Merge pull request #1330 from nextstrain/feat/dataset-name-shortcuts

packages_rs/nextclade-cli/src/cli/nextclade_dataset_get.rs

@@ -64,7 +64,7 @@ pub fn dataset_http_get(http: &mut HttpClient, name: impl AsRef<str>, tag: &Opti
     })
     // Filter by name
     .filter(|dataset| {
-      dataset.path == name
+      dataset.path == name || dataset.shortcuts.contains(&String::from(name))
     })
     .collect_vec();
 

packages_rs/nextclade-cli/src/cli/nextclade_dataset_list.rs

@@ -46,21 +46,14 @@ pub fn nextclade_dataset_list(
     })
     .filter(|dataset| {
       if let Some(name) = &name {
-        name == &dataset.path
+        name == &dataset.path || dataset.shortcuts.contains(name)
       } else {
         true
       }
     })
     .filter(|dataset| {
       if let Some(search) = &search {
-        [
-          Some(dataset.path.as_str()),
-          dataset.name(),
-          dataset.ref_name(),
-          dataset.ref_accession(),
-        ]
-        .iter()
-        .any(|candidate| candidate.unwrap_or_default().contains(search))
+        dataset.search_strings().any(|candidate| candidate.contains(search))
       } else {
         true
       }

packages_rs/nextclade-cli/src/dataset/dataset_download.rs

@@ -220,6 +220,7 @@ pub fn dataset_individual_files_load(
           VirusProperties {
             schema_version: "".to_owned(),
             attributes: BTreeMap::default(),
+            shortcuts: vec![],
             meta: DatasetMeta::default(),
             files: DatasetFiles {
               reference: "".to_owned(),

packages_rs/nextclade-cli/src/dataset/dataset_table.rs

@@ -5,6 +5,7 @@ use itertools::Itertools;
 use nextclade::io::dataset::Dataset;
 use nextclade::o;
 use nextclade::utils::string::surround_with_quotes;
+use std::borrow::Cow;
 
 pub fn format_dataset_table(filtered: &[Dataset]) -> String {
   let mut table = Table::new();
@@ -17,7 +18,19 @@ pub fn format_dataset_table(filtered: &[Dataset]) -> String {
   table.set_header([o!("name"), o!("attributes"), o!("versions"), o!("authors")]);
 
   for dataset in filtered.iter() {
-    let Dataset { attributes, .. } = dataset;
+    let Dataset {
+      path,
+      shortcuts,
+      attributes,
+      ..
+    } = dataset;
+
+    let name = if !shortcuts.is_empty() {
+      let shortcuts = shortcuts.iter().map(surround_with_quotes).join(", ");
+      Cow::Owned(format!("{path}\n(shortcuts: {shortcuts})"))
+    } else {
+      Cow::Borrowed(path)
+    };
 
     let attrs = attributes
       .iter()
@@ -34,7 +47,7 @@ pub fn format_dataset_table(filtered: &[Dataset]) -> String {
 
     let authors = dataset.meta.authors.join(", ");
 
-    table.add_row([&dataset.path, &attrs, &versions, &authors]);
+    table.add_row([&name, &attrs, &versions, &authors]);
   }
 
   table.to_string()

packages_rs/nextclade-web/src/components/Main/DatasetSelectorList.tsx

@@ -38,7 +38,7 @@ export function DatasetSelectorList({
       attrStrMaybe(dataset.attributes, 'name') ?? '',
       attrStrMaybe(dataset.attributes, 'reference name') ?? '',
       attrStrMaybe(dataset.attributes, 'reference accession') ?? '',
-      dataset.path,
+      ...(dataset.shortcuts ?? []),
     ])
   }, [datasetsActive, datasetsInactive, searchTerm])
 

packages_rs/nextclade-web/src/io/fetchDatasetsIndex.ts

@@ -1,5 +1,5 @@
 import { AxiosError } from 'axios'
-import { get, head, mapValues, sortBy, sortedUniq } from 'lodash'
+import { get, head, isNil, mapValues, sortBy, sortedUniq } from 'lodash'
 import semver from 'semver'
 import { takeFirstMaybe } from 'src/helpers/takeFirstMaybe'
 import urljoin from 'url-join'
@@ -47,7 +47,7 @@ export function findDataset(datasets: Dataset[], name?: string, tag?: string) {
 /** Find the datasets given name, ref and tag */
 export function filterDatasets(datasets: Dataset[], name?: string, tag?: string) {
   return datasets.filter((dataset) => {
-    let isMatch = dataset.path === name
+    let isMatch = !isNil(name) && (dataset.path === name || !!dataset.shortcuts?.includes(name))
 
     if (tag) {
       isMatch = isMatch && dataset.version?.tag === tag

packages_rs/nextclade/src/analyze/virus_properties.rs

@@ -33,6 +33,9 @@ pub struct VirusProperties {
   #[serde(default, skip_serializing_if = "BTreeMap::is_empty")]
   pub attributes: BTreeMap<String, AnyType>,
 
+  #[serde(default, skip_serializing_if = "Vec::is_empty")]
+  pub shortcuts: Vec<String>,
+
   #[serde(default, skip_serializing_if = "DatasetMeta::is_default")]
   pub meta: DatasetMeta,
 

packages_rs/nextclade/src/io/dataset.rs

@@ -3,7 +3,7 @@ use crate::io::schema_version::{SchemaVersion, SchemaVersionParams};
 use crate::o;
 use crate::utils::any::AnyType;
 use eyre::Report;
-use itertools::Itertools;
+use itertools::{chain, Itertools};
 use schemars::JsonSchema;
 use semver::Version;
 use serde::{Deserialize, Serialize};
@@ -57,6 +57,9 @@ pub struct DatasetCollection {
 pub struct Dataset {
   pub path: String,
 
+  #[serde(default, skip_serializing_if = "Vec::is_empty")]
+  pub shortcuts: Vec<String>,
+
   #[serde(default, skip_serializing_if = "BTreeMap::is_empty")]
   pub attributes: BTreeMap<String, AnyType>,
 
@@ -83,6 +86,20 @@ impl Dataset {
     self.attributes.get("name").and_then(AnyType::as_str_maybe)
   }
 
+  pub fn search_strings(&self) -> impl Iterator<Item = &str> {
+    let names = [
+      Some(self.path.as_str()),
+      self.name(),
+      self.ref_name(),
+      self.ref_accession(),
+    ]
+    .into_iter()
+    .flatten();
+
+    let shortcuts = self.shortcuts.iter().map(String::as_str);
+
+    chain!(names, shortcuts)
+  }
   pub fn ref_name(&self) -> Option<&str> {
     self.attributes.get("reference name").and_then(AnyType::as_str_maybe)
   }