# See https://github.com/RDFLib/rdflib/issues/1261
# py -3.6 import.py english-wordnet-2020.ttl turtle
# Windows 7.

# Interpreted.
# 2021-02-25 18:05:27
# 2021-02-25 18:10:09

# Then run:
# py -3.6 setup.py build_ext --inplace

# 2021-02-25 18:54:05
# 2021-02-25 18:58:08

# Speedup: 14%

import os
import sys
import datetime
import linecache
import tracemalloc

# https://stackoverflow.com/questions/552744/how-do-i-profile-memory-usage-in-python
def display_top(snapshot, key_type='lineno', limit=3):
    snapshot = snapshot.filter_traces((
        tracemalloc.Filter(False, "<frozen importlib._bootstrap>"),
        tracemalloc.Filter(False, "<unknown>"),
    ))
    top_stats = snapshot.statistics(key_type)

    print("Top %s lines" % limit)
    for index, stat in enumerate(top_stats[:limit], 1):
        frame = stat.traceback[0]
        # replace "/path/to/module/file.py" with "module/file.py"
        filename = os.sep.join(frame.filename.split(os.sep)[-2:])
        print("#%s: %s:%s: %.1f KiB"
              % (index, filename, frame.lineno, stat.size / 1024))
        line = linecache.getline(frame.filename, frame.lineno).strip()
        if line:
            print('    %s' % line)

    other = top_stats[limit:]
    if other:
        size = sum(stat.size for stat in other)
        print("%s other: %.1f KiB" % (len(other), size / 1024))
    total = sum(stat.size for stat in top_stats)
    print("Total allocated size: %.1f KiB" % (total / 1024))
    

sys.path.insert(0, "rdflib")
import rdflib
print(rdflib.__file__)
g = rdflib.Graph()
print (datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"))

# python3 import.py english-wordnet-2020.ttl turtle
# python3 -m cProfile -o results.prof import.py english-wordnet-2020.ttl turtle
# python3 -m pstats results.prof
# sort tottime
# reverse
# stats

# Expected number of triples: 2956279

input_file = "english-wordnet-2020.ttl" if len(sys.argv) < 2 else sys.argv[1]

input_format = "turtle" if len(sys.argv) < 3 else sys.argv[2]

tracemalloc.start()
g.parse(input_file, format=input_format)
snapshot = tracemalloc.take_snapshot()
display_top(snapshot)

print (datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"))
print("Len=", len(g))