matcher: fix the issue with regex inline-flag in rust oo

Same problem same solution.

rust/hg-core/src/filepatterns.rs

@@ -1,706 +1,756
 // filepatterns.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.
 
 //! Handling of Mercurial-specific patterns.
 
 use crate::{
     utils::{
         files::{canonical_path, get_bytes_from_path, get_path_from_bytes},
         hg_path::{path_to_hg_path_buf, HgPathBuf, HgPathError},
         SliceExt,
     },
     FastHashMap, PatternError,
 };
 use lazy_static::lazy_static;
 use regex::bytes::{NoExpand, Regex};
 use std::ops::Deref;
 use std::path::{Path, PathBuf};
 use std::vec::Vec;
 
 lazy_static! {
     static ref RE_ESCAPE: Vec<Vec<u8>> = {
         let mut v: Vec<Vec<u8>> = (0..=255).map(|byte| vec![byte]).collect();
         let to_escape = b"()[]{}?*+-|^$\\.&~# \t\n\r\x0b\x0c";
         for byte in to_escape {
             v[*byte as usize].insert(0, b'\\');
         }
         v
     };
 }
 
 /// These are matched in order
 const GLOB_REPLACEMENTS: &[(&[u8], &[u8])] =
     &[(b"*/", b"(?:.*/)?"), (b"*", b".*"), (b"", b"[^/]*")];
 
 /// Appended to the regexp of globs
 const GLOB_SUFFIX: &[u8; 7] = b"(?:/|$)";
 
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub enum PatternSyntax {
     /// A regular expression
     Regexp,
     /// Glob that matches at the front of the path
     RootGlob,
     /// Glob that matches at any suffix of the path (still anchored at
     /// slashes)
     Glob,
     /// a path relative to repository root, which is matched recursively
     Path,
     /// A path relative to cwd
     RelPath,
     /// an unrooted glob (*.rs matches Rust files in all dirs)
     RelGlob,
     /// A regexp that needn't match the start of a name
     RelRegexp,
     /// A path relative to repository root, which is matched non-recursively
     /// (will not match subdirectories)
     RootFiles,
     /// A file of patterns to read and include
     Include,
     /// A file of patterns to match against files under the same directory
     SubInclude,
     /// SubInclude with the result of parsing the included file
     ///
     /// Note: there is no ExpandedInclude because that expansion can be done
     /// in place by replacing the Include pattern by the included patterns.
     /// SubInclude requires more handling.
     ///
     /// Note: `Box` is used to minimize size impact on other enum variants
     ExpandedSubInclude(Box<SubInclude>),
 }
 
 /// Transforms a glob pattern into a regex
 fn glob_to_re(pat: &[u8]) -> Vec<u8> {
     let mut input = pat;
     let mut res: Vec<u8> = vec![];
     let mut group_depth = 0;
 
     while let Some((c, rest)) = input.split_first() {
         input = rest;
 
         match c {
             b'*' => {
                 for (source, repl) in GLOB_REPLACEMENTS {
                     if let Some(rest) = input.drop_prefix(source) {
                         input = rest;
                         res.extend(*repl);
                         break;
                     }
                 }
             }
             b'?' => res.extend(b"."),
             b'[' => {
                 match input.iter().skip(1).position(|b| *b == b']') {
                     None => res.extend(b"\\["),
                     Some(end) => {
                         // Account for the one we skipped
                         let end = end + 1;
 
                         res.extend(b"[");
 
                         for (i, b) in input[..end].iter().enumerate() {
                             if *b == b'!' && i == 0 {
                                 res.extend(b"^")
                             } else if *b == b'^' && i == 0 {
                                 res.extend(b"\\^")
                             } else if *b == b'\\' {
                                 res.extend(b"\\\\")
                             } else {
                                 res.push(*b)
                             }
                         }
                         res.extend(b"]");
                         input = &input[end + 1..];
                     }
                 }
             }
             b'{' => {
                 group_depth += 1;
                 res.extend(b"(?:")
             }
             b'}' if group_depth > 0 => {
                 group_depth -= 1;
                 res.extend(b")");
             }
             b',' if group_depth > 0 => res.extend(b"|"),
             b'\\' => {
                 let c = {
                     if let Some((c, rest)) = input.split_first() {
                         input = rest;
                         c
                     } else {
                         c
                     }
                 };
                 res.extend(&RE_ESCAPE[*c as usize])
             }
             _ => res.extend(&RE_ESCAPE[*c as usize]),
         }
     }
     res
 }
 
 fn escape_pattern(pattern: &[u8]) -> Vec<u8> {
     pattern
         .iter()
         .flat_map(|c| RE_ESCAPE[*c as usize].clone())
         .collect()
 }
 
 pub fn parse_pattern_syntax(
     kind: &[u8],
 ) -> Result<PatternSyntax, PatternError> {
     match kind {
         b"re:" => Ok(PatternSyntax::Regexp),
         b"path:" => Ok(PatternSyntax::Path),
         b"relpath:" => Ok(PatternSyntax::RelPath),
         b"rootfilesin:" => Ok(PatternSyntax::RootFiles),
         b"relglob:" => Ok(PatternSyntax::RelGlob),
         b"relre:" => Ok(PatternSyntax::RelRegexp),
         b"glob:" => Ok(PatternSyntax::Glob),
         b"rootglob:" => Ok(PatternSyntax::RootGlob),
         b"include:" => Ok(PatternSyntax::Include),
         b"subinclude:" => Ok(PatternSyntax::SubInclude),
         _ => Err(PatternError::UnsupportedSyntax(
             String::from_utf8_lossy(kind).to_string(),
         )),
     }
 }
 
