dirstate-tree: Remove newly-empty nodes after removing a `DirstateEntry`

This is actually necessary to make `DirstateMap::has_dir` correct, since it
assumes that a node without a `DirstateEntry` has at least one descedant node
with a `DirstateEntry`.

This bug would become apparent when a later changeset persists tree nodes
on disk in the "dirstate-v2" format.

Differential Revision: https://phab.mercurial-scm.org/D10706

rust/hg-core/src/dirstate_tree/dirstate_map.rs

@@ -1,622 +1,627
 use bytes_cast::BytesCast;
 use micro_timer::timed;
 use std::borrow::Cow;
 use std::convert::TryInto;
 use std::path::PathBuf;
 
 use super::path_with_basename::WithBasename;
 use crate::dirstate::parsers::clear_ambiguous_mtime;
 use crate::dirstate::parsers::pack_entry;
 use crate::dirstate::parsers::packed_entry_size;
 use crate::dirstate::parsers::parse_dirstate_entries;
 use crate::dirstate::parsers::Timestamp;
 use crate::matchers::Matcher;
 use crate::utils::hg_path::{HgPath, HgPathBuf};
 use crate::CopyMapIter;
 use crate::DirstateEntry;
 use crate::DirstateError;
 use crate::DirstateMapError;
 use crate::DirstateParents;
 use crate::DirstateStatus;
 use crate::EntryState;
 use crate::FastHashMap;
 use crate::PatternFileWarning;
 use crate::StateMapIter;
 use crate::StatusError;
 use crate::StatusOptions;
 
 pub struct DirstateMap<'on_disk> {
     /// Contents of the `.hg/dirstate` file
     on_disk: &'on_disk [u8],
 
     pub(super) root: ChildNodes<'on_disk>,
 
     /// Number of nodes anywhere in the tree that have `.entry.is_some()`.
     nodes_with_entry_count: usize,
 
     /// Number of nodes anywhere in the tree that have
     /// `.copy_source.is_some()`.
     nodes_with_copy_source_count: usize,
 }
 
 /// Using a plain `HgPathBuf` of the full path from the repository root as a
 /// map key would also work: all paths in a given map have the same parent
 /// path, so comparing full paths gives the same result as comparing base
 /// names. However `BTreeMap` would waste time always re-comparing the same
 /// string prefix.
 pub(super) type ChildNodes<'on_disk> =
     FastHashMap<WithBasename<Cow<'on_disk, HgPath>>, Node<'on_disk>>;
 
 /// Represents a file or a directory
 #[derive(Default)]
 pub(super) struct Node<'on_disk> {
     /// `None` for directories
     pub(super) entry: Option<DirstateEntry>,
 
     pub(super) copy_source: Option<Cow<'on_disk, HgPath>>,
 
     pub(super) children: ChildNodes<'on_disk>,
 
     /// How many (non-inclusive) descendants of this node are tracked files
     tracked_descendants_count: usize,
 }
 
 impl Node<'_> {
     pub(super) fn state(&self) -> Option<EntryState> {
         self.entry.as_ref().map(|entry| entry.state)
     }
 }
 
 /// `(full_path, entry, copy_source)`
 type NodeDataMut<'tree, 'on_disk> = (
     &'tree HgPath,
     &'tree mut Option<DirstateEntry>,
     &'tree mut Option<Cow<'on_disk, HgPath>>,
 );
 
 impl<'on_disk> DirstateMap<'on_disk> {
     pub fn new(
         on_disk: &'on_disk [u8],
     ) -> Result<(Self, Option<DirstateParents>), DirstateError> {
         let mut map = Self {
             on_disk,
             root: ChildNodes::default(),
             nodes_with_entry_count: 0,
             nodes_with_copy_source_count: 0,
         };
         let parents = map.read()?;
         Ok((map, parents))
     }
 
     /// Should only be called in `new`
     #[timed]
     fn read(&mut self) -> Result<Option<DirstateParents>, DirstateError> {
         if self.on_disk.is_empty() {
             return Ok(None);
         }
 
         let parents = parse_dirstate_entries(
             self.on_disk,
             |path, entry, copy_source| {
                 let tracked = entry.state.is_tracked();
                 let node = Self::get_or_insert_node(
                     &mut self.root,
                     path,
                     WithBasename::to_cow_borrowed,
                     |ancestor| {
                         if tracked {
                             ancestor.tracked_descendants_count += 1
                         }
                     },
                 );
                 assert!(
                     node.entry.is_none(),
                     "duplicate dirstate entry in read"
                 );
                 assert!(
                     node.copy_source.is_none(),
                     "duplicate dirstate entry in read"
                 );
                 node.entry = Some(*entry);
                 node.copy_source = copy_source.map(Cow::Borrowed);
                 self.nodes_with_entry_count += 1;
                 if copy_source.is_some() {
                     self.nodes_with_copy_source_count += 1
                 }
             },
         )?;
 
