push: VecDeque::new(),
tokenizer: wrapper,
}
}
}
fn expend<'state, 'input: 'state>(
input: &'state mut ExpenderState<'input>,
) -> impl Iterator<Item = ExpendedToken<'input>> + 'state {
std::iter::from_fn(|| {
if !input.need_push.is_empty() {
input.need_push.pop_front()
} else {
input.tokenizer.next().map(|t| match t {
Token::Word { val, start_pos } => ExpendedToken::Word { val, start_pos },
Token::DoubleQuote { val, start_pos } => {
ExpendedToken::DoubleQuote { val, start_pos }
}
Token::SingleQuote { val, start_pos } => {
ExpendedToken::SingleQuote { val, start_pos }
}
Token::WhiteSpace { val, start_pos } => {
ExpendedToken::WhiteSpace { val, start_pos }
}
})
}
})
}
fn main() {
for line in std::io::stdin().lines() {
let line = line.unwrap();
let mut state = ExpenderState::new(&line);
println!("line is = '{line}'");
println!("token are = {:?}", expend(&mut state).collect::<Vec<_>>());
}
}

10
shcat_c/Makefile
View file

@ -6,7 +6,7 @@
# By: rparodi <rparodi@student.42.fr> +#+ +:+ +#+ # # By: rparodi <rparodi@student.42.fr> +#+ +:+ +#+ #
# +#+#+#+#+#+ +#+ # # +#+#+#+#+#+ +#+ #
# Created: 2023/11/12 11:05:05 by rparodi #+# #+# # # Created: 2023/11/12 11:05:05 by rparodi #+# #+# #
# Updated: 2024/04/13 20:18:33 by rparodi ### ########.fr # # Updated: 2024/04/28 17:05:10 by maiboyer ### ########.fr #
# # # #
# **************************************************************************** # # **************************************************************************** #
@ -23,7 +23,7 @@ CC = cc
RM = rm -rf RM = rm -rf
# Flags # Flags
CFLAGS = -Werror -Wextra -Wall -Wno-unused-command-line-argument -g3 -MMD -lreadline CFLAGS = -Werror -Wextra -Wall -Wno-unused-command-line-argument -g3 -MMD -lreadline -I./libft
# Sources # Sources
LIB = ./libft/ft_bzero.c \ LIB = ./libft/ft_bzero.c \
@ -84,7 +84,7 @@ fclean: clean
re: header fclean all re: header fclean all
# Dependences for all # Dependences for all
$(NAME): $(OBJ) $(LIB_OBJ) $(NAME): $(OBJ) $(LIB_OBJ) $(OBJDIRNAME)/libme.a
@mkdir -p $(OBJDIRNAME) @mkdir -p $(OBJDIRNAME)
@mkdir -p $(OBJDIRNAME)/$(LIBDIRNAME) @mkdir -p $(OBJDIRNAME)/$(LIBDIRNAME)
@mkdir -p $(OBJDIRNAME)/$(SRCDIRNAME) @mkdir -p $(OBJDIRNAME)/$(SRCDIRNAME)
@ -128,6 +128,10 @@ footer:
@printf "$(GOLD) '\"' '\"'$(END)\n" @printf "$(GOLD) '\"' '\"'$(END)\n"
@printf ' $(GREY)The compilation is$(END) $(GOLD)finish$(END)\n $(GREY)Have a good $(END)$(GOLD)correction !$(END)\n' @printf ' $(GREY)The compilation is$(END) $(GOLD)finish$(END)\n $(GREY)Have a good $(END)$(GOLD)correction !$(END)\n'
$(OBJDIRNAME)/libme.a:
@$(MAKE) --no-print-directory -C ./stdme/ LIB_NAME="$(realpath ./$(stdme))/" "BUILD_DIR=$(shell realpath ./$(OBJDIRNAME))"
pull: pull:
@printf "$(GREEN)Pulling Submodules$(END)\n" @printf "$(GREEN)Pulling Submodules$(END)\n"
@git submodule init @git submodule init

1
shcat_c/stdme Submodule

@ -0,0 +1 @@
Subproject commit dc3c8ff9dc6f396a8fefd4ad89883e5285171b23

1
stdme

@ -1 +0,0 @@
Subproject commit b3ec36536db39e871e06e6073c05bf2f965adf99