import json
from random import sample, randint
from uuid import uuid4def gen_random_words():with open("D:\\exp\\test_data\\dictionary.txt") as f:words = [word.strip() for word in f]f.close()# print "OK. words length:", len(words)return sample(words, 3000)return []total_words = 0
def sample_words(search_words, random_words):global total_wordssample_cnt = 1000for word in random_words:total_words += 1if len(search_words) < sample_cnt:search_words.append(word)else:if randint(1, total_words) <= sample_cnt:kick_off = randint(0, sample_cnt-1)search_words[kick_off] = worddef gen_an_event(words, search_words):event_data = {}for i in range(50):query_words = sample(words, randint(1, 10))sample_words(search_words,query_words)event_data["field-"+str(i)] = " ".join(query_words)return {"event": event_data, "sourcetype": "hec_test2"}if __name__ == "__main__":search_words = []for i in range(500):words = gen_random_words()index_head = json.dumps({"index" : { "_index" : "hec_test2", "_type" : "hec_type2" } })es_out_put = ""splunk_out_put = ""for i in range(500):if i == 0:es_out_put += index_head + "\n"else:es_out_put += "\n" + index_head + "\n"event = gen_an_event(words, search_words)splunk_out_put += json.dumps(event)es_out_put += json.dumps(event["event"])# print es_out_put# print splunk_out_putout_puts = [es_out_put, splunk_out_put]file_name = str(uuid4()) + ".json"for i,dir_name in enumerate(["ES", "Splunk"]):outfile = "D:\\test_data\\%s\\%s" % (dir_name, file_name)f = open(outfile, "w")f.write(out_puts[i])f.close()print outfileoutfile = "D:\\test_data\\search_words.txt"f = open(outfile, "w")f.write(json.dumps(search_words))f.close()