Full Code of allenai/ir_datasets for AI

gitextract_2j6ggfs5/

├── .github/
│   ├── ISSUE_TEMPLATE/
│   │   ├── bug_report.md
│   │   ├── dataset-addition.md
│   │   ├── documentation.md
│   │   └── feature_request.md
│   └── workflows/
│       ├── deploy.yml
│       └── test.yml
├── .gitignore
├── LICENSE
├── MANIFEST.in
├── README.md
├── examples/
│   ├── adding_datasets.ipynb
│   ├── clirmatrix_example.py
│   ├── ir_datasets.ipynb
│   └── ir_datasets_cli.ipynb
├── ir_datasets/
│   ├── __init__.py
│   ├── __main__.py
│   ├── commands/
│   │   ├── __init__.py
│   │   ├── build_c4_checkpoints.py
│   │   ├── build_clueweb_warc_indexes.py
│   │   ├── build_download_cache.py
│   │   ├── clean.py
│   │   ├── doc_fifos.py
│   │   ├── export.py
│   │   ├── generate_metadata.py
│   │   ├── list.py
│   │   └── lookup.py
│   ├── datasets/
│   │   ├── __init__.py
│   │   ├── antique.py
│   │   ├── aol_ia.py
│   │   ├── aquaint.py
│   │   ├── argsme.py
│   │   ├── base.py
│   │   ├── beir.py
│   │   ├── c4.py
│   │   ├── car.py
│   │   ├── clinicaltrials.py
│   │   ├── clirmatrix.py
│   │   ├── clueweb09.py
│   │   ├── clueweb12.py
│   │   ├── codec.py
│   │   ├── codesearchnet.py
│   │   ├── cord19.py
│   │   ├── cranfield.py
│   │   ├── csl.py
│   │   ├── disks45.py
│   │   ├── dpr_w100.py
│   │   ├── gov.py
│   │   ├── gov2.py
│   │   ├── hc4.py
│   │   ├── highwire.py
│   │   ├── istella22.py
│   │   ├── kilt.py
│   │   ├── lotte.py
│   │   ├── medline.py
│   │   ├── miracl.py
│   │   ├── mmarco.py
│   │   ├── mr_tydi.py
│   │   ├── msmarco_document.py
│   │   ├── msmarco_document_v2.py
│   │   ├── msmarco_passage.py
│   │   ├── msmarco_passage_v2.py
│   │   ├── msmarco_qna.py
│   │   ├── nano_beir.py
│   │   ├── natural_questions.py
│   │   ├── neuclir.py
│   │   ├── neumarco.py
│   │   ├── nfcorpus.py
│   │   ├── nyt.py
│   │   ├── pmc.py
│   │   ├── sara.py
│   │   ├── touche.py
│   │   ├── touche_image.py
│   │   ├── trec_arabic.py
│   │   ├── trec_cast.py
│   │   ├── trec_fair.py
│   │   ├── trec_mandarin.py
│   │   ├── trec_robust04.py
│   │   ├── trec_spanish.py
│   │   ├── trec_tot.py
│   │   ├── trec_tot_2025.py
│   │   ├── tripclick.py
│   │   ├── tweets2013_ia.py
│   │   ├── vaswani.py
│   │   ├── wapo.py
│   │   ├── wikiclir.py
│   │   └── wikir.py
│   ├── docs/
│   │   ├── antique.yaml
│   │   ├── aol-ia.yaml
│   │   ├── aquaint.yaml
│   │   ├── argsme.yaml
│   │   ├── beir.yaml
│   │   ├── bibliography.bib
│   │   ├── c4.yaml
│   │   ├── car.yaml
│   │   ├── clinicaltrials.yaml
│   │   ├── clirmatrix.yaml
│   │   ├── clueweb09.yaml
│   │   ├── clueweb12.yaml
│   │   ├── codec.yaml
│   │   ├── codesearchnet.yaml
│   │   ├── cord19.yaml
│   │   ├── cranfield.yaml
│   │   ├── csl.yaml
│   │   ├── disks45.yaml
│   │   ├── dpr-w100.yaml
│   │   ├── gov.yaml
│   │   ├── gov2.yaml
│   │   ├── hc4.yaml
│   │   ├── highwire.yaml
│   │   ├── istella22.yaml
│   │   ├── kilt.yaml
│   │   ├── lotte.yaml
│   │   ├── medline.yaml
│   │   ├── miracl.yaml
│   │   ├── mmarco.yaml
│   │   ├── mr-tydi.yaml
│   │   ├── msmarco-document-v2.yaml
│   │   ├── msmarco-document.yaml
│   │   ├── msmarco-passage-v2.yaml
│   │   ├── msmarco-passage.yaml
│   │   ├── msmarco-qna.yaml
│   │   ├── nano-beir.yaml
│   │   ├── natural-questions.yaml
│   │   ├── neuclir.yaml
│   │   ├── neumarco.yaml
│   │   ├── nfcorpus.yaml
│   │   ├── nyt.yaml
│   │   ├── pmc.yaml
│   │   ├── sara.yaml
│   │   ├── touche-image.yaml
│   │   ├── touche.yaml
│   │   ├── trec-arabic.yaml
│   │   ├── trec-cast.yaml
│   │   ├── trec-fair.yaml
│   │   ├── trec-mandarin.yaml
│   │   ├── trec-robust04.yaml
│   │   ├── trec-spanish.yaml
│   │   ├── trec-tot-2025.yaml
│   │   ├── trec-tot.yaml
│   │   ├── tripclick.yaml
│   │   ├── tweets2013-ia.yaml
│   │   ├── vaswani.yaml
│   │   ├── wapo.yaml
│   │   ├── wikiclir.yaml
│   │   └── wikir.yaml
│   ├── etc/
│   │   ├── downloads.json
│   │   └── metadata.json
│   ├── formats/
│   │   ├── __init__.py
│   │   ├── argsme.py
│   │   ├── base.py
│   │   ├── clirmatrix.py
│   │   ├── csv_fmt.py
│   │   ├── extracted_cc.py
│   │   ├── jsonl.py
│   │   ├── ntcir.py
│   │   ├── touche.py
│   │   ├── touche_image.py
│   │   ├── trec.py
│   │   ├── tsv.py
│   │   └── webarc.py
│   ├── indices/
│   │   ├── __init__.py
│   │   ├── base.py
│   │   ├── cache_docstore.py
│   │   ├── clueweb_warc.py
│   │   ├── indexed_tsv_docstore.py
│   │   ├── lz4_pickle.py
│   │   ├── numpy_sorted_index.py
│   │   └── zpickle_docstore.py
│   ├── lazy_libs.py
│   ├── log.py
│   ├── util/
│   │   ├── __init__.py
│   │   ├── docs/
│   │   │   ├── __init__.py
│   │   │   ├── lazy.py
│   │   │   ├── multiple.py
│   │   │   └── subset.py
│   │   ├── download.py
│   │   ├── fileio.py
│   │   ├── hash.py
│   │   ├── html_parsing.py
│   │   ├── metadata.py
│   │   └── registry.py
│   └── wrappers/
│       ├── __init__.py
│       └── html_extractor.py
├── pyproject.toml
├── requirements-test.txt
├── requirements.txt
└── test/
    ├── __init__.py
    ├── downloads.py
    ├── dummy/
    │   ├── docs.tsv
    │   ├── qrels
    │   └── queries.tsv
    ├── formats/
    │   ├── __init__.py
    │   ├── test_trec.py
    │   └── test_tsv.py
    ├── indices/
    │   ├── __init__.py
    │   ├── lz4_pickle.py
    │   └── numpy_sorted.py
    ├── integration/
    │   ├── __init__.py
    │   ├── antique.py
    │   ├── aol_ia.py
    │   ├── aquaint.py
    │   ├── argsme.py
    │   ├── base.py
    │   ├── beir.py
    │   ├── c4.py
    │   ├── car.py
    │   ├── clinicaltrials.py
    │   ├── clirmatrix.py
    │   ├── clueweb09.py
    │   ├── clueweb12.py
    │   ├── codec.py
    │   ├── codesearchnet.py
    │   ├── cord19.py
    │   ├── cranfield.py
    │   ├── csl.py
    │   ├── disks45.py
    │   ├── dpr_w100.py
    │   ├── dummy.py
    │   ├── gov.py
    │   ├── gov2.py
    │   ├── hc4.py
    │   ├── highwire.py
    │   ├── istella22.py
    │   ├── kilt.py
    │   ├── lotte.py
    │   ├── medline.py
    │   ├── miracl.py
    │   ├── mmarco.py
    │   ├── mr_tydi.py
    │   ├── msmarco_document.py
    │   ├── msmarco_document_v2.py
    │   ├── msmarco_passage.py
    │   ├── msmarco_passage_v2.py
    │   ├── msmarco_qna.py
    │   ├── nano_beir.py
    │   ├── natural_questions.py
    │   ├── neuclir.py
    │   ├── neumarco.py
    │   ├── nfcorpus.py
    │   ├── nyt.py
    │   ├── pmc.py
    │   ├── sara.py
    │   ├── touche.py
    │   ├── touche_image.py
    │   ├── trec_arabic.py
    │   ├── trec_cast.py
    │   ├── trec_fair.py
    │   ├── trec_mandarin.py
    │   ├── trec_robust04.py
    │   ├── trec_spanish.py
    │   ├── trec_tot.py
    │   ├── trec_tot_2024.py
    │   ├── trec_tot_2025/
    │   │   ├── test_docs_iter.py
    │   │   ├── test_docs_store.py
    │   │   ├── test_qrel_iter.py
    │   │   └── test_queries_iter.py
    │   ├── tripclick.py
    │   ├── tweets2013_ia.py
    │   ├── vaswani.py
    │   ├── wapo.py
    │   ├── wikiclir.py
    │   └── wikir.py
    ├── metadata.py
    ├── test_defaulttext.py
    ├── util/
    │   └── docs/
    │       ├── __init__.py
    │       ├── data.py
    │       ├── test_multiple.py
    │       └── test_subset.py
    └── util.py

SYMBOL INDEX (2346 symbols across 176 files)

FILE: ir_datasets/__init__.py
  class EntityType (line 2) | class EntityType(Enum):
  function load (line 21) | def load(name):
  function parent_id (line 25) | def parent_id(dataset_id: str, entity_type: EntityType) -> str:
  function docs_parent_id (line 51) | def docs_parent_id(dataset_id: str) -> str:
  function queries_parent_id (line 56) | def queries_parent_id(dataset_id: str) -> str:
  function qrels_parent_id (line 60) | def qrels_parent_id(dataset_id: str) -> str:
  function scoreddocs_parent_id (line 64) | def scoreddocs_parent_id(dataset_id: str) -> str:
  function docpairs_parent_id (line 68) | def docpairs_parent_id(dataset_id: str) -> str:
  function qlogs_parent_id (line 72) | def qlogs_parent_id(dataset_id: str) -> str:
  function create_dataset (line 76) | def create_dataset(docs_tsv=None, queries_tsv=None, qrels_trec=None):
  function main (line 91) | def main(args):
  function main_cli (line 100) | def main_cli():

FILE: ir_datasets/commands/build_c4_checkpoints.py
  function process (line 16) | def process(args):
  function main (line 35) | def main(args):

FILE: ir_datasets/commands/build_clueweb_warc_indexes.py
  function process (line 11) | def process(args):
  function main (line 20) | def main(args):

FILE: ir_datasets/commands/build_download_cache.py
  function tmp_environ (line 15) | def tmp_environ(**kwargs):
  function _build_cache (line 31) | def _build_cache(data, dir, prefix=''):
  function main (line 60) | def main(args):

FILE: ir_datasets/commands/clean.py
  function walk_path (line 16) | def walk_path(start_path='.', skips=[]):
  function clean (line 33) | def clean(dataset, yes=False, list=False, human=True):
  function main (line 79) | def main(args):

FILE: ir_datasets/commands/doc_fifos.py
  function main (line 16) | def main(args):

FILE: ir_datasets/commands/export.py
  function main_docs (line 10) | def main_docs(dataset, args):
  function main_queries (line 19) | def main_queries(dataset, args):
  function main_qrels (line 28) | def main_qrels(dataset, args):
  function main_scoreddocs (line 37) | def main_scoreddocs(dataset, args):
  function main_docpairs (line 48) | def main_docpairs(dataset, args):
  class TsvExporter (line 57) | class TsvExporter:
    method __init__ (line 58) | def __init__(self, data_cls, out, fields=None):
    method next (line 81) | def next(self, record):
    method flush (line 98) | def flush(self):
  class JsonlExporter (line 102) | class JsonlExporter:
    method __init__ (line 103) | def __init__(self, data_cls, out, fields=None):
    method next (line 123) | def next(self, record):
    method encode (line 127) | def encode(self, value):
    method flush (line 134) | def flush(self):
  function is_tuple_elip (line 137) | def is_tuple_elip(annotation):
  class TrecQrelsExporter (line 144) | class TrecQrelsExporter:
    method __init__ (line 145) | def __init__(self, data_cls, out, fields=None):
    method next (line 163) | def next(self, record):
    method flush (line 167) | def flush(self):
  class TrecRunExporter (line 171) | class TrecRunExporter:
    method __init__ (line 172) | def __init__(self, data_cls, out, fields=None):
    method next (line 180) | def next(self, record):
    method flush (line 186) | def flush(self):
  function main (line 201) | def main(args):

FILE: ir_datasets/commands/generate_metadata.py
  function dataset2metadata (line 15) | def dataset2metadata(args):
  function write_metadata_file (line 38) | def write_metadata_file(data, file):
  function main (line 49) | def main(args):

FILE: ir_datasets/commands/list.py
  function main (line 10) | def main(args):

FILE: ir_datasets/commands/lookup.py
  function qid_lookup (line 10) | def qid_lookup(dataset, args):
  function did_lookup (line 23) | def did_lookup(dataset, args):
  function main (line 36) | def main(args):

FILE: ir_datasets/datasets/antique.py
  function _init (line 32) | def _init():

FILE: ir_datasets/datasets/aol_ia.py
  class LogItem (line 27) | class LogItem(NamedTuple):
  class AolQlog (line 33) | class AolQlog(NamedTuple):
  class AolIaDoc (line 41) | class AolIaDoc(NamedTuple):
    method default_text (line 47) | def default_text(self):
  class AolQlogs (line 54) | class AolQlogs(BaseQlogs):
    method __init__ (line 55) | def __init__(self, dlc):
    method qlogs_iter (line 58) | def qlogs_iter(self):
    method qlogs_cls (line 68) | def qlogs_cls(self):
    method qlogs_count (line 71) | def qlogs_count(self):
  class _ManagedDlc (line 75) | class _ManagedDlc:
    method __init__ (line 76) | def __init__(self, manager, path):
    method stream (line 81) | def stream(self):
    method path (line 86) | def path(self, force=True):
  class AolManager (line 92) | class AolManager:
    method __init__ (line 93) | def __init__(self, log_dlcs, id2wb_dlc, base_path):
    method docs_store (line 102) | def docs_store(self, options=DEFAULT_DOCSTORE_OPTIONS):
    method _internal_docs_store (line 106) | def _internal_docs_store(self, options: DocstoreOptions=DEFAULT_DOCSTO...
    method _build_docs (line 111) | def _build_docs(self):
    method build (line 135) | def build(self):
    method file_ref (line 177) | def file_ref(self, path):
  function _init (line 182) | def _init():

FILE: ir_datasets/datasets/aquaint.py
  function _init (line 23) | def _init():

FILE: ir_datasets/datasets/argsme.py
  function _init (line 40) | def _init():

FILE: ir_datasets/datasets/base.py
  class Dataset (line 12) | class Dataset:
    method __init__ (line 13) | def __init__(self, *constituents):
    method __getstate__ (line 17) | def __getstate__(self):
    method __setstate__ (line 20) | def __setstate__(self, state):
    method __getattr__ (line 23) | def __getattr__(self, attr):
    method __repr__ (line 53) | def __repr__(self):
    method __dir__ (line 72) | def __dir__(self):
    method has (line 78) | def has(self, etype: ir_datasets.EntityType) -> bool:
    method has_docs (line 82) | def has_docs(self):
    method has_queries (line 85) | def has_queries(self):
    method has_qrels (line 88) | def has_qrels(self):
    method has_scoreddocs (line 91) | def has_scoreddocs(self):
    method has_docpairs (line 94) | def has_docpairs(self):
    method has_qlogs (line 97) | def has_qlogs(self):
  class _BetaPythonApiDocs (line 101) | class _BetaPythonApiDocs:
    method __init__ (line 102) | def __init__(self, handler):
    method __iter__ (line 108) | def __iter__(self):
    method __len__ (line 111) | def __len__(self):
    method __getitem__ (line 114) | def __getitem__(self, key):
    method __repr__ (line 117) | def __repr__(self):
    method lookup (line 120) | def lookup(self, doc_ids):
    method lookup_iter (line 127) | def lookup_iter(self, doc_ids):
    method metadata (line 136) | def metadata(self):
  class _BetaPythonApiQueries (line 140) | class _BetaPythonApiQueries:
    method __init__ (line 141) | def __init__(self, handler):
    method __iter__ (line 147) | def __iter__(self):
    method __repr__ (line 150) | def __repr__(self):
    method __len__ (line 153) | def __len__(self):
    method lookup (line 163) | def lookup(self, query_ids):
    method lookup_iter (line 170) | def lookup_iter(self, query_ids):
    method metadata (line 181) | def metadata(self):
  class _BetaPythonApiQrels (line 185) | class _BetaPythonApiQrels:
    method __init__ (line 186) | def __init__(self, handler):
    method __iter__ (line 192) | def __iter__(self):
    method __repr__ (line 195) | def __repr__(self):
    method asdict (line 198) | def asdict(self):
    method __len__ (line 203) | def __len__(self):
    method metadata (line 214) | def metadata(self):
  class _BetaPythonApiScoreddocs (line 218) | class _BetaPythonApiScoreddocs:
    method __init__ (line 219) | def __init__(self, handler):
    method __iter__ (line 223) | def __iter__(self):
    method __repr__ (line 226) | def __repr__(self):
    method __len__ (line 229) | def __len__(self):
    method metadata (line 238) | def metadata(self):
  class _BetaPythonApiDocpairs (line 242) | class _BetaPythonApiDocpairs:
    method __init__ (line 243) | def __init__(self, handler):
    method __iter__ (line 247) | def __iter__(self):
    method __repr__ (line 250) | def __repr__(self):
    method __len__ (line 253) | def __len__(self):
    method metadata (line 262) | def metadata(self):
  class _BetaPythonApiQlogs (line 266) | class _BetaPythonApiQlogs:
    method __init__ (line 267) | def __init__(self, handler):
    method __iter__ (line 271) | def __iter__(self):
    method __repr__ (line 274) | def __repr__(self):
    method __len__ (line 277) | def __len__(self):
    method metadata (line 286) | def metadata(self):
  class FilteredQueries (line 290) | class FilteredQueries(BaseQueries):
    method __init__ (line 291) | def __init__(self, queries_handler, lazy_qids, mode='include'):
    method queries_iter (line 296) | def queries_iter(self):
    method queries_cls (line 306) | def queries_cls(self):
    method queries_handler (line 309) | def queries_handler(self):
    method queries_lang (line 312) | def queries_lang(self):
  class FilteredQrels (line 316) | class FilteredQrels(BaseQrels):
    method __init__ (line 317) | def __init__(self, qrels_handler, lazy_qids, mode='include'):
    method qrels_iter (line 322) | def qrels_iter(self):
    method qrels_defs (line 332) | def qrels_defs(self):
    method qrels_handler (line 335) | def qrels_handler(self):
  class FilteredScoredDocs (line 339) | class FilteredScoredDocs(BaseScoredDocs):
    method __init__ (line 340) | def __init__(self, scoreddocs_handler, lazy_qids, mode='include'):
    method scoreddocs_iter (line 345) | def scoreddocs_iter(self):
    method scoreddocs_handler (line 355) | def scoreddocs_handler(self):
  class FilteredDocPairs (line 359) | class FilteredDocPairs(BaseDocPairs):
    method __init__ (line 360) | def __init__(self, docpairs_handler, lazy_qids, mode='include'):
    method docpairs_iter (line 365) | def docpairs_iter(self):
    method docpairs_handler (line 375) | def docpairs_handler(self):
  class YamlDocumentation (line 379) | class YamlDocumentation:
    method __init__ (line 380) | def __init__(self, file):
    method __call__ (line 384) | def __call__(self, key):
    method get_key (line 387) | def get_key(self, key):
  class YamlDocumentationProvider (line 395) | class YamlDocumentationProvider:
    method __init__ (line 396) | def __init__(self, documentation, key):
    method documentation (line 400) | def documentation(self):
  class Deprecated (line 407) | class Deprecated:
    method __init__ (line 408) | def __init__(self, message):
    method deprecated (line 411) | def deprecated(self):
  class ExpectedFile (line 415) | class ExpectedFile:
    method __init__ (line 416) | def __init__(self, path, expected_md5=None, instructions=None):
    method path (line 421) | def path(self, force=True):
    method stream (line 429) | def stream(self):
  class Concat (line 436) | class Concat(Dataset):
    method __getattr__ (line 437) | def __getattr__(self, attr):

FILE: ir_datasets/datasets/beir.py
  class BeirDoc (line 16) | class BeirDoc(NamedTuple):
    method default_text (line 21) | def default_text(self):
  class BeirTitleDoc (line 28) | class BeirTitleDoc(NamedTuple):
    method default_text (line 32) | def default_text(self):
  class BeirTitleUrlDoc (line 38) | class BeirTitleUrlDoc(NamedTuple):
    method default_text (line 43) | def default_text(self):
  class BeirSciDoc (line 49) | class BeirSciDoc(NamedTuple):
    method default_text (line 57) | def default_text(self):
  class BeirCordDoc (line 63) | class BeirCordDoc(NamedTuple):
    method default_text (line 69) | def default_text(self):
  class BeirToucheDoc (line 75) | class BeirToucheDoc(NamedTuple):
    method default_text (line 81) | def default_text(self):
  class BeirCqaDoc (line 87) | class BeirCqaDoc(NamedTuple):
    method default_text (line 92) | def default_text(self):
  class BeirUrlQuery (line 98) | class BeirUrlQuery(NamedTuple):
    method default_text (line 102) | def default_text(self):
  class BeirSciQuery (line 108) | class BeirSciQuery(NamedTuple):
    method default_text (line 115) | def default_text(self):
  class BeirToucheQuery (line 121) | class BeirToucheQuery(NamedTuple):
    method default_text (line 126) | def default_text(self):
  class BeirCovidQuery (line 132) | class BeirCovidQuery(NamedTuple):
    method default_text (line 137) | def default_text(self):
  class BeirCqaQuery (line 143) | class BeirCqaQuery(NamedTuple):
    method default_text (line 147) | def default_text(self):
  function _map_field (line 153) | def _map_field(field, data):
  class BeirDocs (line 163) | class BeirDocs(BaseDocs):
    method __init__ (line 164) | def __init__(self, name, dlc, doc_type):
    method docs_iter (line 170) | def docs_iter(self):
    method _docs_iter (line 173) | def _docs_iter(self):
    method docs_cls (line 179) | def docs_cls(self):
    method docs_store (line 182) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 193) | def docs_count(self):
    method docs_namespace (line 197) | def docs_namespace(self):
    method docs_lang (line 200) | def docs_lang(self):
  class BeirQueries (line 204) | class BeirQueries(BaseQueries):
    method __init__ (line 205) | def __init__(self, name, dlc, query_type):
    method queries_iter (line 211) | def queries_iter(self):
    method queries_cls (line 217) | def queries_cls(self):
    method queries_namespace (line 220) | def queries_namespace(self):
    method queries_lang (line 223) | def queries_lang(self):
  class BeirQrels (line 227) | class BeirQrels(BaseQrels):
    method __init__ (line 228) | def __init__(self, qrels_dlc, qrels_defs):
    method qrels_path (line 232) | def qrels_path(self):
    method qrels_iter (line 235) | def qrels_iter(self):
    method qrels_cls (line 249) | def qrels_cls(self):
    method qrels_defs (line 252) | def qrels_defs(self):
  function _init (line 256) | def _init():
  function qid_filter (line 333) | def qid_filter(subset_qrels):

FILE: ir_datasets/datasets/c4.py
  class C4Doc (line 20) | class C4Doc(NamedTuple):
    method default_text (line 25) | def default_text(self):
  class MisinfoQuery (line 32) | class MisinfoQuery(NamedTuple):
    method default_text (line 40) | def default_text(self):
  class C4Source (line 47) | class C4Source(DocSource):
    method __init__ (line 48) | def __init__(self, name, dlc, checkpoint_dlc, doc_count, checkpoint_fr...
    method __len__ (line 58) | def __len__(self):
    method __iter__ (line 61) | def __iter__(self):
    method checkpoints (line 64) | def checkpoints(self):
  class C4SourceIter (line 72) | class C4SourceIter(DocSourceSeekableIter):
    method __init__ (line 73) | def __init__(self, source):
    method close (line 78) | def close(self):
    method __next__ (line 83) | def __next__(self):
    method seek (line 92) | def seek(self, idx):
  class C4Docstore (line 114) | class C4Docstore(Docstore):
    method __init__ (line 115) | def __init__(self, docs, options=DEFAULT_DOCSTORE_OPTIONS):
    method get_many_iter (line 119) | def get_many_iter(self, doc_ids):
  class C4Docs (line 144) | class C4Docs(BaseDocs):
    method __init__ (line 145) | def __init__(self, sources_dlc, checkpoint_dlc, base_path, source_name...
    method docs_iter (line 154) | def docs_iter(self):
    method docs_cls (line 157) | def docs_cls(self):
    method docs_store (line 160) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 164) | def docs_count(self, force=False):
    method docs_namespace (line 168) | def docs_namespace(self):
    method docs_lang (line 171) | def docs_lang(self):
    method docs_source_iter (line 174) | def docs_source_iter(self):
    method _docs_sources (line 177) | def _docs_sources(self):
  function _init (line 208) | def _init():

FILE: ir_datasets/datasets/car.py
  class CarQuery (line 27) | class CarQuery(NamedTuple):
    method default_text (line 32) | def default_text(self):
  class CarDocs (line 39) | class CarDocs(BaseDocs):
    method __init__ (line 40) | def __init__(self, streamer, count_hint=None):
    method docs_iter (line 46) | def docs_iter(self):
    method docs_cls (line 53) | def docs_cls(self):
    method docs_store (line 56) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 67) | def docs_count(self):
    method docs_namespace (line 71) | def docs_namespace(self):
    method docs_lang (line 74) | def docs_lang(self):
  class CarQueries (line 77) | class CarQueries(BaseQueries):
    method __init__ (line 78) | def __init__(self, streamer):
    method queries_iter (line 82) | def queries_iter(self):
    method queries_namespace (line 93) | def queries_namespace(self):
    method queries_cls (line 96) | def queries_cls(self):
    method queries_lang (line 99) | def queries_lang(self):
  function _init (line 102) | def _init():

FILE: ir_datasets/datasets/clinicaltrials.py
  class ClinicalTrialsDoc (line 37) | class ClinicalTrialsDoc(NamedTuple):
  class ClinicalTrialsDocs (line 46) | class ClinicalTrialsDocs(BaseDocs):
    method __init__ (line 47) | def __init__(self, name, dlcs, compress_format='tgz', count_hint=None):
    method docs_iter (line 53) | def docs_iter(self):
    method _docs_iter (line 56) | def _docs_iter(self):
    method _parse_doc (line 76) | def _parse_doc(self, xml):
    method docs_path (line 93) | def docs_path(self, force=True):
    method docs_store (line 96) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_cls (line 107) | def docs_cls(self):
    method docs_namespace (line 110) | def docs_namespace(self):
    method docs_count (line 113) | def docs_count(self):
    method docs_lang (line 117) | def docs_lang(self):
  function _init (line 121) | def _init():

