match: simplify the rust-side file pattern kind parsing

There's no need to add the ':' characters if
we're simply pattern matching against constants next.

rust/hg-core/src/filepatterns.rs

@@ -1,874 +1,874 b''
 // 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"[^/]*")];
 
 #[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 single exact path relative to repository root
     FilePath,
     /// 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)
     RootFilesIn,
     /// 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
 pub 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(
+pub fn parse_pattern_syntax_kind(
     kind: &[u8],
 ) -> Result<PatternSyntax, PatternError> {
     match kind {
-        b"re:" => Ok(PatternSyntax::Regexp),
-        b"path:" => Ok(PatternSyntax::Path),
-        b"filepath:" => Ok(PatternSyntax::FilePath),
-        b"relpath:" => Ok(PatternSyntax::RelPath),
-        b"rootfilesin:" => Ok(PatternSyntax::RootFilesIn),
-        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),
+        b"re" => Ok(PatternSyntax::Regexp),
+        b"path" => Ok(PatternSyntax::Path),
+        b"filepath" => Ok(PatternSyntax::FilePath),
+        b"relpath" => Ok(PatternSyntax::RelPath),
+        b"rootfilesin" => Ok(PatternSyntax::RootFilesIn),
+        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, glob_suffix: &[u8]) -> 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();
             }
             match FLAG_RE.find(pattern) {
                 Some(mat) => {
                     let s = mat.start();
                     let e = mat.end();
                     [
                         &b"(?"[..],
                         &pattern[s + 2..e - 1],
                         &b":"[..],
                         if pattern[e] == b'^'
                             || pattern[e] == b'*'
                             || pattern[e..].starts_with(b".*")
                         {
                             &b""[..]
                         } else {
                             &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::RootFilesIn => {
             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(_)
         | PatternSyntax::FilePath => 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,
     glob_suffix: &[u8],
 ) -> Result<Option<Vec<u8>>, PatternError> {
     let IgnorePattern {
         pattern, syntax, ..
     } = entry;
     let pattern = match syntax {
         PatternSyntax::RootGlob
         | PatternSyntax::Path
         | PatternSyntax::RelGlob
         | PatternSyntax::RelPath
         | PatternSyntax::RootFilesIn => normalize_path_bytes(pattern),
         PatternSyntax::Include | PatternSyntax::SubInclude => {
             return Err(PatternError::NonRegexPattern(entry.clone()))
         }
         _ => pattern.to_owned(),
     };
     let is_simple_rootglob = *syntax == PatternSyntax::RootGlob
         && !pattern.iter().any(|b| GLOB_SPECIAL_CHARACTERS.contains(b));
     if is_simple_rootglob || syntax == &PatternSyntax::FilePath {
         Ok(None)
     } else {
         let mut entry = entry.clone();
         entry.pattern = pattern;
         Ok(Some(_build_single_regex(&entry, glob_suffix)))
     }
 }
 
 lazy_static! {
     static ref SYNTAXES: FastHashMap<&'static [u8], PatternSyntax> = {
         let mut m = FastHashMap::default();
 
         m.insert(b"re:".as_ref(), PatternSyntax::Regexp);
         m.insert(b"regexp:".as_ref(), PatternSyntax::Regexp);
         m.insert(b"path:".as_ref(), PatternSyntax::Path);
         m.insert(b"filepath:".as_ref(), PatternSyntax::FilePath);
         m.insert(b"relpath:".as_ref(), PatternSyntax::RelPath);
         m.insert(b"rootfilesin:".as_ref(), PatternSyntax::RootFilesIn);
         m.insert(b"relglob:".as_ref(), PatternSyntax::RelGlob);
         m.insert(b"relre:".as_ref(), PatternSyntax::RelRegexp);
         m.insert(b"glob:".as_ref(), PatternSyntax::Glob);
         m.insert(b"rootglob:".as_ref(), PatternSyntax::RootGlob);
         m.insert(b"include:".as_ref(), PatternSyntax::Include);
         m.insert(b"subinclude:".as_ref(), PatternSyntax::SubInclude);
 
