view rust/hg-core/src/vfs.rs @ 48981:f3aafd785e65

filemerge: add support for partial conflict resolution by external tool

A common class of merge conflicts is in imports/#includes/etc. It's
relatively easy to write a tool that can resolve these conflicts,
perhaps by naively just unioning the statements and leaving any
cleanup to other tools to do later [1]. Such specialized tools cannot
generally resolve all conflicts in a file, of course. Let's therefore
call them "partial merge tools". Note that the internal simplemerge
algorithm is such a partial merge tool - one that only resolves
trivial "conflicts" where one side is unchanged or both sides change
in the same way.

One can also imagine having smarter language-aware partial tools that
merge the AST. It may be useful for such tools to interactively let
the user resolve any conflicts it can't resolve itself. However,
having the option of implementing it as a partial merge tool means
that the developer doesn't *need* to create a UI for it. Instead, the
user can resolve any remaining conflicts with their regular merge tool
(e.g. `:merge3` or `meld).

We don't currently have a way to let the user define such partial
merge tools. That's what this patch addresses. It lets the user
configure partial merge tools to run. Each tool can be configured to
run only on files matching certain patterns (e.g. "*.py"). The tool
takes three inputs (local, base, other) and resolves conflicts by
updating these in place. For example, let's say the inputs are these:


base:
```
import sys

def main():
  print('Hello')
```

local:
```
import os
import sys

def main():
  print('Hi')
```

other:
```
import re
import sys

def main():
  print('Howdy')
```

A partial merge tool could now resolve the conflicting imports by
replacing the import statements in *all* files by the following
snippet, while leaving the remainder of the files unchanged.

```
import os
import re
import sys
```

As a result, simplemerge and any regular merge tool that runs after
the partial merge tool(s) will consider the imports to be
non-conflicting and will only present the conflict in `main()` to the
user.

Differential Revision: https://phab.mercurial-scm.org/D12356

use crate::errors::{HgError, IoErrorContext, IoResultExt};
use memmap2::{Mmap, MmapOptions};
use std::io::{ErrorKind, Write};
use std::path::{Path, PathBuf};

/// Filesystem access abstraction for the contents of a given "base" diretory
#[derive(Clone, Copy)]
pub struct Vfs<'a> {
    pub(crate) base: &'a Path,
}

struct FileNotFound(std::io::Error, PathBuf);

impl Vfs<'_> {
    pub fn join(&self, relative_path: impl AsRef<Path>) -> PathBuf {
        self.base.join(relative_path)
    }

    pub fn symlink_metadata(
        &self,
        relative_path: impl AsRef<Path>,
    ) -> Result<std::fs::Metadata, HgError> {
        let path = self.join(relative_path);
        std::fs::symlink_metadata(&path).when_reading_file(&path)
    }

    pub fn read_link(
        &self,
        relative_path: impl AsRef<Path>,
    ) -> Result<PathBuf, HgError> {
        let path = self.join(relative_path);
        std::fs::read_link(&path).when_reading_file(&path)
    }

    pub fn read(
        &self,
        relative_path: impl AsRef<Path>,
    ) -> Result<Vec<u8>, HgError> {
        let path = self.join(relative_path);
        std::fs::read(&path).when_reading_file(&path)
    }

    fn mmap_open_gen(
        &self,
        relative_path: impl AsRef<Path>,
    ) -> Result<Result<Mmap, FileNotFound>, HgError> {
        let path = self.join(relative_path);
        let file = match std::fs::File::open(&path) {
            Err(err) => {
                if let ErrorKind::NotFound = err.kind() {
                    return Ok(Err(FileNotFound(err, path)));
                };
                return (Err(err)).when_reading_file(&path);
            }
            Ok(file) => file,
        };
        // TODO: what are the safety requirements here?
        let mmap = unsafe { MmapOptions::new().map(&file) }
            .when_reading_file(&path)?;
        Ok(Ok(mmap))
    }

    pub fn mmap_open_opt(
        &self,
        relative_path: impl AsRef<Path>,
    ) -> Result<Option<Mmap>, HgError> {
        self.mmap_open_gen(relative_path).map(|res| res.ok())
    }

    pub fn mmap_open(
        &self,
        relative_path: impl AsRef<Path>,
    ) -> Result<Mmap, HgError> {
        match self.mmap_open_gen(relative_path)? {
            Err(FileNotFound(err, path)) => Err(err).when_reading_file(&path),
            Ok(res) => Ok(res),
        }
    }

    pub fn rename(
        &self,
        relative_from: impl AsRef<Path>,
        relative_to: impl AsRef<Path>,
    ) -> Result<(), HgError> {
        let from = self.join(relative_from);
        let to = self.join(relative_to);
        std::fs::rename(&from, &to)
            .with_context(|| IoErrorContext::RenamingFile { from, to })
    }

    pub fn remove_file(
        &self,
        relative_path: impl AsRef<Path>,
    ) -> Result<(), HgError> {
        let path = self.join(relative_path);
        std::fs::remove_file(&path)
            .with_context(|| IoErrorContext::RemovingFile(path))
    }

    #[cfg(unix)]
    pub fn create_symlink(
        &self,
        relative_link_path: impl AsRef<Path>,
        target_path: impl AsRef<Path>,
    ) -> Result<(), HgError> {
        let link_path = self.join(relative_link_path);
        std::os::unix::fs::symlink(target_path, &link_path)
            .when_writing_file(&link_path)
    }

    /// Write `contents` into a temporary file, then rename to `relative_path`.
    /// This makes writing to a file "atomic": a reader opening that path will
    /// see either the previous contents of the file or the complete new
    /// content, never a partial write.
    pub fn atomic_write(
        &self,
        relative_path: impl AsRef<Path>,
        contents: &[u8],
    ) -> Result<(), HgError> {
        let mut tmp = tempfile::NamedTempFile::new_in(self.base)
            .when_writing_file(self.base)?;
        tmp.write_all(contents)
            .and_then(|()| tmp.flush())
            .when_writing_file(tmp.path())?;
        let path = self.join(relative_path);
        tmp.persist(&path)
            .map_err(|e| e.error)
            .when_writing_file(&path)?;
        Ok(())
    }
}

fn fs_metadata(
    path: impl AsRef<Path>,
) -> Result<Option<std::fs::Metadata>, HgError> {
    let path = path.as_ref();
    match std::fs::metadata(path) {
        Ok(meta) => Ok(Some(meta)),
        Err(error) => match error.kind() {
            // TODO: when we require a Rust version where `NotADirectory` is
            // stable, invert this logic and return None for it and `NotFound`
            // and propagate any other error.
            ErrorKind::PermissionDenied => Err(error).with_context(|| {
                IoErrorContext::ReadingMetadata(path.to_owned())
            }),
            _ => Ok(None),
        },
    }
}

pub(crate) fn is_dir(path: impl AsRef<Path>) -> Result<bool, HgError> {
    Ok(fs_metadata(path)?.map_or(false, |meta| meta.is_dir()))
}

pub(crate) fn is_file(path: impl AsRef<Path>) -> Result<bool, HgError> {
    Ok(fs_metadata(path)?.map_or(false, |meta| meta.is_file()))
}