def get_sync_dict_list(self, insert_or_updata) -> list:
"""
insert_or_updata 指明配置的是更新还是插入，-1时为插入，0为更新
本方法的写法为强规则，调用add_value_to_sync_dict_list配置
第一个参数为list，第二个参数为字段名，第三个参数为字段值，第四个参数为特殊配置
"""
sync_dict_list = self.get_sync_predefined_dict_list(insert_or_updata)
object_table_data = self._dataset
# 时间信息
dso_time = object_table_data.value_by_name(0, 'dso_time', '')
dso_time_json = CJson()
dso_time_json.load_obj(dso_time)
self.add_value_to_sync_dict_list(
sync_dict_list, 'begdate',
dso_time_json.xpath_one('start_time', ''))
self.add_value_to_sync_dict_list(
sync_dict_list, 'enddate', dso_time_json.xpath_one('end_time', ''))
self.add_value_to_sync_dict_list(
sync_dict_list, 'imagedate',
CUtils.to_day_format(dso_time_json.xpath_one('time', ''),
dso_time_json.xpath_one('time', '')))
self.add_value_to_sync_dict_list(
sync_dict_list, 'producetime',
CUtils.to_day_format(dso_time_json.xpath_one('time', ''),
dso_time_json.xpath_one('time', '')))
self.add_value_to_sync_dict_list(
sync_dict_list, 'imagedatetag',
self.transform_time_to_imagedatetag(
CUtils.to_day_format(dso_time_json.xpath_one('time', ''),
dso_time_json.xpath_one('time', ''))))
if insert_or_updata:
self.add_value_to_sync_dict_list(sync_dict_list, 'isdel', '1')
return sync_dict_list
def get_sync_predefined_dict_list(self, insert_or_updata) -> list:
"""
insert_or_updata 指明配置的是更新还是插入，-1时为插入，0为更新
本方法的写法为强规则，调用add_value_to_sync_dict_list配置
第一个参数为list，第二个参数为字段名，第三个参数为字段值，第四个参数为特殊配置
本方法处理公共部分
datacount:数据量 secrecylevel:密级 regioncode:行政区码 regionname:行政区 resolution:分辨率
colormodel:色彩模式 piexldepth:像素位数 scale:比例尺分母 mainrssource:主要星源 交插件去处理
"""
sync_dict_list = list()
object_table_id = self._obj_id # 获取oid
object_table_data = self._dataset
self.add_value_to_sync_dict_list(sync_dict_list, 'aprid',
object_table_id)
self.add_value_to_sync_dict_list(
sync_dict_list, 'productname',
object_table_data.value_by_name(0, 'dsoobjectname', ''))
self.add_value_to_sync_dict_list(sync_dict_list, 'producttype',
self._obj_type_code)
self.add_value_to_sync_dict_list(
sync_dict_list, 'dsodatatype',
object_table_data.value_by_name(0, 'dsodatatype', ''))
dso_time = object_table_data.value_by_name(0, 'dso_time', '')
dso_time_json = CJson()
dso_time_json.load_obj(dso_time)
self.add_value_to_sync_dict_list(
sync_dict_list, 'begdate',
dso_time_json.xpath_one('start_time', ''))
self.add_value_to_sync_dict_list(
sync_dict_list, 'enddate', dso_time_json.xpath_one('end_time', ''))
self.add_value_to_sync_dict_list(
sync_dict_list, 'imagedate',
CUtils.to_day_format(dso_time_json.xpath_one('time', ''),
dso_time_json.xpath_one('time', '')))
# datacount:数据数量
# secrecylevel:密级
# regioncode:行政区码
# regionname:行政区 上面四个字段交插件处理
self.add_value_to_sync_dict_list( # 配置子查询，调用函数
sync_dict_list, 'centerx', '''
(select
st_x(st_centroid(
(select dso_geo_wgs84 from dm2_storage_object where dsoid='{0}')
))::decimal(8, 2))
'''.format(object_table_id), self.DataValueType_SQL)
self.add_value_to_sync_dict_list(
sync_dict_list, 'centery', '''
(select
st_y(st_centroid(
(select dso_geo_wgs84 from dm2_storage_object where dsoid='{0}')
))::decimal(8, 2))
'''.format(object_table_id), self.DataValueType_SQL)
self.add_value_to_sync_dict_list(
sync_dict_list, 'geomwkt', '''
st_astext(
(select dso_geo_wgs84 from dm2_storage_object where dsoid='{0}')
)
'''.format(object_table_id), self.DataValueType_SQL)
self.add_value_to_sync_dict_list(
sync_dict_list, 'geomobj', '''
