implemented basic data extraction

This commit is contained in:
specCon18 2024-05-29 19:14:26 -04:00
parent fe3787fd7a
commit 46fc01b803
13 changed files with 578 additions and 0 deletions

1
.direnv/flake-profile Symbolic link
View file

@ -0,0 +1 @@
flake-profile-1-link

View file

@ -0,0 +1 @@
/nix/store/i3rlyi8v4kyhgadm396y1cqv2grr7w14-nix-shell-env

1
.envrc Normal file
View file

@ -0,0 +1 @@
use flake

2
.gitignore vendored Normal file
View file

@ -0,0 +1,2 @@
/target
/test_dir/*

300
Cargo.lock generated Normal file
View file

@ -0,0 +1,300 @@
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
version = 3
[[package]]
name = "anstream"
version = "0.6.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "418c75fa768af9c03be99d17643f93f79bbba589895012a80e3452a19ddda15b"
dependencies = [
"anstyle",
"anstyle-parse",
"anstyle-query",
"anstyle-wincon",
"colorchoice",
"is_terminal_polyfill",
"utf8parse",
]
[[package]]
name = "anstyle"
version = "1.0.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "038dfcf04a5feb68e9c60b21c9625a54c2c0616e79b72b0fd87075a056ae1d1b"
[[package]]
name = "anstyle-parse"
version = "0.2.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c03a11a9034d92058ceb6ee011ce58af4a9bf61491aa7e1e59ecd24bd40d22d4"
dependencies = [
"utf8parse",
]
[[package]]
name = "anstyle-query"
version = "1.0.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a64c907d4e79225ac72e2a354c9ce84d50ebb4586dee56c82b3ee73004f537f5"
dependencies = [
"windows-sys",
]
[[package]]
name = "anstyle-wincon"
version = "3.0.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "61a38449feb7068f52bb06c12759005cf459ee52bb4adc1d5a7c4322d716fb19"
dependencies = [
"anstyle",
"windows-sys",
]
[[package]]
name = "cc"
version = "1.0.98"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "41c270e7540d725e65ac7f1b212ac8ce349719624d7bcff99f8e2e488e8cf03f"
[[package]]
name = "cfg-if"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
[[package]]
name = "clap"
version = "4.5.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "90bc066a67923782aa8515dbaea16946c5bcc5addbd668bb80af688e53e548a0"
dependencies = [
"clap_builder",
"clap_derive",
]
[[package]]
name = "clap_builder"
version = "4.5.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ae129e2e766ae0ec03484e609954119f123cc1fe650337e155d03b022f24f7b4"
dependencies = [
"anstream",
"anstyle",
"clap_lex",
"strsim",
]
[[package]]
name = "clap_derive"
version = "4.5.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "528131438037fd55894f62d6e9f068b8f45ac57ffa77517819645d10aed04f64"
dependencies = [
"heck",
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "clap_lex"
version = "0.7.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "98cc8fbded0c607b7ba9dd60cd98df59af97e84d24e49c8557331cfc26d301ce"
[[package]]
name = "colorchoice"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0b6a852b24ab71dffc585bcb46eaf7959d175cb865a7152e35b348d1b2960422"
[[package]]
name = "getrandom"
version = "0.2.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c4567c8db10ae91089c99af84c68c38da3ec2f087c3f82960bcdbf3656b6f4d7"
dependencies = [
"cfg-if",
"libc",
"wasi",
]
[[package]]
name = "heck"
version = "0.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
[[package]]
name = "is_terminal_polyfill"
version = "1.70.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f8478577c03552c21db0e2724ffb8986a5ce7af88107e6be5d2ee6e158c12800"
[[package]]
name = "libc"
version = "0.2.155"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "97b3888a4aecf77e811145cadf6eef5901f4782c53886191b2f693f24761847c"
[[package]]
name = "proc-macro2"
version = "1.0.84"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ec96c6a92621310b51366f1e28d05ef11489516e93be030060e5fc12024a49d6"
