replace occurrences of "mimetype" w/ "MIME type"

This commit is contained in:
Lynne Megido 2021-11-25 06:29:27 +10:00
parent ec10b58482
commit 33f4eb4135
Signed by: lynnesbian
GPG Key ID: F0A184B5213D9F90
8 changed files with 33 additions and 33 deletions

View File

@ -132,7 +132,7 @@ this version of `clap`, which caused the build to fail. Also, `clap` 3 beta 4 de
- System extension set (`.dll`, `.so`, `.exe`...) - System extension set (`.dll`, `.so`, `.exe`...)
- [`infer`] backend now supports Ren'Py archive (`.rpa`) files - [`infer`] backend now supports Ren'Py archive (`.rpa`) files
### Changed ### Changed
- Output is now sorted: Files that couldn't be read, then files with no known mimetype, then files with no known - Output is now sorted: Files that couldn't be read, then files with no known MIME type, then files with no known
extensions, then files with the wrong extension extensions, then files with the wrong extension
- Added Apple iWork document formats to Documents extension set (`.pages`, `.key`, `.numbers`) - Added Apple iWork document formats to Documents extension set (`.pages`, `.key`, `.numbers`)
### Fixed ### Fixed
@ -164,7 +164,7 @@ this version of `clap`, which caused the build to fail. Also, `clap` 3 beta 4 de
### Added ### Added
- fif can now traverse symlinks with the `-f`/`--follow-symlinks` flag - fif can now traverse symlinks with the `-f`/`--follow-symlinks` flag
### Changed ### Changed
- Better mime type detection: - Better MIME type detection:
- Consider "some/x-thing" and "some/thing" to be identical - 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 - Use a patched version of mime_guess (which took a while to make 0u0;) with many more extension/type mappings
- Extensions are no longer mandatory - running fif without `-e` or `-E` will scan all files, regardless of extension - Extensions are no longer mandatory - running fif without `-e` or `-E` will scan all files, regardless of extension

View File

@ -176,7 +176,7 @@ The five logging levels are used as follows:
| Level | Description | Example | | Level | Description | Example |
|-|-|-| |-|-|-|
| error | Errors that cause fif to stop running | fif was unable to open the provided directory | | error | Errors that cause fif to stop running | fif was unable to open the provided directory |
| warn | Warnings that don't cause fif to stop running | fif was unable to determine the mime type of a given file | | warn | Warnings that don't cause fif to stop running | fif was unable to determine the MIME type of a given file |
| info | Information pertaining to fif's status | The provided directory was scanned without issue, and no files are in need of renaming | | info | Information pertaining to fif's status | The provided directory was scanned without issue, and no files are in need of renaming |
| debug | Debug information - usually not important to end users | The list of extensions fif will consider | | debug | Debug information - usually not important to end users | The list of extensions fif will consider |
| trace | Trace info - usually not important to end users | "Found 15 items to check", "Scan successful", etc. | | trace | Trace info - usually not important to end users | "Found 15 items to check", "Scan successful", etc. |