(select dso_geo_wgs84 from dm2_storage_object where dsoid='{0}')
'''.format(object_table_id), self.DataValueType_SQL)
self.add_value_to_sync_dict_list(
sync_dict_list, 'browserimg',
object_table_data.value_by_name(0, 'dso_browser', ''))
self.add_value_to_sync_dict_list(
sync_dict_list, 'thumbimg',
object_table_data.value_by_name(0, 'dso_thumb', ''))
self.add_value_to_sync_dict_list(
sync_dict_list, 'producetime',
CUtils.to_day_format(dso_time_json.xpath_one('time', ''),
dso_time_json.xpath_one('time', '')))
# resolution:分辨率，交插件处理
self.add_value_to_sync_dict_list(
sync_dict_list, 'imgsize', '''
(select round((sum(dodfilesize)/1048576),2) from dm2_storage_obj_detail where dodobjectid='{0}')
'''.format(object_table_id), self.DataValueType_SQL)
# colormodel:交插件处理
# piexldepth:交插件处理
if insert_or_updata:
self.add_value_to_sync_dict_list(sync_dict_list, 'isdel', '0')
now_time = CUtils.any_2_str(
datetime.datetime.now().strftime('%F %T'))
self.add_value_to_sync_dict_list(sync_dict_list, 'addtime',
now_time)
self.add_value_to_sync_dict_list(
sync_dict_list, 'extent',
"(select dso_geo_bb_wgs84 from dm2_storage_object where dsoid='{0}')"
.format(object_table_id), self.DataValueType_SQL)
self.add_value_to_sync_dict_list(
sync_dict_list, 'proj',
object_table_data.value_by_name(0, 'dso_prj_wkt', ''))
# remark:暂时为空
# ispublishservice:暂时为空
self.add_value_to_sync_dict_list(sync_dict_list, 'queryable', '0')
# scale:交插件处理
# mainrssource:交插件处理
self.add_value_to_sync_dict_list(
sync_dict_list, 'dsdid',
object_table_data.value_by_name(0, 'query_directory_id', ''))
self.add_value_to_sync_dict_list(
sync_dict_list, 'dsfid',
object_table_data.value_by_name(0, 'query_file_id', ''))
self.add_value_to_sync_dict_list(
sync_dict_list, 'imagedatetag',
self.transform_time_to_imagedatetag(
CUtils.to_day_format(dso_time_json.xpath_one('time', ''),
dso_time_json.xpath_one('time', ''))))
return sync_dict_list
def _do_access(self) -> str:
try:
quality_info_xml = self._quality_info # 获取质检xml
quality_summary = self._dataset.value_by_name(0, 'dso_quality_summary', '')
quality_summary_json = CJson()
quality_summary_json.load_obj(quality_summary)
access_wait_flag = self.DB_False # 定义等待标志，为True则存在检查项目为等待
access_forbid_flag = self.DB_False # 定义禁止标志，为True则存在检查项目为禁止
message = ''
# 文件与影像质检部分
file_qa = quality_summary_json.xpath_one('total', '')
image_qa = quality_summary_json.xpath_one('metadata.data', '')
if CUtils.equal_ignore_case(file_qa, self.QA_Result_Error) \
or CUtils.equal_ignore_case(image_qa, self.QA_Result_Error):
message = message + '[数据与其相关文件的质检存在error!请进行修正！]'
access_forbid_flag = self.DB_True
elif CUtils.equal_ignore_case(file_qa, self.QA_Result_Warn) \
or CUtils.equal_ignore_case(image_qa, self.QA_Result_Warn):
message = message + '[数据与其相关文件的质检存在warn!请进行检查！]'
access_wait_flag = self.DB_True
elif CUtils.equal_ignore_case(quality_summary, ''):
message = message + '[数据质检未进行，可能数据存在问题!请进行检查！]'
access_forbid_flag = self.DB_True
else:
pass
for qa_name, qa_id in self.access_check_dict().items(): # 循环写好的检查列表
# qa_id = CUtils.dict_value_by_name(access_check_dict, 'qa_id', '') # 获取id
qa_node = quality_info_xml.xpath_one("//item[@id='{0}']".format(qa_id)) # 查询xml中的节点
if qa_node is not None:
node_result = CXml.get_attr(qa_node, self.Name_Result, '', False) # 获取质检结果
if CUtils.equal_ignore_case(node_result, self.QA_Result_Pass):
pass
elif CUtils.equal_ignore_case(node_result, self.QA_Result_Warn): # 警告则等待