dependencies = [
"unicode-ident",
]
[[package]]
name = "quote"
version = "1.0.36"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0fa76aaf39101c457836aec0ce2316dbdc3ab723cdda1c6bd4e6ad4208acaca7"
dependencies = [
"proc-macro2",
]
[[package]]
name = "ring"
version = "0.17.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c17fa4cb658e3583423e915b9f3acc01cceaee1860e33d59ebae66adc3a2dc0d"
dependencies = [
"cc",
"cfg-if",
"getrandom",
"libc",
"spin",
"untrusted",
"windows-sys",
]
[[package]]
name = "spin"
version = "0.9.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6980e8d7511241f8acf4aebddbb1ff938df5eebe98691418c4468d0b72a96a67"
[[package]]
name = "strsim"
version = "0.11.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f"
[[package]]
name = "syn"
version = "2.0.66"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c42f3f41a2de00b01c0aaad383c5a45241efc8b2d1eda5661812fda5f3cdcff5"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "unicode-ident"
version = "1.0.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
[[package]]
name = "untrusted"
version = "0.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8ecb6da28b8a351d773b68d5825ac39017e680750f980f3a1a85cd8dd28a47c1"
[[package]]
name = "utf8parse"
version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "711b9620af191e0cdc7468a8d14e709c3dcdb115b36f838e601583af800a370a"
[[package]]
name = "wasi"
version = "0.11.0+wasi-snapshot-preview1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
[[package]]
name = "windows-sys"
version = "0.52.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
dependencies = [
"windows-targets",
]
[[package]]
name = "windows-targets"
version = "0.52.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6f0713a46559409d202e70e28227288446bf7841d3211583a4b53e3f6d96e7eb"
dependencies = [
"windows_aarch64_gnullvm",
"windows_aarch64_msvc",
"windows_i686_gnu",
"windows_i686_gnullvm",
"windows_i686_msvc",
"windows_x86_64_gnu",
"windows_x86_64_gnullvm",
"windows_x86_64_msvc",
]
[[package]]
name = "windows_aarch64_gnullvm"
version = "0.52.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7088eed71e8b8dda258ecc8bac5fb1153c5cffaf2578fc8ff5d61e23578d3263"
[[package]]
name = "windows_aarch64_msvc"
version = "0.52.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9985fd1504e250c615ca5f281c3f7a6da76213ebd5ccc9561496568a2752afb6"
[[package]]
name = "windows_i686_gnu"
version = "0.52.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "88ba073cf16d5372720ec942a8ccbf61626074c6d4dd2e745299726ce8b89670"
[[package]]
name = "windows_i686_gnullvm"
version = "0.52.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "87f4261229030a858f36b459e748ae97545d6f1ec60e5e0d6a3d32e0dc232ee9"
[[package]]
name = "windows_i686_msvc"
version = "0.52.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "db3c2bf3d13d5b658be73463284eaf12830ac9a26a90c717b7f771dfe97487bf"
[[package]]
name = "windows_x86_64_gnu"
version = "0.52.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4e4246f76bdeff09eb48875a0fd3e2af6aada79d409d33011886d3e1581517d9"
[[package]]
name = "windows_x86_64_gnullvm"
version = "0.52.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "852298e482cd67c356ddd9570386e2862b5673c85bd5f88df9ab6802b334c596"
[[package]]
name = "windows_x86_64_msvc"
version = "0.52.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bec47e5bfd1bff0eeaf6d8b485cc1074891a197ab4225d504cb7a1ab88b02bf0"
[[package]]
name = "yunodo"
version = "0.1.0"
dependencies = [
"clap",
"ring",
]

9
Cargo.toml Normal file
View file

@ -0,0 +1,9 @@
[package]
name = "yunodo"
version = "0.1.0"
edition = "2021"
[dependencies]
clap = { version = "4.5.4", features = ["derive"] }
ring = "0.17.8"

