#41: first script to shrink OWLdoc files

toardb/utils/prepare_OWLDoc.py

+#!/usr/bin/python3
+# -*- coding: utf-8 -*-
+"""
+OWLDoc preprocessing
+====================
+
+see:  https://gitlab.version.fz-juelich.de/esde/toar-data/toardb_fastapi/-/issues/41
+
+deleting all lines
+    from the first <div id='isdefinedby_(1)'> line
+    and including the last but one line </div><!-- usage (1)
+    -->  [Note: The (1) could be a different number e.g. (3)]
+There are cases where the usage line is not present
+"""
+
+__author__ = "Sabine Schroeder"
+__version__ = "0.5"
+__date__ = "2021/03/24"
+__maintainer__ = "Sabine Schroeder"
+__email__ = "s.schroeder@fz-juelich.de"
+
+import sys
+import os
+import getopt
+
+
+def usage():
+    msg = ["Usage: prepare_OWLDoc.py options",
+           "Options:   -h, --help              help",
+           "           -f, --filename  str     filename"]
+    print("\n".join([m for m in msg]))
+
+
+def get_options(argv):
+    """analyse command line options and argument"""
+
+    long_opt = ["help", "filename="]
+    try:
+        opts, args = getopt.gnu_getopt(argv, "hf:", long_opt)
+    except getopt.GetoptError as e:
+        print(str(e))
+        usage()
+        sys.exit(2)
+    filename = ''
+    for o, a in opts:
+        if o in ("-h", "--help"):
+            usage()
+            sys.exit()
+        elif o in ("-f", "--filename"):
+            filename = a
+    if filename == '':
+        usage()
+        sys.exit(2)
+    return filename
+
+
+def shrink_file(filename):
+
+    # open input file
+    rd = open (filename, "r")
+
+    # open output file
+
+    wr = open ("../individuals/"+filename, "w")
+
+    # read list of lines
+    lines = rd.readlines()
+
+    # determine lines to copy to output file
+    index_head = 0
+    try: 
+        index_head = lines.index("<div id='isdefinedby_(1)'>\n") + 1
+    except ValueError as e:
+        pass
+    if index_head  == 0:
+        print (f"no 'isdefinedby_(1)' found for file {filename} --> unchanged")
+        for line in lines:
+            wr.write(line)
+    else:
+        index_pos_list =[]
+        index_pos = 0
+        while True:
+            try:
+                # Search for item in list from indexPos to the end of list
+                index_pos = lines.index("</div><!-- usage (1) -->\n", index_pos)
+                # Add the index position in list
+                index_pos_list.append(index_pos)
+                index_pos += 1
+            except ValueError as e:
+                break
+        if len(index_pos_list) <= 1:
+            print (f"no or only one 'usage (1)' found for file {filename} --> unchanged")
+            for line in lines:
+                wr.write(line)
+        else:
+            index_tail = index_pos_list[-2]
+            for i in range(index_head+1):
+                wr.write(lines[i]) 
+            for i in range(index_tail+1,len(lines),1):
+                wr.write(lines[i]) 
+
+    # Close file 
+    rd.close()
+
+
+if __name__ == "__main__":
+
+    filename = get_options(sys.argv)
+    shrink_file(filename)
+    

toardb/utils/prepare_OWLDoc.sh

+#!/bin/bash
+
+for FILENAME in OWL*html
+do
+  echo $FILENAME
+  ./prepare_OWLDoc.py -f "$FILENAME"
+done