def test_histogram():
lines = H.hashdb(["histogram", db1])
H.str_equals(lines[4], '{"total_hashes": 3, "total_distinct_hashes": 1}')
H.str_equals(lines[5], '{"duplicates":1, "distinct_hashes":1, "total":1}')
H.str_equals(lines[6], '{"duplicates":2, "distinct_hashes":1, "total":2}')
H.str_equals(lines[7], '')
H.int_equals(len(lines), 8)
def test_size():
lines = H.hashdb(["size", db1])
#print(*lines, sep='\n')
H.str_equals(lines[0], 'hash store size: 3')
H.str_equals(lines[1], 'source store size: 2')
H.str_equals(lines[2], '')
H.int_equals(len(lines), 3)
def test_hash_block_size():
# create new DB
shutil.rmtree(db1, True)
H.hashdb(["create", db1])
# wrong hash block size
H.write_temp_dfxml_hash(byte_run_len=1024)
changes = H.parse_changes(H.hashdb(["import", db1, "temp_dfxml_hash"]))
H.int_equals(changes['hashes_inserted'], 0)
H.int_equals(changes['hashes_not_inserted_mismatched_hash_block_size'], 1)
def test_scan_hash():
# hash present
lines = H.hashdb(["scan_hash", db1, "00"])
H.str_equals(lines[0], '["00",{"count":2}]')
H.int_equals(len(lines), 2)
# hash not present
lines = H.hashdb(["scan_hash", db1, "33"])
H.str_equals(lines[0], '["33",{"count":0}]')
H.int_equals(len(lines), 2)
def test_add():
# one hash in db1 is added to db2
shutil.rmtree(db1, True)
shutil.rmtree(db2, True)
H.hashdb(["create", db1])
H.write_temp_dfxml_hash()
H.hashdb(["import", db1, "temp_dfxml_hash"])
H.hashdb(["add", db1, db2])
sizes = H.parse_sizes(H.hashdb(["size", db2]))
H.int_equals(sizes['hash_store_size'],1)
H.int_equals(sizes['source_store_size'],1)
def test_add_multiple():
# hash from db1 and db2 result in two hashes in db3
shutil.rmtree(db1, True)
shutil.rmtree(db2, True)
shutil.rmtree(db3, True)
H.hashdb(["create", db1])
H.write_temp_dfxml_hash(repository_name="r1")
H.hashdb(["import", db1, "temp_dfxml_hash"])
H.hashdb(["create", db2])
H.write_temp_dfxml_hash(repository_name="r2")
H.hashdb(["import", db2, "temp_dfxml_hash"])
H.hashdb(["add_multiple", db1, db2, db3])
sizes = H.parse_sizes(H.hashdb(["size", db3]))
H.int_equals(sizes['hash_store_size'],2)
H.int_equals(sizes['source_store_size'],2)
def test_add_repository():
# hash with correct repository name is added
shutil.rmtree(db1, True)
shutil.rmtree(db2, True)
H.rm_tempfile(xml1)
H.hashdb(["create", db1])
H.write_temp_dfxml_hash(repository_name="r1")
H.hashdb(["import", db1, "temp_dfxml_hash"])
H.write_temp_dfxml_hash(repository_name="r2")
H.hashdb(["import", db1, "temp_dfxml_hash"])
H.hashdb(["add_repository", db1, db2, "r1"])
sizes = H.parse_sizes(H.hashdb(["size", db2]))
H.int_equals(sizes['hash_store_size'],1)
H.int_equals(sizes['source_store_size'],1)
H.hashdb(["export", db2, xml1])
H.dfxml_hash_equals(repository_name="r1")
def test_subtract():
# db1 - db2 -> db3 where source must match
shutil.rmtree(db1, True)
shutil.rmtree(db2, True)
shutil.rmtree(db3, True)
H.rm_tempfile(xml1)
H.hashdb(["create", db1])
H.hashdb(["create", db2])
H.write_temp_dfxml_hash(repository_name="r1")
H.hashdb(["import", db1, "temp_dfxml_hash"])
H.hashdb(["import", db2, "temp_dfxml_hash"])
H.write_temp_dfxml_hash(repository_name="r2")
H.hashdb(["import", db1, "temp_dfxml_hash"])
H.hashdb(["subtract", db1, db2, db3])
sizes = H.parse_sizes(H.hashdb(["size", db3]))
H.int_equals(sizes['hash_store_size'],1)
H.hashdb(["export", db3, xml1])
H.dfxml_hash_equals(repository_name="r2")
def test_duplicates():
lines = H.hashdb(["duplicates", db1, "0"])
H.str_equals(lines[4], 'No hashes were found with this count.')