26
flake.lock generated Normal file
View file

@ -0,0 +1,26 @@
{
"nodes": {
"nixpkgs": {
"locked": {
"lastModified": 1715774670,
"narHash": "sha256-iJYnKMtLi5u6hZhJm94cRNSDG5Rz6ZzIkGbhPFtDRm0=",
"owner": "NixOS",
"repo": "nixpkgs",
"rev": "b3fcfcfabd01b947a1e4f36622bbffa3985bdac6",
"type": "github"
},
"original": {
"id": "nixpkgs",
"ref": "nixpkgs-unstable",
"type": "indirect"
}
},
"root": {
"inputs": {
"nixpkgs": "nixpkgs"
}
}
},
"root": "root",
"version": 7
}

31
flake.nix Normal file
View file

@ -0,0 +1,31 @@
{
description = "SunServer";
inputs={
nixpkgs.url = "nixpkgs/nixpkgs-unstable";
};
outputs = { self, nixpkgs }@inputs:
let
supportedSystems = [ "x86_64-linux" ];
forAllSystems = nixpkgs.lib.genAttrs supportedSystems;
#v I improved how you call in packages
pkgs = forAllSystems (system:
import nixpkgs {
inherit system;
#v this can be adjusted to read args passed without impure later
# config = { allowUnfreePredicate = pkg: builtins.elem (nixpkgs.lib.getName pkg) [
# ];
# };
}
);
in {
packages = forAllSystems (system: {
default = pkgs.${system}.callPackage ./nix/default.nix { };
});
devShells = forAllSystems (system: {
default = pkgs.${system}.callPackage ./nix/devshell.nix { };
});
nixConfig = {
};
};
}

11
nix/default.nix Normal file
View file

@ -0,0 +1,11 @@
{ pkgs ? import <nixpkgs> { }, lib }:
pkgs.rustPlatform.buildRustPackage rec {
pname = "algos-in-rust";
version = "1.0.0";
cargoLock.lockFile = ../Cargo.lock;
src = pkgs.lib.cleanSource ../.;
buildInputs = [ ];
nativeBuildInputs = [ pkgs.pkg-config ];
doCheck = false;
}

16
nix/devshell.nix Normal file
View file

@ -0,0 +1,16 @@
{ pkgs ? import <nixpkgs> { } }:
pkgs.mkShell {
# Get dependencies from the main package
inputsFrom = [ (pkgs.callPackage ./default.nix { }) ];
# Additional tooling
buildInputs = with pkgs; [
cargo
cargo-watch
rustc
rustup
clippy
bacon
rust-analyzer
pkg-config
];
}

32
nix/flake.nix Normal file
View file

@ -0,0 +1,32 @@
{
description = "SunServer";
inputs={
nixpkgs.url = "nixpkgs/nixpkgs-unstable";
};
outputs = { self, nixpkgs }@inputs:
let
supportedSystems = [ "x86_64-linux" ];
forAllSystems = nixpkgs.lib.genAttrs supportedSystems;
#v I improved how you call in packages
pkgs = forAllSystems (system:
import nixpkgs {
inherit system;
#v this can be adjusted to read args passed without impure later
config = { allowUnfreePredicate = pkg: builtins.elem (nixpkgs.lib.getName pkg) [
"unrar"
];
};
}
);
in {
packages = forAllSystems (system: {
default = pkgs.${system}.callPackage ./nix/default.nix { };
});
devShells = forAllSystems (system: {
default = pkgs.${system}.callPackage ./nix/devshell.nix { };
});
nixConfig = {
};
};
}

