rust-filepatterns: add `rust-cpython` bindings for `filepatterns`

This change adds the `rust-cpython` interface for top-level functions and
exceptions in the filepatterns module.

Contrary to the Python implementation, this tries to have finer-grained
exceptions to allow for better readability and flow control down the line.

Differential Revision: https://phab.mercurial-scm.org/D6272

rust/hg-cpython/src/exceptions.rs

@@ -12,8 +12,8 b''
 //! existing Python exceptions if appropriate.
 //!
 //! [`GraphError`]: struct.GraphError.html
-use cpython::exc::ValueError;
-use cpython::{PyErr, Python};
+use cpython::exc::{ValueError, RuntimeError};
+use cpython::{PyErr, Python, exc};
 use hg;
 
 py_exception!(rustext, GraphError, ValueError);
@@ -28,9 +28,43 b' impl GraphError {'
                 match py
                     .import("mercurial.error")
                     .and_then(|m| m.get(py, "WdirUnsupported"))
-                {
-                    Err(e) => e,
-                    Ok(cls) => PyErr::from_instance(py, cls),
+                    {
+                        Err(e) => e,
+                        Ok(cls) => PyErr::from_instance(py, cls),
+                    }
+            }
+        }
+    }
+}
+
+py_exception!(rustext, PatternError, RuntimeError);
+py_exception!(rustext, PatternFileError, RuntimeError);
+
+impl PatternError {
+    pub fn pynew(py: Python, inner: hg::PatternError) -> PyErr {
+        match inner {
+            hg::PatternError::UnsupportedSyntax(m) => {
+                PatternError::new(py, ("PatternError", m))
+            }
+        }
+    }
+}
+
+
+impl PatternFileError {
+    pub fn pynew(py: Python, inner: hg::PatternFileError) -> PyErr {
+        match inner {
+            hg::PatternFileError::IO(e) => {
+                let value = (
+                    e.raw_os_error().unwrap_or(2),
+                    e.to_string()
+                );
+                PyErr::new::<exc::IOError, _>(py, value)
+            }
+            hg::PatternFileError::Pattern(e, l) => {
+                match e {
+                    hg::PatternError::UnsupportedSyntax(m) =>
+                        PatternFileError::new(py, ("PatternFileError", m, l))
                 }
             }
         }

rust/hg-cpython/src/filepatterns.rs

@@ -1,220 +1,115 b''
-// ancestors.rs
+// filepatterns.rs
 //
-// Copyright 2018 Georges Racinet <[e-mail]>
+// Copyright 2019, Georges Racinet <[e-mail]>,
+// 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::ancestors` module provided by the
-//! `hg-core` crate. From Python, this will be seen as `rustext.ancestor`
-//! and can be used as replacement for the the pure `ancestor` Python module.
-//!
-//! # Classes visible from Python:
-//! - [`LazyAncestors`] is the Rust implementation of
-//!   `mercurial.ancestor.lazyancestors`. The only difference is that it is
-//!   instantiated with a C `parsers.index` instance instead of a parents
-//!   function.
-//!
-//! - [`MissingAncestors`] is the Rust implementation of
-//!   `mercurial.ancestor.incrementalmissingancestors`.
+//! Bindings for the `hg::filepatterns` module provided by the
+//! `hg-core` crate. From Python, this will be seen as `rustext.filepatterns`
+//! and can be used as replacement for the the pure `filepatterns` Python module.
 //!
-//!   API differences:
-//!    + it is instantiated with a C `parsers.index`
-//!      instance instead of a parents function.
-//!    + `MissingAncestors.bases` is a method returning a tuple instead of
-//!      a set-valued attribute. We could return a Python set easily if our
-//!      [PySet PR](https://github.com/dgrunwald/rust-cpython/pull/165)
-//!      is accepted.
-//!
-//! - [`AncestorsIterator`] is the Rust counterpart of the
-//!   `ancestor._lazyancestorsiter` Python generator. From Python, instances of
-//!   this should be mainly obtained by calling `iter()` on a [`LazyAncestors`]
-//!   instance.
-//!
-//! [`LazyAncestors`]: struct.LazyAncestors.html
-//! [`MissingAncestors`]: struct.MissingAncestors.html
-//! [`AncestorsIterator`]: struct.AncestorsIterator.html
-use crate::conversion::{py_set, rev_pyiter_collect};
-use cindex::Index;
 use cpython::{
-    ObjectProtocol, PyClone, PyDict, PyList, PyModule, PyObject, PyResult,
-    Python, PythonObject, ToPyObject,
+    exc, PyDict, PyErr, PyModule, PyResult, PyString, PyTuple, Python,
+    ToPyObject,
 };
-use exceptions::GraphError;
-use hg::Revision;
-use hg::{
-    AncestorsIterator as CoreIterator, LazyAncestors as CoreLazy,
-    MissingAncestors as CoreMissing,
+use hg::{build_single_regex, read_pattern_file, PatternTuple};
+use exceptions::{
+    PatternError,
+    PatternFileError,
 };
-use std::cell::RefCell;
-use std::collections::HashSet;
 