+lazy_static! {
+    static ref FLAG_RE: Regex = Regex::new(r"^\(\?[aiLmsux]+\)").unwrap();
+}
+
 /// Builds the regex that corresponds to the given pattern.
 /// If within a `syntax: regexp` context, returns the pattern,
 /// otherwise, returns the corresponding regex.
 fn _build_single_regex(entry: &IgnorePattern) -> Vec<u8> {
     let IgnorePattern {
         syntax, pattern, ..
     } = entry;
     if pattern.is_empty() {
         return vec![];
     }
     match syntax {
         PatternSyntax::Regexp => pattern.to_owned(),
         PatternSyntax::RelRegexp => {
             // The `regex` crate accepts `**` while `re2` and Python's `re`
             // do not. Checking for `*` correctly triggers the same error all
             // engines.
             if pattern[0] == b'^'
                 || pattern[0] == b'*'
                 || pattern.starts_with(b".*")
             {
                 return pattern.to_owned();
             }
-            [&b".*"[..], pattern].concat()
+            match FLAG_RE.find(pattern) {
+                Some(mat) => {
+                    let s = mat.start();
+                    let e = mat.end();
+                    [
+                        &b"(?"[..],
+                        &pattern[s + 2..e - 1],
+                        &b":"[..],
+                        &b".*"[..],
+                        &pattern[e..],
+                        &b")"[..],
+                    ]
+                    .concat()
+                }
+                None => [&b".*"[..], pattern].concat(),
+            }
         }
         PatternSyntax::Path | PatternSyntax::RelPath => {
             if pattern == b"." {
                 return vec![];
             }
             [escape_pattern(pattern).as_slice(), b"(?:/|$)"].concat()
         }
         PatternSyntax::RootFiles => {
             let mut res = if pattern == b"." {
                 vec![]
             } else {
                 // Pattern is a directory name.
                 [escape_pattern(pattern).as_slice(), b"/"].concat()
             };
 
             // Anything after the pattern must be a non-directory.
             res.extend(b"[^/]+$");
             res
         }
         PatternSyntax::RelGlob => {
             let glob_re = glob_to_re(pattern);
             if let Some(rest) = glob_re.drop_prefix(b"[^/]*") {
                 [b".*", rest, GLOB_SUFFIX].concat()
             } else {
                 [b"(?:.*/)?", glob_re.as_slice(), GLOB_SUFFIX].concat()
             }
         }
         PatternSyntax::Glob | PatternSyntax::RootGlob => {
             [glob_to_re(pattern).as_slice(), GLOB_SUFFIX].concat()
         }
         PatternSyntax::Include
         | PatternSyntax::SubInclude
         | PatternSyntax::ExpandedSubInclude(_) => unreachable!(),
     }
 }
 
 const GLOB_SPECIAL_CHARACTERS: [u8; 7] =
     [b'*', b'?', b'[', b']', b'{', b'}', b'\\'];
 
 /// TODO support other platforms
 #[cfg(unix)]
 pub fn normalize_path_bytes(bytes: &[u8]) -> Vec<u8> {
     if bytes.is_empty() {
         return b".".to_vec();
     }
     let sep = b'/';
 
     let mut initial_slashes = bytes.iter().take_while(|b| **b == sep).count();
     if initial_slashes > 2 {
         // POSIX allows one or two initial slashes, but treats three or more
         // as single slash.
         initial_slashes = 1;
     }
     let components = bytes
         .split(|b| *b == sep)
         .filter(|c| !(c.is_empty() || c == b"."))
         .fold(vec![], |mut acc, component| {
             if component != b".."
                 || (initial_slashes == 0 && acc.is_empty())
                 || (!acc.is_empty() && acc[acc.len() - 1] == b"..")
             {
                 acc.push(component)
             } else if !acc.is_empty() {
                 acc.pop();
             }
             acc
         });
     let mut new_bytes = components.join(&sep);
 
     if initial_slashes > 0 {
         let mut buf: Vec<_> = (0..initial_slashes).map(|_| sep).collect();
         buf.extend(new_bytes);
         new_bytes = buf;
     }
     if new_bytes.is_empty() {
         b".".to_vec()
     } else {
         new_bytes
     }
 }
 
