1 files changed, 85 insertions, 0 deletions
diff --git a/Code/validate_parameter_for_buildCmatrix.py b/Code/validate_parameter_for_buildCmatrix.py
new file mode 100644
index 0000000..ced6062
--- /dev/null
+++ b/Code/validate_parameter_for_buildCmatrix.py
@@ -0,0 +1,85 @@
+# Usage: python validate_parameter_for_buildCmatrix.py
+# Purpose: make sure all files exist.
+# Hui 24 Jan 2018 Jinhua
+
+import os, sys
+import numpy as np
+import glob
+import time
+import subprocess
+from datetime import datetime
+
+def get_value(s, delimit):
+    lst = s.split(delimit, 1) # only split at the first delimit    
+    return lst[1].strip()
+
+def get_key_value(s):
+    lst = s.split('=')
+    k, v = lst[0], lst[1]
+    return (k.strip(), v.strip())
+
+def validate_gene_file(fname):
+    f = open(fname)
+    lines = f.readlines()
+    f.close()
+    for line in lines: # check all lines
+        line = line.strip()
+        lst = line.split('\t')
+        if len(lst) < 6:
+            print('Not enought fields: %s.  Only %d are given. Each line must have gene_id, gene_name, chr, start, end, strand, description (optional).  See prepare_gene_file.py in the documentation on how to prepare this file.' % (line, len(lst)))
+            sys.exit()
+
+def validate_parameter_for_buildcmatrix(fname):
+    # first the file must exist
+    if not os.path.exists(fname):
+        print('CANNOT FIND %s.' % (fname))
+        sys.exit()
+    f = open(fname)
+    lines = f.readlines()
+    f.close()
+    d = {}
+    location_count = 0
+    for line in lines:
+        line = line.strip()
+        if line.startswith('%%'):
+            k, v = get_key_value(line[2:])
+            d[k] = v
+            if k == 'GENE_FILE' or k == 'CHR_INFO':
+                if not os.path.exists(v):
+                    print('%s not exists.' % (v))
+                    sys.exit()
+                if k == 'GENE_FILE':
+                    validate_gene_file(v)
+            if k == 'DESTINATION':
+                if not os.path.isdir(v):
+                    print('%s not exists.' % (v))
+                    sys.exit()
+            if k == 'TARGET_RANGE':
+                if int(v) <= 0:
+                    print('Target range (%d) must be greater than 0.' % (v))
+                    sys.exit()
+        if line.startswith('LOCATION:'):
+            v = get_value(line, ':')
+            location_count += 1
+            if not os.path.exists(v):
+                print('Location %s does not exists.' % (v))
+                #sys.exit()
+
+    if not 'GENE_FILE' in d:
+        print('Must specify GENE_FILE.')
+        sys.exit()
+    if not 'DESTINATION' in d:
+        print('Must specify DESTINATION.')
+        sys.exit()
+    if not 'CHR_INFO' in d:
+        print('Must specify CHR_INFO.')
+        sys.exit()        
+    if location_count == 0:
+        print('Must contain at least one ChIP-seq.')
+        sys.exit()
+
+## main
+
+PARAMETER_FOR_BUILDCMATRIX = '../Data/parameter/parameter_for_buildCmatrix.txt'
+validate_parameter_for_buildcmatrix(PARAMETER_FOR_BUILDCMATRIX)
+