uf-select

#!/bin/sh
#
#  uf-select - Select sequences from an unfasta file
#  Copyright (C) 2016  Marco van Zwetselaar <io@zwets.it>
#
#  This program is free software: you can redistribute it and/or modify
#  it under the terms of the GNU General Public License as published by
#  the Free Software Foundation, either version 3 of the License, or
#  (at your option) any later version.
#
#  This program is distributed in the hope that it will be useful,
#  but WITHOUT ANY WARRANTY; without even the implied warranty of
#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#  GNU General Public License for more details.
#
#  You should have received a copy of the GNU General Public License
#  along with this program.  If not, see <http://www.gnu.org/licenses/>.
#
#  This utility is part of http://io.zwets.it/unfasta

# Function to exit this script with an error message on stderr
err_exit() {
    echo "$(basename "$0"): $*" >&2
    exit 1
}

# Function to show usage information and exit
usage_exit() {
    echo "
Usage: $(basename $0) [OPTIONS] [FILE ...]

  Select sequences from unfasta FILEs and write to standard output.
  If no FILE is present or when FILE is '-', read standard input.

  OPTIONS
   -n, --nth N[,..]  Select the nth sequence(s) for each file
   -i, --id SEQID    Select the sequence whose ID equals SEQID
   -g, --grep REGEX  Select sequences whose header matches REGEX
   -l, --len MIN     Select sequences whose length is at least MIN

  Options -n, -i, -g are mutually exclusive.  One of -n, -i, -g, -l
  must be specified.
" >&2
    exit ${1:-1}
}

# Parse options

unset NTH SEQID REGEX
MINLEN=0

while [ $# -ne 0 ] && [ "$(expr "$1" : '\(.\)..*')" = "-" ]; do
    case $1 in
    --nth=*)   NTH="${1#--nth=}" ;;
    -n|--nth)  shift && NTH="$1" || usage_exit ;;
    --id=*)    SEQID="${1#--id=}" ;;
    -i|--id)   shift && SEQID="$1" || usage_exit ;;
    --grep=*)  REGEX="${1#--grep=}" ;;
    -g|--grep) shift && REGEX="$1" || usage_exit ;;
    --len=*)   MINLEN=${1#--len=} ;;
    -l|--len)  shift && MINLEN=$1 || usage_exit ;;
    -h|--help) usage_exit 0 ;;
    -)         break ;;
    *)         usage_exit ;;
    esac
    shift || usage_exit
done

# Check options

[ -z "$NTH" ] || [ -z "${SEQID}${REGEX}" ] || err_exit "options --nth, --id, and --grep cannot be combined"
[ -z "$SEQID" ] || [ -z "${NTH}${REGEX}" ] || err_exit "options --nth, --id, and --grep cannot be combined"
[ -z "$REGEX" ] || [ -z "${NTH}${SEQID}" ] || err_exit "options --nth, --id, and --grep cannot be combined"
[ -z "$NTH" ] || expr "$NTH" : '\([0-9]\+\(,[0-9]\+\)*$\)' >/dev/null || err_exit "not a valid number list: $NTH"

# Do the work

FILE="${1:--}"

while [ -n "$FILE" ]; do
    if [ -n "$NTH" ]; then
        gawk -bO -v NTH=$NTH '
        BEGIN { split(NTH,lines,/,/) } 
        { for (x in lines) if (int((NR+1)/2) == lines[x]) print }
        ' "$FILE"
    elif [ -n "$SEQID" ]; then
        gawk -bO -v SEQID="$SEQID" '
            NR % 2 == 1 && $1 == ">" SEQID { print; getline; print }
        ' "$FILE"
    elif [ -n "$REGEX" ]; then
        gawk -bO "$(printf 'NR %% 2 == 1 && /%s/ { print; getline; print }\n' "$REGEX")" "$FILE"
    elif [ $MINLEN -ne 0 ]; then
        cat "$FILE"
    else
        usage_exit
    fi
    [ $# -gt 0 ] && shift && FILE="$1" || FILE=""
done | gawk -bO -v MINLEN="$MINLEN" '
    NR%2 == 1 { H=$0 }
    NR%2 == 0 && length() >= MINLEN { print H; print }'

# vim: sts=4:sw=4:et:si:ai