feature: add cleanup

Signed-off-by: Amneesh Singh <natto@weirdnatto.in>

Cargo.lock

@@ -2,6 +2,15 @@
 # It is not intended for manual editing.
 version = 4
 
+[[package]]
+name = "android_system_properties"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "819e7219dbd41043ac279b19830f2efc897156490d7fd6ea916720117ee66311"
+dependencies = [
+ "libc",
+]
+
 [[package]]
 name = "atomic-waker"
 version = "1.1.2"
@@ -9,10 +18,16 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1505bd5d3d116872e7271a6d4e16d81d0c8570876c8de68093a09ac269d8aac0"
 
 [[package]]
-name = "axum"
+name = "autocfg"
-version = "0.8.6"
+version = "1.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8a18ed336352031311f4e0b4dd2ff392d4fbb370777c9d18d7fc9d7359f73871"
+checksum = "c08606f8c3cbf4ce6ec8e28fb0014a2c086708fe954eaa885384a6165172e7e8"
+
+[[package]]
+name = "axum"
+version = "0.8.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5b098575ebe77cb6d14fc7f32749631a6e44edbef6b796f89b020e99ba20d425"
 dependencies = [
  "axum-core",
  "bytes",
@@ -68,10 +83,26 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "812e12b5285cc515a9c72a5c1d3b6d46a19dac5acfef5265968c166106e31dd3"
 
 [[package]]
-name = "bytes"
+name = "bumpalo"
-version = "1.10.1"
+version = "3.19.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d71b6127be86fdcfddb610f7182ac57211d4b18a3e9c82eb2d17662f2227ad6a"
+checksum = "46c5e41b57b8bba42a04676d81cb89e9ee8e859a1a66f80a5a72e1cb76b34d43"
+
+[[package]]
+name = "bytes"
+version = "1.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b35204fbdc0b3f4446b89fc1ac2cf84a8a68971995d0bf2e925ec7cd960f9cb3"
+
+[[package]]
+name = "cc"
+version = "1.2.46"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b97463e1064cb1b1c1384ad0a0b9c8abd0988e2a91f52606c80ef14aadb63e36"
+dependencies = [
+ "find-msvc-tools",
+ "shlex",
+]
 
 [[package]]
 name = "cfg-if"
@@ -79,6 +110,25 @@ version = "1.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
 
+[[package]]
+name = "chrono"
+version = "0.4.42"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "145052bdd345b87320e369255277e3fb5152762ad123a901ef5c262dd38fe8d2"
+dependencies = [
+ "iana-time-zone",
+ "js-sys",
+ "num-traits",
+ "wasm-bindgen",
+ "windows-link",
+]
+
+[[package]]
+name = "core-foundation-sys"
+version = "0.8.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
+
 [[package]]
 name = "encoding_rs"
 version = "0.8.35"
@@ -88,6 +138,12 @@ dependencies = [
  "cfg-if",
 ]
 
+[[package]]
+name = "find-msvc-tools"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3a3076410a55c90011c298b04d0cfa770b00fa04e1e3c97d3f6c9de105a03844"
+
 [[package]]
 name = "fnv"
 version = "1.0.7"
@@ -215,9 +271,9 @@ checksum = "df3b46402a9d5adb4c86a0cf463f42e19994e3ee891101b1841f30a545cb49a9"
 
 [[package]]
 name = "hyper"
-version = "1.7.0"
+version = "1.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eb3aa54a13a0dfe7fbe3a59e0c76093041720fdc77b110cc0fc260fafb4dc51e"
+checksum = "2ab2d4f250c3d7b1c9fcdff1cece94ea4e2dfbec68614f7b87cb205f24ca9d11"
 dependencies = [
  "atomic-waker",
  "bytes",
@@ -236,9 +292,9 @@ dependencies = [
 
 [[package]]
 name = "hyper-util"
-version = "0.1.17"
+version = "0.1.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3c6995591a8f1380fcb4ba966a252a4b29188d51d2b89e3a252f5305be65aea8"
+checksum = "52e9a2a24dc5c6821e71a7030e1e14b7b632acac55c40e9d2e082c621261bb56"
 dependencies = [
  "bytes",
  "futures-core",
@@ -250,12 +306,46 @@ dependencies = [
  "tower-service",
 ]
 
