def test_load_breakpoint_continue():
"""
movie数据集 断点续传
"""
# 进行导入错误停止错误停止
cmd_error = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--check-vertex true "
res_error = InsertData(cmd_error,
schema='schema_movie.groovy',
struct='struct_movie.json',
dir='movie').load_graph()
res_error.communicate()
# 进行断点续传
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--incremental-mode true "
res = InsertData(cmd,
schema='schema_movie.groovy',
struct='struct_movie.json',
dir='movie').load_graph()
res.communicate()
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] == 49015
def test_load_error_file_reload():
"""
movie数据集 进行错误文件导入
"""
# 进行导入错误文件的生成
cmd_error = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--check-basic_operation true "
res_error = InsertData(cmd_error,
schema='schema_movie.groovy',
struct='struct_movie.json',
dir='movie').load_graph()
res_error.communicate()
# 进行错误文件的导入
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--check-basic_operation true " \
"--failure-mode true"
res = InsertData(cmd,
schema='schema_movie.groovy',
struct='struct_movie.json',
dir='movie').load_graph()
res.communicate()
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] > 500
assert res_assert[1] > 500
def test_ttl_use_loader(self):
"""
ttl + loader导入
"""
print(_cfg.server_backend)
# 插入设置ttl的数据 顶点:艺人->ttl=5s；边:属于->ttl=5s
gremlin = "graph.schema().propertyKey('名称').asText().ifNotExist().create();" \
"graph.schema().propertyKey('类型').asText().valueSet().ifNotExist().create();" \
"graph.schema().propertyKey('发行时间').asDate().ifNotExist().create();" \
"graph.schema().propertyKey('演员').asText().ifNotExist().create();" \
"graph.schema().vertexLabel('电影').useCustomizeStringId()" \
".properties('名称','类型','发行时间').ifNotExist().create();" \
"graph.schema().vertexLabel('艺人').useCustomizeStringId().properties('演员')" \
".ttl(5000L).ifNotExist().create();" \
"graph.schema().vertexLabel('类型').useCustomizeStringId().properties('类型').ifNotExist().create();" \
"graph.schema().vertexLabel('年份').useCustomizeStringId().properties('发行时间').ifNotExist().create();" \
"graph.schema().edgeLabel('导演').link('艺人','电影').ifNotExist().create();" \
"graph.schema().edgeLabel('演出').link('艺人','电影').ifNotExist().create();" \
"graph.schema().edgeLabel('属于').link('电影','类型').properties('发行时间')" \
".ttl(5000L).ifNotExist().create();" \
"graph.schema().edgeLabel('发行于').link('电影','年份').properties('发行时间').ifNotExist().create();"
code, res_gremlin = Gremlin().gremlin_post(gremlin, auth=auth)
print(code, res_gremlin)
assert 200
assert res_gremlin['result']['data'][0]['name'] == '发行于'
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s "
res = InsertData(cmd, struct='struct_movie.json',
dir='movie').load_graph()
res.communicate()
# stdout, stderr = res.communicate()
# print(' ---> ' + str(stdout) + ' === ' + str(stderr))
# 进行查询 线程休眠时间大于ttl的设置时间
time.sleep(30)
# 断言
code, res = Gremlin().gremlin_post("g.V().count();", auth=auth)
assert code == 200
assert res['result']['data'][
0] != 16034 # rocksdb后端中的设置ttl，进行count()操作有bug
code, res = Gremlin().gremlin_post("g.E().count();", auth=auth)
assert code == 200
assert res['result']['data'][
0] == 83809 # rocksdb后端中的设置ttl，进行count()操作有bug
code, res = Gremlin().gremlin_post("g.V('吴宇森');", auth=auth)
assert code == 200
assert res['result']['data'] == []
code, res = Gremlin().gremlin_post("g.E('S铁汉柔情 > 3 >> S动作');",
auth=auth)
assert code == 200
assert res['result']['data'] == []
def test_load_set_max_lines():
"""
network数据集 插入最大条数限制
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--max-read-lines 10000000 "
res = InsertData(cmd, schema='schema_checkVertex.groovy', struct='struct_checkVertex.json', dir='network') \
.load_graph()
res.communicate()
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] == 1000
assert res_assert[1] == 15156
def test_load_set_single_concurrent():
"""
network数据集 设置单条导入并发数
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--single-insert-threads 5 "
res = InsertData(cmd, schema='schema_checkVertex.groovy', struct='struct_checkVertex.json', dir='network') \
.load_graph()
res.communicate()
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] == 1000
assert res_assert[1] == 15156
def test_load_network_retry_times():
"""
network数据集 导入时候发生特定异常进行重试次数设置
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--retry-times 10 "
res = InsertData(cmd, schema='schema_checkVertex.groovy', struct='struct_checkVertex.json', dir='network') \
.load_graph()
res.communicate()
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] == 1000
assert res_assert[1] == 15156
def test_load_hlm_batch_insert_threads():