message = message + '[业务元数据的质检中，项目{0}不符合要求，建议修正！]'.format(qa_name)
access_wait_flag = self.DB_True
else: # 错误以及其他情况，比如''，或者为其他字段
message = message + '[业务元数据的质检中，项目{0}不符合要求，必须修改后方可入库！]'.format(qa_name)
access_forbid_flag = self.DB_True
else:
message = message + '[业务元数据的质检中，没有项目{0}，请进行修正！]'.format(qa_name)
access_forbid_flag = self.DB_True
# 数据库部分
access_wait_flag, access_forbid_flag, message = \
self.db_access_check(access_wait_flag, access_forbid_flag, message)
# 开始进行检查的结果判断
access_flag = self.DataAccess_Pass
if access_forbid_flag:
access_flag = self.DataAccess_Forbid
elif access_wait_flag:
access_flag = self.DataAccess_Wait
if CUtils.equal_ignore_case(message, ''):
message = '模块可以进行访问!'
result = CResult.merge_result(
self.Success,
'模块[{0}.{1}]对对象[{2}]的访问能力已经分析完毕!分析结果为:{3}'.format(
CUtils.dict_value_by_name(self.information(), self.Name_ID, ''),
CUtils.dict_value_by_name(self.information(), self.Name_Title, ''),
self._obj_name,
message
)
)
return CResult.merge_result_info(result, self.Name_Access, access_flag)
except Exception as error:
result = CResult.merge_result(
self.Failure,
'模块[{0}.{1}]对对象[{2}]的访问能力的分析存在异常!详细情况: {3}!'.format(
CUtils.dict_value_by_name(self.information(), self.Name_ID, ''),
CUtils.dict_value_by_name(self.information(), self.Name_Title, ''),
self._obj_name,
error.__str__()
)
)
return CResult.merge_result_info(result, self.Name_Access, self.DataAccess_Forbid)
def test_load_obj(self):
data = {'a': 1, 'b': 2, 'c': 3, 'd': 4, 'e': 5}
json_obj = CJson()
json_obj.load_obj(data)
assert json_obj.xpath_one('a', -1) == 1
def object_copy_stat(self, storage_id, object_id, object_name,
object_relation_name):
try:
ds_object_stat = CFactory().give_me_db(
self.get_mission_db_id()).one_row(
'''
select sum(dodfilesize), max(dodfilemodifytime) from dm2_storage_obj_detail where dodobjectid = :object_id
''', {'object_id': object_id})
object_size = None
object_last_modify_time = None
if not ds_object_stat.is_empty():
object_size = ds_object_stat.value_by_index(0, 0, 0)
object_last_modify_time = ds_object_stat.value_by_index(
0, 1, None)
batch_root_relation_dir = CFactory().give_me_db(
self.get_mission_db_id()).one_value(
'''
select dsddirectory
from dm2_storage_directory
where dsdStorageid = :storage_id and position(dsddirectory || '{0}' in :directory) = 1
and dsddirectory <> ''
order by dsddirectory
limit 1
'''.format(CFile.sep()), {
'storage_id': storage_id,
'directory': object_relation_name
}, object_relation_name)
# 更新当前对象的存储大小, 以及最后修改时间
CFactory().give_me_db(self.get_mission_db_id()).execute(
'''
update dm2_storage_object
set dso_volumn_now = :object_size, dso_obj_lastmodifytime = :object_last_modify_time
where dsoid = :object_id
''', {
'object_id': object_id,
'object_size': object_size,
'object_last_modify_time': object_last_modify_time
})
count_copy_same_filename_core = CFactory().give_me_db(
self.get_mission_db_id()).one_value(
'''
select count(dm2_storage_object.dsoid)
from dm2_storage_object
left join dm2_storage_directory on dm2_storage_object.dsoid = dm2_storage_directory.dsd_object_id
left join dm2_storage on dm2_storage_directory.dsdstorageid = dm2_storage.dstid
where
dm2_storage.dstid is not null
and dm2_storage.dsttype = '{0}'
and dm2_storage_object.dsoobjectname = :object_name
and dm2_storage_object.dsoid <> :object_id
and dm2_storage_object.dsodatatype = '{1}'
'''.format(self.Storage_Type_Core, self.FileType_Dir), {
'object_id': object_id,
'object_name': object_name
