add option for following symlinks, make extensions optional, new version!!

CHANGELOG.md

@@ -2,11 +2,17 @@
 Dates are given in YYYY-MM-DD format.
 
 ## v0.2
-### v0.2.11 (Unreleased)
+### v0.2.11 (0201-)
+#### Features
+- fif can now traverse symlinks with the `-f`/`--follow-symlinks` flag
+- Extensions are no longer mandatory - running fif without `-e` or `-E` will scan all files, regardless of extension
+  (files without extensions are still skipped unless the -S flag is used)
+#### Bugfixes
 - Fixed compilation on big endian 32-bit architectures (see
   [here]https://github.com/bodil/smartstring/blob/v0.2.6/src/config.rs#L101-L103 for why that was a problem in the first
   place)
-- Fixed broken tests
+- Fixed broken tests for the [`infer`] backend
+#### Other
 - Better mime type detection:
   - Consider "some/x-thing" and "some/thing" to be identical
   - Use a patched version of mime_guess (which took a while to make 0u0;) with many more extension<->type mappings

Cargo.lock

@@ -177,7 +177,7 @@ dependencies = [
 
 [[package]]
 name = "fif"
-version = "0.2.10"
+version = "0.2.11"
 dependencies = [
  "cached",
  "cfg-if",

Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "fif"
 description = "A command-line tool for detecting and optionally correcting files with incorrect extensions."
-version = "0.2.10"
+version = "0.2.11"
 authors = ["Lynnesbian <lynne@bune.city>"]
 edition = "2018"
 license = "GPL-3.0-or-later"
@@ -42,9 +42,9 @@ smartstring = "0.2.6"
 
 [patch.crates-io]
 # use git version while waiting on a release incorporating https://github.com/ebassi/xdg-mime-rs/commit/de5a6dd
-xdg-mime = {git = "https://github.com/ebassi/xdg-mime-rs", version = "0.3", rev = "de5a6dd" }
+xdg-mime = { git = "https://github.com/ebassi/xdg-mime-rs", version = "0.3", rev = "de5a6dd" }
 # forked version with many more mime types
-mime_guess = {git = "https://github.com/Lynnesbian/mime_guess", version = "2.0.4"}
+mime_guess = { git = "https://github.com/Lynnesbian/mime_guess", version = "2.0.4" }
 
 [dependencies.clap]
 version = "3.0.0-beta.2"

clippy.sh

@@ -13,10 +13,12 @@ cargo clippy --tests -- \
  -W clippy::wrong_pub_self_convention \
  -A clippy::unused_io_amount \
  -A clippy::redundant_closure_for_method_calls \
- -A clippy::shadow_unrelated
+ -A clippy::shadow_unrelated \
+ -A clippy::option_if_let_else
 
 # ALLOWS:
 # unused_io_amount: there are two places where i want to read up to X bytes and i'm fine with getting less than that
 # redundant_closure...: the alternative is often much more verbose
 # shadow_unrelated: sometimes things that seem unrelated are actually related ;)
+# option_if_let_else: the suggested code is usually harder to read than the original
 

src/formats.rs

@@ -167,6 +167,8 @@ impl Format for Script {
 	}
 }
 
+// PowerShell is a noun, not a type
+#[allow(clippy::doc_markdown)]
 /// PowerShell script.
 pub struct PowerShell {}
 

src/main.rs

@@ -81,7 +81,7 @@ fn main() {
 
 	debug!("Checking files with extensions: {:?}", extensions);
 
-	let entries = scan_directory(&args.dirs, &extensions, &args.get_scan_opts());
+	let entries = scan_directory(&args.dirs, extensions.as_ref(), &args.get_scan_opts());
 
 	if entries.is_none() {
 		// no need to log anything for fatal errors - fif will already have printed something obvious like
@@ -112,8 +112,9 @@ fn main() {
 		match result {
 			Ok(r) => {
 				debug!(
-					"{:?} should have file extension {}",
+					"{:?} is {}, should have file extension {}",
 					r.file,
+					r.mime,
 					r.recommended_extension().unwrap_or_else(|| "???".into())
 				)
 			}
@@ -165,8 +166,8 @@ cfg_if! {
 }
 
