Essential start-over code for a GEDCOM import parser

[Uncle Buddy]

In the process of writing code to import GEDCOM, I've started over so many times that it has become useful to have a starter kit. Here are the basic elements I always use when I start over.

Each reincarnation of this code gets closer to being finished before design mistakes pile up to a critical mass that buries me in problems too complex to bother with. At this point I either put the project on the shelf, start over, or vow to never try again. The current state of computer genealogy can't live without GEDCOM so here is the code I use to start over with:



# gedcom_import_parser_model_blank_for_starting_over.py

import sqlite3
from datetime import datetime




import_file = "d:/treebard_gps/app/python/r_a_neal_gedcomx.ged"

class GedKanDu():
   def __init__(self, import_file):

       self.import_file = import_file

       self.head = []
       self.vendor = ""
       self.submitter = ""

       trim_last_line = self.trim_trlr()
       self.split_file(self.import_file)
       self.save_head()
       self.save_lines(trim=trim_last_line)

   def save_lines(self, trim=False):
       i = open(self.data_file, "r", encoding="utf-8-sig")
       if trim:
           values = i.readlines()[:-1]
       else:
           values = i.readlines()
       for ln in values:
           line = ln.replace("\n", "").strip()
           print(line)

   def split_file(self, import_file):
       filename = import_file.split("/")[-1].replace(".ged", "")
       stamp = datetime.now().strftime("%Y%m%d%H%M")
       self.head_file = f"d:/treebard_gps/app/python/{filename}_{stamp}_HEAD.ged"
       self.data_file = f"d:/treebard_gps/app/python/{filename}_{stamp}_DATA.ged"

       with open(import_file, mode="r", encoding="utf-8-sig") as gedcom, open(
               self.head_file, mode="w", encoding="utf-8-sig") as head:
           for idx,line in enumerate(gedcom):
               if line.startswith("0 @") is False:
                   head.write(line)
               else:
                   here = idx
                   break

       with open(import_file, mode="r", encoding="utf-8-sig") as gedcom,  open(
               self.data_file, mode="w", encoding="utf-8-sig") as values:
           for idx, line in enumerate(gedcom):
               if line.startswith("0 @") and idx >= here:
                   values.write(line)
               elif idx >= here:
                   values.write(line)  

   def save_head(self):

       def get_vendor(line):
           self.vendor = line.split()[2]

       def get_submitter(line):
           fk = line.split()[2]
           self.submitter = int(''.join(c for c in fk if c.isdigit()))

       h = open(self.head_file, "r", encoding="utf-8-sig")
       for idx, line in enumerate(h.readlines()):
           line = line.replace("\n", "")
           self.head.append(line)
       HEAD_DICT = {"SOUR": get_vendor, "SUBM": get_submitter}
       for line in self.head:
           for k,v in HEAD_DICT.items():
               if k in line:
                   v(line)
                   break

   def trim_trlr(self):
       """ Ignore `0 TRLR` at end of GEDCOM so we don't have to check every
           line for it. Do this without storing the entire file in memory.
       """
       with open(self.import_file) as f:
           for line in f:
               pass
           bottom_line = line
       if bottom_line.startswith("0 T"):
           return True
       else:
           return False

if __name__ == "__main__":
 
   GEDKANDU = GedKanDu(import_file)

[Uncle Buddy]

Starting this GEDCOM import parser writing task over is now officially my new hobby. I don't even want to finish it any more. I'm now starting over every day, and learning more than ever.