Skip to content
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

Jump to bottom

Japanese test improvements #962

Merged
merged 4 commits into from
Jul 28, 2021
Merged

Japanese test improvements #962

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
119a4ff
Update Japanese tests with more sensible data
wallace11 Jul 28, 2021
1095a7d
Add another Japanese test
wallace11 Jul 28, 2021
e8348e2
Remove excessive spaces
wallace11 Jul 28, 2021
4af8dd0
Preprocess japanese texts to find dates
eikek Jul 28, 2021
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
18 changes: 15 additions & 3 deletions modules/analysis/src/main/scala/docspell/analysis/date/DateFind.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,9 +21,7 @@ import docspell.common._
object DateFind {

def findDates(text: String, lang: Language): Stream[Pure, NerDateLabel] =
TextSplitter
.splitToken(text, " \t.,\n\r/年月日".toSet)
.filter(w => lang != Language.Latvian || w.value != "gada")
splitWords(text, lang)
.sliding(3)
.filter(_.size == 3)
.flatMap(q =>
Expand All @@ -44,6 +42,20 @@ object DateFind {
)
)

private[this] val jpnChars =
("年月日" + MonthName.getAll(Language.Japanese).map(_.mkString).mkString).toSet

private def splitWords(text: String, lang: Language): Stream[Pure, Word] = {
val stext =
if (lang == Language.Japanese) {
text.map(c => if (jpnChars.contains(c)) c else ' ')
} else text

TextSplitter
.splitToken(stext, " \t.,\n\r/年月日".toSet)
.filter(w => lang != Language.Latvian || w.value != "gada")
}

case class SimpleDate(year: Int, month: Int, day: Int) {
def toLocalDate: LocalDate =
LocalDate.of(if (year < 100) 2000 + year else year, month, day)
Expand Down
19 changes: 15 additions & 4 deletions modules/analysis/src/test/scala/docspell/analysis/date/DateFindSpec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -146,23 +146,34 @@ class DateFindSpec extends FunSuite {
test("find japanese dates") {
assertEquals(
DateFind
.findDates("some text in japanese 2021.7.21 and more", Language.Japanese)
.findDates("今日の日付は2021.7.21です。", Language.Japanese)
.toVector,
Vector(
NerDateLabel(
LocalDate.of(2021, 7, 21),
NerLabel("2021.7.21", NerTag.Date, 22, 31)
NerLabel("2021.7.21", NerTag.Date, 6, 15)
)
)
)
assertEquals(
DateFind
.findDates("some text in japanese 2021年7月21日 and more", Language.Japanese)
.findDates("今日の日付は2021年7月21日です。", Language.Japanese)
.toVector,
Vector(
NerDateLabel(
LocalDate.of(2021, 7, 21),
NerLabel("2021年7月21", NerTag.Date, 22, 31)
NerLabel("2021年7月21", NerTag.Date, 6, 15)
)
)
)
assertEquals(
DateFind
.findDates("年月日2021年7月21日（日）", Language.Japanese)
.toVector,
Vector(
NerDateLabel(
LocalDate.of(2021, 7, 21),
NerLabel("2021年7月21", NerTag.Date, 3, 12)
)
)
)
Expand Down