Skip to content

Move to traits to avoid unnecessary allocs #110

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

Draft
wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

Move to traits to avoid unnecessary allocs #110

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
dd283c2
Move to traits to avoid unnecessary allocs
awong-dev Apr 18, 2024
17cd86d
Use closure for cut strategy instead of trait
awong-dev Apr 22, 2024
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
45 changes: 31 additions & 14 deletions src/lib.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -570,31 +570,49 @@ impl Jieba {
route.clear();
}

#[allow(non_snake_case)]
fn cut_internal<'a>(&self, sentence: &'a str, cut_all: bool, hmm: bool) -> Vec<&'a str> {
// This is the output buffer.
let heuristic_capacity = sentence.len() / 2;
let mut words = Vec::with_capacity(heuristic_capacity);

if cut_all {
self.cut_internal2(sentence, cut_all, &mut words, |j, s, w| j.cut_all_internal(s, w));
} else {
let mut route: Vec<(f64, usize)> = Vec::with_capacity(heuristic_capacity);
let mut dag = StaticSparseDAG::with_size_hint(heuristic_capacity);
if hmm {
// TODO: Why is this sentence.chars().count() and not sentence.len()?
let mut hmm_context = hmm::HmmContext::new(sentence.chars().count());
self.cut_internal2(sentence, cut_all, &mut words, |j, s, w| {
j.cut_dag_hmm(s, w, &mut route, &mut dag, &mut hmm_context)
});
} else {
self.cut_internal2(sentence, cut_all, &mut words, |j, s, w| {
j.cut_dag_no_hmm(s, w, &mut route, &mut dag)
});
}
}
words
}

fn cut_internal2<'a>(
&self,
sentence: &'a str,
cut_all: bool,
words: &mut Vec<&'a str>,
mut cut_strategy: impl FnMut(&Self, &'a str, &mut Vec<&'a str>),
) {
// This is for this algorithm's selector.
let re_han: &Regex = if cut_all { &RE_HAN_CUT_ALL } else { &RE_HAN_DEFAULT };
let re_skip: &Regex = if cut_all { &RE_SKIP_CUT_ALL } else { &RE_SKIP_DEFAULT };
let splitter = SplitMatches::new(re_han, sentence);
let mut route = Vec::with_capacity(heuristic_capacity);
let mut dag = StaticSparseDAG::with_size_hint(heuristic_capacity);

let mut hmm_context = hmm::HmmContext::new(sentence.chars().count());

for state in splitter {
match state {
SplitState::Matched(_) => {
let block = state.into_str();
assert!(!block.is_empty());

if cut_all {
self.cut_all_internal(block, &mut words);
} else if hmm {
self.cut_dag_hmm(block, &mut words, &mut route, &mut dag, &mut hmm_context);
} else {
self.cut_dag_no_hmm(block, &mut words, &mut route, &mut dag);
}
cut_strategy(self, block, words)
}
SplitState::Unmatched(_) => {
let block = state.into_str();
Expand Down Expand Up @@ -622,7 +640,6 @@ impl Jieba {
}
}
}
words
}

/// Cut the input text
Expand Down