-
Notifications
You must be signed in to change notification settings - Fork 34
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* Add custom cleaning configs for CJK * Make custom filters direction specific * Update tests * Fix mono cleaning for CJK * Update Taskcluster kind * Update config generator to use custom cleaning configs for CJK
- Loading branch information
Showing
11 changed files
with
513 additions
and
7 deletions.
There are no files selected for viewing
77 changes: 77 additions & 0 deletions
77
pipeline/clean/opuscleaner/configs/en-ja/default.filters.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 +1,77 @@ | ||
| { | ||
| "version": 1, | ||
| "files": [ | ||
| ], | ||
| "filters": [ | ||
| { | ||
| "filter": "remove_empty_lines", | ||
| "parameters": {}, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "normalize_whitespace", | ||
| "parameters": { | ||
| "COLLAPSE": true | ||
| }, | ||
| "language": "<src>" | ||
| }, | ||
| { | ||
| "filter": "deescape-special-chars", | ||
| "parameters": { | ||
| "LANG1": "other" | ||
| }, | ||
| "language": "<src>" | ||
| }, | ||
| { | ||
| "filter": "max_length", | ||
| "parameters": { | ||
| "MAXLENGTH": 150, | ||
| "MINLENGTH": 1 | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "fix_wiki", | ||
| "parameters": { | ||
| "ALWAYS": false, | ||
| "FOOTNOTES": true, | ||
| "URLS": true, | ||
| "WIKILINKS": true, | ||
| "CODE": true, | ||
| "HEADINGS": true, | ||
| "REMOVEEMPTYLINES": true | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "alpha_ratio", | ||
| "parameters": { | ||
| "LANG1": "<src>", | ||
| "LANG2": "<trg>", | ||
| "SRCWORDRAT": 0.4, | ||
| "TRGWORDRAT": 0.0, | ||
| "SRCALPHARAT": 0.5, | ||
| "TRGALPHARAT": 0.0, | ||
| "DEBUG": false | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "num_mismatch", | ||
| "parameters": { | ||
| "RATIO": 1, | ||
| "DEBUG": false | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "fasttext_filter", | ||
| "parameters": { | ||
| "FASTTEXT_MODEL_TYPE": "large", | ||
| "LANG1": "<src>", | ||
| "LANG2": "<trg>" | ||
| }, | ||
| "language": null | ||
| } | ||
| ] | ||
| } |
77 changes: 77 additions & 0 deletions
77
pipeline/clean/opuscleaner/configs/en-ko/default.filters.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 +1,77 @@ | ||
| { | ||
| "version": 1, | ||
| "files": [ | ||
| ], | ||
| "filters": [ | ||
| { | ||
| "filter": "remove_empty_lines", | ||
| "parameters": {}, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "normalize_whitespace", | ||
| "parameters": { | ||
| "COLLAPSE": true | ||
| }, | ||
| "language": "<src>" | ||
| }, | ||
| { | ||
| "filter": "deescape-special-chars", | ||
| "parameters": { | ||
| "LANG1": "other" | ||
| }, | ||
| "language": "<src>" | ||
| }, | ||
| { | ||
| "filter": "max_length", | ||
| "parameters": { | ||
| "MAXLENGTH": 150, | ||
| "MINLENGTH": 1 | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "fix_wiki", | ||
| "parameters": { | ||
| "ALWAYS": false, | ||
| "FOOTNOTES": true, | ||
| "URLS": true, | ||
| "WIKILINKS": true, | ||
| "CODE": true, | ||
| "HEADINGS": true, | ||
| "REMOVEEMPTYLINES": true | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "alpha_ratio", | ||
| "parameters": { | ||
| "LANG1": "<src>", | ||
| "LANG2": "<trg>", | ||
| "SRCWORDRAT": 0.4, | ||
| "TRGWORDRAT": 0.0, | ||
| "SRCALPHARAT": 0.5, | ||
| "TRGALPHARAT": 0.0, | ||
| "DEBUG": false | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "num_mismatch", | ||
| "parameters": { | ||
| "RATIO": 1, | ||
| "DEBUG": false | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "fasttext_filter", | ||
| "parameters": { | ||
| "FASTTEXT_MODEL_TYPE": "large", | ||
| "LANG1": "<src>", | ||
| "LANG2": "<trg>" | ||
| }, | ||
| "language": null | ||
| } | ||
| ] | ||
| } |
77 changes: 77 additions & 0 deletions
77
pipeline/clean/opuscleaner/configs/en-zh/default.filters.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 +1,77 @@ | ||
| { | ||
| "version": 1, | ||
| "files": [ | ||
| ], | ||
| "filters": [ | ||
| { | ||
| "filter": "remove_empty_lines", | ||
| "parameters": {}, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "normalize_whitespace", | ||
| "parameters": { | ||
| "COLLAPSE": true | ||
| }, | ||
| "language": "<src>" | ||
| }, | ||
| { | ||
| "filter": "deescape-special-chars", | ||
| "parameters": { | ||
| "LANG1": "other" | ||
| }, | ||
