Compare commits

..

No commits in common. "64efb0de2716681e1bb35d4e6fac8af5ebf97142" and "80f14085cf42c15bcb513ff69c325e22350da6b8" have entirely different histories.

11 changed files with 115 additions and 258 deletions

View file

@ -39,13 +39,13 @@ stages:
- .gitlab-ci.yml - .gitlab-ci.yml
script: script:
cargo build --no-default-features --locked --features="json $FEATURES" cargo build --no-default-features --locked --features="$FEATURES"
.cargo-test: .cargo-test:
extends: .cargo-build extends: .cargo-build
stage: test stage: test
script: script:
cargo test --no-default-features --locked --verbose --features="json $FEATURES" cargo test --no-default-features --locked --verbose --features="$FEATURES"
clippy: clippy:
stage: lint stage: lint

View file

@ -2,10 +2,6 @@
Dates are given in YYYY-MM-DD format. Dates are given in YYYY-MM-DD format.
## v0.3 ## v0.3
### v0.3.1 (2021-xx-yy)
#### Features
- Added JSON output support via `-o json`
### v0.3.0 (2021-04-28) ### v0.3.0 (2021-04-28)
#### Features #### Features
- Added `-x`/`--exclude` flag for excluding file extensions (overrides `-e` or `-E` - `-E images -x jpg` scans all image - Added `-x`/`--exclude` flag for excluding file extensions (overrides `-e` or `-E` - `-E images -x jpg` scans all image

