rhg: fallback to slow path on invalid patterns in hgignore

rust/rhg/src/error.rs

@@ -1,290 +1,295 b''
 use crate::ui::utf8_to_local;
 use crate::ui::UiError;
 use crate::NoRepoInCwdError;
 use format_bytes::format_bytes;
 use hg::config::{ConfigError, ConfigParseError, ConfigValueParseError};
 use hg::dirstate_tree::on_disk::DirstateV2ParseError;
 use hg::errors::HgError;
 use hg::exit_codes;
 use hg::repo::RepoError;
 use hg::revlog::revlog::RevlogError;
 use hg::sparse::SparseConfigError;
 use hg::utils::files::get_bytes_from_path;
 use hg::{DirstateError, DirstateMapError, StatusError};
 use std::convert::From;
 
 /// The kind of command error
 #[derive(Debug)]
 pub enum CommandError {
     /// Exit with an error message and "standard" failure exit code.
     Abort {
         message: Vec<u8>,
         detailed_exit_code: exit_codes::ExitCode,
         hint: Option<Vec<u8>>,
     },
 
     /// Exit with a failure exit code but no message.
     Unsuccessful,
 
     /// Encountered something (such as a CLI argument, repository layout, …)
     /// not supported by this version of `rhg`. Depending on configuration
     /// `rhg` may attempt to silently fall back to Python-based `hg`, which
     /// may or may not support this feature.
     UnsupportedFeature { message: Vec<u8> },
     /// The fallback executable does not exist (or has some other problem if
     /// we end up being more precise about broken fallbacks).
     InvalidFallback { path: Vec<u8>, err: String },
 }
 
 impl CommandError {
     pub fn abort(message: impl AsRef<str>) -> Self {
         CommandError::abort_with_exit_code(message, exit_codes::ABORT)
     }
 
     pub fn abort_with_exit_code(
         message: impl AsRef<str>,
         detailed_exit_code: exit_codes::ExitCode,
     ) -> Self {
         CommandError::Abort {
             // TODO: bytes-based (instead of Unicode-based) formatting
             // of error messages to handle non-UTF-8 filenames etc:
             // https://www.mercurial-scm.org/wiki/EncodingStrategy#Mixing_output
             message: utf8_to_local(message.as_ref()).into(),
             detailed_exit_code: detailed_exit_code,
             hint: None,
         }
     }
 
     pub fn abort_with_exit_code_and_hint(
         message: impl AsRef<str>,
         detailed_exit_code: exit_codes::ExitCode,
         hint: Option<impl AsRef<str>>,
     ) -> Self {
         CommandError::Abort {
             message: utf8_to_local(message.as_ref()).into(),
             detailed_exit_code,
             hint: hint.map(|h| utf8_to_local(h.as_ref()).into()),
         }
     }
 
     pub fn abort_with_exit_code_bytes(
         message: impl AsRef<[u8]>,
         detailed_exit_code: exit_codes::ExitCode,
     ) -> Self {
         // TODO: use this everywhere it makes sense instead of the string
         // version.
         CommandError::Abort {
             message: message.as_ref().into(),
             detailed_exit_code,
             hint: None,
         }
     }
 
     pub fn unsupported(message: impl AsRef<str>) -> Self {
         CommandError::UnsupportedFeature {
             message: utf8_to_local(message.as_ref()).into(),
         }
     }
 }
 
 /// For now we don’t differenciate between invalid CLI args and valid for `hg`
 /// but not supported yet by `rhg`.
 impl From<clap::Error> for CommandError {
     fn from(error: clap::Error) -> Self {
         CommandError::unsupported(error.to_string())
     }
 }
 
 impl From<HgError> for CommandError {
     fn from(error: HgError) -> Self {
         match error {
             HgError::UnsupportedFeature(message) => {
                 CommandError::unsupported(message)
             }
             HgError::CensoredNodeError => {
                 CommandError::unsupported("Encountered a censored node")
             }
             HgError::Abort {
                 message,
                 detailed_exit_code,
                 hint,
             } => CommandError::abort_with_exit_code_and_hint(
                 message,
                 detailed_exit_code,
                 hint,
             ),
             _ => CommandError::abort(error.to_string()),
         }
     }
 }
 
 impl From<ConfigValueParseError> for CommandError {
     fn from(error: ConfigValueParseError) -> Self {
         CommandError::abort_with_exit_code(
             error.to_string(),
             exit_codes::CONFIG_ERROR_ABORT,
         )
     }
 }
 
 impl From<UiError> for CommandError {
     fn from(_error: UiError) -> Self {
         // If we already failed writing to stdout or stderr,
         // writing an error message to stderr about it would be likely to fail
         // too.
         CommandError::abort("")
     }
 }
 
 impl From<RepoError> for CommandError {
     fn from(error: RepoError) -> Self {
         match error {
             RepoError::NotFound { at } => {
                 CommandError::abort_with_exit_code_bytes(
                     format_bytes!(
                         b"abort: repository {} not found",
                         get_bytes_from_path(at)
                     ),
                     exit_codes::ABORT,
                 )
             }
             RepoError::ConfigParseError(error) => error.into(),
             RepoError::Other(error) => error.into(),
         }
     }
 }
 
 impl<'a> From<&'a NoRepoInCwdError> for CommandError {
     fn from(error: &'a NoRepoInCwdError) -> Self {
         let NoRepoInCwdError { cwd } = error;
         CommandError::abort_with_exit_code_bytes(
             format_bytes!(
                 b"abort: no repository found in '{}' (.hg not found)!",
                 get_bytes_from_path(cwd)
             ),
             exit_codes::ABORT,
         )
     }
 }
 
