rust-dirstate-status: update bridge for new rust version of `dirstate.status`

Differential Revision: https://phab.mercurial-scm.org/D7530

rust/hg-core/src/lib.rs

@@ -1,173 +1,173 b''
 // Copyright 2018 Georges Racinet <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 mod ancestors;
 pub mod dagops;
 pub use ancestors::{AncestorsIterator, LazyAncestors, MissingAncestors};
 mod dirstate;
 pub mod discovery;
 pub mod testing; // unconditionally built, for use from integration tests
 pub use dirstate::{
     dirs_multiset::{DirsMultiset, DirsMultisetIter},
     dirstate_map::DirstateMap,
     parsers::{pack_dirstate, parse_dirstate, PARENT_SIZE},
-    status::status,
+    status::{status, StatusResult},
     CopyMap, CopyMapIter, DirstateEntry, DirstateParents, EntryState,
     StateMap, StateMapIter,
 };
 mod filepatterns;
 pub mod matchers;
 pub mod utils;
 
 use crate::utils::hg_path::HgPathBuf;
 pub use filepatterns::{
     build_single_regex, read_pattern_file, PatternSyntax, PatternTuple,
 };
 use std::collections::HashMap;
 use twox_hash::RandomXxHashBuilder64;
 
 /// Mercurial revision numbers
 ///
 /// As noted in revlog.c, revision numbers are actually encoded in
 /// 4 bytes, and are liberally converted to ints, whence the i32
 pub type Revision = i32;
 
 /// Marker expressing the absence of a parent
 ///
 /// Independently of the actual representation, `NULL_REVISION` is guaranteed
 /// to be smaller that all existing revisions.
 pub const NULL_REVISION: Revision = -1;
 
 /// Same as `mercurial.node.wdirrev`
 ///
 /// This is also equal to `i32::max_value()`, but it's better to spell
 /// it out explicitely, same as in `mercurial.node`
 pub const WORKING_DIRECTORY_REVISION: Revision = 0x7fffffff;
 
 /// The simplest expression of what we need of Mercurial DAGs.
 pub trait Graph {
     /// Return the two parents of the given `Revision`.
     ///
     /// Each of the parents can be independently `NULL_REVISION`
     fn parents(&self, rev: Revision) -> Result<[Revision; 2], GraphError>;
 }
 
 pub type LineNumber = usize;
 
 /// Rust's default hasher is too slow because it tries to prevent collision
 /// attacks. We are not concerned about those: if an ill-minded person has
 /// write access to your repository, you have other issues.
 pub type FastHashMap<K, V> = HashMap<K, V, RandomXxHashBuilder64>;
 
 #[derive(Clone, Debug, PartialEq)]
 pub enum GraphError {
     ParentOutOfRange(Revision),
     WorkingDirectoryUnsupported,
 }
 
 #[derive(Clone, Debug, PartialEq)]
 pub enum DirstateParseError {
     TooLittleData,
     Overflow,
     CorruptedEntry(String),
     Damaged,
 }
 
 impl From<std::io::Error> for DirstateParseError {
     fn from(e: std::io::Error) -> Self {
         DirstateParseError::CorruptedEntry(e.to_string())
     }
 }
 
 impl ToString for DirstateParseError {
     fn to_string(&self) -> String {
         use crate::DirstateParseError::*;
         match self {
             TooLittleData => "Too little data for dirstate.".to_string(),
             Overflow => "Overflow in dirstate.".to_string(),
             CorruptedEntry(e) => format!("Corrupted entry: {:?}.", e),
             Damaged => "Dirstate appears to be damaged.".to_string(),
         }
     }
 }
 
 #[derive(Debug, PartialEq)]
 pub enum DirstatePackError {
     CorruptedEntry(String),
     CorruptedParent,
     BadSize(usize, usize),
 }
 
 impl From<std::io::Error> for DirstatePackError {
     fn from(e: std::io::Error) -> Self {
         DirstatePackError::CorruptedEntry(e.to_string())
     }
 }
 #[derive(Debug, PartialEq)]
 pub enum DirstateMapError {
     PathNotFound(HgPathBuf),
     EmptyPath,
     ConsecutiveSlashes,
 }
 
 impl ToString for DirstateMapError {
     fn to_string(&self) -> String {
         use crate::DirstateMapError::*;
         match self {
             PathNotFound(_) => "expected a value, found none".to_string(),
             EmptyPath => "Overflow in dirstate.".to_string(),
             ConsecutiveSlashes => {
                 "found invalid consecutive slashes in path".to_string()
             }
         }
     }
 }
 
 pub enum DirstateError {
     Parse(DirstateParseError),
     Pack(DirstatePackError),
     Map(DirstateMapError),
     IO(std::io::Error),
 }
 
 impl From<DirstateParseError> for DirstateError {
     fn from(e: DirstateParseError) -> Self {
         DirstateError::Parse(e)
     }
 }
 
 impl From<DirstatePackError> for DirstateError {
     fn from(e: DirstatePackError) -> Self {
         DirstateError::Pack(e)
     }
 }
 