83
Cargo.lock generated
View file

@ -116,9 +116,9 @@ dependencies = [
[[package]] [[package]]
name = "crossbeam-epoch" name = "crossbeam-epoch"
version = "0.9.4" version = "0.9.3"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "52fb27eab85b17fbb9f6fd667089e07d6a2eb8743d02639ee7f6a7a7729c9c94" checksum = "2584f639eb95fea8c798496315b297cf81b9b58b6d30ab066a75455333cf4b12"
dependencies = [ dependencies = [
"cfg-if", "cfg-if",
"crossbeam-utils", "crossbeam-utils",
@ -129,9 +129,9 @@ dependencies = [
[[package]] [[package]]
name = "crossbeam-utils" name = "crossbeam-utils"
version = "0.8.4" version = "0.8.3"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4feb231f0d4d6af81aed15928e58ecf5816aa62a2393e2c82f46973e92a9a278" checksum = "e7e9d99fa91428effe99c5c6d4634cdeba32b8cf784fc428a2a687f61a952c49"
dependencies = [ dependencies = [
"autocfg", "autocfg",
"cfg-if", "cfg-if",
@ -182,6 +182,15 @@ version = "1.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "de853764b47027c2e862a995c34978ffa63c1501f2e15f987ba11bd4f9bba193" checksum = "de853764b47027c2e862a995c34978ffa63c1501f2e15f987ba11bd4f9bba193"
[[package]]
name = "fastrand"
version = "1.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "77b705829d1e87f762c2df6da140b26af5839e1033aa84aa5f56bb688e4e1bdb"
dependencies = [
"instant",
]
[[package]] [[package]]
name = "fif" name = "fif"
version = "0.3.0" version = "0.3.0"
@ -191,15 +200,13 @@ dependencies = [
"clap", "clap",
"env_logger", "env_logger",
"exitcode", "exitcode",
"fastrand",
"infer", "infer",
"itertools", "itertools",
"log", "log",
"new_mime_guess", "new_mime_guess",
"once_cell", "once_cell",
"rand",
"rayon", "rayon",
"serde",
"serde_json",
"smartstring", "smartstring",
"snailquote", "snailquote",
"tempfile", "tempfile",
@ -267,6 +274,15 @@ dependencies = [
"cfb", "cfb",
] ]
[[package]]
name = "instant"
version = "0.1.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "61124eeebbd69b8190558df225adf7e4caafce0d743919e5d6b19652314ec5ec"
dependencies = [
"cfg-if",
]
[[package]] [[package]]
name = "itertools" name = "itertools"
version = "0.10.0" version = "0.10.0"
@ -276,12 +292,6 @@ dependencies = [
"either", "either",
] ]
[[package]]
name = "itoa"
version = "0.4.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dd25036021b0de88a0aff6b850051563c6516d0bf53f8638938edbb9de732736"
[[package]] [[package]]
name = "lazy_static" name = "lazy_static"
version = "1.4.0" version = "1.4.0"
@ -318,9 +328,9 @@ dependencies = [
[[package]] [[package]]
name = "memchr" name = "memchr"
version = "2.4.0" version = "2.3.4"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b16bd47d9e329435e309c58469fe0791c2d0d1ba96ec0954152a5ae2b04387dc" checksum = "0ee1c47aaa256ecabcaea351eae4a9b01ef39ed810004e298d2511ed284b1525"
[[package]] [[package]]
name = "memoffset" name = "memoffset"
@ -495,9 +505,9 @@ dependencies = [
[[package]] [[package]]
name = "redox_syscall" name = "redox_syscall"
version = "0.2.8" version = "0.2.6"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "742739e41cd49414de871ea5e549afb7e2a3ac77b589bcbebe8c82fab37147fc" checksum = "8270314b5ccceb518e7e578952f0b72b88222d02e8f77f5ecf7abbb673539041"
dependencies = [ dependencies = [
"bitflags", "bitflags",
] ]
@ -542,37 +552,6 @@ version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d29ab0c6d3fc0ee92fe66e2d99f700eab17a8d57d1c1d3b748380fb20baa78cd" checksum = "d29ab0c6d3fc0ee92fe66e2d99f700eab17a8d57d1c1d3b748380fb20baa78cd"
[[package]]
name = "serde"
version = "1.0.125"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "558dc50e1a5a5fa7112ca2ce4effcb321b0300c0d4ccf0776a9f60cd89031171"
dependencies = [
"serde_derive",
]
[[package]]
name = "serde_derive"
version = "1.0.125"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b093b7a2bb58203b5da3056c05b4ec1fed827dcfdb37347a8841695263b3d06d"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "serde_json"
version = "1.0.64"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "799e97dc9fdae36a5c8b8f2cae9ce2ee9fdce2058c57a93e6099d919fd982f79"
dependencies = [
"itoa",
"ryu",
"serde",
]
[[package]] [[package]]
name = "smartstring" name = "smartstring"
version = "0.2.6" version = "0.2.6"
@ -600,9 +579,9 @@ checksum = "a2eb9349b6444b326872e140eb1cf5e7c522154d69e7a0ffb0fb81c06b37543f"
[[package]] [[package]]
name = "syn" name = "syn"
version = "1.0.72" version = "1.0.71"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a1e8cdbefb79a9a5a65e0db8b47b723ee907b7c7f8496c76a1770b5c310bab82" checksum = "ad184cc9470f9117b2ac6817bfe297307418819ba40552f9b3846f05c33d5373"
dependencies = [ dependencies = [
"proc-macro2", "proc-macro2",
"quote", "quote",
@ -695,9 +674,9 @@ checksum = "9337591893a19b88d8d87f2cec1e73fad5cdfd10e5a6f349f498ad6ea2ffb1e3"
[[package]] [[package]]
name = "unicode-xid" name = "unicode-xid"
version = "0.2.2" version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8ccb82d61f80a663efe1f787a51b16b5a51e3314d6ac365b08639f52387b33f3" checksum = "f7fe0bb3479651439c9112f72b6c505038574c9fbb575ed1bf3b797fa39dd564"
[[package]] [[package]]
name = "unicode_categories" name = "unicode_categories"