 /// Returns `true` if a file matches the given criteria. This means checking whether the file's extension appears in
-/// `exts`, potentially skipping over hidden files, and so on.
-fn wanted_file(entry: &DirEntry, exts: &[&str], scan_opts: &ScanOpts) -> bool {
+/// `exts` (if specified), potentially skipping over hidden files, and so on.
+fn wanted_file(entry: &DirEntry, exts: Option<&Vec<&str>>, scan_opts: &ScanOpts) -> bool {
 	if entry.depth() == 0 {
 		// the root directory should always be scanned.
 		return true;
@@ -189,7 +190,13 @@ fn wanted_file(entry: &DirEntry, exts: &[&str], scan_opts: &ScanOpts) -> bool {
 		return false;
 	}
 
+	if let Some(exts) = exts {
+		// only scan if the file has one of the specified extensions.
 		exts.contains(&ext.unwrap().to_string_lossy().to_lowercase().as_str())
+	} else {
+		// no extensions specified - no reason not to scan this file.
+		true
+	}
 }
 
 /// Given a file path, returns its extension, using [`std::path::Path::extension`].
@@ -264,8 +271,8 @@ fn scan_from_walkdir(entries: &[DirEntry]) -> Vec<Result<Findings, ScanError>> {
 
 /// Scans a given directory with [`WalkDir`], filters with [`wanted_file`], checks for errors, and returns a vector of
 /// [DirEntry]s.
-fn scan_directory(dirs: &Path, exts: &[&str], scan_opts: &ScanOpts) -> Option<Vec<DirEntry>> {
-	let stepper = WalkDir::new(dirs).into_iter();
+fn scan_directory(dirs: &Path, exts: Option<&Vec<&str>>, scan_opts: &ScanOpts) -> Option<Vec<DirEntry>> {
+	let stepper = WalkDir::new(dirs).follow_links(scan_opts.follow_symlinks).into_iter();
 	let mut probably_fatal_error = false;
 	let entries: Vec<DirEntry> = stepper
 		.filter_entry(|e| wanted_file(e, exts, scan_opts)) // filter out unwanted files

src/parameters.rs

@@ -42,17 +42,11 @@ pub enum OutputFormat {
 )]
 pub struct Parameters {
 	/// Only examine files with these extensions (Comma-separated list)
-	#[clap(
-		short,
-		long,
-		use_delimiter = true,
-		require_delimiter = true,
-		required_unless_present = "ext-set"
-	)]
+	#[clap(short, long, use_delimiter = true, require_delimiter = true, group = "extensions")]
 	pub exts: Option<Vec<StringType>>,
 
 	/// Use a preset list of extensions as the search filter
-	#[clap(short = 'E', long, arg_enum, required_unless_present = "exts")]
+	#[clap(short = 'E', long, arg_enum, group = "extensions")]
 	pub ext_set: Option<ExtensionSet>,
 
 	/// Don't skip hidden files and directories
@@ -67,6 +61,10 @@ pub struct Parameters {
 	#[clap(short, long, default_value = DEFAULT_FORMAT, arg_enum)]
 	pub output_format: OutputFormat,
 
+	/// Follow symlinks
+	#[clap(short, long)]
+	pub follow_symlinks: bool,
+
 	/// Directory to process
 	// TODO: right now this can only take a single directory - should this be improved?
 	#[clap(name = "DIR", default_value = ".", parse(from_os_str))]
@@ -74,24 +72,27 @@ pub struct Parameters {
 }
 