}, 0) + CFactory().give_me_db(
self.get_mission_db_id()).one_value(
'''
select count(dm2_storage_object.dsoid)
from dm2_storage_object
left join dm2_storage_file on dm2_storage_file.dsf_object_id = dm2_storage_object.dsoid
left join dm2_storage on dm2_storage_file.dsfstorageid = dm2_storage.dstid
where
dm2_storage.dstid is not null
and dm2_storage.dsttype = '{0}'
and dm2_storage_object.dsoobjectname = :object_name
and dm2_storage_object.dsoid <> :object_id
and dm2_storage_object.dsodatatype = '{1}'
'''.format(self.Storage_Type_Core, self.FileType_File), {
'object_id': object_id,
'object_name': object_name
}, 0)
count_copy_same_filename_and_size_core = CFactory().give_me_db(
self.get_mission_db_id()).one_value(
'''
select count(dm2_storage_object.dsoid)
from dm2_storage_object
left join dm2_storage_directory on dm2_storage_object.dsoid = dm2_storage_directory.dsd_object_id
left join dm2_storage on dm2_storage_directory.dsdstorageid = dm2_storage.dstid
where
dm2_storage.dstid is not null
and dm2_storage.dsttype = '{0}'
and dm2_storage_object.dso_volumn_now = :object_size
and dm2_storage_object.dsoobjectname = :object_name
and dm2_storage_object.dsoid <> :object_id
and dm2_storage_object.dsodatatype = '{1}'
'''.format(self.Storage_Type_Core, self.FileType_Dir), {
'object_id': object_id,
'object_name': object_name,
'object_size': object_size
}, 0) + CFactory().give_me_db(
self.get_mission_db_id()).one_value(
'''
select count(dm2_storage_object.dsoid)
from dm2_storage_object
left join dm2_storage_file on dm2_storage_file.dsf_object_id = dm2_storage_object.dsoid
left join dm2_storage on dm2_storage_file.dsfstorageid = dm2_storage.dstid
where
dm2_storage.dstid is not null
and dm2_storage.dsttype = '{0}'
and dm2_storage_object.dso_volumn_now = :object_size
and dm2_storage_object.dsoobjectname = :object_name
and dm2_storage_object.dsoid <> :object_id
and dm2_storage_object.dsodatatype = '{1}'
'''.format(self.Storage_Type_Core, self.FileType_File), {
'object_id': object_id,
'object_name': object_name,
'object_size': object_size
}, 0)
count_copy_same_filename_same_batch = CFactory().give_me_db(
self.get_mission_db_id()).one_value(
'''
select count(dm2_storage_object.dsoid)
from dm2_storage_object
left join dm2_storage_directory on dm2_storage_object.dsoid = dm2_storage_directory.dsd_object_id
left join dm2_storage on dm2_storage_directory.dsdstorageid = dm2_storage.dstid
where
dm2_storage.dstid = :storage_id
and position(:directory in dm2_storage_directory.dsddirectory) = 1
and dm2_storage_object.dsoobjectname = :object_name
and dm2_storage_object.dsoid <> :object_id
and dm2_storage_object.dsodatatype = '{0}'
'''.format(self.FileType_Dir), {
'storage_id': storage_id,
'object_id': object_id,
'object_name': object_name,
'directory': batch_root_relation_dir
}, 0) + CFactory().give_me_db(
self.get_mission_db_id()).one_value(
'''
select count(dm2_storage_object.dsoid)
from dm2_storage_object
left join dm2_storage_file on dm2_storage_file.dsf_object_id = dm2_storage_object.dsoid
left join dm2_storage on dm2_storage_file.dsfstorageid = dm2_storage.dstid
where
dm2_storage.dstid = :storage_id
and position(:directory in dm2_storage_file.dsffilerelationname) = 1
and dm2_storage_object.dsoobjectname = :object_name
and dm2_storage_object.dsoid <> :object_id
and dm2_storage_object.dsodatatype = '{0}'
'''.format(self.FileType_File), {
'storage_id': storage_id,
'object_id': object_id,
