def main():
# zz = parse_all_metainfo(POSTS_PATH, save_to=METADATA_PATH)
xx = load_all_metainfo(METADATA_PATH)
mk_index()
return
lucifer.loadIndex(INDEX_PATH)
ss = "Goethe saw the sea for the first time in his life when he"
raw_res = lucifer.searchQuery(ss, 17, 1)
print(raw_res)
# res = json.loads(raw_res)
# trunc = sorted(res.items(), key= lambda x: x[1], reverse=True)[:10]
# pprint(trunc)
# print("res size =", len(res))
# print("index size = %d kB" % (os.path.getsize(INDEX_PATH) // 1024))
# return
return
lucifer.addDocument(doc2)
lucifer.addDocument(doc3)
lucifer.showIndex("c++")
lucifer.showIndex("garbage")
def proc_file(path):
f = open(path)
txt1 = f.read()
f.close()
url = get_url(txt1)
i = 0
for _id, doc in split_text(txt1):
chapter_id = url + "index.xhtml#" + _id
hh = get_header(doc)
# print(chapter_id)
# print(">> ", hh)
lucifer.addDocument(chapter_id, doc)
i += 1
return i
def proc_file(path):
f = open(path)
txt1 = f.read()
f.close()
url = get_url(txt1)
i = 0
for _id, doc in split_text(txt1):
chapter_id = url + "index.xhtml#" + _id
hh = get_header(doc)
# print(chapter_id)
# print(">> ", hh)
lucifer.addDocument(chapter_id, doc)
i += 1
return i
def main():
# zz = parse_all_metainfo(POSTS_PATH, save_to=METADATA_PATH)
xx = load_all_metainfo(METADATA_PATH)
mk_index()
return
lucifer.loadIndex(INDEX_PATH)
ss = "Goethe saw the sea for the first time in his life when he"
raw_res = lucifer.searchQuery(ss, 17, 1)
print(raw_res)
# res = json.loads(raw_res)
# trunc = sorted(res.items(), key= lambda x: x[1], reverse=True)[:10]
# pprint(trunc)
# print("res size =", len(res))
# print("index size = %d kB" % (os.path.getsize(INDEX_PATH) // 1024))
# return
return
lucifer.addDocument(doc2)
lucifer.addDocument(doc3)
lucifer.showIndex("c++")
lucifer.showIndex("garbage")