H.int_equals(len(lines), 6)
lines = H.hashdb(["duplicates", db1, "1"])
H.str_equals(lines[3], '["11",{"count":1}]')
H.int_equals(len(lines), 6)
lines = H.hashdb(["duplicates", db1, "2"])
H.str_equals(lines[3], '["00",{"count":2}]')
H.int_equals(len(lines), 6)
lines = H.hashdb(["duplicates", db1, "3"])
H.str_equals(lines[4], 'No hashes were found with this count.')
H.int_equals(len(lines), 6)
def test_intersect():
# db1 with a,b and db2 with b,c intersect to db3 with just b
# using same hash and different repository name
shutil.rmtree(db1, True)
shutil.rmtree(db2, True)
shutil.rmtree(db3, True)
H.rm_tempfile(xml1)
H.hashdb(["create", db1])
H.hashdb(["create", db2])
H.write_temp_dfxml_hash(repository_name="r1")
H.hashdb(["import", db1, "temp_dfxml_hash"])
H.write_temp_dfxml_hash(repository_name="r2")
H.hashdb(["import", db1, "temp_dfxml_hash"])
H.hashdb(["import", db2, "temp_dfxml_hash"])
H.write_temp_dfxml_hash(repository_name="r3")
H.hashdb(["import", db2, "temp_dfxml_hash"])
H.hashdb(["intersect", db1, db2, db3])
sizes = H.parse_sizes(H.hashdb(["size", db3]))
H.int_equals(sizes['hash_store_size'],1)
H.int_equals(sizes['source_store_size'],1)
H.hashdb(["export", db3, xml1])
H.dfxml_hash_equals(repository_name="r2")
def test_intersect_hash():
# db1 with a,b and db2 with b,c intersect to db3 with just b
# using different hash
shutil.rmtree(db1, True)
shutil.rmtree(db2, True)
shutil.rmtree(db3, True)
H.rm_tempfile(xml1)
H.hashdb(["create", db1])
H.hashdb(["create", db2])
H.write_temp_dfxml_hash(byte_run_hashdigest="00112233445566778899aabbccddeef1")
H.hashdb(["import", db1, "temp_dfxml_hash"])
H.write_temp_dfxml_hash(byte_run_hashdigest="00112233445566778899aabbccddeef2")
H.hashdb(["import", db1, "temp_dfxml_hash"])
H.hashdb(["import", db2, "temp_dfxml_hash"])
H.write_temp_dfxml_hash(byte_run_hashdigest="00112233445566778899aabbccddeef3")
H.hashdb(["import", db2, "temp_dfxml_hash"])
H.hashdb(["intersect_hash", db1, db2, db3])
sizes = H.parse_sizes(H.hashdb(["size", db3]))
H.int_equals(sizes['hash_store_size'],1)
H.int_equals(sizes['source_store_size'],1)
H.hashdb(["export", db3, xml1])
H.dfxml_hash_equals(byte_run_hashdigest="00112233445566778899aabbccddeef2")
def test_byte_alignment():
# create new DB with byte alignment 2
shutil.rmtree(db1, True)
H.hashdb(["create", db1, "-a2"])
# valid
H.write_temp_dfxml_hash(byte_run_file_offset=6)
changes = H.parse_changes(H.hashdb(["import", db1, "temp_dfxml_hash"]))
H.int_equals(changes['hashes_inserted'], 1)
# invalid
H.write_temp_dfxml_hash(byte_run_file_offset=7)
changes = H.parse_changes(H.hashdb(["import", db1, "temp_dfxml_hash"]))
H.int_equals(changes['hashes_inserted'], 0)
H.int_equals(changes['hashes_not_inserted_invalid_byte_alignment'], 1)
# valid
H.write_temp_dfxml_hash(byte_run_file_offset=8)
changes = H.parse_changes(H.hashdb(["import", db1, "temp_dfxml_hash"]))