'object_name': object_name,
'directory': batch_root_relation_dir
}, 0)
count_copy_same_filename_and_size_same_batch = CFactory(
).give_me_db(self.get_mission_db_id()).one_value(
'''
select count(dm2_storage_object.dsoid)
from dm2_storage_object
left join dm2_storage_directory on dm2_storage_object.dsoid = dm2_storage_directory.dsd_object_id
left join dm2_storage on dm2_storage_directory.dsdstorageid = dm2_storage.dstid
where
dm2_storage.dstid = :storage_id
and position(:directory in dm2_storage_directory.dsddirectory) = 1
and dm2_storage_object.dso_volumn_now = :object_size
and dm2_storage_object.dsoobjectname = :object_name
and dm2_storage_object.dsoid <> :object_id
and dm2_storage_object.dsodatatype = '{0}'
'''.format(self.FileType_Dir), {
'storage_id': storage_id,
'object_id': object_id,
'object_name': object_name,
'object_size': object_size,
'directory': object_relation_name
}, 0) + CFactory().give_me_db(
self.get_mission_db_id()).one_value(
'''
select count(dm2_storage_object.dsoid)
from dm2_storage_object
left join dm2_storage_file on dm2_storage_file.dsf_object_id = dm2_storage_object.dsoid
left join dm2_storage on dm2_storage_file.dsfstorageid = dm2_storage.dstid
where
dm2_storage.dstid = :storage_id
and position(:directory in dm2_storage_file.dsffilerelationname) = 1
and dm2_storage_object.dso_volumn_now = :object_size
and dm2_storage_object.dsoobjectname = :object_name
and dm2_storage_object.dsoid <> :object_id
and dm2_storage_object.dsodatatype = '{0}'
'''.format(self.FileType_File), {
'storage_id': storage_id,
'object_id': object_id,
'object_name': object_name,
'object_size': object_size,
'directory': object_relation_name
}, 0)
json_text = None
if count_copy_same_filename_and_size_same_batch + \
count_copy_same_filename_and_size_core + \
count_copy_same_filename_same_batch + count_copy_same_filename_core > 0:
json_obj = CJson()
json_obj.load_obj({
self.Storage_Type_Core: {
self.Name_FileName:
count_copy_same_filename_core,
'{0}_{1}'.format(self.Name_FileName, self.Name_Size):
count_copy_same_filename_and_size_core
},
self.Storage_Type_InBound: {
self.Name_FileName:
count_copy_same_filename_same_batch,
'{0}_{1}'.format(self.Name_FileName, self.Name_Size):
count_copy_same_filename_and_size_same_batch
}
})
json_text = json_obj.to_json()
CFactory().give_me_db(self.get_mission_db_id()).execute(
'''
update dm2_storage_object
set dsocopystat = :copy_stat
where dsoid = :dsoid
''', {
'dsoid': object_id,
'copy_stat': json_text
})
return CResult.merge_result(self.Success, '数据容量统计和数据重复数据分析成功完成! ')
except Exception as error:
return CResult.merge_result(
self.Failure,
'数据容量统计和数据重复数据分析过程出现错误, 详细情况: {0}'.format(error.__str__()))
def access(self) -> str:
try:
# quality_info_xml = self._quality_info # 获取质检xml
quality_summary = self._dataset.value_by_name(
0, 'dso_quality_summary', '')
quality_summary_json = CJson()
quality_summary_json.load_obj(quality_summary)
access_wait_flag = self.DB_False # 定义等待标志，为True则存在检查项目为等待
access_forbid_flag = self.DB_False # 定义禁止标志，为True则存在检查项目为禁止
message = ''
# 文件与影像质检部分
file_qa = quality_summary_json.xpath_one('total', '')
image_qa = quality_summary_json.xpath_one('metadata.data', '')
business_qa = quality_summary_json.xpath_one(
'metadata.business', '')
if CUtils.equal_ignore_case(file_qa, self.QA_Result_Error) \
or CUtils.equal_ignore_case(image_qa, self.QA_Result_Error) \
or CUtils.equal_ignore_case(business_qa, self.QA_Result_Error):
message = message + '[数据与其相关文件的质检存在error!请进行修正！]'
access_forbid_flag = self.DB_True
elif CUtils.equal_ignore_case(file_qa, self.QA_Result_Warn) \
or CUtils.equal_ignore_case(image_qa, self.QA_Result_Warn) \
or CUtils.equal_ignore_case(business_qa, self.QA_Result_Warn):
message = message + '[数据与其相关文件的质检存在warn!请进行检查！]'
access_wait_flag = self.DB_True
else:
pass
# 数据库部分
access_wait_flag, access_forbid_flag, message = \
self.db_access_check(access_wait_flag, access_forbid_flag, message)
# 开始进行检查的结果判断
access_flag = self.DataAccess_Pass
if access_forbid_flag:
access_flag = self.DataAccess_Forbid
elif access_wait_flag:
access_flag = self.DataAccess_Wait
if CUtils.equal_ignore_case(message, ''):
message = '模块可以进行访问!'
result = CResult.merge_result(
self.Success,
'模块[{0}.{1}]对对象[{2}]的访问能力已经分析完毕!分析结果为:{3}'.format(
CUtils.dict_value_by_name(self.information(), self.Name_ID,
''),
CUtils.dict_value_by_name(self.information(),
self.Name_Title, ''),
self._obj_name, message))
return CResult.merge_result_info(result, self.Name_Access,
access_flag)
except Exception as error:
result = CResult.merge_result(
self.Failure,
'模块[{0}.{1}]对对象[{2}]的访问能力的分析存在异常!详细情况: {3}!'.format(
CUtils.dict_value_by_name(self.information(), self.Name_ID,
''),
CUtils.dict_value_by_name(self.information(),
self.Name_Title, ''),
self._obj_name, error.__str__()))
return CResult.merge_result_info(result, self.Name_Access,
self.DataAccess_Forbid)
def process_main_table(self):
object_table_id = self._obj_id # 获取oid
object_table_data = self._dataset
metadata_bus_dict = self.get_metadata_bus_dict()
main_table_name = CUtils.dict_value_by_name(self.information(),
'main_table_name',
'ap_product')
main_table = CTable()
main_table.load_info(self._db_id, main_table_name)
main_table.column_list.column_by_name('id').set_value(object_table_id)
productname = CUtils.dict_value_by_name(metadata_bus_dict,
'productname', None)
if CUtils.equal_ignore_case(productname, ''):
productname = object_table_data.value_by_name(
0, 'dsoobjectname', None)
main_table.column_list.column_by_name('productname').set_value(
productname)
main_table.column_list.column_by_name('producttype').set_value(
CUtils.dict_value_by_name(metadata_bus_dict, 'producttype', None))
main_table.column_list.column_by_name('regioncode').set_null()
main_table.column_list.column_by_name('productattribute').set_value(
CUtils.dict_value_by_name(metadata_bus_dict, 'productattribute',
None))
centerlatitude = CUtils.dict_value_by_name(metadata_bus_dict,
'centerlatitude', None)
centerlongitude = CUtils.dict_value_by_name(metadata_bus_dict,
'centerlongitude', None)
centerlonlat = '{0},{1}'.format(centerlongitude, centerlatitude)
main_table.column_list.column_by_name('centerlonlat').set_value(
centerlonlat)
main_table.column_list.column_by_name('geomwkt').set_sql('''
st_astext(
(select dso_geo_wgs84 from dm2_storage_object where dsoid='{0}')
)
'''.format(object_table_id))
main_table.column_list.column_by_name('geomobj').set_sql('''
(select dso_geo_wgs84 from dm2_storage_object where dsoid='{0}')
'''.format(object_table_id))
main_table.column_list.column_by_name('browserimg').set_value(
'{0}{1}'.format(
CFile.sep(),
object_table_data.value_by_name(0, 'dso_browser', None)))
main_table.column_list.column_by_name('thumbimg').set_value(
'{0}{1}'.format(
CFile.sep(),
object_table_data.value_by_name(0, 'dso_thumb', None)))
main_table.column_list.column_by_name('publishdate').set_value(
CUtils.dict_value_by_name(metadata_bus_dict, 'publishdate', None))
main_table.column_list.column_by_name('copyright').set_value(
CUtils.dict_value_by_name(metadata_bus_dict, 'copyright', None))
dso_time = object_table_data.value_by_name(0, 'dso_time', None)
dso_time_json = CJson()
dso_time_json.load_obj(dso_time)
imgdate = dso_time_json.xpath_one('time', None)
if not CUtils.equal_ignore_case(imgdate, ''):
main_table.column_list.column_by_name('imgdate').set_value(
imgdate[0:4])
else:
main_table.column_list.column_by_name('imgdate').set_null()
main_table.column_list.column_by_name('starttime').set_value(
dso_time_json.xpath_one('start_time', None))
main_table.column_list.column_by_name('endtime').set_value(
dso_time_json.xpath_one('end_time', None))
resolution = CUtils.any_2_str(
CUtils.dict_value_by_name(metadata_bus_dict, 'resolution', None))
if not CUtils.equal_ignore_case(resolution, ''):
if '/' in resolution:
resolution_list = resolution.split('/')
temp_list = list()
for resolution in resolution_list:
temp_list.append(CUtils.to_decimal(resolution, -1))
temp_list = list(set(temp_list)) # 去重
if -1 in temp_list:
temp_list.remove(-1)
if len(temp_list) > 0:
main_table.column_list.column_by_name(
'resolution').set_value(min(temp_list))
else:
main_table.column_list.column_by_name(
'resolution').set_value(0)
else:
main_table.column_list.column_by_name('resolution').set_value(
resolution)
else:
main_table.column_list.column_by_name('resolution').set_value(0)
main_table.column_list.column_by_name('filesize').set_sql('''
(select sum(dodfilesize) from dm2_storage_obj_detail where dodobjectid='{0}')
'''.format(object_table_id))
productid = CUtils.dict_value_by_name(metadata_bus_dict, 'productid',
None)
if CUtils.equal_ignore_case(productid, ''):
object_type = object_table_data.value_by_name(0, 'dsodatatype', '')
if CUtils.equal_ignore_case(object_type, self.Name_Dir):
main_table.column_list.column_by_name('productid').set_value(
object_table_data.value_by_name(0, 'dsoobjectname', None))
elif CUtils.equal_ignore_case(object_type, self.Name_File):
main_table.column_list.column_by_name('productid').set_sql('''
(SELECT dsffilename FROM dm2_storage_file WHERE dsf_object_id = '{0}')
'''.format(object_table_id))
else:
main_table.column_list.column_by_name('productid').set_null()
else:
main_table.column_list.column_by_name('productid').set_value(
productid)
main_table.column_list.column_by_name('remark').set_value(
CUtils.dict_value_by_name(metadata_bus_dict, 'remark', None))
main_table.column_list.column_by_name('extent').set_sql('''
(select dso_geo_bb_wgs84 from dm2_storage_object where dsoid='{0}')
'''.format(object_table_id))
main_table.column_list.column_by_name('proj').set_null() # 原始数据保持空
main_table.column_list.column_by_name('dataid').set_value(
object_table_id)
main_table.column_list.column_by_name('shplog').set_null()
if not main_table.if_exists():
now_time = CUtils.any_2_str(
datetime.datetime.now().strftime('%F %T'))
main_table.column_list.column_by_name('addtime').set_value(
now_time)
main_table.column_list.column_by_name('isdel').set_value(0)
main_table.column_list.column_by_name('projectnames').set_value(
'productname')
result = main_table.save_data()
return result
def process(self) -> str:
"""
在这里提取文档数据的元数据, 将元数据文件存储在self.file_content.work_root_dir下, 固定名称为self.FileName_MetaData, 注意返回的串中有元数据的格式
注意: 如果出现内存泄漏现象, 则使用新建进程提取元数据, 放置到文件中, 在本进程中解析元数据!!!