 impl From<ConfigError> for CommandError {
     fn from(error: ConfigError) -> Self {
         match error {
             ConfigError::Parse(error) => error.into(),
             ConfigError::Other(error) => error.into(),
         }
     }
 }
 
 impl From<ConfigParseError> for CommandError {
     fn from(error: ConfigParseError) -> Self {
         let ConfigParseError {
             origin,
             line,
             message,
         } = error;
         let line_message = if let Some(line_number) = line {
             format_bytes!(b":{}", line_number.to_string().into_bytes())
         } else {
             Vec::new()
         };
         CommandError::abort_with_exit_code_bytes(
             format_bytes!(
                 b"config error at {}{}: {}",
                 origin,
                 line_message,
                 message
             ),
             exit_codes::CONFIG_ERROR_ABORT,
         )
     }
 }
 
 impl From<(RevlogError, &str)> for CommandError {
     fn from((err, rev): (RevlogError, &str)) -> CommandError {
         match err {
             RevlogError::WDirUnsupported => CommandError::abort(
                 "abort: working directory revision cannot be specified",
             ),
             RevlogError::InvalidRevision => CommandError::abort(format!(
                 "abort: invalid revision identifier: {}",
                 rev
             )),
             RevlogError::AmbiguousPrefix => CommandError::abort(format!(
                 "abort: ambiguous revision identifier: {}",
                 rev
             )),
             RevlogError::Other(error) => error.into(),
         }
     }
 }
 
 impl From<StatusError> for CommandError {
     fn from(error: StatusError) -> Self {
-        CommandError::abort(format!("{}", error))
+        match error {
+            StatusError::Pattern(_) => {
+                CommandError::unsupported(format!("{}", error))
+            }
+            _ => CommandError::abort(format!("{}", error)),
+        }
     }
 }
 
 impl From<DirstateMapError> for CommandError {
     fn from(error: DirstateMapError) -> Self {
         CommandError::abort(format!("{}", error))
     }
 }
 
 impl From<DirstateError> for CommandError {
     fn from(error: DirstateError) -> Self {
         match error {
             DirstateError::Common(error) => error.into(),
             DirstateError::Map(error) => error.into(),
         }
     }
 }
 
 impl From<DirstateV2ParseError> for CommandError {
     fn from(error: DirstateV2ParseError) -> Self {
         HgError::from(error).into()
     }
 }
 
 impl From<SparseConfigError> for CommandError {
     fn from(e: SparseConfigError) -> Self {
         match e {
             SparseConfigError::IncludesAfterExcludes { context } => {
                 Self::abort_with_exit_code_bytes(
                     format_bytes!(
                         b"{} config cannot have includes after excludes",
                         context
                     ),
                     exit_codes::CONFIG_PARSE_ERROR_ABORT,
                 )
             }
             SparseConfigError::EntryOutsideSection { context, line } => {
                 Self::abort_with_exit_code_bytes(
                     format_bytes!(
                         b"{} config entry outside of section: {}",
                         context,
                         &line,
                     ),
                     exit_codes::CONFIG_PARSE_ERROR_ABORT,
                 )
             }
             SparseConfigError::InvalidNarrowPrefix(prefix) => {
                 Self::abort_with_exit_code_bytes(
                     format_bytes!(
                         b"invalid prefix on narrow pattern: {}",
                         &prefix
                     ),
                     exit_codes::ABORT,
                 )
             }
             SparseConfigError::IncludesInNarrow => Self::abort(
                 "including other spec files using '%include' \
                     is not supported in narrowspec",
             ),
             SparseConfigError::HgError(e) => Self::from(e),
             SparseConfigError::PatternError(e) => {
                 Self::unsupported(format!("{}", e))
             }
         }
     }
 }

tests/test-hgignore.t

@@ -1,449 +1,437 b''
 #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
-#if no-rhg
   $ hg status
   abort: $TESTTMP/ignorerepo/.hgignore: invalid pattern (relre): *.o (glob)
   [255]
-#endif
-#if rhg
-  $ hg status
-  Unsupported syntax regex parse error:
-      ^(?:*.o)
-          ^
-  error: repetition operator missing expression
-  [255]
-#endif
 
   $ echo 're:^(?!a).*\.o$' > .hgignore
-#if no-rhg
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? a.o
   ? syntax
-#endif
 #if rhg
-  $ hg status
-  Unsupported syntax regex parse error:
+  $ 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
-  [255]
+  [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
 
   $ hg status > /dev/null
   $ cat .hg/testhgignore .hg/testhgignorerel .hgignore dir2/.hgignore dir1/.hgignore dir1/.hgignoretwo | $TESTDIR/f --sha1
   sha1=6e315b60f15fb5dfa02be00f3e2c8f923051f5ff
   $ hg debugstate --docket | grep ignore
   ignore pattern hash: 6e315b60f15fb5dfa02be00f3e2c8f923051f5ff
 
   $ echo rel > .hg/testhgignorerel
   $ hg status > /dev/null
   $ cat .hg/testhgignore .hg/testhgignorerel .hgignore dir2/.hgignore dir1/.hgignore dir1/.hgignoretwo | $TESTDIR/f --sha1
   sha1=dea19cc7119213f24b6b582a4bae7b0cb063e34e
   $ hg debugstate --docket | grep ignore
   ignore pattern hash: dea19cc7119213f24b6b582a4bae7b0cb063e34e
 
 #endif