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

update link in TLC to be github links #1737

Merged
merged 2 commits into from
Jan 14, 2021
Merged

update link in TLC to be github links #1737

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7a6ba6c
update link to be github links
chameleonTK Jan 14, 2021
8bceaa0
format code
chameleonTK Jan 14, 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
2 changes: 1 addition & 1 deletion datasets/tlc/dataset_infos.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"tlcv2.0": {"description": "Thai Literature Corpora (TLC): Corpora of machine-ingestible Thai classical literature texts.\n\nRelease: 6/25/19\n\nIt consists of two datasets:\n\n## TLC set\nIt is texts from [Vajirayana Digital Library](https://vajirayana.org/), stored by chapters and stanzas (non-tokenized).\n\ntlc v.2.0 (6/17/19 : a total of 34 documents, 292,270 lines, 31,790,734 characters)\ntlc v.1.0 (6/11/19 : a total of 25 documents, 113,981 lines, 28,775,761 characters)\n\n## TNHC set\nIt is texts from Thai National Historical Corpus, stored by lines (manually tokenized).\n\ntnhc v.1.0 (6/25/19 : a total of 47 documents, 756,478 lines, 13,361,142 characters)\n", "citation": "@misc{\n author={Sawatphol, Jitkapat},\n title={Thai Literature Corpora},\n year={2019},\n howpublished={\\url{https://attapol.github.io/tlc.html}}\n}\n", "homepage": "https://attapol.github.io/tlc.html", "license": "", "features": {"ch_num": {"dtype": "string", "id": null, "_type": "Value"}, "title": {"dtype": "string", "id": null, "_type": "Value"}, "text": {"feature": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "length": -1, "id": null, "_type": "Sequence"}}, "post_processed": null, "supervised_keys": null, "builder_name": "tlc", "config_name": "tlcv2.0", "version": {"version_str": "2.0.0", "description": null, "major": 2, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 32498, "num_examples": 1, "dataset_name": "tlc"}}, "download_checksums": {"https://drive.google.com/uc?export=download&id=1S2T72b3Kkcvy4XZcxwIipoRn6ELa4hhV": {"num_bytes": 5551710, "checksum": "56aff251d17a33b4c6a12d2b41c9fe6aaa676d08a87d12e253f465107b13ae88"}}, "download_size": 5551710, "post_processing_size": null, "dataset_size": 32498, "size_in_bytes": 5584208}, "tlcv1.0": {"description": "Thai Literature Corpora (TLC): Corpora of machine-ingestible Thai classical literature texts.\n\nRelease: 6/25/19\n\nIt consists of two datasets:\n\n## TLC set\nIt is texts from [Vajirayana Digital Library](https://vajirayana.org/), stored by chapters and stanzas (non-tokenized).\n\ntlc v.2.0 (6/17/19 : a total of 34 documents, 292,270 lines, 31,790,734 characters)\ntlc v.1.0 (6/11/19 : a total of 25 documents, 113,981 lines, 28,775,761 characters)\n\n## TNHC set\nIt is texts from Thai National Historical Corpus, stored by lines (manually tokenized).\n\ntnhc v.1.0 (6/25/19 : a total of 47 documents, 756,478 lines, 13,361,142 characters)\n", "citation": "@misc{\n author={Sawatphol, Jitkapat},\n title={Thai Literature Corpora},\n year={2019},\n howpublished={\\url{https://attapol.github.io/tlc.html}}\n}\n", "homepage": "https://attapol.github.io/tlc.html", "license": "", "features": {"ch_num": {"dtype": "string", "id": null, "_type": "Value"}, "title": {"dtype": "string", "id": null, "_type": "Value"}, "text": {"feature": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "length": -1, "id": null, "_type": "Sequence"}}, "post_processed": null, "supervised_keys": null, "builder_name": "tlc", "config_name": "tlcv1.0", "version": {"version_str": "1.0.0", "description": null, "major": 1, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 32498, "num_examples": 1, "dataset_name": "tlc"}}, "download_checksums": {"https://drive.google.com/uc?export=download&id=15E64fwMeAff0bAsFGaSsv9NYeVHn1drE": {"num_bytes": 2904472, "checksum": "9b27c79bfde97960f4cb3530a2e6a89360c219c0530e8aea593883f4847214df"}}, "download_size": 2904472, "post_processing_size": null, "dataset_size": 32498, "size_in_bytes": 2936970}, "tnhcv1.0": {"description": "Thai Literature Corpora (TLC): Corpora of machine-ingestible Thai classical literature texts.