From 12d9001bb82d6914f64fe333c8a009f8891dfbcf Mon Sep 17 00:00:00 2001
From: Lynnesbian <lynne@bune.city>
Date: Sun, 4 Apr 2021 22:42:34 +1000
Subject: [PATCH] better mime type detection

- consider some/x-thing and some/thing to be identical
- use a patched version of mime_guess with many more extension/type mappings
---
 CHANGELOG.md      |  3 +++
 Cargo.lock        | 21 ++++++++++-----------
 Cargo.toml        |  2 ++
 src/inspectors.rs | 19 ++++++++++++++++++-
 4 files changed, 33 insertions(+), 12 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index e40a80c..590cf0e 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,9 @@ Dates are given in YYYY-MM-DD format.
   [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
+- 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
 
 ### v0.2.10 (2021-03-26)
 - PowerShell support!
diff --git a/Cargo.lock b/Cargo.lock
index a4bbaa6..d18d079 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -284,9 +284,9 @@ dependencies = [
 
 [[package]]
 name = "libc"
-version = "0.2.91"
+version = "0.2.92"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8916b1f6ca17130ec6568feccee27c156ad12037880833a3b842a823236502e7"
+checksum = "56d855069fafbb9b344c0f962150cd2c1187975cb1c22c1522c240d8c4986714"
 
 [[package]]
 name = "log"
@@ -305,9 +305,9 @@ checksum = "0ee1c47aaa256ecabcaea351eae4a9b01ef39ed810004e298d2511ed284b1525"
 
 [[package]]
 name = "memoffset"
-version = "0.6.1"
+version = "0.6.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "157b4208e3059a8f9e78d559edc658e13df41410cb3ae03979c83130067fdd87"
+checksum = "f83fb6581e8ed1f85fd45c116db8405483899489e38406156c25eb743554361d"
 dependencies = [
  "autocfg",
 ]
@@ -320,9 +320,8 @@ checksum = "2a60c7ce501c71e03a9c9c0d35b861413ae925bd979cc7a4e30d060069aaac8d"
 
 [[package]]
 name = "mime_guess"
-version = "2.0.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2684d4c2e97d99848d30b324b00c8fcc7e5c897b7cbb5819b09e7c90e8baf212"
+version = "2.0.4"
+source = "git+https://github.com/Lynnesbian/mime_guess#679d3b8887d30bd43a83f162d61b7226675c7012"
 dependencies = [
  "mime",
  "unicase",
@@ -393,9 +392,9 @@ dependencies = [
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.24"
+version = "1.0.26"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1e0704ee1a7e00d7bb417d0770ea303c1bccbabf0ef1667dae92b5967f5f8a71"
+checksum = "a152013215dca273577e18d2bf00fa862b89b24169fb78c4c95aeb07992c9cec"
 dependencies = [
  "unicode-xid",
 ]
@@ -550,9 +549,9 @@ checksum = "a2eb9349b6444b326872e140eb1cf5e7c522154d69e7a0ffb0fb81c06b37543f"
 
 [[package]]
 name = "syn"
-version = "1.0.64"
+version = "1.0.68"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3fd9d1e9976102a03c542daa2eff1b43f9d72306342f3f8b3ed5fb8908195d6f"
+checksum = "3ce15dd3ed8aa2f8eeac4716d6ef5ab58b6b9256db41d7e1a0224c2788e8fd87"
 dependencies = [
  "proc-macro2",
  "quote",
diff --git a/Cargo.toml b/Cargo.toml
index 1970fcc..8e17f49 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -43,6 +43,8 @@ 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"}
 
 [dependencies.clap]
 version = "3.0.0-beta.2"
diff --git a/src/inspectors.rs b/src/inspectors.rs
index a3067f5..980589c 100644
--- a/src/inspectors.rs
+++ b/src/inspectors.rs
@@ -72,7 +72,24 @@ cached! {
 		// match on the mime's `essence_str` 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 essence_str
 		// (which includes the suffix) fixes this.
-		match mime_guess::get_mime_extensions_str(mime.essence_str()) {
+		let essence = mime.essence_str();
+		let mut exts = mime_guess::get_mime_extensions_str(essence);
+		if exts.is_none() {
+			// no matches :c
+			// mime_guess' database isn't exactly perfect... there are a lot of times where the db will return "some/x-thing"
+			// but mime_guess only understands "some/thing", or vice-versa.
+			// so, if there appear to be no extensions, try replacing "some/x-thing" with "some/thing", or "some/thing" with
+			// "some/x-thing".
+			if essence.contains("/x-") {
+				// replace e.g. "application/x-gzip" with "application/gzip"
+				exts = mime_guess::get_mime_extensions_str(&essence.replace("/x-", "/"));
+			} else {
+				// replace e.g. "video/mp2t" with "video/x-mp2t"
+				exts = mime_guess::get_mime_extensions_str(&essence.replace("/", "/x-"));
+			}
+		}
+
+		match exts {
 			Some(exts) => {
 				let possible_exts: Vec<String> = exts.iter().map(|e| String::from(*e)).collect();