 /// Wrapper function to `_build_single_regex` that short-circuits 'exact' globs
 /// that don't need to be transformed into a regex.
 pub fn build_single_regex(
     entry: &IgnorePattern,
 ) -> Result<Option<Vec<u8>>, PatternError> {
     let IgnorePattern {
         pattern, syntax, ..
     } = entry;
     let pattern = match syntax {
         PatternSyntax::RootGlob
         | PatternSyntax::Path
         | PatternSyntax::RelGlob
         | PatternSyntax::RootFiles => normalize_path_bytes(&pattern),
         PatternSyntax::Include | PatternSyntax::SubInclude => {
             return Err(PatternError::NonRegexPattern(entry.clone()))
         }
         _ => pattern.to_owned(),
     };
     if *syntax == PatternSyntax::RootGlob
         && !pattern.iter().any(|b| GLOB_SPECIAL_CHARACTERS.contains(b))
     {
         Ok(None)
     } else {
         let mut entry = entry.clone();
         entry.pattern = pattern;
         Ok(Some(_build_single_regex(&entry)))
     }
 }
 
 lazy_static! {
     static ref SYNTAXES: FastHashMap<&'static [u8], &'static [u8]> = {
         let mut m = FastHashMap::default();
 
         m.insert(b"re".as_ref(), b"relre:".as_ref());
         m.insert(b"regexp".as_ref(), b"relre:".as_ref());
         m.insert(b"glob".as_ref(), b"relglob:".as_ref());
         m.insert(b"rootglob".as_ref(), b"rootglob:".as_ref());
         m.insert(b"include".as_ref(), b"include:".as_ref());
         m.insert(b"subinclude".as_ref(), b"subinclude:".as_ref());
         m.insert(b"path".as_ref(), b"path:".as_ref());
         m.insert(b"rootfilesin".as_ref(), b"rootfilesin:".as_ref());
         m
     };
 }
 
 #[derive(Debug)]
 pub enum PatternFileWarning {
     /// (file path, syntax bytes)
     InvalidSyntax(PathBuf, Vec<u8>),
     /// File path
     NoSuchFile(PathBuf),
 }
 
 pub fn parse_pattern_file_contents(
     lines: &[u8],
     file_path: &Path,
     default_syntax_override: Option<&[u8]>,
     warn: bool,
 ) -> Result<(Vec<IgnorePattern>, Vec<PatternFileWarning>), PatternError> {
     let comment_regex = Regex::new(r"((?:^|[^\\])(?:\\\\)*)#.*").unwrap();
 
     #[allow(clippy::trivial_regex)]
     let comment_escape_regex = Regex::new(r"\\#").unwrap();
     let mut inputs: Vec<IgnorePattern> = vec![];
     let mut warnings: Vec<PatternFileWarning> = vec![];
 
     let mut current_syntax =
         default_syntax_override.unwrap_or(b"relre:".as_ref());
 
     for (line_number, mut line) in lines.split(|c| *c == b'\n').enumerate() {
         let line_number = line_number + 1;
 
         let line_buf;
         if line.contains(&b'#') {
             if let Some(cap) = comment_regex.captures(line) {
                 line = &line[..cap.get(1).unwrap().end()]
             }
             line_buf = comment_escape_regex.replace_all(line, NoExpand(b"#"));
             line = &line_buf;
         }
 
         let mut line = line.trim_end();
 
         if line.is_empty() {
             continue;
         }
 
         if let Some(syntax) = line.drop_prefix(b"syntax:") {
             let syntax = syntax.trim();
 
             if let Some(rel_syntax) = SYNTAXES.get(syntax) {
                 current_syntax = rel_syntax;
             } else if warn {
                 warnings.push(PatternFileWarning::InvalidSyntax(
                     file_path.to_owned(),
                     syntax.to_owned(),
                 ));
             }
             continue;
         }
 
         let mut line_syntax: &[u8] = &current_syntax;
 
         for (s, rels) in SYNTAXES.iter() {
             if let Some(rest) = line.drop_prefix(rels) {
                 line_syntax = rels;
                 line = rest;
                 break;
             }
             if let Some(rest) = line.drop_prefix(&[s, &b":"[..]].concat()) {
                 line_syntax = rels;
                 line = rest;
                 break;
             }
         }
 
         inputs.push(IgnorePattern::new(
             parse_pattern_syntax(&line_syntax).map_err(|e| match e {
                 PatternError::UnsupportedSyntax(syntax) => {
                     PatternError::UnsupportedSyntaxInFile(
                         syntax,
                         file_path.to_string_lossy().into(),
                         line_number,
                     )
                 }
                 _ => e,
             })?,
             &line,
             file_path,
         ));
     }
     Ok((inputs, warnings))
 }
 
 pub fn read_pattern_file(
     file_path: &Path,
     warn: bool,
     inspect_pattern_bytes: &mut impl FnMut(&Path, &[u8]),
 ) -> Result<(Vec<IgnorePattern>, Vec<PatternFileWarning>), PatternError> {
     match std::fs::read(file_path) {
         Ok(contents) => {
             inspect_pattern_bytes(file_path, &contents);
             parse_pattern_file_contents(&contents, file_path, None, warn)
         }
         Err(e) if e.kind() == std::io::ErrorKind::NotFound => Ok((
             vec![],
             vec![PatternFileWarning::NoSuchFile(file_path.to_owned())],
         )),
         Err(e) => Err(e.into()),
     }
 }
 
