cleanup

Author: pnrobinson

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "ga4ghphetools"
-version = "0.5.21"
+version = "0.5.22"
 edition = "2021"
 keywords = ["GA4GH", "Phenopacket Schema", "Human Phenotype Ontology"]
 description = "Generate GA4GH phenopackets from tabular data"

src/etl/etl_tools.rs

@@ -572,7 +572,7 @@ impl EtlTools {
     pub fn get_cohort_data(&mut self) -> Result<CohortData, String> {
         self.check_is_completely_transformed()?;
         self.qc()?;
-        let hpo_duplets = Self::all_hpo_duplets(&self);
+        let hpo_duplets = Self::all_hpo_duplets(self);
         let ultra_terms: Vec<_> = hpo_duplets
             .iter()
             .filter(|d| d.hpo_label().contains("Ultra"))
@@ -584,7 +584,7 @@ impl EtlTools {
             .collect();
         let disease = match &self.dto.disease {
             Some(d) => d.clone(),
-            None => { return Err(format!("Cannot create CohortData if ETL does not have disease data"))},
+            None => { return Err("Cannot create CohortData if ETL does not have disease data".to_string())},
         };
         let mut row_list: Vec<RowData> = Vec::new();
         let n_rows = self.get_row_count()?;

src/export/cohort_renderer.rs

@@ -87,12 +87,12 @@ pub struct TopLevelHpoRenderer {
 impl TopLevelHpoRenderer  {
     pub fn new(
         top_level_name: &str,
-        hpo_header: &Vec<HpoTermDuplet>,
+        hpo_header: &[HpoTermDuplet],
         rows: Vec<CohortRow>) -> Self {
         Self { 
             top_level_name: top_level_name.to_string(), 
             anchor: Self::make_anchor_id(top_level_name),
-            hpo_header: hpo_header.clone(), 
+            hpo_header: hpo_header.to_vec(), 
             n_hpo: hpo_header.len(),
             rows: rows 
         }
@@ -139,13 +139,13 @@ impl CohortRenderer {
         let top_level_map = match crate::hpo::get_hpo_terms_by_toplevel(cohort.clone(), hpo.clone()){
             Ok(tlmap) => tlmap,
             Err(e) => {
-                eprint!("{}", e.to_string());
+                eprint!("{}", e);
                 HashMap::<String, Vec<HpoTermDuplet>>::new()
             }
         };
         let mut top_level_list: Vec<TopLevelHpoRenderer> = Vec::new();
         for top in top_level_map {
-            let top_level = Self::get_top_level_section(&top.0, top.1, &cohort)
+            let top_level = Self::get_top_level_section(&top.0, top.1, cohort)
                 .map_err(|e|e.to_string())?;
             top_level_list.push(top_level);
         }

src/export/html_renderer.rs

@@ -27,7 +27,7 @@ impl HtmlRenderer {
             e
         });
         match html {
-            Ok(html) => { return html;},
+            Ok(html) => { html },
             Err(e) => {
                 panic!("{:?}",e);
             }

src/export/table_compare.rs

@@ -189,10 +189,10 @@ impl CategoryCounter {
     }
 
     pub fn over_threshold(&self, threshold: usize) -> bool {
-        return self
+        self
             .row_counter_list
             .iter()
-            .any(|c| c.over_threshold(threshold));
+            .any(|c| c.over_threshold(threshold))
     }
 
     pub fn get_subheader(&self) -> Vec<String> {
@@ -317,11 +317,11 @@ impl TableCompare {
             citation_set.insert(citation);
         };
         let citation_list: Vec<Citation> = citation_set.into_iter().collect();
-        return citation_list;
+        citation_list
     }
 
     pub fn get_citations(&self) -> Vec<Citation> {
-        return self.citation_list.clone();
+        self.citation_list.clone()
     }
 
 
@@ -373,14 +373,14 @@ impl TableCompare {
     }
 
     pub fn get_category_counters(&self) -> Vec<CategoryCounter> {
-        return self.category_map.values().cloned().collect()
+        self.category_map.values().cloned().collect()
     }
 
     pub(crate) fn get_count(&self, duplet: &HpoTermDuplet) -> usize {
-        return match self.total_term_count_map.get(duplet) {
+        match self.total_term_count_map.get(duplet) {
             Some(c) => *c,
             None => 0,
-        };
+        }
     }
 
 

src/factory/cohort_qc.rs

@@ -17,11 +17,11 @@ impl ConflictMap {
 
 
     fn conflict_count(&self) -> usize {
-            self.na_terms.len()
+        self.na_terms.len()
     }
 
     pub fn no_conflict(&self) -> bool {
-        return self.conflict_count() == 0;
+        self.conflict_count() == 0
     }
 
     pub fn report(&self) -> String {
@@ -100,9 +100,9 @@ impl CohortDataQc {
     pub fn qc_conflicting_pairs(&self, cohort: &CohortData) -> Result<(), String> {
         let conflicting_pairs = self.get_conflicting_termid_pairs(cohort)?;
         if conflicting_pairs.no_conflict() {
-            return Ok(())
+            Ok(())
         } else {
-            return Err(conflicting_pairs.report());
+            Err(conflicting_pairs.report())
         }   
     }
 
@@ -152,7 +152,7 @@ impl CohortDataQc {
             for tid in conflict_map.na_terms {
                 let idx = term_id_to_index_map
                     .get(&tid)
-                    .ok_or_else(|| format!("Could not get index for {}", tid.to_string()))?;
+                    .ok_or_else(|| format!("Could not get index for {}", tid))?;
                 row.hpo_data[*idx] = crate::dto::hpo_term_dto::CellValue::Na;
             }
         }

src/factory/gene_variant_bundle.rs

@@ -45,7 +45,7 @@ impl GeneVariantBundle {
 
       // Start index is the index in the template matrix where this block of columns starts
     pub fn from_row(
-        row: &Vec<String>,
+        row: &[String],
         start_idx: usize
     ) -> std::result::Result<Self, String> {
         let i = start_idx;

src/factory/mod.rs

@@ -28,13 +28,9 @@ mod cohort_qc;
 /// * `cohort_dto` - A [`CohortData`] object representing the cohort.
 ///
 /// # Returns
-/// * `Ok(String)` containing the template filename if the cohort is Mendelian,
-///   contains exactly one gene transcript, and has a cohort acronym.
+/// * `Ok(String)` containing the template filename (generated in the front end)
 /// * `Err(String)` if:
-///   - The cohort is not Mendelian,
-///   - No disease data is available,
-///   - More than one gene transcript is present (non-Mendelian case not implemented),
-///   - Or the cohort acronym is missing.
+///   - the cohort acronym is missing.
 ///
 /// # Errors
 /// This function returns an error with a descriptive message when the filename
@@ -46,29 +42,12 @@ mod cohort_qc;
 /// // e.g., "ACVR1_FOP_individuals.json"
 /// ```
 pub fn extract_template_name(cohort_dto: &CohortData) -> Result<String, String> {
-    if cohort_dto.is_melded() {
-        let name = melded_cohort_name(cohort_dto)?;
-        return Ok(format!("{}_individuals.json", name));
+    let acronym = match &cohort_dto.cohort_acronym {
+        Some(name) => name.to_string(),
+        None => {return Err("No cohort acronym found".to_string());}
     };
-    let disease_data = match cohort_dto.disease_list.first() {
-        Some(data) => data.clone(),
-        None => { return Err(format!("Could not extract disease data from Mendelian cohort"));},
-    };
-     if disease_data.gene_transcript_list.is_empty() {
-        return Err(format!("No gene/transcript objects found for.")); 
-    };
-    // one or multiple gene symbols: YFG1 or YFG1-YFG2
-    // this will work for Mendelian and digenic
-    let symbol_str = disease_data
-        .gene_transcript_list
-        .iter()
-        .map(|gtd| gtd.gene_symbol.to_string())
-        .collect::<Vec<_>>()
-        .join("-");
-    match &cohort_dto.cohort_acronym {
-        Some(acronym) => Ok(format!("{}_{}_individuals.json", symbol_str, acronym)),
-        None => Err(format!("Cannot get template name if acronym is missing.")),
-    }
+
+    Ok(format!("{}_individuals.json", acronym))
 }
 
 

src/hpoa/hpo_term_counter.rs

@@ -22,7 +22,7 @@ impl HpoTermCounter {
             let pmid = row.individual_data.pmid.clone();
             let term_data_list = pmid_to_term_data_list_d
                 .entry(pmid)
-                .or_insert(Vec::new());
+                .or_default();
             for (value, duplet) in row.hpo_data.iter().zip(cohort_dto.hpo_headers.clone()) {
                 let hpo_data = HpoTermData{
                     term_duplet: duplet.clone(),
@@ -39,7 +39,7 @@ impl HpoTermCounter {
                 if term_data.is_not_ascertained() {
                     continue; // Some of our upstream data has "na" values for a specific HPO term. There is no use adding these non-values to the HPOA (because they would yield 0/0)
                 }
-                let cterm = counted_term_map.entry(term_data.term_id().to_string()).or_insert(CountedHpoTerm::new(term_data.term_id(), term_data.label(), &pmid));
+                let cterm = counted_term_map.entry(term_data.term_id().to_string()).or_insert(CountedHpoTerm::new(term_data.term_id(), term_data.label(), pmid));
                 cterm.increment_value(&term_data.entry);
             }
             // we are now done with the counted terms for the current PMID

src/hpoa/hpoa_onset_calculator.rs

@@ -28,7 +28,7 @@ impl HpoaOnsetCalculator {
                     return Err(format!("Invalid age string '{}' for '{}'", onset, row.individual_data.individual_id));
                 }
                 let onset_term = age::get_onset_term(&onset)?;
-                let onset_list = pmid_to_onset_string_d.entry(pmid).or_insert(Vec::new());
+                let onset_list = pmid_to_onset_string_d.entry(pmid).or_default();
                 onset_list.push(onset_term);
             }
         }