View file

@ -18,11 +18,10 @@ exclude = [".idea/", "*.toml", "!Cargo.toml", "*.sh", "*.py", "*.yml", "*.md", "
maintenance = { status = "experimental" } maintenance = { status = "experimental" }
[features] [features]
default = ["multi-threaded", "json"] default = ["multi-threaded"]
multi-threaded = ["rayon"] multi-threaded = ["rayon"]
infer-backend = [] infer-backend = []
xdg-mime-backend = [] xdg-mime-backend = []
json = ["serde", "serde_json"]
[dependencies] [dependencies]
walkdir = "2.3.2" walkdir = "2.3.2"
@ -35,8 +34,6 @@ rayon = { version = "1.5.0", optional = true }
exitcode = "1.1.2" exitcode = "1.1.2"
cfg-if = "1.0.0" cfg-if = "1.0.0"
itertools = "0.10.0" itertools = "0.10.0"
serde = { version = "1.0", features = ["derive"], optional = true }
serde_json = { version = "1.0", optional = true }
[target.'cfg(unix)'.dependencies] [target.'cfg(unix)'.dependencies]
xdg-mime = "0.3.3" xdg-mime = "0.3.3"
@ -60,7 +57,7 @@ default-features = false
[dev-dependencies] [dev-dependencies]
tempfile = "3.2.0" tempfile = "3.2.0"
rand = "0.8.3" fastrand = "1.4.1"
[profile.release] [profile.release]
lto = "thin" lto = "thin"

View file

@ -1,5 +1,4 @@
max_width = 120 max_width = 120
fn_single_line = true
hard_tabs = true hard_tabs = true
tab_spaces = 2 tab_spaces = 2
newline_style = "Unix" newline_style = "Unix"

View file

@ -5,10 +5,6 @@ use mime_guess::Mime;
use crate::inspectors::mime_extension_lookup; use crate::inspectors::mime_extension_lookup;
use crate::string_type::String; use crate::string_type::String;
#[cfg(feature = "json")]
use serde::{ser::SerializeStruct, Serializer};
use std::fmt::{Display, Formatter};
/// Information about a scanned file. /// Information about a scanned file.
#[derive(Ord, PartialOrd, Eq, PartialEq)] #[derive(Ord, PartialOrd, Eq, PartialEq)]
pub struct Findings<'a> { pub struct Findings<'a> {
@ -20,50 +16,8 @@ pub struct Findings<'a> {
pub mime: Mime, pub mime: Mime,
} }
#[cfg(feature = "json")]
impl<'a> serde::Serialize for Findings<'a> {
fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
where
S: Serializer,
{
// the second parameter is the number of fields in the struct -- in this case, 3
let mut state = serializer.serialize_struct("Findings", 3)?;
state.serialize_field("file", &self.file)?;
state.serialize_field("valid", &self.valid)?;
state.serialize_field("mime", &self.mime.essence_str())?;
state.end()
}
}
impl<'a> Findings<'a> { impl<'a> Findings<'a> {
pub fn recommended_extension(&self) -> Option<String> { pub fn recommended_extension(&self) -> Option<String> {
mime_extension_lookup(self.mime.clone()).map(|extensions| extensions[0].clone()) mime_extension_lookup(self.mime.clone()).map(|extensions| extensions[0].clone())
} }
} }
#[derive(Debug, PartialEq, PartialOrd, Ord, Eq)]
#[cfg_attr(feature = "json", derive(serde::Serialize))]
#[cfg_attr(feature = "json", serde(tag = "type", content = "path"))]
pub enum ScanError<'a> {
/// Something went wrong while trying to read the given file.
File(&'a Path),
/// Failed to determine the mimetype of the given file.
Mime(&'a Path),
}
impl<'a> Display for ScanError<'a> {
fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
write!(
f,
"Couldn't {} file: {}",
match self {
Self::File(_) => "read",
Self::Mime(_) => "determine mime type of",
},
match self {
Self::File(f) | Self::Mime(f) => f.to_string_lossy(),
}
)
}
}