-py_class!(pub class AncestorsIterator |py| {
-    data inner: RefCell<Box<CoreIterator<Index>>>;
-
-    def __next__(&self) -> PyResult<Option<Revision>> {
-        match self.inner(py).borrow_mut().next() {
-            Some(Err(e)) => Err(GraphError::pynew(py, e)),
-            None => Ok(None),
-            Some(Ok(r)) => Ok(Some(r)),
+/// Rust does not like functions with different return signatures.
+/// The 3-tuple version is always returned by the hg-core function,
+/// the (potential) conversion is handled at this level since it is not likely
+/// to have any measurable impact on performance.
+///
+/// The Python implementation passes a function reference for `warn` instead
+/// of a boolean that is used to emit warnings while parsing. The Rust
+/// implementation chooses to accumulate the warnings and propagate them to
+/// Python upon completion. See the `readpatternfile` function in `match.py`
+/// for more details.
+fn read_pattern_file_wrapper(
+    py: Python,
+    file_path: String,
+    warn: bool,
+    source_info: bool,
+) -> PyResult<PyTuple> {
+    match read_pattern_file(file_path, warn) {
+        Ok((patterns, warnings)) => {
+            if source_info {
+                return Ok((patterns, warnings).to_py_object(py));
+            }
+            let itemgetter = |x: &PatternTuple| x.0.to_py_object(py);
+            let results: Vec<PyString> =
+                patterns.iter().map(itemgetter).collect();
+            Ok((results, warnings).to_py_object(py))
         }
-    }
-
-    def __contains__(&self, rev: Revision) -> PyResult<bool> {
-        self.inner(py).borrow_mut().contains(rev)
-            .map_err(|e| GraphError::pynew(py, e))
-    }
-
-    def __iter__(&self) -> PyResult<Self> {
-        Ok(self.clone_ref(py))
-    }
-
-    def __new__(_cls, index: PyObject, initrevs: PyObject, stoprev: Revision,
-                inclusive: bool) -> PyResult<AncestorsIterator> {
-        let initvec: Vec<Revision> = rev_pyiter_collect(py, &initrevs)?;
-        let ait = CoreIterator::new(
-            Index::new(py, index)?,
-            initvec,
-            stoprev,
-            inclusive,
-        )
-        .map_err(|e| GraphError::pynew(py, e))?;
-        AncestorsIterator::from_inner(py, ait)
-    }
-
-});
-
-impl AncestorsIterator {
-    pub fn from_inner(py: Python, ait: CoreIterator<Index>) -> PyResult<Self> {
-        Self::create_instance(py, RefCell::new(Box::new(ait)))
+        Err(e) => Err(PatternFileError::pynew(py, e)),
     }
 }
 