+[[package]]
+name = "iana-time-zone"
+version = "0.1.64"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "33e57f83510bb73707521ebaffa789ec8caf86f9657cad665b092b581d40e9fb"
+dependencies = [
+ "android_system_properties",
+ "core-foundation-sys",
+ "iana-time-zone-haiku",
+ "js-sys",
+ "log",
+ "wasm-bindgen",
+ "windows-core",
+]
+
+[[package]]
+name = "iana-time-zone-haiku"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f31827a206f56af32e590ba56d5d2d085f558508192593743f16b2306495269f"
+dependencies = [
+ "cc",
+]
+
 [[package]]
 name = "itoa"
 version = "1.0.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4a5f13b858c8d314ee3e8f639011f7ccefe71f97f96e50151fb991f267928e2c"
 
+[[package]]
+name = "js-sys"
+version = "0.3.82"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b011eec8cc36da2aab2d5cff675ec18454fad408585853910a202391cf9f8e65"
+dependencies = [
+ "once_cell",
+ "wasm-bindgen",
+]
+
 [[package]]
 name = "libc"
 version = "0.2.177"
@@ -333,6 +423,15 @@ dependencies = [
  "version_check",
 ]
 
+[[package]]
+name = "num-traits"
+version = "0.2.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "071dfc062690e90b734c0b2273ce72ad0ffa95f0c74596bc250dcfd960262841"
+dependencies = [
+ "autocfg",
+]
+
 [[package]]
 name = "once_cell"
 version = "1.21.3"
@@ -451,6 +550,12 @@ dependencies = [
  "bitflags",
 ]
 
+[[package]]
+name = "rustversion"
+version = "1.0.22"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b39cdef0fa800fc44525c84ccb54a029961a8215f9619753635a9c0d2538d46d"
+
 [[package]]
 name = "ryu"
 version = "1.0.20"
@@ -528,6 +633,12 @@ dependencies = [
  "serde",
 ]
 
+[[package]]
+name = "shlex"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
+
 [[package]]
 name = "signal-hook-registry"
 version = "1.4.6"
@@ -567,9 +678,9 @@ checksum = "6980e8d7511241f8acf4aebddbb1ff938df5eebe98691418c4468d0b72a96a67"
 
 [[package]]
 name = "syn"
-version = "2.0.109"
+version = "2.0.110"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2f17c7e013e88258aa9543dcbe81aca68a667a9ac37cd69c9fbc07858bfe0e2f"
+checksum = "a99801b5bd34ede4cf3fc688c5919368fea4e4814a4664359503e6015b280aea"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -704,12 +815,110 @@ dependencies = [
  "wit-bindgen",
 ]
 
+[[package]]
+name = "wasm-bindgen"
+version = "0.2.105"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "da95793dfc411fbbd93f5be7715b0578ec61fe87cb1a42b12eb625caa5c5ea60"
+dependencies = [
+ "cfg-if",
+ "once_cell",
+ "rustversion",
+ "wasm-bindgen-macro",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-macro"
+version = "0.2.105"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "04264334509e04a7bf8690f2384ef5265f05143a4bff3889ab7a3269adab59c2"
+dependencies = [
+ "quote",
+ "wasm-bindgen-macro-support",
+]
+
+[[package]]
+name = "wasm-bindgen-macro-support"
+version = "0.2.105"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "420bc339d9f322e562942d52e115d57e950d12d88983a14c79b86859ee6c7ebc"
+dependencies = [
+ "bumpalo",
+ "proc-macro2",
+ "quote",
+ "syn",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-shared"
+version = "0.2.105"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "76f218a38c84bcb33c25ec7059b07847d465ce0e0a76b995e134a45adcb6af76"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "windows-core"
+version = "0.62.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b8e83a14d34d0623b51dce9581199302a221863196a1dde71a7663a4c2be9deb"
+dependencies = [
+ "windows-implement",
+ "windows-interface",
+ "windows-link",
+ "windows-result",
+ "windows-strings",
+]
+
+[[package]]
+name = "windows-implement"
+version = "0.60.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "053e2e040ab57b9dc951b72c264860db7eb3b0200ba345b4e4c3b14f67855ddf"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "windows-interface"
+version = "0.59.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f316c4a2570ba26bbec722032c4099d8c8bc095efccdc15688708623367e358"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
 [[package]]
 name = "windows-link"
 version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
 