 /// Represents an entry in an "ignore" file.
 #[derive(Debug, Eq, PartialEq, Clone)]
 pub struct IgnorePattern {
     pub syntax: PatternSyntax,
     pub pattern: Vec<u8>,
     pub source: PathBuf,
 }
 
 impl IgnorePattern {
     pub fn new(syntax: PatternSyntax, pattern: &[u8], source: &Path) -> Self {
         Self {
             syntax,
             pattern: pattern.to_owned(),
             source: source.to_owned(),
         }
     }
 }
 
 pub type PatternResult<T> = Result<T, PatternError>;
 
 /// Wrapper for `read_pattern_file` that also recursively expands `include:`
 /// and `subinclude:` patterns.
 ///
 /// The former are expanded in place, while `PatternSyntax::ExpandedSubInclude`
 /// is used for the latter to form a tree of patterns.
 pub fn get_patterns_from_file(
     pattern_file: &Path,
     root_dir: &Path,
     inspect_pattern_bytes: &mut impl FnMut(&Path, &[u8]),
 ) -> PatternResult<(Vec<IgnorePattern>, Vec<PatternFileWarning>)> {
     let (patterns, mut warnings) =
         read_pattern_file(pattern_file, true, inspect_pattern_bytes)?;
     let patterns = patterns
         .into_iter()
         .flat_map(|entry| -> PatternResult<_> {
             Ok(match &entry.syntax {
                 PatternSyntax::Include => {
                     let inner_include =
                         root_dir.join(get_path_from_bytes(&entry.pattern));
                     let (inner_pats, inner_warnings) = get_patterns_from_file(
                         &inner_include,
                         root_dir,
                         inspect_pattern_bytes,
                     )?;
                     warnings.extend(inner_warnings);
                     inner_pats
                 }
                 PatternSyntax::SubInclude => {
                     let mut sub_include = SubInclude::new(
                         &root_dir,
                         &entry.pattern,
                         &entry.source,
                     )?;
                     let (inner_patterns, inner_warnings) =
                         get_patterns_from_file(
                             &sub_include.path,
                             &sub_include.root,
                             inspect_pattern_bytes,
                         )?;
                     sub_include.included_patterns = inner_patterns;
                     warnings.extend(inner_warnings);
                     vec![IgnorePattern {
                         syntax: PatternSyntax::ExpandedSubInclude(Box::new(
                             sub_include,
                         )),
                         ..entry
                     }]
                 }
                 _ => vec![entry],
             })
         })
         .flatten()
         .collect();
 
     Ok((patterns, warnings))
 }
 
 /// Holds all the information needed to handle a `subinclude:` pattern.
 #[derive(Debug, PartialEq, Eq, Clone)]
 pub struct SubInclude {
     /// Will be used for repository (hg) paths that start with this prefix.
     /// It is relative to the current working directory, so comparing against
     /// repository paths is painless.
     pub prefix: HgPathBuf,
     /// The file itself, containing the patterns
     pub path: PathBuf,
     /// Folder in the filesystem where this it applies
     pub root: PathBuf,
 
     pub included_patterns: Vec<IgnorePattern>,
 }
 
 impl SubInclude {
     pub fn new(
         root_dir: &Path,
         pattern: &[u8],
         source: &Path,
     ) -> Result<SubInclude, HgPathError> {
         let normalized_source =
             normalize_path_bytes(&get_bytes_from_path(source));
 
         let source_root = get_path_from_bytes(&normalized_source);
         let source_root =
             source_root.parent().unwrap_or_else(|| source_root.deref());
 
         let path = source_root.join(get_path_from_bytes(pattern));
         let new_root = path.parent().unwrap_or_else(|| path.deref());
 
         let prefix = canonical_path(root_dir, root_dir, new_root)?;
 
         Ok(Self {
             prefix: path_to_hg_path_buf(prefix).and_then(|mut p| {
                 if !p.is_empty() {
                     p.push_byte(b'/');
                 }
                 Ok(p)
             })?,
             path: path.to_owned(),
             root: new_root.to_owned(),
             included_patterns: Vec::new(),
         })
     }
 }
 
 /// Separate and pre-process subincludes from other patterns for the "ignore"
 /// phase.
 pub fn filter_subincludes(
     ignore_patterns: Vec<IgnorePattern>,
 ) -> Result<(Vec<Box<SubInclude>>, Vec<IgnorePattern>), HgPathError> {
     let mut subincludes = vec![];
     let mut others = vec![];
 
     for pattern in ignore_patterns {
         if let PatternSyntax::ExpandedSubInclude(sub_include) = pattern.syntax
         {
             subincludes.push(sub_include);
         } else {
             others.push(pattern)
         }
     }
     Ok((subincludes, others))
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use pretty_assertions::assert_eq;
 
