Merge pull request #1505 from sdroege/unicollate-non-utf8

glib: Collation keys are not necessary valid UTF-8
gtk-rs · Sep 9, 2024 · d34db6b · d34db6b
2 parents d3aa5fc + 8c44ec1
commit d34db6b
Show file tree

Hide file tree

Showing 2 changed files with 174 additions and 11 deletions.
diff --git a/glib/src/unicollate.rs b/glib/src/unicollate.rs
@@ -1,11 +1,11 @@
 // Take a look at the license at the top of the repository in the LICENSE file.
 
-use crate::{ffi, translate::*};
+use crate::ffi;
 
 // rustdoc-stripper-ignore-next
 /// A `CollationKey` allows ordering strings using the linguistically correct rules for the current locale.
 #[derive(Clone, Debug, PartialEq, Eq, PartialOrd, Ord)]
-pub struct CollationKey(crate::GString);
+pub struct CollationKey(crate::Slice<u8>);
 
 impl<T: AsRef<str>> From<T> for CollationKey {
     // rustdoc-stripper-ignore-next
@@ -15,10 +15,10 @@ impl<T: AsRef<str>> From<T> for CollationKey {
     fn from(s: T) -> Self {
         let s = s.as_ref();
         let key = unsafe {
-            from_glib_full(ffi::g_utf8_collate_key(
-                s.as_ptr() as *const _,
-                s.len() as isize,
-            ))
+            let ptr = ffi::g_utf8_collate_key(s.as_ptr() as *const _, s.len() as isize);
+            let len = libc::strlen(ptr);
+
+            crate::Slice::from_glib_full_num(ptr as *mut u8, len)
         };
         Self(key)
     }
@@ -29,7 +29,7 @@ impl<T: AsRef<str>> From<T> for CollationKey {
 /// Compared to `CollationKey`, filename collation keys take into consideration dots and other characters
 /// commonly found in file names.
 #[derive(Clone, Debug, PartialEq, Eq, PartialOrd, Ord)]
-pub struct FilenameCollationKey(crate::GString);
+pub struct FilenameCollationKey(crate::Slice<u8>);
 
 impl<T: AsRef<str>> From<T> for FilenameCollationKey {
     // rustdoc-stripper-ignore-next
@@ -39,10 +39,11 @@ impl<T: AsRef<str>> From<T> for FilenameCollationKey {
     fn from(s: T) -> Self {
         let s = s.as_ref();
         let key = unsafe {
-            from_glib_full(ffi::g_utf8_collate_key_for_filename(
-                s.as_ptr() as *const _,
-                s.len() as isize,
-            ))
+            let ptr =
+                ffi::g_utf8_collate_key_for_filename(s.as_ptr() as *const _, s.len() as isize);
+            let len = libc::strlen(ptr);
+
+            crate::Slice::from_glib_full_num(ptr as *mut u8, len)
         };
         Self(key)
     }
@@ -71,6 +72,25 @@ mod tests {
         assert_eq!(unsorted, sorted);
     }
 
+    #[test]
+    fn collate_non_ascii() {
+        let mut unsorted = vec![
+            String::from("猫の手も借りたい"),
+            String::from("日本語は難しい"),
+            String::from("ありがとう"),
+        ];
+
+        let sorted = vec![
+            String::from("ありがとう"),
+            String::from("日本語は難しい"),
+            String::from("猫の手も借りたい"),
+        ];
+
+        unsorted.sort_by(|s1, s2| CollationKey::from(&s1).cmp(&CollationKey::from(&s2)));
+
+        assert_eq!(unsorted, sorted);
+    }
+
     #[test]
     fn collate_filenames() {
         let mut unsorted = vec![
@@ -91,4 +111,49 @@ mod tests {
 