View file

@ -9,7 +9,7 @@ use std::path::Path;
use cfg_if::cfg_if; use cfg_if::cfg_if;
use snailquote::escape; use snailquote::escape;
use crate::findings::ScanError; use crate::scan_error::ScanError;
use crate::{Findings, BACKEND}; use crate::{Findings, BACKEND};
use itertools::Itertools; use itertools::Itertools;
@ -65,18 +65,26 @@ pub enum Writable<'a> {
// the lifetime of a lifetime // the lifetime of a lifetime
impl<'a> From<&'a str> for Writable<'a> { impl<'a> From<&'a str> for Writable<'a> {
fn from(s: &'a str) -> Writable<'a> { Writable::String(s) } fn from(s: &'a str) -> Writable<'a> {
Writable::String(s)
}
} }
impl<'a> From<&'a Path> for Writable<'a> { impl<'a> From<&'a Path> for Writable<'a> {
fn from(p: &'a Path) -> Writable<'a> { Writable::Path(p) } fn from(p: &'a Path) -> Writable<'a> {
Writable::Path(p)
}
} }
impl<'a> From<&'a OsStr> for Writable<'a> { impl<'a> From<&'a OsStr> for Writable<'a> {
fn from(p: &'a OsStr) -> Writable<'a> { Writable::Path(p.as_ref()) } fn from(p: &'a OsStr) -> Writable<'a> {
Writable::Path(p.as_ref())
}
} }
fn generated_by() -> String { format!("Generated by fif {} ({} backend)", VERSION.unwrap_or("???"), BACKEND) } fn generated_by() -> String {
format!("Generated by fif {} ({} backend)", VERSION.unwrap_or("???"), BACKEND)
}
fn smart_write<W: Write>(f: &mut W, writeables: &[Writable]) -> io::Result<()> { fn smart_write<W: Write>(f: &mut W, writeables: &[Writable]) -> io::Result<()> {
// ehhhh // ehhhh
@ -94,9 +102,9 @@ fn smart_write<W: Write>(f: &mut W, writeables: &[Writable]) -> io::Result<()> {
} }
Writable::String(s) => write!(f, "{}", s)?, Writable::String(s) => write!(f, "{}", s)?,
Writable::Path(path) => { Writable::Path(path) => {
if let Some(path_str) = path.to_str() { if let Some(string) = path.to_str() {
let escaped = escape(path_str); let escaped = escape(string);
if escaped.as_ref() == path_str { if escaped == string {
// the escaped string is the same as the input - this will occur for inputs like "file.txt" which don't // the escaped string is the same as the input - this will occur for inputs like "file.txt" which don't
// need to be escaped. however, it's Best Practice™ to escape such strings anyway, so we prefix/suffix the // need to be escaped. however, it's Best Practice™ to escape such strings anyway, so we prefix/suffix the
// escaped string with single quotes. // escaped string with single quotes.
@ -124,21 +132,14 @@ fn smart_write<W: Write>(f: &mut W, writeables: &[Writable]) -> io::Result<()> {
Ok(()) Ok(())
} }
// TODO: this might need a restructure.
// it would be nice if i didn't have to write a case for every OutputFormat variant that looked like
// OutputFormat::PowerShell => PowerShell::new().write_all(...)
// also, JSON's implementation differs vastly from PowerShell and Shell's implementations. Maybe they shouldn't be
// treated as implementing the same trait, since in that case, the format trait is more of a concept rather than an
// actual definition of behaviour.
// structuring code is *hard*
pub trait Format { pub trait Format {
fn new() -> Self; fn new() -> Self;