| "language": "<src>" | ||
| }, | ||
| { | ||
| "filter": "max_length", | ||
| "parameters": { | ||
| "MAXLENGTH": 150, | ||
| "MINLENGTH": 1 | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "fix_wiki", | ||
| "parameters": { | ||
| "ALWAYS": false, | ||
| "FOOTNOTES": true, | ||
| "URLS": true, | ||
| "WIKILINKS": true, | ||
| "CODE": true, | ||
| "HEADINGS": true, | ||
| "REMOVEEMPTYLINES": true | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "alpha_ratio", | ||
| "parameters": { | ||
| "LANG1": "<src>", | ||
| "LANG2": "<trg>", | ||
| "SRCWORDRAT": 0.4, | ||
| "TRGWORDRAT": 0.0, | ||
| "SRCALPHARAT": 0.5, | ||
| "TRGALPHARAT": 0.0, | ||
| "DEBUG": false | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "num_mismatch", | ||
| "parameters": { | ||
| "RATIO": 1, | ||
| "DEBUG": false | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "fasttext_filter", | ||
| "parameters": { | ||
| "FASTTEXT_MODEL_TYPE": "large", | ||
| "LANG1": "<src>", | ||
| "LANG2": "<trg>" | ||
| }, | ||
| "language": null | ||
| } | ||
| ] | ||
| } |
77 changes: 77 additions & 0 deletions
77
pipeline/clean/opuscleaner/configs/ja-en/default.filters.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 +1,77 @@ | ||
| { | ||
| "version": 1, | ||
| "files": [ | ||
| ], | ||
| "filters": [ | ||
| { | ||
| "filter": "remove_empty_lines", | ||
| "parameters": {}, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "normalize_whitespace", | ||
| "parameters": { | ||
| "COLLAPSE": true | ||
| }, | ||
| "language": "<trg>" | ||
| }, | ||
| { | ||
| "filter": "deescape-special-chars", | ||
| "parameters": { | ||
| "LANG1": "other" | ||
| }, | ||
| "language": "<trg>" | ||
| }, | ||
| { | ||
| "filter": "max_length", | ||
| "parameters": { | ||
| "MAXLENGTH": 150, | ||
| "MINLENGTH": 1 | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "fix_wiki", | ||
| "parameters": { | ||
| "ALWAYS": false, | ||
| "FOOTNOTES": true, | ||
| "URLS": true, | ||
| "WIKILINKS": true, | ||
| "CODE": true, | ||
| "HEADINGS": true, | ||
| "REMOVEEMPTYLINES": true | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "alpha_ratio", | ||
| "parameters": { | ||
| "LANG1": "<src>", | ||
| "LANG2": "<trg>", | ||
| "SRCWORDRAT": 0.0, | ||
| "TRGWORDRAT": 0.4, | ||
| "SRCALPHARAT": 0.0, | ||
| "TRGALPHARAT": 0.5, | ||
| "DEBUG": false | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "num_mismatch", | ||
| "parameters": { | ||
| "RATIO": 1, | ||
| "DEBUG": false | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "fasttext_filter", | ||
| "parameters": { | ||
| "FASTTEXT_MODEL_TYPE": "large", | ||
| "LANG1": "<src>", | ||
| "LANG2": "<trg>" | ||
| }, | ||
| "language": null | ||
| } | ||
| ] | ||
| } |
77 changes: 77 additions & 0 deletions
77
pipeline/clean/opuscleaner/configs/ko-en/default.filters.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 +1,77 @@ | ||
| { | ||
| "version": 1, | ||
| "files": [ | ||
| ], | ||
| "filters": [ | ||
| { | ||
| "filter": "remove_empty_lines", | ||
| "parameters": {}, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "normalize_whitespace", | ||
| "parameters": { | ||
| "COLLAPSE": true | ||
| }, | ||
| "language": "<trg>" | ||
| }, | ||
| { | ||
| "filter": "deescape-special-chars", | ||
| "parameters": { | ||
| "LANG1": "other" | ||
| }, | ||
| "language": "<trg>" | ||
| }, | ||
| { | ||
| "filter": "max_length", | ||
| "parameters": { | ||
| "MAXLENGTH": 150, | ||
| "MINLENGTH": 1 | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "fix_wiki", | ||
| "parameters": { | ||
| "ALWAYS": false, | ||
| "FOOTNOTES": true, | ||
| "URLS": true, | ||
| "WIKILINKS": true, | ||
| "CODE": true, | ||
| "HEADINGS": true, | ||
| "REMOVEEMPTYLINES": true | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "alpha_ratio", | ||
| "parameters": { | ||
| "LANG1": "<src>", | ||
| "LANG2": "<trg>", | ||
| "SRCWORDRAT": 0.0, | ||
| "TRGWORDRAT": 0.4, | ||
| "SRCALPHARAT": 0.0, | ||
| "TRGALPHARAT": 0.5, | ||
| "DEBUG": false | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "num_mismatch", | ||
| "parameters": { | ||
| "RATIO": 1, | ||
| "DEBUG": false | ||
| }, | ||
| "language": null | ||
| }, | ||
| { | ||
| "filter": "fasttext_filter", | ||
| "parameters": { | ||
| "FASTTEXT_MODEL_TYPE": "large", | ||
| "LANG1": "<src>", | ||
| "LANG2": "<trg>" | ||
| }, | ||
| "language": null | ||
| } | ||
| ] | ||
| } |
Oops, something went wrong.