FILE: ir_datasets/datasets/clirmatrix.py
  function _init (line 24) | def _init():

FILE: ir_datasets/datasets/clueweb09.py
  class TrecWebTrackQuery (line 37) | class TrecWebTrackQuery(NamedTuple):
    method default_text (line 43) | def default_text(self):
  class ClueWeb09Docs (line 50) | class ClueWeb09Docs(WarcDocs):
    method __init__ (line 51) | def __init__(self, docs_dlc, chk_dlc, dirs=None, lang=None):
    method docs_path (line 59) | def docs_path(self, force=True):
    method _docs_iter_source_files (line 62) | def _docs_iter_source_files(self):
    method _docs_id_to_source_file (line 70) | def _docs_id_to_source_file(self, doc_id):
    method _docs_source_file_to_checkpoint (line 85) | def _docs_source_file_to_checkpoint(self, source_file):
    method _docs_warc_file_counts (line 94) | def _docs_warc_file_counts(self):
    method docs_namespace (line 111) | def docs_namespace(self):
  class CatBQrelFilter (line 115) | class CatBQrelFilter(BaseQrels):
    method __init__ (line 116) | def __init__(self, qrels_handler):
    method qrels_iter (line 119) | def qrels_iter(self):
    method qrels_defs (line 126) | def qrels_defs(self):
    method qrels_cls (line 129) | def qrels_cls(self):
    method qrels_path (line 132) | def qrels_path(self):
  function _init (line 136) | def _init():

FILE: ir_datasets/datasets/clueweb12.py
  class TrecWebTrackQuery (line 57) | class TrecWebTrackQuery(NamedTuple):
    method default_text (line 63) | def default_text(self):
  class NtcirQuery (line 70) | class NtcirQuery(NamedTuple):
    method default_text (line 74) | def default_text(self):
  class MisinfoQuery (line 81) | class MisinfoQuery(NamedTuple):
    method default_text (line 87) | def default_text(self):
  class MisinfoQrel (line 94) | class MisinfoQrel(NamedTuple):
  class EhealthQrel (line 102) | class EhealthQrel(NamedTuple):
  class MsinfoQrels (line 111) | class MsinfoQrels(TrecQrels):
    method qrels_iter (line 112) | def qrels_iter(self):
    method qrels_cls (line 124) | def qrels_cls(self):
  class EhealthQrels (line 128) | class EhealthQrels(TrecQrels):
    method __init__ (line 129) | def __init__(self, qrels_dlcs, qtrust_dlcs, qunder_dlcs, qrels_defs, q...
    method qrels_iter (line 136) | def qrels_iter(self):
    method qrels_cls (line 154) | def qrels_cls(self):
  class FixAmp (line 158) | class FixAmp:
    method __init__ (line 159) | def __init__(self, streamer):
    method stream (line 162) | def stream(self):
    method __iter__ (line 165) | def __iter__(self):
  class ClueWeb12Docs (line 171) | class ClueWeb12Docs(WarcDocs):
    method __init__ (line 172) | def __init__(self, docs_dlc, chk_dlc=None):
    method docs_path (line 178) | def docs_path(self, force=True):
    method _docs_iter_source_files (line 181) | def _docs_iter_source_files(self):
    method _docs_id_to_source_file (line 186) | def _docs_id_to_source_file(self, doc_id):
    method _docs_source_file_to_checkpoint (line 195) | def _docs_source_file_to_checkpoint(self, source_file):
    method _docs_warc_file_counts (line 206) | def _docs_warc_file_counts(self):
    method docs_namespace (line 219) | def docs_namespace(self):
  class ClueWeb12b13Extractor (line 223) | class ClueWeb12b13Extractor:
    method __init__ (line 224) | def __init__(self, docs_dlc, extract_jar_dlc):
    method path (line 228) | def path(self, force=True):
    method _create_record_counts_if_needed (line 245) | def _create_record_counts_if_needed(self, path):
    method stream (line 265) | def stream(self):
  function _init (line 269) | def _init():

FILE: ir_datasets/datasets/codec.py
  class CodecDoc (line 25) | class CodecDoc(NamedTuple):
    method default_text (line 30) | def default_text(self):
  class CodecQuery (line 33) | class CodecQuery(NamedTuple):
    method default_text (line 38) | def default_text(self):
  class CodecQueries (line 45) | class CodecQueries(BaseQueries):
    method __init__ (line 46) | def __init__(self, streamer, qid_filter=None):
    method queries_iter (line 51) | def queries_iter(self):
    method queries_cls (line 58) | def queries_cls(self):
    method queries_namespace (line 61) | def queries_namespace(self):
    method queries_lang (line 64) | def queries_lang(self):
  function filter_qids (line 68) | def filter_qids(domain, queries_handler):
  function _init (line 72) | def _init():

FILE: ir_datasets/datasets/codesearchnet.py
  class CodeSearchNetDoc (line 32) | class CodeSearchNetDoc(NamedTuple):
  class CodeSearchNetChallengeQrel (line 41) | class CodeSearchNetChallengeQrel(NamedTuple):
  class CodeSearchNetDocs (line 48) | class CodeSearchNetDocs(BaseDocs):
    method __init__ (line 49) | def __init__(self, docs_dlcs):
    method docs_iter (line 54) | def docs_iter(self):
    method docs_cls (line 70) | def docs_cls(self):
    method docs_store (line 73) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 84) | def docs_count(self):
    method docs_namespace (line 88) | def docs_namespace(self):
    method docs_lang (line 91) | def docs_lang(self):
  class CodeSearchNetQueries (line 95) | class CodeSearchNetQueries(BaseQueries):
    method __init__ (line 96) | def __init__(self, queries_dlcs, split):
    method queries_iter (line 101) | def queries_iter(self):
    method queries_cls (line 113) | def queries_cls(self):
    method queries_namespace (line 116) | def queries_namespace(self):
    method queries_lang (line 119) | def queries_lang(self):
  class CodeSearchNetQrels (line 123) | class CodeSearchNetQrels(BaseQrels):
    method __init__ (line 124) | def __init__(self, qrels_dlcs, split):
    method qrels_iter (line 129) | def qrels_iter(self):
    method qrels_cls (line 143) | def qrels_cls(self):
    method qrels_defs (line 146) | def qrels_defs(self):
    method queries_lang (line 149) | def queries_lang(self):
  class CodeSearchNetChallengeQueries (line 153) | class CodeSearchNetChallengeQueries(BaseQueries):
    method __init__ (line 154) | def __init__(self, queries_dlc):
    method queries_path (line 158) | def queries_path(self):
    method queries_iter (line 161) | def queries_iter(self):
    method queries_cls (line 169) | def queries_cls(self):
    method queries_namespace (line 172) | def queries_namespace(self):
  class CodeSearchNetChallengeQrels (line 176) | class CodeSearchNetChallengeQrels(BaseQrels):
    method __init__ (line 177) | def __init__(self, qrels_dlc, queries_handler):
    method qrels_path (line 182) | def qrels_path(self):
    method qrels_iter (line 185) | def qrels_iter(self):
    method qrels_cls (line 196) | def qrels_cls(self):
    method qrels_defs (line 199) | def qrels_defs(self):
  function _init (line 203) | def _init():

FILE: ir_datasets/datasets/cord19.py
  class Cord19Doc (line 24) | class Cord19Doc(NamedTuple):
    method default_text (line 30) | def default_text(self):
  class Cord19FullTextSection (line 37) | class Cord19FullTextSection(NamedTuple):
  class Cord19FullTextDoc (line 42) | class Cord19FullTextDoc(NamedTuple):
    method default_text (line 49) | def default_text(self):
  class Cord19Docs (line 71) | class Cord19Docs(BaseDocs):
    method __init__ (line 72) | def __init__(self, streamer, extr_path, date, include_fulltext=False, ...
    method docs_path (line 79) | def docs_path(self, force=True):
    method docs_cls (line 85) | def docs_cls(self):
    method docs_iter (line 88) | def docs_iter(self):
    method _docs_iter (line 91) | def _docs_iter(self):
    method docs_store (line 161) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 172) | def docs_count(self):
    method docs_namespace (line 176) | def docs_namespace(self):
    method docs_lang (line 179) | def docs_lang(self):
  function _init (line 183) | def _init():

FILE: ir_datasets/datasets/cranfield.py
  class CranfieldDoc (line 25) | class CranfieldDoc(NamedTuple):
    method default_text (line 31) | def default_text(self):
  function prefix_sentinel_splitter (line 38) | def prefix_sentinel_splitter(it, sentinel):
  class CranfieldDocs (line 48) | class CranfieldDocs(BaseDocs):
    method __init__ (line 49) | def __init__(self, docs_dlc):
    method docs_path (line 53) | def docs_path(self, force=True):
    method docs_iter (line 57) | def docs_iter(self):
    method docs_cls (line 77) | def docs_cls(self):
    method docs_store (line 80) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 91) | def docs_count(self):
    method docs_namespace (line 95) | def docs_namespace():
    method docs_lang (line 98) | def docs_lang(self):
  class CranfieldQueries (line 102) | class CranfieldQueries(BaseQueries):
    method __init__ (line 103) | def __init__(self, queries_dlc):
    method queries_path (line 107) | def queries_path(self):
    method queries_iter (line 110) | def queries_iter(self):
    method queries_cls (line 127) | def queries_cls(self):
    method queries_namespace (line 130) | def queries_namespace(self):
    method queries_lang (line 133) | def queries_lang(self):
  class CranfieldQrels (line 137) | class CranfieldQrels(BaseQrels):
    method __init__ (line 138) | def __init__(self, qrels_dlc):
    method qrels_path (line 141) | def qrels_path(self):
    method qrels_iter (line 144) | def qrels_iter(self):
    method qrels_cls (line 154) | def qrels_cls(self):
    method qrels_defs (line 157) | def qrels_defs(self):
  function _init (line 161) | def _init():

FILE: ir_datasets/datasets/csl.py
  class CslDoc (line 15) | class CslDoc(NamedTuple):
    method default_text (line 24) | def default_text(self):
  function _init (line 34) | def _init():

FILE: ir_datasets/datasets/disks45.py
  function _init (line 35) | def _init():
  function make_filter (line 98) | def make_filter(fold):

FILE: ir_datasets/datasets/dpr_w100.py
  class DprW100Doc (line 23) | class DprW100Doc(NamedTuple):
    method default_text (line 27) | def default_text(self):
  class DprW100Query (line 34) | class DprW100Query(NamedTuple):
    method default_text (line 38) | def default_text(self):
  class DprW100Manager (line 45) | class DprW100Manager:
    method __init__ (line 46) | def __init__(self, dlc, base_path, passage_id_key='passage_id'):
    method build (line 52) | def build(self):
    method file_ref (line 85) | def file_ref(self, path):
  class _ManagedDlc (line 89) | class _ManagedDlc:
    method __init__ (line 90) | def __init__(self, manager, path):
    method stream (line 95) | def stream(self):
    method path (line 100) | def path(self, force=True):
  class DprW100Queries (line 106) | class DprW100Queries(BaseQueries):
    method __init__ (line 107) | def __init__(self, dlc):
    method queries_iter (line 110) | def queries_iter(self):
    method queries_cls (line 116) | def queries_cls(self):
    method queries_namespace (line 119) | def queries_namespace(self):
    method queries_lang (line 122) | def queries_lang(self):
  function _init (line 126) | def _init():

FILE: ir_datasets/datasets/gov.py
  class GovWeb02Query (line 49) | class GovWeb02Query(NamedTuple):
    method default_text (line 53) | def default_text(self):
  class GovDoc (line 60) | class GovDoc(NamedTuple):
    method default_text (line 66) | def default_text(self):
  class GovDocs (line 70) | class GovDocs(BaseDocs):
    method __init__ (line 71) | def __init__(self, docs_dlc):
    method docs_path (line 75) | def docs_path(self, force=True):
    method docs_iter (line 78) | def docs_iter(self):
    method _docs_iter (line 81) | def _docs_iter(self):
    method docs_cls (line 87) | def docs_cls(self):
    method _docs_ctxt_iter_gov (line 90) | def _docs_ctxt_iter_gov(self, gov2f):
    method _process_gov_doc (line 106) | def _process_gov_doc(self, raw_doc):
    method _extract_next_block (line 129) | def _extract_next_block(self, inp, START, END):
    method docs_store (line 138) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 149) | def docs_count(self):
    method docs_namespace (line 153) | def docs_namespace(self):
    method docs_lang (line 156) | def docs_lang(self):
  function _init (line 160) | def _init():

FILE: ir_datasets/datasets/gov2.py
  class Gov2Doc (line 43) | class Gov2Doc(NamedTuple):
    method default_text (line 49) | def default_text(self):
  class Gov2DocIter (line 54) | class Gov2DocIter:
    method __init__ (line 55) | def __init__(self, gov2_docs, slice):
    method __next__ (line 64) | def __next__(self):
    method close (line 93) | def close(self):
    method __iter__ (line 96) | def __iter__(self):
    method __del__ (line 99) | def __del__(self):
    method __getitem__ (line 102) | def __getitem__(self, key):
  class Gov2Docs (line 118) | class Gov2Docs(BaseDocs):
    method __init__ (line 119) | def __init__(self, docs_dlc, doccount_dlc):
    method docs_path (line 125) | def docs_path(self, force=True):
    method _docs_iter_source_files (line 128) | def _docs_iter_source_files(self):
    method docs_iter (line 134) | def docs_iter(self):
    method docs_cls (line 137) | def docs_cls(self):
    method _docs_ctxt_iter_gov2 (line 140) | def _docs_ctxt_iter_gov2(self, gov2f):
    method _process_gov2_doc (line 156) | def _process_gov2_doc(self, raw_doc):
    method _extract_next_block (line 179) | def _extract_next_block(self, inp, START, END):
    method _docs_id_to_source_file (line 188) | def _docs_id_to_source_file(self, doc_id):
    method _docs_file_counts (line 196) | def _docs_file_counts(self):
    method docs_store (line 208) | def docs_store(self, options=ir_datasets.indices.DEFAULT_DOCSTORE_OPTI...
    method docs_count (line 212) | def docs_count(self):
    method docs_namespace (line 215) | def docs_namespace(self):
    method docs_lang (line 218) | def docs_lang(self):
  class Gov2Docstore (line 222) | class Gov2Docstore(Docstore):
    method __init__ (line 223) | def __init__(self, gov2_docs, options=ir_datasets.indices.DEFAULT_DOCS...
    method get_many_iter (line 227) | def get_many_iter(self, doc_ids):
  class RewriteQids (line 246) | class RewriteQids(BaseQrels):
    method __init__ (line 247) | def __init__(self, base_qrels, qid_map):
    method qrels_iter (line 251) | def qrels_iter(self):
    method qrels_defs (line 258) | def qrels_defs(self):
    method qrels_path (line 261) | def qrels_path(self):
    method qrels_cls (line 264) | def qrels_cls(self):
  class Gov2DocCountFile (line 268) | class Gov2DocCountFile:
    method __init__ (line 269) | def __init__(self, path, docs_dlc):
    method path (line 273) | def path(self, force=True):
    method stream (line 291) | def stream(self):
  function _init (line 295) | def _init():

FILE: ir_datasets/datasets/hc4.py
  function _init (line 22) | def _init():

FILE: ir_datasets/datasets/highwire.py
  class HighwireSpan (line 28) | class HighwireSpan(NamedTuple):
  class HighwireDoc (line 34) | class HighwireDoc(NamedTuple):
    method default_text (line 39) | def default_text(self):
  class TrecGenomicsQrel (line 46) | class TrecGenomicsQrel(NamedTuple):
  class HighwireQrel (line 54) | class HighwireQrel(NamedTuple):
  class HighwireDocs (line 62) | class HighwireDocs(BaseDocs):
    method __init__ (line 63) | def __init__(self, dlcs, legalspans_dlc):
    method docs_iter (line 67) | def docs_iter(self):
    method _docs_iter (line 70) | def _docs_iter(self):
    method docs_path (line 101) | def docs_path(self, force=True):
    method docs_store (line 104) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_cls (line 115) | def docs_cls(self):
    method docs_namespace (line 118) | def docs_namespace(self):
    method docs_count (line 121) | def docs_count(self):
    method docs_lang (line 125) | def docs_lang(self):
  class TrecGenomicsQueries (line 129) | class TrecGenomicsQueries(BaseQueries):
    method __init__ (line 130) | def __init__(self, queries_dlc):
    method queries_iter (line 133) | def queries_iter(self):
    method queries_cls (line 142) | def queries_cls(self):
    method queries_namespace (line 145) | def queries_namespace(self):
    method queries_lang (line 148) | def queries_lang(self):
  class HighwireQrels (line 152) | class HighwireQrels(BaseQrels):
    method __init__ (line 153) | def __init__(self, qrels_dlc, qrel_defs):
    method qrels_iter (line 157) | def qrels_iter(self):
    method qrels_defs (line 172) | def qrels_defs(self):
    method qrels_path (line 175) | def qrels_path(self):
    method qrels_cls (line 178) | def qrels_cls(self):
  function _init (line 182) | def _init():

FILE: ir_datasets/datasets/istella22.py
  class Istella22Doc (line 13) | class Istella22Doc(NamedTuple):
    method default_text (line 21) | def default_text(self):
  function _init (line 34) | def _init():
  function fold_qids_factory (line 71) | def fold_qids_factory(fold, base_dlc):

FILE: ir_datasets/datasets/kilt.py
  class KiltDocAnchor (line 25) | class KiltDocAnchor(NamedTuple):
  class KiltDoc (line 33) | class KiltDoc(NamedTuple):
    method default_text (line 46) | def default_text(self):
  function strip_markup (line 53) | def strip_markup(text):
  class KiltDocs (line 61) | class KiltDocs(BaseDocs):
    method __init__ (line 62) | def __init__(self, streamer, count_hint=None):
    method docs_iter (line 68) | def docs_iter(self):
    method docs_cls (line 90) | def docs_cls(self):
    method docs_store (line 93) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 104) | def docs_count(self):
    method docs_namespace (line 108) | def docs_namespace(self):
    method docs_lang (line 111) | def docs_lang(self):
    method docs_kilt_raw_iter (line 114) | def docs_kilt_raw_iter(self):
  function _init (line 120) | def _init():

FILE: ir_datasets/datasets/lotte.py
  class LotteQrels (line 18) | class LotteQrels(BaseQrels):
    method __init__ (line 19) | def __init__(self, qrels_dlc):
    method qrels_path (line 22) | def qrels_path(self):
    method qrels_iter (line 25) | def qrels_iter(self):
    method qrels_cls (line 32) | def qrels_cls(self):
    method qrels_defs (line 35) | def qrels_defs(self):
  function _init (line 39) | def _init():

FILE: ir_datasets/datasets/medline.py
  class MedlineDoc (line 35) | class MedlineDoc(NamedTuple):
    method default_text (line 39) | def default_text(self):
  class TrecGenomicsQuery (line 46) | class TrecGenomicsQuery(NamedTuple):
    method default_text (line 51) | def default_text(self):
  class TrecPm2017Query (line 58) | class TrecPm2017Query(NamedTuple):
    method default_text (line 64) | def default_text(self):
  class TrecPmQuery (line 71) | class TrecPmQuery(NamedTuple):
    method default_text (line 76) | def default_text(self):
  class ConcatFile (line 83) | class ConcatFile:
    method __init__ (line 88) | def __init__(self, files):
    method read (line 91) | def read(self, count=None):
  class MedlineDocs (line 100) | class MedlineDocs(BaseDocs):
    method __init__ (line 101) | def __init__(self, name, dlcs, count_hint=None):
    method docs_iter (line 107) | def docs_iter(self):
    method docs_path (line 141) | def docs_path(self, force=True):
    method docs_store (line 144) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_cls (line 156) | def docs_cls(self):
    method docs_namespace (line 159) | def docs_namespace(self):
    method docs_count (line 162) | def docs_count(self):
    method docs_lang (line 166) | def docs_lang(self):
  class AacrAscoDocs (line 170) | class AacrAscoDocs(BaseDocs):
    method __init__ (line 171) | def __init__(self, dlc):
    method docs_iter (line 175) | def docs_iter(self):
    method docs_path (line 194) | def docs_path(self, force=True):
    method docs_store (line 197) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_cls (line 207) | def docs_cls(self):
    method docs_namespace (line 210) | def docs_namespace(self):
    method docs_count (line 213) | def docs_count(self):
    method docs_lang (line 217) | def docs_lang(self):
  class ConcatDocs (line 221) | class ConcatDocs(BaseDocs):
    method __init__ (line 222) | def __init__(self, docs, count_hint=None):
    method docs_iter (line 226) | def docs_iter(self):
    method docs_iter (line 230) | def docs_iter(self):
    method docs_path (line 234) | def docs_path(self, force=True):
    method docs_store (line 237) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_cls (line 248) | def docs_cls(self):
    method docs_namespace (line 251) | def docs_namespace(self):
    method docs_lang (line 254) | def docs_lang(self):
    method docs_count (line 257) | def docs_count(self):
  function _init (line 262) | def _init():

FILE: ir_datasets/datasets/miracl.py
  class MiraclDoc (line 16) | class MiraclDoc(NamedTuple):
    method default_text (line 20) | def default_text(self):
  function _init (line 24) | def _init():

FILE: ir_datasets/datasets/mmarco.py
  function _init (line 19) | def _init():

FILE: ir_datasets/datasets/mr_tydi.py
  class MrTydiDocs (line 20) | class MrTydiDocs(BaseDocs):
    method __init__ (line 21) | def __init__(self, dlc, lang, count_hint=None):
    method docs_iter (line 28) | def docs_iter(self):
    method docs_cls (line 34) | def docs_cls(self):
    method docs_store (line 37) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 48) | def docs_count(self):
    method docs_namespace (line 52) | def docs_namespace(self):
    method docs_lang (line 55) | def docs_lang(self):
  function _init (line 59) | def _init():

FILE: ir_datasets/datasets/msmarco_document.py
  class MsMarcoDocument (line 30) | class MsMarcoDocument(NamedTuple):
    method default_text (line 35) | def default_text(self):
  class MsMarcoTrecDocs (line 43) | class MsMarcoTrecDocs(TrecDocs):
    method __init__ (line 44) | def __init__(self, docs_dlc):
    method docs_iter (line 48) | def docs_iter(self):
    method docs_cls (line 60) | def docs_cls(self):
    method docs_namespace (line 63) | def docs_namespace(self):
  class MsMarcoAnchorTextDocument (line 67) | class MsMarcoAnchorTextDocument(NamedTuple):
    method default_text (line 71) | def default_text(self):
  class MsMarcoAnchorTextDocs (line 78) | class MsMarcoAnchorTextDocs(BaseDocs):
    method __init__ (line 79) | def __init__(self, dlc, count_hint):
    method docs_iter (line 85) | def docs_iter(self):
    method docs_cls (line 91) | def docs_cls(self):
    method docs_store (line 94) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 105) | def docs_count(self):
    method docs_namespace (line 109) | def docs_namespace(self):
    method docs_lang (line 112) | def docs_lang(self):
  function _init (line 116) | def _init():

FILE: ir_datasets/datasets/msmarco_document_v2.py
  class MsMarcoV2Document (line 25) | class MsMarcoV2Document(NamedTuple):
    method default_text (line 31) | def default_text(self):
  class MsMarcoV2Docs (line 38) | class MsMarcoV2Docs(BaseDocs):
    method __init__ (line 39) | def __init__(self, dlc):
    method docs_iter (line 44) | def docs_iter(self):
    method docs_cls (line 61) | def docs_cls(self):
    method docs_store (line 64) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 94) | def docs_count(self):
    method docs_namespace (line 98) | def docs_namespace(self):
    method docs_lang (line 101) | def docs_lang(self):
  class MsMarcoV2AnchorTextDocument (line 106) | class MsMarcoV2AnchorTextDocument(NamedTuple):
    method default_text (line 110) | def default_text(self):
  class MsMarcoV2AnchorTextDocs (line 117) | class MsMarcoV2AnchorTextDocs(BaseDocs):
    method __init__ (line 118) | def __init__(self, dlc, count_hint):
    method docs_iter (line 124) | def docs_iter(self):
    method docs_cls (line 130) | def docs_cls(self):
    method docs_store (line 133) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 144) | def docs_count(self):
    method docs_namespace (line 148) | def docs_namespace(self):
    method docs_lang (line 151) | def docs_lang(self):
  function _init (line 155) | def _init():

FILE: ir_datasets/datasets/msmarco_passage.py
  class ExtractQidPid (line 44) | class ExtractQidPid:
    method __init__ (line 45) | def __init__(self, streamer):
    method stream (line 48) | def stream(self):
    method __iter__ (line 51) | def __iter__(self):
  class FixEncoding (line 63) | class FixEncoding:
    method __init__ (line 64) | def __init__(self, streamer):
    method stream (line 67) | def stream(self):
    method __iter__ (line 70) | def __iter__(self):
  class MapSmallTriplesQidPid (line 104) | class MapSmallTriplesQidPid:
    method __init__ (line 105) | def __init__(self, streamer, corpus_stream, queries_handler):
    method stream (line 110) | def stream(self):
    method __iter__ (line 113) | def __iter__(self):
  function _init (line 157) | def _init():

FILE: ir_datasets/datasets/msmarco_passage_v2.py
  class MsMarcoV2Passage (line 26) | class MsMarcoV2Passage(NamedTuple):
    method default_text (line 31) | def default_text(self):
  function parse_msmarco_passage (line 38) | def parse_msmarco_passage(line):
  class MsMarcoV2Passages (line 49) | class MsMarcoV2Passages(BaseDocs):
    method __init__ (line 50) | def __init__(self, dlc, pos_dlc=None):
    method docs_iter (line 56) | def docs_iter(self):
    method docs_cls (line 72) | def docs_cls(self):
    method docs_store (line 75) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 80) | def docs_count(self):
    method docs_namespace (line 84) | def docs_namespace(self):
    method docs_lang (line 87) | def docs_lang(self):
    method docs_path (line 90) | def docs_path(self, force=True):
  class MsMarcoV2DocStore (line 94) | class MsMarcoV2DocStore(ir_datasets.indices.Docstore):
    method __init__ (line 95) | def __init__(self, docs_handler, options=DEFAULT_DOCSTORE_OPTIONS):
    method get_many_iter (line 109) | def get_many_iter(self, keys):
    method build (line 142) | def build(self):
    method built (line 167) | def built(self):
    method __iter__ (line 170) | def __iter__(self):
    method _iter_source_files (line 174) | def _iter_source_files(self):
    method count (line 178) | def count(self):
  class MsMarcoV2PassageIter (line 185) | class MsMarcoV2PassageIter:
    method __init__ (line 186) | def __init__(self, docstore, slice):
    method __next__ (line 197) | def __next__(self):
    method close (line 229) | def close(self):
    method __iter__ (line 236) | def __iter__(self):
    method __del__ (line 239) | def __del__(self):
    method __getitem__ (line 242) | def __getitem__(self, key):
  function _init (line 258) | def _init():

