bycoffe · September 15, 2009 13:08 · Sep 8, 2010 · Sep 1, 2010 · Sep 15, 2009 · Sep 15, 2009
diff --git a/csvcut b/csvcut
@@ -50,6 +50,7 @@ delimiter = ','
 output_delimiter = ' '
 cols = [0, ]
 show_headers = False
+quotechar = None
 
 if opts:
     opts = dict(opts)
@@ -64,8 +65,6 @@ if opts:
         output_delimiter = opts['-o']
     if '-q' in opts:
         quotechar = opts['-q']
-    else:
-        quotechar = None
 
 for row in csv.reader(i, delimiter=delimiter, quotechar=quotechar):
     if show_headers:

diff --git a/csvcut b/csvcut
@@ -16,6 +16,10 @@ Usage:
     csvcut -f 0,2 -d "|" foobar.csv
     (prints the first and third columns of the pipe-delimited foobar.csv)
 
+    csvcut -f 0,2 -t foobar.csv
+    (prints the first and third columns of the tab-delimited foobar.csv
+     if present, the -d option will be ignored.)
+
     csvcut -h foobar.csv
     (prints the values of the first line of foobar.csv, preceded by the field index which would 
      be used to display that column.  If present, the -f option will be ignored.)
@@ -31,9 +35,12 @@ Usage:
     csvcut -f : -o "|" foobar.csv
     (prints all the columns of the comma-delimited foobar.csv; output will be
     pipe-delimited.)
+
+    csvcut -f 0,1 -d "," -q "|" foobar.csv
+    (prints the first two columns of the comma-delimited, pipe-quoted foorbar.csv.)
 """
 import sys, csv, getopt
-opts, args = getopt.getopt(sys.argv[1:], "f:d:o:h", [])
+opts, args = getopt.getopt(sys.argv[1:], "f:d:o:q:ht", [])
 if args:
     i = open(args[0])
 else:
@@ -49,17 +56,23 @@ if opts:
     show_headers = '-h' in opts
     if '-f' in opts:
         cols = opts['-f'].split(",")
-    if '-d' in opts:
+    if '-t' in opts:
+        delimiter = "\t"    
+    elif '-d' in opts:
         delimiter = opts['-d']
     if '-o' in opts:
         output_delimiter = opts['-o']
+    if '-q' in opts:
+        quotechar = opts['-q']
+    else:
+        quotechar = None
 
-for row in csv.reader(i, delimiter=delimiter):
+for row in csv.reader(i, delimiter=delimiter, quotechar=quotechar):
     if show_headers:
         for i,c in enumerate(row):
             print "%3i: %s" % (i,c)
         break
     writer = csv.writer(sys.stdout, delimiter=output_delimiter)
     if cols == [':']:
         cols = range(len(row))
-    writer.writerow([row[int(c)] for c in cols])
+    writer.writerow([row[int(c)] for c in cols])
diff --git a/csvcut b/csvcut
@@ -27,6 +27,10 @@ Usage:
     csvcut -f 0,1,2 -o "|" foobar.csv
     (prints the first three columns of the comma-delimited foobar.csv; output
     will be pipe-delimited.)
+
+    csvcut -f : -o "|" foobar.csv
+    (prints all the columns of the comma-delimited foobar.csv; output will be
+    pipe-delimited.)
 """
 import sys, csv, getopt
 opts, args = getopt.getopt(sys.argv[1:], "f:d:o:h", [])
@@ -56,4 +60,6 @@ for row in csv.reader(i, delimiter=delimiter):
             print "%3i: %s" % (i,c)
         break
     writer = csv.writer(sys.stdout, delimiter=output_delimiter)
+    if cols == [':']:
+        cols = range(len(row))
     writer.writerow([row[int(c)] for c in cols])
diff --git a/csvcut b/csvcut
@@ -34,9 +34,12 @@ if args:
     i = open(args[0])
 else:
     i = sys.stdin
+
 delimiter = ','
 output_delimiter = ' '
 cols = [0, ]
+show_headers = False
+
 if opts:
     opts = dict(opts)
     show_headers = '-h' in opts
@@ -46,6 +49,7 @@ if opts:
         delimiter = opts['-d']
     if '-o' in opts:
         output_delimiter = opts['-o']
+
 for row in csv.reader(i, delimiter=delimiter):
     if show_headers:
         for i,c in enumerate(row):

diff --git a/csvcut b/csvcut
@@ -4,8 +4,6 @@ Like cut, but for CSVs. To be used from a shell command line.
 