56
src/file_tree.rs Normal file
View file

@ -0,0 +1,56 @@
use std::collections::HashMap;
// Define the structure for a File
#[derive(Debug)]
struct File {
name: String, //TODO: make sha384 digest :ODOT//
path: String,
}
// Define the structure for a Directory
#[derive(Debug)]
struct Directory {
parent:Box<Node>,
files: Vec<File>,
subdirectories: HashMap<String, Node>,
}
// Define a node of the B-tree
#[derive(Debug)]
enum Node {
File(File),
Directory(Box<Directory>),
}
// Define the B-tree structure
#[derive(Debug)]
struct BTree {
root: Node,
}
// Implement methods for BTree
impl BTree {
fn new(root: Node) -> Self {
BTree { root }
}
fn print(&self) {
self.print_recursive(&self.root, 0);
}
fn print_recursive(&self, node: &Node, depth: usize) {
match node {
Node::File(file) => {
println!("{}{}", "-".repeat(depth), file.name);
}
Node::Directory(dir) => {
println!("{}{:#?}", "-".repeat(depth), dir.parent);
for file in &dir.files {
println!("{}{}", "-".repeat(depth + 1), file.name);
}
for (_, subdir) in &dir.subdirectories {
self.print_recursive(subdir, depth + 1);
}
}
}
}
}

92
src/main.rs Normal file
View file

@ -0,0 +1,92 @@
use clap::Parser;
use std::{io,fs,path::PathBuf};
//TODO: implement mod file_tree; :ODOT//
#[derive(Parser)]
#[command(name = "YUNODO")]
#[command(version = "0.1.0")]
#[command(about = "parse file tree for //TODO: comments", long_about = "parses a directory of files for substrings of //TODO: and outputs all instances in a parsable format")]
struct Cli {
/// Sets a custom config file
#[arg(short, long, value_name = "PATH")]
path: Option<PathBuf>,
#[arg(short, long, value_name = "DEBUG")]
debug: Option<bool>,
}
fn read_files_in_directory(dir_path: &str) -> io::Result<Vec<(String, Vec<String>)>> {
let mut files_content = Vec::new();
let paths = fs::read_dir(dir_path)?;
for path in paths {
let entry = path?;
let path = entry.path();
if path.is_file() {
let filename = path.file_name().unwrap().to_string_lossy().into_owned();
let content = fs::read_to_string(&path)?;
let lines: Vec<String> = content.lines().map(|s| s.to_string()).collect();
files_content.push((filename, lines));
} else if path.is_dir() {
let subdir_path = path.to_string_lossy().into_owned();
let subdir_content = read_files_in_directory(&subdir_path)?;
files_content.extend(subdir_content);
}
}
Ok(files_content)
}
fn main() {
let cli = Cli::parse();
if let Some(path) = cli.path.as_deref() {
let path_string = path.display().to_string();
match read_files_in_directory(&path_string.as_str()) {
Ok(files_content) => {
for (filename, lines) in files_content {
for (line_number, line) in lines.iter().enumerate() {
// Check if the line starts with "//" and not within strings or other signatures
if !line.contains("//") {
continue;
}
let mut in_string = false;
let mut in_comment = false;
let mut in_signature = false;
for (i, c) in line.chars().enumerate() {
match c {
'"' => in_string = !in_string,
'/' if !in_string => {
if i + 1 < line.len() && line.chars().nth(i + 1).unwrap() == '/' {
in_comment = true;
break;
} else if i + 1 < line.len() && line.chars().nth(i + 1).unwrap() == '*' {
in_comment = true;
}
}
'*' if i + 1 < line.len() && line.chars().nth(i + 1).unwrap() == '/' && in_comment => {
in_comment = false;
break;
}
_ => (),
}
}
if in_comment {
let mut v: Vec<&str> = line.split("//TODO:").collect();
if let Some(last_part) = v.last() {
if let Some(end_index) = last_part.find(":ODOT//") {
let extracted = &last_part[..end_index];
println!("({})->({})->({}) |~| {}", path_string, filename, line_number + 1, extracted);
}
}
}
}
}
}
Err(err) => {
eprintln!("Error: {}", err);
}
}
}
}