FILE: ir_datasets/datasets/msmarco_qna.py
  class MsMarcoQnAQuery (line 29) | class MsMarcoQnAQuery(NamedTuple):
    method default_text (line 34) | def default_text(self):
  class MsMarcoQnAEvalQuery (line 41) | class MsMarcoQnAEvalQuery(NamedTuple):
    method default_text (line 45) | def default_text(self):
  class MsMarcoQnADoc (line 52) | class MsMarcoQnADoc(NamedTuple):
    method default_text (line 58) | def default_text(self):
  class MsMarcoQnAManager (line 96) | class MsMarcoQnAManager:
    method __init__ (line 97) | def __init__(self, train_dlc, dev_dlc, eval_dlc, base_path):
    method docs_store (line 104) | def docs_store(self, options: DocstoreOptions=DEFAULT_DOCSTORE_OPTIONS):
    method _internal_docs_store (line 108) | def _internal_docs_store(self, options: DocstoreOptions=DEFAULT_DOCSTO...
    method build (line 113) | def build(self):
    method file_ref (line 281) | def file_ref(self, path):
  class _ManagedDlc (line 285) | class _ManagedDlc:
    method __init__ (line 286) | def __init__(self, manager, path):
    method stream (line 291) | def stream(self):
    method path (line 296) | def path(self, force=True):
  function _init (line 302) | def _init():

FILE: ir_datasets/datasets/nano_beir.py
  function _map_field (line 19) | def _map_field(field, data):
  function parquet_iter (line 27) | def parquet_iter(path):
  class NanoBeirDocs (line 37) | class NanoBeirDocs(BaseDocs):
    method __init__ (line 38) | def __init__(self, name, dlc, doc_type):
    method docs_iter (line 44) | def docs_iter(self):
    method _docs_iter (line 47) | def _docs_iter(self):
    method docs_cls (line 51) | def docs_cls(self):
    method docs_store (line 54) | def docs_store(self, field="doc_id", options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 65) | def docs_count(self):
    method docs_namespace (line 69) | def docs_namespace(self):
    method docs_lang (line 72) | def docs_lang(self):
  class NanoBeirQueries (line 76) | class NanoBeirQueries(BaseQueries):
    method __init__ (line 77) | def __init__(self, name, dlc, query_type):
    method queries_iter (line 83) | def queries_iter(self):
    method queries_cls (line 87) | def queries_cls(self):
    method queries_namespace (line 90) | def queries_namespace(self):
    method queries_lang (line 93) | def queries_lang(self):
  class NanoBeirQrels (line 97) | class NanoBeirQrels(BaseQrels):
    method __init__ (line 98) | def __init__(self, qrels_dlc, qrels_defs):
    method qrels_path (line 102) | def qrels_path(self):
    method qrels_iter (line 105) | def qrels_iter(self):
    method qrels_cls (line 109) | def qrels_cls(self):
    method qrels_defs (line 112) | def qrels_defs(self):
  function _init (line 116) | def _init():

FILE: ir_datasets/datasets/natural_questions.py
  class NqPassageDoc (line 13) | class NqPassageDoc(NamedTuple):
    method default_text (line 24) | def default_text(self):
  class NqQrel (line 32) | class NqQrel(NamedTuple):
  class NqManager (line 40) | class NqManager:
    method __init__ (line 41) | def __init__(self, dlcs, base_path):
    method docs_store (line 46) | def docs_store(self, options: DocstoreOptions = DEFAULT_DOCSTORE_OPTIO...
    method _internal_docs_store (line 50) | def _internal_docs_store(self, options: DocstoreOptions = DEFAULT_DOCS...
    method build (line 55) | def build(self):
    method file_ref (line 138) | def file_ref(self, path):
  class _ManagedDlc (line 142) | class _ManagedDlc:
    method __init__ (line 143) | def __init__(self, manager, path):
    method stream (line 148) | def stream(self):
    method path (line 153) | def path(self, force=True):
  class NqQrels (line 159) | class NqQrels(BaseQrels):
    method __init__ (line 160) | def __init__(self, dlc):
    method qrels_iter (line 164) | def qrels_iter(self):
    method qrels_cls (line 170) | def qrels_cls(self):
    method qrels_defs (line 173) | def qrels_defs(self):
  class NqScoredDocs (line 177) | class NqScoredDocs(BaseScoredDocs):
    method __init__ (line 178) | def __init__(self, dlc):
    method scoreddocs_iter (line 182) | def scoreddocs_iter(self):
    method scoreddocs_cls (line 189) | def scoreddocs_cls(self):
  function _init (line 194) | def _init():

FILE: ir_datasets/datasets/neuclir.py
  function get_ids (line 24) | def get_ids(dlcs):
  class FilteredExctractedCCDocs (line 32) | class FilteredExctractedCCDocs(ExctractedCCDocs):
    method __init__ (line 33) | def __init__(self, docs_dlc, subset_lang, include_doc_id_dlc, filter_n...
    method _doc_store_path (line 38) | def _doc_store_path(self):
    method _internal_docs_iter (line 41) | def _internal_docs_iter(self):
  class FilteredTrecQrels (line 48) | class FilteredTrecQrels(TrecQrels):
    method __init__ (line 49) | def __init__(self, qrels_dlc, qrels_defs, include_doc_id_dlc, format_3...
    method qrels_iter (line 53) | def qrels_iter(self):
  class LangFilteredTrecQrels (line 60) | class LangFilteredTrecQrels(TrecQrels):
    method __init__ (line 61) | def __init__(self, qrels_dlc, qrels_defs, lang, format_3col=False):
    method qrels_iter (line 65) | def qrels_iter(self):
  function _init (line 77) | def _init():
  function _lazy_qids_set (line 138) | def _lazy_qids_set(qrels):

FILE: ir_datasets/datasets/neumarco.py
  function _init (line 13) | def _init():

FILE: ir_datasets/datasets/nfcorpus.py
  class NfCorpusDoc (line 20) | class NfCorpusDoc(NamedTuple):
    method default_text (line 25) | def default_text(self):
  class NfCorpusQuery (line 31) | class NfCorpusQuery(NamedTuple):
    method default_text (line 35) | def default_text(self):
  class NfCorpusVideoQuery (line 41) | class NfCorpusVideoQuery(NamedTuple):
    method default_text (line 45) | def default_text(self):
  class ZipQueries (line 51) | class ZipQueries(BaseQueries):
    method __init__ (line 52) | def __init__(self, queries, idxs, qtype):
    method queries_iter (line 57) | def queries_iter(self):
    method queries_cls (line 62) | def queries_cls(self):
    method queries_path (line 65) | def queries_path(self):
    method queries_namespace (line 68) | def queries_namespace(self):
    method queries_lang (line 71) | def queries_lang(self):
  function _init (line 75) | def _init():

FILE: ir_datasets/datasets/nyt.py
  class NytDoc (line 28) | class NytDoc(NamedTuple):
    method default_text (line 33) | def default_text(self):
  class NytDocs (line 41) | class NytDocs(BaseDocs):
    method __init__ (line 42) | def __init__(self, dlc):
    method docs_path (line 45) | def docs_path(self, force=True):
    method docs_cls (line 48) | def docs_cls(self):
    method docs_iter (line 51) | def docs_iter(self):
    method _docs_iter (line 54) | def _docs_iter(self):
    method docs_store (line 76) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 87) | def docs_count(self):
    method docs_namespace (line 91) | def docs_namespace(self):
    method docs_lang (line 94) | def docs_lang(self):
  class NytQueries (line 97) | class NytQueries(BaseQueries):
    method __init__ (line 98) | def __init__(self, collection):
    method queries_iter (line 101) | def queries_iter(self):
    method queries_namespace (line 105) | def queries_namespace(self):
    method queries_lang (line 108) | def queries_lang(self):
  class NytQrels (line 112) | class NytQrels(BaseQrels):
    method __init__ (line 113) | def __init__(self, collection):
    method qrels_iter (line 116) | def qrels_iter(self):
    method qrels_defs (line 120) | def qrels_defs(self):
  function _init (line 124) | def _init():

FILE: ir_datasets/datasets/pmc.py
  class PmcDoc (line 33) | class PmcDoc(NamedTuple):
    method default_text (line 39) | def default_text(self):
  class TrecCdsQuery (line 46) | class TrecCdsQuery(NamedTuple):
    method default_text (line 51) | def default_text(self):
  class TrecCds2016Query (line 58) | class TrecCds2016Query(NamedTuple):
    method default_text (line 64) | def default_text(self):
  class PmcDocs (line 71) | class PmcDocs(BaseDocs):
    method __init__ (line 72) | def __init__(self, dlcs, path, duplicate_dlcs=[], count_hint=None):
    method docs_iter (line 78) | def docs_iter(self):
    method _docs_iter (line 81) | def _docs_iter(self):
    method docs_path (line 116) | def docs_path(self, force=True):
    method docs_store (line 119) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_cls (line 130) | def docs_cls(self):
    method docs_namespace (line 133) | def docs_namespace(self):
    method docs_count (line 136) | def docs_count(self):
    method docs_lang (line 140) | def docs_lang(self):
  function _init (line 144) | def _init():

FILE: ir_datasets/datasets/sara.py
  class SaraDoc (line 23) | class SaraDoc(NamedTuple):
    method default_text (line 27) | def default_text(self):
  class SaraDocs (line 30) | class SaraDocs(BaseDocs):
    method __init__ (line 31) | def __init__(self,dlc):
    method docs_iter (line 35) | def docs_iter(self):
    method _docs_iter (line 38) | def _docs_iter(self):
    method docs_store (line 59) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 70) | def docs_count(self):
    method docs_namespace (line 74) | def docs_namespace(self):
    method docs_lang (line 77) | def docs_lang(self):
    method docs_cls (line 80) | def docs_cls(self):
  function _init (line 84) | def _init():

FILE: ir_datasets/datasets/touche.py
  function _init (line 53) | def _init():

FILE: ir_datasets/datasets/touche_image.py
  function _init (line 9) | def _init():

FILE: ir_datasets/datasets/trec_arabic.py
  function _init (line 22) | def _init():

FILE: ir_datasets/datasets/trec_cast.py
  class CastPassage (line 59) | class CastPassage(NamedTuple):
  class CastDoc (line 65) | class CastDoc(NamedTuple):
    method default_text (line 71) | def default_text(self):
  class CastPassageDoc (line 78) | class CastPassageDoc(NamedTuple):
    method default_text (line 84) | def default_text(self):
  class Cast2019Query (line 91) | class Cast2019Query(NamedTuple):
    method default_text (line 99) | def default_text(self):
  class Cast2020Query (line 106) | class Cast2020Query(NamedTuple):
    method default_text (line 115) | def default_text(self):
  class Cast2021Query (line 122) | class Cast2021Query(NamedTuple):
    method default_text (line 131) | def default_text(self):
  class Cast2022Query (line 138) | class Cast2022Query(NamedTuple):
    method default_text (line 149) | def default_text(self):
  class CastPassageIter (line 156) | class CastPassageIter:
    method __init__ (line 157) | def __init__(self, docstore, doc_psg_offsets, slice):
    method __next__ (line 172) | def __next__(self):
    method __iter__ (line 195) | def __iter__(self):
    method __getitem__ (line 198) | def __getitem__(self, key):
  class CastPassageDocstore (line 214) | class CastPassageDocstore(ir_datasets.indices.Docstore):
    method __init__ (line 215) | def __init__(self, docs_docstore, options=DEFAULT_DOCSTORE_OPTIONS):
    method get_many_iter (line 219) | def get_many_iter(self, doc_ids):
  class LazyCastPassageIter (line 236) | class LazyCastPassageIter:
    method __init__ (line 237) | def __init__(self, docs: "CastPassageDocs"):
    method __iter__ (line 243) | def __iter__(self):
    method __next__ (line 246) | def __next__(self):
    method __getitem__ (line 260) | def __getitem__(self, key):
  class CastPassageDocs (line 293) | class CastPassageDocs(BaseDocs):
    method __init__ (line 294) | def __init__(self, docs, count):
    method docs_iter (line 299) | def docs_iter(self):
    method docs_cls (line 302) | def docs_cls(self):
    method docs_store (line 305) | def docs_store(self, field="doc_id", options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 308) | def docs_count(self):
    method docs_namespace (line 311) | def docs_namespace(self):
    method docs_lang (line 314) | def docs_lang(self):
  class SegmentedDocs (line 318) | class SegmentedDocs(BaseTransformedDocs):
    method __init__ (line 327) | def __init__(self, docs, segments_dl: BaseDownload, store_name: str):
    method docs_iter (line 331) | def docs_iter(self):
  class CastQueries (line 358) | class CastQueries(BaseQueries):
    method __init__ (line 359) | def __init__(self, dlc, query_type):
    method queries_iter (line 364) | def queries_iter(self):
    method queries_cls (line 416) | def queries_cls(self):
    method queries_namespace (line 419) | def queries_namespace(self):
    method queries_lang (line 422) | def queries_lang(self):
  class WapoV4Docs (line 426) | class WapoV4Docs(IRDSDocuments):
    method __init__ (line 427) | def __init__(self, dsid: str):
    method docs_cls (line 430) | def docs_cls(self):
    method docs_iter (line 433) | def docs_iter(self):
  class KiltCastDocs (line 465) | class KiltCastDocs(TransformedDocs):
    method __init__ (line 466) | def __init__(self, dsid: str):
    method docs_iter (line 469) | def docs_iter(self):
    method transform (line 476) | def transform(self, doc):
  class WapoDupes (line 483) | class WapoDupes(Dupes):
    method doc_ids (line 485) | def doc_ids(self):
  function transform_msmarco_v1 (line 496) | def transform_msmarco_v1(doc):
  function transform_msmarco_v2 (line 502) | def transform_msmarco_v2(doc):
  function _init (line 507) | def _init():

FILE: ir_datasets/datasets/trec_fair.py
  class FairTrecDoc (line 22) | class FairTrecDoc(NamedTuple):
    method default_text (line 31) | def default_text(self):
  class FairTrec2022Doc (line 38) | class FairTrec2022Doc(NamedTuple):
    method default_text (line 62) | def default_text(self):
  class FairTrecQuery (line 69) | class FairTrecQuery(NamedTuple):
    method default_text (line 75) | def default_text(self):
  class FairTrec2022TrainQuery (line 81) | class FairTrec2022TrainQuery(NamedTuple):
    method default_text (line 85) | def default_text(self):
  class FairTrecEvalQuery (line 92) | class FairTrecEvalQuery(NamedTuple):
    method default_text (line 97) | def default_text(self):
  class FairTrecDocs (line 104) | class FairTrecDocs(BaseDocs):
    method __init__ (line 105) | def __init__(self, dlc, mlc):
    method docs_iter (line 110) | def docs_iter(self):
    method _docs_iter (line 113) | def _docs_iter(self):
    method docs_cls (line 147) | def docs_cls(self):
    method docs_store (line 150) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 162) | def docs_count(self):
    method docs_namespace (line 166) | def docs_namespace(self):
    method docs_lang (line 169) | def docs_lang(self):
  class FairTrecQueries (line 173) | class FairTrecQueries(BaseQueries):
    method __init__ (line 174) | def __init__(self, dlc, qtype):
    method queries_iter (line 179) | def queries_iter(self):
    method queries_cls (line 190) | def queries_cls(self):
    method queries_lang (line 193) | def queries_lang(self):
  class FairTrecQrels (line 196) | class FairTrecQrels(BaseQrels):
    method __init__ (line 197) | def __init__(self, qrels_dlc):
    method qrels_path (line 200) | def qrels_path(self):
    method qrels_iter (line 203) | def qrels_iter(self):
    method qrels_cls (line 210) | def qrels_cls(self):
    method qrels_defs (line 213) | def qrels_defs(self):
  class JsonlDocs (line 217) | class JsonlDocs(BaseDocs):
    method __init__ (line 218) | def __init__(self, dlc, metadata_dlc, doc_type, field_map, count_hint):
    method docs_iter (line 226) | def docs_iter(self):
    method _docs_iter_first (line 229) | def _docs_iter_first(self):
    method docs_cls (line 242) | def docs_cls(self):
    method docs_store (line 245) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 256) | def docs_count(self):
    method docs_namespace (line 260) | def docs_namespace(self):
    method docs_lang (line 263) | def docs_lang(self):
  function _init (line 266) | def _init():

FILE: ir_datasets/datasets/trec_mandarin.py
  class TrecMandarinQuery (line 11) | class TrecMandarinQuery(NamedTuple):
    method default_text (line 19) | def default_text(self):
  function _init (line 42) | def _init():

FILE: ir_datasets/datasets/trec_robust04.py
  function _init (line 33) | def _init():
  function make_filter (line 67) | def make_filter(fold):

FILE: ir_datasets/datasets/trec_spanish.py
  class TrecDescOnlyQuery (line 10) | class TrecDescOnlyQuery(NamedTuple):
    method default_text (line 13) | def default_text(self):
  class TrecSpanish3Query (line 19) | class TrecSpanish3Query(NamedTuple):
    method default_text (line 27) | def default_text(self):
  class TrecSpanish4Query (line 33) | class TrecSpanish4Query(NamedTuple):
    method default_text (line 39) | def default_text(self):
  class TrecSpanishTranslateQueries (line 65) | class TrecSpanishTranslateQueries:
    method __init__ (line 66) | def __init__(self, parent, query_cls):
    method __getattr__ (line 70) | def __getattr__(self, attr):
    method queries_iter (line 73) | def queries_iter(self):
    method queries_cls (line 92) | def queries_cls(self):
  function _init (line 96) | def _init():

FILE: ir_datasets/datasets/trec_tot.py
  class TipOfTheTongueDoc (line 10) | class TipOfTheTongueDoc(NamedTuple):
    method default_text (line 19) | def default_text(self):
  class TipOfTheTongueDoc2024 (line 25) | class TipOfTheTongueDoc2024(NamedTuple):
    method default_text (line 32) | def default_text(self):
  class TipOfTheTongueQuery2024 (line 38) | class TipOfTheTongueQuery2024(NamedTuple):
    method default_text (line 42) | def default_text(self):
  class TipOfTheTongueQuery (line 46) | class TipOfTheTongueQuery(NamedTuple):
    method default_text (line 54) | def default_text(self):
  function _init (line 61) | def _init():

FILE: ir_datasets/datasets/trec_tot_2025.py
  class JsonlDocumentOffset (line 18) | class JsonlDocumentOffset(NamedTuple):
  class TrecToT2025Doc (line 24) | class TrecToT2025Doc(NamedTuple):
    method _from_json (line 31) | def _from_json(json_doc):
    method default_text (line 34) | def default_text(self):
  class JsonlWithOffsetsDocsStore (line 38) | class JsonlWithOffsetsDocsStore(Docstore):
    method __init__ (line 39) | def __init__(self, docs, offsets, options=DEFAULT_DOCSTORE_OPTIONS):
    method offsets_iter (line 46) | def offsets_iter(self):
    method docs_dict (line 52) | def docs_dict(self):
    method get_many_iter (line 62) | def get_many_iter(self, doc_ids):
  class TrecToT2025DocsStore (line 73) | class TrecToT2025DocsStore(JsonlWithOffsetsDocsStore):
    method get_many_iter (line 74) | def get_many_iter(self, doc_ids):
  class JsonlDocumentsWithOffsets (line 79) | class JsonlDocumentsWithOffsets(BaseDocs):
    method __init__ (line 80) | def __init__(self, docs, offsets):
    method docs_iter (line 84) | def docs_iter(self):
    method docs_cls (line 89) | def docs_cls(self):
    method docs_store (line 92) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_namespace (line 95) | def docs_namespace(self):
    method docs_count (line 98) | def docs_count(self):
    method docs_lang (line 101) | def docs_lang(self):
  class TrecToT2025Dataset (line 105) | class TrecToT2025Dataset(Dataset):
    method __init__ (line 106) | def __init__(self, docs_jsonl_file, offset_jsonl_file, queries=None, q...
  function register_dataset (line 117) | def register_dataset():

FILE: ir_datasets/datasets/tripclick.py
  class ConcatQueries (line 41) | class ConcatQueries(BaseQueries):
    method __init__ (line 42) | def __init__(self, queries):
    method queries_iter (line 45) | def queries_iter(self):
    method queries_path (line 49) | def queries_path(self):
    method queries_cls (line 52) | def queries_cls(self):
    method queries_namespace (line 55) | def queries_namespace(self):
    method queries_lang (line 58) | def queries_lang(self):
  class ConcatQrels (line 62) | class ConcatQrels(BaseQrels):
    method __init__ (line 63) | def __init__(self, qrels):
    method qrels_iter (line 66) | def qrels_iter(self):
    method qrels_path (line 70) | def qrels_path(self):
    method qrels_cls (line 73) | def qrels_cls(self):
    method qrels_defs (line 76) | def qrels_defs(self):
  class ConcatScoreddocs (line 80) | class ConcatScoreddocs(BaseScoredDocs):
    method __init__ (line 81) | def __init__(self, scoreddocs):
    method scoreddocs_iter (line 84) | def scoreddocs_iter(self):
    method scoreddocs_path (line 88) | def scoreddocs_path(self, force=True):
    method scoreddocs_cls (line 91) | def scoreddocs_cls(self):
  class LogItem (line 95) | class LogItem(NamedTuple):
  class TripClickQlog (line 100) | class TripClickQlog(NamedTuple):
  class TripClickPartialDoc (line 108) | class TripClickPartialDoc(NamedTuple):
    method default_text (line 112) | def default_text(self):
  class TripClickQlogs (line 119) | class TripClickQlogs(BaseQlogs):
    method __init__ (line 120) | def __init__(self, dlc):
    method qlogs_iter (line 123) | def qlogs_iter(self):
    method qlogs_cls (line 143) | def qlogs_cls(self):
    method qlogs_count (line 146) | def qlogs_count(self):
  class DocPairGenerator (line 150) | class DocPairGenerator:
    method __init__ (line 151) | def __init__(self, docpair_dlc, collection, queries, cache_path):
    method path (line 157) | def path(self, force=True):
    method stream (line 191) | def stream(self):
  class FixAllarticles (line 200) | class FixAllarticles:
    method __init__ (line 201) | def __init__(self, streamer):
    method stream (line 204) | def stream(self):
    method __iter__ (line 207) | def __iter__(self):
  function _init (line 240) | def _init():

FILE: ir_datasets/datasets/tweets2013_ia.py
  class TweetDoc (line 49) | class TweetDoc(NamedTuple):
    method default_text (line 59) | def default_text(self):
  class TrecMb13Query (line 66) | class TrecMb13Query(NamedTuple):
    method default_text (line 71) | def default_text(self):
  class TrecMb14Query (line 78) | class TrecMb14Query(NamedTuple):
    method default_text (line 84) | def default_text(self):
  class TweetWriter (line 143) | class TweetWriter:
    method __init__ (line 144) | def __init__(self, base_path, max_tweets_per_block=100):
    method add (line 150) | def add(self, file_name, tweet_id, tweet_data):
    method flush (line 156) | def flush(self):
  class Tweets2013IaDocIter (line 171) | class Tweets2013IaDocIter:
    method __init__ (line 172) | def __init__(self, tweets_docs, slice):
    method __next__ (line 181) | def __next__(self):
    method close (line 210) | def close(self):
    method __iter__ (line 214) | def __iter__(self):
    method __del__ (line 217) | def __del__(self):
    method __getitem__ (line 220) | def __getitem__(self, key):
  class TweetsDocstore (line 236) | class TweetsDocstore(Docstore):
    method __init__ (line 237) | def __init__(self, tweets_docs, options=DEFAULT_DOCSTORE_OPTIONS):
    method get_many_iter (line 241) | def get_many_iter(self, doc_ids):
  class Tweets2013IaDocs (line 288) | class Tweets2013IaDocs(BaseDocs):
    method __init__ (line 289) | def __init__(self, docs_dlcs, base_path):
    method _id2file (line 294) | def _id2file(self, snowflake_id):
    method _docs_build (line 300) | def _docs_build(self):
    method docs_iter (line 360) | def docs_iter(self):
    method docs_cls (line 363) | def docs_cls(self):
    method docs_store (line 366) | def docs_store(self, options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_path (line 369) | def docs_path(self, force=False):
    method docs_count (line 372) | def docs_count(self, force=False):
    method docs_namespace (line 377) | def docs_namespace(self):
    method docs_lang (line 380) | def docs_lang(self):
    method _docs_file_counts (line 383) | def _docs_file_counts(self):
    method _docs_iter_source_files (line 394) | def _docs_iter_source_files(self):
    method _docs_ctxt_iter_tweets (line 397) | def _docs_ctxt_iter_tweets(self, source_file):
    method _docs_source_to_doc (line 405) | def _docs_source_to_doc(self, source, data):
  function _init (line 410) | def _init():

FILE: ir_datasets/datasets/vaswani.py
  function sentinel_splitter (line 19) | def sentinel_splitter(it, sentinel):
  class VaswaniDocs (line 25) | class VaswaniDocs(BaseDocs):
    method __init__ (line 26) | def __init__(self, docs_dlc):
    method docs_path (line 30) | def docs_path(self, force=True):
    method docs_iter (line 34) | def docs_iter(self):
    method docs_cls (line 42) | def docs_cls(self):
    method docs_store (line 45) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 56) | def docs_count(self):
    method docs_namespace (line 60) | def docs_namespace():
    method docs_lang (line 63) | def docs_lang(self):
  class VaswaniQueries (line 67) | class VaswaniQueries(BaseQueries):
    method __init__ (line 68) | def __init__(self, queries_dlc):
    method queries_path (line 72) | def queries_path(self):
    method queries_iter (line 75) | def queries_iter(self):
    method queries_cls (line 83) | def queries_cls(self):
    method queries_namespace (line 86) | def queries_namespace(self):
    method queries_lang (line 89) | def queries_lang(self):
  class VaswaniQrels (line 93) | class VaswaniQrels(BaseQrels):
    method __init__ (line 94) | def __init__(self, qrels_dlc):
    method qrels_path (line 97) | def qrels_path(self):
    method qrels_iter (line 100) | def qrels_iter(self):
    method qrels_cls (line 109) | def qrels_cls(self):
    method qrels_defs (line 112) | def qrels_defs(self):
  function _init (line 116) | def _init():

FILE: ir_datasets/datasets/wapo.py
  class WapoDocMedia (line 38) | class WapoDocMedia(NamedTuple):
  class WapoDoc (line 44) | class WapoDoc(NamedTuple):
    method default_text (line 54) | def default_text(self):
  class TrecBackgroundLinkingQuery (line 61) | class TrecBackgroundLinkingQuery(NamedTuple):
  class WapoDocs (line 67) | class WapoDocs(BaseDocs):
    method __init__ (line 68) | def __init__(self, dlc, file_name):
    method docs_path (line 72) | def docs_path(self, force=True):
    method docs_cls (line 75) | def docs_cls(self):
    method docs_iter (line 78) | def docs_iter(self):
    method _docs_iter (line 81) | def _docs_iter(self):
    method docs_wapo_raw_iter (line 129) | def docs_wapo_raw_iter(self):
    method docs_store (line 140) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 150) | def docs_count(self):
    method docs_namespace (line 154) | def docs_namespace(self):
    method docs_lang (line 157) | def docs_lang(self):
  function _init (line 161) | def _init():

FILE: ir_datasets/datasets/wikiclir.py
  class WikiClirQuery (line 19) | class WikiClirQuery(NamedTuple):
    method default_text (line 23) | def default_text(self):
  class WikiClirDoc (line 30) | class WikiClirDoc(NamedTuple):
    method default_text (line 34) | def default_text(self):
  function _init (line 41) | def _init():
  function _qid_filter (line 99) | def _qid_filter(qrels):

FILE: ir_datasets/datasets/wikir.py
  function _init (line 20) | def _init():