 #[derive(Debug)]
 pub enum PatternError {
     UnsupportedSyntax(String),
 }
 
 #[derive(Debug)]
 pub enum PatternFileError {
     IO(std::io::Error),
     Pattern(PatternError, LineNumber),
 }
 
 impl From<std::io::Error> for PatternFileError {
     fn from(e: std::io::Error) -> Self {
         PatternFileError::IO(e)
     }
 }
 
 impl From<DirstateMapError> for DirstateError {
     fn from(e: DirstateMapError) -> Self {
         DirstateError::Map(e)
     }
 }
 
 impl From<std::io::Error> for DirstateError {
     fn from(e: std::io::Error) -> Self {
         DirstateError::IO(e)
     }
 }

rust/hg-cpython/src/dirstate.rs

@@ -1,131 +1,132 b''
 // dirstate.rs
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Bindings for the `hg::dirstate` module provided by the
 //! `hg-core` package.
 //!
 //! From Python, this will be seen as `mercurial.rustext.dirstate`
 mod copymap;
 mod dirs_multiset;
 mod dirstate_map;
 mod status;
 use crate::dirstate::{
     dirs_multiset::Dirs, dirstate_map::DirstateMap, status::status_wrapper,
 };
 use cpython::{
     exc, PyBytes, PyDict, PyErr, PyModule, PyObject, PyResult, PySequence,
     Python,
 };
 use hg::{
     utils::hg_path::HgPathBuf, DirstateEntry, DirstateParseError, EntryState,
     StateMap,
 };
 use libc::{c_char, c_int};
 use std::convert::TryFrom;
 
 // C code uses a custom `dirstate_tuple` type, checks in multiple instances
 // for this type, and raises a Python `Exception` if the check does not pass.
 // Because this type differs only in name from the regular Python tuple, it
 // would be a good idea in the near future to remove it entirely to allow
 // for a pure Python tuple of the same effective structure to be used,
 // rendering this type and the capsule below useless.
 py_capsule_fn!(
     from mercurial.cext.parsers import make_dirstate_tuple_CAPI
         as make_dirstate_tuple_capi
         signature (
             state: c_char,
             mode: c_int,
             size: c_int,
             mtime: c_int,
         ) -> *mut RawPyObject
 );
 
 pub fn make_dirstate_tuple(
     py: Python,
     entry: &DirstateEntry,
 ) -> PyResult<PyObject> {
     // might be silly to retrieve capsule function in hot loop
     let make = make_dirstate_tuple_capi::retrieve(py)?;
 
     let &DirstateEntry {
         state,
         mode,
         size,
         mtime,
     } = entry;
     // Explicitly go through u8 first, then cast to platform-specific `c_char`
     // because Into<u8> has a specific implementation while `as c_char` would
     // just do a naive enum cast.
     let state_code: u8 = state.into();
 
     let maybe_obj = unsafe {
         let ptr = make(state_code as c_char, mode, size, mtime);
         PyObject::from_owned_ptr_opt(py, ptr)
     };
     maybe_obj.ok_or_else(|| PyErr::fetch(py))
 }
 
 pub fn extract_dirstate(py: Python, dmap: &PyDict) -> Result<StateMap, PyErr> {
     dmap.items(py)
         .iter()
         .map(|(filename, stats)| {
             let stats = stats.extract::<PySequence>(py)?;
             let state = stats.get_item(py, 0)?.extract::<PyBytes>(py)?;
             let state = EntryState::try_from(state.data(py)[0]).map_err(
                 |e: DirstateParseError| {
                     PyErr::new::<exc::ValueError, _>(py, e.to_string())
                 },
             )?;
             let mode = stats.get_item(py, 1)?.extract(py)?;
             let size = stats.get_item(py, 2)?.extract(py)?;
             let mtime = stats.get_item(py, 3)?.extract(py)?;
             let filename = filename.extract::<PyBytes>(py)?;
             let filename = filename.data(py);
             Ok((
                 HgPathBuf::from(filename.to_owned()),
                 DirstateEntry {
                     state,
                     mode,
                     size,
                     mtime,
                 },
             ))
         })
         .collect()
 }
 
 /// Create the module, with `__package__` given from parent
 pub fn init_module(py: Python, package: &str) -> PyResult<PyModule> {
     let dotted_name = &format!("{}.dirstate", package);
     let m = PyModule::new(py, dotted_name)?;
 
     m.add(py, "__package__", package)?;
     m.add(py, "__doc__", "Dirstate - Rust implementation")?;
 
     m.add_class::<Dirs>(py)?;
     m.add_class::<DirstateMap>(py)?;
     m.add(
         py,
         "status",
         py_fn!(
             py,
             status_wrapper(
                 dmap: DirstateMap,
                 root_dir: PyObject,
+                matcher: PyObject,
                 list_clean: bool,
                 last_normal_time: i64,
                 check_exec: bool
             )
         ),
     )?;
 
     let sys = PyModule::import(py, "sys")?;
     let sys_modules: PyDict = sys.get(py, "modules")?.extract(py)?;
     sys_modules.set_item(py, dotted_name, &m)?;
 
