changeset 42850:b1b984f9c01d

rust-utils: add normalize_case util to mirror Python one

While we still don't handle filenames properly cross-platform, this at least
sticks closer to the Python behavior.

Differential Revision: https://phab.mercurial-scm.org/D6756

--- a/rust/hg-core/src/dirstate/dirstate_map.rs	Wed Aug 28 08:16:58 2019 -0400
+++ b/rust/hg-core/src/dirstate/dirstate_map.rs	Thu Aug 22 14:31:07 2019 +0200
@@ -7,9 +7,10 @@
 
 use crate::{
     dirstate::{parsers::PARENT_SIZE, EntryState},
-    pack_dirstate, parse_dirstate, CopyMap, DirsMultiset, DirstateEntry,
-    DirstateError, DirstateMapError, DirstateParents, DirstateParseError,
-    StateMap,
+    pack_dirstate, parse_dirstate,
+    utils::files::normalize_case,
+    CopyMap, DirsMultiset, DirstateEntry, DirstateError, DirstateMapError,
+    DirstateParents, DirstateParseError, StateMap,
 };
 use core::borrow::Borrow;
 use std::collections::{HashMap, HashSet};
@@ -127,7 +128,7 @@
         }
 
         if let Some(ref mut file_fold_map) = self.file_fold_map {
-            file_fold_map.remove(&filename.to_ascii_uppercase());
+            file_fold_map.remove(&normalize_case(filename));
         }
         self.state_map.insert(
             filename.to_owned(),
@@ -162,7 +163,7 @@
             }
         }
         if let Some(ref mut file_fold_map) = self.file_fold_map {
-            file_fold_map.remove(&filename.to_ascii_uppercase());
+            file_fold_map.remove(&normalize_case(filename));
         }
         self.non_normal_set.remove(filename);
 
@@ -326,10 +327,8 @@
         for (filename, DirstateEntry { state, .. }) in self.state_map.borrow()
         {
             if *state == EntryState::Removed {
-                new_file_fold_map.insert(
-                    filename.to_ascii_uppercase().to_owned(),
-                    filename.to_owned(),
-                );
+                new_file_fold_map
+                    .insert(normalize_case(filename), filename.to_owned());
             }
         }
         self.file_fold_map = Some(new_file_fold_map);

--- a/rust/hg-core/src/utils/files.rs	Wed Aug 28 08:16:58 2019 -0400
+++ b/rust/hg-core/src/utils/files.rs	Thu Aug 22 14:31:07 2019 +0200
@@ -71,6 +71,15 @@
     dirs
 }
 
+/// TODO improve handling of utf8 file names. Our overall strategy for
+/// filenames has to be revisited anyway, since Windows is UTF-16.
+pub fn normalize_case(bytes: &[u8]) -> Vec<u8> {
+    #[cfg(windows)] // NTFS compares via upper()
+    return bytes.to_ascii_uppercase();
+    #[cfg(unix)]
+    bytes.to_ascii_lowercase()
+}
+
 #[cfg(test)]
 mod tests {
     #[test]