H.int_equals(changes['hashes_inserted'], 1)
def test_scan_expanded_hash():
# all
lines = H.hashdb(["scan_expanded_hash", db1, "11"])
H.str_equals(lines[3], '{"block_hashdigest":"11", "count":1, "source_list_id":654825492, "sources":[{"source_id":2,"file_offset":0,"label":"L","repository_name":"r2","filename":"file1","file_hashdigest":"ff112233445566778899aabbccddeeff"}]}')
H.int_equals(len(lines), 5)
# -m0
lines = H.hashdb(["scan_expanded_hash", "-m0", db1, "11"])
H.str_equals(lines[3], '{"block_hashdigest":"11", "count":1, "source_list_id":654825492}')
H.int_equals(len(lines), 5)
# -m1
lines = H.hashdb(["scan_expanded_hash", "-m1", db1, "11"])
H.str_equals(lines[3], '{"block_hashdigest":"11", "count":1, "source_list_id":654825492, "sources":[{"source_id":2,"file_offset":0,"label":"L","repository_name":"r2","filename":"file1","file_hashdigest":"ff112233445566778899aabbccddeeff"}]}')
H.int_equals(len(lines), 5)
def test_hash_table():
# source_id 0
lines = H.hashdb(["hash_table", db1, "0"])
H.str_equals(lines[0], 'The requested source ID is not in the database.')
H.int_equals(len(lines), 2)
# source_id 1
lines = H.hashdb(["hash_table", db1, "1"])
H.str_equals(lines[3], '# {"source_id":1,"repository_name":"r1","filename":"file1","file_hashdigest":"ff112233445566778899aabbccddeeff"}')
H.str_equals(lines[5], '4096 00 {"count":2}')
H.str_equals(lines[6], '8192 00 {"count":2}')
H.int_equals(len(lines), 8)
# source_id 2
lines = H.hashdb(["hash_table", db1, "2"])
H.str_equals(lines[3], '# {"source_id":2,"repository_name":"repositoryname","filename":"file1","file_hashdigest":"ff112233445566778899aabbccddeeff"}')
H.str_equals(lines[5], '12288 11 {"count":1}')
H.int_equals(len(lines), 7)
# source_id 3
lines = H.hashdb(["hash_table", db1, "3"])
H.str_equals(lines[0], 'The requested source ID is not in the database.')
H.int_equals(len(lines), 2)
def test_max_duplicates():
# create new DB with max 2
shutil.rmtree(db1, True)
H.hashdb(["create", db1, "-m2"])
# add three entries where only two are allowed
H.write_temp_dfxml_hash(byte_run_file_offset=4096*1)
changes = H.parse_changes(H.hashdb(["import", db1, "temp_dfxml_hash"]))
H.write_temp_dfxml_hash(byte_run_file_offset=4096*2)
changes = H.parse_changes(H.hashdb(["import", db1, "temp_dfxml_hash"]))
H.write_temp_dfxml_hash(byte_run_file_offset=4096*3)
changes = H.parse_changes(H.hashdb(["import", db1, "temp_dfxml_hash"]))
H.int_equals(changes['hashes_inserted'], 0)
H.int_equals(changes['hashes_not_inserted_exceeds_max_duplicates'], 1)
sizes = H.parse_sizes(H.hashdb(["size", db1]))
H.int_equals(sizes['hash_store_size'], 2)
def test_explain_identified_blocks():
# test empty file
write_empty_identified_blocks()
lines = H.hashdb(["explain_identified_blocks", db1, "temp_identified_blocks"])
H.str_equals(lines[3], '# hashes')
H.str_equals(lines[4], '# There are no hashes to report.')