"""
hlm数据集 设置批量导入并发数
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--batch-insert-threads 50 "
res = InsertData(cmd,
schema='schema_hlm.groovy',
struct='struct_hlm.json',
dir='hlm').load_graph()
res.communicate()
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] == 41
assert res_assert[1] == 51
def test_load_hlm_max_read_lines():
"""
hlm数据集 插入最大条数限制
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--max-read-lines 10000000 "
res = InsertData(cmd,
schema='schema_hlm.groovy',
struct='struct_hlm.json',
dir='hlm').load_graph()
res.communicate()
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] == 41
assert res_assert[1] == 51
def test_load_single_insert_threads():
"""
movie数据集 设置单条导入并发数
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--single-insert-threads 5 "
res = InsertData(cmd,
schema='schema_movie.groovy',
struct='struct_movie.json',
dir='movie').load_graph()
res.communicate()
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] == 49015
assert res_assert[1] == 117356
def test_load_dry_run():
"""
movie数据集 只解析不导入模式
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--dry-run true "
res = InsertData(cmd,
schema='schema_movie.groovy',
struct='struct_movie.json',
dir='movie').load_graph()
res.communicate()
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] == 0
assert res_assert[1] == 0
def test_load_batch_size():
"""
movie数据集 导入每个批次包含的条数
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--batch-size 500 "
res = InsertData(cmd,
schema='schema_movie.groovy',
struct='struct_movie.json',
dir='movie').load_graph()
res.communicate()
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] == 49015
assert res_assert[1] == 117356
def test_load_movie_max_parse_errors():
"""
movie数据集 最大解析错误条数
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--max-parse-errors 5000 "
res = InsertData(cmd,
schema='schema_movie.groovy',
struct='struct_movie.json',
dir='movie').load_graph()
res.communicate()
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] == 49015
assert res_assert[1] == 117356
def test_load_help_message():
"""
movie数据集 查看help信息
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--help "
res = InsertData(cmd,
schema='schema_movie.groovy',
struct='struct_movie.json',
dir='movie').load_graph()
# res.communicate()
stdout, stderr = res.communicate()
print(str(stdout) + '\n' + str(stderr))
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert str(stdout, 'utf-8').startswith("Usage: <main class> [options]")
def test_load_hlm_retry_times():
"""
hlm数据集 导入时候发生特定异常进行重试次数设置
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--retry-times 10 "
res = InsertData(cmd,
schema='schema_hlm.groovy',
struct='struct_hlm.json',
dir='hlm').load_graph()
res.communicate()
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] == 41
assert res_assert[1] == 51
def test_load_network_check_vertex():
"""
network数据集 清空图导入 & 检查顶点
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--check-basic_operation true "
res = InsertData(cmd, schema='schema_checkVertex.groovy', struct='struct_checkVertex.json', dir='network') \
.load_graph()
res.communicate()
# stdout, stderr = res.communicate()
# print(str(stdout) + '\n' + str(stderr))
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] == 1000
assert res_assert[1] == 15156
def test_load_retry_interval():
"""
movie数据集 重试时间间隔（s）
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"x " \
"--retry-times 10 " \
"--retry-interval 10 "
res = InsertData(cmd,
schema='schema_movie.groovy',
struct='struct_movie.json',
dir='movie').load_graph()
res.communicate()
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] == 49015
assert res_assert[1] == 117356
def test_load_clear_all_data():
"""
movie数据集 清空图导入
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true "
res = InsertData(part_cmd=cmd,
schema='schema_movie.groovy',
struct='struct_movie.json',
dir='movie').load_graph()
res.communicate()
# stdout, stderr = res.communicate()
# print(str(stdout) + '\n' + str(stderr))
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] == 49015
assert res_assert[1] == 117356
def test_load_check_basic_operation():
"""
hlm数据集 清空图导入 & 检查顶点
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--check-basic_operation true "
res = InsertData(cmd,
schema='schema_hlm.groovy',
struct='struct_hlm.json',
dir='hlm').load_graph()
res.communicate()
# stdout, stderr = res.communicate()
# print(str(stdout) + '\n' + str(stderr))
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] == 41
assert res_assert[1] == 51
def setup_class(self):
"""
测试类开始
"""
if _cfg.server_backend == 'cassandra':
clear_graph()
else:
Gremlin().gremlin_post('graph.truncateBackend();') # 适用gremlin语句进行truncate操作
InsertData(gremlin='gremlin_alg_03.txt').gremlin_graph()
def setup_class(self):
"""
测试类开始
"""
print('++++++++++++++++ start ')
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true "
InsertData(part_cmd=cmd,
schema='schema_checkVertex.groovy',
struct='struct_checkVertex.json',
dir='network').load_graph()
def test_load_close_print():
"""
movie数据集 关闭动态打印信息
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--print-progress false "
res = InsertData(cmd,
schema='schema_movie.groovy',
struct='struct_movie.json',
dir='movie').load_graph()
# res.communicate()
stdout, stderr = res.communicate()
print(str(stdout) + '\n' + str(stderr))
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert str(stdout, 'utf-8').split('\n')[1] == 'count metrics'
assert res_assert[0] == 49015
assert res_assert[1] == 117356
def test_load_movie_check_data_customizeId_error():
"""
movie数据集 导入前检查顶点
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--check-vertex true "
res = InsertData(cmd,
schema='schema_movie_01.groovy',
struct='struct_movie_01.json',
dir='movie').load_graph()
res.communicate()
# stdout, stderr = res.communicate()
# print(' ---> ' + str(stdout) + ' === ' + str(stderr))
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] == 49036
assert res_assert[
1] != 117356 # 加上check vertex时有bug：因为movie数据集中的不同顶点类型的ID会覆盖，导致边导入的时候会报错。
def test_load_check_vertex():
"""
movie数据集 导入前检查顶点
"""
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s -s %s " \
"--clear-all-data true " \
"--check-vertex true " \
"--batch-insert-threads 1 " \
"--single-insert-threads 1 " \
"--max-parse-errors 1 " \
"--max-insert-errors 1"
res = InsertData(cmd,
schema='schema_checkVertex.groovy',
struct='struct_checkVertex.json',
dir='check_vertex_data').load_graph()
res.communicate()
# stdout, stderr = res.communicate()
# print(' ---> ' + str(stdout) + ' === ' + str(stderr))
res_assert = InsertData().loader_assert()
print(res_assert)
assert res.returncode == 0
assert res_assert[0] == 22
assert res_assert[1] == 9
def test_ttl_use_migrate(self):
"""
顶点ttl + 数据迁移
"""
# premise = 插入设置ttl的数据 顶点:艺人->ttl=5s；边:属于->ttl=5s
gremlin = "graph.schema().propertyKey('名称').asText().ifNotExist().create();" \
"graph.schema().propertyKey('类型').asText().valueSet().ifNotExist().create();" \
"graph.schema().propertyKey('发行时间').asDate().ifNotExist().create();" \
"graph.schema().propertyKey('演员').asText().ifNotExist().create();" \
"graph.schema().vertexLabel('电影').useCustomizeStringId()" \
".properties('名称','类型','发行时间').ifNotExist().create();" \
"graph.schema().vertexLabel('艺人').useCustomizeStringId().properties('演员')" \
".ttl(5000L).ifNotExist().create();" \
"graph.schema().vertexLabel('类型').useCustomizeStringId().properties('类型').ifNotExist().create();" \
"graph.schema().vertexLabel('年份').useCustomizeStringId().properties('发行时间').ifNotExist().create();" \
"graph.schema().edgeLabel('导演').link('艺人','电影').ifNotExist().create();" \
"graph.schema().edgeLabel('演出').link('艺人','电影').ifNotExist().create();" \
"graph.schema().edgeLabel('属于').link('电影','类型').properties('发行时间')" \
".ttl(5000L).ifNotExist().create();" \
"graph.schema().edgeLabel('发行于').link('电影','年份').properties('发行时间').ifNotExist().create();"
code, res_gremlin = Gremlin().gremlin_post(gremlin, auth=auth)
print(code, res_gremlin)
assert 200
assert res_gremlin['result']['data'][0]['name'] == '发行于'
cmd = "%s/bin/hugegraph-loader.sh -h %s -p %d -g %s -f %s "
res = InsertData(cmd, struct='struct_movie.json',
dir='movie').load_graph()
res.communicate()
time.sleep(30) # ttl 生效后进行下边操作
code, res = Gremlin().gremlin_post("g.V('吴宇森');", auth=auth)
assert code == 200
assert res['result']['data'] == []
code, res = Gremlin().gremlin_post("g.E('S铁汉柔情 > 3 >> S动作');",
auth=auth)
assert code == 200
assert res['result']['data'] == []
#### 数据迁移
target_clear_graph()
cmd = "./bin/hugegraph --url %s --graph %s %s %s migrate " \
"--target-url %s " \
"--target-graph %s " \
"%s " \
"%s " \
"--graph-mode RESTORING "
res = run_shell(cmd)
stdout, stderr = res.communicate()
print(' ---> ' + str(stdout) + ' === ' + str(stderr))
code, res = Gremlin().gremlin_post("g.V('吴宇森');",
auth=target_auth,
host=_cfg.tools_target_host,
port=_cfg.tools_target_port,
protocol=taret_protocol)
print(code, res)
assert code == 200
assert res['result']['data'] == []
code, res = Gremlin().gremlin_post("g.E('S铁汉柔情 > 3 >> S动作');",
auth=target_auth,
host=_cfg.tools_target_host,
port=_cfg.tools_target_port,
protocol=taret_protocol)
print(code, res)
assert code == 200
assert res['result']['data'] == []