         Ok(Some(parents.clone()))
     }
 
     fn get_node(&self, path: &HgPath) -> Option<&Node> {
         let mut children = &self.root;
         let mut components = path.components();
         let mut component =
             components.next().expect("expected at least one components");
         loop {
             let child = children.get(component)?;
             if let Some(next_component) = components.next() {
                 component = next_component;
                 children = &child.children;
             } else {
                 return Some(child);
             }
         }
     }
 
     /// Returns a mutable reference to the node at `path` if it exists
     ///
     /// This takes `root` instead of `&mut self` so that callers can mutate
     /// other fields while the returned borrow is still valid
     fn get_node_mut<'tree>(
         root: &'tree mut ChildNodes<'on_disk>,
         path: &HgPath,
     ) -> Option<&'tree mut Node<'on_disk>> {
         let mut children = root;
         let mut components = path.components();
         let mut component =
             components.next().expect("expected at least one components");
         loop {
             let child = children.get_mut(component)?;
             if let Some(next_component) = components.next() {
                 component = next_component;
                 children = &mut child.children;
             } else {
                 return Some(child);
             }
         }
     }
 
     fn get_or_insert_node<'tree, 'path>(
         root: &'tree mut ChildNodes<'on_disk>,
         path: &'path HgPath,
         to_cow: impl Fn(
             WithBasename<&'path HgPath>,
         ) -> WithBasename<Cow<'on_disk, HgPath>>,
         mut each_ancestor: impl FnMut(&mut Node),
     ) -> &'tree mut Node<'on_disk> {
         let mut child_nodes = root;
         let mut inclusive_ancestor_paths =
             WithBasename::inclusive_ancestors_of(path);
         let mut ancestor_path = inclusive_ancestor_paths
             .next()
             .expect("expected at least one inclusive ancestor");
         loop {
             // TODO: can we avoid allocating an owned key in cases where the
             // map already contains that key, without introducing double
             // lookup?
             let child_node =
                 child_nodes.entry(to_cow(ancestor_path)).or_default();
             if let Some(next) = inclusive_ancestor_paths.next() {
                 each_ancestor(child_node);
                 ancestor_path = next;
                 child_nodes = &mut child_node.children;
             } else {
                 return child_node;
             }
         }
     }
 
     fn add_or_remove_file(
         &mut self,
         path: &HgPath,
         old_state: EntryState,
         new_entry: DirstateEntry,
     ) {
         let tracked_count_increment =
             match (old_state.is_tracked(), new_entry.state.is_tracked()) {
                 (false, true) => 1,
                 (true, false) => -1,
                 _ => 0,
             };
 
         let node = Self::get_or_insert_node(
             &mut self.root,
             path,
             WithBasename::to_cow_owned,
             |ancestor| {
                 // We can’t use `+= increment` because the counter is unsigned,
                 // and we want debug builds to detect accidental underflow
                 // through zero
                 match tracked_count_increment {
                     1 => ancestor.tracked_descendants_count += 1,
                     -1 => ancestor.tracked_descendants_count -= 1,
                     _ => {}
                 }
             },
         );
         if node.entry.is_none() {
             self.nodes_with_entry_count += 1
         }
         node.entry = Some(new_entry)
     }
 
     fn iter_nodes<'a>(
         &'a self,
     ) -> impl Iterator<Item = (&'a HgPath, &'a Node)> + 'a {
         // Depth first tree traversal.
         //
         // If we could afford internal iteration and recursion,
         // this would look like:
         //
         // ```
         // fn traverse_children(
         //     children: &ChildNodes,
         //     each: &mut impl FnMut(&Node),
         // ) {
         //     for child in children.values() {
         //         traverse_children(&child.children, each);
         //         each(child);
         //     }
         // }
         // ```
         //
         // However we want an external iterator and therefore can’t use the
         // call stack. Use an explicit stack instead:
         let mut stack = Vec::new();
         let mut iter = self.root.iter();
         std::iter::from_fn(move || {
             while let Some((key, child_node)) = iter.next() {
                 // Pseudo-recursion
                 let new_iter = child_node.children.iter();
                 let old_iter = std::mem::replace(&mut iter, new_iter);
                 let key = &**key.full_path();
                 stack.push((key, child_node, old_iter));
             }
             // Found the end of a `children.iter()` iterator.
             if let Some((key, child_node, next_iter)) = stack.pop() {
                 // "Return" from pseudo-recursion by restoring state from the
                 // explicit stack
                 iter = next_iter;
 
                 Some((key, child_node))
             } else {
                 // Reached the bottom of the stack, we’re done
                 None
             }
         })
     }
 
