randomize line batches for project 2 in 723

randomize_read.py

import sys
import random

# Given file name, make an iterator returning random line batches, each of which is also randomized
def iterRandomLines(filename):
    batches = readBatches(filename)
    random.shuffle(batches)
    for lines in batches:
        random.shuffle(lines) #FIXME: we don't want to randomize lines within each batch
        for line in lines:
            yield line
        yield ""

# Given file name, return (list of (listof lines)) grouped by consecutive non-empty lines
def readBatches(filename):
    h = open(filename, 'r')
    batches = []
    batch = []
    for l in h:
        l = l.strip()
        if l == "":
            batches.append(batch)
            batch = []
        else:
            batch.append(l)
    h.close()
    return batches