         m
     };
 }
 
 #[derive(Debug)]
 pub enum PatternFileWarning {
     /// (file path, syntax bytes)
     InvalidSyntax(PathBuf, Vec<u8>),
     /// File path
     NoSuchFile(PathBuf),
 }
 
 pub fn parse_one_pattern(
     pattern: &[u8],
     source: &Path,
     default: PatternSyntax,
     normalize: bool,
 ) -> IgnorePattern {
     let mut pattern_bytes: &[u8] = pattern;
     let mut syntax = default;
 
     for (s, val) in SYNTAXES.iter() {
         if let Some(rest) = pattern_bytes.drop_prefix(s) {
             syntax = val.clone();
             pattern_bytes = rest;
             break;
         }
     }
 
     let pattern = match syntax {
         PatternSyntax::RootGlob
         | PatternSyntax::Path
         | PatternSyntax::Glob
         | PatternSyntax::RelGlob
         | PatternSyntax::RelPath
         | PatternSyntax::RootFilesIn
             if normalize =>
         {
             normalize_path_bytes(pattern_bytes)
         }
         _ => pattern_bytes.to_vec(),
     };
 
     IgnorePattern {
         syntax,
         pattern,
         source: source.to_owned(),
     }
 }
 
 pub fn parse_pattern_file_contents(
     lines: &[u8],
     file_path: &Path,
     default_syntax_override: Option<PatternSyntax>,
     warn: bool,
     relativize: 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(PatternSyntax::RelRegexp);
 
     for mut line in lines.split(|c| *c == b'\n') {
         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 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(parsed) =
                 SYNTAXES.get([syntax, &b":"[..]].concat().as_slice())
             {
                 current_syntax = parsed.clone();
             } else if warn {
                 warnings.push(PatternFileWarning::InvalidSyntax(
                     file_path.to_owned(),
                     syntax.to_owned(),
                 ));
             }
         } else {
             let pattern = parse_one_pattern(
                 line,
                 file_path,
                 current_syntax.clone(),
                 false,
             );
             inputs.push(if relativize {
                 pattern.to_relative()
             } else {
                 pattern
             })
         }
     }
     Ok((inputs, warnings))
 }
 
 pub fn parse_pattern_args(
     patterns: Vec<Vec<u8>>,
     cwd: &Path,
     root: &Path,
 ) -> Result<Vec<IgnorePattern>, HgPathError> {
     let mut ignore_patterns: Vec<IgnorePattern> = Vec::new();
     for pattern in patterns {
         let pattern = parse_one_pattern(
             &pattern,
             Path::new("<args>"),
             PatternSyntax::RelPath,
             true,
         );
         match pattern.syntax {
             PatternSyntax::RelGlob | PatternSyntax::RelPath => {
                 let name = get_path_from_bytes(&pattern.pattern);
                 let canon = canonical_path(root, cwd, name)?;
                 ignore_patterns.push(IgnorePattern {
                     syntax: pattern.syntax,
                     pattern: get_bytes_from_path(canon),
                     source: pattern.source,
                 })
             }
             _ => ignore_patterns.push(pattern.to_owned()),
         };
     }
     Ok(ignore_patterns)
 }
 
 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, true)
         }
         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 fn to_relative(self) -> Self {
         let Self {
             syntax,
             pattern,
             source,
         } = self;
         Self {
             syntax: match syntax {
                 PatternSyntax::Regexp => PatternSyntax::RelRegexp,
                 PatternSyntax::Glob => PatternSyntax::RelGlob,
                 x => x,
             },
             pattern,
             source,
         }
     }
 }
 
 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(source_root);
 
