Mercurial > public > mercurial-scm > hg

diff rust/hg-core/src/revlog/index.rs @ 51202:002b49905aac

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
rust-index: implementation of __getitem__ Although the removed panic tends to prove if the full test suite did pass that the case when the input is a node id does not happen, it is best not to remove it right now. Raising IndexError is crucial for iteration on the index to stop, given the default CPython sequence iterator, see for instance https://github.com/zpoint/CPython-Internals/blobs/master/BasicObject/iter/iter.md This was spotted by `test-rust-ancestors.py`, which does simple interations on indexes (as preflight checks). In `revlog.c`, `index_getitem` defaults to `index_get` when called on revision numbers, which does raise `IndexError` with the same message as the one we are introducing here.
author Rapha?l Gom?s <rgomes@octobus.net>
date Thu, 02 Nov 2023 11:19:54 +0100
parents 7434747343ab
children e9d47e2f5dcf
line wrap: on
line diff
--- a/rust/hg-core/src/revlog/index.rs	Wed Sep 27 11:34:52 2023 +0200
+++ b/rust/hg-core/src/revlog/index.rs	Thu Nov 02 11:19:54 2023 +0100
@@ -123,6 +123,10 @@
         }
         Ok(())
     }
+
+    fn is_new(&self) -> bool {
+        self.bytes.is_empty()
+    }
 }
 
 impl std::ops::Index<std::ops::Range<usize>> for IndexData {
@@ -146,6 +150,7 @@
     }
 }
 
+#[derive(Debug, PartialEq, Eq)]
 pub struct RevisionDataParams {
     pub flags: u16,
     pub data_offset: u64,
@@ -163,6 +168,27 @@
     pub _rank: i32,
 }
 
+impl Default for RevisionDataParams {
+    fn default() -> Self {
+        Self {
+            flags: 0,
+            data_offset: 0,
+            data_compressed_length: 0,
+            data_uncompressed_length: 0,
+            data_delta_base: -1,
+            link_rev: -1,
+            parent_rev_1: -1,
+            parent_rev_2: -1,
+            node_id: [0; NODE_BYTES_LENGTH],
+            _sidedata_offset: 0,
+            _sidedata_compressed_length: 0,
+            data_compression_mode: COMPRESSION_MODE_INLINE,
+            _sidedata_compression_mode: COMPRESSION_MODE_INLINE,
+            _rank: -1,
+        }
+    }
+}
+
 #[derive(BytesCast)]
 #[repr(C)]
 pub struct RevisionDataV1 {
@@ -397,6 +423,29 @@
         })
     }
 
+    pub fn entry_as_params(
+        &self,
+        rev: UncheckedRevision,
+    ) -> Option<RevisionDataParams> {
+        let rev = self.check_revision(rev)?;
+        self.get_entry(rev).map(|e| RevisionDataParams {
+            flags: e.flags(),
+            data_offset: if rev.0 == 0 && !self.bytes.is_new() {
+                e.flags() as u64
+            } else {
+                e.raw_offset()
+            },
+            data_compressed_length: e.compressed_len().try_into().unwrap(),
+            data_uncompressed_length: e.uncompressed_len(),
+            data_delta_base: e.base_revision_or_base_of_delta_chain().0,
+            link_rev: e.link_revision().0,
+            parent_rev_1: e.p1().0,
+            parent_rev_2: e.p2().0,
+            node_id: e.hash().as_bytes().try_into().unwrap(),
+            ..Default::default()
+        })
+    }
+
     fn get_entry_inline(
         &self,
         rev: Revision,
@@ -519,6 +568,9 @@
             BigEndian::read_u64(&bytes[..]) as usize
         }
     }
+    pub fn raw_offset(&self) -> u64 {
+        BigEndian::read_u64(&self.bytes[0..8])
+    }
 
     pub fn flags(&self) -> u16 {
         BigEndian::read_u16(&self.bytes[6..=7])