fn rename<W: Write>(&self, _f: &mut W, _from: &Path, _to: &Path) -> io::Result<()> { unreachable!() } fn rename<W: Write>(&self, f: &mut W, from: &Path, to: &Path) -> io::Result<()>;
fn no_known_extension<W: Write>(&self, _f: &mut W, _path: &Path) -> io::Result<()> { unreachable!() } fn no_known_extension<W: Write>(&self, f: &mut W, path: &Path) -> io::Result<()>;
fn unreadable<W: Write>(&self, _f: &mut W, _path: &Path) -> io::Result<()> { unreachable!() } fn unreadable<W: Write>(&self, f: &mut W, path: &Path) -> io::Result<()>;
fn unknown_type<W: Write>(&self, _f: &mut W, _path: &Path) -> io::Result<()> { unreachable!() } fn unknown_type<W: Write>(&self, f: &mut W, path: &Path) -> io::Result<()>;
fn header<W: Write>(&self, _f: &mut W, _entries: &Entries) -> io::Result<()> { unreachable!() } fn header<W: Write>(&self, f: &mut W, entries: &Entries) -> io::Result<()>;
fn footer<W: Write>(&self, _f: &mut W, _entries: &Entries) -> io::Result<()> { unreachable!() } fn footer<W: Write>(&self, f: &mut W, entries: &Entries) -> io::Result<()>;
fn write_all<W: Write>(&self, f: &mut W, entries: &Entries) -> io::Result<()> { fn write_all<W: Write>(&self, f: &mut W, entries: &Entries) -> io::Result<()> {
// TODO: clean this up - it's kinda messy // TODO: clean this up - it's kinda messy
@ -185,7 +186,9 @@ pub trait Format {
pub struct Shell {} pub struct Shell {}
impl Format for Shell { impl Format for Shell {
fn new() -> Self { Self {} } fn new() -> Self {
Self {}
}
fn rename<W: Write>(&self, f: &mut W, from: &Path, to: &Path) -> io::Result<()> { fn rename<W: Write>(&self, f: &mut W, from: &Path, to: &Path) -> io::Result<()> {
smart_write(f, writablesln!("mv -v -i -- ", from, Space, to)) smart_write(f, writablesln!("mv -v -i -- ", from, Space, to))
@ -227,7 +230,9 @@ impl Format for Shell {
pub struct PowerShell {} pub struct PowerShell {}
impl Format for PowerShell { impl Format for PowerShell {
fn new() -> Self { Self {} } fn new() -> Self {
Self {}
}
fn rename<W: Write>(&self, f: &mut W, from: &Path, to: &Path) -> io::Result<()> { fn rename<W: Write>(&self, f: &mut W, from: &Path, to: &Path) -> io::Result<()> {
// unfortunately there doesn't seem to be an equivalent of sh's `mv -i` -- passing the '-Confirm' flag will prompt // unfortunately there doesn't seem to be an equivalent of sh's `mv -i` -- passing the '-Confirm' flag will prompt
@ -281,34 +286,3 @@ impl Format for PowerShell {
smart_write(f, writablesln![Newline, "Write-Output 'Done!'"]) smart_write(f, writablesln![Newline, "Write-Output 'Done!'"])
} }
} }
#[cfg(feature = "json")]
pub struct Json;
#[cfg(feature = "json")]
impl Format for Json {
fn new() -> Self { Self {} }
fn write_all<W: Write>(&self, f: &mut W, entries: &Entries) -> io::Result<()> {
#[derive(serde::Serialize)]
struct SerdeEntries<'a> {
errors: &'a Vec<&'a ScanError<'a>>,
findings: &'a Vec<&'a Findings<'a>>,
}
let result = serde_json::to_writer_pretty(
f,
&SerdeEntries {
errors: &entries.iter().filter_map(|e| e.as_ref().err()).sorted().collect(),
findings: &entries.iter().filter_map(|f| f.as_ref().ok()).sorted().collect(),
},
);
if let Err(err) = result {
log::error!("Error while serialising: {}", err);
return Err(err.into());
}
Ok(())
}
}

