-
Notifications
You must be signed in to change notification settings - Fork 340
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
New: (en) Add year suffix extraction refiner
- Loading branch information
Wanasit Tanakitrungruang
committed
Aug 10, 2024
1 parent
be759f7
commit be6e995
Showing
3 changed files
with
68 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,37 @@ | ||
import { ParsingContext, Refiner } from "../../../chrono"; | ||
import { ParsingResult } from "../../../results"; | ||
import { YEAR_PATTERN, parseYear } from "../constants"; | ||
|
||
const YEAR_SUFFIX_PATTERN = new RegExp(`^\\s*(${YEAR_PATTERN})`, "i"); | ||
const YEAR_GROUP = 1; | ||
export default class ENExtractYearSuffixRefiner implements Refiner { | ||
refine(context: ParsingContext, results: ParsingResult[]): ParsingResult[] { | ||
results.forEach(function (result) { | ||
context.debug(() => { | ||
console.log("ENExtractYearSuffixRefiner", result.text, result.start); | ||
}); | ||
if (!result.start.isDateWithUnknownYear()) { | ||
return; | ||
} | ||
|
||
const suffix = context.text.substring(result.index + result.text.length); | ||
const match = YEAR_SUFFIX_PATTERN.exec(suffix); | ||
if (!match) { | ||
return; | ||
} | ||
|
||
context.debug(() => { | ||
console.log(`Extracting year: '${match[0]}' into : ${result}`); | ||
}); | ||
|
||
const year = parseYear(match[YEAR_GROUP]); | ||
if (result.end != null) { | ||
result.end.assign("year", year); | ||
} | ||
result.start.assign("year", year); | ||
result.text += match[0]; | ||
}); | ||
|
||
return results; | ||
} | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters