comparison rust/hg-core/src/matchers.rs @ 47379:f6bb181c75f8

rust: Parse "subinclude"d files along the way, not later

When parsing a `.hgignore` file and encountering an `include:` line,
the included file is parsed recursively right then in a depth-first fashion.

With `subinclude:` however included files were parsed (recursively) much later.
This changes it to be expanded during parsing, like `.hgignore`.

The motivation for this is an upcoming changeset that needs to detect changes
in which files are ignored or not. The plan is to hash all ignore files while
they are being read, and store that hash in the dirstate (in v2 format).
In order to allow a potential alternative implementations to read that format,
the algorithm to compute that hash must be documented. Having a well-defined
depth-first ordering for the tree of (sub-)included files makes that easier.

Differential Revision: https://phab.mercurial-scm.org/D10834

47378:777c3d231913

use crate::{
    dirstate::dirs_multiset::DirsChildrenMultiset,
    filepatterns::{
        build_single_regex, filter_subincludes, get_patterns_from_file,
        PatternFileWarning, PatternResult, SubInclude,
    },
    utils::{
        files::find_dirs,
        hg_path::{HgPath, HgPathBuf},
        Escaped,

/// };
/// use std::path::Path;
/// ///
/// let ignore_patterns =
/// vec![IgnorePattern::new(PatternSyntax::RootGlob, b"this*", Path::new(""))];
/// let (matcher, _) = IncludeMatcher::new(ignore_patterns, "".as_ref()).unwrap();
/// ///
/// assert_eq!(matcher.matches(HgPath::new(b"testing")), false);
/// assert_eq!(matcher.matches(HgPath::new(b"this should work")), true);
/// assert_eq!(matcher.matches(HgPath::new(b"this also")), true);
/// assert_eq!(matcher.matches(HgPath::new(b"but not this")), false);

    Ok(move |path: &HgPath| re.is_match(path.as_bytes()))
}

/// Returns the regex pattern and a function that matches an `HgPath` against
/// said regex formed by the given ignore patterns.
fn build_regex_match<'a>(
    ignore_patterns: &'a [&'a IgnorePattern],
) -> PatternResult<(Vec<u8>, Box<dyn Fn(&HgPath) -> bool + Sync>)> {
    let mut regexps = vec![];
    let mut exact_set = HashSet::new();

    for pattern in ignore_patterns {

}

/// Returns a function that checks whether a given file (in the general sense)
/// should be matched.
fn build_match<'a, 'b>(
    ignore_patterns: &'a [IgnorePattern],
    root_dir: &Path,
) -> PatternResult<(
    Vec<u8>,
    Box<dyn Fn(&HgPath) -> bool + 'b + Sync>,
    Vec<PatternFileWarning>,
)> {
    let mut match_funcs: Vec<Box<dyn Fn(&HgPath) -> bool + Sync>> = vec![];
    // For debugging and printing
    let mut patterns = vec![];
    let mut all_warnings = vec![];

    let (subincludes, ignore_patterns) =
        filter_subincludes(ignore_patterns, root_dir)?;

    if !subincludes.is_empty() {
        // Build prefix-based matcher functions for subincludes
        let mut submatchers = FastHashMap::default();
        let mut prefixes = vec![];

        for SubInclude { prefix, root, path } in subincludes.into_iter() {
            let (match_fn, warnings) =
                get_ignore_function(vec![path.to_path_buf()], &root)?;
            all_warnings.extend(warnings);
            prefixes.push(prefix.to_owned());
            submatchers.insert(prefix.to_owned(), match_fn);
        }

        let match_subinclude = move |filename: &HgPath| {
            for prefix in prefixes.iter() {
                if let Some(rel) = filename.relative_to(prefix) {

            match_funcs.push(match_func)
        }
    }

    Ok(if match_funcs.len() == 1 {
        (patterns, match_funcs.remove(0), all_warnings)
    } else {
        (
            patterns,
            Box::new(move |f: &HgPath| -> bool {
                match_funcs.iter().any(|match_func| match_func(f))
            }),
            all_warnings,
        )
    })
}

