Skip to content

Compute word boundary flags in start state. #308

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Dec 29, 2016
Merged

Compute word boundary flags in start state. #308

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 22 additions & 3 deletions src/dfa.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1378,7 +1378,9 @@ impl<'a> Fsm<'a> {
((empty_flags.end as u8) << 1) |
((empty_flags.start_line as u8) << 2) |
((empty_flags.end_line as u8) << 3) |
((state_flags.is_word() as u8) << 4))
((empty_flags.word_boundary as u8) << 4) |
((empty_flags.not_word_boundary as u8) << 5) |
((state_flags.is_word() as u8) << 6))
as usize
};
match self.cache.start_states[flagi] {
Expand Down Expand Up @@ -1412,9 +1414,17 @@ impl<'a> Fsm<'a> {
empty_flags.end = text.len() == 0;
empty_flags.start_line = at == 0 || text[at - 1] == b'\n';
empty_flags.end_line = text.len() == 0;
if at > 0 && Byte::byte(text[at - 1]).is_ascii_word() {

let is_word_last = at > 0 && Byte::byte(text[at - 1]).is_ascii_word();
let is_word = at < text.len() && Byte::byte(text[at]).is_ascii_word();
if is_word_last {
state_flags.set_word();
}
if is_word == is_word_last {
empty_flags.not_word_boundary = true;
} else {
empty_flags.word_boundary = true;
}
(empty_flags, state_flags)
}

Expand All @@ -1433,9 +1443,18 @@ impl<'a> Fsm<'a> {
empty_flags.end = text.len() == 0;
empty_flags.start_line = at == text.len() || text[at] == b'\n';
empty_flags.end_line = text.len() == 0;
if at < text.len() && Byte::byte(text[at]).is_ascii_word() {

let is_word_last =
at < text.len() && Byte::byte(text[at]).is_ascii_word();
let is_word = at > 0 && Byte::byte(text[at - 1]).is_ascii_word();
if is_word_last {
state_flags.set_word();
}
if is_word == is_word_last {
empty_flags.not_word_boundary = true;
} else {
empty_flags.word_boundary = true;
}
(empty_flags, state_flags)
}

Expand Down
7 changes: 7 additions & 0 deletions tests/regression.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,3 +75,10 @@ mat!(lits_unambiguous1, u!(r"(ABC|CDA|BC)X"), "CDAX", Some((0, 4)));
// See: https://github.com/rust-lang-nursery/regex/issues/291
mat!(lits_unambiguous2, u!(r"((IMG|CAM|MG|MB2)_|(DSCN|CIMG))(?P<n>[0-9]+)$"),
"CIMG2341", Some((0, 8)), Some((0, 4)), None, Some((0, 4)), Some((4, 8)));

// See: https://github.com/rust-lang-nursery/regex/issues/271
mat!(end_not_wb, u!(r"$(?-u:\B)"), "\u{5c124}\u{b576c}", Some((8, 8)));
mat!(endl_or_wb, u!(r"(?m:$)|(?-u:\b)"), "\u{6084e}", Some((4, 4)));
mat!(zero_or_end, u!(r"(?i-u:\x00)|$"), "\u{e682f}", Some((4, 4)));
mat!(y_or_endl, u!(r"(?i-u:y)|(?m:$)"), "\u{b4331}", Some((4, 4)));
mat!(wb_start_x, u!(r"(?u:\b)^(?-u:X)"), "X", Some((0, 1)));