     #[test]
     fn escape_pattern_test() {
         let untouched =
             br#"!"%',/0123456789:;<=>@ABCDEFGHIJKLMNOPQRSTUVWXYZ_`abcdefghijklmnopqrstuvwxyz"#;
         assert_eq!(escape_pattern(untouched), untouched.to_vec());
         // All escape codes
         assert_eq!(
             escape_pattern(br#"()[]{}?*+-|^$\\.&~# \t\n\r\v\f"#),
             br#"\(\)\[\]\{\}\?\*\+\-\|\^\$\\\\\.\&\~\#\ \\t\\n\\r\\v\\f"#
                 .to_vec()
         );
     }
 
     #[test]
     fn glob_test() {
         assert_eq!(glob_to_re(br#"?"#), br#"."#);
         assert_eq!(glob_to_re(br#"*"#), br#"[^/]*"#);
         assert_eq!(glob_to_re(br#"**"#), br#".*"#);
         assert_eq!(glob_to_re(br#"**/a"#), br#"(?:.*/)?a"#);
         assert_eq!(glob_to_re(br#"a/**/b"#), br#"a/(?:.*/)?b"#);
         assert_eq!(glob_to_re(br#"[a*?!^][^b][!c]"#), br#"[a*?!^][\^b][^c]"#);
         assert_eq!(glob_to_re(br#"{a,b}"#), br#"(?:a|b)"#);
         assert_eq!(glob_to_re(br#".\*\?"#), br#"\.\*\?"#);
     }
 
     #[test]
     fn test_parse_pattern_file_contents() {
         let lines = b"syntax: glob\n*.elc";
 
         assert_eq!(
             parse_pattern_file_contents(
                 lines,
                 Path::new("file_path"),
                 None,
                 false
             )
             .unwrap()
             .0,
             vec![IgnorePattern::new(
                 PatternSyntax::RelGlob,
                 b"*.elc",
                 Path::new("file_path")
             )],
         );
 
         let lines = b"syntax: include\nsyntax: glob";
 
         assert_eq!(
             parse_pattern_file_contents(
                 lines,
                 Path::new("file_path"),
                 None,
                 false
             )
             .unwrap()
             .0,
             vec![]
         );
         let lines = b"glob:**.o";
         assert_eq!(
             parse_pattern_file_contents(
                 lines,
                 Path::new("file_path"),
                 None,
                 false
             )
             .unwrap()
             .0,
             vec![IgnorePattern::new(
                 PatternSyntax::RelGlob,
                 b"**.o",
                 Path::new("file_path")
             )]
         );
     }
 
     #[test]
     fn test_build_single_regex() {
         assert_eq!(
             build_single_regex(&IgnorePattern::new(
                 PatternSyntax::RelGlob,
                 b"rust/target/",
                 Path::new("")
             ))
             .unwrap(),
             Some(br"(?:.*/)?rust/target(?:/|$)".to_vec()),
         );
         assert_eq!(
             build_single_regex(&IgnorePattern::new(
                 PatternSyntax::Regexp,
                 br"rust/target/\d+",
                 Path::new("")
             ))
             .unwrap(),
             Some(br"rust/target/\d+".to_vec()),
         );
     }
 
     #[test]
     fn test_build_single_regex_shortcut() {
         assert_eq!(
             build_single_regex(&IgnorePattern::new(
                 PatternSyntax::RootGlob,
                 b"",
                 Path::new("")
             ))
             .unwrap(),
             None,
         );
         assert_eq!(
             build_single_regex(&IgnorePattern::new(
                 PatternSyntax::RootGlob,
                 b"whatever",
                 Path::new("")
             ))
             .unwrap(),
             None,
         );
         assert_eq!(
             build_single_regex(&IgnorePattern::new(
                 PatternSyntax::RootGlob,
                 b"*.o",
                 Path::new("")
             ))
             .unwrap(),
             Some(br"[^/]*\.o(?:/|$)".to_vec()),
         );
     }
+
+    #[test]
+    fn test_build_single_relregex() {
+        assert_eq!(
+            build_single_regex(&IgnorePattern::new(
+                PatternSyntax::RelRegexp,
+                b"^ba{2}r",
+                Path::new("")
+            ))
+            .unwrap(),
+            Some(b"^ba{2}r".to_vec()),
+        );
+        assert_eq!(
+            build_single_regex(&IgnorePattern::new(
+                PatternSyntax::RelRegexp,
+                b"ba{2}r",
+                Path::new("")
+            ))
+            .unwrap(),
+            Some(b".*ba{2}r".to_vec()),
+        );
+        assert_eq!(
+            build_single_regex(&IgnorePattern::new(
+                PatternSyntax::RelRegexp,
+                b"(?ia)ba{2}r",
+                Path::new("")
+            ))
+            .unwrap(),
+            Some(b"(?ia:.*ba{2}r)".to_vec()),
+        );
+    }
 }

tests/test-hgignore.t

@@ -1,515 +1,514
 #testcases dirstate-v1 dirstate-v2
 
 #if dirstate-v2
   $ cat >> $HGRCPATH << EOF
   > [format]
   > use-dirstate-v2=1
   > [storage]
   > dirstate-v2.slow-path=allow
   > EOF
 #endif
 