     /// Mutable iterator for the `(entry, copy source)` of each node.
     ///
     /// It would not be safe to yield mutable references to nodes themeselves
     /// with `-> impl Iterator<Item = &mut Node>` since child nodes are
     /// reachable from their ancestor nodes, potentially creating multiple
     /// `&mut` references to a given node.
     fn iter_node_data_mut<'tree>(
         &'tree mut self,
     ) -> impl Iterator<Item = NodeDataMut<'tree, 'on_disk>> + 'tree {
         // Explict stack for pseudo-recursion, see `iter_nodes` above.
         let mut stack = Vec::new();
         let mut iter = self.root.iter_mut();
         std::iter::from_fn(move || {
             while let Some((key, child_node)) = iter.next() {
                 // Pseudo-recursion
                 let data = (
                     &**key.full_path(),
                     &mut child_node.entry,
                     &mut child_node.copy_source,
                 );
                 let new_iter = child_node.children.iter_mut();
                 let old_iter = std::mem::replace(&mut iter, new_iter);
                 stack.push((data, old_iter));
             }
             // Found the end of a `children.values_mut()` iterator.
             if let Some((data, next_iter)) = stack.pop() {
                 // "Return" from pseudo-recursion by restoring state from the
                 // explicit stack
                 iter = next_iter;
 
                 Some(data)
             } else {
                 // Reached the bottom of the stack, we’re done
                 None
             }
         })
     }
 }
 
 impl<'on_disk> super::dispatch::DirstateMapMethods for DirstateMap<'on_disk> {
     fn clear(&mut self) {
         self.root.clear();
         self.nodes_with_entry_count = 0;
         self.nodes_with_copy_source_count = 0;
     }
 
     fn add_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
         entry: DirstateEntry,
     ) -> Result<(), DirstateMapError> {
         self.add_or_remove_file(filename, old_state, entry);
         Ok(())
     }
 
     fn remove_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
         size: i32,
     ) -> Result<(), DirstateMapError> {
         let entry = DirstateEntry {
             state: EntryState::Removed,
             mode: 0,
             size,
             mtime: 0,
         };
         self.add_or_remove_file(filename, old_state, entry);
         Ok(())
     }
 
     fn drop_file(
         &mut self,
         filename: &HgPath,
         old_state: EntryState,
     ) -> Result<bool, DirstateMapError> {
         struct Dropped {
             was_tracked: bool,
             had_entry: bool,
             had_copy_source: bool,
         }
         fn recur(nodes: &mut ChildNodes, path: &HgPath) -> Option<Dropped> {
             let (first_path_component, rest_of_path) =
                 path.split_first_component();
             let node = nodes.get_mut(first_path_component)?;
             let dropped;
             if let Some(rest) = rest_of_path {
                 dropped = recur(&mut node.children, rest)?;
                 if dropped.was_tracked {
                     node.tracked_descendants_count -= 1;
                 }
             } else {
                 dropped = Dropped {
                     was_tracked: node
                         .entry
                         .as_ref()
                         .map_or(false, |entry| entry.state.is_tracked()),
                     had_entry: node.entry.take().is_some(),
                     had_copy_source: node.copy_source.take().is_some(),
                 };
-                // TODO: this leaves in the tree a "non-file" node. Should we
-                // remove the node instead, together with ancestor nodes for
-                // directories that become empty?
+            }
+            // After recursion, for both leaf (rest_of_path is None) nodes and
+            // parent nodes, remove a node if it just became empty.
+            if node.entry.is_none()
+                && node.copy_source.is_none()
+                && node.children.is_empty()
+            {
+                nodes.remove(first_path_component);
             }
             Some(dropped)
         }
 
         if let Some(dropped) = recur(&mut self.root, filename) {
             if dropped.had_entry {
                 self.nodes_with_entry_count -= 1
             }
             if dropped.had_copy_source {
                 self.nodes_with_copy_source_count -= 1
             }
             Ok(dropped.had_entry)
         } else {
             debug_assert!(!old_state.is_tracked());
             Ok(false)
         }
     }
 
     fn clear_ambiguous_times(&mut self, filenames: Vec<HgPathBuf>, now: i32) {
         for filename in filenames {
             if let Some(node) = Self::get_node_mut(&mut self.root, &filename) {
                 if let Some(entry) = node.entry.as_mut() {
                     clear_ambiguous_mtime(entry, now);
                 }
             }
         }
     }
 
     fn non_normal_entries_contains(&mut self, key: &HgPath) -> bool {
         self.get_node(key)
             .and_then(|node| node.entry.as_ref())
             .map_or(false, DirstateEntry::is_non_normal)
     }
 
     fn non_normal_entries_remove(&mut self, _key: &HgPath) {
         // Do nothing, this `DirstateMap` does not have a separate "non normal
         // entries" set that need to be kept up to date
     }
 
     fn non_normal_or_other_parent_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPath> + '_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.entry
                 .as_ref()
                 .filter(|entry| {
                     entry.is_non_normal() || entry.is_from_other_parent()
                 })
                 .map(|_| path)
         }))
     }
 