FILE: ir_datasets/formats/argsme.py
  class ArgsMeStance (line 17) | class ArgsMeStance(Enum):
    method from_json (line 26) | def from_json(json: str) -> "ArgsMeStance":
  class ArgsMeMode (line 35) | class ArgsMeMode(Enum):
    method from_json (line 40) | def from_json(json: str) -> "ArgsMeMode":
  class ArgsMeSourceDomain (line 49) | class ArgsMeSourceDomain(Enum):
    method from_json (line 57) | def from_json(json: str) -> "ArgsMeSourceDomain":
  class ArgsMePremiseAnnotation (line 72) | class ArgsMePremiseAnnotation(NamedTuple):
    method from_json (line 82) | def from_json(json: dict) -> "ArgsMePremiseAnnotation":
  class ArgsMePremise (line 89) | class ArgsMePremise(NamedTuple):
    method from_json (line 99) | def from_json(json: dict) -> "ArgsMePremise":
  class ArgsMeAspect (line 110) | class ArgsMeAspect(NamedTuple):
    method from_json (line 117) | def from_json(json: dict) -> "ArgsMeAspect":
  class ArgsMeSentence (line 125) | class ArgsMeSentence(NamedTuple):
    method from_json (line 130) | def from_json(json: dict) -> "ArgsMeSentence":
  class ArgsMeDoc (line 137) | class ArgsMeDoc(NamedTuple):
    method default_text (line 169) | def default_text(self):
    method from_json (line 176) | def from_json(json: dict) -> "ArgsMeDoc":
  class ArgsMeProcessedDoc (line 315) | class ArgsMeProcessedDoc(NamedTuple):
    method from_csv (line 349) | def from_csv(csv: dict) -> "ArgsMeProcessedDoc":
  class ArgsMeDocs (line 363) | class ArgsMeDocs(BaseDocs):
    method __init__ (line 369) | def __init__(
    method docs_path (line 381) | def docs_path(self):
    method docs_iter (line 385) | def docs_iter(self):
    method docs_store (line 393) | def docs_store(self, field="doc_id", options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 404) | def docs_count(self):
    method docs_cls (line 407) | def docs_cls(self):
    method docs_namespace (line 410) | def docs_namespace(self):
    method docs_lang (line 413) | def docs_lang(self):
  class ArgsMeProcessedDocs (line 417) | class ArgsMeProcessedDocs(BaseDocs):
    method __init__ (line 423) | def __init__(
    method docs_path (line 435) | def docs_path(self):
    method docs_iter (line 439) | def docs_iter(self):
    method docs_store (line 448) | def docs_store(self, field="doc_id", options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 459) | def docs_count(self):
    method docs_cls (line 462) | def docs_cls(self):
    method docs_namespace (line 465) | def docs_namespace(self):
    method docs_lang (line 468) | def docs_lang(self):
  class ArgsMeCombinedDocs (line 472) | class ArgsMeCombinedDocs(BaseDocs):
    method __init__ (line 479) | def __init__(
    method docs_path (line 493) | def docs_path(self):
    method docs_iter (line 497) | def docs_iter(self):
    method docs_store (line 502) | def docs_store(self, field="doc_id", options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 513) | def docs_count(self):
    method docs_cls (line 520) | def docs_cls(self):
    method docs_namespace (line 527) | def docs_namespace(self):
    method docs_lang (line 534) | def docs_lang(self):

FILE: ir_datasets/formats/base.py
  class GenericDoc (line 10) | class GenericDoc(NamedTuple):
    method default_text (line 13) | def default_text(self):
  class GenericQuery (line 16) | class GenericQuery(NamedTuple):
    method default_text (line 19) | def default_text(self):
  class GenericQrel (line 22) | class GenericQrel(NamedTuple):
  class GenericScoredDoc (line 27) | class GenericScoredDoc(NamedTuple):
  class GenericDocPair (line 32) | class GenericDocPair(NamedTuple):
  class BaseDocs (line 38) | class BaseDocs:
    method __getattr__ (line 42) | def __getattr__(self, attr):
    method docs_iter (line 48) | def docs_iter(self):
    method docs_count (line 51) | def docs_count(self):
    method docs_handler (line 54) | def docs_handler(self):
    method docs_cls (line 57) | def docs_cls(self):
    method docs_namespace (line 60) | def docs_namespace(self):
    method docs_lang (line 63) | def docs_lang(self):
  class BaseQueries (line 67) | class BaseQueries:
    method __getattr__ (line 71) | def __getattr__(self, attr):
    method queries_iter (line 77) | def queries_iter(self):
    method queries_handler (line 80) | def queries_handler(self):
    method queries_cls (line 83) | def queries_cls(self):
    method queries_namespace (line 86) | def queries_namespace(self):
    method queries_lang (line 89) | def queries_lang(self):
  class BaseQrels (line 93) | class BaseQrels:
    method __getattr__ (line 97) | def __getattr__(self, attr):
    method qrels_iter (line 103) | def qrels_iter(self):
    method qrels_defs (line 106) | def qrels_defs(self):
    method qrels_path (line 109) | def qrels_path(self):
    method qrels_cls (line 112) | def qrels_cls(self):
    method qrels_handler (line 115) | def qrels_handler(self):
  class BaseScoredDocs (line 119) | class BaseScoredDocs:
    method __getattr__ (line 123) | def __getattr__(self, attr):
    method scoreddocs_path (line 129) | def scoreddocs_path(self):
    method scoreddocs_iter (line 132) | def scoreddocs_iter(self):
    method scoreddocs_cls (line 135) | def scoreddocs_cls(self):
    method scoreddocs_handler (line 138) | def scoreddocs_handler(self):
  class BaseDocPairs (line 142) | class BaseDocPairs:
    method __getattr__ (line 146) | def __getattr__(self, attr):
    method docpairs_path (line 152) | def docpairs_path(self):
    method docpairs_iter (line 155) | def docpairs_iter(self):
    method docpairs_cls (line 158) | def docpairs_cls(self):
    method docpairs_handler (line 161) | def docpairs_handler(self):
  class BaseQlogs (line 165) | class BaseQlogs:
    method __getattr__ (line 169) | def __getattr__(self, attr):
    method qlogs_iter (line 175) | def qlogs_iter(self):
    method qlogs_cls (line 178) | def qlogs_cls(self):
    method qlogs_count (line 181) | def qlogs_count(self):
    method qlogs_handler (line 184) | def qlogs_handler(self):
  function qrels_dict (line 191) | def qrels_dict(qrels_handler):
  function hasher (line 201) | def hasher(iter_fn, hashfn=hashlib.md5):
  function _calc_metadata (line 218) | def _calc_metadata(iter_fn, metadata_fields=(), count_by_value_field=None):
  class DocstoreBackedDocs (line 263) | class DocstoreBackedDocs(BaseDocs):
    method __init__ (line 267) | def __init__(self, docstore_lazy, docs_cls=GenericDoc, namespace=None,...
    method docs_iter (line 274) | def docs_iter(self):
    method docs_count (line 277) | def docs_count(self):
    method docs_cls (line 281) | def docs_cls(self):
    method docs_namespace (line 284) | def docs_namespace(self):
    method docs_lang (line 287) | def docs_lang(self):
    method docs_store (line 290) | def docs_store(self):
  class DocSourceSeekableIter (line 296) | class DocSourceSeekableIter:
    method __next__ (line 297) | def __next__(self) -> NamedTuple:
    method seek (line 303) | def seek(self, pos):
    method close (line 309) | def close(self):
    method __enter__ (line 315) | def __enter__(self):
    method __exit__ (line 318) | def __exit__(self, exc_type, exc_val, exc_tb):
    method __iter__ (line 321) | def __iter__(self):
  class DocSource (line 325) | class DocSource:
    method __len__ (line 326) | def __len__(self) -> int:
    method __iter__ (line 332) | def __iter__(self) -> DocSourceSeekableIter:
  class SourceDocIter (line 339) | class SourceDocIter:
    method __init__ (line 340) | def __init__(self, docs, slice):
    method __next__ (line 349) | def __next__(self):
    method close (line 373) | def close(self):
    method __iter__ (line 378) | def __iter__(self):
    method __del__ (line 381) | def __del__(self):
    method __getitem__ (line 384) | def __getitem__(self, key):

FILE: ir_datasets/formats/clirmatrix.py
  class CLIRMatrixQueries (line 7) | class CLIRMatrixQueries(BaseQueries):
    method __init__ (line 8) | def __init__(self, streamer, query_lang):
    method queries_iter (line 13) | def queries_iter(self):
    method queries_namespace (line 25) | def queries_namespace(self):
    method queries_cls (line 28) | def queries_cls(self):
    method queries_lang (line 31) | def queries_lang(self):
  class CLIRMatrixQrels (line 35) | class CLIRMatrixQrels(TrecQrels):
    method qrels_iter (line 36) | def qrels_iter(self):

FILE: ir_datasets/formats/csv_fmt.py
  class _CsvBase (line 12) | class _CsvBase:
    method __init__ (line 13) | def __init__(self, dlc, cls, datatype):
    method _path (line 19) | def _path(self, force=True):
    method _iter (line 22) | def _iter(self):
  class CsvDocs (line 34) | class CsvDocs(_CsvBase, BaseDocs):
    method __init__ (line 35) | def __init__(self, docs_dlc, doc_cls=GenericDoc, doc_store_index_field...
    method docs_path (line 43) | def docs_path(self, force=True):
    method docs_iter (line 47) | def docs_iter(self):
    method docs_cls (line 50) | def docs_cls(self):
    method docs_store (line 53) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_namespace (line 65) | def docs_namespace(self):
    method docs_count (line 68) | def docs_count(self):
    method docs_lang (line 73) | def docs_lang(self):
  class CsvQueries (line 77) | class CsvQueries(_CsvBase, BaseQueries):
    method __init__ (line 78) | def __init__(self, queries_dlc, query_cls=GenericQuery, namespace=None...
    method queries_path (line 83) | def queries_path(self):
    method queries_iter (line 86) | def queries_iter(self):
    method queries_cls (line 89) | def queries_cls(self):
    method queries_namespace (line 92) | def queries_namespace(self):
    method queries_lang (line 95) | def queries_lang(self):
  class CsvDocPairs (line 99) | class CsvDocPairs(_CsvBase, BaseDocPairs):
    method __init__ (line 100) | def __init__(self, docpairs_dlc, docpair_cls=GenericDocPair):
    method docpairs_path (line 103) | def docpairs_path(self):
    method docpairs_iter (line 106) | def docpairs_iter(self):
    method docpairs_cls (line 109) | def docpairs_cls(self):

FILE: ir_datasets/formats/extracted_cc.py
  class ExctractedCCDoc (line 14) | class ExctractedCCDoc(NamedTuple):
    method default_text (line 21) | def default_text(self):
  class ExctractedCCDocs (line 28) | class ExctractedCCDocs(BaseDocs):
    method __init__ (line 30) | def __init__(self, docs_dlc, subset_lang=None, namespace=None, count=N...
    method docs_path (line 37) | def docs_path(self, force=True):
    method docs_iter (line 43) | def docs_iter(self):
    method _doc_store_path (line 46) | def _doc_store_path(self):
    method docs_store (line 49) | def docs_store(self):
    method _internal_docs_iter (line 59) | def _internal_docs_iter(self):
    method docs_cls (line 72) | def docs_cls(self):
    method docs_namespace (line 75) | def docs_namespace(self):
    method docs_count (line 78) | def docs_count(self):
    method docs_lang (line 81) | def docs_lang(self):
  class ExctractedCCQuery (line 85) | class ExctractedCCQuery(NamedTuple):
    method default_text (line 98) | def default_text(self):
  class ExctractedCCNoReportQuery (line 104) | class ExctractedCCNoReportQuery(NamedTuple):
    method default_text (line 116) | def default_text(self):
  class ExctractedCCNoReportNoHtNarQuery (line 122) | class ExctractedCCNoReportNoHtNarQuery(NamedTuple):
    method default_text (line 133) | def default_text(self):
  class ExctractedCCMultiMtQuery (line 140) | class ExctractedCCMultiMtQuery(NamedTuple):
    method default_text (line 154) | def default_text(self):
  class ExctractedCCQueries (line 161) | class ExctractedCCQueries(BaseQueries):
    method __init__ (line 162) | def __init__(self, queries_dlc, subset_lang=None, filter_lwq=True, cls...
    method queries_path (line 171) | def queries_path(self):
    method queries_cls (line 174) | def queries_cls(self):
    method queries_namespace (line 177) | def queries_namespace(self):
    method queries_iter (line 180) | def queries_iter(self):
    method _internal_queries_iter (line 184) | def _internal_queries_iter(self, dlc):
    method _produce_query (line 191) | def _produce_query(self, line):

FILE: ir_datasets/formats/jsonl.py
  class _JsonlBase (line 12) | class _JsonlBase:
    method __init__ (line 13) | def __init__(self, dlcs, cls, datatype, mapping=None):
    method _path (line 23) | def _path(self, force=True):
    method _iter (line 26) | def _iter(self):
  class JsonlDocs (line 34) | class JsonlDocs(_JsonlBase, BaseDocs):
    method __init__ (line 35) | def __init__(self, docs_dlcs, doc_cls=GenericDoc, mapping=None, doc_st...
    method docs_path (line 43) | def docs_path(self, force=True):
    method docs_iter (line 47) | def docs_iter(self):
    method docs_cls (line 50) | def docs_cls(self):
    method docs_store (line 53) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_namespace (line 65) | def docs_namespace(self):
    method docs_count (line 68) | def docs_count(self):
    method docs_lang (line 73) | def docs_lang(self):
  class JsonlQueries (line 77) | class JsonlQueries(_JsonlBase, BaseQueries):
    method __init__ (line 78) | def __init__(self, query_dlcs, query_cls=GenericQuery, mapping=None, l...
    method queries_path (line 83) | def queries_path(self, force=True):
    method queries_iter (line 86) | def queries_iter(self):
    method queries_cls (line 89) | def queries_cls(self):
    method queries_namespace (line 92) | def queries_namespace(self):
    method queries_lang (line 95) | def queries_lang(self):

FILE: ir_datasets/formats/ntcir.py
  class NtcirQrels (line 5) | class NtcirQrels(TrecQrels):
    method qrels_iter (line 6) | def qrels_iter(self):

FILE: ir_datasets/formats/touche.py
  class ToucheQuery (line 12) | class ToucheQuery(NamedTuple):
    method default_text (line 17) | def default_text(self):
  class ToucheTitleQuery (line 24) | class ToucheTitleQuery(NamedTuple):
    method default_text (line 27) | def default_text(self):
  class ToucheComparativeQuery (line 34) | class ToucheComparativeQuery(NamedTuple):
    method default_text (line 40) | def default_text(self):
  class ToucheQualityQrel (line 47) | class ToucheQualityQrel(NamedTuple):
  class ToucheQualityCoherenceQrel (line 55) | class ToucheQualityCoherenceQrel(NamedTuple):
  class ToucheComparativeStance (line 64) | class ToucheComparativeStance(Enum):
  class ToucheQualityComparativeStanceQrel (line 71) | class ToucheQualityComparativeStanceQrel(NamedTuple):
  class ToucheControversialStance (line 80) | class ToucheControversialStance(Enum):
  class ToucheControversialStanceQrel (line 86) | class ToucheControversialStanceQrel(NamedTuple):
  class TouchePassageDoc (line 93) | class TouchePassageDoc(NamedTuple):
    method default_text (line 97) | def default_text(self):
  class ToucheQueries (line 104) | class ToucheQueries(BaseQueries):
    method __init__ (line 109) | def __init__(
    method queries_path (line 119) | def queries_path(self):
    method queries_iter (line 122) | def queries_iter(self):
    method queries_cls (line 142) | def queries_cls(self):
    method queries_namespace (line 145) | def queries_namespace(self):
    method queries_lang (line 148) | def queries_lang(self):
  class ToucheTitleQueries (line 152) | class ToucheTitleQueries(BaseQueries):
    method __init__ (line 157) | def __init__(
    method queries_path (line 167) | def queries_path(self):
    method queries_iter (line 170) | def queries_iter(self):
    method queries_cls (line 186) | def queries_cls(self):
    method queries_namespace (line 189) | def queries_namespace(self):
    method queries_lang (line 192) | def queries_lang(self):
  class ToucheComparativeQueries (line 196) | class ToucheComparativeQueries(BaseQueries):
    method __init__ (line 201) | def __init__(
    method queries_path (line 211) | def queries_path(self):
    method queries_iter (line 214) | def queries_iter(self):
    method queries_cls (line 238) | def queries_cls(self):
    method queries_namespace (line 241) | def queries_namespace(self):
    method queries_lang (line 244) | def queries_lang(self):
  class ToucheQrels (line 248) | class ToucheQrels(BaseQrels):
    method __init__ (line 253) | def __init__(
    method qrels_path (line 263) | def qrels_path(self):
    method qrels_iter (line 266) | def qrels_iter(self):
    method qrels_cls (line 299) | def qrels_cls(self):
    method qrels_defs (line 302) | def qrels_defs(self):
  class ToucheQualityQrels (line 306) | class ToucheQualityQrels(BaseQrels):
    method __init__ (line 311) | def __init__(
    method qrels_path (line 321) | def qrels_path(self):
    method qrels_iter (line 324) | def qrels_iter(self):
    method qrels_cls (line 384) | def qrels_cls(self):
    method qrels_defs (line 387) | def qrels_defs(self):
  class ToucheQualityCoherenceQrels (line 391) | class ToucheQualityCoherenceQrels(BaseQrels):
    method __init__ (line 397) | def __init__(
    method qrels_path (line 409) | def qrels_path(self):
    method qrels_iter (line 412) | def qrels_iter(self):
    method qrels_cls (line 506) | def qrels_cls(self):
    method qrels_defs (line 509) | def qrels_defs(self):
  class ToucheQualityComparativeStanceQrels (line 513) | class ToucheQualityComparativeStanceQrels(BaseQrels):
    method __init__ (line 519) | def __init__(
    method qrels_path (line 531) | def qrels_path(self):
    method qrels_iter (line 534) | def qrels_iter(self):
    method qrels_cls (line 626) | def qrels_cls(self):
    method qrels_defs (line 629) | def qrels_defs(self):
  class ToucheControversialStanceQrels (line 633) | class ToucheControversialStanceQrels(BaseQrels):
    method __init__ (line 637) | def __init__(self, source: Any, definitions: Dict[int, str]):
    method qrels_path (line 641) | def qrels_path(self):
    method qrels_iter (line 644) | def qrels_iter(self):
    method qrels_cls (line 669) | def qrels_cls(self):
    method qrels_defs (line 672) | def qrels_defs(self):
  class TouchePassageDocs (line 676) | class TouchePassageDocs(BaseDocs):
    method __init__ (line 682) | def __init__(
    method docs_path (line 694) | def docs_path(self):
    method docs_iter (line 698) | def docs_iter(self):
    method docs_store (line 709) | def docs_store(self, field="doc_id", options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 720) | def docs_count(self):
    method docs_cls (line 723) | def docs_cls(self):
    method docs_namespace (line 726) | def docs_namespace(self):
    method docs_lang (line 729) | def docs_lang(self):

FILE: ir_datasets/formats/touche_image.py
  class ToucheImageRanking (line 13) | class ToucheImageRanking(NamedTuple):
  class ToucheImageNode (line 19) | class ToucheImageNode(NamedTuple):
  class ToucheImagePage (line 29) | class ToucheImagePage(NamedTuple):
  class ToucheImageDoc (line 41) | class ToucheImageDoc(NamedTuple):
  class ToucheImageDocs (line 56) | class ToucheImageDocs(BaseDocs):
    method __init__ (line 64) | def __init__(
    method docs_path (line 80) | def docs_path(self):
    method docs_iter (line 84) | def docs_iter(self):
    method docs_store (line 222) | def docs_store(self, field="doc_id", options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 233) | def docs_count(self):
    method docs_cls (line 236) | def docs_cls(self):
    method docs_namespace (line 239) | def docs_namespace(self):
    method docs_lang (line 242) | def docs_lang(self):

FILE: ir_datasets/formats/trec.py
  class TrecDoc (line 16) | class TrecDoc(NamedTuple):
    method default_text (line 20) | def default_text(self):
  class TitleUrlTextDoc (line 26) | class TitleUrlTextDoc(NamedTuple):
    method default_text (line 31) | def default_text(self):
  class TrecParsedDoc (line 37) | class TrecParsedDoc(NamedTuple):
    method default_text (line 42) | def default_text(self):
  class TrecQuery (line 48) | class TrecQuery(NamedTuple):
    method default_text (line 53) | def default_text(self):
  class TrecSubtopic (line 59) | class TrecSubtopic(NamedTuple):
  class TrecQrel (line 64) | class TrecQrel(NamedTuple):
  class TrecSubQrel (line 70) | class TrecSubQrel(NamedTuple):
  class TrecPrel (line 76) | class TrecPrel(NamedTuple):
  class TrecDocs (line 86) | class TrecDocs(BaseDocs):
    method __init__ (line 87) | def __init__(self, docs_dlc, encoding=None, path_globs=None, content_t...
    method docs_path (line 113) | def docs_path(self, force=True):
    method docs_iter (line 117) | def docs_iter(self):
    method _docs_iter (line 153) | def _docs_iter(self, path):
    method _parser_bs (line 171) | def _parser_bs(self, stream):
    method _parser_text (line 196) | def _parser_text(self, stream):
    method _parser_tut (line 216) | def _parser_tut(self, stream):
    method _parser_sax (line 238) | def _parser_sax(self, stream):
    method docs_cls (line 257) | def docs_cls(self):
    method docs_store (line 260) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_count (line 276) | def docs_count(self):
    method docs_namespace (line 280) | def docs_namespace(self):
    method docs_lang (line 283) | def docs_lang(self):
  class TrecQueries (line 293) | class TrecQueries(BaseQueries):
    method __init__ (line 294) | def __init__(self, queries_dlc, qtype=TrecQuery, qtype_map=None, encod...
    method queries_path (line 303) | def queries_path(self):
    method queries_iter (line 306) | def queries_iter(self):
    method queries_cls (line 328) | def queries_cls(self):
    method queries_namespace (line 331) | def queries_namespace(self):
    method queries_lang (line 334) | def queries_lang(self):
  class TrecXmlQueries (line 338) | class TrecXmlQueries(BaseQueries):
    method __init__ (line 339) | def __init__(self, queries_dlc, qtype=TrecQuery, qtype_map=None, encod...
    method queries_path (line 348) | def queries_path(self):
    method queries_iter (line 351) | def queries_iter(self):
    method queries_cls (line 382) | def queries_cls(self):
    method queries_namespace (line 385) | def queries_namespace(self):
    method queries_lang (line 388) | def queries_lang(self):
  class TrecColonQueries (line 392) | class TrecColonQueries(BaseQueries):
    method __init__ (line 393) | def __init__(self, queries_dlc, encoding=None, namespace=None, lang=No...
    method queries_iter (line 399) | def queries_iter(self):
    method queries_path (line 407) | def queries_path(self):
    method queries_cls (line 410) | def queries_cls(self):
    method queries_namespace (line 413) | def queries_namespace(self):
    method queries_lang (line 416) | def queries_lang(self):
  class TrecQrels (line 420) | class TrecQrels(BaseQrels):
    method __init__ (line 421) | def __init__(self, qrels_dlc, qrels_defs, format_3col=False):
    method qrels_path (line 426) | def qrels_path(self):
    method qrels_iter (line 429) | def qrels_iter(self):
    method _qrels_internal_iter (line 436) | def _qrels_internal_iter(self, dlc):
    method qrels_cls (line 454) | def qrels_cls(self):
    method qrels_defs (line 457) | def qrels_defs(self):
  class TrecPrels (line 461) | class TrecPrels(TrecQrels):
    method qrels_iter (line 462) | def qrels_iter(self):
    method qrels_cls (line 474) | def qrels_cls(self):
  class TrecSubQrels (line 478) | class TrecSubQrels(BaseQrels):
    method __init__ (line 479) | def __init__(self, qrels_dlc, qrels_defs):
    method qrels_path (line 483) | def qrels_path(self):
    method qrels_iter (line 486) | def qrels_iter(self):
    method _qrels_internal_iter (line 493) | def _qrels_internal_iter(self, dlc):
    method qrels_cls (line 506) | def qrels_cls(self):
    method qrels_defs (line 509) | def qrels_defs(self):
  class TrecScoredDocs (line 513) | class TrecScoredDocs(BaseScoredDocs):
    method __init__ (line 514) | def __init__(self, scoreddocs_dlc, negate_score=False):
    method scoreddocs_path (line 518) | def scoreddocs_path(self):
    method scoreddocs_iter (line 521) | def scoreddocs_iter(self):

FILE: ir_datasets/formats/tsv.py
  class FileLineIter (line 9) | class FileLineIter:
    method __init__ (line 10) | def __init__(self, dlc, start=None, stop=None, step=1):
    method __next__ (line 20) | def __next__(self):
    method __iter__ (line 47) | def __iter__(self):
    method __del__ (line 50) | def __del__(self):
    method __getitem__ (line 53) | def __getitem__(self, key):
  class TsvIter (line 84) | class TsvIter:
    method __init__ (line 85) | def __init__(self, cls, line_iter):
    method __iter__ (line 89) | def __iter__(self):
    method __next__ (line 92) | def __next__(self):
    method __getitem__ (line 110) | def __getitem__(self, key):
  class _TsvBase (line 114) | class _TsvBase:
    method __init__ (line 115) | def __init__(self, dlc, cls, datatype, skip_first_line=False):
    method _path (line 122) | def _path(self, force=True):
    method _iter (line 125) | def _iter(self):
  class TsvDocs (line 133) | class TsvDocs(_TsvBase, BaseDocs):
    method __init__ (line 134) | def __init__(self, docs_dlc, doc_cls=GenericDoc, doc_store_index_field...
    method docs_path (line 142) | def docs_path(self, force=True):
    method docs_iter (line 146) | def docs_iter(self):
    method docs_cls (line 149) | def docs_cls(self):
    method docs_store (line 152) | def docs_store(self, field='doc_id', options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_namespace (line 165) | def docs_namespace(self):
    method docs_count (line 168) | def docs_count(self):
    method docs_lang (line 173) | def docs_lang(self):
  class TsvQueries (line 177) | class TsvQueries(_TsvBase, BaseQueries):
    method __init__ (line 178) | def __init__(self, queries_dlc, query_cls=GenericQuery, namespace=None...
    method queries_path (line 183) | def queries_path(self):
    method queries_iter (line 186) | def queries_iter(self):
    method queries_cls (line 189) | def queries_cls(self):
    method queries_namespace (line 192) | def queries_namespace(self):
    method queries_lang (line 195) | def queries_lang(self):
  class TsvDocPairs (line 199) | class TsvDocPairs(_TsvBase, BaseDocPairs):
    method __init__ (line 200) | def __init__(self, docpairs_dlc, docpair_cls=GenericDocPair):
    method docpairs_path (line 203) | def docpairs_path(self):
    method docpairs_iter (line 206) | def docpairs_iter(self):
    method docpairs_cls (line 209) | def docpairs_cls(self):

FILE: ir_datasets/formats/webarc.py
  class WarcDoc (line 10) | class WarcDoc(NamedTuple):
    method default_text (line 17) | def default_text(self):
  class WarcDocs (line 25) | class WarcDocs(BaseDocs):
    method __init__ (line 26) | def __init__(self, id_header='WARC-TREC-ID', warc_cw09=False, lang=None):
    method docs_iter (line 32) | def docs_iter(self):
    method _docs_warc_lib (line 35) | def _docs_warc_lib(self):
    method _docs_ctxt_iter_warc (line 40) | def _docs_ctxt_iter_warc(self, warcf):
    method docs_path (line 67) | def docs_path(self, force=True):
    method _docs_iter_source_files (line 70) | def _docs_iter_source_files(self):
    method _docs_id_to_source_file (line 73) | def _docs_id_to_source_file(self, doc_id):
    method _docs_warc_file_counts (line 77) | def _docs_warc_file_counts(self):
    method _docs_source_file_to_checkpoint (line 80) | def _docs_source_file_to_checkpoint(self, source_file):
    method docs_store (line 84) | def docs_store(self, options=ir_datasets.indices.DEFAULT_DOCSTORE_OPTI...
    method docs_cls (line 88) | def docs_cls(self):
    method docs_count (line 91) | def docs_count(self):
    method docs_lang (line 94) | def docs_lang(self):

FILE: ir_datasets/indices/base.py
  class FileAccess (line 5) | class FileAccess(Enum):
  class DocstoreOptions (line 12) | class DocstoreOptions:
  class Docstore (line 19) | class Docstore:
    method __init__ (line 20) | def __init__(self, doc_cls, id_field='doc_id', options: DocstoreOption...
    method get (line 26) | def get(self, doc_id, field=None):
    method get_many (line 32) | def get_many(self, doc_ids, field=None):
    method get_many_iter (line 42) | def get_many_iter(self, doc_ids):
    method clear_cache (line 45) | def clear_cache(self):

FILE: ir_datasets/indices/cache_docstore.py
  class CacheDocstore (line 7) | class CacheDocstore(Docstore):
    method __init__ (line 8) | def __init__(self, full_store, path, cache_cls=Lz4PickleLookup, option...
    method get_many_iter (line 14) | def get_many_iter(self, doc_ids):
    method clear_cache (line 26) | def clear_cache(self):

FILE: ir_datasets/indices/clueweb_warc.py
  class WarcIndexFile (line 8) | class WarcIndexFile:
    method __init__ (line 9) | def __init__(self, fileobj, mode, doc_id_size=25):
    method write (line 15) | def write(self, doc_id, doc_idx, state, pos, out_offset):
    method read (line 28) | def read(self):
    method peek_doc_id (line 45) | def peek_doc_id(self):
    method peek_doc_idx (line 48) | def peek_doc_idx(self):
    method __bool__ (line 54) | def __bool__(self):
    method __enter__ (line 58) | def __enter__(self):
    method __exit__ (line 61) | def __exit__(self, exc_type, exc_val, exc_tb):
    method close (line 64) | def close(self):
  class ClueWebWarcIndex (line 68) | class ClueWebWarcIndex:
    method __init__ (line 69) | def __init__(self, source_path, index_path, id_field='WARC-TREC-ID', w...
    method build (line 76) | def build(self, checkpoint_freq=8*1024*1024):
    method built (line 100) | def built(self):
    method get_many_iter (line 103) | def get_many_iter(self, doc_ids, docs_obj):
  class ClueWebWarcDocstore (line 132) | class ClueWebWarcDocstore(Docstore):
    method __init__ (line 133) | def __init__(self, warc_docs, options=None):
    method get_many_iter (line 139) | def get_many_iter(self, doc_ids):
  class WarcIter (line 162) | class WarcIter:
    method __init__ (line 163) | def __init__(self, warc_docs, slice):
    method __next__ (line 174) | def __next__(self):
    method close (line 221) | def close(self):
    method __iter__ (line 233) | def __iter__(self):
    method __del__ (line 236) | def __del__(self):
    method __getitem__ (line 239) | def __getitem__(self, key):

FILE: ir_datasets/indices/indexed_tsv_docstore.py
  class ZPickleKeyValueStore (line 14) | class ZPickleKeyValueStore:
    method __init__ (line 15) | def __init__(self, path, value_encoder=None):
    method built (line 20) | def built(self):
    method idx (line 23) | def idx(self):
    method bin (line 28) | def bin(self):
    method purge (line 33) | def purge(self):
    method transaction (line 42) | def transaction(self):
    method __getitem__ (line 47) | def __getitem__(self, value):
    method path (line 68) | def path(self, force=True):
    method __iter__ (line 71) | def __iter__(self):
    method __len__ (line 83) | def __len__(self):
  class IndexedTsvKeyValueStore (line 89) | class IndexedTsvKeyValueStore:
    method __init__ (line 90) | def __init__(self, path, value_encoder=None):
    method built (line 96) | def built(self):
    method idx (line 99) | def idx(self):
    method tsv (line 104) | def tsv(self):
    method purge (line 109) | def purge(self):
    method transaction (line 118) | def transaction(self):
    method __getitem__ (line 123) | def __getitem__(self, value):
    method path (line 156) | def path(self, force=True):
    method __iter__ (line 159) | def __iter__(self):
    method __len__ (line 179) | def __len__(self):
  class IndexedTsvDocStoreTransaction (line 184) | class IndexedTsvDocStoreTransaction:
    method __init__ (line 185) | def __init__(self, docstore):
    method __enter__ (line 191) | def __enter__(self):
    method __exit__ (line 194) | def __exit__(self, exc_type, exc_val, exc_tb):
    method commit (line 200) | def commit(self):
    method discard (line 207) | def discard(self):
    method add (line 210) | def add(self, key, fields):
  class ZPickleDocStoreTransaction (line 221) | class ZPickleDocStoreTransaction:
    method __init__ (line 222) | def __init__(self, docstore):
    method __enter__ (line 228) | def __enter__(self):
    method __exit__ (line 231) | def __exit__(self, exc_type, exc_val, exc_tb):
    method commit (line 237) | def commit(self):
    method discard (line 242) | def discard(self):
    method add (line 245) | def add(self, key, fields):
  class NumpyPosIndex (line 255) | class NumpyPosIndex:
    method __init__ (line 256) | def __init__(self, path):
    method add (line 265) | def add(self, did, idx):
    method commit (line 270) | def commit(self):
    method _lazy_load (line 287) | def _lazy_load(self):
    method get (line 295) | def get(self, did):
    method close (line 303) | def close(self):
    method __iter__ (line 312) | def __iter__(self):
    method __len__ (line 318) | def __len__(self):
  function dir_size (line 324) | def dir_size(path):
  class IndexedTsvDocstore (line 336) | class IndexedTsvDocstore:
    method __init__ (line 339) | def __init__(self, path, doc_cls, value_encoder='json', id_field='doc_...
    method built (line 346) | def built(self):
    method purge (line 349) | def purge(self):
    method build (line 352) | def build(self, documents):
    method get (line 357) | def get(self, did, field=None):
    method get_many (line 363) | def get_many(self, dids, field=None):
    method num_docs (line 372) | def num_docs(self):
    method docids (line 375) | def docids(self):
    method iter_docs (line 378) | def iter_docs(self):
    method path (line 382) | def path(self, force=True):
    method file_size (line 385) | def file_size(self):

FILE: ir_datasets/indices/lz4_pickle.py
  function _read_next (line 20) | def _read_next(f, data_cls):
  function _skip_next (line 29) | def _skip_next(f):
  function _write_next (line 34) | def _write_next(f, record):
  function safe_str (line 44) | def safe_str(s):
  class Lz4PickleIter (line 48) | class Lz4PickleIter:
    method __init__ (line 49) | def __init__(self, lookup, slice):
    method __next__ (line 56) | def __next__(self):
    method __iter__ (line 83) | def __iter__(self):
    method __del__ (line 86) | def __del__(self):
    method __getitem__ (line 95) | def __getitem__(self, key):
  class Lz4PickleLookup (line 111) | class Lz4PickleLookup:
    method __init__ (line 112) | def __init__(
    method bin (line 145) | def bin(self):
    method pos (line 166) | def pos(self):
    method idx (line 171) | def idx(self):
    method close (line 176) | def close(self):
    method clear (line 187) | def clear(self):
    method __del__ (line 195) | def __del__(self):
    method transaction (line 199) | def transaction(self):
    method __getitem__ (line 210) | def __getitem__(self, values):
    method path (line 231) | def path(self, force=True):
    method __iter__ (line 234) | def __iter__(self):
    method __len__ (line 237) | def __len__(self):
  class Lz4PickleTransaction (line 242) | class Lz4PickleTransaction:
    method __init__ (line 243) | def __init__(self, lookup):
    method __enter__ (line 251) | def __enter__(self):
    method __exit__ (line 263) | def __exit__(self, exc_type, exc_val, exc_tb):
    method commit (line 270) | def commit(self):
    method rollback (line 282) | def rollback(self):
    method add (line 294) | def add(self, record):
  class PickleLz4FullStore (line 307) | class PickleLz4FullStore(Docstore):
    method __init__ (line 308) | def __init__(
    method get_many_iter (line 334) | def get_many_iter(self, keys):
    method build (line 338) | def build(self):
    method built (line 355) | def built(self):
    method clear_cache (line 358) | def clear_cache(self):
    method __iter__ (line 361) | def __iter__(self):
    method count (line 365) | def count(self):

FILE: ir_datasets/indices/numpy_sorted_index.py
  class NumpySortedIndex (line 5) | class NumpySortedIndex:
    method __init__ (line 6) | def __init__(self, path, file_access=FileAccess.MMAP):
    method add (line 16) | def add(self, key, idx):
    method commit (line 21) | def commit(self):
    method _exists (line 46) | def _exists(self):
    method _lazy_load (line 49) | def _lazy_load(self):
    method __getitem__ (line 64) | def __getitem__(self, keys):
    method close (line 76) | def close(self):
    method clear (line 85) | def clear(self):
    method __del__ (line 92) | def __del__(self):
    method __iter__ (line 95) | def __iter__(self):
    method __len__ (line 102) | def __len__(self):
  class NumpyPosIndex (line 110) | class NumpyPosIndex:
    method __init__ (line 111) | def __init__(self, path, file_access=FileAccess.MMAP):
    method add (line 118) | def add(self, idx):
    method commit (line 123) | def commit(self):
    method _exists (line 139) | def _exists(self):
    method _lazy_load (line 142) | def _lazy_load(self):
    method __getitem__ (line 153) | def __getitem__(self, idxs):
    method close (line 163) | def close(self):
    method clear (line 168) | def clear(self):
    method __del__ (line 173) | def __del__(self):
    method __iter__ (line 176) | def __iter__(self):
    method __len__ (line 183) | def __len__(self):

FILE: ir_datasets/indices/zpickle_docstore.py
  class ZPickleKeyValueStore (line 15) | class ZPickleKeyValueStore:
    method __init__ (line 16) | def __init__(self, path, id_idx, doc_cls):
    method built (line 23) | def built(self):
    method idx (line 26) | def idx(self):
    method bin (line 31) | def bin(self):
    method purge (line 36) | def purge(self):
    method transaction (line 45) | def transaction(self):
    method __getitem__ (line 50) | def __getitem__(self, value):
    method path (line 72) | def path(self, force=True):
    method __iter__ (line 75) | def __iter__(self):
    method __len__ (line 88) | def __len__(self):
  class ZPickleDocStoreTransaction (line 93) | class ZPickleDocStoreTransaction:
    method __init__ (line 94) | def __init__(self, docstore):
    method __enter__ (line 100) | def __enter__(self):
    method __exit__ (line 103) | def __exit__(self, exc_type, exc_val, exc_tb):
    method commit (line 109) | def commit(self):
    method discard (line 114) | def discard(self):
    method add (line 117) | def add(self, key, fields):
  class ZPickleDocStore (line 127) | class ZPickleDocStore:
    method __init__ (line 130) | def __init__(self, path, doc_cls, id_field='doc_id'):
    method built (line 137) | def built(self):
    method purge (line 140) | def purge(self):
    method build (line 143) | def build(self, documents):
    method get (line 148) | def get(self, did, field=None):
    method get_many (line 153) | def get_many(self, dids, field=None):
    method num_docs (line 162) | def num_docs(self):
    method docids (line 165) | def docids(self):
    method __iter__ (line 168) | def __iter__(self):
    method path (line 171) | def path(self, force=True):

FILE: ir_datasets/lazy_libs.py
  function numpy (line 5) | def numpy():
  function tqdm (line 12) | def tqdm():
  function requests (line 19) | def requests():
  function bs4 (line 26) | def bs4():
  function inscriptis (line 36) | def inscriptis():
  function yaml (line 46) | def yaml():
  function json (line 53) | def json():
  function trec_car (line 60) | def trec_car():
  function warc (line 69) | def warc():
  function warc_clueweb09 (line 78) | def warc_clueweb09():
  function lz4_block (line 87) | def lz4_block():
  function lz4_frame (line 93) | def lz4_frame():
  function zlib_state (line 99) | def zlib_state():
  function xml_etree (line 108) | def xml_etree():
  function lxml_html (line 114) | def lxml_html():
  function ijson (line 120) | def ijson():
  function pyautocorpus (line 129) | def pyautocorpus():
  function unlzw3 (line 138) | def unlzw3():
  function pyarrow_parquet (line 147) | def pyarrow_parquet():

FILE: ir_datasets/log.py
  class TqdmHandler (line 9) | class TqdmHandler(logging.StreamHandler):
    method __init__ (line 10) | def __init__(self):
    method emit (line 13) | def emit(self, record):
  class Logger (line 36) | class Logger:
    method __init__ (line 37) | def __init__(self, name):
    method logger (line 41) | def logger(self):
    method debug (line 55) | def debug(self, text, **kwargs):
    method info (line 58) | def info(self, text, **kwargs):
    method warn (line 61) | def warn(self, text, **kwargs):
    method error (line 64) | def error(self, text, **kwargs):
    method critical (line 67) | def critical(self, text, **kwargs):
    method log (line 70) | def log(self, level, text, **kwargs):
    method pbar (line 73) | def pbar(self, it, *args, **kwargs):
    method pbar_raw (line 103) | def pbar_raw(self, *args, **kwargs):
    method duration (line 137) | def duration(self, message, level='INFO'):
  function easy (line 151) | def easy(name=None):
  function format_interval (line 158) | def format_interval(t):

FILE: ir_datasets/util/__init__.py
  function tmp_path (line 23) | def tmp_path():
  function home_path (line 30) | def home_path():
  function finialized_file (line 38) | def finialized_file(path, mode):
  class Lazy (line 55) | class Lazy:
    method __init__ (line 56) | def __init__(self, fn):
    method __call__ (line 62) | def __call__(self):
    method is_loaded (line 71) | def is_loaded(self):
  function apply_sub_slice (line 75) | def apply_sub_slice(orig_slice: slice, new_slice: slice):
  function slice_idx (line 130) | def slice_idx(orig_slice: slice, index: int):
  class DocstoreSplitter (line 138) | class DocstoreSplitter:
    method __init__ (line 139) | def __init__(self, it, docs_store):
    method __iter__ (line 143) | def __iter__(self):
    method __next__ (line 146) | def __next__(self):
    method __getitem__ (line 149) | def __getitem__(self, key):
  function use_docstore (line 153) | def use_docstore(fn):
  class Migrator (line 166) | class Migrator:
    method __init__ (line 167) | def __init__(self, version_file, version, affected_files, message=None...
    method __getattr__ (line 175) | def __getattr__(self, attr):
    method __call__ (line 181) | def __call__(self, wrapped):
    method _migrate (line 184) | def _migrate(self, fn):
    method _read_version (line 209) | def _read_version(self):
  function check_disk_free (line 214) | def check_disk_free(target_path, required_size, message='Insufficient di...
  function format_file_size (line 244) | def format_file_size(size):
  function ws_tok (line 253) | def ws_tok(s):

FILE: ir_datasets/util/docs/lazy.py
  class IRDSDocuments (line 13) | class IRDSDocuments(BaseDocs):
    method __init__ (line 16) | def __init__(self, ds_id: str):
    method docs (line 24) | def docs(self):
    method docs_cls (line 27) | def docs_cls(self):
    method docs_lang (line 30) | def docs_lang(self):
    method docs_count (line 33) | def docs_count(self):
    method docs_iter (line 36) | def docs_iter(self):
  class LazyDocs (line 40) | class LazyDocs(IRDSDocuments):
    method docs_store (line 42) | def docs_store(self, field="doc_id", options=DEFAULT_DOCSTORE_OPTIONS):
  class DirectAccessDocs (line 46) | class DirectAccessDocs(Protocol):
    method __call__ (line 47) | def __call__(self) -> Sequence:
  class DocsListView (line 52) | class DocsListView:
    method __init__ (line 55) | def __init__(self, docs: "DocsList", slice: slice):
    method __getitem__ (line 59) | def __getitem__(self, slice: Union[int, slice]):
  class DocsList (line 66) | class DocsList(ABC):
    method get (line 70) | def get(self, ix: int):
    method __len__ (line 74) | def __len__(self):
    method __getitem__ (line 77) | def __getitem__(self, slice: Union[int, slice]):
  class LazyDocsIter (line 84) | class LazyDocsIter:
    method __init__ (line 88) | def __init__(self, _get_list_fn: DirectAccessDocs, iter):
    method _list (line 93) | def _list(self):
    method __getitem__ (line 96) | def __getitem__(self, slice: Union[int, slice]):
    method __iter__ (line 99) | def __iter__(self):
    method __next__ (line 102) | def __next__(self):
  class BaseTransformedDocs (line 106) | class BaseTransformedDocs(BaseDocs):
    method __init__ (line 107) | def __init__(self, docs: BaseDocs, cls, store_name, count=None):
    method docs_cls (line 118) | def docs_cls(self):
    method docs_lang (line 121) | def docs_lang(self):
    method docs_count (line 124) | def docs_count(self):
    method docs_store (line 128) | def docs_store(self, field="doc_id", options=DEFAULT_DOCSTORE_OPTIONS):
  class TransformedDocs (line 140) | class TransformedDocs(BaseTransformedDocs):
    method __init__ (line 141) | def __init__(
    method docs_store (line 155) | def docs_store(self, field="doc_id", options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_iter (line 160) | def docs_iter(self):
  class TransformedDocstore (line 166) | class TransformedDocstore(Docstore):
    method __init__ (line 169) | def __init__(self, store, transform):
    method get_many (line 173) | def get_many(self, doc_ids, field=None):
  class IterDocs (line 180) | class IterDocs(BaseDocs):
    method __init__ (line 183) | def __init__(
    method docs_count (line 200) | def docs_count(self):
    method docs_iter (line 205) | def docs_iter(self):
    method docs_cls (line 211) | def docs_cls(self):
    method docs_store (line 215) | def docs_store(self, field="doc_id", options=DEFAULT_DOCSTORE_OPTIONS):
    method docs_namespace (line 226) | def docs_namespace(self):
    method docs_lang (line 229) | def docs_lang(self):

FILE: ir_datasets/util/docs/multiple.py
  class PrefixedDocsSpec (line 15) | class PrefixedDocsSpec:
    method length (line 26) | def length(self):
  class PrefixedDocstore (line 30) | class PrefixedDocstore(Docstore):
    method __init__ (line 31) | def __init__(self, docs_mapping: List[PrefixedDocsSpec], field="doc_id...
    method get_many (line 38) | def get_many(self, doc_ids: Sequence[str], field=None):
  class PrefixedDocs (line 68) | class PrefixedDocs(BaseDocs):
    method __init__ (line 71) | def __init__(self, store_name: Optional[str], *docs_mapping: PrefixedD...
    method lazy_self (line 83) | def lazy_self(self):
    method docs_cls (line 111) | def docs_cls(self):
    method docs_namespace (line 114) | def docs_namespace(self):
    method docs_lang (line 117) | def docs_lang(self):
    method __iter__ (line 120) | def __iter__(self):
    method _iter (line 123) | def _iter(self):
    method docs_iter (line 130) | def docs_iter(self):
    method docs_count (line 135) | def docs_count(self):
    method docs_store (line 142) | def docs_store(self, field="doc_id", options=DEFAULT_DOCSTORE_OPTIONS):

FILE: ir_datasets/util/docs/subset.py
  class DocsSubsetList (line 15) | class DocsSubsetList(DocsList):
    method __init__ (line 18) | def __init__(self, main: "DocsSubset", indices: array.array):
    method get (line 22) | def get(self, ix: int):
    method __len__ (line 31) | def __len__(self):
  class Dupes (line 35) | class Dupes:
    method __init__ (line 36) | def __init__(self, base: BaseDownload, prefix: Optional[str] = None):
    method remove_prefix (line 42) | def remove_prefix(self, doc_id: str):
    method doc_ids (line 47) | def doc_ids(self):
    method has (line 56) | def has(self, doc_id: str):
    method __len__ (line 59) | def __len__(self):
  class ColonCommaDupes (line 63) | class ColonCommaDupes(Dupes):
    method doc_ids (line 70) | def doc_ids(self):
  class DocsSubset (line 83) | class DocsSubset(BaseDocs):
    method __init__ (line 86) | def __init__(self, store_name: str, docs: BaseDocs, removed_ids: "Dupe...
    method docs_list (line 92) | def docs_list(self):
    method docs_cls (line 118) | def docs_cls(self):
    method docs_lang (line 121) | def docs_lang(self):
    method docs_count (line 124) | def docs_count(self):
    method docs_iter (line 129) | def docs_iter(self):
    method docs_namespace (line 139) | def docs_namespace(self):
    method docs_store (line 142) | def docs_store(self, field="doc_id", options=DEFAULT_DOCSTORE_OPTIONS):

FILE: ir_datasets/util/download.py
  class BaseDownload (line 20) | class BaseDownload:
    method stream (line 21) | def stream(self):
  class GoogleCloudBucketStream (line 24) | class GoogleCloudBucketStream(BaseDownload):
    method __init__ (line 25) | def __init__(self, url, tries=None):
    method __repr__ (line 29) | def __repr__(self):
    method stream (line 33) | def stream(self):
  class GoogleDriveDownload (line 39) | class GoogleDriveDownload(BaseDownload):
    method __init__ (line 40) | def __init__(self, url, tries=None):
    method stream (line 44) | def stream(self):
  class RequestsDownload (line 64) | class RequestsDownload(BaseDownload):
    method __init__ (line 65) | def __init__(self, url, tries=None, cookies=None, headers=None, auth=N...
    method stream (line 73) | def stream(self):
    method __iter__ (line 77) | def __iter__(self):
    method _iter_response_data (line 145) | def _iter_response_data(self, response, http_args, skip):
    method __repr__ (line 168) | def __repr__(self):
    method _handle_auth (line 171) | def _handle_auth(self, http_args):
  class LocalDownload (line 192) | class LocalDownload(BaseDownload):
    method __init__ (line 193) | def __init__(self, path, message=None, mkdir=True):
    method path (line 199) | def path(self, force=True):
    method stream (line 207) | def stream(self):
  function _cleanup_tmp (line 215) | def _cleanup_tmp(file):
  class Download (line 222) | class Download:
    method __init__ (line 225) | def __init__(self, mirrors, cache_path=None, expected_md5=None, dua=No...
    method path (line 234) | def path(self, force=True):
    method stream (line 283) | def stream(self):
    method dua_ctxt (line 295) | def dua_ctxt(cls, dua):
  class _DownloadConfig (line 301) | class _DownloadConfig:
    method __init__ (line 302) | def __init__(self, file=None, base_path=None, contents=None, dua=None,...
    method contents (line 311) | def contents(self):
    method context (line 317) | def context(self, key, base_path=None, dua=None):
    method get_home_path (line 321) | def get_home_path(self):
    method get_download_path (line 326) | def get_download_path(self):
    method __getitem__ (line 332) | def __getitem__(self, key):

FILE: ir_datasets/util/fileio.py
  class IterStream (line 21) | class IterStream(io.RawIOBase):
    method __init__ (line 22) | def __init__(self, it):
    method readable (line 27) | def readable(self):
    method readinto (line 30) | def readinto(self, b):
  class Cache (line 45) | class Cache:
    method __init__ (line 46) | def __init__(self, streamer, path):
    method verify (line 50) | def verify(self):
    method stream (line 77) | def stream(self):
    method path (line 82) | def path(self, force=True):
  class TarExtract (line 88) | class TarExtract:
    method __init__ (line 89) | def __init__(self, streamer, tar_path, compression='gz'):
    method stream (line 95) | def stream(self):
  class TarExtractAll (line 109) | class TarExtractAll:
    method __init__ (line 110) | def __init__(self, streamer, extract_path, compression='gz', path_glob...
    method path (line 116) | def path(self, force=True):
    method stream (line 134) | def stream(self):
  class RelativePath (line 138) | class RelativePath:
    method __init__ (line 139) | def __init__(self, streamer, path):
    method path (line 143) | def path(self, force=True):
    method stream (line 147) | def stream(self):
  class ReTar (line 152) | class ReTar:
    method __init__ (line 153) | def __init__(self, streamer, output_file, keep_globs, compression='gz'):
    method stream (line 160) | def stream(self):
  class GzipExtract (line 177) | class GzipExtract:
    method __init__ (line 178) | def __init__(self, streamer):
    method __getattr__ (line 181) | def __getattr__(self, attr):
    method stream (line 185) | def stream(self):
  class Bz2Extract (line 190) | class Bz2Extract:
    method __init__ (line 191) | def __init__(self, streamer):
    method __getattr__ (line 194) | def __getattr__(self, attr):
    method stream (line 198) | def stream(self):
  class Lz4Extract (line 203) | class Lz4Extract:
    method __init__ (line 204) | def __init__(self, streamer):
    method __getattr__ (line 207) | def __getattr__(self, attr):
    method stream (line 211) | def stream(self):
  class ZipExtract (line 217) | class ZipExtract:
    method __init__ (line 218) | def __init__(self, dlc, zip_path):
    method path (line 222) | def path(self, force=True):
    method stream (line 226) | def stream(self):
  class ZipExtractCache (line 234) | class ZipExtractCache:
    method __init__ (line 235) | def __init__(self, dlc, extract_path):
    method path (line 239) | def path(self, force=True):
    method stream (line 250) | def stream(self):
  class StringFile (line 254) | class StringFile:
    method __init__ (line 255) | def __init__(self, contents, path='MOCK'):
    method path (line 261) | def path(self, force=True):
    method stream (line 265) | def stream(self):
  class PackageDataFile (line 269) | class PackageDataFile:
    method __init__ (line 270) | def __init__(self, path, package='ir_datasets'):
    method path (line 274) | def path(self, force=True):
    method stream (line 278) | def stream(self):

FILE: ir_datasets/util/hash.py
  class HashVerificationError (line 10) | class HashVerificationError(IOError):
  class HashVerifier (line 14) | class HashVerifier:
    method __init__ (line 15) | def __init__(self, expected, algo='md5'):
    method update (line 20) | def update(self, b):
    method __enter__ (line 23) | def __enter__(self):
    method __exit__ (line 27) | def __exit__(self, exc_type, exc_val, exc_tb):
  class HashStream (line 37) | class HashStream(io.RawIOBase):
    method __init__ (line 38) | def __init__(self, stream, expected, algo='md5'):
    method readable (line 44) | def readable(self):
    method readinto (line 47) | def readinto(self, b):

FILE: ir_datasets/util/html_parsing.py
  function find_charset (line 7) | def find_charset(text):
  function decode_html (line 22) | def decode_html(body, headers=None):
  function sax_html_parser (line 31) | def sax_html_parser(body, headers=None, force_encoding=None, fields=None):
  class SaxExtractor (line 47) | class SaxExtractor:
    method __init__ (line 49) | def __init__(self, fields):
    method get_values (line 55) | def get_values(self):
    method _join_text (line 58) | def _join_text(self, text):
    method data (line 68) | def data(self, data):
    method start (line 76) | def start(self, tag, attrs):
    method end (line 84) | def end(self, tag):
    method close (line 92) | def close(self):
    method comment (line 95) | def comment(self, data):
    method doctype (line 98) | def doctype(self, *args):
    method pi (line 101) | def pi(self, *args):

