db: add MIME sniffing for binary clipboard previews

Signed-off-by: NotAShelf <raf@notashelf.dev>
Change-Id: I70416269dd40496758b6e5431e77a9456a6a6964
This commit is contained in:
raf 2026-02-27 10:34:32 +03:00
commit 181edcefb1
Signed by: NotAShelf
GPG key ID: 29D95B64378DB4BF
3 changed files with 307 additions and 20 deletions

288
Cargo.lock generated
View file

@ -686,6 +686,17 @@ dependencies = [
"objc2",
]
[[package]]
name = "displaydoc"
version = "0.2.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.117",
]
[[package]]
name = "document-features"
version = "0.2.12"
@ -900,6 +911,15 @@ version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "77ce24cb58228fbb8aa041425bb1050850ac19177686ea6e0f41a70416f56fdb"
[[package]]
name = "form_urlencoded"
version = "1.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cb4cb245038516f5f85277875cdaa4f7d2c9a0fa0468de06ed190163b1581fcf"
dependencies = [
"percent-encoding",
]
[[package]]
name = "futures-core"
version = "0.3.31"
@ -1017,12 +1037,114 @@ version = "2.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "135b12329e5e3ce057a9f972339ea52bc954fe1e9358ef27f95e89716fbc5424"
[[package]]
name = "icu_collections"
version = "2.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4c6b649701667bbe825c3b7e6388cb521c23d88644678e83c0c4d0a621a34b43"
dependencies = [
"displaydoc",
"potential_utf",
"yoke",
"zerofrom",
"zerovec",
]
[[package]]
name = "icu_locale_core"
version = "2.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "edba7861004dd3714265b4db54a3c390e880ab658fec5f7db895fae2046b5bb6"
dependencies = [
"displaydoc",
"litemap",
"tinystr",
"writeable",
"zerovec",
]
[[package]]
name = "icu_normalizer"
version = "2.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5f6c8828b67bf8908d82127b2054ea1b4427ff0230ee9141c54251934ab1b599"
dependencies = [
"icu_collections",
"icu_normalizer_data",
"icu_properties",
"icu_provider",
"smallvec",
"zerovec",
]
[[package]]
name = "icu_normalizer_data"
version = "2.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7aedcccd01fc5fe81e6b489c15b247b8b0690feb23304303a9e560f37efc560a"
[[package]]
name = "icu_properties"
version = "2.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "020bfc02fe870ec3a66d93e677ccca0562506e5872c650f893269e08615d74ec"
dependencies = [
"icu_collections",
"icu_locale_core",
"icu_properties_data",
"icu_provider",
"zerotrie",
"zerovec",
]
[[package]]
name = "icu_properties_data"
version = "2.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "616c294cf8d725c6afcd8f55abc17c56464ef6211f9ed59cccffe534129c77af"
[[package]]
name = "icu_provider"
version = "2.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "85962cf0ce02e1e0a629cc34e7ca3e373ce20dda4c4d7294bbd0bf1fdb59e614"
dependencies = [
"displaydoc",
"icu_locale_core",
"writeable",
"yoke",
"zerofrom",
"zerotrie",
"zerovec",
]
[[package]]
name = "ident_case"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b9e0384b61958566e926dc50660321d12159025e767c18e043daf26b70104c39"
[[package]]
name = "idna"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3b0875f23caa03898994f6ddc501886a45c7d3d62d04d2d90788d47be1b1e4de"
dependencies = [
"idna_adapter",
"smallvec",
"utf8_iter",
]
[[package]]
name = "idna_adapter"
version = "1.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3acae9609540aa318d1bc588455225fb2085b9ed0c4f6bd0d9d5bcd86f1a0344"
dependencies = [
"icu_normalizer",
"icu_properties",
]
[[package]]
name = "imagesize"
version = "0.14.0"
@ -1200,6 +1322,12 @@ version = "0.12.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "32a66949e030da00e8c7d4434b251670a91556f4144941d37452769c25d58a53"
[[package]]
name = "litemap"
version = "0.8.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6373607a59f0be73a39b6fe456b8192fcc3585f602af20751600e974dd455e77"
[[package]]
name = "litrs"
version = "1.0.0"
@ -1273,6 +1401,22 @@ dependencies = [
"autocfg",
]
[[package]]
name = "mime"
version = "0.3.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6877bb514081ee2a7ff5ef9de3281f14a4dd4bceac4c09388074a6b5df8a139a"
[[package]]
name = "mime-sniffer"
version = "0.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6b8b2a64cd735f1d5f17ff6701ced3cc3c54851f9448caf454cd9c923d812408"
dependencies = [
"mime",
"url",
]
[[package]]
name = "minimal-lexical"
version = "0.2.1"
@ -1523,6 +1667,12 @@ dependencies = [
"windows-link 0.2.1",
]
[[package]]
name = "percent-encoding"
version = "2.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9b4f627cb1b25917193a259e49bdad08f671f8d9708acfd5fe0a8c1455d87220"
[[package]]
name = "pest"
version = "2.8.5"
@ -1681,6 +1831,15 @@ dependencies = [
"portable-atomic",
]
[[package]]
name = "potential_utf"
version = "0.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b73949432f5e2a09657003c25bca5e19a0e9c84f8058ca374f49e0ebe605af77"
dependencies = [
"zerovec",
]
[[package]]
name = "powerfmt"
version = "0.2.0"
@ -2122,6 +2281,12 @@ dependencies = [
"wasm-bindgen",
]
[[package]]
name = "stable_deref_trait"
version = "1.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6ce2be8dc25455e1f91df71bfa12ad37d7af1092ae736f3a6cd0e37bc7810596"
[[package]]
name = "stash-clipboard"
version = "0.3.6"
@ -2139,6 +2304,7 @@ dependencies = [
"inquire",
"libc",
"log",
"mime-sniffer",
"notify-rust",
"ratatui",
"regex",
@ -2210,6 +2376,17 @@ dependencies = [
"unicode-ident",
]
[[package]]
name = "synstructure"
version = "0.13.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "728a70f3dbaf5bab7f0c4b1ac8d7ae5ea60a4b5549c8a5914361c99147a709d2"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.117",
]
[[package]]
name = "tauri-winrt-notification"
version = "0.7.2"
@ -2368,6 +2545,16 @@ version = "0.1.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7694e1cfe791f8d31026952abf09c69ca6f6fa4e1a1229e18988f06a04a12dca"
[[package]]
name = "tinystr"
version = "0.8.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "42d3e9c45c09de15d06dd8acf5f4e0e399e85927b7f00711024eb7ae10fa4869"
dependencies = [
"displaydoc",
"zerovec",
]
[[package]]
name = "toml_datetime"
version = "0.7.5+spec-1.1.0"
@ -2514,6 +2701,24 @@ version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254"
[[package]]
name = "url"
version = "2.5.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ff67a8a4397373c3ef660812acab3268222035010ab8680ec4215f38ba3d0eed"
dependencies = [
"form_urlencoded",
"idna",
"percent-encoding",
"serde",
]
[[package]]
name = "utf8_iter"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"
[[package]]
name = "utf8parse"
version = "0.2.2"
@ -2953,6 +3158,35 @@ dependencies = [
"wayland-protocols-wlr",
]
[[package]]
name = "writeable"
version = "0.6.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9edde0db4769d2dc68579893f2306b26c6ecfbe0ef499b013d731b7b9247e0b9"
[[package]]
name = "yoke"
version = "0.8.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "72d6e5c6afb84d73944e5cedb052c4680d5657337201555f9f2a16b7406d4954"
dependencies = [
"stable_deref_trait",
"yoke-derive",
"zerofrom",
]
[[package]]
name = "yoke-derive"
version = "0.8.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b659052874eb698efe5b9e8cf382204678a0086ebf46982b79d6ca3182927e5d"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.117",
"synstructure",
]
[[package]]
name = "zbus"
version = "5.13.2"
@ -3014,6 +3248,60 @@ dependencies = [
"zvariant",
]
[[package]]
name = "zerofrom"
version = "0.1.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "50cc42e0333e05660c3587f3bf9d0478688e15d870fab3346451ce7f8c9fbea5"
dependencies = [
"zerofrom-derive",
]
[[package]]
name = "zerofrom-derive"
version = "0.1.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d71e5d6e06ab090c67b5e44993ec16b72dcbaabc526db883a360057678b48502"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.117",
"synstructure",
]
[[package]]
name = "zerotrie"
version = "0.2.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2a59c17a5562d507e4b54960e8569ebee33bee890c70aa3fe7b97e85a9fd7851"
dependencies = [
"displaydoc",
"yoke",
"zerofrom",
]
[[package]]
name = "zerovec"
version = "0.11.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6c28719294829477f525be0186d13efa9a3c602f7ec202ca9e353d310fb9a002"
dependencies = [
"yoke",
"zerofrom",
"zerovec-derive",
]
[[package]]
name = "zerovec-derive"
version = "0.11.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "eadce39539ca5cb3985590102671f2567e659fca9666581ad3411d59207951f3"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.117",
]
[[package]]
name = "zmij"
version = "1.0.16"