\n\nRelease: 6/25/19\n\nIt consists of two datasets:\n\n## TLC set\nIt is texts from [Vajirayana Digital Library](https://vajirayana.org/), stored by chapters and stanzas (non-tokenized).\n\ntlc v.2.0 (6/17/19 : a total of 34 documents, 292,270 lines, 31,790,734 characters)\ntlc v.1.0 (6/11/19 : a total of 25 documents, 113,981 lines, 28,775,761 characters)\n\n## TNHC set\nIt is texts from Thai National Historical Corpus, stored by lines (manually tokenized).\n\ntnhc v.1.0 (6/25/19 : a total of 47 documents, 756,478 lines, 13,361,142 characters)\n", "citation": "@misc{\n author={Sawatphol, Jitkapat},\n title={Thai Literature Corpora},\n year={2019},\n howpublished={\\url{https://attapol.github.io/tlc.html}}\n}\n", "homepage": "https://attapol.github.io/tlc.html", "license": "", "features": {"text": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}}, "post_processed": null, "supervised_keys": null, "builder_name": "tlc", "config_name": "tnhcv1.0", "version": {"version_str": "1.0.0", "description": null, "major": 1, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 25198, "num_examples": 152, "dataset_name": "tlc"}}, "download_checksums": {"https://drive.google.com/uc?export=download&id=1T_ib-NOwQV6O6lEjCjvZReUA3pQ4h-gD": {"num_bytes": 1465403, "checksum": "ba534fb18bb07595a82e3981a164384494b01d49918939b11fe417423a637e6f"}}, "download_size": 1465403, "post_processing_size": null, "dataset_size": 25198, "size_in_bytes": 1490601}}
{"tlcv1.0": {"description": "Thai Literature Corpora (TLC): Corpora of machine-ingestible Thai classical literature texts.\n\nRelease: 6/25/19\n\nIt consists of two datasets:\n\n## TLC set\nIt is texts from [Vajirayana Digital Library](https://vajirayana.org/), stored by chapters and stanzas (non-tokenized).\n\ntlc v.2.0 (6/17/19 : a total of 34 documents, 292,270 lines, 31,790,734 characters)\ntlc v.1.0 (6/11/19 : a total of 25 documents, 113,981 lines, 28,775,761 characters)\n\n## TNHC set\nIt is texts from Thai National Historical Corpus, stored by lines (manually tokenized).\n\ntnhc v.1.0 (6/25/19 : a total of 47 documents, 756,478 lines, 13,361,142 characters)\n", "citation": "@misc{\n author={Sawatphol, Jitkapat},\n title={Thai Literature Corpora},\n year={2019},\n howpublished={\\url{https://attapol.github.io/tlc.html}}\n}\n", "homepage": "https://attapol.github.io/tlc.html", "license": "", "features": {"ch_num": {"dtype": "string", "id": null, "_type": "Value"}, "title": {"dtype": "string", "id": null, "_type": "Value"}, "text": {"feature": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "length": -1, "id": null, "_type": "Sequence"}}, "post_processed": null, "supervised_keys": null, "builder_name": "tlc", "config_name": "tlcv1.0", "version": {"version_str": "1.0.0", "description": null, "major": 1, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 32498, "num_examples": 1, "dataset_name": "tlc"}}, "download_checksums": {"/~https://github.com/jitkapat/thailitcorpus/releases/download/v.1.0/tlc_v.1.0.tar.gz": {"num_bytes": 2904472, "checksum": "9b27c79bfde97960f4cb3530a2e6a89360c219c0530e8aea593883f4847214df"}}, "download_size": 2904472, "post_processing_size": null, "dataset_size": 32498, "size_in_bytes": 2936970}, "tlcv2.0": {"description": "Thai Literature Corpora (TLC): Corpora of machine-ingestible Thai classical literature texts.\n\nRelease: 6/25/19\n\nIt consists of two datasets:\n\n## TLC set\nIt is texts from [Vajirayana Digital Library](https://vajirayana.org/), stored by chapters and stanzas (non-tokenized).