count_species_rank_binomen.sh from binomen

count_species_rank_binomen.sh

#!/bin/bash
OTT_DIR=$1
ROOT_TAXON=$2

echo "Extracting taxa that are descendants of ${ROOT_TAXON}"
otc-taxonomy-parser \
    $OTT_DIR \
    --format="%R | %N |" \
    -r $ROOT_TAXON \
    --cull-flags "major_rank_conflict,major_rank_conflict_inherited,environmental,viral,barren,not_otu,hidden,was_container,inconsistent,hybrid,merged" \
    > "all-${ROOT_TAXON}.txt"

echo "pulling out the species rank"
cat "all-${ROOT_TAXON}.txt"  | grep '^species [|]' | sed -E 's/species \| //' | sed -E 's/ \|.*//' > "species-${ROOT_TAXON}.txt"

echo "pulling out the two word names"
cat "species-${ROOT_TAXON}.txt" | sed -E '/[A-Z0-9a-z]+ [0-9A-Za-z].+ [0-9A-Za-z].+/d' | sed -E '/^[A-Z0-9a-z]+$/d' > "species-binomens-${ROOT_TAXON}.txt"

wc -l "species-binomens-${ROOT_TAXON}.txt"