     fn set_non_normal_other_parent_entries(&mut self, _force: bool) {
         // Do nothing, this `DirstateMap` does not have a separate "non normal
         // entries" and "from other parent" sets that need to be recomputed
     }
 
     fn iter_non_normal_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPath> + Send + '_> {
         self.iter_non_normal_paths_panic()
     }
 
     fn iter_non_normal_paths_panic(
         &self,
     ) -> Box<dyn Iterator<Item = &HgPath> + Send + '_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.entry
                 .as_ref()
                 .filter(|entry| entry.is_non_normal())
                 .map(|_| path)
         }))
     }
 
     fn iter_other_parent_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPath> + Send + '_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.entry
                 .as_ref()
                 .filter(|entry| entry.is_from_other_parent())
                 .map(|_| path)
         }))
     }
 
     fn has_tracked_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateMapError> {
         if let Some(node) = self.get_node(directory) {
             // A node without a `DirstateEntry` was created to hold child
             // nodes, and is therefore a directory.
             Ok(node.entry.is_none() && node.tracked_descendants_count > 0)
         } else {
             Ok(false)
         }
     }
 
     fn has_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateMapError> {
         if let Some(node) = self.get_node(directory) {
             // A node without a `DirstateEntry` was created to hold child
             // nodes, and is therefore a directory.
             Ok(node.entry.is_none())
         } else {
             Ok(false)
         }
     }
 
     fn pack(
         &mut self,
         parents: DirstateParents,
         now: Timestamp,
     ) -> Result<Vec<u8>, DirstateError> {
         // Optizimation (to be measured?): pre-compute size to avoid `Vec`
         // reallocations
         let mut size = parents.as_bytes().len();
         for (path, node) in self.iter_nodes() {
             if node.entry.is_some() {
                 size += packed_entry_size(
                     path,
                     node.copy_source.as_ref().map(|p| &**p),
                 )
             }
         }
 
         let mut packed = Vec::with_capacity(size);
         packed.extend(parents.as_bytes());
 
         let now: i32 = now.0.try_into().expect("time overflow");
         for (path, opt_entry, copy_source) in self.iter_node_data_mut() {
             if let Some(entry) = opt_entry {
                 clear_ambiguous_mtime(entry, now);
                 pack_entry(
                     path,
                     entry,
                     copy_source.as_ref().map(|p| &**p),
                     &mut packed,
                 );
             }
         }
         Ok(packed)
     }
 
     fn set_all_dirs(&mut self) -> Result<(), DirstateMapError> {
         // Do nothing, this `DirstateMap` does not a separate `all_dirs` that
         // needs to be recomputed
         Ok(())
     }
 
     fn set_dirs(&mut self) -> Result<(), DirstateMapError> {
         // Do nothing, this `DirstateMap` does not a separate `dirs` that needs
         // to be recomputed
         Ok(())
     }
 
     fn status<'a>(
         &'a mut self,
         matcher: &'a (dyn Matcher + Sync),
         root_dir: PathBuf,
         ignore_files: Vec<PathBuf>,
         options: StatusOptions,
     ) -> Result<(DirstateStatus<'a>, Vec<PatternFileWarning>), StatusError>
     {
         super::status::status(self, matcher, root_dir, ignore_files, options)
     }
 
     fn copy_map_len(&self) -> usize {
         self.nodes_with_copy_source_count
     }
 
     fn copy_map_iter(&self) -> CopyMapIter<'_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.copy_source
                 .as_ref()
                 .map(|copy_source| (path, &**copy_source))
         }))
     }
 
     fn copy_map_contains_key(&self, key: &HgPath) -> bool {
         if let Some(node) = self.get_node(key) {
             node.copy_source.is_some()
         } else {
             false
         }
     }
 
     fn copy_map_get(&self, key: &HgPath) -> Option<&HgPath> {
         self.get_node(key)?.copy_source.as_ref().map(|p| &**p)
     }
 
     fn copy_map_remove(&mut self, key: &HgPath) -> Option<HgPathBuf> {
         let count = &mut self.nodes_with_copy_source_count;
         Self::get_node_mut(&mut self.root, key).and_then(|node| {
             if node.copy_source.is_some() {
                 *count -= 1
             }
             node.copy_source.take().map(Cow::into_owned)
         })
     }
 
     fn copy_map_insert(
         &mut self,
         key: HgPathBuf,
         value: HgPathBuf,
     ) -> Option<HgPathBuf> {
         let node = Self::get_or_insert_node(
             &mut self.root,
             &key,
             WithBasename::to_cow_owned,
             |_ancestor| {},
         );
         if node.copy_source.is_none() {
             self.nodes_with_copy_source_count += 1
         }
         node.copy_source.replace(value.into()).map(Cow::into_owned)
     }
 
     fn len(&self) -> usize {
         self.nodes_with_entry_count
     }
 
     fn contains_key(&self, key: &HgPath) -> bool {
         self.get(key).is_some()
     }
 
     fn get(&self, key: &HgPath) -> Option<&DirstateEntry> {
         self.get_node(key)?.entry.as_ref()
     }
 
     fn iter(&self) -> StateMapIter<'_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.entry.as_ref().map(|entry| (path, entry))
         }))
     }
 }

tests/test-status.t

@@ -1,868 +1,871
 #testcases dirstate-v1 dirstate-v1-tree
 
 #if dirstate-v1-tree
 #require rust
   $ echo '[experimental]' >> $HGRCPATH
   $ echo 'dirstate-tree.in-memory=1' >> $HGRCPATH
 #endif
 
