fixed powershell output

sort order: files that couldn't be read, then files with no known mimetype, then files with no known extensions, then files with the wrong extension

CHANGELOG.md

@@ -2,12 +2,16 @@
 Dates are given in YYYY-MM-DD format.
 
 ## v0.2
-### v0.2.12 (2021-???)
+### v0.2.13 (2021-???)
 - Added Apple iWork document formats to documents extension set
 - Cleaned up and properly documented tests
-- Renamed `Script` (in `formats.rs`) to `Shell`, in line with renaming in `paramaters.rs`
+- Renamed `Script` (in `formats.rs`) to `Shell`, in line with renaming in `parameters.rs`
-- Added .rpa (renpy archive) support
+- Added .rpa (Ren'Py archive) support to infer backend
 - Added system extension set
+- [`xdg-mime`] no longer uses git version
+- Output is sorted: Files that couldn't be read, then files with no known mimetype, then files with no known extensions,
+  then files with the wrong extension
+- Fixed some bad formatting in PowerShell output
 
 ### v0.2.12 (2021-04-14)
 #### Features

Cargo.lock

@@ -202,6 +202,7 @@ dependencies = [
  "exitcode",
  "fastrand",
  "infer",
+ "itertools",
  "log",
  "mime_guess",
  "once_cell",
@@ -282,6 +283,15 @@ dependencies = [
  "cfg-if",
 ]
 
+[[package]]
+name = "itertools"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "37d572918e350e82412fe766d24b15e6682fb2ed2bbe018280caa810397cb319"
+dependencies = [
+ "either",
+]
+
 [[package]]
 name = "lazy_static"
 version = "1.4.0"
@@ -742,7 +752,8 @@ checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
 [[package]]
 name = "xdg-mime"
 version = "0.3.3"
-source = "git+https://github.com/ebassi/xdg-mime-rs?rev=de5a6dd#de5a6dd04b1a225894c51b5c6e5f5a22ffa46373"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "87bf7b69bb50588d70a36e467be29d3df3e8c32580276d62eded9738c1a797aa"
 dependencies = [
  "dirs-next",
  "glob",

Cargo.toml

@@ -33,16 +33,15 @@ infer = "0.4.0"
 rayon = { version = "1.5.0", optional = true }
 exitcode = "1.1.2"
 cfg-if = "1.0.0"
+itertools = "0.10.0"
 
 [target.'cfg(unix)'.dependencies]
-xdg-mime = "0.3.2"
+xdg-mime = "0.3.3"
 
 [target.'cfg(not(all(target_endian = "big", target_pointer_width = "32")))'.dependencies]
 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" }
 # forked version with many more mime types
 mime_guess = { git = "https://github.com/Lynnesbian/mime_guess", version = "2.0.4" }
 
@@ -70,6 +69,9 @@ lto = "thin"
 [profile.test]
 opt-level = 0
 
-# optimise dependencies, even when producing debug builds
+# optimise dependencies, even when producing debug and test builds
 [profile.dev.package."*"]
 opt-level = 3
+
+[profile.test.package."*"]
+opt-level = 3

src/extension_set.rs

@@ -43,9 +43,10 @@ impl ExtensionSet {
 			// many compressed file types follow the name scheme "application/x.+compressed.*" - maybe this can be used
 			// somehow to extract extensions for compressed files from mime_guess?
 			Self::Archives => vec!["zip", "tar", "gz", "zst", "xz", "rar", "7z", "bz", "bz2", "tgz", "rpa"],
-			Self::System => vec!["com", "dll", "exe", "sys", "reg", "nt", "cpl", "msi", "efi", "bio", "rcv", "mbr", "sbf", "grub", "ko", "dylib", "pdb", "hdmp", "crash",
+			Self::System => vec![
+				"com", "dll", "exe", "sys", "reg", "nt", "cpl", "msi", "efi", "bio", "rcv", "mbr", "sbf", "grub", "ko",
+				"dylib", "pdb", "hdmp", "crash",
 			],
-			Self::Archives => vec!["zip", "tar", "gz", "zst", "xz", "rar", "7z", "bz", "bz2", "tgz"],
 		}
 	}
 }

src/findings.rs

@@ -1,11 +1,12 @@
 use std::path::Path;
 
-use crate::string_type::String;
 use mime_guess::Mime;
 
 use crate::inspectors::mime_extension_lookup;
+use crate::string_type::String;
 
 /// Information about a scanned file.
+#[derive(Ord, PartialOrd, Eq, PartialEq)]
 pub struct Findings<'a> {
 	/// The location of the scanned file.
 	pub file: &'a Path,

src/formats.rs

@@ -1,5 +1,6 @@
 //! The various formats that [fif](crate) can output to.
 