View file

@ -27,6 +27,7 @@ imagesize = "0.14.0"
inquire = { version = "0.9.4", default-features = false, features = [ "crossterm" ] }
libc = "0.2.182"
log = "0.4.29"
mime-sniffer = "0.1.3"
notify-rust = { version = "4.12.0", optional = true }
ratatui = "0.30.0"
regex = "1.12.3"

View file

@ -10,7 +10,8 @@ use std::{
};
use base64::prelude::*;
use log::{debug, error, warn};
use log::{debug, error, info, warn};
use mime_sniffer::MimeTypeSniffer;
use regex::Regex;
use rusqlite::{Connection, OptionalExtension, params};
use serde::{Deserialize, Serialize};
@ -1065,26 +1066,14 @@ pub fn preview_entry(data: &[u8], mime: Option<&str>, width: u32) -> String {
}
}
// For non-text data, use lossy conversion
let s = String::from_utf8_lossy(data);
truncate(s.trim(), width as usize, "")
// For non-text/non-image data, try to sniff the MIME type
if let Some(sniffed) = data.sniff_mime_type() {
return format!("[[ binary data {} {} ]]", size_str(data.len()), sniffed);
}
pub fn truncate(s: &str, max: usize, ellip: &str) -> String {
let char_count = s.chars().count();
if char_count > max {
let mut result = String::with_capacity(max * 4 + ellip.len()); // UTF-8 worst case
let mut char_iter = s.chars();
for _ in 0..max {
if let Some(c) = char_iter.next() {
result.push(c);
}
}
result.push_str(ellip);
result
} else {
s.to_string()
}
// Shouldn't reach here if MIME is properly set, but just in case
info!("Mimetype sniffing failed, omitting");
format!("[[ binary data {} ]]", size_str(data.len()))
}
pub fn size_str(size: usize) -> String {
@ -1963,6 +1952,15 @@ mod tests {
assert_eq!(size_str(1024 * 1024), "1 MiB");
}
#[test]
fn test_preview_entry_binary_sniffed() {
// PDF magic bytes
let data = b"%PDF-1.4 fake pdf content here for testing";
let preview = preview_entry(data, None, 100);
assert!(preview.contains("binary data"));
assert!(preview.contains("application/pdf"));
}
#[test]
fn test_copy_entry_returns_data() {
let db = test_db();