Skip to content

fix memory consumption: skip precalculating the affixes, test #3

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

Open
szacskesz wants to merge 1 commit into
base: master
Choose a base branch
from
Open

fix memory consumption: skip precalculating the affixes, test #3

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
43 changes: 20 additions & 23 deletions src/dic/word.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ export class Word {
* treated as a "word" argument.
* @param aff - {@link Aff} data to use.
*/
constructor(line: string, aff: Aff) {
constructor(line: string, private aff: Aff) {
// a hack so that the split regex doesn't get confused with escapes
line = line.replaceAll("\\/", "_||_")

Expand Down Expand Up @@ -101,25 +101,6 @@ export class Word {
}
}
}

// precalculating the affixes here improves performance for ngram suggestions
if (this.flags) {
const prefixes = iterate(this.flags)
.filter(flag => aff.PFX.has(flag))
.map(flag => aff.PFX.get(flag)!)
.flatten()
.filter(prefix => prefix.relevant(this.stem))
.toSet()

const suffixes = iterate(this.flags)
.filter(flag => aff.SFX.has(flag))
.map(flag => aff.SFX.get(flag)!)
.flatten()
.filter(suffix => suffix.relevant(this.stem))
.toSet()

this.affixes = { prefixes, suffixes }
}
}

/**
Expand All @@ -141,13 +122,29 @@ export class Word {
forms(similarTo?: string) {
const res: string[] = [this.stem]

if (!this.affixes) return res
if (!this.flags) return res

const affixes = {
prefixes: iterate(this.flags)
.filter(flag => this.aff.PFX.has(flag))
.map(flag => this.aff.PFX.get(flag)!)
.flatten()
.filter(prefix => prefix.relevant(this.stem))
.toSet(),

suffixes: iterate(this.flags)
.filter(flag => this.aff.SFX.has(flag))
.map(flag => this.aff.SFX.get(flag)!)
.flatten()
.filter(suffix => suffix.relevant(this.stem))
.toSet(),
};

const suffixes = iterate(this.affixes.suffixes)
const suffixes = iterate(affixes.suffixes)
.filter(suffix => (similarTo ? similarTo.endsWith(suffix.add) : true))
.toArray()

const prefixes = iterate(this.affixes.prefixes)
const prefixes = iterate(affixes.prefixes)
.filter(prefix => (similarTo ? similarTo.startsWith(prefix.add) : true))
.toArray()

Expand Down
Loading