-py_class!(pub class LazyAncestors |py| {
-    data inner: RefCell<Box<CoreLazy<Index>>>;
-
-    def __contains__(&self, rev: Revision) -> PyResult<bool> {
-        self.inner(py)
-            .borrow_mut()
-            .contains(rev)
-            .map_err(|e| GraphError::pynew(py, e))
-    }
-
-    def __iter__(&self) -> PyResult<AncestorsIterator> {
-        AncestorsIterator::from_inner(py, self.inner(py).borrow().iter())
-    }
-
-    def __bool__(&self) -> PyResult<bool> {
-        Ok(!self.inner(py).borrow().is_empty())
+fn build_single_regex_wrapper(
+    py: Python,
+    kind: String,
+    pat: String,
+    globsuffix: String,
+) -> PyResult<PyString> {
+    match build_single_regex(
+        kind.as_ref(),
+        pat.as_bytes(),
+        globsuffix.as_bytes(),
+    ) {
+        Ok(regex) => match String::from_utf8(regex) {
+            Ok(regex) => Ok(regex.to_py_object(py)),
+            Err(e) => Err(PyErr::new::<exc::UnicodeDecodeError, _>(
+                py,
+                e.to_string(),
+            )),
+        },
+        Err(e) => Err(PatternError::pynew(py, e)),
     }
-
-    def __new__(_cls, index: PyObject, initrevs: PyObject, stoprev: Revision,
-                inclusive: bool) -> PyResult<Self> {
-        let initvec: Vec<Revision> = rev_pyiter_collect(py, &initrevs)?;
-
-        let lazy =
-            CoreLazy::new(Index::new(py, index)?, initvec, stoprev, inclusive)
-                .map_err(|e| GraphError::pynew(py, e))?;
-
-        Self::create_instance(py, RefCell::new(Box::new(lazy)))
-        }
-
-});
-
-py_class!(pub class MissingAncestors |py| {
-    data inner: RefCell<Box<CoreMissing<Index>>>;
-
-    def __new__(_cls, index: PyObject, bases: PyObject) -> PyResult<MissingAncestors> {
-        let bases_vec: Vec<Revision> = rev_pyiter_collect(py, &bases)?;
-        let inner = CoreMissing::new(Index::new(py, index)?, bases_vec);
-        MissingAncestors::create_instance(py, RefCell::new(Box::new(inner)))
-    }
-
-    def hasbases(&self) -> PyResult<bool> {
-        Ok(self.inner(py).borrow().has_bases())
-    }
-
-    def addbases(&self, bases: PyObject) -> PyResult<PyObject> {
-        let mut inner = self.inner(py).borrow_mut();
-        let bases_vec: Vec<Revision> = rev_pyiter_collect(py, &bases)?;
-        inner.add_bases(bases_vec);
-        // cpython doc has examples with PyResult<()> but this gives me
-        //   the trait `cpython::ToPyObject` is not implemented for `()`
-        // so let's return an explicit None
-        Ok(py.None())
-    }
+}
 
-    def bases(&self) -> PyResult<PyObject> {
-        py_set(py, self.inner(py).borrow().get_bases())
-    }
-
-    def basesheads(&self) -> PyResult<PyObject> {
-        let inner = self.inner(py).borrow();
-        py_set(py, &inner.bases_heads().map_err(|e| GraphError::pynew(py, e))?)
-    }
-
-    def removeancestorsfrom(&self, revs: PyObject) -> PyResult<PyObject> {
-        let mut inner = self.inner(py).borrow_mut();
-        // this is very lame: we convert to a Rust set, update it in place
-        // and then convert back to Python, only to have Python remove the
-        // excess (thankfully, Python is happy with a list or even an iterator)
-        // Leads to improve this:
-        //  - have the CoreMissing instead do something emit revisions to
-        //    discard
-        //  - define a trait for sets of revisions in the core and implement
-        //    it for a Python set rewrapped with the GIL marker
-        let mut revs_pyset: HashSet<Revision> = rev_pyiter_collect(py, &revs)?;
-        inner.remove_ancestors_from(&mut revs_pyset)
-            .map_err(|e| GraphError::pynew(py, e))?;
+pub fn init_module(py: Python, package: &str) -> PyResult<PyModule> {
+    let dotted_name = &format!("{}.filepatterns", package);
+    let m = PyModule::new(py, dotted_name)?;
 
