diff options
| author | zsloan | 2024-06-24 19:24:33 +0000 |
|---|---|---|
| committer | zsloan | 2024-06-24 19:24:33 +0000 |
| commit | a2eb0c2dff1ab93ff88f2c22754f4d3fc593078f (patch) | |
| tree | 6baf7899d081a208799e21dfcb9928e4b0abf921 | |
| parent | de1594fc15a5b81bcf2618c6e83ad4b93280d9cf (diff) | |
| download | genenetwork3-a2eb0c2dff1ab93ff88f2c22754f4d3fc593078f.tar.gz | |
Use dataset Name instead of FullName for indexing
The Name is generally used as the identifier, while the FullName can container spaces which can cause problems
| -rwxr-xr-x | scripts/index-genenetwork | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/scripts/index-genenetwork b/scripts/index-genenetwork index 34c68f2..d1eaf6f 100755 --- a/scripts/index-genenetwork +++ b/scripts/index-genenetwork @@ -304,7 +304,7 @@ def index_genes(xapian_build_directory: pathlib.Path, chunk_index: int, namespac trait["additive"].bind(partial(add_additive, doc)) # Index free text. - for key in ["description", "tissue", "dataset_fullname"]: + for key in ["description", "tissue", "dataset"]: trait[key].bind(index_text) trait.pop("probe_target_description").bind(index_text) for key in ["name", "symbol", "species", "group"]: @@ -316,7 +316,7 @@ def index_genes(xapian_build_directory: pathlib.Path, chunk_index: int, namespac trait["species"].bind(index_species) trait["group"].bind(index_group) trait["tissue"].bind(index_tissue) - trait["dataset_fullname"].bind(index_dataset) + trait["dataset"].bind(index_dataset) trait["symbol"].bind(index_symbol) trait["chr"].bind(index_chr) trait["geno_chr"].bind(index_peakchr) @@ -352,7 +352,7 @@ def index_phenotypes(xapian_build_directory: pathlib.Path, chunk_index: int, nam trait["year"].bind(partial(add_year, doc)) # Index free text. - for key in ["description", "authors", "dataset_fullname"]: + for key in ["description", "authors", "dataset"]: trait[key].bind(index_text) for key in ["Abstract", "Title"]: trait.pop(key).bind(index_text) @@ -366,7 +366,7 @@ def index_phenotypes(xapian_build_directory: pathlib.Path, chunk_index: int, nam trait["group"].bind(index_group) trait["authors"].bind(index_authors) trait["geno_chr"].bind(index_peakchr) - trait["dataset_fullname"].bind(index_dataset) + trait["dataset"].bind(index_dataset) # Convert name from integer to string. trait["name"] = trait["name"].map(str) |