View file

@ -30,10 +30,10 @@ use once_cell::sync::OnceCell;
use walkdir::{DirEntry, WalkDir}; use walkdir::{DirEntry, WalkDir};
use crate::findings::Findings; use crate::findings::Findings;
use crate::findings::ScanError;
use crate::formats::{Format, PowerShell, Shell}; use crate::formats::{Format, PowerShell, Shell};
use crate::mime_db::MimeDb; use crate::mime_db::MimeDb;
use crate::parameters::{OutputFormat, ScanOpts}; use crate::parameters::{OutputFormat, ScanOpts};
use crate::scan_error::ScanError;
use std::collections::BTreeSet; use std::collections::BTreeSet;
mod findings; mod findings;
@ -41,6 +41,7 @@ mod formats;
mod inspectors; mod inspectors;
mod mime_db; mod mime_db;
mod parameters; mod parameters;
mod scan_error;
pub(crate) mod string_type; pub(crate) mod string_type;
#[cfg(test)] #[cfg(test)]
@ -117,7 +118,7 @@ fn main() {
.filter( .filter(
|result| result.is_err() || !result.as_ref().unwrap().valid, |result| result.is_err() || !result.as_ref().unwrap().valid,
// TODO: find a way to trace! the valid files without doing ↓ // TODO: find a way to trace! the valid files without doing ↓
// || if result.as_ref().unwrap().valid { trace!("{:?} ok", result.as_ref().unwrap().file); false } else { true } // || if result.as_ref().unwrap().valid { trace!("{:?} is fine", result.as_ref().unwrap().file); false } else { true }
) )
.collect(); .collect();
@ -147,8 +148,6 @@ fn main() {
let result = match args.output_format { let result = match args.output_format {
OutputFormat::Sh => Shell::new().write_all(&mut buffered_stdout, &results), OutputFormat::Sh => Shell::new().write_all(&mut buffered_stdout, &results),
OutputFormat::PowerShell => PowerShell::new().write_all(&mut buffered_stdout, &results), OutputFormat::PowerShell => PowerShell::new().write_all(&mut buffered_stdout, &results),
#[cfg(feature = "json")]
OutputFormat::Json => formats::Json::new().write_all(&mut buffered_stdout, &results),
OutputFormat::Text => todo!(), OutputFormat::Text => todo!(),
}; };
@ -229,7 +228,9 @@ fn wanted_file(
} }
/// Given a file path, returns its extension, using [`std::path::Path::extension`]. /// Given a file path, returns its extension, using [`std::path::Path::extension`].
fn extension_from_path(path: &Path) -> Option<&OsStr> { path.extension() } fn extension_from_path(path: &Path) -> Option<&OsStr> {
path.extension()
}
/// Inspects the given entry, returning a [`Findings`] on success and a [`ScanError`] on failure. /// Inspects the given entry, returning a [`Findings`] on success and a [`ScanError`] on failure.
/// ///