-        // convert as Python list
-        let mut remaining_pyint_vec: Vec<PyObject> = Vec::with_capacity(
-            revs_pyset.len());
-        for rev in revs_pyset {
-            remaining_pyint_vec.push(rev.to_py_object(py).into_object());
-        }
-        let remaining_pylist = PyList::new(py, remaining_pyint_vec.as_slice());
-        revs.call_method(py, "intersection_update", (remaining_pylist, ), None)
-    }
-
-    def missingancestors(&self, revs: PyObject) -> PyResult<PyList> {
-        let mut inner = self.inner(py).borrow_mut();
-        let revs_vec: Vec<Revision> = rev_pyiter_collect(py, &revs)?;
-        let missing_vec = match inner.missing_ancestors(revs_vec) {
-            Ok(missing) => missing,
-            Err(e) => {
-                return Err(GraphError::pynew(py, e));
-            }
-        };
-        // convert as Python list
-        let mut missing_pyint_vec: Vec<PyObject> = Vec::with_capacity(
-            missing_vec.len());
-        for rev in missing_vec {
-            missing_pyint_vec.push(rev.to_py_object(py).into_object());
-        }
-        Ok(PyList::new(py, missing_pyint_vec.as_slice()))
-    }
-});
-
-/// Create the module, with __package__ given from parent
-pub fn init_module(py: Python, package: &str) -> PyResult<PyModule> {
-    let dotted_name = &format!("{}.ancestor", package);
-    let m = PyModule::new(py, dotted_name)?;
     m.add(py, "__package__", package)?;
     m.add(
         py,
         "__doc__",
-        "Generic DAG ancestor algorithms - Rust implementation",
+        "Patterns files parsing - Rust implementation",
     )?;
-    m.add_class::<AncestorsIterator>(py)?;
-    m.add_class::<LazyAncestors>(py)?;
-    m.add_class::<MissingAncestors>(py)?;
+    m.add(
+        py,
+        "build_single_regex",
+        py_fn!(
+            py,
+            build_single_regex_wrapper(
+                kind: String,
+                pat: String,
+                globsuffix: String
+            )
+        ),
+    )?;
+    m.add(
+        py,
+        "read_pattern_file",
+        py_fn!(
+            py,
+            read_pattern_file_wrapper(
+                file_path: String,
+                warn: bool,
+                source_info: 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)?;
-    // Example C code (see pyexpat.c and import.c) will "give away the
-    // reference", but we won't because it will be consumed once the
-    // Rust PyObject is dropped.
+
     Ok(m)
 }

rust/hg-cpython/src/lib.rs

@@ -32,6 +32,7 b' pub mod dagops;'
 pub mod discovery;
 pub mod exceptions;
 pub mod dirstate;
+pub mod filepatterns;
 
 py_module_initializer!(rustext, initrustext, PyInit_rustext, |py, m| {
     m.add(
@@ -45,6 +46,9 b' py_module_initializer!(rustext, initrust'
     m.add(py, "dagop", dagops::init_module(py, &dotted_name)?)?;
     m.add(py, "discovery", discovery::init_module(py, &dotted_name)?)?;
     m.add(py, "dirstate", dirstate::init_module(py, &dotted_name)?)?;
+    m.add(py, "filepatterns", filepatterns::init_module(py, &dotted_name)?)?;
     m.add(py, "GraphError", py.get_type::<exceptions::GraphError>())?;
+    m.add(py, "PatternFileError", py.get_type::<exceptions::PatternFileError>())?;
+    m.add(py, "PatternError", py.get_type::<exceptions::PatternError>())?;
     Ok(())
 });