   $ hg init repo1
   $ cd repo1
   $ mkdir a b a/1 b/1 b/2
   $ touch in_root a/in_a b/in_b a/1/in_a_1 b/1/in_b_1 b/2/in_b_2
 
 hg status in repo root:
 
   $ hg status
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
 
 hg status . in repo root:
 
   $ hg status .
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
 
   $ hg status --cwd a
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd a .
   ? 1/in_a_1
   ? in_a
   $ hg status --cwd a ..
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
 
   $ hg status --cwd b
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd b .
   ? 1/in_b_1
   ? 2/in_b_2
   ? in_b
   $ hg status --cwd b ..
   ? ../a/1/in_a_1
   ? ../a/in_a
   ? 1/in_b_1
   ? 2/in_b_2
   ? in_b
   ? ../in_root
 
   $ hg status --cwd a/1
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd a/1 .
   ? in_a_1
   $ hg status --cwd a/1 ..
   ? in_a_1
   ? ../in_a
 
   $ hg status --cwd b/1
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd b/1 .
   ? in_b_1
   $ hg status --cwd b/1 ..
   ? in_b_1
   ? ../2/in_b_2
   ? ../in_b
 
   $ hg status --cwd b/2
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd b/2 .
   ? in_b_2
   $ hg status --cwd b/2 ..
   ? ../1/in_b_1
   ? in_b_2
   ? ../in_b
 
 combining patterns with root and patterns without a root works
 
   $ hg st a/in_a re:.*b$
   ? a/in_a
   ? b/in_b
 
 tweaking defaults works
   $ hg status --cwd a --config ui.tweakdefaults=yes
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
   $ HGPLAIN=1 hg status --cwd a --config ui.tweakdefaults=yes
   ? a/1/in_a_1 (glob)
   ? a/in_a (glob)
   ? b/1/in_b_1 (glob)
   ? b/2/in_b_2 (glob)
   ? b/in_b (glob)
   ? in_root
   $ HGPLAINEXCEPT=tweakdefaults hg status --cwd a --config ui.tweakdefaults=yes
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root (glob)
 
 relative paths can be requested
 
   $ hg status --cwd a --config ui.relative-paths=yes
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
 
   $ hg status --cwd a . --config ui.relative-paths=legacy
   ? 1/in_a_1
   ? in_a
   $ hg status --cwd a . --config ui.relative-paths=no
   ? a/1/in_a_1
   ? a/in_a
 
 commands.status.relative overrides ui.relative-paths
 
   $ cat >> $HGRCPATH <<EOF
   > [ui]
   > relative-paths = False
   > [commands]
   > status.relative = True
   > EOF
   $ hg status --cwd a
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
   $ HGPLAIN=1 hg status --cwd a
   ? a/1/in_a_1 (glob)
   ? a/in_a (glob)
   ? b/1/in_b_1 (glob)
   ? b/2/in_b_2 (glob)
   ? b/in_b (glob)
   ? in_root
 
 if relative paths are explicitly off, tweakdefaults doesn't change it
   $ cat >> $HGRCPATH <<EOF
   > [commands]
   > status.relative = False
   > EOF
   $ hg status --cwd a --config ui.tweakdefaults=yes
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
 
   $ cd ..
 
   $ hg init repo2
   $ cd repo2
   $ touch modified removed deleted ignored
   $ echo "^ignored$" > .hgignore
   $ hg ci -A -m 'initial checkin'
   adding .hgignore
   adding deleted
   adding modified
   adding removed
   $ touch modified added unknown ignored
   $ hg add added
   $ hg remove removed
   $ rm deleted
 
 hg status:
 
   $ hg status
   A added
   R removed
   ! deleted
   ? unknown
 
 hg status modified added removed deleted unknown never-existed ignored:
 
   $ hg status modified added removed deleted unknown never-existed ignored
   never-existed: * (glob)
   A added
   R removed
   ! deleted
   ? unknown
 
   $ hg copy modified copied
 
 hg status -C:
 
   $ hg status -C
   A added
   A copied
     modified
   R removed
   ! deleted
   ? unknown
 
 hg status -A:
 
   $ hg status -A
   A added
   A copied
     modified
   R removed
   ! deleted
   ? unknown
   I ignored
   C .hgignore
   C modified
 
