#!/usr/bin/python3
'''Output the necessary for updating a segment index file with lastmod'''
import sys, re

import unpackz

PAT = re.compile(b'\r\nLast-Modified: ([^\r]*)',re.MULTILINE)

def whereandwhat(count,offset,data,outfile):
  '''Callback from unpackz to extract what we need'''
  #if offset == 345053206:
  #  breakpoint()
  if data.startswith(b'WARC/1.0\r\nWARC-Type: response\r\n') and \
         b'Last-Modified: ' in data:  # included for speed (worth factor of 3)
    if (http_start := data.find(b'\r\nHTTP/')) == -1:
      print("missing HTTP at %s %s"%(count,offset),
            file=sys.stderr)
      return
    if (http_end := data.find(b'\r\n\r\n',http_start)) == -1:
      print("missing end of HTTP at %s %s"%(count,offset),
            file=sys.stderr)
      return
    if (m:=PAT.search(data,http_start,http_end)):
      print(count,offset,m[1].decode('UTF-8'),sep='\t')
      
unpackz.unpackz(sys.argv[1],whereandwhat)