H.str_equals(lines[5], '# sources')
H.str_equals(lines[6], '# There are no sources to report.')
H.int_equals(len(lines), 8)
# test all
write_full_identified_blocks()
lines = H.hashdb(["explain_identified_blocks", db1, "temp_identified_blocks"])
H.str_equals(lines[3], '# hashes')
H.str_equals(lines[4], '["00",{"count":2},[{"source_id":1,"file_offset":4096},{"source_id":1,"file_offset":8192,"label":"H"}]]')
H.str_equals(lines[5], '["11",{"count":1},[{"source_id":2,"file_offset":12288,"label":"L"}]]')
H.str_equals(lines[6], '# sources')
H.str_equals(lines[7], '{"source_id":1,"repository_name":"r1","filename":"file1","file_hashdigest":"ff112233445566778899aabbccddeeff"}')
H.str_equals(lines[8], '{"source_id":2,"repository_name":"repositoryname","filename":"file1","file_hashdigest":"ff112233445566778899aabbccddeeff"}')
H.int_equals(len(lines), 10)
# test all with -m0
write_full_identified_blocks()
lines = H.hashdb(["explain_identified_blocks", "-m0", db1, "temp_identified_blocks"])
H.str_equals(lines[3], '# hashes')
H.str_equals(lines[4], '# There are no hashes to report.')
H.str_equals(lines[5], '# sources')
H.str_equals(lines[6], '# There are no sources to report.')
H.int_equals(len(lines), 8)
# test all with -m1
write_full_identified_blocks()
lines = H.hashdb(["explain_identified_blocks", "-m1", db1, "temp_identified_blocks"])
H.str_equals(lines[3], '# hashes')
H.str_equals(lines[4], '["11",{"count":1},[{"source_id":2,"file_offset":12288,"label":"L"}]]')
H.str_equals(lines[5], '# sources')
H.str_equals(lines[6], '{"source_id":2,"repository_name":"repositoryname","filename":"file1","file_hashdigest":"ff112233445566778899aabbccddeeff"}')
H.int_equals(len(lines), 8)
# test all with -m2
write_full_identified_blocks()
lines = H.hashdb(["explain_identified_blocks", "-m2", db1, "temp_identified_blocks"])
H.str_equals(lines[3], '# hashes')
H.str_equals(lines[4], '["00",{"count":2},[{"source_id":1,"file_offset":4096},{"source_id":1,"file_offset":8192,"label":"H"}]]')
H.str_equals(lines[5], '["11",{"count":1},[{"source_id":2,"file_offset":12288,"label":"L"}]]')
H.str_equals(lines[6], '# sources')
H.str_equals(lines[7], '{"source_id":1,"repository_name":"r1","filename":"file1","file_hashdigest":"ff112233445566778899aabbccddeeff"}')
H.str_equals(lines[8], '{"source_id":2,"repository_name":"repositoryname","filename":"file1","file_hashdigest":"ff112233445566778899aabbccddeeff"}')
H.int_equals(len(lines), 10)
# test invalid hash value
write_wrong_identified_blocks()
lines = H.hashdb(["explain_identified_blocks", db1, "temp_identified_blocks"])
H.str_equals((lines[3])[:5], 'Error')
H.str_equals(lines[4], '# hashes')
H.str_equals(lines[5], '# There are no hashes to report.')
H.str_equals(lines[6], '# sources')
H.str_equals(lines[7], '# There are no sources to report.')
