-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #85 from s12chung/read_korean
Read korean and fix slices queries/responses
- Loading branch information
Showing
20 changed files
with
360 additions
and
25 deletions.
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
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
233 changes: 233 additions & 0 deletions
233
db/pkg/db/testdata/TestQueries_SourceStructuredIndex/basic.json
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 +1,233 @@ | ||
[ | ||
{ | ||
"name": "split", | ||
"reference": "split.txt", | ||
"parts": [ | ||
{ | ||
"tokenized_texts": [ | ||
{ | ||
"text": "내가 가는 이길이", | ||
"translation": "The road that I’m taking", | ||
"tokens": [ | ||
{ | ||
"text": "내", | ||
"part_of_speech": "Pronoun", | ||
"start_index": 0, | ||
"length": 1 | ||
}, | ||
{ | ||
"text": "가", | ||
"part_of_speech": "Postposition", | ||
"start_index": 1, | ||
"length": 1 | ||
}, | ||
{ | ||
"text": "가", | ||
"part_of_speech": "Verb", | ||
"start_index": 3, | ||
"length": 1 | ||
}, | ||
{ | ||
"text": "는", | ||
"part_of_speech": "Ending", | ||
"start_index": 4, | ||
"length": 1 | ||
}, | ||
{ | ||
"text": "이길", | ||
"part_of_speech": "Noun", | ||
"start_index": 6, | ||
"length": 2 | ||
}, | ||
{ | ||
"text": "이", | ||
"part_of_speech": "Postposition", | ||
"start_index": 8, | ||
"length": 1 | ||
} | ||
] | ||
}, | ||
{ | ||
"text": "어디로 가는지", | ||
"translation": "Where it’s leading me to, where it’s taking me", | ||
"tokens": [ | ||
{ | ||
"text": "어디", | ||
"part_of_speech": "Pronoun", | ||
"start_index": 0, | ||
"length": 2 | ||
}, | ||
{ | ||
"text": "로", | ||
"part_of_speech": "Postposition", | ||
"start_index": 2, | ||
"length": 1 | ||
}, | ||
{ | ||
"text": "가", | ||
"part_of_speech": "Verb", | ||
"start_index": 4, | ||
"length": 1 | ||
}, | ||
{ | ||
"text": "는지", | ||
"part_of_speech": "Ending", | ||
"start_index": 5, | ||
"length": 2 | ||
} | ||
] | ||
} | ||
] | ||
} | ||
], | ||
"updated_at": "0001-01-01T00:00:00Z", | ||
"created_at": "0001-01-01T00:00:00Z" | ||
}, | ||
{ | ||
"name": "weave", | ||
"reference": "weave.txt", | ||
"parts": [ | ||
{ | ||
"media": { | ||
"image_key": "testdb.SourcePartMediaImageKey.png" | ||
}, | ||
"tokenized_texts": [ | ||
{ | ||
"text": "이것은 샘플 파일입니다. tmp/in.txt에 자신의 텍스트를 입력합니다.", | ||
"translation": "This is a sample file. Put your own text at: tmp/in.txt.", | ||
"tokens": [ | ||
{ | ||
"text": "이것", | ||
"part_of_speech": "Pronoun", | ||
"start_index": 0, | ||
"length": 2 | ||
}, | ||
{ | ||
"text": "은", | ||
"part_of_speech": "Postposition", | ||
"start_index": 2, | ||
"length": 1 | ||
}, | ||
{ | ||
"text": "샘플", | ||
"part_of_speech": "Noun", | ||
"start_index": 4, | ||
"length": 2 | ||
}, | ||
{ | ||
"text": "파일", | ||
"part_of_speech": "Noun", | ||
"start_index": 7, | ||
"length": 2 | ||
}, | ||
{ | ||
"text": "이", | ||
"part_of_speech": "Copula", | ||
"start_index": 9, | ||
"length": 1 | ||
}, | ||
{ | ||
"text": "ㅂ니다", | ||
"part_of_speech": "Ending", | ||
"start_index": 10, | ||
"length": 3 | ||
}, | ||
{ | ||
"text": ".", | ||
"part_of_speech": "Punctuation", | ||
"start_index": 13, | ||
"length": 1 | ||
}, | ||
{ | ||
"text": "tmp", | ||
"part_of_speech": "OtherLanguage", | ||
"start_index": 15, | ||
"length": 3 | ||
}, | ||
{ | ||
"text": "/", | ||
"part_of_speech": "Punctuation", | ||
"start_index": 18, | ||
"length": 1 | ||
}, | ||
{ | ||
"text": "in", | ||
"part_of_speech": "OtherLanguage", | ||
"start_index": 19, | ||
"length": 2 | ||
}, | ||
{ | ||
"text": ".", | ||
"part_of_speech": "Punctuation", | ||
"start_index": 21, | ||
"length": 1 | ||
}, | ||
{ | ||
"text": "txt", | ||
"part_of_speech": "OtherLanguage", | ||
"start_index": 22, | ||
"length": 3 | ||
}, | ||
{ | ||
"text": "에", | ||
"part_of_speech": "Postposition", | ||
"start_index": 25, | ||
"length": 1 | ||
}, | ||
{ | ||
"text": "자신", | ||
"part_of_speech": "Noun", | ||
"start_index": 27, | ||
"length": 2 | ||
}, | ||
{ | ||
"text": "의", | ||
"part_of_speech": "Postposition", | ||
"start_index": 29, | ||
"length": 1 | ||
}, | ||
{ | ||
"text": "텍스트", | ||
"part_of_speech": "Noun", | ||
"start_index": 31, | ||
"length": 3 | ||
}, | ||
{ | ||
"text": "를", | ||
"part_of_speech": "Postposition", | ||
"start_index": 34, | ||
"length": 1 | ||
}, | ||
{ | ||
"text": "입력", | ||
"part_of_speech": "Noun", | ||
"start_index": 36, | ||
"length": 2 | ||
}, | ||
{ | ||
"text": "하", | ||
"part_of_speech": "Suffix", | ||
"start_index": 38, | ||
"length": 1 | ||
}, | ||
{ | ||
"text": "ㅂ니다", | ||
"part_of_speech": "Ending", | ||
"start_index": 39, | ||
"length": 3 | ||
}, | ||
{ | ||
"text": ".", | ||
"part_of_speech": "Punctuation", | ||
"start_index": 42, | ||
"length": 1 | ||
} | ||
] | ||
} | ||
] | ||
} | ||
], | ||
"updated_at": "0001-01-01T00:00:00Z", | ||
"created_at": "0001-01-01T00:00:00Z" | ||
} | ||
] |
1 change: 1 addition & 0 deletions
1
db/pkg/db/testdata/TestQueries_SourceStructuredIndex/clear.json
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 @@ | ||
null |
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
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
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
File renamed without changes.
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 @@ | ||
[] |
File renamed without changes.
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 @@ | ||
[] |
Oops, something went wrong.