View File

@ -22,10 +22,10 @@ use walkdir::{DirEntry, WalkDir};
use crate::findings::{Findings, ScanError}; use crate::findings::{Findings, ScanError};
use crate::mime_db::MimeDb; use crate::mime_db::MimeDb;
use crate::parameters::ScanOpts; use crate::parameters::ScanOpts;
use crate::{String, MIMEDB};
use crate::utils::APPLICATION_ZIP; use crate::utils::APPLICATION_ZIP;
use crate::{String, MIMEDB};
/// Cache of mimetypes and their associated extensions, used by [`mime_extension_lookup()`] /// Cache of MIME types and their associated extensions, used by [`mime_extension_lookup()`]
static MIMEXT: Lazy<RwLock<HashMap<String, Option<Vec<String>>>>> = Lazy::new(|| RwLock::new(HashMap::new())); static MIMEXT: Lazy<RwLock<HashMap<String, Option<Vec<String>>>>> = Lazy::new(|| RwLock::new(HashMap::new()));
/// The number of bytes to read initially when identifying a file's MIME type. Used in the [`mime_type`] function. /// The number of bytes to read initially when identifying a file's MIME type. Used in the [`mime_type`] function.
@ -39,7 +39,7 @@ pub const INITIAL_BUF_SIZE: usize = 128;
/// the [`mime_type`] function. /// the [`mime_type`] function.
pub const BUF_SIZE: usize = 8192; pub const BUF_SIZE: usize = 8192;
/// A [`Mime`] representing the "application/x-ole-storage" mimetype. /// A [`Mime`] representing the "application/x-ole-storage" MIME type.
static APPLICATION_X_OLE_STORAGE: Lazy<Mime> = Lazy::new(|| Mime::from_str("application/x-ole-storage").unwrap()); static APPLICATION_X_OLE_STORAGE: Lazy<Mime> = Lazy::new(|| Mime::from_str("application/x-ole-storage").unwrap());
cfg_if! { cfg_if! {
@ -114,29 +114,29 @@ pub fn wanted_file(
/// 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.
/// ///
/// In the event of an IO error, the returned [`ScanError`] will be of type [`ScanError::File`]. Otherwise, a /// In the event of an IO error, the returned [`ScanError`] will be of type [`ScanError::File`]. Otherwise, a
/// [`ScanError::Mime`] will be returned, meaning that the file was scanned successfully, but a mimetype could not be /// [`ScanError::Mime`] will be returned, meaning that the file was scanned successfully, but a MIME type could not be
/// determined. /// determined.
pub fn scan_file(entry: &DirEntry, canonical_paths: bool) -> Result<Findings, ScanError> { pub fn scan_file(entry: &DirEntry, canonical_paths: bool) -> Result<Findings, ScanError> {
let path = entry.path(); let path = entry.path();
// try to determine mimetype for this entry // try to determine MIME type for this entry
let result = match mime_type(&*MIMEDB, path) { let result = match mime_type(&*MIMEDB, path) {
// an error occurred while trying to read the file // an error occurred while trying to read the file
Err(_) => return Err(ScanError::File(path)), Err(_) => return Err(ScanError::File(path)),
// the file was read successfully, but we were unable to determine its mimetype // the file was read successfully, but we were unable to determine its MIME type
Ok(None) => return Err(ScanError::Mime(path)), Ok(None) => return Err(ScanError::Mime(path)),
// a mimetype was found! // a MIME type was found!
Ok(Some(result)) => result, Ok(Some(result)) => result,
}; };
// set of known extensions for the given mimetype // set of known extensions for the given MIME type
let known_exts = mime_extension_lookup(result.essence_str().into()); let known_exts = mime_extension_lookup(result.essence_str().into());
// file extension for this particular file // file extension for this particular file
let entry_ext = path.extension(); let entry_ext = path.extension();
let valid = match known_exts { let valid = match known_exts {
// there is a known set of extensions for this mimetype, and the file has an extension // there is a known set of extensions for this MIME type, and the file has an extension
Some(e) if entry_ext.is_some() => e.contains(&entry_ext.unwrap().to_string_lossy().to_lowercase().into()), Some(e) if entry_ext.is_some() => e.contains(&entry_ext.unwrap().to_string_lossy().to_lowercase().into()),
// either this file has no extension, or there is no known set of extensions for this mimetype :( // either this file has no extension, or there is no known set of extensions for this MIME type :(
Some(_) | None => false, Some(_) | None => false,
}; };
@ -249,7 +249,7 @@ pub fn scan_directory(
} }
} }
/// Tries to identify the mimetype of a file from a given path. /// Tries to identify the MIME type of a file from a given path.
pub fn mime_type<T: MimeDb>(db: &T, path: &Path) -> io::Result<Option<Mime>> { pub fn mime_type<T: MimeDb>(db: &T, path: &Path) -> io::Result<Option<Mime>> {
let mut buffer = [0; INITIAL_BUF_SIZE]; let mut buffer = [0; INITIAL_BUF_SIZE];
let mut file = File::open(path)?; let mut file = File::open(path)?;
@ -278,7 +278,7 @@ pub fn mime_type<T: MimeDb>(db: &T, path: &Path) -> io::Result<Option<Mime>> {
} }
let r = r.filter(|mime| let r = r.filter(|mime|
// some mime types should be investigated further, reading up to BUF_SIZE even if they've been determined already // some MIME types should be investigated further, reading up to BUF_SIZE even if they've been determined already
// one such type is XML - there's many more specific types that can be determined by reading further (such as SVG) // one such type is XML - there's many more specific types that can be determined by reading further (such as SVG)
mime != &mime::TEXT_XML mime != &mime::TEXT_XML
// another is ZIP - many file formats (DOCX, ODT, JAR...) are just ZIP files with particular data structures. // another is ZIP - many file formats (DOCX, ODT, JAR...) are just ZIP files with particular data structures.
@ -301,7 +301,7 @@ pub fn mime_type<T: MimeDb>(db: &T, path: &Path) -> io::Result<Option<Mime>> {
Ok(db.get_type(&buffer)) Ok(db.get_type(&buffer))
} }
/// Returns a list of known extensions for this mime type, if any. /// Returns a list of known extensions for this MIME type, if any.
/// This function uses the [`Mime`]'s "essence" rather than the [`Mime`] itself - [`mime_guess::get_mime_extensions`] /// This function uses the [`Mime`]'s "essence" rather than the [`Mime`] itself - [`mime_guess::get_mime_extensions`]
/// ignores the type suffix, treating "image/svg+xml" as "image/svg", and thus fails to find any extensions. Passing the /// ignores the type suffix, treating "image/svg+xml" as "image/svg", and thus fails to find any extensions. Passing the
/// `essence_str` (which includes the suffix) fixes this. /// `essence_str` (which includes the suffix) fixes this.
@ -358,7 +358,7 @@ pub fn mime_extension_lookup(essence: String) -> Option<Vec<String>> {
] ]
.concat() .concat()
} else if essence == "application/x-ms-dos-executable" { } else if essence == "application/x-ms-dos-executable" {
// .dll, .exe, and .scr files are given the same mime type... but you definitely don't want to rename one to the // .dll, .exe, and .scr files are given the same MIME type... but you definitely don't want to rename one to the
// other! // other!
[vec![String::from("dll"), String::from("exe"), String::from("scr")], possible_exts].concat() [vec![String::from("dll"), String::from("exe"), String::from("scr")], possible_exts].concat()
} else { } else {