   $ hg init ignorerepo
   $ cd ignorerepo
 
 debugignore with no hgignore should be deterministic:
   $ hg debugignore
   <nevermatcher>
 
 Issue562: .hgignore requires newline at end:
 
   $ touch foo
   $ touch bar
   $ touch baz
   $ cat > makeignore.py <<EOF
   > f = open(".hgignore", "w")
   > f.write("ignore\n")
   > f.write("foo\n")
   > # No EOL here
   > f.write("bar")
   > f.close()
   > EOF
 
   $ "$PYTHON" makeignore.py
 
 Should display baz only:
 
   $ hg status
   ? baz
 
   $ rm foo bar baz .hgignore makeignore.py
 
   $ touch a.o
   $ touch a.c
   $ touch syntax
   $ mkdir dir
   $ touch dir/a.o
   $ touch dir/b.o
   $ touch dir/c.o
 
   $ hg add dir/a.o
   $ hg commit -m 0
   $ hg add dir/b.o
 
   $ hg status
   A dir/b.o
   ? a.c
   ? a.o
   ? dir/c.o
   ? syntax
 
   $ echo "*.o" > .hgignore
   $ hg status
   abort: $TESTTMP/ignorerepo/.hgignore: invalid pattern (relre): *.o (glob)
   [255]
 
 Test relre with flags (issue6759)
 ---------------------------------
 
 regexp with flag is the first one
 
   $ echo 're:(?i)\.O$' > .hgignore
   $ echo 're:.hgignore' >> .hgignore
   $ hg status
   A dir/b.o
   ? a.c
   ? syntax
 
 regex with flag is not the first one
 
   $ echo 're:.hgignore' > .hgignore
   $ echo 're:(?i)\.O$' >> .hgignore
   $ hg status
   A dir/b.o
   ? a.c
   ? syntax
 
 flag in a pattern should affect that pattern only
 
   $ echo 're:(?i)\.O$' > .hgignore
   $ echo 're:.HGIGNORE' >> .hgignore
   $ hg status
   A dir/b.o
-  ? .hgignore (no-rust !)
-  ? .hgignore (rust missing-correct-output !)
+  ? .hgignore
   ? a.c
   ? syntax
 
   $ echo 're:.HGIGNORE' > .hgignore
   $ echo 're:(?i)\.O$' >> .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? syntax
 
 
 further testing
 ---------------
 
   $ echo 're:^(?!a).*\.o$' > .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? a.o
   ? syntax
 #if rhg
   $ hg status --config rhg.on-unsupported=abort
   unsupported feature: Unsupported syntax regex parse error:
       ^(?:^(?!a).*\.o$)
            ^^^
   error: look-around, including look-ahead and look-behind, is not supported
   [252]
 #endif
 
 Ensure given files are relative to cwd
 
   $ echo "dir/.*\.o" > .hgignore
   $ hg status -i
   I dir/c.o
 
   $ hg debugignore dir/c.o dir/missing.o
   dir/c.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: 'dir/.*\.o') (glob)
   dir/missing.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: 'dir/.*\.o') (glob)
   $ cd dir
   $ hg debugignore c.o missing.o
   c.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: 'dir/.*\.o') (glob)
   missing.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: 'dir/.*\.o') (glob)
 
 For icasefs, inexact matches also work, except for missing files
 
 #if icasefs
   $ hg debugignore c.O missing.O
   c.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: 'dir/.*\.o') (glob)
   missing.O is not ignored
 #endif
 
   $ cd ..
 
   $ echo ".*\.o" > .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? syntax
 
 Ensure that comments work:
 
   $ touch 'foo#bar' 'quux#' 'quu0#'
 #if no-windows
   $ touch 'baz\' 'baz\wat' 'ba0\#wat' 'ba1\\' 'ba1\\wat' 'quu0\'
 #endif
 
   $ cat <<'EOF' >> .hgignore
   > # full-line comment
   >   # whitespace-only comment line
   > syntax# pattern, no whitespace, then comment
   > a.c  # pattern, then whitespace, then comment
   > baz\\# # (escaped) backslash, then comment
   > ba0\\\#w # (escaped) backslash, escaped comment character, then comment
   > ba1\\\\# # (escaped) backslashes, then comment
   > foo\#b # escaped comment character
   > quux\## escaped comment character at end of name
   > EOF
   $ hg status
   A dir/b.o
   ? .hgignore
   ? quu0#
   ? quu0\ (no-windows !)
 