     Ok(m)
 }

rust/hg-cpython/src/dirstate/status.rs

@@ -1,80 +1,129 b''
 // status.rs
 //
 // Copyright 2019, Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Bindings for the `hg::status` module provided by the
 //! `hg-core` crate. From Python, this will be seen as
 //! `rustext.dirstate.status`.
 
 use crate::dirstate::DirstateMap;
 use cpython::exc::ValueError;
 use cpython::{
-    PyBytes, PyErr, PyList, PyObject, PyResult, Python, PythonObject,
-    ToPyObject,
+    ObjectProtocol, PyBytes, PyErr, PyList, PyObject, PyResult, PyTuple,
+    Python, PythonObject, ToPyObject,
 };
-use hg::utils::files::get_path_from_bytes;
-
-use hg::matchers::AlwaysMatcher;
-use hg::status;
-use hg::utils::hg_path::HgPath;
+use hg::utils::hg_path::HgPathBuf;
+use hg::{
+    matchers::{AlwaysMatcher, FileMatcher},
+    status,
+    utils::{files::get_path_from_bytes, hg_path::HgPath},
+    StatusResult,
+};
+use std::borrow::Borrow;
 
 /// This will be useless once trait impls for collection are added to `PyBytes`
 /// upstream.
 fn collect_pybytes_list<P: AsRef<HgPath>>(
     py: Python,
     collection: &[P],
 ) -> PyList {
     let list = PyList::new(py, &[]);
 
     for (i, path) in collection.iter().enumerate() {
         list.insert_item(
             py,
             i,
             PyBytes::new(py, path.as_ref().as_bytes()).into_object(),
         )
     }
 
     list
 }
 
 pub fn status_wrapper(
     py: Python,
     dmap: DirstateMap,
+    matcher: PyObject,
     root_dir: PyObject,
     list_clean: bool,
     last_normal_time: i64,
     check_exec: bool,
 ) -> PyResult<(PyList, PyList, PyList, PyList, PyList, PyList, PyList)> {
     let bytes = root_dir.extract::<PyBytes>(py)?;
     let root_dir = get_path_from_bytes(bytes.data(py));
 
     let dmap: DirstateMap = dmap.to_py_object(py);
     let dmap = dmap.get_inner(py);
 
-    // TODO removed in the next patch to get the code to compile. This patch
-    // is part of a series and does not make real sense on its own.
-    let matcher = AlwaysMatcher;
+    match matcher.get_type(py).name(py).borrow() {
+        "alwaysmatcher" => {
+            let matcher = AlwaysMatcher;
+            let (lookup, status_res) = status(
+                &dmap,
+                &matcher,
+                &root_dir,
+                list_clean,
+                last_normal_time,
+                check_exec,
+            )
+            .map_err(|e| PyErr::new::<ValueError, _>(py, e.to_string()))?;
+            build_response(lookup, status_res, py)
+        }
+        "exactmatcher" => {
+            let files = matcher.call_method(
+                py,
+                "files",
+                PyTuple::new(py, &[]),
+                None,
+            )?;
+            let files: PyList = files.cast_into(py)?;
+            let files: PyResult<Vec<HgPathBuf>> = files
+                .iter(py)
+                .map(|f| {
+                    Ok(HgPathBuf::from_bytes(
+                        f.extract::<PyBytes>(py)?.data(py),
+                    ))
+                })
+                .collect();
 
-    let (lookup, status_res) = status(
-        &dmap,
-        &matcher,
-        &root_dir,
-        list_clean,
-        last_normal_time,
-        check_exec,
-    )
-    .map_err(|e| PyErr::new::<ValueError, _>(py, e.to_string()))?;
+            let files = files?;
+            let matcher = FileMatcher::new(&files)
+                .map_err(|e| PyErr::new::<ValueError, _>(py, e.to_string()))?;
+            let (lookup, status_res) = status(
+                &dmap,
+                &matcher,
+                &root_dir,
+                list_clean,
+                last_normal_time,
+                check_exec,
+            )
+            .map_err(|e| PyErr::new::<ValueError, _>(py, e.to_string()))?;
+            build_response(lookup, status_res, py)
+        }
+        e => {
+            return Err(PyErr::new::<ValueError, _>(
+                py,
+                format!("Unsupported matcher {}", e),
+            ));
+        }
+    }
+}
 
+fn build_response(
+    lookup: Vec<&HgPath>,
+    status_res: StatusResult,
+    py: Python,
+) -> PyResult<(PyList, PyList, PyList, PyList, PyList, PyList, PyList)> {
     let modified = collect_pybytes_list(py, status_res.modified.as_ref());
     let added = collect_pybytes_list(py, status_res.added.as_ref());
     let removed = collect_pybytes_list(py, status_res.removed.as_ref());
     let deleted = collect_pybytes_list(py, status_res.deleted.as_ref());
     let clean = collect_pybytes_list(py, status_res.clean.as_ref());
     let lookup = collect_pybytes_list(py, lookup.as_ref());
     let unknown = PyList::new(py, &[]);
 
     Ok((lookup, modified, added, removed, deleted, unknown, clean))
 }