FILE: ir_datasets/util/metadata.py
  class MetadataComponent (line 8) | class MetadataComponent:
    method __init__ (line 9) | def __init__(self, dataset_id, dataset, provider=None):
    method dataset_id (line 18) | def dataset_id(self):
    method metadata (line 21) | def metadata(self):
    method _metadata (line 28) | def _metadata(self, etype: ir_datasets.EntityType):
    method _count (line 31) | def _count(self, etype):
  class MetadataProvider (line 47) | class MetadataProvider:
    method __init__ (line 48) | def __init__(self, metadata_loader: Callable[[], Dict[str, Any]]):
    method get_metadata (line 52) | def get_metadata(self, dsid: str, entity_type: ir_datasets.EntityType)...
    method json_loader (line 62) | def json_loader(dlc):
  function count_hint (line 72) | def count_hint(

FILE: ir_datasets/util/registry.py
  class Registry (line 11) | class Registry:
    method __init__ (line 12) | def __init__(self, allow_overwrite=False):
    method __getitem__ (line 17) | def __getitem__(self, key):
    method __iter__ (line 31) | def __iter__(self):
    method register (line 34) | def register(self, name, obj):
    method register_pattern (line 45) | def register_pattern(self, pattern, initializer):

FILE: ir_datasets/wrappers/html_extractor.py
  function bs4_extract (line 11) | def bs4_extract(html):
  function inscriptis_extract (line 21) | def inscriptis_extract(html):
  class HtmlDocIter (line 26) | class HtmlDocIter:
    method __init__ (line 27) | def __init__(self, it, extractor):
    method __next__ (line 32) | def __next__(self):
    method __iter__ (line 35) | def __iter__(self):
    method __getitem__ (line 38) | def __getitem__(self, key):
  class HtmlDocExtractor (line 45) | class HtmlDocExtractor:
    method __init__ (line 46) | def __init__(self, dataset, extractor='bs4', parallel=0.8):
    method __getattr__ (line 68) | def __getattr__(self, attr):
    method docs_iter (line 71) | def docs_iter(self):
    method docs_store (line 74) | def docs_store(self, options=ir_datasets.indices.DEFAULT_DOCSTORE_OPTI...
  class HtmlDocExtractorDocStoreWrapper (line 78) | class HtmlDocExtractorDocStoreWrapper(ir_datasets.indices.Docstore):
    method __init__ (line 79) | def __init__(self, docstore, extractor):
    method get_many_iter (line 84) | def get_many_iter(self, doc_ids):
    method clear_cache (line 87) | def clear_cache(self):
  function _doc_map_it (line 92) | def _doc_map_it(it, extractor):
  function _doc_map (line 123) | def _doc_map(args):

FILE: test/downloads.py
  function tmp_environ (line 22) | def tmp_environ(**kwargs):
  class TestDownloads (line 38) | class TestDownloads(unittest.TestCase):
    method test_downloads (line 45) | def test_downloads(self):
    method _test_download_iter (line 68) | def _test_download_iter(self, data, prefix=''):
    method _test_download (line 81) | def _test_download(self, data, download_id):

FILE: test/formats/test_trec.py
  class TestTrec (line 8) | class TestTrec(unittest.TestCase):
    method test_qrels (line 10) | def test_qrels(self):
    method test_qrels_bad_line (line 33) | def test_qrels_bad_line(self):
    method test_queries (line 50) | def test_queries(self):
    method test_docs (line 89) | def test_docs(self):
    method tearDown (line 130) | def tearDown(self):

FILE: test/formats/test_tsv.py
  class TestTsv (line 9) | class TestTsv(unittest.TestCase):
    method test_core (line 11) | def test_core(self):
    method test_too_many_columns (line 41) | def test_too_many_columns(self):
    method test_too_few_columns (line 66) | def test_too_few_columns(self):
    method test_flex_columns (line 90) | def test_flex_columns(self):
    method tearDown (line 122) | def tearDown(self):

FILE: test/indices/lz4_pickle.py
  class TestLz4PickleLookup (line 8) | class TestLz4PickleLookup(unittest.TestCase):
    method test_lz4_pickle_lookup (line 9) | def test_lz4_pickle_lookup(self):

FILE: test/indices/numpy_sorted.py
  class TestNumpySortedIndex (line 7) | class TestNumpySortedIndex(unittest.TestCase):
    method test_numpy_sorted_index (line 8) | def test_numpy_sorted_index(self):

FILE: test/integration/antique.py
  class TestAntique (line 6) | class TestAntique(DatasetIntegrationTest):
    method test_antique (line 7) | def test_antique(self):
    method test_antique_train (line 14) | def test_antique_train(self):
    method test_antique_train_split200train (line 26) | def test_antique_train_split200train(self):
    method test_antique_train_split200valid (line 38) | def test_antique_train_split200valid(self):
    method test_antique_test (line 50) | def test_antique_test(self):
    method test_antique_test_nonoffensive (line 62) | def test_antique_test_nonoffensive(self):

FILE: test/integration/aol_ia.py
  class TestAolIa (line 10) | class TestAolIa(DatasetIntegrationTest):
    method test_docs (line 11) | def test_docs(self):
    method test_queries (line 18) | def test_queries(self):
    method test_qrels (line 25) | def test_qrels(self):
    method test_qlog (line 32) | def test_qlog(self):

FILE: test/integration/aquaint.py
  class TestAquaint (line 7) | class TestAquaint(DatasetIntegrationTest):
    method test_docs (line 8) | def test_docs(self):
    method test_queries (line 15) | def test_queries(self):
    method test_qrels (line 22) | def test_qrels(self):

FILE: test/integration/argsme.py
  class TestArgsMe (line 11) | class TestArgsMe(DatasetIntegrationTest):
    method test_docs (line 13) | def test_docs(self):

FILE: test/integration/base.py
  class DatasetIntegrationTest (line 9) | class DatasetIntegrationTest(unittest.TestCase):
    method _test_docs (line 10) | def _test_docs(self, dataset_name, count=None, items=None, test_docsto...
    method _test_queries (line 49) | def _test_queries(self, dataset_name, count=None, items=None):
    method _test_qrels (line 71) | def _test_qrels(self, dataset_name, count=None, items=None):
    method _test_qlogs (line 93) | def _test_qlogs(self, dataset_name, count=None, items=None):
    method _test_docpairs (line 115) | def _test_docpairs(self, dataset_name, count=None, items=None):
    method _build_test_docs (line 137) | def _build_test_docs(self, dataset_name, include_count=True, include_i...
    method _build_test_queries (line 157) | def _build_test_queries(self, dataset_name):
    method _build_test_qrels (line 173) | def _build_test_qrels(self, dataset_name):
    method _build_test_scoreddocs (line 189) | def _build_test_scoreddocs(self, dataset_name):
    method _build_test_docpairs (line 205) | def _build_test_docpairs(self, dataset_name):
    method _test_scoreddocs (line 217) | def _test_scoreddocs(self, dataset_name, count=None, items=None):
    method _build_test_qlogs (line 237) | def _build_test_qlogs(self, dataset_name):
    method _assert_namedtuple (line 249) | def _assert_namedtuple(self, a, b):
    method _replace_regex_namedtuple (line 268) | def _replace_regex_namedtuple(self, tup, maxlen=200):
    method _repr_namedtuples (line 287) | def _repr_namedtuples(self, items):
    method _repr_namedtuple (line 294) | def _repr_namedtuple(self, value):

FILE: test/integration/beir.py
  class TestBeir (line 8) | class TestBeir(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 157) | def test_queries(self):
    method test_qrels (line 399) | def test_qrels(self):

FILE: test/integration/c4.py
  class TestCar (line 7) | class TestCar(DatasetIntegrationTest):
    method test_docs (line 8) | def test_docs(self):
    method test_queries (line 19) | def test_queries(self):

FILE: test/integration/car.py
  class TestCar (line 8) | class TestCar(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 21) | def test_queries(self):
    method test_qrels (line 58) | def test_qrels(self):

FILE: test/integration/clinicaltrials.py
  class TestClinicalTrials (line 13) | class TestClinicalTrials(DatasetIntegrationTest):
    method test_docs (line 14) | def test_docs(self):
    method test_queries (line 31) | def test_queries(self):
    method test_qrels (line 58) | def test_qrels(self):

FILE: test/integration/clirmatrix.py
  class TestCLIRMatrix (line 12) | class TestCLIRMatrix(DatasetIntegrationTest):
    method test_docs (line 13) | def test_docs(self):
    method test_queries (line 35) | def test_queries(self):
    method test_qrels (line 82) | def test_qrels(self):

FILE: test/integration/clueweb09.py
  class TestClueWeb09 (line 12) | class TestClueWeb09(DatasetIntegrationTest):
    method test_clueweb09_docs (line 13) | def test_clueweb09_docs(self):
    method test_clueweb09_docstore (line 76) | def test_clueweb09_docstore(self):
    method test_clueweb09_queries (line 97) | def test_clueweb09_queries(self):
    method test_clueweb09_qrels (line 144) | def test_clueweb09_qrels(self):

FILE: test/integration/clueweb12.py
  class TestClueWeb12 (line 12) | class TestClueWeb12(DatasetIntegrationTest):
    method test_clueweb12_docs (line 13) | def test_clueweb12_docs(self):
    method test_clueweb12_docs_html (line 25) | def test_clueweb12_docs_html(self):
    method test_clueweb12_docstore (line 44) | def test_clueweb12_docstore(self):
    method test_clueweb12_queries (line 67) | def test_clueweb12_queries(self):
    method test_clueweb12_qrels (line 135) | def test_clueweb12_qrels(self):

FILE: test/integration/codec.py
  class TestCodec (line 8) | class TestCodec(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 16) | def test_queries(self):
    method test_qrels (line 38) | def test_qrels(self):

FILE: test/integration/codesearchnet.py
  class TestCodeSearchNet (line 8) | class TestCodeSearchNet(DatasetIntegrationTest):
    method test_codesearchnet_docs (line 9) | def test_codesearchnet_docs(self):
    method test_codesearchnet_queries (line 16) | def test_codesearchnet_queries(self):
    method test_codesearchnet_qrels (line 38) | def test_codesearchnet_qrels(self):

FILE: test/integration/cord19.py
  class TestCord19 (line 8) | class TestCord19(DatasetIntegrationTest):
    method test_cord19_docs (line 9) | def test_cord19_docs(self):
    method test_cord19_queries (line 46) | def test_cord19_queries(self):
    method test_cord19_qrels (line 83) | def test_cord19_qrels(self):

FILE: test/integration/cranfield.py
  class TestCranfield (line 8) | class TestCranfield(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 16) | def test_queries(self):
    method test_qrels (line 23) | def test_qrels(self):

FILE: test/integration/csl.py
  class TestCsl (line 8) | class TestCsl(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 16) | def test_queries(self):
    method test_qrels (line 23) | def test_qrels(self):

FILE: test/integration/disks45.py
  class TestDisks45 (line 8) | class TestDisks45(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 16) | def test_queries(self):
    method test_qrels (line 58) | def test_qrels(self):

FILE: test/integration/dpr_w100.py
  class TestDprW100 (line 8) | class TestDprW100(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 16) | def test_queries(self):
    method test_qrels (line 38) | def test_qrels(self):

FILE: test/integration/dummy.py
  class TestDummy (line 10) | class TestDummy(DatasetIntegrationTest):
    method test_dummy_docs (line 11) | def test_dummy_docs(self):
    method test_dummy_queries (line 23) | def test_dummy_queries(self):
    method test_dummy_qrels (line 35) | def test_dummy_qrels(self):
    method tearDown (line 46) | def tearDown(self):

FILE: test/integration/gov.py
  class TestGov (line 12) | class TestGov(DatasetIntegrationTest):
    method test_docs (line 13) | def test_docs(self):
    method test_queries (line 20) | def test_queries(self):
    method test_gov2_qrels (line 47) | def test_gov2_qrels(self):

FILE: test/integration/gov2.py
  class TestGov2 (line 12) | class TestGov2(DatasetIntegrationTest):
    method test_gov2_docs (line 13) | def test_gov2_docs(self):
    method test_gov2_docstore (line 20) | def test_gov2_docstore(self):
    method test_gov2_queries (line 35) | def test_gov2_queries(self):
    method test_gov2_qrels (line 107) | def test_gov2_qrels(self):

FILE: test/integration/hc4.py
  class TestHC4 (line 6) | class TestHC4(DatasetIntegrationTest):
    method test_hc4_zh_docs (line 7) | def test_hc4_zh_docs(self):
    method test_hc4_fa_docs (line 14) | def test_hc4_fa_docs(self):
    method test_hc4_ru_docs (line 21) | def test_hc4_ru_docs(self):
    method test_hc4_zh_query (line 28) | def test_hc4_zh_query(self):
    method test_hc4_fa_query (line 40) | def test_hc4_fa_query(self):
    method test_hc4_ru_query (line 53) | def test_hc4_ru_query(self):
    method test_hc4_zh_qrels (line 64) | def test_hc4_zh_qrels(self):
    method test_hc4_fa_qrels (line 78) | def test_hc4_fa_qrels(self):
    method test_hc4_ru_qrels (line 92) | def test_hc4_ru_qrels(self):

FILE: test/integration/highwire.py
  class TestHighwire (line 12) | class TestHighwire(DatasetIntegrationTest):
    method test_highwire_docs (line 13) | def test_highwire_docs(self):
    method test_highwire_queries (line 21) | def test_highwire_queries(self):
    method test_highwire_qrels (line 34) | def test_highwire_qrels(self):

FILE: test/integration/istella22.py
  class TestIstella22 (line 9) | class TestIstella22(DatasetIntegrationTest):
    method test_docs (line 10) | def test_docs(self):
    method test_queries (line 17) | def test_queries(self):
    method test_qrels (line 49) | def test_qrels(self):

FILE: test/integration/kilt.py
  class TestKilt (line 9) | class TestKilt(DatasetIntegrationTest):
    method test_docs (line 10) | def test_docs(self):
    method test_queries (line 17) | def test_queries(self):
    method test_qrels (line 39) | def test_qrels(self):

FILE: test/integration/lotte.py
  class TestLotte (line 8) | class TestLotte(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 71) | def test_queries(self):
    method test_qrels (line 193) | def test_qrels(self):

FILE: test/integration/medline.py
  class TestMedline (line 12) | class TestMedline(DatasetIntegrationTest):
    method test_medline_docs (line 13) | def test_medline_docs(self):
    method test_medline_queries (line 25) | def test_medline_queries(self):
    method test_medline_qrels (line 47) | def test_medline_qrels(self):

FILE: test/integration/miracl.py
  class TestMiracl (line 12) | class TestMiracl(DatasetIntegrationTest):
    method test_docs (line 13) | def test_docs(self):
    method test_queries (line 105) | def test_queries(self):
    method test_qrels (line 422) | def test_qrels(self):

FILE: test/integration/mmarco.py
  class TestMMarco (line 11) | class TestMMarco(DatasetIntegrationTest):
    method test_docs (line 12) | def test_docs(self):
    method test_queries (line 120) | def test_queries(self):
    method test_qrels (line 471) | def test_qrels(self):
    method test_scoreddocs (line 634) | def test_scoreddocs(self):
    method test_docpairs (line 742) | def test_docpairs(self):

FILE: test/integration/mr_tydi.py
  class TestMrTydi (line 8) | class TestMrTydi(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 66) | def test_queries(self):
    method test_qrels (line 288) | def test_qrels(self):

FILE: test/integration/msmarco_document.py
  class TestMsMarcoDocument (line 8) | class TestMsMarcoDocument(DatasetIntegrationTest):
    method test_msmarco_document_docs (line 9) | def test_msmarco_document_docs(self):
    method test_msmarco_document_queries (line 16) | def test_msmarco_document_queries(self):
    method test_msmarco_document_qrels (line 89) | def test_msmarco_document_qrels(self):
    method test_msmarco_document_scoreddocs (line 156) | def test_msmarco_document_scoreddocs(self):
    method test_anchor_text (line 189) | def test_anchor_text(self):

FILE: test/integration/msmarco_document_v2.py
  class TestMsMarcoDocumentV2 (line 8) | class TestMsMarcoDocumentV2(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 16) | def test_queries(self):
    method test_qrels (line 83) | def test_qrels(self):
    method test_scoreddocs (line 150) | def test_scoreddocs(self):
    method test_anchor_text (line 192) | def test_anchor_text(self):

FILE: test/integration/msmarco_passage.py
  class TestMsMarcoPassage (line 6) | class TestMsMarcoPassage(DatasetIntegrationTest):
    method test_msmarco_passage_docs (line 7) | def test_msmarco_passage_docs(self):
    method test_msmarco_passage_queries (line 24) | def test_msmarco_passage_queries(self):
    method test_msmarco_passage_qrels (line 131) | def test_msmarco_passage_qrels(self):
    method test_msmarco_passage_docpairs (line 229) | def test_msmarco_passage_docpairs(self):
    method test_msmarco_passage_scoreddocs (line 251) | def test_msmarco_passage_scoreddocs(self):

FILE: test/integration/msmarco_passage_v2.py
  class TestMsMarcoPassageV2 (line 9) | class TestMsMarcoPassageV2(DatasetIntegrationTest):
    method test_docs (line 10) | def test_docs(self):
    method test_queries (line 27) | def test_queries(self):
    method test_qrels (line 74) | def test_qrels(self):
    method test_scoreddocs (line 121) | def test_scoreddocs(self):

FILE: test/integration/msmarco_qna.py
  class TestMsMarcoQnA (line 8) | class TestMsMarcoQnA(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 16) | def test_queries(self):
    method test_qrels (line 33) | def test_qrels(self):
    method test_scoreddocs (line 45) | def test_scoreddocs(self):

FILE: test/integration/nano_beir.py
  class TestBeir (line 8) | class TestBeir(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 77) | def test_queries(self):
    method test_qrels (line 144) | def test_qrels(self):

FILE: test/integration/natural_questions.py
  class TestNq (line 8) | class TestNq(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 16) | def test_queries(self):
    method test_qrels (line 28) | def test_qrels(self):
    method test_scoreddocs (line 40) | def test_scoreddocs(self):

FILE: test/integration/neuclir.py
  class TestNeuCLIR22 (line 7) | class TestNeuCLIR22(DatasetIntegrationTest):
    method test_docs (line 8) | def test_docs(self):
    method test_queries (line 45) | def test_queries(self):
    method test_qrels (line 97) | def test_qrels(self):

FILE: test/integration/neumarco.py
  class TestNeuMarco (line 7) | class TestNeuMarco(DatasetIntegrationTest):
    method test_docs (line 8) | def test_docs(self):
    method test_queries (line 25) | def test_queries(self):
    method test_qrels (line 53) | def test_qrels(self):
    method test_docpairs (line 81) | def test_docpairs(self):

FILE: test/integration/nfcorpus.py
  class TestNf (line 12) | class TestNf(DatasetIntegrationTest):
    method test_nf_docs (line 13) | def test_nf_docs(self):
    method test_nf_queries (line 20) | def test_nf_queries(self):
    method test_gov2_qrels (line 67) | def test_gov2_qrels(self):

FILE: test/integration/nyt.py
  class TestNyt (line 8) | class TestNyt(DatasetIntegrationTest):
    method test_nyt_docs (line 9) | def test_nyt_docs(self):
    method test_nyt_queries (line 16) | def test_nyt_queries(self):
    method test_nyt_qrels (line 38) | def test_nyt_qrels(self):

FILE: test/integration/pmc.py
  class TestPmc (line 12) | class TestPmc(DatasetIntegrationTest):
    method test_pmc_docs (line 13) | def test_pmc_docs(self):
    method test_pmc_queries (line 25) | def test_pmc_queries(self):
    method test_pmc_qrels (line 42) | def test_pmc_qrels(self):

FILE: test/integration/sara.py
  class TestSara (line 8) | class TestSara(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 16) | def test_queries(self):
    method test_qrels (line 24) | def test_qrels(self):

FILE: test/integration/touche.py
  class TestTouche (line 11) | class TestTouche(DatasetIntegrationTest):
    method test_queries (line 14) | def test_queries(self):
    method test_qrels (line 177) | def test_qrels(self):

FILE: test/integration/touche_image.py
  class TestToucheImage (line 8) | class TestToucheImage(DatasetIntegrationTest):
    method test_docs (line 11) | def test_docs(self):

FILE: test/integration/trec_arabic.py
  class TestTrecArabic (line 7) | class TestTrecArabic(DatasetIntegrationTest):
    method test_trec_arabic_docs (line 8) | def test_trec_arabic_docs(self):
    method test_trec_arabic_queries (line 15) | def test_trec_arabic_queries(self):
    method test_trec_arabic_qrels (line 27) | def test_trec_arabic_qrels(self):

FILE: test/integration/trec_cast.py
  class TestTrecCast (line 8) | class TestTrecCast(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 29) | def test_queries(self):
    method test_qrels (line 72) | def test_qrels(self):
    method test_scoreddocs (line 114) | def test_scoreddocs(self):

FILE: test/integration/trec_fair.py
  class TestFairTrec (line 8) | class TestFairTrec(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 21) | def test_queries(self):
    method test_qrels (line 38) | def test_qrels(self):

FILE: test/integration/trec_mandarin.py
  class TestTrecMandarin (line 8) | class TestTrecMandarin(DatasetIntegrationTest):
    method test_trec_mandarin_docs (line 9) | def test_trec_mandarin_docs(self):
    method test_trec_mandarin_queries (line 16) | def test_trec_mandarin_queries(self):
    method test_trec_mandarin_qrels (line 28) | def test_trec_mandarin_qrels(self):

FILE: test/integration/trec_robust04.py
  class TestTrecRobust04 (line 7) | class TestTrecRobust04(DatasetIntegrationTest):
    method test_trec_robust04_docs (line 8) | def test_trec_robust04_docs(self):
    method test_trec_robust04_queries (line 16) | def test_trec_robust04_queries(self):
    method test_trec_robust04_qrels (line 48) | def test_trec_robust04_qrels(self):

FILE: test/integration/trec_spanish.py
  class TestTrecSpanish (line 8) | class TestTrecSpanish(DatasetIntegrationTest):
    method test_trec_spanish_docs (line 9) | def test_trec_spanish_docs(self):
    method test_trec_spanish_queries (line 16) | def test_trec_spanish_queries(self):
    method test_trec_spanish_qrels (line 28) | def test_trec_spanish_qrels(self):

FILE: test/integration/trec_tot.py
  class TestTipOfTheTongue (line 9) | class TestTipOfTheTongue(DatasetIntegrationTest):
    method test_tip_of_the_tongue_docs (line 10) | def test_tip_of_the_tongue_docs(self):
    method test_test_tip_of_the_tongue_queries_train (line 17) | def test_test_tip_of_the_tongue_queries_train(self):
    method test_test_tip_of_the_tongue_queries_dev (line 24) | def test_test_tip_of_the_tongue_queries_dev(self):
    method test_test_tip_of_the_tongue_qrels_train (line 31) | def test_test_tip_of_the_tongue_qrels_train(self):
    method test_test_tip_of_the_tongue_qrels_dev (line 39) | def test_test_tip_of_the_tongue_qrels_dev(self):

FILE: test/integration/trec_tot_2024.py
  class TestTipOfTheTongue (line 9) | class TestTipOfTheTongue(DatasetIntegrationTest):
    method test_tip_of_the_tongue_docs (line 10) | def test_tip_of_the_tongue_docs(self):
    method test_tip_of_the_tongue_queries (line 16) | def test_tip_of_the_tongue_queries(self):

FILE: test/integration/trec_tot_2025/test_docs_iter.py
  function load_dataset (line 3) | def load_dataset():
  function load_doc_number (line 7) | def load_doc_number(num):
  class TestDocsIter (line 14) | class TestDocsIter(unittest.TestCase):
    method test_dataset_can_be_loaded (line 15) | def test_dataset_can_be_loaded(self):
    method test_first_doc (line 19) | def test_first_doc(self):
    method test_third_doc (line 30) | def test_third_doc(self):

FILE: test/integration/trec_tot_2025/test_docs_store.py
  function load_docs_store (line 3) | def load_docs_store():
  class TestDocsStore (line 7) | class TestDocsStore(unittest.TestCase):
    method test_docs_store_can_be_loaded (line 8) | def test_docs_store_can_be_loaded(self):
    method test_first_doc (line 12) | def test_first_doc(self):
    method test_third_doc (line 23) | def test_third_doc(self):
    method test_some_random_doc (line 33) | def test_some_random_doc(self):

FILE: test/integration/trec_tot_2025/test_qrel_iter.py
  function load_dataset (line 3) | def load_dataset(dataset_id):
  function load_qrel_number (line 7) | def load_qrel_number(dataset_id, num):
  class TestQrelIter (line 14) | class TestQrelIter(unittest.TestCase):
    method test_train_dataset_can_be_loaded (line 15) | def test_train_dataset_can_be_loaded(self):
    method test_dev1_dataset_can_be_loaded (line 19) | def test_dev1_dataset_can_be_loaded(self):
    method test_dev2_dataset_can_be_loaded (line 23) | def test_dev2_dataset_can_be_loaded(self):
    method test_dev3_dataset_can_be_loaded (line 27) | def test_dev3_dataset_can_be_loaded(self):
    method test_train_qrel_iter (line 31) | def test_train_qrel_iter(self):
    method test_dev1_qrel_iter (line 37) | def test_dev1_qrel_iter(self):
    method test_dev2_qrel_iter (line 43) | def test_dev2_qrel_iter(self):
    method test_dev3_qrel_iter (line 49) | def test_dev3_qrel_iter(self):

FILE: test/integration/trec_tot_2025/test_queries_iter.py
  function load_dataset (line 3) | def load_dataset(dataset_id):
  function load_query_number (line 7) | def load_query_number(dataset_id, num):
  class TestQueriesIter (line 14) | class TestQueriesIter(unittest.TestCase):
    method test_train_dataset_can_be_loaded (line 15) | def test_train_dataset_can_be_loaded(self):
    method test_dev1_dataset_can_be_loaded (line 19) | def test_dev1_dataset_can_be_loaded(self):
    method test_dev2_dataset_can_be_loaded (line 23) | def test_dev2_dataset_can_be_loaded(self):
    method test_dev3_dataset_can_be_loaded (line 27) | def test_dev3_dataset_can_be_loaded(self):
    method test_query_from_train_dataset_can_be_loaded_01 (line 31) | def test_query_from_train_dataset_can_be_loaded_01(self):
    method test_query_from_train_dataset_can_be_loaded_02 (line 37) | def test_query_from_train_dataset_can_be_loaded_02(self):
    method test_query_from_dev1_dataset_can_be_loaded_01 (line 43) | def test_query_from_dev1_dataset_can_be_loaded_01(self):
    method test_query_from_dev1_dataset_can_be_loaded_02 (line 49) | def test_query_from_dev1_dataset_can_be_loaded_02(self):
    method test_query_from_dev2_dataset_can_be_loaded_01 (line 55) | def test_query_from_dev2_dataset_can_be_loaded_01(self):
    method test_query_from_dev2_dataset_can_be_loaded_02 (line 61) | def test_query_from_dev2_dataset_can_be_loaded_02(self):
    method test_query_from_dev3_dataset_can_be_loaded_01 (line 67) | def test_query_from_dev3_dataset_can_be_loaded_01(self):
    method test_query_from_dev3_dataset_can_be_loaded_02 (line 73) | def test_query_from_dev3_dataset_can_be_loaded_02(self):
    method test_query_from_test_dataset_can_be_loaded_01 (line 79) | def test_query_from_test_dataset_can_be_loaded_01(self):
    method test_query_from_test_dataset_can_be_loaded_02 (line 85) | def test_query_from_test_dataset_can_be_loaded_02(self):

FILE: test/integration/tripclick.py
  class TestTripclick (line 9) | class TestTripclick(DatasetIntegrationTest):
    method test_docs (line 10) | def test_docs(self):
    method test_queries (line 22) | def test_queries(self):
    method test_qlogs (line 94) | def test_qlogs(self):
    method test_qrels (line 103) | def test_qrels(self):
    method test_scoreddocs (line 155) | def test_scoreddocs(self):
    method test_docpairs (line 202) | def test_docpairs(self):