+[[package]]
+name = "windows-result"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7781fa89eaf60850ac3d2da7af8e5242a5ea78d1a11c49bf2910bb5a73853eb5"
+dependencies = [
+ "windows-link",
+]
+
+[[package]]
+name = "windows-strings"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7837d08f69c77cf6b07689544538e017c1bfcf57e34b4c0ff58e6c2cd3b37091"
+dependencies = [
+ "windows-link",
+]
+
 [[package]]
 name = "windows-sys"
 version = "0.60.2"
@@ -804,6 +1013,7 @@ name = "yamaf"
 version = "0.1.0"
 dependencies = [
  "axum",
+ "chrono",
  "futures-util",
  "mime_guess",
  "rand",

Cargo.toml

@@ -7,8 +7,12 @@ edition = "2024"
 
 [dependencies]
 axum = { version = "0.8.6", features = ["multipart"] }
+chrono = "*"
 futures-util = "0.3.31"
 mime_guess= "*"
 rand = "*"
 tokio = { version = "1.48.0", features = ["full"] }
 tokio-util = { version = "0.7.17", features = ["io"] }
+
+[features]
+cleanup = []

README.org

@@ -18,7 +18,19 @@
 | EXTERNAL_HOST    | User facing domain name, used to return accessible URLs                             | ${INTERNAL_HOST}             |
 | EXTERNAL_HAS_TLS | URLs in html have https if set, otherwise http                                      | -                            |
 | MAX_FILES        | This does not actually limit the number of files, and used to calculate bodysize    | 10                           |
-| MAX_FILESIZE_MB  | Determines the max filesize possible, used to return failure and calculate bodysize | 100M                       |
+| MAX_FILESIZE_MB  | Determines the max filesize possible, used to return failure and calculate bodysize | 100M                         |
+| MIN_FILEDAYS     | Minimum number of days for file retention                                           | 30 days                      |
+| MAX_FILEDAYS     | Maximum number of days for file retention                                           | 365 days                     |
+
+** Retention
+
+File retention is as per the following formula
+
+#+begin_src text
+retention = min_days + (max_days - min_days) * (1 - file_size / max_size)) ^ e
+#+end_src
+
+Cleanup happens everyday when midnight (IST) has passed
 
 
 [fn:1] https://git.weirdnatto.in/natto1784/simple-filehost/

flake.nix

@@ -47,17 +47,14 @@
 
         cargoArtifacts = craneLib.buildDepsOnly commonArgs;
 
-        yamaf = craneLib.buildPackage (
+        yamaf = pkgs.callPackage ./nix/yamaf.nix {
-          commonArgs
+          inherit craneLib lib src;
-          // {
+        };
-            inherit cargoArtifacts;
-            doCheck = false;
-          }
-        );
       in
       {
         packages = {
           inherit yamaf;
+          yamaf-all = yamaf.override { withCleanup = true; };
           default = yamaf;
           image = pkgs.dockerTools.buildImage {
             name = "yamaf";

nix/yamaf.nix

@@ -0,0 +1,15 @@
+{
+  craneLib,
+  lib,
+  src,
+  withCleanup ? false,
+}:
+let
+  cargoArtifacts = craneLib.buildDepsOnly { inherit src; };
+in
+craneLib.buildPackage {
+  inherit cargoArtifacts src;
+  doCheck = false;
+
+  cargoExtraArgs = lib.optionalString withCleanup "--features cleanup";
+}