 /// Further options relating to scanning.
+#[derive(PartialEq, Debug)]
 pub struct ScanOpts {
 	/// Whether hidden files and directories should be scanned.
 	pub hidden: bool,
 	/// Whether files without extensions should be scanned.
 	pub extensionless: bool,
+	/// Should symlinks be followed?
+	pub follow_symlinks: bool,
 }
 
 impl Parameters {
-	pub fn extensions(&self) -> Vec<&str> {
+	pub fn extensions(&self) -> Option<Vec<&str>> {
 		if let Some(exts) = &self.exts {
 			// extensions supplied like "-e png,jpg,jpeg"
-			exts.iter().map(|s| s.as_str()).collect()
+			Some(exts.iter().map(|s| s.as_str()).collect())
 		} else if let Some(exts) = &self.ext_set {
 			// extensions supplied like "-E images"
-			exts.extensions()
+			Some(exts.extensions())
 		} else {
-			// neither -E nor -e was passed - this should be impossible
-			unreachable!()
+			// neither -E nor -e was passed
+			None
 		}
 	}
 
@@ -99,6 +100,7 @@ impl Parameters {
 		ScanOpts {
 			hidden: self.scan_hidden,
 			extensionless: self.scan_extensionless,
+			follow_symlinks: self.follow_symlinks,
 		}
 	}
 }

src/string_type.rs

@@ -5,7 +5,7 @@ cfg_if! {
 		// most architectures
 		pub use smartstring::alias::String;
 	} else {
-		// powerpc
+		// powerpc and other big endian 32-bit archs
 		pub use std::string::String;
 	}
 }

src/tests/mod.rs

@@ -101,11 +101,12 @@ fn simple_directory() {
 	let scan_opts = ScanOpts {
 		hidden: true,
 		extensionless: false,
+		follow_symlinks: false,
 	};
 
 	let entries = scan_directory(
 		&dir.path().to_path_buf(),
-		&["jpg", "jpeg", "png", "pdf", "zip"],
+		Some(&vec!["jpg", "jpeg", "png", "pdf", "zip"]),
 		&scan_opts,
 	)
 	.expect("Directory scan failed.");
@@ -157,21 +158,51 @@ fn simple_directory() {
 fn argument_parsing() {
 	use clap::Clap;
 
-	// check if "jpg" is in the list of extensions to be considered when passing "-E images"
-	let args: Parameters = Parameters::parse_from(vec!["fif", "-E", "images"]);
-	assert!(args.extensions().contains(&"jpg"));
+	// pass `-f`, which enables following symlinks, and `-E images`, which scans files with image extensions
+	let args: Parameters = Parameters::parse_from(vec!["fif", "-f", "-E", "images"]);
+
+	// check if "jpg" is in the list of extensions to be scanned
+	assert!(args
+		.extensions()
+		.expect("args.extensions() should contain the `images` set!")
+		.contains(&"jpg"));
 
 	// make sure "scan_hidden" is false
 	assert!(!args.scan_hidden);
 
 	// exts should be none
 	assert!(args.exts.is_none());
+
+	// get the ScanOpts, and make sure they match expectations
+	assert_eq!(
+		args.get_scan_opts(),
+		ScanOpts {
+			hidden: false,
+			extensionless: false,
+			follow_symlinks: true
+		}
+	)
 }
 
 #[test]
 fn rejects_bad_args() {
 	use clap::Clap;
-	assert!(Parameters::try_parse_from(vec!["fif", "-abcdefg", "-E", "-e"]).is_err());
+	let tests = [
+		// Non-existent flags:
+		vec!["fif", "-abcdefghijklmnopqrstuvwxyz"],
+		// `-E` without specifying a set:
+		vec!["fif", "-E"],
+		// `-E` with an invalid set:
+		vec!["fif", "-E", "pebis"],
+		// `-E` and `-e`:
+		vec!["fif", "-E", "media", "-e", "jpg"],
+		// `-e` with nothing but commas:
+		vec!["fif", "-e", ",,,,,"],
+	];
+
+	for test in &tests {
+		assert!(Parameters::try_parse_from(test).is_err(), "Failed to reject {:?}", test);
+	}
 }
 
 #[test]