   $ cat <<'EOF' > .hgignore
   > .*\.o
   > syntax: glob
   > syntax# pattern, no whitespace, then comment
   > a.c  # pattern, then whitespace, then comment
   > baz\\#* # (escaped) backslash, then comment
   > ba0\\\#w* # (escaped) backslash, escaped comment character, then comment
   > ba1\\\\#* # (escaped) backslashes, then comment
   > foo\#b* # escaped comment character
   > quux\## escaped comment character at end of name
   > quu0[\#]# escaped comment character inside [...]
   > EOF
   $ hg status
   A dir/b.o
   ? .hgignore
   ? ba1\\wat (no-windows !)
   ? baz\wat (no-windows !)
   ? quu0\ (no-windows !)
 
   $ rm 'foo#bar' 'quux#' 'quu0#'
 #if no-windows
   $ rm 'baz\' 'baz\wat' 'ba0\#wat' 'ba1\\' 'ba1\\wat' 'quu0\'
 #endif
 
 Check that '^\.' does not ignore the root directory:
 
   $ echo "^\." > .hgignore
   $ hg status
   A dir/b.o
   ? a.c
   ? a.o
   ? dir/c.o
   ? syntax
 
 Test that patterns from ui.ignore options are read:
 
   $ echo > .hgignore
   $ cat >> $HGRCPATH << EOF
   > [ui]
   > ignore.other = $TESTTMP/ignorerepo/.hg/testhgignore
   > EOF
   $ echo "glob:**.o" > .hg/testhgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? syntax
 
 empty out testhgignore
   $ echo > .hg/testhgignore
 
 Test relative ignore path (issue4473):
 
   $ cat >> $HGRCPATH << EOF
   > [ui]
   > ignore.relative = .hg/testhgignorerel
   > EOF
   $ echo "glob:*.o" > .hg/testhgignorerel
   $ cd dir
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? syntax
   $ hg debugignore
   <includematcher includes='.*\\.o(?:/|$)'>
 
   $ cd ..
   $ echo > .hg/testhgignorerel
   $ echo "syntax: glob" > .hgignore
   $ echo "re:.*\.o" >> .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? syntax
 
   $ echo "syntax: invalid" > .hgignore
   $ hg status
   $TESTTMP/ignorerepo/.hgignore: ignoring invalid syntax 'invalid'
   A dir/b.o
   ? .hgignore
   ? a.c
   ? a.o
   ? dir/c.o
   ? syntax
 
   $ echo "syntax: glob" > .hgignore
   $ echo "*.o" >> .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? syntax
 
   $ echo "relglob:syntax*" > .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? a.o
   ? dir/c.o
 
   $ echo "relglob:*" > .hgignore
   $ hg status
   A dir/b.o
 
   $ cd dir
   $ hg status .
   A b.o
 
   $ hg debugignore
   <includematcher includes='.*(?:/|$)'>
 
   $ hg debugignore b.o
   b.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: '*') (glob)
 
   $ cd ..
 
 Check patterns that match only the directory
 
 "(fsmonitor !)" below assumes that fsmonitor is enabled with
 "walk_on_invalidate = false" (default), which doesn't involve
 re-walking whole repository at detection of .hgignore change.
 
   $ echo "^dir\$" > .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? a.o
   ? dir/c.o (fsmonitor !)
   ? syntax
 
 Check recursive glob pattern matches no directories (dir/**/c.o matches dir/c.o)
 
   $ echo "syntax: glob" > .hgignore
   $ echo "dir/**/c.o" >> .hgignore
   $ touch dir/c.o
   $ mkdir dir/subdir
   $ touch dir/subdir/c.o
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? a.o
   ? syntax
   $ hg debugignore a.c
   a.c is not ignored
   $ hg debugignore dir/c.o
   dir/c.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 2: 'dir/**/c.o') (glob)
 
 Check rooted globs
 
   $ hg purge --all --config extensions.purge=
   $ echo "syntax: rootglob" > .hgignore
   $ echo "a/*.ext" >> .hgignore
   $ for p in a b/a aa; do mkdir -p $p; touch $p/b.ext; done
   $ hg status -A 'set:**.ext'
   ? aa/b.ext
   ? b/a/b.ext
   I a/b.ext
 
 Check using 'include:' in ignore file
 
   $ hg purge --all --config extensions.purge=
   $ touch foo.included
 
   $ echo ".*.included" > otherignore
   $ hg status -I "include:otherignore"
   ? foo.included
 
   $ echo "include:otherignore" >> .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? otherignore
 
 Check recursive uses of 'include:'
 
   $ echo "include:nested/ignore" >> otherignore
   $ mkdir nested nested/more
   $ echo "glob:*ignore" > nested/ignore
   $ echo "rootglob:a" >> nested/ignore
   $ touch a nested/a nested/more/a
   $ hg status
   A dir/b.o
   ? nested/a
   ? nested/more/a
   $ rm a nested/a nested/more/a
 
   $ cp otherignore goodignore
   $ echo "include:badignore" >> otherignore
   $ hg status
   skipping unreadable pattern file 'badignore': $ENOENT$
   A dir/b.o
 