\n\ntlc v.2.0 (6/17/19 : a total of 34 documents, 292,270 lines, 31,790,734 characters)\ntlc v.1.0 (6/11/19 : a total of 25 documents, 113,981 lines, 28,775,761 characters)\n\n## TNHC set\nIt is texts from Thai National Historical Corpus, stored by lines (manually tokenized).\n\ntnhc v.1.0 (6/25/19 : a total of 47 documents, 756,478 lines, 13,361,142 characters)\n", "citation": "@misc{\n author={Sawatphol, Jitkapat},\n title={Thai Literature Corpora},\n year={2019},\n howpublished={\\url{https://attapol.github.io/tlc.html}}\n}\n", "homepage": "https://attapol.github.io/tlc.html", "license": "", "features": {"ch_num": {"dtype": "string", "id": null, "_type": "Value"}, "title": {"dtype": "string", "id": null, "_type": "Value"}, "text": {"feature": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "length": -1, "id": null, "_type": "Sequence"}}, "post_processed": null, "supervised_keys": null, "builder_name": "tlc", "config_name": "tlcv2.0", "version": {"version_str": "2.0.0", "description": null, "major": 2, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 32498, "num_examples": 1, "dataset_name": "tlc"}}, "download_checksums": {"/~https://github.com/jitkapat/thailitcorpus/releases/download/v.2.0/tlc_v.2.0.tar.gz": {"num_bytes": 5551710, "checksum": "56aff251d17a33b4c6a12d2b41c9fe6aaa676d08a87d12e253f465107b13ae88"}}, "download_size": 5551710, "post_processing_size": null, "dataset_size": 32498, "size_in_bytes": 5584208}, "tnhcv1.0": {"description": "Thai Literature Corpora (TLC): Corpora of machine-ingestible Thai classical literature texts.\n\nRelease: 6/25/19\n\nIt consists of two datasets:\n\n## TLC set\nIt is texts from [Vajirayana Digital Library](https://vajirayana.org/), stored by chapters and stanzas (non-tokenized).\n\ntlc v.2.0 (6/17/19 : a total of 34 documents, 292,270 lines, 31,790,734 characters)\ntlc v.1.0 (6/11/19 : a total of 25 documents, 113,981 lines, 28,775,761 characters)\n\n## TNHC set\nIt is texts from Thai National Historical Corpus, stored by lines (manually tokenized).\n\ntnhc v.1.0 (6/25/19 : a total of 47 documents, 756,478 lines, 13,361,142 characters)\n", "citation": "@misc{\n author={Sawatphol, Jitkapat},\n title={Thai Literature Corpora},\n year={2019},\n howpublished={\\url{https://attapol.github.io/tlc.html}}\n}\n", "homepage": "https://attapol.github.io/tlc.html", "license": "", "features": {"text": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}}, "post_processed": null, "supervised_keys": null, "builder_name": "tlc", "config_name": "tnhcv1.0", "version": {"version_str": "1.0.0", "description": null, "major": 1, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 25198, "num_examples": 152, "dataset_name": "tlc"}}, "download_checksums": {"/~https://github.com/jitkapat/thailitcorpus/releases/download/v.1.0/tnhc_v.1.0.tar.gz": {"num_bytes": 1465403, "checksum": "ba534fb18bb07595a82e3981a164384494b01d49918939b11fe417423a637e6f"}}, "download_size": 1465403, "post_processing_size": null, "dataset_size": 25198, "size_in_bytes": 1490601}}
7 changes: 4 additions & 3 deletions datasets/tlc/tlc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,9 +41,9 @@
"""

_URLs = {
"tlcv1.0": "https://drive.google.com/uc?export=download&id=15E64fwMeAff0bAsFGaSsv9NYeVHn1drE",
"tlcv2.0": "https://drive.google.com/uc?export=download&id=1S2T72b3Kkcvy4XZcxwIipoRn6ELa4hhV",
"tnhcv1.0": "https://drive.google.com/uc?export=download&id=1T_ib-NOwQV6O6lEjCjvZReUA3pQ4h-gD",
"tlcv1.0": "https://github.com/jitkapat/thailitcorpus/releases/download/v.1.0/tlc_v.1.0.tar.gz",
"tlcv2.0": "https://github.com/jitkapat/thailitcorpus/releases/download/v.2.0/tlc_v.2.0.tar.gz",
"tnhcv1.0": "https://github.com/jitkapat/thailitcorpus/releases/download/v.1.0/tnhc_v.1.0.tar.gz",
}


Expand Down Expand Up @@ -104,6 +104,7 @@ def _info(self):

def _split_generators(self, dl_manager):
data_path = dl_manager.download_and_extract(_URLs[self.config.name])

return [
datasets.SplitGenerator(
name=datasets.Split.TRAIN,
Expand Down