View file

@ -24,9 +24,6 @@ pub enum OutputFormat {
PowerShell, PowerShell,
/// Plain text. /// Plain text.
Text, Text,
/// JSON.
#[cfg(feature = "json")]
Json,
} }
// TODO: convert this to macro style?: https://docs.rs/clap/3.0.0-beta.2/clap/index.html#using-macros // TODO: convert this to macro style?: https://docs.rs/clap/3.0.0-beta.2/clap/index.html#using-macros
@ -51,37 +48,23 @@ pub struct Parameters {
/// Only examine files with these extensions. /// Only examine files with these extensions.
/// Multiple extensions can be specified by either using the flag multiple times (`-e jpg -e png -e gif`), or by /// Multiple extensions can be specified by either using the flag multiple times (`-e jpg -e png -e gif`), or by
/// separating them with commas (`-e jpg,png,gif`). /// separating them with commas (`-e jpg,png,gif`).
#[clap(short, long, use_delimiter = true, require_delimiter = true, value_name = "ext", validator = lowercase_exts)] #[clap(short, long, use_delimiter = true, require_delimiter = true, value_name = "ext")]
pub exts: Option<Vec<StringType>>, pub exts: Option<Vec<StringType>>,
/// Use these preset lists of extensions as the search filter (comma-separated list). /// Use these preset lists of extensions as the search filter (comma-separated list).
/// `media` includes all extensions from the `audio`, `video`, and `images` sets, making `-E media` equivalent to /// `media` includes all extensions from the `audio`, `video`, and `images` sets, making `-E media` equivalent to
/// `-E audio,video,images`. /// `-E audio,video,images`.
#[clap( #[clap(short = 'E', long, arg_enum, use_delimiter = true, require_delimiter = true, value_name = "set")]
short = 'E',
long,
arg_enum,
use_delimiter = true,
require_delimiter = true,
value_name = "set"
)]
pub ext_set: Vec<ExtensionSet>, pub ext_set: Vec<ExtensionSet>,
/// Don't scan files with these extensions. /// Don't scan files with these extensions.
/// This option takes precedence over extensions specified with `-e` or `-E`. /// This option takes precedence over extensions specified with `-e` or `-E`.
#[clap(short = 'x', long, use_delimiter = true, require_delimiter = true, value_name = "ext", validator = lowercase_exts)] #[clap(short = 'x', long, use_delimiter = true, require_delimiter = true, value_name = "ext")]
pub exclude: Option<Vec<StringType>>, pub exclude: Option<Vec<StringType>>,
/// Exclude files using a preset list of extensions. /// Exclude files using a preset list of extensions.
/// This option takes precedence over extensions specified with `-e` or `-E`. /// This option takes precedence over extensions specified with `-e` or `-E`.
#[clap( #[clap(short = 'X', long, arg_enum, use_delimiter = true, require_delimiter = true, value_name = "set")]
short = 'X',
long,
arg_enum,
use_delimiter = true,
require_delimiter = true,
value_name = "set"
)]
pub exclude_set: Vec<ExtensionSet>, pub exclude_set: Vec<ExtensionSet>,
/// Don't skip hidden files and directories. /// Don't skip hidden files and directories.
@ -120,14 +103,6 @@ pub struct Parameters {
pub dirs: PathBuf, pub dirs: PathBuf,
} }
fn lowercase_exts(exts: &str) -> Result<(), String> {
// TODO: i would much rather accept uppercase exts and convert them to lowercase than just rejecting lowercase exts...
if exts.to_lowercase() != exts {
return Err(String::from("Supplied extensions must be lowercase"));
}
Ok(())
}
/// Further options relating to scanning. /// Further options relating to scanning.
#[derive(PartialEq, Debug)] #[derive(PartialEq, Debug)]
pub struct ScanOpts { pub struct ScanOpts {
@ -214,14 +189,14 @@ impl Parameters {
match self.quiet { match self.quiet {
0 => { 0 => {
match self.verbose { match self.verbose {
0 => "info", // no verbosity flags specified 0 => "info", // no verbosity flags specified
1 => "debug", // -v 1 => "debug", // -v
_ => "trace", // -vv... _ => "trace" // -vv...
} }
} },
1 => "warn", // -q 1 => "warn", // -q
2 => "error", // -qq 2 => "error", // -qq
_ => "off", // -qqq... _ => "off" // -qqq...
} }
} }
} }

26
src/scan_error.rs Normal file
View file

@ -0,0 +1,26 @@
use std::fmt::{Display, Formatter, Result};
use std::path::Path;
#[derive(Debug, PartialEq, PartialOrd, Ord, Eq)]
pub enum ScanError<'a> {
/// Something went wrong while trying to read the given file.
File(&'a Path),
/// Failed to determine the mimetype of the given file.
Mime(&'a Path),
}
impl<'a> Display for ScanError<'a> {
fn fmt(&self, f: &mut Formatter<'_>) -> Result {
write!(
f,
"Couldn't {} file: {}",
match self {
Self::File(_) => "read",
Self::Mime(_) => "determine mime type of",
},
match self {
Self::File(f) | Self::Mime(f) => f.to_string_lossy(),
}
)
}
}