+use std::ffi::OsStr;
 use std::io::{self, Write};
 #[cfg(unix)]
 use std::os::unix::ffi::OsStrExt;
@@ -9,7 +10,7 @@ use snailquote::escape;
 
 use crate::scan_error::ScanError;
 use crate::{Findings, BACKEND};
-use std::ffi::OsStr;
+use itertools::Itertools;
 
 /// The current version of fif, as defined in Cargo.toml.
 const VERSION: Option<&'static str> = option_env!("CARGO_PKG_VERSION");
@@ -83,18 +84,23 @@ pub trait Format {
 		// TODO: clean this up - it's kinda messy
 		self.header(entries, f)?;
 
-		for entry in entries {
+		// output will be generated in the order:
-			match entry {
+		// - files that couldn't be read
-				Ok(finding) => {
+		// - files with no known mime type
-					if let Some(ext) = finding.recommended_extension() {
+		// - files with no known extension
-						self.rename(f, finding.file, &finding.file.with_extension(ext.as_str()))?
+		// - files with a known extension
-					} else {
+		// files that already have a correct extension won't be represented in the output.
-						self.no_known_extension(f, finding.file)?
-					}
-				}
 
-				Err(error) => {
+		// sort errors so unreadable files appear before files with unknown mimetypes - ScanError impls Ord such that
-					// something went wrong 0uo
+		// ScanError::File > ScanError::Mime
+		let errors = entries.iter().filter_map(|e| e.as_ref().err()).sorted();
+		// sort files so that files with no known extension come before those with known extensions - None > Some("jpg")
+		let findings = entries
+			.iter()
+			.filter_map(|e| e.as_ref().ok())
+			.sorted_by(|a, b| b.recommended_extension().cmp(&a.recommended_extension()).reverse());
+
+		for error in errors {
 			match error {
 				// failed to read the file
 				ScanError::File(path) => self.unreadable(f, path)?,
@@ -102,6 +108,12 @@ pub trait Format {
 				ScanError::Mime(path) => self.unknown_type(f, path)?,
 			}
 		}
+
+		for finding in findings {
+			if let Some(ext) = finding.recommended_extension() {
+				self.rename(f, finding.file, &finding.file.with_extension(ext.as_str()))?
+			} else {
+				self.no_known_extension(f, finding.file)?
 			}
 		}
 
@@ -214,7 +226,7 @@ impl Format for PowerShell {
 	fn unknown_type<W: Write>(&self, f: &mut W, path: &Path) -> io::Result<()> {
 		smart_write(
 			f,
-			&["<# Failed to detect mime type for ".into(), path.into(), "#>".into()],
+			&["<# Failed to detect mime type for ".into(), path.into(), "#>".into(), Writable::Newline],
 		)
 	}
 

src/inspectors.rs

@@ -91,8 +91,6 @@ cached! {
 			}
 		}
 
-
-
 		match exts {
 			Some(exts) => {
 				let possible_exts: Vec<String> = exts.iter().map(|e| String::from(*e)).collect();

src/main.rs

@@ -17,11 +17,14 @@
 #![forbid(unsafe_code)]
 #![warn(trivial_casts, unused_lifetimes, unused_qualifications)]
 
-use std::io::{stdout, BufWriter};
+use std::ffi::OsStr;
+use std::io::{stdout, BufWriter, Write};
 use std::path::Path;
+use std::process::exit;
 
 use cfg_if::cfg_if;
 use clap::Clap;
+use env_logger::Env;
 use log::{debug, error, info, trace, warn};
 use once_cell::sync::OnceCell;
 #[cfg(feature = "multi-threaded")]
@@ -33,9 +36,6 @@ use crate::formats::{Format, PowerShell, Shell};
 use crate::mime_db::MimeDb;
 use crate::parameters::{OutputFormat, ScanOpts};
 use crate::scan_error::ScanError;
-use env_logger::Env;
-use std::ffi::OsStr;
-use std::process::exit;
 
 mod extension_set;
 mod findings;
@@ -143,6 +143,11 @@ fn main() {
 		exit(exitcode::IOERR);
 	}
 
+	if buffered_stdout.flush().is_err() {
+		error!("Failed to flush stdout.");
+		exit(exitcode::IOERR);
+	}
+
 	debug!("Done");
 }
 

src/scan_error.rs

@@ -1,7 +1,7 @@
 use std::fmt::{Display, Formatter, Result};
 use std::path::Path;
 
-#[derive(Debug)]
+#[derive(Debug, PartialEq, PartialOrd, Ord, Eq)]
 pub enum ScanError<'a> {
 	/// Something went wrong while trying to read the given file.
 	File(&'a Path),

src/tests/mod.rs

@@ -192,7 +192,7 @@ fn argument_parsing() {
 		ScanOpts {
 			hidden: false,
 			extensionless: false,
-			follow_symlinks: true
+			follow_symlinks: true,
 		},
 		"ScanOpts are incorrect"
 	)