/// Parses all "ignore" files with their recursive includes and returns a

            get_patterns_from_file(pattern_file, root_dir)?;

        all_patterns.extend(patterns.to_owned());
        all_warnings.extend(warnings);
    }
    let (matcher, warnings) = IncludeMatcher::new(all_patterns, root_dir)?;
    all_warnings.extend(warnings);
    Ok((
        Box::new(move |path: &HgPath| matcher.matches(path)),
        all_warnings,
    ))
}

impl<'a> IncludeMatcher<'a> {
    pub fn new(
        ignore_patterns: Vec<IgnorePattern>,
        root_dir: &Path,
    ) -> PatternResult<(Self, Vec<PatternFileWarning>)> {
        let (patterns, match_fn, warnings) =
            build_match(&ignore_patterns, root_dir)?;
        let RootsDirsAndParents {
            roots,
            dirs,
            parents,
        } = roots_dirs_and_parents(&ignore_patterns)?;

        let prefix = ignore_patterns.iter().any(|k| match k.syntax {
            PatternSyntax::Path | PatternSyntax::RelPath => true,
            _ => false,
        });

        Ok((
            Self {
                patterns,
                match_fn,
                prefix,
                roots,
                dirs,
                parents,
            },
            warnings,
        ))
    }

    fn get_all_parents_children(&self) -> DirsChildrenMultiset {
        // TODO cache
        let thing = self

    }

    #[test]
    fn test_includematcher() {
        // VisitchildrensetPrefix
        let (matcher, _) = IncludeMatcher::new(
            vec![IgnorePattern::new(
                PatternSyntax::RelPath,
                b"dir/subdir",
                Path::new(""),
            )],
            "".as_ref(),
        )
        .unwrap();

        let mut set = HashSet::new();
        set.insert(HgPath::new(b"dir"));
        assert_eq!(

            matcher.visit_children_set(HgPath::new(b"folder")),
            VisitChildrenSet::Empty
        );

        // VisitchildrensetRootfilesin
        let (matcher, _) = IncludeMatcher::new(
            vec![IgnorePattern::new(
                PatternSyntax::RootFiles,
                b"dir/subdir",
                Path::new(""),
            )],
            "".as_ref(),
        )
        .unwrap();

        let mut set = HashSet::new();
        set.insert(HgPath::new(b"dir"));
        assert_eq!(

            matcher.visit_children_set(HgPath::new(b"folder")),
            VisitChildrenSet::Empty
        );

        // VisitchildrensetGlob
        let (matcher, _) = IncludeMatcher::new(
            vec![IgnorePattern::new(
                PatternSyntax::Glob,
                b"dir/z*",
                Path::new(""),
            )],
            "".as_ref(),
        )
        .unwrap();

        let mut set = HashSet::new();
        set.insert(HgPath::new(b"dir"));
        assert_eq!(

47379:f6bb181c75f8

use crate::{
    dirstate::dirs_multiset::DirsChildrenMultiset,
    filepatterns::{
        build_single_regex, filter_subincludes, get_patterns_from_file,
        PatternFileWarning, PatternResult,
    },
    utils::{
        files::find_dirs,
        hg_path::{HgPath, HgPathBuf},
        Escaped,

/// };
/// use std::path::Path;
/// ///
/// let ignore_patterns =
/// vec![IgnorePattern::new(PatternSyntax::RootGlob, b"this*", Path::new(""))];
/// let matcher = IncludeMatcher::new(ignore_patterns).unwrap();
/// ///
/// assert_eq!(matcher.matches(HgPath::new(b"testing")), false);
/// assert_eq!(matcher.matches(HgPath::new(b"this should work")), true);
/// assert_eq!(matcher.matches(HgPath::new(b"this also")), true);
/// assert_eq!(matcher.matches(HgPath::new(b"but not this")), false);