         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).map(|mut p| {
                 if !p.is_empty() {
                     p.push_byte(b'/');
                 }
                 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<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,
                 true,
             )
             .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,
                 true,
             )
             .unwrap()
             .0,
             vec![]
         );
         let lines = b"glob:**.o";
         assert_eq!(
             parse_pattern_file_contents(
                 lines,
                 Path::new("file_path"),
                 None,
                 false,
                 true,
             )
             .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("")
                 ),
                 b"(?:/|$)"
             )
             .unwrap(),
             Some(br"(?:.*/)?rust/target(?:/|$)".to_vec()),
         );
         assert_eq!(
             build_single_regex(
                 &IgnorePattern::new(
                     PatternSyntax::Regexp,
                     br"rust/target/\d+",
                     Path::new("")
                 ),
                 b"(?:/|$)"
             )
             .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("")
                 ),
                 b"(?:/|$)"
             )
             .unwrap(),
             None,
         );
         assert_eq!(
             build_single_regex(
                 &IgnorePattern::new(
                     PatternSyntax::RootGlob,
                     b"whatever",
                     Path::new("")
                 ),
                 b"(?:/|$)"
             )
             .unwrap(),
             None,
         );
         assert_eq!(
             build_single_regex(
                 &IgnorePattern::new(
                     PatternSyntax::RootGlob,
                     b"*.o",
                     Path::new("")
                 ),
                 b"(?:/|$)"
             )
             .unwrap(),
             Some(br"[^/]*\.o(?:/|$)".to_vec()),
         );
     }
 
     #[test]
     fn test_build_single_relregex() {
         assert_eq!(
             build_single_regex(
                 &IgnorePattern::new(
                     PatternSyntax::RelRegexp,
                     b"^ba{2}r",
                     Path::new("")
                 ),
                 b"(?:/|$)"
             )
             .unwrap(),
             Some(b"^ba{2}r".to_vec()),
         );
         assert_eq!(
             build_single_regex(
                 &IgnorePattern::new(
                     PatternSyntax::RelRegexp,
                     b"ba{2}r",
                     Path::new("")
                 ),
                 b"(?:/|$)"
             )
             .unwrap(),
             Some(b".*ba{2}r".to_vec()),
         );
         assert_eq!(
             build_single_regex(
                 &IgnorePattern::new(
                     PatternSyntax::RelRegexp,
                     b"(?ia)ba{2}r",
                     Path::new("")
                 ),
                 b"(?:/|$)"
             )
             .unwrap(),
             Some(b"(?ia:.*ba{2}r)".to_vec()),
         );
         assert_eq!(
             build_single_regex(
                 &IgnorePattern::new(
                     PatternSyntax::RelRegexp,
                     b"(?ia)^ba{2}r",
                     Path::new("")
                 ),
                 b"(?:/|$)"
             )
             .unwrap(),
             Some(b"(?ia:^ba{2}r)".to_vec()),
         );
     }
 }

rust/hg-core/src/lib.rs

@@ -1,144 +1,144 b''
 // Copyright 2018-2020 Georges Racinet <[e-mail]>
 //           and Mercurial contributors
 //
 // 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 mod errors;
 pub mod narrow;
 pub mod sparse;
 pub use ancestors::{AncestorsIterator, MissingAncestors};
 pub mod dirstate;
 pub mod dirstate_tree;
 pub mod discovery;
 pub mod exit_codes;
 pub mod requirements;
 pub mod testing; // unconditionally built, for use from integration tests
 pub use dirstate::{
     dirs_multiset::{DirsMultiset, DirsMultisetIter},
     status::{
         BadMatch, BadType, DirstateStatus, HgPathCow, StatusError,
         StatusOptions,
     },
     DirstateEntry, DirstateParents, EntryState,
 };
 pub mod copy_tracing;
 pub mod filepatterns;
 pub mod matchers;
 pub mod repo;
 pub mod revlog;
 pub use revlog::*;
 pub mod checkexec;
 pub mod config;
 pub mod lock;
 pub mod logging;
 pub mod operations;
 pub mod revset;
 pub mod utils;
 pub mod vfs;
 
 use crate::utils::hg_path::{HgPathBuf, HgPathError};
 pub use filepatterns::{
-    parse_pattern_syntax, read_pattern_file, IgnorePattern,
+    parse_pattern_syntax_kind, read_pattern_file, IgnorePattern,
     PatternFileWarning, PatternSyntax,
 };
 use std::collections::HashMap;
 use std::fmt;
 use twox_hash::RandomXxHashBuilder64;
 
 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>;
 
 // TODO: should this be the default `FastHashMap` for all of hg-core, not just
 // dirstate_tree? How does XxHash compare with AHash, hashbrown’s default?
 pub type FastHashbrownMap<K, V> =
     hashbrown::HashMap<K, V, RandomXxHashBuilder64>;
 