src/index.html

@@ -1,31 +1,45 @@
 <!DOCTYPE html>
 <html>
-   <head>
+  <head>
-      <title>{{TITLE}}</title>
+    <title>{{TITLE}}</title>
-   </head>
+  </head>
-   <body>
+  <body>
-      <h1>{{TITLE}}</h1>
+    <h1>{{TITLE}}</h1>
-      <p>
+
-         Use curl to upload:
+    <p>
-         <br>
+      Use curl to upload:
-         <code>
+      <br>
-         curl -F file=@"[file]" {{USER_URL}}
+      <code>
-         </code>
+        curl -F file=@"[file]" {{USER_URL}}
-         <br>
+      </code>
-         <br>
+      <br>
-         If key is enabled then a field "key" will be required.
+      <br>
-         <br>
+      If key is enabled then a field "key" will be required.
-         Make sure the key is the first field in the multipart before any files.
+      <br>
-         <br>
+      Make sure the key is the first field in the multipart before any files.
-         <code>
+      <br>
-         curl -F "key=[key]" -F file=@"[file]" -F file=@"[file2]" {{USER_URL}}
+      <code>
-         </code>
+        curl -F "key=[key]" -F file=@"[file]" -F file=@"[file2]" {{USER_URL}}
-      </p>
+      </code>
-      <form method="post" enctype="multipart/form-data">
+    </p>
-         {{KEY_FIELD}}
+
-         <input type="file" name="file" multiple>
+    <form method="post" enctype="multipart/form-data">
-         <br>
+      {{KEY_FIELD}}
-         <button type="submit">Upload</button>
+      <input type="file" name="file" multiple>
-      </form>
+      <br>
-      <div id="progress-container"></div>
+      <button type="submit">Upload</button>
+    </form>
+
+    <!-- CLEANUP_START -->
+    <h4>Cleanup</h4>
+    File retention is as per the following formula
+    <pre><code>
+    max_size = {{MAX_SIZE}} // in megabytes
+    max_days = {{MAX_DAYS}}
+    min_days = {{MIN_DAYS}}
+    retention = min_days + (max_days - min_days) * (1 - file_size / max_size)) ^ e
+    </code></pre>
+    Cleanup happens everyday when midnight (IST) has passed
+    <!-- CLEANUP_END -->
+
 </html>

src/main.rs

@@ -6,11 +6,10 @@ use axum::{
     response::{Html, IntoResponse, Response},
     routing::get,
 };
-
 use rand::{Rng, distr::Alphanumeric};
 use std::{env, net::SocketAddr, sync::LazyLock};
 use std::{env::VarError, path::PathBuf};
-use tokio::fs::File;
+use tokio::fs;
 use tokio_util::io::ReaderStream;
 
 struct Config {
@@ -23,12 +22,14 @@ struct Config {
     external_protocol: &'static str,
     max_filesize: usize,
     max_bodysize: usize,
+    min_filedays: usize,
+    max_filedays: usize,
 }
 
 static CONFIG: LazyLock<Config> = LazyLock::new(|| {
     let root_dir = env::var("ROOT_DIR").unwrap_or_else(|_| "/var/files".to_string());
     let key = env::var("KEY");
-    let title = env::var("TITLE").unwrap_or_else(|_| "Simpler Filehost".to_string());
+    let title = env::var("TITLE").unwrap_or_else(|_| "Yet Another Mid Ahh Filehost".to_string());
 
     let internal_host = env::var("INTERNAL_HOST").unwrap_or_else(|_| "127.0.0.1".to_string());
     let internal_port = env::var("INTERNAL_PORT")
@@ -54,6 +55,18 @@ static CONFIG: LazyLock<Config> = LazyLock::new(|| {
         << 20;
     let max_bodysize = max_files * max_filesize * 2;
 
+    let min_filedays = env::var("MIN_FILEDAYS")
+        .ok()
+        .and_then(|x| x.parse().ok())
+        .unwrap_or(30);
+
+    let max_filedays = env::var("MAX_FILEDAYS")
+        .ok()
+        .and_then(|x| x.parse().ok())
+        .unwrap_or(365);
+
+    assert!(max_filedays >= min_filedays);
+
     Config {
         root_dir,
         key,
@@ -64,6 +77,8 @@ static CONFIG: LazyLock<Config> = LazyLock::new(|| {
         external_protocol,
         max_filesize,
         max_bodysize,
+        min_filedays,
+        max_filedays,
     }
 });
 
@@ -86,6 +101,35 @@ async fn main() {
         addr, CONFIG.root_dir
     );
 
+    /* cleanup cronjob */
+    #[cfg(feature = "cleanup")]
+    tokio::spawn(async move {
+        use chrono::{Local, NaiveDate};
+
+        let mut last_cleanup_day: NaiveDate = Local::now().date_naive();
+
+        loop {
+            use tokio::time::{Duration, sleep};
+
+            /* every 30 minutes */
+            sleep(Duration::from_secs(30 * 60)).await;
+
+            let now = Local::now();
+            let today = now.date_naive();
+
+            /* if the date changed, midnight has passed */
+            if today > last_cleanup_day {
+                println!("attempting cleanup at {}", now.to_string());
+                if let Err(e) = cleanup_directory().await {
+                    eprintln!("cleanup failed: {}", e);
+                } else {
+                    println!("cleanup succeeded!");
+                    last_cleanup_day = today;
+                }
+            }
+        }
+    });
+
     axum::serve(listener, app).await.unwrap();
 }
 