         assert_eq!(unsorted, sorted);
     }
+
+    #[test]
+    fn collate_filenames_non_ascii() {
+        let mut unsorted = vec![
+            String::from("猫の手も借りたい.foo"),
+            String::from("日本語は難しい.bar"),
+            String::from("ありがとう.baz"),
+        ];
+
+        let sorted = vec![
+            String::from("ありがとう.baz"),
+            String::from("日本語は難しい.bar"),
+            String::from("猫の手も借りたい.foo"),
+        ];
+
+        unsorted.sort_by(|s1, s2| {
+            FilenameCollationKey::from(&s1).cmp(&FilenameCollationKey::from(&s2))
+        });
+
+        assert_eq!(unsorted, sorted);
+    }
+
+    #[test]
+    fn collate_filenames_from_path() {
+        use std::path::PathBuf;
+
+        let mut unsorted = vec![
+            PathBuf::from("猫の手も借りたい.foo"),
+            PathBuf::from("日本語は難しい.bar"),
+            PathBuf::from("ありがとう.baz"),
+        ];
+
+        let sorted = vec![
+            PathBuf::from("ありがとう.baz"),
+            PathBuf::from("日本語は難しい.bar"),
+            PathBuf::from("猫の手も借りたい.foo"),
+        ];
+
+        unsorted.sort_by(|s1, s2| {
+            FilenameCollationKey::from(&s1.to_string_lossy())
+                .cmp(&FilenameCollationKey::from(&s2.to_string_lossy()))
+        });
+
+        assert_eq!(unsorted, sorted);
+    }
 }
diff --git a/glib/tests/unicollate.rs b/glib/tests/unicollate.rs
@@ -0,0 +1,98 @@
+use glib::{CollationKey, FilenameCollationKey};
+
+fn init() {
+    use std::sync::Once;
+    static ONCE: Once = Once::new();
+
+    // Make sure that all tests below are running with the system
+    // locale and not the "C" locale.
+    ONCE.call_once(|| unsafe {
+        libc::setlocale(libc::LC_ALL, b"\0".as_ptr() as *const _);
+    });
+}
+
+#[test]
+fn collate() {
+    init();
+
+    let mut unsorted = vec![
+        String::from("bcd"),
+        String::from("cde"),
+        String::from("abc"),
+    ];
+
+    let sorted = vec![
+        String::from("abc"),
+        String::from("bcd"),
+        String::from("cde"),
+    ];
+
+    unsorted.sort_by(|s1, s2| CollationKey::from(&s1).cmp(&CollationKey::from(&s2)));
+
+    assert_eq!(unsorted, sorted);
+}
+
+#[test]
+fn collate_non_ascii() {
+    init();
+
+    let mut unsorted = vec![
+        String::from("猫の手も借りたい"),
+        String::from("日本語は難しい"),
+        String::from("ありがとう"),
+    ];
+
+    let sorted = vec![
+        String::from("ありがとう"),
+        String::from("日本語は難しい"),
+        String::from("猫の手も借りたい"),
+    ];
+
+    unsorted.sort_by(|s1, s2| CollationKey::from(&s1).cmp(&CollationKey::from(&s2)));
+
+    assert_eq!(unsorted, sorted);
+}
+
+#[test]
+fn collate_filenames() {
+    init();
+
+    let mut unsorted = vec![
+        String::from("bcd.a"),
+        String::from("cde.b"),
+        String::from("abc.c"),
+    ];
+
+    let sorted = vec![
+        String::from("abc.c"),
+        String::from("bcd.a"),
+        String::from("cde.b"),
+    ];
+
+    unsorted
+        .sort_by(|s1, s2| FilenameCollationKey::from(&s1).cmp(&FilenameCollationKey::from(&s2)));
+
+    assert_eq!(unsorted, sorted);
+}
+
+#[test]
+fn collate_filenames_non_ascii() {
+    init();
+
+    let mut unsorted = vec![
+        String::from("猫の手も借りたい.foo"),
+        String::from("日本語は難しい.bar"),
+        String::from("ありがとう.baz"),
+    ];
+
+    let sorted = vec![
+        String::from("ありがとう.baz"),
+        String::from("日本語は難しい.bar"),
+        String::from("猫の手も借りたい.foo"),
+    ];
+
+    unsorted
+        .sort_by(|s1, s2| FilenameCollationKey::from(&s1).cmp(&FilenameCollationKey::from(&s2)));
+
+    assert_eq!(unsorted, sorted);
+}