 #[derive(Debug, PartialEq)]
 pub enum DirstateMapError {
     PathNotFound(HgPathBuf),
     InvalidPath(HgPathError),
 }
 
 impl From<HgPathError> for DirstateMapError {
     fn from(error: HgPathError) -> Self {
         Self::InvalidPath(error)
     }
 }
 
 impl fmt::Display for DirstateMapError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             DirstateMapError::PathNotFound(_) => {
                 f.write_str("expected a value, found none")
             }
             DirstateMapError::InvalidPath(path_error) => path_error.fmt(f),
         }
     }
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum DirstateError {
     Map(DirstateMapError),
     Common(errors::HgError),
 }
 
 impl From<HgPathError> for DirstateError {
     fn from(error: HgPathError) -> Self {
         Self::Map(DirstateMapError::InvalidPath(error))
     }
 }
 
 impl fmt::Display for DirstateError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             DirstateError::Map(error) => error.fmt(f),
             DirstateError::Common(error) => error.fmt(f),
         }
     }
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum PatternError {
     #[from]
     Path(HgPathError),
     UnsupportedSyntax(String),
     UnsupportedSyntaxInFile(String, String, usize),
     TooLong(usize),
     #[from]
     IO(std::io::Error),
     /// Needed a pattern that can be turned into a regex but got one that
     /// can't. This should only happen through programmer error.
     NonRegexPattern(IgnorePattern),
 }
 
 impl fmt::Display for PatternError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             PatternError::UnsupportedSyntax(syntax) => {
                 write!(f, "Unsupported syntax {}", syntax)
             }
             PatternError::UnsupportedSyntaxInFile(syntax, file_path, line) => {
                 write!(
                     f,
                     "{}:{}: unsupported syntax {}",
                     file_path, line, syntax
                 )
             }
             PatternError::TooLong(size) => {
                 write!(f, "matcher pattern is too long ({} bytes)", size)
             }
             PatternError::IO(error) => error.fmt(f),
             PatternError::Path(error) => error.fmt(f),
             PatternError::NonRegexPattern(pattern) => {
                 write!(f, "'{:?}' cannot be turned into a regex", pattern)
             }
         }
     }
 }

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

@@ -1,328 +1,324 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, exceptions::FallbackError};
 use cpython::{
     exc::ValueError, ObjectProtocol, PyBool, PyBytes, PyErr, PyList, PyObject,
     PyResult, PyTuple, Python, PythonObject, ToPyObject,
 };
 use hg::dirstate::status::StatusPath;
 use hg::matchers::{
     DifferenceMatcher, IntersectionMatcher, Matcher, NeverMatcher,
     PatternMatcher, UnionMatcher,
 };
 use hg::{
     matchers::{AlwaysMatcher, FileMatcher, IncludeMatcher},
-    parse_pattern_syntax,
+    parse_pattern_syntax_kind,
     utils::{
         files::{get_bytes_from_path, get_path_from_bytes},
         hg_path::{HgPath, HgPathBuf},
     },
     BadMatch, DirstateStatus, IgnorePattern, PatternError, PatternFileWarning,
     StatusError, StatusOptions,
 };
 use std::borrow::Borrow;
 
 fn collect_status_path_list(py: Python, paths: &[StatusPath<'_>]) -> PyList {
     collect_pybytes_list(py, paths.iter().map(|item| &*item.path))
 }
 
 /// This will be useless once trait impls for collection are added to `PyBytes`
 /// upstream.
 fn collect_pybytes_list(
     py: Python,
     iter: impl Iterator<Item = impl AsRef<HgPath>>,
 ) -> PyList {
     let list = PyList::new(py, &[]);
 
     for path in iter {
         list.append(
             py,
             PyBytes::new(py, path.as_ref().as_bytes()).into_object(),
         )
     }
 
     list
 }
 
 fn collect_bad_matches(
     py: Python,
     collection: &[(impl AsRef<HgPath>, BadMatch)],
 ) -> PyResult<PyList> {
     let list = PyList::new(py, &[]);
 