   $ hg status -A -T '{status} {path} {node|shortest}\n'
   A added ffff
   A copied ffff
   R removed ffff
   ! deleted ffff
   ? unknown ffff
   I ignored ffff
   C .hgignore ffff
   C modified ffff
 
   $ hg status -A -Tjson
   [
    {
     "itemtype": "file",
     "path": "added",
     "status": "A"
    },
    {
     "itemtype": "file",
     "path": "copied",
     "source": "modified",
     "status": "A"
    },
    {
     "itemtype": "file",
     "path": "removed",
     "status": "R"
    },
    {
     "itemtype": "file",
     "path": "deleted",
     "status": "!"
    },
    {
     "itemtype": "file",
     "path": "unknown",
     "status": "?"
    },
    {
     "itemtype": "file",
     "path": "ignored",
     "status": "I"
    },
    {
     "itemtype": "file",
     "path": ".hgignore",
     "status": "C"
    },
    {
     "itemtype": "file",
     "path": "modified",
     "status": "C"
    }
   ]
 
   $ hg status -A -Tpickle > pickle
   >>> from __future__ import print_function
   >>> from mercurial import util
   >>> pickle = util.pickle
   >>> data = sorted((x[b'status'].decode(), x[b'path'].decode()) for x in pickle.load(open("pickle", r"rb")))
   >>> for s, p in data: print("%s %s" % (s, p))
   ! deleted
   ? pickle
   ? unknown
   A added
   A copied
   C .hgignore
   C modified
   I ignored
   R removed
   $ rm pickle
 
   $ echo "^ignoreddir$" > .hgignore
   $ mkdir ignoreddir
   $ touch ignoreddir/file
 
 Test templater support:
 
   $ hg status -AT "[{status}]\t{if(source, '{source} -> ')}{path}\n"
   [M]	.hgignore
   [A]	added
   [A]	modified -> copied
   [R]	removed
   [!]	deleted
   [?]	ignored
   [?]	unknown
   [I]	ignoreddir/file
   [C]	modified
   $ hg status -AT default
   M .hgignore
   A added
   A copied
     modified
   R removed
   ! deleted
   ? ignored
   ? unknown
   I ignoreddir/file
   C modified
   $ hg status -T compact
   abort: "status" not in template map
   [255]
 
 hg status ignoreddir/file:
 
   $ hg status ignoreddir/file
 
 hg status -i ignoreddir/file:
 
   $ hg status -i ignoreddir/file
   I ignoreddir/file
   $ cd ..
 
 Check 'status -q' and some combinations
 
   $ hg init repo3
   $ cd repo3
   $ touch modified removed deleted ignored
   $ echo "^ignored$" > .hgignore
   $ hg commit -A -m 'initial checkin'
   adding .hgignore
   adding deleted
   adding modified
   adding removed
   $ touch added unknown ignored
   $ hg add added
   $ echo "test" >> modified
   $ hg remove removed
   $ rm deleted
   $ hg copy modified copied
 
 Specify working directory revision explicitly, that should be the same as
 "hg status"
 
   $ hg status --change "wdir()"
   M modified
   A added
   A copied
   R removed
   ! deleted
   ? unknown
 
 Run status with 2 different flags.
 Check if result is the same or different.
 If result is not as expected, raise error
 
   $ assert() {
   >     hg status $1 > ../a
   >     hg status $2 > ../b
   >     if diff ../a ../b > /dev/null; then
   >         out=0
   >     else
   >         out=1
   >     fi
   >     if [ $3 -eq 0 ]; then
   >         df="same"
   >     else
   >         df="different"
   >     fi
   >     if [ $out -ne $3 ]; then
   >         echo "Error on $1 and $2, should be $df."
   >     fi
   > }
 
 Assert flag1 flag2 [0-same | 1-different]
 
   $ assert "-q" "-mard"      0
   $ assert "-A" "-marduicC"  0
   $ assert "-qA" "-mardcC"   0
   $ assert "-qAui" "-A"      0
   $ assert "-qAu" "-marducC" 0
   $ assert "-qAi" "-mardicC" 0
   $ assert "-qu" "-u"        0
   $ assert "-q" "-u"         1
   $ assert "-m" "-a"         1
   $ assert "-r" "-d"         1
   $ cd ..
 