   $ mv goodignore otherignore
 
 Check using 'include:' while in a non-root directory
 
   $ cd ..
   $ hg -R ignorerepo status
   A dir/b.o
   $ cd ignorerepo
 
 Check including subincludes
 
   $ hg revert -q --all
   $ hg purge --all --config extensions.purge=
   $ echo ".hgignore" > .hgignore
   $ mkdir dir1 dir2
   $ touch dir1/file1 dir1/file2 dir2/file1 dir2/file2
   $ echo "subinclude:dir2/.hgignore" >> .hgignore
   $ echo "glob:file*2" > dir2/.hgignore
   $ hg status
   ? dir1/file1
   ? dir1/file2
   ? dir2/file1
 
 Check including subincludes with other patterns
 
   $ echo "subinclude:dir1/.hgignore" >> .hgignore
 
   $ mkdir dir1/subdir
   $ touch dir1/subdir/file1
   $ echo "rootglob:f?le1" > dir1/.hgignore
   $ hg status
   ? dir1/file2
   ? dir1/subdir/file1
   ? dir2/file1
   $ rm dir1/subdir/file1
 
   $ echo "regexp:f.le1" > dir1/.hgignore
   $ hg status
   ? dir1/file2
   ? dir2/file1
 
 Check multiple levels of sub-ignores
 
   $ touch dir1/subdir/subfile1 dir1/subdir/subfile3 dir1/subdir/subfile4
   $ echo "subinclude:subdir/.hgignore" >> dir1/.hgignore
   $ echo "glob:subfil*3" >> dir1/subdir/.hgignore
 
   $ hg status
   ? dir1/file2
   ? dir1/subdir/subfile4
   ? dir2/file1
 
 Check include subignore at the same level
 
   $ mv dir1/subdir/.hgignore dir1/.hgignoretwo
   $ echo "regexp:f.le1" > dir1/.hgignore
   $ echo "subinclude:.hgignoretwo" >> dir1/.hgignore
   $ echo "glob:file*2" > dir1/.hgignoretwo
 
   $ hg status | grep file2
   [1]
   $ hg debugignore dir1/file2
   dir1/file2 is ignored
   (ignore rule in dir2/.hgignore, line 1: 'file*2')
 
 #if windows
 
 Windows paths are accepted on input
 
   $ rm dir1/.hgignore
   $ echo "dir1/file*" >> .hgignore
   $ hg debugignore "dir1\file2"
   dir1/file2 is ignored
   (ignore rule in $TESTTMP\ignorerepo\.hgignore, line 4: 'dir1/file*')
   $ hg up -qC .
 
 #endif
 
 #if dirstate-v2 rust
 
 Check the hash of ignore patterns written in the dirstate
 This is an optimization that is only relevant when using the Rust extensions
 
   $ cat_filename_and_hash () {
   >     for i in "$@"; do
   >         printf "$i "
   >         cat "$i" | "$TESTDIR"/f --raw-sha1 | sed 's/^raw-sha1=//'
   >     done
   > }
   $ hg status > /dev/null
   $ cat_filename_and_hash .hg/testhgignore .hg/testhgignorerel .hgignore dir2/.hgignore dir1/.hgignore dir1/.hgignoretwo | $TESTDIR/f --sha1
   sha1=c0beb296395d48ced8e14f39009c4ea6e409bfe6
   $ hg debugstate --docket | grep ignore
   ignore pattern hash: c0beb296395d48ced8e14f39009c4ea6e409bfe6
 
   $ echo rel > .hg/testhgignorerel
   $ hg status > /dev/null
   $ cat_filename_and_hash .hg/testhgignore .hg/testhgignorerel .hgignore dir2/.hgignore dir1/.hgignore dir1/.hgignoretwo | $TESTDIR/f --sha1
   sha1=b8e63d3428ec38abc68baa27631516d5ec46b7fa
   $ hg debugstate --docket | grep ignore
   ignore pattern hash: b8e63d3428ec38abc68baa27631516d5ec46b7fa
   $ cd ..
 
 Check that the hash depends on the source of the hgignore patterns
 (otherwise the context is lost and things like subinclude are cached improperly)
 
   $ hg init ignore-collision
   $ cd ignore-collision
   $ echo > .hg/testhgignorerel
 
   $ mkdir dir1/ dir1/subdir
   $ touch dir1/subdir/f dir1/subdir/ignored1
   $ echo 'ignored1' > dir1/.hgignore
 
   $ mkdir dir2 dir2/subdir
   $ touch dir2/subdir/f dir2/subdir/ignored2
   $ echo 'ignored2' > dir2/.hgignore
   $ echo 'subinclude:dir2/.hgignore' >> .hgignore
   $ echo 'subinclude:dir1/.hgignore' >> .hgignore
 
   $ hg commit -Aqm_
 
   $ > dir1/.hgignore
   $ echo 'ignored' > dir2/.hgignore
   $ echo 'ignored1' >> dir2/.hgignore
   $ hg status
   M dir1/.hgignore
   M dir2/.hgignore
   ? dir1/subdir/ignored1
 
 #endif