add util/csv_merge

biology/bio_plasmid_get_insert.pl

@@ -0,0 +1,48 @@
+#!/usr/bin/perl
+
+use strict;
+use File::Basename;
+use BioUtil::Seq;
+
+# M13
+my $prefix = "AGCGGCCGCGAATTGCCCTT";
+my $suffix = "AAGGGCAATTCGTTTAAACCT";
+
+$0 = basename $0;
+my $usage = <<USAGE;
+
+usage: $0 <forward seq> <reverse seq>
+
+USAGE
+
+die $usage unless @ARGV == 2;
+
+my $seqf = get_the_one_seq( shift @ARGV );
+my $seqr = revcom (get_the_one_seq( shift @ARGV ) );
+
+my $sf =  extract_insert( $prefix, $suffix, $seqf );
+my $sr =  extract_insert( $prefix, $suffix, $seqr );
+
+if ( $sf ne $sr ) {
+    print "forward: $sf\nreverse: $sr\n";
+    die "forward and reverse sequences are not equal!";
+}
+
+print $sf, "\n";
+
+
+
+sub extract_insert {
+    my ( $prefix, $suffix, $seq ) = @_;
+    die "prefix and suffix do not match sequence!\n"
+        unless $seq =~ /$prefix(.+)$suffix/;
+    return $1;
+}
+
+sub get_the_one_seq {
+    my ($file) = @_;
+    my $seqs = read_sequence_from_fasta_file($file);
+    die "only one sequence should be in $file. Please check it.\n"
+        unless keys %$seqs == 1;
+    return ( values %$seqs )[0];
+}

util/csv_grep

@@ -75,12 +75,12 @@ if args.patternfile:
     with open(args.patternfile, newline='') as patternfile:
         reader = csv.reader(patternfile, delimiter=args.fs, quotechar=args.qc)
         for row in reader:
-            nrow = len(row)
-            if nrow == 0:
+            ncolumn = len(row)
+            if ncolumn == 0:
                 continue
-            if nrow < args.pk:
+            if ncolumn < args.pk:
                 logging.error(
-                    "-pk ({}) is beyond number of column ({})".format(args.pk, nrow))
+                    "-pk ({}) is beyond number of column ({})".format(args.pk, ncolumn))
                 sys.exit(1)
             elif args.pk < 1:
                 args.pk = 1

util/csv_merge

@@ -0,0 +1,73 @@
+#!/usr/bin/env python3
+
+import argparse
+import csv
+import sys
+import logging
+
+args = None
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description="Merge csvfile1 to csvfile2",
+                                     epilog="https://github.com/shenwei356/bio_scripts")
+
+    parser.add_argument('csvfile1', type=str, help='cvsfile1')
+    parser.add_argument("key1", type=int, help='Column number of key in csvfile1')
+    parser.add_argument('csvfile2', type=str, help='cvsfile2')
+    parser.add_argument("key2", type=int, help='Column number of key in csvfile2')
+    parser.add_argument("-H1", help="not containing head in cvsfile1", action="store_true")
+    parser.add_argument("-H2", help="not containing head in cvsfile2", action="store_true")
+    parser.add_argument("-F", '--fs', type=str, default="\t",
+                        help='Field separator [\\t]')
+    parser.add_argument("-Q", '--qc', type=str, default='"',
+                        help='Quote char["]')
+
+    args = parser.parse_args()
+
+    return args
+
+
+def read_csv_file(file, key):
+    data, indexdict = [], {}
+    index = 0
+
+    with open(file, newline='') as fh:
+        reader = csv.reader(fh, delimiter=args.fs, quotechar=args.qc)
+        for row in reader:
+            ncolumn = len(row)
+            if ncolumn == 0:
+                continue
+            if ncolumn < key:
+                logging.error(
+                    "key ({}) is beyond number of column ({})".format(key, ncolumn))
+                print(row)
+                sys.exit(1)
+            elif key < 1:
+                args.pk = 1
+
+            data.append(row)
+            indexdict[row[key - 1].strip()] = index
+            index += 1
+
+    return data, indexdict
+
+
+if __name__ == '__main__':
+    logging.basicConfig(level=logging.DEBUG, format="[%(levelname)s] %(message)s")
+
+    args = parse_args()
+
+    data1, map1 = read_csv_file(args.csvfile1, args.key1)
+    data2, map2 = read_csv_file(args.csvfile2, args.key2)
+
+    if not args.H2:
+        print('\t'.join(data2[0]), end='')
+        data2 = data2[1:]
+        if not args.H1:
+            print('\t', end='')
+            print('\t'.join(data1[0]), end='')
+        print()
+
+    for row in data2:
+        print('\t'.join(row), '\t'.join(data1[map1[row[args.key2 - 1]]]), sep='\t')