     let os = py.import("os")?;
     let get_error_message = |code: i32| -> PyResult<_> {
         os.call(
             py,
             "strerror",
             PyTuple::new(py, &[code.to_py_object(py).into_object()]),
             None,
         )
     };
 
     for (path, bad_match) in collection.iter() {
         let message = match bad_match {
             BadMatch::OsError(code) => get_error_message(*code)?,
             BadMatch::BadType(bad_type) => {
                 format!("unsupported file type (type is {})", bad_type)
                     .to_py_object(py)
                     .into_object()
             }
         };
         list.append(
             py,
             (PyBytes::new(py, path.as_ref().as_bytes()), message)
                 .to_py_object(py)
                 .into_object(),
         )
     }
 
     Ok(list)
 }
 
 fn handle_fallback(py: Python, err: StatusError) -> PyErr {
     match err {
         StatusError::Pattern(e) => {
             let as_string = e.to_string();
             log::trace!("Rust status fallback: `{}`", &as_string);
 
             PyErr::new::<FallbackError, _>(py, &as_string)
         }
         e => PyErr::new::<ValueError, _>(py, e.to_string()),
     }
 }
 
 pub fn status_wrapper(
     py: Python,
     dmap: DirstateMap,
     matcher: PyObject,
     root_dir: PyObject,
     ignore_files: PyList,
     check_exec: bool,
     list_clean: bool,
     list_ignored: bool,
     list_unknown: bool,
     collect_traversed_dirs: bool,
 ) -> PyResult<PyTuple> {
     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 mut dmap = dmap.get_inner_mut(py);
 
     let ignore_files: PyResult<Vec<_>> = ignore_files
         .iter(py)
         .map(|b| {
             let file = b.extract::<PyBytes>(py)?;
             Ok(get_path_from_bytes(file.data(py)).to_owned())
         })
         .collect();
     let ignore_files = ignore_files?;
     // The caller may call `copymap.items()` separately
     let list_copies = false;
 
     let after_status = |res: Result<(DirstateStatus<'_>, _), StatusError>| {
         let (status_res, warnings) =
             res.map_err(|e| handle_fallback(py, e))?;
         build_response(py, status_res, warnings)
     };
 
     let matcher = extract_matcher(py, matcher)?;
     dmap.with_status(
         &*matcher,
         root_dir.to_path_buf(),
         ignore_files,
         StatusOptions {
             check_exec,
             list_clean,
             list_ignored,
             list_unknown,
             list_copies,
             collect_traversed_dirs,
         },
         after_status,
     )
 }
 
 fn collect_kindpats(
     py: Python,
     matcher: PyObject,
 ) -> PyResult<Vec<IgnorePattern>> {
     matcher
         .getattr(py, "_kindpats")?
         .iter(py)?
         .map(|k| {
             let k = k?;
-            let syntax = parse_pattern_syntax(
-                &[
-                    k.get_item(py, 0)?.extract::<PyBytes>(py)?.data(py),
-                    &b":"[..],
-                ]
-                .concat(),
+            let syntax = parse_pattern_syntax_kind(
+                k.get_item(py, 0)?.extract::<PyBytes>(py)?.data(py),
             )
             .map_err(|e| handle_fallback(py, StatusError::Pattern(e)))?;
             let pattern = k.get_item(py, 1)?.extract::<PyBytes>(py)?;
             let pattern = pattern.data(py);
             let source = k.get_item(py, 2)?.extract::<PyBytes>(py)?;
             let source = get_path_from_bytes(source.data(py));
             let new = IgnorePattern::new(syntax, pattern, source);
             Ok(new)
         })
         .collect()
 }
 