@@ -108,6 +152,19 @@ static INDEX_HTML: LazyLock<String> = LazyLock::new(|| {
         },
     );
 
+    if cfg!(feature = "cleanup") {
+        html = html
+            .replace("{{MAX_SIZE}}", &(CONFIG.max_filesize >> 20).to_string())
+            .replace("{{MAX_DAYS}}", &CONFIG.max_filedays.to_string())
+            .replace("{{MIN_DAYS}}", &CONFIG.min_filedays.to_string());
+    } else {
+        if let Some(start) = html.find("<!-- CLEANUP_START -->") {
+            if let Some(end) = html.find("<!-- CLEANUP_END -->") {
+                html.replace_range(start..end + "<!-- CLEANUP_END -->".len(), "");
+            }
+        }
+    }
+
     html
 });
 
@@ -205,7 +262,7 @@ async fn upload(mut payload: Multipart) -> Result<impl IntoResponse, YamafError>
 
                 let save_path = std::path::Path::new(&CONFIG.root_dir).join(&filename);
 
-                let mut file = File::create(&save_path)
+                let mut file = fs::File::create(&save_path)
                     .await
                     .map_err(|_| YamafError::InternalError("Internal i/o error".into()))?;
 
@@ -223,7 +280,7 @@ async fn upload(mut payload: Multipart) -> Result<impl IntoResponse, YamafError>
                         .ok_or_else(|| YamafError::BadRequest("File too large".into()))?;
 
                     if written > CONFIG.max_filesize {
-                        _ = tokio::fs::remove_file(&save_path).await;
+                        _ = fs::remove_file(&save_path).await;
 
                         return Err(YamafError::FileTooBig(filename));
                     }
@@ -260,10 +317,10 @@ async fn upload(mut payload: Multipart) -> Result<impl IntoResponse, YamafError>
 async fn serve_file(Path(filename): Path<String>) -> Result<impl IntoResponse, YamafError> {
     let path = PathBuf::from(&CONFIG.root_dir).join(&filename);
 
-    let metadata = tokio::fs::metadata(&path)
+    let metadata = fs::metadata(&path)
         .await
         .map_err(|_| YamafError::FileNotFound)?;
-    let file = File::open(&path)
+    let file = fs::File::open(&path)
         .await
         .map_err(|_| YamafError::FileNotFound)?;
     let mime = mime_guess::from_path(&path).first_or_octet_stream();
@@ -289,3 +346,36 @@ async fn serve_file(Path(filename): Path<String>) -> Result<impl IntoResponse, Y
 
     Ok((StatusCode::OK, headers, body).into_response())
 }
+
+#[cfg(feature = "cleanup")]
+async fn cleanup_directory() -> Result<(), std::io::Error> {
+    let dir = std::path::Path::new(&CONFIG.root_dir);
+    let mut entries = fs::read_dir(dir).await?;
+
+    while let Some(entry) = entries.next_entry().await? {
+        use std::os::unix::fs::MetadataExt;
+        use std::time::SystemTime;
+
+        let path = entry.path();
+        let meta = entry.metadata().await?;
+        let modified = meta.modified().unwrap_or(SystemTime::UNIX_EPOCH);
+        let age = SystemTime::now()
+            .duration_since(modified)
+            .unwrap_or_default();
+
+        /* min_days + (max_days - min_days) * (1 - size/max_size)^e */
+        let retention = (CONFIG.min_filedays as f64
+            + (CONFIG.max_filedays - CONFIG.min_filedays) as f64
+                * (1.0 - (meta.size() as f64 / CONFIG.max_filesize as f64))
+                    .powf(std::f64::consts::E))
+            * 24.0
+            * 60.0;
+
+        if meta.is_file() && age.as_secs_f64() > retention {
+            fs::remove_file(&path).await?;
+            println!("Deleted {:?}", path);
+        }
+    }
+
+    Ok(())
+}