H.int_equals(len(lines), 9)
def test_sources():
lines = H.hashdb(["sources", db1])
H.str_equals(lines[0], '{"source_id":1,"repository_name":"r1","filename":"file1","file_hashdigest":"ff112233445566778899aabbccddeeff"}')
H.str_equals(lines[1], '{"source_id":2,"repository_name":"repositoryname","filename":"file1","file_hashdigest":"ff112233445566778899aabbccddeeff"}')
H.str_equals(lines[2], '')
H.int_equals(len(lines), 3)
def test_scan():
lines = H.hashdb(["scan", db1, xml1])
#print(*lines, sep='\n')
H.str_equals(lines[4], '["00",{"count":2}]')
H.str_equals(lines[7], '["11",{"count":1}]')
H.int_equals(len(lines), 10)
def test_hash_truncation():
# create new DB with 3 byte hash truncation, no Bloom
shutil.rmtree(db1, True)
H.hashdb(["create", db1, "-t3", "--bloom", "disabled"])
# valid entry
H.write_temp_dfxml_hash(byte_run_hashdigest='00112233')
changes = H.parse_changes(H.hashdb(["import", db1, "temp_dfxml_hash"]))
H.int_equals(changes['hashes_inserted'], 1)
# duplicate element
H.write_temp_dfxml_hash(byte_run_hashdigest='00112244')
changes = H.parse_changes(H.hashdb(["import", db1, "temp_dfxml_hash"]))
H.int_equals(changes['hashes_not_inserted_duplicate_element'], 1)
# valid entry
H.write_temp_dfxml_hash(byte_run_hashdigest='00114433')
changes = H.parse_changes(H.hashdb(["import", db1, "temp_dfxml_hash"]))
H.int_equals(changes['hashes_inserted'], 1)
# create new DB with 3 byte hash truncation, with Bloom
shutil.rmtree(db1, True)
H.hashdb(["create", db1, "-t3"])
# valid entry
H.write_temp_dfxml_hash(byte_run_hashdigest='00112233')
changes = H.parse_changes(H.hashdb(["import", db1, "temp_dfxml_hash"]))
H.int_equals(changes['hashes_inserted'], 1)
# duplicate element
H.write_temp_dfxml_hash(byte_run_hashdigest='00112244')
changes = H.parse_changes(H.hashdb(["import", db1, "temp_dfxml_hash"]))
H.int_equals(changes['hashes_not_inserted_duplicate_element'], 1)
# valid entry
H.write_temp_dfxml_hash(byte_run_hashdigest='00114433')
changes = H.parse_changes(H.hashdb(["import", db1, "temp_dfxml_hash"]))
H.int_equals(changes['hashes_inserted'], 1)
def test_expand_identified_blocks():
# test empty file
write_empty_identified_blocks()
lines = H.hashdb(["expand_identified_blocks", db1, "temp_identified_blocks"])
H.int_equals(len(lines), 4)
# test all
write_full_identified_blocks()
lines = H.hashdb(["expand_identified_blocks", db1, "temp_identified_blocks"])
H.str_equals(lines[3], '4096 00 [{"count":2},{"source_list_id":2844319735, "sources":[{"source_id":1,"file_offset":4096,"repository_name":"r1","filename":"file1","file_hashdigest":"ff112233445566778899aabbccddeeff"},{"source_id":1,"file_offset":8192,"label":"H"}]}]')
H.str_equals(lines[4], '8192 00 [{"count":2},{"source_list_id":2844319735, "sources":[{"source_id":1,"file_offset":4096},{"source_id":1,"file_offset":8192,"label":"H"}]}]')
H.str_equals(lines[5], '12288 11 [{"count":1},{"source_list_id":654825492, "sources":[{"source_id":2,"file_offset":12288,"label":"L","repository_name":"repositoryname","filename":"file1","file_hashdigest":"ff112233445566778899aabbccddeeff"}]}]')
H.int_equals(len(lines), 7)