View file

@ -1,5 +1,5 @@
use crate::findings::Findings; use crate::findings::Findings;
use crate::formats::{Format, PowerShell, Shell}; use crate::formats::{Format, Shell};
use crate::inspectors::{mime_extension_lookup, BUF_SIZE}; use crate::inspectors::{mime_extension_lookup, BUF_SIZE};
use crate::mime_db::MimeDb; use crate::mime_db::MimeDb;
use crate::string_type::String; use crate::string_type::String;
@ -304,15 +304,14 @@ fn rejects_bad_args() {
/// Generate random series of bytes and try to identify them. This test makes no assertions and can only fail if the /// Generate random series of bytes and try to identify them. This test makes no assertions and can only fail if the
/// mime database somehow panics or hangs. /// mime database somehow panics or hangs.
fn identify_random_bytes() { fn identify_random_bytes() {
use rand::RngCore;
let db = get_mime_db(); let db = get_mime_db();
let mut rng = rand::thread_rng(); let rng = fastrand::Rng::new();
let mut bytes: [u8; BUF_SIZE * 2] = [0; BUF_SIZE * 2]; let mut bytes: Vec<u8>;
let mut results: HashMap<Mime, i32> = HashMap::new(); let mut results: HashMap<Mime, i32> = HashMap::new();
for _ in 1..1000 { for _ in 1..500 {
rng.fill_bytes(&mut bytes); bytes = std::iter::repeat_with(|| rng.u8(..)).take(BUF_SIZE * 2).collect();
if let Some(detected_type) = db.get_type(&bytes) { if let Some(detected_type) = db.get_type(&*bytes) {
*results.entry(detected_type).or_insert(0) += 1; *results.entry(detected_type).or_insert(0) += 1;
} }
} }
@ -336,61 +335,21 @@ fn outputs_move_commands() {
mime: IMAGE_JPEG, mime: IMAGE_JPEG,
})]; })];
for format in &["Shell", "PowerShell"] {
let mut cursor = std::io::Cursor::new(Vec::new());
let mut contents = std::string::String::new();
match *format {
"Shell" => Shell::new().write_all(&mut cursor, &entries),
"PowerShell" => PowerShell::new().write_all(&mut cursor, &entries),
_ => unreachable!(),
}
.expect("Failed to write to cursor");
cursor.set_position(0);
cursor
.read_to_string(&mut contents)
.expect("Failed to read from cursor to string");
// the output should contain a command like "mv -i misnamed_file.png misnamed_file.jpg"
assert!(
contents.contains("misnamed_file.jpg"),
"{} output doesn't contain move command!\n===\n{}",
format,
contents
)
}
}
#[test]
/// Ensure JSON output is valid.
fn test_json() {
use crate::formats::Json;
use std::io::Read;
// create an example finding stating that "misnamed_file.png" has been identified as a jpeg file
let entries = vec![Ok(Findings {
file: Path::new("misnamed_file.png"),
valid: false,
mime: IMAGE_JPEG,
})];
let mut cursor = std::io::Cursor::new(Vec::new()); let mut cursor = std::io::Cursor::new(Vec::new());
let mut contents = std::string::String::new(); let mut contents = std::string::String::new();
Json::new() Shell::new()
.write_all(&mut cursor, &entries) .write_all(&mut cursor, &entries)
.expect("Failed to write to cursor"); .expect("Failed to write to cursor");
cursor.set_position(0); cursor.set_position(0);
cursor cursor
.read_to_string(&mut contents) .read_to_string(&mut contents)
.expect("Failed to read from cursor to string"); .expect("Failed to read from cursor to string");
// the output should contain the file's mime type // the output should contain a command like "mv -i misnamed_file.png misnamed_file.jpg"
assert!( assert!(
contents.contains(IMAGE_JPEG.essence_str()), contents.contains("misnamed_file.jpg"),
"JSON output doesn't contain move command!\n===\n{}", "Output doesn't contain move command!"
contents
) )
} }
@ -432,10 +391,7 @@ fn writables_is_correct() {
#[test] #[test]
/// Test various combinations of verbosity flags. /// Test various combinations of verbosity flags.
fn verbosity() { fn verbosity() {
assert!( assert!(Parameters::try_parse_from(&["fif", "-q", "-v"]).is_err(), "Failed to reject usage of both -q and -v!");
Parameters::try_parse_from(&["fif", "-q", "-v"]).is_err(),
"Failed to reject usage of both -q and -v!"
);
let mut expected_results = HashMap::new(); let mut expected_results = HashMap::new();
expected_results.insert("-qqqqqqqq", "off"); expected_results.insert("-qqqqqqqq", "off");