   $ hg init repo4
   $ cd repo4
   $ touch modified removed deleted
   $ hg ci -q -A -m 'initial checkin'
   $ touch added unknown
   $ hg add added
   $ hg remove removed
   $ rm deleted
   $ echo x > modified
   $ hg copy modified copied
   $ hg ci -m 'test checkin' -d "1000001 0"
   $ rm *
   $ touch unrelated
   $ hg ci -q -A -m 'unrelated checkin' -d "1000002 0"
 
 hg status --change 1:
 
   $ hg status --change 1
   M modified
   A added
   A copied
   R removed
 
 hg status --change 1 unrelated:
 
   $ hg status --change 1 unrelated
 
 hg status -C --change 1 added modified copied removed deleted:
 
   $ hg status -C --change 1 added modified copied removed deleted
   M modified
   A added
   A copied
     modified
   R removed
 
 hg status -A --change 1 and revset:
 
   $ hg status -A --change '1|1'
   M modified
   A added
   A copied
     modified
   R removed
   C deleted
 
   $ cd ..
 
 hg status with --rev and reverted changes:
 
   $ hg init reverted-changes-repo
   $ cd reverted-changes-repo
   $ echo a > file
   $ hg add file
   $ hg ci -m a
   $ echo b > file
   $ hg ci -m b
 
 reverted file should appear clean
 
   $ hg revert -r 0 .
   reverting file
   $ hg status -A --rev 0
   C file
 
 #if execbit
 reverted file with changed flag should appear modified
 
   $ chmod +x file
   $ hg status -A --rev 0
   M file
 
   $ hg revert -r 0 .
   reverting file
 
 reverted and committed file with changed flag should appear modified
 
   $ hg co -C .
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ chmod +x file
   $ hg ci -m 'change flag'
   $ hg status -A --rev 1 --rev 2
   M file
   $ hg diff -r 1 -r 2
 
 #endif
 
   $ cd ..
 
 hg status of binary file starting with '\1\n', a separator for metadata:
 
   $ hg init repo5
   $ cd repo5
   >>> open("010a", r"wb").write(b"\1\nfoo") and None
   $ hg ci -q -A -m 'initial checkin'
   $ hg status -A
   C 010a
 
   >>> open("010a", r"wb").write(b"\1\nbar") and None
   $ hg status -A
   M 010a
   $ hg ci -q -m 'modify 010a'
   $ hg status -A --rev 0:1
   M 010a
 
   $ touch empty
   $ hg ci -q -A -m 'add another file'
   $ hg status -A --rev 1:2 010a
   C 010a
 
   $ cd ..
 
 test "hg status" with "directory pattern" which matches against files
 only known on target revision.
 
   $ hg init repo6
   $ cd repo6
 
   $ echo a > a.txt
   $ hg add a.txt
   $ hg commit -m '#0'
   $ mkdir -p 1/2/3/4/5
   $ echo b > 1/2/3/4/5/b.txt
   $ hg add 1/2/3/4/5/b.txt
   $ hg commit -m '#1'
 
   $ hg update -C 0 > /dev/null
   $ hg status -A
   C a.txt
 
 the directory matching against specified pattern should be removed,
 because directory existence prevents 'dirstate.walk()' from showing
 warning message about such pattern.
 
   $ test ! -d 1
   $ hg status -A --rev 1 1/2/3/4/5/b.txt
   R 1/2/3/4/5/b.txt
   $ hg status -A --rev 1 1/2/3/4/5
   R 1/2/3/4/5/b.txt
   $ hg status -A --rev 1 1/2/3
   R 1/2/3/4/5/b.txt
   $ hg status -A --rev 1 1
   R 1/2/3/4/5/b.txt
 
   $ hg status --config ui.formatdebug=True --rev 1 1
   status = [
       {
           'itemtype': 'file',
           'path': '1/2/3/4/5/b.txt',
           'status': 'R'
       },
   ]
 
 #if windows
   $ hg --config ui.slash=false status -A --rev 1 1
   R 1\2\3\4\5\b.txt
 #endif
 
   $ cd ..
 
 Status after move overwriting a file (issue4458)
 =================================================
 
 
   $ hg init issue4458
   $ cd issue4458
   $ echo a > a
   $ echo b > b
   $ hg commit -Am base
   adding a
   adding b
 
 
 with --force
 
   $ hg mv b --force a
   $ hg st --copies
   M a
     b
   R b
   $ hg revert --all
   reverting a
   undeleting b
   $ rm *.orig
 
 without force
 
   $ hg rm a
   $ hg st --copies
   R a
   $ hg mv b a
   $ hg st --copies
   M a
     b
   R b
 
 using ui.statuscopies setting
   $ hg st --config ui.statuscopies=true
   M a
     b
   R b
   $ hg st --config ui.statuscopies=false
   M a
   R b
   $ hg st --config ui.tweakdefaults=yes
   M a
     b
   R b
 
 using log status template (issue5155)
   $ hg log -Tstatus -r 'wdir()' -C
   changeset:   2147483647:ffffffffffff
   parent:      0:8c55c58b4c0e
   user:        test
   date:        * (glob)
   files:
   M a
     b
   R b
   
   $ hg log -GTstatus -r 'wdir()' -C
   o  changeset:   2147483647:ffffffffffff
   |  parent:      0:8c55c58b4c0e
   ~  user:        test
      date:        * (glob)
      files:
      M a
        b
      R b
   
 
 Other "bug" highlight, the revision status does not report the copy information.
 This is buggy behavior.
 