# test all with -m0
write_full_identified_blocks()
lines = H.hashdb(["expand_identified_blocks", "-m0", db1, "temp_identified_blocks"])
H.str_equals(lines[3], '4096 00 [{"count":2},{"source_list_id":2844319735}]')
H.str_equals(lines[4], '8192 00 [{"count":2},{"source_list_id":2844319735}]')
H.str_equals(lines[5], '12288 11 [{"count":1},{"source_list_id":654825492}]')
H.int_equals(len(lines), 7)
# test all with -m1
write_full_identified_blocks()
lines = H.hashdb(["expand_identified_blocks", "-m1", db1, "temp_identified_blocks"])
H.str_equals(lines[3], '4096 00 [{"count":2},{"source_list_id":2844319735, "sources":[{"source_id":1,"file_offset":4096,"repository_name":"r1","filename":"file1","file_hashdigest":"ff112233445566778899aabbccddeeff"},{"source_id":1,"file_offset":8192,"label":"H"}]}]')
H.str_equals(lines[4], '8192 00 [{"count":2},{"source_list_id":2844319735, "sources":[{"source_id":1,"file_offset":4096},{"source_id":1,"file_offset":8192,"label":"H"}]}]')
H.str_equals(lines[5], '12288 11 [{"count":1},{"source_list_id":654825492, "sources":[{"source_id":2,"file_offset":12288,"label":"L","repository_name":"repositoryname","filename":"file1","file_hashdigest":"ff112233445566778899aabbccddeeff"}]}]');
H.int_equals(len(lines), 7)
# test all with -m2
write_full_identified_blocks()
print(*lines, sep='\n')
lines = H.hashdb(["expand_identified_blocks", "-m2", db1, "temp_identified_blocks"])
H.str_equals(lines[3], '4096 00 [{"count":2},{"source_list_id":2844319735, "sources":[{"source_id":1,"file_offset":4096,"repository_name":"r1","filename":"file1","file_hashdigest":"ff112233445566778899aabbccddeeff"},{"source_id":1,"file_offset":8192,"label":"H"}]}]')
H.str_equals(lines[4], '8192 00 [{"count":2},{"source_list_id":2844319735, "sources":[{"source_id":1,"file_offset":4096},{"source_id":1,"file_offset":8192,"label":"H"}]}]')
H.str_equals(lines[5], '12288 11 [{"count":1},{"source_list_id":654825492, "sources":[{"source_id":2,"file_offset":12288,"label":"L","repository_name":"repositoryname","filename":"file1","file_hashdigest":"ff112233445566778899aabbccddeeff"}]}]')
H.int_equals(len(lines), 7)
# test invalid hash value
write_wrong_identified_blocks()
lines = H.hashdb(["expand_identified_blocks", db1, "temp_identified_blocks"])
H.str_equals((lines[3])[:5], 'Error')
H.int_equals(len(lines), 5)
def test_basic_settings():
# remove existing DB
shutil.rmtree(db1, True)
# create new DB
H.hashdb(["create", db1, "-p1024", "-m3", "-a 128", "-t 7", "--bloom=disabled", "--bloom_kM=4:14"])
# validate settings parameters
settings = H.parse_settings(db1)
H.int_equals(settings['settings_version'], 2)
H.int_equals(settings['byte_alignment'], 128)
H.int_equals(settings['hash_truncation'], 7)
H.int_equals(settings['hash_block_size'], 1024)
H.int_equals(settings['maximum_hash_duplicates'], 3)
H.bool_equals(settings['bloom_used'], False)
H.int_equals(settings['bloom_k_hash_functions'], 4)
H.int_equals(settings['bloom_M_hash_size'], 14)
# byte alignment boundary
H.write_temp_dfxml_hash(byte_run_len=1024)
changes = H.parse_changes(H.hashdb(["import", db1, "temp_dfxml_hash"]))
H.int_equals(changes['hashes_inserted'], 1)