View File

@ -20,9 +20,9 @@ use crate::String;
pub struct Findings { pub struct Findings {
/// The location of the scanned file. /// The location of the scanned file.
pub file: PathBuf, pub file: PathBuf,
/// Whether or not the file's extension is valid for its mimetype. /// Whether or not the file's extension is valid for its MIME type.
pub valid: bool, pub valid: bool,
/// The file's mimetype. /// The file's MIME type.
pub mime: Mime, pub mime: Mime,
} }
@ -79,7 +79,7 @@ impl serde::Serialize for Findings {
pub enum ScanError<'a> { pub enum ScanError<'a> {
/// Something went wrong while trying to read the given file. /// Something went wrong while trying to read the given file.
File(&'a Path), File(&'a Path),
/// Failed to determine the mimetype of the given file. /// Failed to determine the MIME type of the given file.
Mime(&'a Path), Mime(&'a Path),
} }
@ -90,7 +90,7 @@ impl<'a> Display for ScanError<'a> {
"Couldn't {} file: {}", "Couldn't {} file: {}",
match self { match self {
Self::File(_) => "read", Self::File(_) => "read",
Self::Mime(_) => "determine mime type of", Self::Mime(_) => "determine MIME type of",
}, },
match self { match self {
Self::File(f) | Self::Mime(f) => f.to_string_lossy(), Self::File(f) | Self::Mime(f) => f.to_string_lossy(),

View File

@ -136,7 +136,7 @@ pub trait FormatSteps {
match error { match error {
// failed to read the file // failed to read the file
ScanError::File(path) => self.unreadable(f, path)?, ScanError::File(path) => self.unreadable(f, path)?,
// file was read successfully, but we couldn't determine a mimetype // file was read successfully, but we couldn't determine a MIME type
ScanError::Mime(path) => self.unknown_type(f, path)?, ScanError::Mime(path) => self.unknown_type(f, path)?,
} }
} }
@ -188,7 +188,7 @@ impl FormatSteps for Shell {
} }
fn unknown_type<W: Write>(&self, f: &mut W, path: &Path) -> io::Result<()> { fn unknown_type<W: Write>(&self, f: &mut W, path: &Path) -> io::Result<()> {
smart_write(f, writablesln!["# Failed to detect mime type for ", path]) smart_write(f, writablesln!["# Failed to detect MIME type for ", path])
} }
fn header<W: Write>(&self, f: &mut W) -> io::Result<()> { fn header<W: Write>(&self, f: &mut W) -> io::Result<()> {
@ -241,7 +241,7 @@ impl FormatSteps for PowerShell {
} }
fn unknown_type<W: Write>(&self, f: &mut W, path: &Path) -> io::Result<()> { fn unknown_type<W: Write>(&self, f: &mut W, path: &Path) -> io::Result<()> {
smart_write(f, writablesln!["<# Failed to detect mime type for ", path, " #>"]) smart_write(f, writablesln!["<# Failed to detect MIME type for ", path, " #>"])
} }
fn header<W: Write>(&self, f: &mut W) -> io::Result<()> { fn header<W: Write>(&self, f: &mut W) -> io::Result<()> {

View File

@ -18,7 +18,7 @@ use mime::Mime;
pub trait MimeDb { pub trait MimeDb {
/// Initialise the database. /// Initialise the database.
fn init() -> Self; fn init() -> Self;
/// Given a slice of bytes, returns the inferred mimetype, if any. /// Given a slice of bytes, returns the inferred MIME type, if any.
fn get_type(&self, data: &[u8]) -> Option<Mime>; fn get_type(&self, data: &[u8]) -> Option<Mime>;
} }