 /// Transform a Python matcher into a Rust matcher.
 fn extract_matcher(
     py: Python,
     matcher: PyObject,
 ) -> PyResult<Box<dyn Matcher + Sync>> {
     let tampered = matcher
         .call_method(py, "was_tampered_with", PyTuple::empty(py), None)?
         .extract::<PyBool>(py)?
         .is_true();
     if tampered {
         return Err(handle_fallback(
             py,
             StatusError::Pattern(PatternError::UnsupportedSyntax(
                 "Pattern matcher was tampered with!".to_string(),
             )),
         ));
     };
     match matcher.get_type(py).name(py).borrow() {
         "alwaysmatcher" => Ok(Box::new(AlwaysMatcher)),
         "nevermatcher" => Ok(Box::new(NeverMatcher)),
         "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 files = files?;
             let file_matcher = FileMatcher::new(files)
                 .map_err(|e| PyErr::new::<ValueError, _>(py, e.to_string()))?;
             Ok(Box::new(file_matcher))
         }
         "includematcher" => {
             // Get the patterns from Python even though most of them are
             // redundant with those we will parse later on, as they include
             // those passed from the command line.
             let ignore_patterns = collect_kindpats(py, matcher)?;
 
             let matcher = IncludeMatcher::new(ignore_patterns)
                 .map_err(|e| handle_fallback(py, e.into()))?;
 
             Ok(Box::new(matcher))
         }
         "unionmatcher" => {
             let matchers: PyResult<Vec<_>> = matcher
                 .getattr(py, "_matchers")?
                 .iter(py)?
                 .map(|py_matcher| extract_matcher(py, py_matcher?))
                 .collect();
 
             Ok(Box::new(UnionMatcher::new(matchers?)))
         }
         "intersectionmatcher" => {
             let m1 = extract_matcher(py, matcher.getattr(py, "_m1")?)?;
             let m2 = extract_matcher(py, matcher.getattr(py, "_m2")?)?;
 
             Ok(Box::new(IntersectionMatcher::new(m1, m2)))
         }
         "differencematcher" => {
             let m1 = extract_matcher(py, matcher.getattr(py, "_m1")?)?;
             let m2 = extract_matcher(py, matcher.getattr(py, "_m2")?)?;
 
             Ok(Box::new(DifferenceMatcher::new(m1, m2)))
         }
         "patternmatcher" => {
             let patterns = collect_kindpats(py, matcher)?;
 
             let matcher = PatternMatcher::new(patterns)
                 .map_err(|e| handle_fallback(py, e.into()))?;
 
             Ok(Box::new(matcher))
         }
         e => Err(PyErr::new::<FallbackError, _>(
             py,
             format!("Unsupported matcher {}", e),
         )),
     }
 }
 
 fn build_response(
     py: Python,
     status_res: DirstateStatus,
     warnings: Vec<PatternFileWarning>,
 ) -> PyResult<PyTuple> {
     let modified = collect_status_path_list(py, &status_res.modified);
     let added = collect_status_path_list(py, &status_res.added);
     let removed = collect_status_path_list(py, &status_res.removed);
     let deleted = collect_status_path_list(py, &status_res.deleted);
     let clean = collect_status_path_list(py, &status_res.clean);
     let ignored = collect_status_path_list(py, &status_res.ignored);
     let unknown = collect_status_path_list(py, &status_res.unknown);
     let unsure = collect_status_path_list(py, &status_res.unsure);
     let bad = collect_bad_matches(py, &status_res.bad)?;
     let traversed = collect_pybytes_list(py, status_res.traversed.iter());
     let dirty = status_res.dirty.to_py_object(py);
     let py_warnings = PyList::new(py, &[]);
     for warning in warnings.iter() {
         // We use duck-typing on the Python side for dispatch, good enough for
         // now.
         match warning {
             PatternFileWarning::InvalidSyntax(file, syn) => {
                 py_warnings.append(
                     py,
                     (
                         PyBytes::new(py, &get_bytes_from_path(file)),
                         PyBytes::new(py, syn),
                     )
                         .to_py_object(py)
                         .into_object(),
                 );
             }
             PatternFileWarning::NoSuchFile(file) => py_warnings.append(
                 py,
                 PyBytes::new(py, &get_bytes_from_path(file)).into_object(),
             ),
         }
     }
 
     Ok(PyTuple::new(
         py,
         &[
             unsure.into_object(),
             modified.into_object(),
             added.into_object(),
             removed.into_object(),
             deleted.into_object(),
             clean.into_object(),
             ignored.into_object(),
             unknown.into_object(),
             py_warnings.into_object(),
             bad.into_object(),
             traversed.into_object(),
             dirty.into_object(),
         ][..],
     ))
 }