From b46c381c3e247216a3c0bc2ac09f6dc16cd07500 Mon Sep 17 00:00:00 2001
From: einarr <einarr@pvv.ntnu.no>
Date: Thu, 5 Feb 2009 00:11:48 +0000
Subject: [PATCH] Added txt2ftsv, a script to build ftsv category datasets from
 lists of identifiers. Usages is txt2ftsv [-d dimension] [-o output.ftsv] [-n
 dsname] [FILE1 [FILE2 ...]] Input and output can be - for STDIN/STDOUT
 respectively. The script is primarily ment as a hack to easily load
 selections. Data is only half sanitized.

---
 bin/txt2ftsv | 86 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 86 insertions(+)
 create mode 100755 bin/txt2ftsv

diff --git a/bin/txt2ftsv b/bin/txt2ftsv
new file mode 100755
index 0000000..dccc696
--- /dev/null
+++ b/bin/txt2ftsv
@@ -0,0 +1,86 @@
+#!/usr/bin/env python
+
+import numpy
+import os.path
+import sys
+
+from laydi import dataset
+from getopt import getopt
+
+dimension = 'dim_doe'
+output_fn = '-'
+ds_name = None
+
+def print_help():
+    print
+    print 'options:'
+    print '    -h, --help             Show this help text.'
+    print '    -d, --dimension=DIM    Make output in dimension DIM'
+    print '    -n, --name=NAME        Set name of output dataset'
+    print '    -o, --output=FILE      Save output dataset in FILE'
+    print
+
+def parse_options():
+    global ds_name
+    global output_fn
+
+    short_opts = 'hd:n:o:'
+    long_opts = ['help', 'dimension', 'name', 'output']
+    options, params = getopt(sys.argv[1:], short_opts, long_opts)
+
+    for opt, val in options:
+        if opt in ['-h', '--help']:
+            print_help()
+            sys.exit(0)
+        elif opt in ['-d', '--dimension']:
+            global dimension
+            dimension = val
+        elif opt in ['-n', '--name']:
+            ds_name = val
+        elif opt in ['-o', '--output']:
+            output_fn = val
+    
+    if ds_name == None:
+        if output_fn != None:
+            ds_name = output_fn
+        else:
+            ds_name = 'txt2ftsv'
+
+    if len(params) == 0:
+        print_help()
+        sys.exit(1)
+
+    return params
+
+def read_file(fd):
+    lines = fd.readlines()
+    return [l.strip() for l in lines if l.strip() != '']
+    
+def build_dataset(dimension, id_lists, filenames):
+    all_ids = reduce(set.union, [set(x) for x in id_lists])
+    x = numpy.zeros((len(all_ids), len(id_lists)), 'b')
+    for i, idl in enumerate(id_lists):
+        for j, id in enumerate(idl):
+            x[j,i] = True
+    return dataset.CategoryDataset(x, [(dimension, all_ids), ('files', filenames)], name=ds_name)
+
+if __name__ == '__main__':
+    id_lists = []
+
+    filenames = parse_options()
+    for fn in filenames:
+        if os.path.exists(fn):
+            fd = open(fn)
+            id_lists.append(read_file(fd))
+            fd.close()
+        elif fn == '-':
+            id_lists.append(read_file(sys.stdin))
+
+    ds = build_dataset(dimension, id_lists, filenames)
+    print ds
+
+    if output_fn == '-':
+        dataset.write_ftsv(sys.stdout, ds)
+    else:
+        dataset.write_ftsv(output_fn, ds)
+