   $ hg commit -m 'blah'
   $ hg st --copies --change .
   M a
   R b
 
 using log status template, the copy information is displayed correctly.
   $ hg log -Tstatus -r. -C
   changeset:   1:6685fde43d21
   tag:         tip
   user:        test
   date:        * (glob)
   summary:     blah
   files:
   M a
     b
   R b
   
 
   $ cd ..
 
 Make sure .hg doesn't show up even as a symlink
 
   $ hg init repo0
   $ mkdir symlink-repo0
   $ cd symlink-repo0
   $ ln -s ../repo0/.hg
   $ hg status
 
 If the size hasn’t changed but mtime has, status needs to read the contents
 of the file to check whether it has changed
 
   $ echo 1 > a
   $ echo 1 > b
   $ touch -t 200102030000 a b
   $ hg commit -Aqm '#0'
   $ echo 2 > a
   $ touch -t 200102040000 a b
   $ hg status
   M a
 
 Asking specifically for the status of a deleted/removed file
 
   $ rm a
   $ rm b
   $ hg status a
   ! a
   $ hg rm a
   $ hg rm b
   $ hg status a
   R a
+  $ hg commit -qm '#1'
+  $ hg status a
+  a: $ENOENT$
 
 Check using include flag with pattern when status does not need to traverse
 the working directory (issue6483)
 
   $ cd ..
   $ hg init issue6483
   $ cd issue6483
   $ touch a.py b.rs
   $ hg add a.py b.rs
   $ hg st -aI "*.py"
   A a.py
 
 Also check exclude pattern
 
   $ hg st -aX "*.rs"
   A a.py
 
 issue6335
 When a directory containing a tracked file gets symlinked, as of 5.8
 `hg st` only gives the correct answer about clean (or deleted) files
 if also listing unknowns.
 The tree-based dirstate and status algorithm fix this:
 
 #if symlink no-dirstate-v1
 
   $ cd ..
   $ hg init issue6335
   $ cd issue6335
   $ mkdir foo
   $ touch foo/a
   $ hg ci -Ama
   adding foo/a
   $ mv foo bar
   $ ln -s bar foo
   $ hg status
   ! foo/a
   ? bar/a
   ? foo
 
   $ hg status -c  # incorrect output with `dirstate-v1`
   $ hg status -cu
   ? bar/a
   ? foo
   $ hg status -d  # incorrect output with `dirstate-v1`
   ! foo/a
   $ hg status -du
   ! foo/a
   ? bar/a
   ? foo
 
 #endif
 
 
 Create a repo with files in each possible status
 
   $ cd ..
   $ hg init repo7
   $ cd repo7
   $ mkdir subdir
   $ touch clean modified deleted removed
   $ touch subdir/clean subdir/modified subdir/deleted subdir/removed
   $ echo ignored > .hgignore
   $ hg ci -Aqm '#0'
   $ echo 1 > modified
   $ echo 1 > subdir/modified
   $ rm deleted
   $ rm subdir/deleted
   $ hg rm removed
   $ hg rm subdir/removed
   $ touch unknown ignored
   $ touch subdir/unknown subdir/ignored
 
 Check the output
 
   $ hg status
   M modified
   M subdir/modified
   R removed
   R subdir/removed
   ! deleted
   ! subdir/deleted
   ? subdir/unknown
   ? unknown
 
   $ hg status -mard
   M modified
   M subdir/modified
   R removed
   R subdir/removed
   ! deleted
   ! subdir/deleted
 
   $ hg status -A
   M modified
   M subdir/modified
   R removed
   R subdir/removed
   ! deleted
   ! subdir/deleted
   ? subdir/unknown
   ? unknown
   I ignored
   I subdir/ignored
   C .hgignore
   C clean
   C subdir/clean
 
 Note: `hg status some-name` creates a patternmatcher which is not supported
 yet by the Rust implementation of status, but includematcher is supported.
 --include is used below for that reason
 
 Remove a directory that contains tracked files
 
   $ rm -r subdir
   $ hg status --include subdir
   R subdir/removed
   ! subdir/clean
   ! subdir/deleted
   ! subdir/modified
 
 … and replace it by a file
 
   $ touch subdir
   $ hg status --include subdir
   R subdir/removed
   ! subdir/clean
   ! subdir/deleted
   ! subdir/modified
   ? subdir
 
 Replaced a deleted or removed file with a directory
 
   $ mkdir deleted removed
   $ touch deleted/1 removed/1
   $ hg status --include deleted --include removed
   R removed
   ! deleted
   ? deleted/1
   ? removed/1
   $ hg add removed/1
   $ hg status --include deleted --include removed
   A removed/1
   R removed
   ! deleted
   ? deleted/1
 
 Deeply nested files in an ignored directory are still listed on request
 
   $ echo ignored-dir >> .hgignore
   $ mkdir ignored-dir
   $ mkdir ignored-dir/subdir
   $ touch ignored-dir/subdir/1
   $ hg status --ignored
   I ignored
   I ignored-dir/subdir/1