 Note that fields are zero-based, as opposed to 'cut' where they are 1-based.
 
-Leveraged from/motivated by an example from @bycoffe
-
 Should use something better than getopt, but this works...
 
 Usage: 
@@ -21,14 +19,23 @@ Usage:
     csvcut -h foobar.csv
     (prints the values of the first line of foobar.csv, preceded by the field index which would 
      be used to display that column.  If present, the -f option will be ignored.)
+
+    csvcut -f 0,1,2 -d "|" -o , foobar.csv
+    (prints the first three columns of the pipe-delimited foobar.csv; output
+    will be comma-delimited.)
+
+    csvcut -f 0,1,2 -o "|" foobar.csv
+    (prints the first three columns of the comma-delimited foobar.csv; output
+    will be pipe-delimited.)
 """
 import sys, csv, getopt
-opts, args = getopt.getopt(sys.argv[1:], "f:d:h", [])
+opts, args = getopt.getopt(sys.argv[1:], "f:d:o:h", [])
 if args:
     i = open(args[0])
 else:
     i = sys.stdin
 delimiter = ','
+output_delimiter = ' '
 cols = [0, ]
 if opts:
     opts = dict(opts)
@@ -37,12 +44,12 @@ if opts:
         cols = opts['-f'].split(",")
     if '-d' in opts:
         delimiter = opts['-d']
+    if '-o' in opts:
+        output_delimiter = opts['-o']
 for row in csv.reader(i, delimiter=delimiter):
     if show_headers:
         for i,c in enumerate(row):
             print "%3i: %s" % (i,c)
-        break    
-    for c in cols:
-        print row[int(c)],
-    print
-
+        break
+    writer = csv.writer(sys.stdout, delimiter=output_delimiter)
+    writer.writerow([row[int(c)] for c in cols])
diff --git a/csvcut b/csvcut
@@ -32,7 +32,7 @@ delimiter = ','
 cols = [0, ]
 if opts:
     opts = dict(opts)
-    show_headers = bool('-h' in opts or '--header' in opts)
+    show_headers = '-h' in opts
     if '-f' in opts:
         cols = opts['-f'].split(",")
     if '-d' in opts:

diff --git a/csvcut b/csvcut
@@ -6,6 +6,8 @@ Note that fields are zero-based, as opposed to 'cut' where they are 1-based.
 
 Leveraged from/motivated by an example from @bycoffe
 
+Should use something better than getopt, but this works...
+
 Usage: 
     csvcut foobar.csv
     (prints the first column of each row of foobar.csv)
@@ -15,9 +17,13 @@ Usage:
 
     csvcut -f 0,2 -d "|" foobar.csv
     (prints the first and third columns of the pipe-delimited foobar.csv)
+
+    csvcut -h foobar.csv
+    (prints the values of the first line of foobar.csv, preceded by the field index which would 
+     be used to display that column.  If present, the -f option will be ignored.)
 """
 import sys, csv, getopt
-opts, args = getopt.getopt(sys.argv[1:], "f:d:", ["fields=", "delimiter="])
+opts, args = getopt.getopt(sys.argv[1:], "f:d:h", [])
 if args:
     i = open(args[0])
 else:
@@ -26,11 +32,17 @@ delimiter = ','
 cols = [0, ]
 if opts:
     opts = dict(opts)
+    show_headers = bool('-h' in opts or '--header' in opts)
     if '-f' in opts:
         cols = opts['-f'].split(",")
     if '-d' in opts:
         delimiter = opts['-d']
 for row in csv.reader(i, delimiter=delimiter):
+    if show_headers:
+        for i,c in enumerate(row):
+            print "%3i: %s" % (i,c)
+        break    
     for c in cols:
         print row[int(c)],
-    print
+    print
+
diff --git a/csvcut b/csvcut
@@ -22,8 +22,8 @@ if args:
     i = open(args[0])
 else:
     i = sys.stdin
-delimiter = ',' 
-cols = [1]
+delimiter = ','
+cols = [0, ]
 if opts:
     opts = dict(opts)
     if '-f' in opts:

diff --git a/csvcut b/csvcut
@@ -1,9 +1,6 @@
 #!/usr/bin/env python
 """
 Like cut, but for CSVs. To be used from a shell command line.
- 
-Change row[1] to the row index to be printed. row[1] will print the second
-item in the row.
 
 Note that fields are zero-based, as opposed to 'cut' where they are 1-based.
 
@@ -15,19 +12,25 @@ Usage:
     
     head -10 foobar.csv | csvcut -f 0,2
     (prints the first and third columns of the first ten lines of foobar.csv)
+
+    csvcut -f 0,2 -d "|" foobar.csv
+    (prints the first and third columns of the pipe-delimited foobar.csv)
 """
 import sys, csv, getopt
-opts, args = getopt.getopt(sys.argv[1:], "f:", ["fields="])
+opts, args = getopt.getopt(sys.argv[1:], "f:d:", ["fields=", "delimiter="])
 if args:
     i = open(args[0])
 else:
     i = sys.stdin
+delimiter = ',' 
+cols = [1]
 if opts:
-    cols = opts[0][1].split(",")    
-else:
-    cols = [0]    
-for row in csv.reader(i):
+    opts = dict(opts)
+    if '-f' in opts:
+        cols = opts['-f'].split(",")
+    if '-d' in opts:
+        delimiter = opts['-d']
+for row in csv.reader(i, delimiter=delimiter):
     for c in cols:
         print row[int(c)],
-    print
-
+    print
diff --git a/csvcut b/csvcut
@@ -5,7 +5,16 @@ Like cut, but for CSVs. To be used from a shell command line.
 Change row[1] to the row index to be printed. row[1] will print the second
 item in the row.
 
-Leveraged from an example from @bycoffe
+Note that fields are zero-based, as opposed to 'cut' where they are 1-based.
+
+Leveraged from/motivated by an example from @bycoffe
+
+Usage: 
+    csvcut foobar.csv
+    (prints the first column of each row of foobar.csv)
+    
+    head -10 foobar.csv | csvcut -f 0,2
+    (prints the first and third columns of the first ten lines of foobar.csv)
 """
 import sys, csv, getopt
 opts, args = getopt.getopt(sys.argv[1:], "f:", ["fields="])
@@ -16,7 +25,7 @@ else:
 if opts:
     cols = opts[0][1].split(",")    
 else:
-    cols = [1]    
+    cols = [0]    
 for row in csv.reader(i):
     for c in cols:
         print row[int(c)],

diff --git a/csvcut b/csvcut
@@ -0,0 +1,24 @@
+#!/usr/bin/env python
+"""
+Like cut, but for CSVs. To be used from a shell command line.
+ 
+Change row[1] to the row index to be printed. row[1] will print the second
+item in the row.
+
+Leveraged from an example from @bycoffe
+"""
+import sys, csv, getopt
+opts, args = getopt.getopt(sys.argv[1:], "f:", ["fields="])
+if args:
+    i = open(args[0])
+else:
+    i = sys.stdin
+if opts:
+    cols = opts[0][1].split(",")    
+else:
+    cols = [1]    
+for row in csv.reader(i):
+    for c in cols:
+        print row[int(c)],
+    print
+
No results found