    Ok(move |path: &HgPath| re.is_match(path.as_bytes()))
}

/// Returns the regex pattern and a function that matches an `HgPath` against
/// said regex formed by the given ignore patterns.
fn build_regex_match(
    ignore_patterns: &[IgnorePattern],
) -> PatternResult<(Vec<u8>, Box<dyn Fn(&HgPath) -> bool + Sync>)> {
    let mut regexps = vec![];
    let mut exact_set = HashSet::new();

    for pattern in ignore_patterns {

}

/// Returns a function that checks whether a given file (in the general sense)
/// should be matched.
fn build_match<'a, 'b>(
    ignore_patterns: Vec<IgnorePattern>,
) -> PatternResult<(Vec<u8>, Box<dyn Fn(&HgPath) -> bool + 'b + Sync>)> {
    let mut match_funcs: Vec<Box<dyn Fn(&HgPath) -> bool + Sync>> = vec![];
    // For debugging and printing
    let mut patterns = vec![];

    let (subincludes, ignore_patterns) = filter_subincludes(ignore_patterns)?;

    if !subincludes.is_empty() {
        // Build prefix-based matcher functions for subincludes
        let mut submatchers = FastHashMap::default();
        let mut prefixes = vec![];

        for sub_include in subincludes {
            let matcher = IncludeMatcher::new(sub_include.included_patterns)?;
            let match_fn =
                Box::new(move |path: &HgPath| matcher.matches(path));
            prefixes.push(sub_include.prefix.clone());
            submatchers.insert(sub_include.prefix.clone(), match_fn);
        }

        let match_subinclude = move |filename: &HgPath| {
            for prefix in prefixes.iter() {
                if let Some(rel) = filename.relative_to(prefix) {

            match_funcs.push(match_func)
        }
    }

    Ok(if match_funcs.len() == 1 {
        (patterns, match_funcs.remove(0))
    } else {
        (
            patterns,
            Box::new(move |f: &HgPath| -> bool {
                match_funcs.iter().any(|match_func| match_func(f))
            }),
        )
    })
}

/// Parses all "ignore" files with their recursive includes and returns a

            get_patterns_from_file(pattern_file, root_dir)?;

        all_patterns.extend(patterns.to_owned());
        all_warnings.extend(warnings);
    }
    let matcher = IncludeMatcher::new(all_patterns)?;
    Ok((
        Box::new(move |path: &HgPath| matcher.matches(path)),
        all_warnings,
    ))
}

impl<'a> IncludeMatcher<'a> {
    pub fn new(ignore_patterns: Vec<IgnorePattern>) -> PatternResult<Self> {
        let RootsDirsAndParents {
            roots,
            dirs,
            parents,
        } = roots_dirs_and_parents(&ignore_patterns)?;
        let prefix = ignore_patterns.iter().any(|k| match k.syntax {
            PatternSyntax::Path | PatternSyntax::RelPath => true,
            _ => false,
        });
        let (patterns, match_fn) = build_match(ignore_patterns)?;

        Ok(Self {
            patterns,
            match_fn,
            prefix,
            roots,
            dirs,
            parents,
        })
    }

    fn get_all_parents_children(&self) -> DirsChildrenMultiset {
        // TODO cache
        let thing = self

    }

    #[test]
    fn test_includematcher() {
        // VisitchildrensetPrefix
        let matcher = IncludeMatcher::new(vec![IgnorePattern::new(
            PatternSyntax::RelPath,
            b"dir/subdir",
            Path::new(""),
        )])
        .unwrap();

        let mut set = HashSet::new();
        set.insert(HgPath::new(b"dir"));
        assert_eq!(

            matcher.visit_children_set(HgPath::new(b"folder")),
            VisitChildrenSet::Empty
        );

        // VisitchildrensetRootfilesin
        let matcher = IncludeMatcher::new(vec![IgnorePattern::new(
            PatternSyntax::RootFiles,
            b"dir/subdir",
            Path::new(""),
        )])
        .unwrap();

        let mut set = HashSet::new();
        set.insert(HgPath::new(b"dir"));
        assert_eq!(

            matcher.visit_children_set(HgPath::new(b"folder")),
            VisitChildrenSet::Empty
        );

        // VisitchildrensetGlob
        let matcher = IncludeMatcher::new(vec![IgnorePattern::new(
            PatternSyntax::Glob,
            b"dir/z*",
            Path::new(""),
        )])
        .unwrap();

        let mut set = HashSet::new();
        set.insert(HgPath::new(b"dir"));
        assert_eq!(