FILE: test/integration/tweets2013_ia.py
  class TestTweets2013Ia (line 8) | class TestTweets2013Ia(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 16) | def test_queries(self):
    method test_qrels (line 28) | def test_qrels(self):

FILE: test/integration/vaswani.py
  class TestVaswani (line 7) | class TestVaswani(DatasetIntegrationTest):
    method test_vaswani_docs (line 8) | def test_vaswani_docs(self):
    method test_vaswani_queries (line 15) | def test_vaswani_queries(self):
    method test_vaswani_qrels (line 22) | def test_vaswani_qrels(self):

FILE: test/integration/wapo.py
  class TestWapo (line 8) | class TestWapo(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 23) | def test_queries(self):
    method test_qrels (line 45) | def test_qrels(self):

FILE: test/integration/wikiclir.py
  class TestWikiclir (line 8) | class TestWikiclir(DatasetIntegrationTest):
    method test_docs (line 9) | def test_docs(self):
    method test_queries (line 136) | def test_queries(self):
    method test_qrels (line 264) | def test_qrels(self):

FILE: test/integration/wikir.py
  class TestWikir (line 7) | class TestWikir(DatasetIntegrationTest):
    method test_docs (line 8) | def test_docs(self):
    method test_queries (line 45) | def test_queries(self):
    method test_qrels (line 152) | def test_qrels(self):
    method test_scoreddocs (line 259) | def test_scoreddocs(self):

FILE: test/metadata.py
  class TestMetadata (line 5) | class TestMetadata(unittest.TestCase):
    method test_all_metadata_available (line 6) | def test_all_metadata_available(self):
    method _test_ds (line 24) | def _test_ds(self, dsid):

FILE: test/test_defaulttext.py
  function template_instance (line 4) | def template_instance(Cls):
  class TestMetadata (line 21) | class TestMetadata(unittest.TestCase):
    method test_all_defualttext (line 22) | def test_all_defualttext(self):
    method _test_defaulttet (line 26) | def _test_defaulttet(self, dsid):

FILE: test/util.py
  class TestUtil (line 5) | class TestUtil(unittest.TestCase):
    method test_apply_sub_slice (line 6) | def test_apply_sub_slice(self):
    method test_corpus_id (line 23) | def test_corpus_id(self):
    method test_html_find_charset (line 38) | def test_html_find_charset(self):
    method test_decode_html (line 48) | def test_decode_html(self):
    method test_sax_html_parser (line 52) | def test_sax_html_parser(self):

FILE: test/util/docs/data.py
  class OtherDoc (line 8) | class OtherDoc:
    method __init__ (line 9) | def __init__(self, id: str, text: str):
  class FakeDocs (line 14) | class FakeDocs(BaseDocs):
    method __init__ (line 15) | def __init__(self, n_docs: int, namespace = 'test', lang='en', docs_cl...
    method docs_count (line 27) | def docs_count(self):
    method docs_iter (line 30) | def docs_iter(self):
    method docs_cls (line 33) | def docs_cls(self):
    method docs_lang (line 36) | def docs_lang(self):
    method docs_namepace (line 39) | def docs_namepace(self):
    method docs_store (line 42) | def docs_store(self, field="doc_id", options=DEFAULT_DOCSTORE_OPTIONS)...
  class FakeDocstore (line 46) | class FakeDocstore(Docstore):
    method __init__ (line 47) | def __init__(self, docs: FakeDocs):
    method get_many (line 50) | def get_many(self, doc_ids, field=None):

FILE: test/util/docs/test_multiple.py
  function test_multiple_prefixes (line 8) | def test_multiple_prefixes():
  function test_multiple_prefixes_inlined (line 62) | def test_multiple_prefixes_inlined():

FILE: test/util/docs/test_subset.py
  class SimpleDupes (line 4) | class SimpleDupes(Dupes):
    method __init__ (line 5) | def __init__(self, doc_ids):
  function test_subset_simple (line 9) | def test_subset_simple():

