srtfinder.py

# usage: python srtfinder.py filename.rst your quote
# requires https://pypi.org/project/srt/
# can be memory optimized by discarding failed 'read' chars and resetting 'widx'

import srt
import sys
print(sys.argv[1])
with open(sys.argv[1], "r") as f: data = f.read()
p = list(srt.parse(data))

q = " ".join(sys.argv[2:]) # query is all parameters after the filename
print(q)
q = q.lower()
qs = q.split()

print()

def do():
  fidx = 0 # current fragment index
  fsidx = 0 # fragment index where match started, or current
  frag = [] # current fragment
  read = frag # list of read characters
  widx = 0 # index into read
  into_match = 0 # look ahead after widx, also index into query
  while True:
    if (widx+into_match) >= len(read):
      frag = ""
      while len(frag) == 0: # keep reading until non empty fragment
        fidx += 1
        if fidx >= len(p): return # end of file
        frag = p[fidx].content.split()
      read += frag

    if qs[into_match] == read[widx+into_match]:
      into_match += 1
      if into_match == len(qs): # found full match
        print("found full match", qs, ":", fsidx, "-", fidx)
        print(p[fsidx].start, p[fidx].end)
        return
    else:
      into_match = 0
      widx += 1
      fsidx = fidx

do()
print("term.")