View File

@ -43,7 +43,7 @@ fn get_ext() {
} }
#[test] #[test]
/// Ensure that the mime types for JPEG, PNG, PDF, and ZIP are detected from their magic numbers. /// Ensure that the MIME types for JPEG, PNG, PDF, and ZIP are detected from their magic numbers.
fn detect_type() { fn detect_type() {
assert_eq!(MIMEDB.get_type(JPEG_BYTES), Some(IMAGE_JPEG)); assert_eq!(MIMEDB.get_type(JPEG_BYTES), Some(IMAGE_JPEG));
assert_eq!(MIMEDB.get_type(PNG_BYTES), Some(IMAGE_PNG)); assert_eq!(MIMEDB.get_type(PNG_BYTES), Some(IMAGE_PNG));
@ -71,7 +71,7 @@ fn recommend_ext() {
#[test] #[test]
/// Create a simple directory with some files, run `scan_directory` on it, and ensure that the files have their /// Create a simple directory with some files, run `scan_directory` on it, and ensure that the files have their
/// associated mime types correctly deduced. /// associated MIME types correctly deduced.
fn simple_directory() { fn simple_directory() {
use std::borrow::Borrow; use std::borrow::Borrow;
use std::env::set_current_dir; use std::env::set_current_dir;
@ -136,7 +136,7 @@ fn simple_directory() {
// the only invalid file detected should be "wrong.jpg", which is a misnamed png file // the only invalid file detected should be "wrong.jpg", which is a misnamed png file
// 1. ensure detected extension is "jpg" // 1. ensure detected extension is "jpg"
assert_eq!(result.file.as_path().extension().unwrap(), OsStr::new("jpg")); assert_eq!(result.file.as_path().extension().unwrap(), OsStr::new("jpg"));
// 2. ensure detected mime type is IMAGE_PNG // 2. ensure detected MIME type is IMAGE_PNG
assert_eq!(result.mime, IMAGE_PNG); assert_eq!(result.mime, IMAGE_PNG);
// 3. ensure the recommended extension for "wrong.jpg" is "png" // 3. ensure the recommended extension for "wrong.jpg" is "png"
assert_eq!(&result.recommended_extension().unwrap(), &String::from("png")); assert_eq!(&result.recommended_extension().unwrap(), &String::from("png"));
@ -145,7 +145,7 @@ fn simple_directory() {
continue; continue;
} }
// check if the recommended extension for this file is in the list of known extensions for its mimetype - for // check if the recommended extension for this file is in the list of known extensions for its MIME type - for
// example, if the file is determined to be an IMAGE_PNG, its recommended extension should be one of the extensions // example, if the file is determined to be an IMAGE_PNG, its recommended extension should be one of the extensions
// returned by `mime_extension_lookup(IMAGE_PNG)`. // returned by `mime_extension_lookup(IMAGE_PNG)`.
assert!(mime_extension_lookup(result.mime.essence_str().into()) assert!(mime_extension_lookup(result.mime.essence_str().into())
@ -161,8 +161,8 @@ fn simple_directory() {
.to_string_lossy() .to_string_lossy()
.starts_with("test")); .starts_with("test"));
// make sure the guessed mimetype is correct based on the extension of the scanned file // make sure the guessed MIME type is correct based on the extension of the scanned file
// because we already know that the extensions match the mimetype (as we created these files ourselves earlier in // because we already know that the extensions match the MIME type (as we created these files ourselves earlier in
// the test), all files with the "jpg" extension should be IMAGE_JPEGs, etc. // the test), all files with the "jpg" extension should be IMAGE_JPEGs, etc.
let ext = result.file.as_path().extension().unwrap(); let ext = result.file.as_path().extension().unwrap();
assert_eq!( assert_eq!(
@ -400,7 +400,7 @@ fn test_json() {
.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 the file's MIME type
assert!( assert!(
contents.contains(IMAGE_JPEG.essence_str()), contents.contains(IMAGE_JPEG.essence_str()),
"JSON output doesn't contain move command!\n===\n{}", "JSON output doesn't contain move command!\n===\n{}",

View File

@ -39,7 +39,7 @@ pub static CLAP_LONG_VERSION: Lazy<String> = Lazy::new(|| {
.into() .into()
}); });
/// A [`Mime`] representing the "application/zip" mimetype. /// A [`Mime`] representing the "application/zip" MIME type.
pub static APPLICATION_ZIP: Lazy<Mime> = Lazy::new(|| Mime::from_str("application/zip").unwrap()); pub static APPLICATION_ZIP: Lazy<Mime> = Lazy::new(|| Mime::from_str("application/zip").unwrap());
/// Returns the name of the target operating system with proper casing, like "Windows" or "macOS". /// Returns the name of the target operating system with proper casing, like "Windows" or "macOS".