[
  {
    "path": ".github/ISSUE_TEMPLATE/bug_report.md",
    "chars": 484,
    "preview": "---\nname: Bug report\nabout: Errors in behavior or functionality\ntitle: ''\nlabels: bug\nassignees: ''\n\n---\n\n**Describe the"
  },
  {
    "path": ".github/ISSUE_TEMPLATE/dataset-addition.md",
    "chars": 1468,
    "preview": "---\nname: Dataset Addition\nabout: Propose adding a new dataset, collection of related datasets, or feature to\n  existing"
  },
  {
    "path": ".github/ISSUE_TEMPLATE/documentation.md",
    "chars": 183,
    "preview": "---\nname: Documentation\nabout: Additions to or improvmenets to the documentation\ntitle: ''\nlabels: documentation\nassigne"
  },
  {
    "path": ".github/ISSUE_TEMPLATE/feature_request.md",
    "chars": 604,
    "preview": "---\nname: Feature request\nabout: Suggest an idea for this project\ntitle: ''\nlabels: enhancement\nassignees: ''\n\n---\n\n**Is"
  },
  {
    "path": ".github/workflows/deploy.yml",
    "chars": 576,
    "preview": "name: deploy\n\non:\n  release:\n    types: [created]\n\njobs:\n  pypi:\n    runs-on: ubuntu-latest\n    steps:\n    - uses: actio"
  },
  {
    "path": ".github/workflows/test.yml",
    "chars": 1244,
    "preview": "name: test\n\non:\n  push: {branches: [master]} # pushes to master\n  pull_request: {} # all PRs\n\njobs:\n  pytest:\n    strate"
  },
  {
    "path": ".gitignore",
    "chars": 2046,
    "preview": "# Byte-compiled / optimized / DLL files\n__pycache__/\n*.py[cod]\n*$py.class\n\n# C extensions\n*.so\n\n# Distribution / packagi"
  },
  {
    "path": "LICENSE",
    "chars": 11358,
    "preview": "\n                                 Apache License\n                           Version 2.0, January 2004\n                  "
  },
  {
    "path": "MANIFEST.in",
    "chars": 110,
    "preview": "recursive-include ir_datasets *.yaml\nrecursive-include ir_datasets *.bib\nrecursive-include ir_datasets *.json\n"
  },
  {
    "path": "README.md",
    "chars": 11554,
    "preview": "# ir_datasets\n\n`ir_datasets` is a python package that provides a common interface to many IR ad-hoc ranking\nbenchmarks, "
  },
  {
    "path": "examples/adding_datasets.ipynb",
    "chars": 8734,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"markdown\",\n   \"metadata\": {},\n   \"source\": [\n    \"# ir_datasets - Adding Datasets\"\n  "
  },
  {
    "path": "examples/clirmatrix_example.py",
    "chars": 2106,
    "preview": "import ir_datasets\n\"\"\"\ndataset name\nclirmatrix/[query language code]/dataset/[doc language code]/[split]\n\noptions:\n-----"
  },
  {
    "path": "examples/ir_datasets.ipynb",
    "chars": 114685,
    "preview": "{\n  \"nbformat\": 4,\n  \"nbformat_minor\": 0,\n  \"metadata\": {\n    \"colab\": {\n      \"name\": \"ir-datasets.ipynb\",\n      \"prove"
  },
  {
    "path": "examples/ir_datasets_cli.ipynb",
    "chars": 50773,
    "preview": "{\n  \"nbformat\": 4,\n  \"nbformat_minor\": 0,\n  \"metadata\": {\n    \"colab\": {\n      \"name\": \"ir_datasets-cli.ipynb\",\n      \"p"
  },
  {
    "path": "ir_datasets/__init__.py",
    "chars": 3287,
    "preview": "from enum import Enum\nclass EntityType(Enum):\n    docs = \"docs\"\n    queries = \"queries\"\n    qrels = \"qrels\"\n    scoreddo"
  },
  {
    "path": "ir_datasets/__main__.py",
    "chars": 74,
    "preview": "import ir_datasets\n\nif __name__ == '__main__':\n    ir_datasets.main_cli()\n"
  },
  {
    "path": "ir_datasets/commands/__init__.py",
    "chars": 638,
    "preview": "from . import doc_fifos\nfrom . import export\nfrom . import lookup\nfrom . import list as list_cmd\nfrom . import build_clu"
  },
  {
    "path": "ir_datasets/commands/build_c4_checkpoints.py",
    "chars": 3161,
    "preview": "import os\nimport sys\nimport multiprocessing\nfrom pathlib import Path\nimport gzip\nimport hashlib\nimport json\nimport pickl"
  },
  {
    "path": "ir_datasets/commands/build_clueweb_warc_indexes.py",
    "chars": 1728,
    "preview": "import sys\nimport multiprocessing\nfrom pathlib import Path\nimport argparse\nimport ir_datasets\n\n\n_logger = ir_datasets.lo"
  },
  {
    "path": "ir_datasets/commands/build_download_cache.py",
    "chars": 2441,
    "preview": "import sys\nimport time\nimport io\nimport os\nimport argparse\nimport json\nfrom contextlib import contextmanager\nimport ir_d"
  },
  {
    "path": "ir_datasets/commands/clean.py",
    "chars": 4090,
    "preview": "import sys\nimport os\nimport argparse\nimport multiprocessing\nfrom collections import deque\nimport ir_datasets\nfrom ir_dat"
  },
  {
    "path": "ir_datasets/commands/doc_fifos.py",
    "chars": 2983,
    "preview": "import sys\nimport os\nimport select\nimport tempfile\nimport contextlib\nimport json\nimport argparse\nimport multiprocessing\n"
  },
  {
    "path": "ir_datasets/commands/export.py",
    "chars": 10515,
    "preview": "import sys\nimport json\nimport argparse\nimport ir_datasets\n\n\n_logger = ir_datasets.log.easy()\n\n\ndef main_docs(dataset, ar"
  },
  {
    "path": "ir_datasets/commands/generate_metadata.py",
    "chars": 3293,
    "preview": "import time\nimport sys\nimport os\nimport json\nimport argparse\nfrom pathlib import Path\nfrom fnmatch import fnmatch\nimport"
  },
  {
    "path": "ir_datasets/commands/list.py",
    "chars": 476,
    "preview": "import sys\nimport argparse\nimport ir_datasets\nfrom ir_datasets.commands.export import DEFAULT_EXPORTERS\n\n\n_logger = ir_d"
  },
  {
    "path": "ir_datasets/commands/lookup.py",
    "chars": 1910,
    "preview": "import sys\nimport argparse\nimport ir_datasets\nfrom ir_datasets.commands.export import DEFAULT_EXPORTERS\n\n\n_logger = ir_d"
  },
  {
    "path": "ir_datasets/datasets/__init__.py",
    "chars": 1478,
    "preview": "from . import base\nfrom . import antique\nfrom . import aol_ia\nfrom . import aquaint\nfrom . import argsme\nfrom . import b"
  },
  {
    "path": "ir_datasets/datasets/antique.py",
    "chars": 5400,
    "preview": "import io\nimport ir_datasets\nfrom ir_datasets.formats import TsvDocs, TrecQrels, TsvQueries\nfrom ir_datasets.util import"
  },
  {
    "path": "ir_datasets/datasets/aol_ia.py",
    "chars": 8476,
    "preview": "from datetime import datetime\nimport json\nimport pickle\nimport re\nimport contextlib\nfrom collections import Counter\nfrom"
  },
  {
    "path": "ir_datasets/datasets/aquaint.py",
    "chars": 1413,
    "preview": "import ir_datasets\nfrom ir_datasets.util import DownloadConfig\nfrom ir_datasets.formats import TrecQrels, TrecDocs, Trec"
  },
  {
    "path": "ir_datasets/datasets/argsme.py",
    "chars": 3747,
    "preview": "from itertools import chain\nfrom typing import Dict\n\nfrom ir_datasets import registry\nfrom ir_datasets.datasets.base imp"
  },
  {
    "path": "ir_datasets/datasets/base.py",
    "chars": 13934,
    "preview": "import pkgutil\nimport contextlib\nimport itertools\nfrom pathlib import Path\nimport ir_datasets\nfrom ir_datasets.formats i"
  },
  {
    "path": "ir_datasets/datasets/beir.py",
    "chars": 10129,
    "preview": "import json\nimport codecs\nfrom typing import NamedTuple, Dict, List\nimport ir_datasets\nfrom ir_datasets.util import ZipE"
  },
  {
    "path": "ir_datasets/datasets/c4.py",
    "chars": 9363,
    "preview": "import re\nimport os\nimport json\nimport pickle\nfrom pathlib import Path\nfrom typing import NamedTuple, Tuple\nimport ir_da"
  },
  {
    "path": "ir_datasets/datasets/car.py",
    "chars": 6211,
    "preview": "from typing import NamedTuple, Tuple\nimport ir_datasets\nfrom ir_datasets.util import DownloadConfig, TarExtract, ReTar\nf"
  },
  {
    "path": "ir_datasets/datasets/clinicaltrials.py",
    "chars": 6369,
    "preview": "import codecs\nimport itertools\nimport io\nimport gzip\nfrom contextlib import ExitStack\nimport itertools\nfrom typing impor"
  },
  {
    "path": "ir_datasets/datasets/clirmatrix.py",
    "chars": 4642,
    "preview": "import json\nimport contextlib\nfrom pathlib import Path\nfrom typing import NamedTuple\nimport ir_datasets\nfrom ir_datasets"
  },
  {
    "path": "ir_datasets/datasets/clueweb09.py",
    "chars": 13622,
    "preview": "import os\nimport codecs\nfrom pathlib import Path\nfrom typing import NamedTuple, Tuple\nfrom glob import glob\nimport ir_da"
  },
  {
    "path": "ir_datasets/datasets/clueweb12.py",
    "chars": 17599,
    "preview": "import codecs\nimport io\nimport os\nimport gzip\nimport contextlib\nfrom typing import NamedTuple, Tuple\nfrom glob import gl"
  },
  {
    "path": "ir_datasets/datasets/codec.py",
    "chars": 2906,
    "preview": "import json\nfrom typing import NamedTuple\nimport ir_datasets\nfrom ir_datasets.util import Lazy\nfrom ir_datasets.formats "
  },
  {
    "path": "ir_datasets/datasets/codesearchnet.py",
    "chars": 7252,
    "preview": "import json\nimport csv\nimport gzip\nfrom typing import NamedTuple\nimport io\nimport itertools\nfrom pathlib import Path\nimp"
  },
  {
    "path": "ir_datasets/datasets/cord19.py",
    "chars": 10327,
    "preview": "import io\nimport codecs\nimport json\nimport csv\nimport contextlib\nimport os\nimport shutil\nimport tarfile\nfrom collections"
  },
  {
    "path": "ir_datasets/datasets/cranfield.py",
    "chars": 5861,
    "preview": "import io\nimport codecs\nimport itertools\nimport ir_datasets\nfrom typing import NamedTuple\nfrom ir_datasets.util import D"
  },
  {
    "path": "ir_datasets/datasets/csl.py",
    "chars": 1936,
    "preview": "from typing import List, NamedTuple\nfrom enum import Enum\n\nimport ir_datasets\nfrom ir_datasets.util import DownloadConfi"
  },
  {
    "path": "ir_datasets/datasets/disks45.py",
    "chars": 5049,
    "preview": "import ir_datasets\nfrom ir_datasets.util import GzipExtract, TarExtract, Lazy, DownloadConfig\nfrom ir_datasets.formats i"
  },
  {
    "path": "ir_datasets/datasets/dpr_w100.py",
    "chars": 5964,
    "preview": "from typing import NamedTuple, Tuple\nimport contextlib\nimport itertools\nimport ir_datasets\nfrom ir_datasets.util import "
  },
  {
    "path": "ir_datasets/datasets/gov.py",
    "chars": 7318,
    "preview": "import re\nimport io\nimport os\nimport gzip\nimport codecs\nfrom collections import Counter\nfrom contextlib import contextma"
  },
  {
    "path": "ir_datasets/datasets/gov2.py",
    "chars": 17531,
    "preview": "import re\nimport io\nimport os\nimport gzip\nimport codecs\nfrom collections import Counter\nfrom contextlib import contextma"
  },
  {
    "path": "ir_datasets/datasets/hc4.py",
    "chars": 1760,
    "preview": "import ir_datasets\nfrom ir_datasets.util import DownloadConfig\nfrom ir_datasets.formats import TrecQrels\nfrom ir_dataset"
  },
  {
    "path": "ir_datasets/datasets/highwire.py",
    "chars": 7846,
    "preview": "import codecs\nfrom typing import NamedTuple, Tuple\nfrom zipfile import ZipFile\nimport ir_datasets\nfrom ir_datasets.util "
  },
  {
    "path": "ir_datasets/datasets/istella22.py",
    "chars": 2687,
    "preview": "import json\nimport codecs\nfrom typing import NamedTuple, Dict, List\nimport ir_datasets\nfrom ir_datasets.util import TarE"
  },
  {
    "path": "ir_datasets/datasets/kilt.py",
    "chars": 4598,
    "preview": "import json\nimport codecs\nfrom typing import NamedTuple, Tuple\nimport ir_datasets\nfrom ir_datasets.util import TarExtrac"
  },
  {
    "path": "ir_datasets/datasets/lotte.py",
    "chars": 2474,
    "preview": "import json\nimport codecs\nfrom typing import NamedTuple, Dict, List\nimport ir_datasets\nfrom ir_datasets.util import TarE"
  },
  {
    "path": "ir_datasets/datasets/medline.py",
    "chars": 10104,
    "preview": "import codecs\nimport itertools\nimport io\nimport gzip\nfrom contextlib import ExitStack\nimport itertools\nfrom typing impor"
  },
  {
    "path": "ir_datasets/datasets/miracl.py",
    "chars": 3618,
    "preview": "import ir_datasets\nfrom typing import NamedTuple\nfrom ir_datasets.util import DownloadConfig, GzipExtract\nfrom ir_datase"
  },
  {
    "path": "ir_datasets/datasets/mmarco.py",
    "chars": 4466,
    "preview": "import io\nimport codecs\nimport re\nimport ir_datasets\nfrom ir_datasets.util import DownloadConfig, Lazy\nfrom ir_datasets."
  },
  {
    "path": "ir_datasets/datasets/mr_tydi.py",
    "chars": 4162,
    "preview": "import json\nimport codecs\nfrom typing import NamedTuple, Dict\nimport ir_datasets\nfrom ir_datasets.util import TarExtract"
  },
  {
    "path": "ir_datasets/datasets/msmarco_document.py",
    "chars": 9031,
    "preview": "from typing import NamedTuple, List\nimport json\nimport ir_datasets\nfrom ir_datasets.indices import PickleLz4FullStore, D"
  },
  {
    "path": "ir_datasets/datasets/msmarco_document_v2.py",
    "chars": 10130,
    "preview": "import contextlib\nimport gzip\nimport io\nfrom pathlib import Path\nimport json\nfrom typing import NamedTuple, Tuple, List\n"
  },
  {
    "path": "ir_datasets/datasets/msmarco_passage.py",
    "chars": 19477,
    "preview": "import hashlib\nimport io\nimport codecs\nimport re\nimport ir_datasets\nfrom ir_datasets.util import Cache, TarExtract, Iter"
  },
  {
    "path": "ir_datasets/datasets/msmarco_passage_v2.py",
    "chars": 14189,
    "preview": "import re\nimport os\nimport contextlib\nimport gzip\nimport io\nfrom pathlib import Path\nimport json\nfrom typing import Name"
  },
  {
    "path": "ir_datasets/datasets/msmarco_qna.py",
    "chars": 16944,
    "preview": "import hashlib\nimport re\nimport itertools\nimport contextlib\nimport io\nimport codecs\nfrom typing import NamedTuple, Tuple"
  },
  {
    "path": "ir_datasets/datasets/nano_beir.py",
    "chars": 4150,
    "preview": "import ir_datasets\nfrom ir_datasets.datasets.base import Dataset, YamlDocumentation\nfrom ir_datasets.formats import (\n  "
  },
  {
    "path": "ir_datasets/datasets/natural_questions.py",
    "chars": 9935,
    "preview": "from typing import NamedTuple, List\nimport json\nimport contextlib\nimport ir_datasets\nfrom ir_datasets.datasets.base impo"
  },
  {
    "path": "ir_datasets/datasets/neuclir.py",
    "chars": 5979,
    "preview": "import gzip\nimport json\nfrom functools import lru_cache\n\nimport ir_datasets\nfrom ir_datasets.util import DownloadConfig,"
  },
  {
    "path": "ir_datasets/datasets/neumarco.py",
    "chars": 2522,
    "preview": "import io\nimport codecs\nimport re\nimport ir_datasets\nfrom ir_datasets.util import DownloadConfig, TarExtract, Cache\nfrom"
  },
  {
    "path": "ir_datasets/datasets/nfcorpus.py",
    "chars": 7548,
    "preview": "import io\nimport codecs\nimport re\nfrom typing import NamedTuple\nimport ir_datasets\nfrom ir_datasets.util import Cache, T"
  },
  {
    "path": "ir_datasets/datasets/nyt.py",
    "chars": 15807,
    "preview": "import io\nimport tarfile\nfrom typing import NamedTuple\nimport ir_datasets\nfrom ir_datasets.indices import PickleLz4FullS"
  },
  {
    "path": "ir_datasets/datasets/pmc.py",
    "chars": 6450,
    "preview": "import codecs\nimport tarfile\nimport itertools\nfrom typing import NamedTuple, Tuple\nfrom zipfile import ZipFile\nimport xm"
  },
  {
    "path": "ir_datasets/datasets/sara.py",
    "chars": 3346,
    "preview": "import ir_datasets\nfrom ir_datasets.datasets.base import Dataset, YamlDocumentation\nfrom ir_datasets.datasets.base impor"
  },
  {
    "path": "ir_datasets/datasets/touche.py",
    "chars": 8556,
    "preview": "from typing import Dict\n\nfrom ir_datasets import registry\nfrom ir_datasets.datasets.base import Dataset, YamlDocumentati"
  },
  {
    "path": "ir_datasets/datasets/touche_image.py",
    "chars": 1395,
    "preview": "from ir_datasets import registry\nfrom ir_datasets.datasets.base import Dataset, YamlDocumentation\nfrom ir_datasets.forma"
  },
  {
    "path": "ir_datasets/datasets/trec_arabic.py",
    "chars": 1614,
    "preview": "import ir_datasets\nfrom ir_datasets.util import DownloadConfig\nfrom ir_datasets.formats import TrecQrels, TrecDocs, Trec"
  },
  {
    "path": "ir_datasets/datasets/trec_cast.py",
    "chars": 26279,
    "preview": "import gzip\nfrom hashlib import md5\nimport os\nfrom functools import cached_property, lru_cache, partial\nfrom collections"
  },
  {
    "path": "ir_datasets/datasets/trec_fair.py",
    "chars": 11842,
    "preview": "import json\nimport codecs\nfrom typing import NamedTuple, Dict, List, Optional\nimport ir_datasets\nfrom ir_datasets.util i"
  },
  {
    "path": "ir_datasets/datasets/trec_mandarin.py",
    "chars": 2244,
    "preview": "from typing import NamedTuple\nimport ir_datasets\nfrom ir_datasets.util import GzipExtract, DownloadConfig\nfrom ir_datase"
  },
  {
    "path": "ir_datasets/datasets/trec_robust04.py",
    "chars": 3916,
    "preview": "import ir_datasets\nfrom ir_datasets.util import GzipExtract, Lazy, DownloadConfig\nfrom ir_datasets.formats import TrecQr"
  },
  {
    "path": "ir_datasets/datasets/trec_spanish.py",
    "chars": 3993,
    "preview": "from typing import NamedTuple\nimport ir_datasets\nfrom ir_datasets.util import GzipExtract, DownloadConfig\nfrom ir_datase"
  },
  {
    "path": "ir_datasets/datasets/trec_tot.py",
    "chars": 3743,
    "preview": "import ir_datasets\nfrom ir_datasets.util import ZipExtract, Cache, Lazy, DownloadConfig\nfrom ir_datasets.formats import "
  },
  {
    "path": "ir_datasets/datasets/trec_tot_2025.py",
    "chars": 4606,
    "preview": "from ir_datasets import registry\nfrom ir_datasets.datasets.base import Dataset, YamlDocumentation\nfrom ir_datasets.util."
  },
  {
    "path": "ir_datasets/datasets/tripclick.py",
    "chars": 16373,
    "preview": "from pathlib import Path\nimport json\nimport re\nimport os\nimport io\nimport hashlib\nfrom datetime import datetime\nfrom typ"
  },
  {
    "path": "ir_datasets/datasets/tweets2013_ia.py",
    "chars": 19234,
    "preview": "import os\nimport itertools\nimport contextlib\nimport shutil\nimport tarfile\nfrom collections import Counter\nfrom pathlib i"
  },
  {
    "path": "ir_datasets/datasets/vaswani.py",
    "chars": 3969,
    "preview": "import io\nimport itertools\nimport ir_datasets\nfrom ir_datasets.util import DownloadConfig, TarExtract, Cache\nfrom ir_dat"
  },
  {
    "path": "ir_datasets/datasets/wapo.py",
    "chars": 7511,
    "preview": "import io\nimport json\nimport tarfile\nfrom typing import NamedTuple, Tuple, Optional\nimport ir_datasets\nfrom ir_datasets."
  },
  {
    "path": "ir_datasets/datasets/wikiclir.py",
    "chars": 3077,
    "preview": "import contextlib\nfrom pathlib import Path\nfrom typing import NamedTuple\nimport ir_datasets\nfrom ir_datasets.util import"
  },
  {
    "path": "ir_datasets/datasets/wikir.py",
    "chars": 2129,
    "preview": "import contextlib\nfrom pathlib import Path\nfrom typing import NamedTuple\nimport ir_datasets\nfrom ir_datasets.util import"
  },
  {
    "path": "ir_datasets/docs/antique.yaml",
    "chars": 1265,
    "preview": "_:\n  pretty_name: 'ANTIQUE'\n  desc: '\n<p>\n\"ANTIQUE is a non-factoid quesiton answering dataset based on the questions an"
  },
  {
    "path": "ir_datasets/docs/aol-ia.yaml",
    "chars": 1291,
    "preview": "_:\n  pretty_name: 'AOL-IA (Internet Archive)'\n  desc: '\n<p>\nThis is a version of the AOL Query Log. Documents use versio"
  },
  {
    "path": "ir_datasets/docs/aquaint.yaml",
    "chars": 1689,
    "preview": "_:\n  pretty_name: 'AQUAINT'\n  desc: '\n<p>\nA document collection of about 1M English newswire text. Sources are the Xinhu"
  },
  {
    "path": "ir_datasets/docs/argsme.yaml",
    "chars": 4214,
    "preview": "_:\n  pretty_name: \"args.me\"\n  desc: |\n    <p>\n    The args.me corpus is one of the largest argument resources available\n"
  },
  {
    "path": "ir_datasets/docs/beir.yaml",
    "chars": 16887,
    "preview": "_:\n  pretty_name: 'Beir (benchmark suite)'\n  desc: '\n<p>\nBeir is a suite of benchmarks to test zero-shot transfer.\n</p>\n"
  },
  {
    "path": "ir_datasets/docs/bibliography.bib",
    "chars": 36793,
    "preview": "@inproceedings{Hashemi2020Antique,\n  title={ANTIQUE: A Non-Factoid Question Answering Benchmark},\n  author={Helia Hashem"
  },
  {
    "path": "ir_datasets/docs/c4.yaml",
    "chars": 643,
    "preview": "_:\n  pretty_name: 'C4'\n  desc: '\n<p>\nA version of <a href=\"https://www.tensorflow.org/datasets/catalog/c4\">Google''s C4 "
  },
  {
    "path": "ir_datasets/docs/car.yaml",
    "chars": 2537,
    "preview": "_:\n  pretty_name: 'TREC CAR'\n  desc: '\n<p>\nAn ad-hoc passage retrieval collection, constructed from Wikipedia and used a"
  },
  {
    "path": "ir_datasets/docs/clinicaltrials.yaml",
    "chars": 2705,
    "preview": "_:\n  pretty_name: 'Clinical Trials'\n  desc: '\n<p>\nClinical trial information from <a href=\"https://clinicaltrials.gov/\">"
  },
  {
    "path": "ir_datasets/docs/clirmatrix.yaml",
    "chars": 2195,
    "preview": "_:\n  pretty_name: 'CLIRMatrix'\n  desc: '\n<p>\nCLIRMatrix contains is massively large collection of bilingual and multilin"
  },
  {
    "path": "ir_datasets/docs/clueweb09.yaml",
    "chars": 4530,
    "preview": "_:\n  pretty_name: 'ClueWeb09'\n  desc: '\n<p>\nClueWeb 2009 web document collection. Contains over 1B web pages, in 10 lang"
  },
  {
    "path": "ir_datasets/docs/clueweb12.yaml",
    "chars": 7470,
    "preview": "_:\n  pretty_name: 'ClueWeb12'\n  desc: '\n<p>\nClueWeb 2012 web document collection. Contains 733M web pages.\n</p>\n<p>\nThe "
  },
  {
    "path": "ir_datasets/docs/codec.yaml",
    "chars": 1349,
    "preview": "_:\n  pretty_name: 'CODEC'\n  desc: '\n<p>\nCODEC Document Ranking sub-task.\n</p>\n<ul>\n<li>Documents: curated web articles</"
  },
  {
    "path": "ir_datasets/docs/codesearchnet.yaml",
    "chars": 1022,
    "preview": "_:\n  pretty_name: 'CodeSearchNet'\n  desc: '\n<p>\nA benchmark for semantic code search. Uses \n</p>\n<ul>\n  <li>Documents: C"
  },
  {
    "path": "ir_datasets/docs/cord19.yaml",
    "chars": 5002,
    "preview": "_:\n  pretty_name: 'CORD-19'\n  desc: '\n<p>\nCollection of scientific articles related to COVID-19.\n</p>\n<p>\nUses the 2020-"
  },
  {
    "path": "ir_datasets/docs/cranfield.yaml",
    "chars": 300,
    "preview": "_:\n  pretty_name: 'Cranfield'\n  desc: '\n<p>\nA small corpus of 1,400 scientific abstracts.\n</p>\n<ul>\n  <li>Documents: Sci"
  },
  {
    "path": "ir_datasets/docs/csl.yaml",
    "chars": 192,
    "preview": "_:\n  pretty_name: 'CSL'\n  desc: '\n<p>\nThe CSL dataset, used for the TREC NueCLIR technical document task.\n</p>\n'\n\ntrec-2"
  },
  {
    "path": "ir_datasets/docs/disks45.yaml",
    "chars": 4479,
    "preview": "_:\n  pretty_name: 'TREC Disks 4 and 5'\n  desc: '\n<p>\nTREC Disks 4 and 5, including documents from the Financial Times, t"
  },
  {
    "path": "ir_datasets/docs/dpr-w100.yaml",
    "chars": 2184,
    "preview": "_:\n  pretty_name: 'DPR Wiki100'\n  desc: '\n<p>\nA wikipedia dump from 20 December, 2018, split into passages of 100 words."
  },
  {
    "path": "ir_datasets/docs/gov.yaml",
    "chars": 3154,
    "preview": "_:\n  pretty_name: 'GOV'\n  desc: '\n<p>\nGOV web document collection. Used for early TREC Web Tracks. Not to be confused wi"
  },
  {
    "path": "ir_datasets/docs/gov2.yaml",
    "chars": 6202,
    "preview": "_:\n  pretty_name: 'GOV2'\n  desc: '\n<p>\nGOV2 web document collection. Used for the TREC Terabyte Track.\n</p>\n<p>\nThe data"
  },
  {
    "path": "ir_datasets/docs/hc4.yaml",
    "chars": 5257,
    "preview": "_:\n  pretty_name: 'HC4 (HLTCOE CLIR Common-Crawl Collection)'\n  desc: '\n<p>\nHC4 is a new suite of test collections for a"
  },
  {
    "path": "ir_datasets/docs/highwire.yaml",
    "chars": 1574,
    "preview": "_:\n  pretty_name: 'Highwire (TREC Genomics 2006-07)'\n  desc: '\n<p>\nMedical document collection from <a href=\"https://www"
  },
  {
    "path": "ir_datasets/docs/istella22.yaml",
    "chars": 1169,
    "preview": "_:\n  pretty_name: 'Istella22'\n  desc: '\n<p>\nThe Istella22 dataset facilitates comparisions between traditional and neura"
  },
  {
    "path": "ir_datasets/docs/kilt.yaml",
    "chars": 1144,
    "preview": "_:\n  pretty_name: 'KILT'\n  desc: '\n<p>\nKILT is a corpus used for various \"knowledge intensive language tasks\".\n</p>\n<ul>"
  },
  {
    "path": "ir_datasets/docs/lotte.yaml",
    "chars": 7868,
    "preview": "_:\n  pretty_name: 'LoTTE'\n  bibtex_ids: ['Santhanam2021ColBERTv2']\n  desc: '\n<p>\nLoTTE (Long-Tail Topic-stratified Evalu"
  },
  {
    "path": "ir_datasets/docs/medline.yaml",
    "chars": 3031,
    "preview": "_:\n  pretty_name: 'Medline'\n  desc: '\n<p>\nMedical articles from <a href=\"https://www.nlm.nih.gov/bsd/medline.html\">Medli"
  },
  {
    "path": "ir_datasets/docs/miracl.yaml",
    "chars": 8198,
    "preview": "_:\n  pretty_name: 'MIRACL'\n  desc: '\n<p>\nMIRACL is a multilingual adhoc retrieval dataset covering 18 languages.\nThe doc"
  },
  {
    "path": "ir_datasets/docs/mmarco.yaml",
    "chars": 17454,
    "preview": "_:\n  pretty_name: 'mMARCO'\n  desc: '\n<p>\nA version of the MS MARCO passage dataset (<a class=\"ds-ref\">msmarco-passage</a"
  },
  {
    "path": "ir_datasets/docs/mr-tydi.yaml",
    "chars": 5608,
    "preview": "_:\n  pretty_name: 'Mr. TyDi'\n  bibtex_ids: ['Zhang2021MrTyDi', 'Clark2020TyDiQa']\n  desc: '\n<p>\nA multi-lingual benchmar"
  },
  {
    "path": "ir_datasets/docs/msmarco-document-v2.yaml",
    "chars": 4301,
    "preview": "_:\n  pretty_name: 'MSMARCO (document, version 2)'\n  desc: '\n  <p>\nVersion 2 of the MS MARCO document ranking dataset. Th"
  },
  {
    "path": "ir_datasets/docs/msmarco-document.yaml",
    "chars": 5810,
    "preview": "_:\n  pretty_name: 'MSMARCO (document)'\n  desc: '\n  <p>\n\"Based the questions in the [MS-MARCO] Question Answering Dataset"
  },
  {
    "path": "ir_datasets/docs/msmarco-passage-v2.yaml",
    "chars": 3711,
    "preview": "_:\n  pretty_name: 'MSMARCO (passage, version 2)'\n  desc: '\n  <p>\nVersion 2 of the MS MARCO passage ranking dataset. The "
  },
  {
    "path": "ir_datasets/docs/msmarco-passage.yaml",
    "chars": 8734,
    "preview": "_:\n  pretty_name: 'MSMARCO (passage)'\n  desc: '\n<p>\nA passage ranking benchmark with a collection of 8.8 million passage"
  },
  {
    "path": "ir_datasets/docs/msmarco-qna.yaml",
    "chars": 2590,
    "preview": "_:\n  pretty_name: 'MSMARCO (QnA)'\n  desc: '\n<p>\nThe MS MARCO Question Answering dataset. This is the source collection o"
  },
  {
    "path": "ir_datasets/docs/nano-beir.yaml",
    "chars": 5988,
    "preview": "_:\n  pretty_name: 'Nano Beir (benchmark suite)'\n  desc: '\n<p>\nNano Beir is a smaller version (max 50 queries per benchma"
  },
  {
    "path": "ir_datasets/docs/natural-questions.yaml",
    "chars": 1381,
    "preview": "_:\n  pretty_name: 'Natural Questions'\n  desc: '\n<p>\nGoogle Natural Questions is a Q&amp;A dataset containing long, short"
  },
  {
    "path": "ir_datasets/docs/neuclir.yaml",
    "chars": 3992,
    "preview": "_:\n  pretty_name: 'NeuCLIR Corpus'\n  desc: '\n<p>\nThis is the dataset created for <a href=\"https://neuclir.github.io/\">TR"
  },
  {
    "path": "ir_datasets/docs/neumarco.yaml",
    "chars": 2860,
    "preview": "_:\n  pretty_name: \"neuMARCO\"\n  desc: '\n<p>\nA version of <a class=\"ds-ref\">msmarco-passage</a> for cross-language\ninforma"
  },
  {
    "path": "ir_datasets/docs/nfcorpus.yaml",
    "chars": 2124,
    "preview": "_:\n  pretty_name: 'NFCorpus (NutritionFacts)'\n  desc: '\n<p>\n\"NFCorpus is a full-text English retrieval data set for Medi"
  },
  {
    "path": "ir_datasets/docs/nyt.yaml",
    "chars": 2818,
    "preview": "_:\n  pretty_name: 'NYT'\n  desc: '\n  <p>\nThe New York Times Annotated Corpus. Consists of articles published between 1987"
  },
  {
    "path": "ir_datasets/docs/pmc.yaml",
    "chars": 1787,
    "preview": "_:\n  pretty_name: 'PubMed Central (TREC CDS)'\n  desc: '\n<p>\nBio-medical articles from <a href=\"https://www.ncbi.nlm.nih."
  },
  {
    "path": "ir_datasets/docs/sara.yaml",
    "chars": 372,
    "preview": "_: # matches documentation key above\n  pretty_name: 'SARA' # a more human-readable way to present this dataset than the "
  },
  {
    "path": "ir_datasets/docs/touche-image.yaml",
    "chars": 1846,
    "preview": "_:\n  pretty_name: \"Touché Image Search\"\n  desc: |\n    <p>\n    Focused crawl of about 23 841 images (and associated web p"
  },
  {
    "path": "ir_datasets/docs/touche.yaml",
    "chars": 13216,
    "preview": "2020/task-1:\n  pretty_name: \"Touché 2020 Task 1: Argument Retrieval for Controversial Questions\"\n  desc: |\n    <p>\n    D"
  },
  {
    "path": "ir_datasets/docs/trec-arabic.yaml",
    "chars": 1489,
    "preview": "_:\n  pretty_name: 'TREC Arabic'\n  desc: '\n<p>\nA collection of news articles in Arabic, used for multi-lingual evaluation"
  },
  {
    "path": "ir_datasets/docs/trec-cast.yaml",
    "chars": 4543,
    "preview": "_:\n  pretty_name: 'TREC CAsT (Conversational Assistance)'\n  desc: '\n<p>\nThe TREC Conversational Assistance Track (CAsT) "
  },
  {
    "path": "ir_datasets/docs/trec-fair.yaml",
    "chars": 1000,
    "preview": "_:\n  pretty_name: \"TREC Fair Ranking\"\n  desc: '\n<p>\nThe TREC Fair Ranking track evaluates systems according to how well "
  },
  {
    "path": "ir_datasets/docs/trec-mandarin.yaml",
    "chars": 1536,
    "preview": "_:\n  pretty_name: 'TREC Mandarin'\n  desc: '\n<p>\nA collection of news articles in Mandarin in Simplified Chinese, used fo"
  },
  {
    "path": "ir_datasets/docs/trec-robust04.yaml",
    "chars": 2876,
    "preview": "_:\n  pretty_name: 'TREC Robust 2004'\n  desc: '\n<p>\nThe TREC Robust retrieval task focuses on \"improving the consistency "
  },
  {
    "path": "ir_datasets/docs/trec-spanish.yaml",
    "chars": 1458,
    "preview": "_:\n  pretty_name: 'TREC Spanish'\n  desc: '\n<p>\nA collection of news articles in Spanish, used for multi-lingual evaluati"
  },
  {
    "path": "ir_datasets/docs/trec-tot-2025.yaml",
    "chars": 913,
    "preview": "_:\n  pretty_name: 'TREC Tip-of-the-Tongue'\n  desc: '\n<p>\nTip of the tongue: The phenomenon of failing to retrieve someth"
  },
  {
    "path": "ir_datasets/docs/trec-tot.yaml",
    "chars": 813,
    "preview": "_:\n  pretty_name: 'TREC Tip-of-the-Tongue'\n  desc: '\n<p>\nTip of the tongue: The phenomenon of failing to retrieve someth"
  },
  {
    "path": "ir_datasets/docs/tripclick.yaml",
    "chars": 9087,
    "preview": "_:\n  pretty_name: 'TripClick'\n  desc: '\n<p>\nTripClick is a large collection from the <a href=\"https://www.tripdatabase.c"
  },
  {
    "path": "ir_datasets/docs/tweets2013-ia.yaml",
    "chars": 1721,
    "preview": "_:\n  pretty_name: 'Tweets 2013 (Internet Archive)'\n  desc: '\n<p>\nA collection of tweets from a 2-month window achived by"
  },
  {
    "path": "ir_datasets/docs/vaswani.yaml",
    "chars": 305,
    "preview": "_:\n  pretty_name: 'Vaswani'\n  desc: '\n<p>\nA small corpus of roughly 11,000 scientific abstracts.\n</p>\n<ul>\n  <li>Documen"
  },
  {
    "path": "ir_datasets/docs/wapo.yaml",
    "chars": 3079,
    "preview": "_:\n  pretty_name: 'Washington Post'\n  desc: '\n<p>\nThe Washington Post collection.\n</p>'\n  docs_instructions: &inst \"docs"
  },
  {
    "path": "ir_datasets/docs/wikiclir.yaml",
    "chars": 3046,
    "preview": "_:\n  pretty_name: \"WikiCLIR\"\n  desc: '\n<p>\nA Cross-Language IR (CLIR) collection between English queries and other langu"
  },
  {
    "path": "ir_datasets/docs/wikir.yaml",
    "chars": 5125,
    "preview": "_:\n  pretty_name: \"WikIR\"\n  desc: '\n<p>\nA suite of IR benchmarks in multiple languages built from Wikipeida.\n</p>\n<ul>\n<"
  },
  {
    "path": "ir_datasets/etc/downloads.json",
    "chars": 286747,
    "preview": "{\n  \"antique\": {\n    \"docs\": {\n      \"url\": \"https://ciir.cs.umass.edu/downloads/Antique/antique-collection.txt\",\n      "
  },
  {
    "path": "ir_datasets/etc/metadata.json",
    "chars": 135539,
    "preview": "{\n  \"antique\": {\"docs\": {\"count\": 403666, \"fields\": {\"doc_id\": {\"max_len\": 10, \"common_prefix\": \"\"}}}},\n  \"antique/test\""
  },
  {
    "path": "ir_datasets/formats/__init__.py",
    "chars": 1721,
    "preview": "from .base import GenericDoc, GenericQuery, GenericQrel, GenericScoredDoc, GenericDocPair, DocstoreBackedDocs, DocSource"
  },
  {
    "path": "ir_datasets/formats/argsme.py",
    "chars": 16778,
    "preview": "from ast import literal_eval\nfrom csv import DictReader, field_size_limit\nfrom datetime import datetime\nfrom enum import"
  },
  {
    "path": "ir_datasets/formats/base.py",
    "chars": 11804,
    "preview": "import hashlib\nimport json\nimport types\nimport itertools\nfrom typing import NamedTuple\nimport ir_datasets\n\n_logger = ir_"
  },
  {
    "path": "ir_datasets/formats/clirmatrix.py",
    "chars": 1299,
    "preview": "import codecs\nimport json\nfrom . import TrecQrels, TrecQrel\nfrom .base import GenericQuery, BaseQueries\n\n\nclass CLIRMatr"
  },
  {
    "path": "ir_datasets/formats/csv_fmt.py",
    "chars": 3251,
    "preview": "import sys\nimport codecs\nimport contextlib\nimport csv\nfrom typing import Tuple\nimport io\nimport ir_datasets\nfrom .base i"
  },
  {
    "path": "ir_datasets/formats/extracted_cc.py",
    "chars": 8735,
    "preview": "from typing import Dict, NamedTuple\nimport json\n\nimport ir_datasets\nfrom ir_datasets.formats.base import BaseDocs, BaseQ"
  },
  {
    "path": "ir_datasets/formats/jsonl.py",
    "chars": 3067,
    "preview": "import sys\nimport codecs\nimport contextlib\nimport json\nfrom typing import Tuple\nimport io\nimport ir_datasets\nfrom .base "
  },
  {
    "path": "ir_datasets/formats/ntcir.py",
    "chars": 593,
    "preview": "import codecs\nfrom . import TrecQrels, TrecQrel\n\n\nclass NtcirQrels(TrecQrels):\n    def qrels_iter(self):\n        with se"
  },
  {
    "path": "ir_datasets/formats/touche.py",
    "chars": 23436,
    "preview": "from enum import Enum\nfrom io import TextIOWrapper\nfrom json import loads\nfrom typing import NamedTuple, Any, Optional, "
  },
  {
    "path": "ir_datasets/formats/touche_image.py",
    "chars": 8782,
    "preview": "from io import TextIOWrapper\nfrom itertools import takewhile\nfrom json import loads\nfrom re import compile\nfrom typing i"
  },
  {
    "path": "ir_datasets/formats/trec.py",
    "chars": 20308,
    "preview": "import io\nimport codecs\nimport tarfile\nimport re\nimport gzip\nfrom glob import glob as fnglob\nimport xml.etree.ElementTre"
  },
  {
    "path": "ir_datasets/formats/tsv.py",
    "chars": 7144,
    "preview": "import contextlib\nfrom typing import Tuple\nimport io\nimport ir_datasets\nfrom .base import GenericDoc, GenericQuery, Gene"
  },
  {
    "path": "ir_datasets/formats/webarc.py",
    "chars": 3204,
    "preview": "import gzip\nimport re\nfrom contextlib import contextmanager, ExitStack\nfrom typing import NamedTuple\nimport ir_datasets\n"
  },
  {
    "path": "ir_datasets/indices/__init__.py",
    "chars": 421,
    "preview": "from .base import Docstore, DEFAULT_DOCSTORE_OPTIONS, DocstoreOptions, FileAccess\nfrom .indexed_tsv_docstore import Inde"
  },
  {
    "path": "ir_datasets/indices/base.py",
    "chars": 1310,
    "preview": "\nfrom dataclasses import dataclass, field\nfrom enum import Enum\n\nclass FileAccess(Enum):\n    FILE = 0\n    MMAP = 1\n    M"
  },
  {
    "path": "ir_datasets/indices/cache_docstore.py",
    "chars": 1116,
    "preview": "import os\nfrom contextlib import contextmanager\nimport ir_datasets\nfrom . import Docstore, Lz4PickleLookup, DEFAULT_DOCS"
  },
  {
    "path": "ir_datasets/indices/clueweb_warc.py",
    "chars": 11467,
    "preview": "import io\nimport os\nimport gzip\nfrom contextlib import ExitStack\nimport ir_datasets\nfrom . import Docstore\n\nclass WarcIn"
  },
  {
    "path": "ir_datasets/indices/indexed_tsv_docstore.py",
    "chars": 11612,
    "preview": "import os\nimport shutil\nimport json\nimport zlib\nimport pickle\nfrom contextlib import contextmanager\nimport ir_datasets\n\n"
  },
  {
    "path": "ir_datasets/indices/lz4_pickle.py",
    "chars": 11614,
    "preview": "import io\nimport mmap\nimport os\nimport pickle\n\nfrom ir_datasets.indices import DEFAULT_DOCSTORE_OPTIONS, FileAccess\n\ntry"
  },
  {
    "path": "ir_datasets/indices/numpy_sorted_index.py",
    "chars": 6825,
    "preview": "import os\nimport ir_datasets\nfrom ir_datasets.indices import FileAccess\n\nclass NumpySortedIndex:\n    def __init__(self, "
  },
  {
    "path": "ir_datasets/indices/zpickle_docstore.py",
    "chars": 4824,
    "preview": "import os\nimport shutil\nimport json\nimport zlib\nimport pickle\nfrom contextlib import contextmanager\nfrom .indexed_tsv_do"
  },
  {
    "path": "ir_datasets/lazy_libs.py",
    "chars": 4917,
    "preview": "# These libraries can add a bunch of overhead when imported -- which is bad for command line\n# utilities. This file load"
  },
  {
    "path": "ir_datasets/log.py",
    "chars": 5726,
    "preview": "import sys\nimport logging\nimport operator\nfrom contextlib import contextmanager\nfrom time import time\nimport ir_datasets"
  },
  {
    "path": "ir_datasets/util/__init__.py",
    "chars": 9550,
    "preview": "import re\nimport os\nimport math\nimport functools\nimport shutil\nfrom contextlib import contextmanager\nfrom threading impo"
  },
  {
    "path": "ir_datasets/util/docs/__init__.py",
    "chars": 0,
    "preview": ""
  },
  {
    "path": "ir_datasets/util/docs/lazy.py",
    "chars": 6463,
    "preview": "from abc import ABC, abstractmethod\nfrom functools import cached_property, lru_cache\nfrom typing import Iterator, Protoc"
  },
  {
    "path": "ir_datasets/util/docs/multiple.py",
    "chars": 5584,
    "preview": "from typing import List, Sequence, Tuple, Optional\nfrom functools import cached_property, lru_cache\nfrom dataclasses imp"
  },
  {
    "path": "ir_datasets/util/docs/subset.py",
    "chars": 4245,
    "preview": "import array\nimport os\nfrom functools import cached_property, lru_cache\nfrom typing import Optional\n\nimport ir_datasets\n"
  },
  {
    "path": "ir_datasets/util/download.py",
    "chars": 16850,
    "preview": "import json\nimport pkgutil\nimport os\nimport sys\nfrom pathlib import Path\nimport atexit\nfrom collections import deque\nimp"
  },
  {
    "path": "ir_datasets/util/fileio.py",
    "chars": 9099,
    "preview": "import os\nimport contextlib\nimport shutil\nfrom pathlib import Path\nfrom fnmatch import fnmatch\nimport tarfile\nimport gzi"
  },
  {
    "path": "ir_datasets/util/hash.py",
    "chars": 1433,
    "preview": "import io\nimport hashlib\nimport ir_datasets\n\n\n__all__ = ['HashVerificationError', 'HashVerifier', 'HashStream']\n_logger "
  },
  {
    "path": "ir_datasets/util/html_parsing.py",
    "chars": 3341,
    "preview": "from collections import deque\nimport re\nimport io\nimport ir_datasets\n\n\ndef find_charset(text):\n    if text is None:\n    "
  },
  {
    "path": "ir_datasets/util/metadata.py",
    "chars": 3316,
    "preview": "import json\nfrom typing import Callable, Optional, Dict, Any\nfrom functools import partial\nimport ir_datasets\nfrom .file"
  },
  {
    "path": "ir_datasets/util/registry.py",
    "chars": 1591,
    "preview": "import os\nimport re\nimport ir_datasets\nfrom .metadata import MetadataComponent\n\n\n__all__ = 'Registry'\n_logger = ir_datas"
  },
  {
    "path": "ir_datasets/wrappers/__init__.py",
    "chars": 45,
    "preview": "from .html_extractor import HtmlDocExtractor\n"
  },
  {
    "path": "ir_datasets/wrappers/html_extractor.py",
    "chars": 4864,
    "preview": "import math\nimport os\nimport multiprocessing\nfrom threading import Semaphore\nimport ir_datasets\n\n\n_logger = ir_datasets."
  },
  {
    "path": "pyproject.toml",
    "chars": 1898,
    "preview": "[build-system]\nrequires = [\"setuptools>=42\", \"wheel\"]\nbuild-backend = \"setuptools.build_meta\"\n\n[project]\nname = \"ir_data"
  },
  {
    "path": "requirements-test.txt",
    "chars": 20,
    "preview": "pyautocorpus>=0.1.1\n"
  },
  {
    "path": "requirements.txt",
    "chars": 89,
    "preview": "lxml>=4.5.2,<6.0.0\nnumpy>=1.18.1\npyyaml>=5.3.1\nrequests>=2.22.0\ntqdm>=4.38.0\nlz4>=3.1.10\n"
  },
  {
    "path": "test/__init__.py",
    "chars": 0,
    "preview": ""
  },
  {
    "path": "test/downloads.py",
    "chars": 5901,
    "preview": "import requests\nimport gzip\nimport io\nimport random\nimport sys\nimport json\nimport time\nimport datetime\nfrom contextlib i"
  },
  {
    "path": "test/dummy/docs.tsv",
    "chars": 1455,
    "preview": "T1\tCUT, CAP AND BALANCE. TAXED ENOUGH ALREADY!\nT2\tTake a look at and to see these beautiful hotels.\nT3\tUS News named the"
  },
  {
    "path": "test/dummy/qrels",
    "chars": 515,
    "preview": "1 0 T1 0\n1 0 T2 0\n1 0 T4 1\n1 0 T5 0\n1 0 T6 0\n1 0 T7 0\n1 0 T8 1\n1 0 T9 1\n1 0 T10 0\n1 0 T11 0\n1 0 T12 0\n1 0 T13 0\n1 0 T14 "
  },
  {
    "path": "test/dummy/queries.tsv",
    "chars": 72,
    "preview": "1\trepublican party\n2\thospitality industry\n3\tgovernment spending\n4\tmedia\n"
  },
  {
    "path": "test/formats/__init__.py",
    "chars": 0,
    "preview": ""
  },
  {
    "path": "test/formats/test_trec.py",
    "chars": 3281,
    "preview": "import os\nimport shutil\nimport unittest\nfrom ir_datasets.formats import TrecQrel, TrecQrels, TrecQuery, TrecQueries, Tre"
  },
  {
    "path": "test/formats/test_tsv.py",
    "chars": 4027,
    "preview": "import os\nfrom typing import NamedTuple, Tuple\nimport shutil\nimport unittest\nfrom ir_datasets.formats import TsvDocs, Ts"
  },
  {
    "path": "test/indices/__init__.py",
    "chars": 0,
    "preview": ""
  },
  {
    "path": "test/indices/lz4_pickle.py",
    "chars": 3078,
    "preview": "import tempfile\nimport unittest\nimport numpy as np\nfrom ir_datasets.indices import Lz4PickleLookup, FileAccess\nfrom ir_d"
  },
  {
    "path": "test/indices/numpy_sorted.py",
    "chars": 1847,
    "preview": "import tempfile\nimport unittest\nimport numpy as np\nfrom ir_datasets.indices import NumpySortedIndex\n\n\nclass TestNumpySor"
  },
  {
    "path": "test/integration/__init__.py",
    "chars": 0,
    "preview": ""
  },
  {
    "path": "test/integration/antique.py",
    "chars": 6771,
    "preview": "import unittest\nimport ir_datasets\nfrom ir_datasets.formats import GenericDoc, GenericQuery, TrecQrel\nfrom .base import "
  },
  {
    "path": "test/integration/aol_ia.py",
    "chars": 2819,
    "preview": "import re\nimport unittest\nimport datetime\nimport ir_datasets\nfrom ir_datasets.formats import GenericQuery, TrecQrel\nfrom"
  }
]

// ... and 69 more files (download for full content)