#!/usr/bin/env python

import sys

from the_semantic_db_code import *
from the_semantic_db_functions import *
from the_semantic_db_processor import *

C = context_list("fragment documents")


frag_sequences = ["<","|",">"]

s = "some <br>text|you know<"

# ahh.. the Bortic method might be the way to go:
# split[">"]:split["|"]:split["<"]:list
# 
def split_list(fragment,list):
  result = []
  for s in list:
    result += s.split(fragment)
  return result

result = split_list("|",split_list(">",split_list("<",[s])))
print("result:",result)

# OK. Now, lets do the full thing then. The Bortic method is ugly in python, unfortunately.


def first_fragment_string(s,fragments):
  r = [s]
  for frag in fragments:
    r = split_list(frag,r)
  return r

result = first_fragment_string(s,frag_sequences)
print("result:",result)


def fragment_string(s,fragments):
  r = [s]
  for frag in fragments:
    list = r
    r = []
    for s in list:
      r += s.split(frag)
  return r

result = fragment_string(s,frag_sequences)
print("result:",result)


fragments = ["AGCTAA","ACGACG","TATATA"]
s = "AAGCTAGCTAAGGTACGACGAAGCT"
result = fragment_string(s,fragments)
print("s     :",s)
print("result:",result) 

#sys.exit(0)
#############################################
print()
print()


file_table = {
  "eztv-1"        : "web-pages/eztv-1.html",
  "eztv-2"        : "web-pages/eztv-2.html",
  "diary-1"       : "web-pages/k5-diary-1.html",
  "diary-2"       : "web-pages/k5-diary-2.html",
  "wc-comments-1" : "web-pages/wc-comments-1.html",
}

fragments = ["<","|",">"]

def load_fragments(filename,fragments):
  result = superposition()
  with open(filename,'r') as f:
    text = f.read()
    for sequence in fragment_string(text,fragments):
      sequence = sequence.strip()
#      result += ket(str(len(sequence)))
      if len(sequence) > 0:
#        result += ket(str(len(sequence)))
        result += ket(sequence)
  return result

file = "web-pages/wc-comments-1.html"
file = "web-pages/k5-diary-1.html"
result = load_fragments(file,fragments).drop_below(0).coeff_sort().long_display()
print("result:")
print(result)
print()


sys.exit(0)
file1 = "web-pages/k5-diary-1.html"
file2 = "web-pages/k5-diary-2.html"

file1 = "web-pages/eztv-1.html"
file2 = "web-pages/eztv-2.html"
r1 = load_fragments(file1,fragments)
r2 = load_fragments(file2,fragments)
result = silent_simm(r1,r2)
print("result:",result * 100)