:return:
"""
default_result = super().process()
out_metadata_file_fullname = CFile.join_file(
self.file_content.work_root_dir, self.FileName_MetaData)
in_file_fullname = self.file_info.file_name_with_full_path
if not settings.application.xpath_one(
self.Path_Setting_Dependence_Tika_Enable, True):
return default_result
tika_dependence_mode = settings.application.xpath_one(
self.Path_Setting_Dependence_Tika_Mode, self.Name_Server)
if CUtils.equal_ignore_case(tika_dependence_mode, self.Name_Server):
tika_server_url = settings.application.xpath_one(
self.Path_Setting_Dependence_Tika_Server_Url, None)
tika_server_connect_timeout = settings.application.xpath_one(
self.Path_Setting_Dependence_Tika_Server_Timeout, 30)
if CUtils.equal_ignore_case(tika_server_url, ''):
return default_result
try:
parsed = TikaServer.from_file(
in_file_fullname,
tika_server_url,
requestOptions={'timeout': tika_server_connect_timeout})
meta_data_dict = parsed["metadata"]
json_obj = CJson()
json_obj.load_obj(meta_data_dict)
json_obj.to_file(out_metadata_file_fullname)
return CResult.merge_result_info(
CResult.merge_result(
self.Success,
'文档[{0}]的元数据提取成功'.format(in_file_fullname)),
self.Name_Format, self.MetaDataFormat_Json)
except Exception as error:
return CResult.merge_result(
self.Failure, '文档[{0}]的元数据提取过程出现错误, 详细信息为: [{1}]'.format(
in_file_fullname, error.__str__()))
else:
tika_application = settings.application.xpath_one(
self.Path_Setting_Dependence_Tika_Client_App, None)
if CUtils.equal_ignore_case(tika_application, ''):
return default_result
if not CFile.file_or_path_exist(tika_application):
return CResult.merge_result(
self.Failure,
'文档[{0}]的元数据无法提取, 详细原因为: [依赖中间件{1}文件不存在, 请修正后重试!]'.format(
in_file_fullname, tika_application))
try:
tika_client = TikaApplication(file_jar=tika_application)
meta_data_dict = tika_client.extract_only_metadata(
in_file_fullname)
json_obj = CJson()
json_obj.load_obj(meta_data_dict)
json_obj.to_file(out_metadata_file_fullname)
return CResult.merge_result_info(
CResult.merge_result(
self.Success,
'文档[{0}]的元数据提取成功'.format(in_file_fullname)),
self.Name_Format, self.MetaDataFormat_Json)
except Exception as error:
return CResult.merge_result(
self.Failure, '文档[{0}]的元数据提取过程出现错误, 详细信息为: [{1}]'.format(
in_file_fullname, error.__str__()))
# result = raster_mdreader.get_metadata_2_file(out_metadata_file_fullname)
# result = CProcessUtils.processing_method(raster_mdreader.get_metadata_2_file, out_metadata_file_fullname)
# 进程调用模式
# p_one = Process(target=raster_mdreader.get_metadata_2_file, args=(out_metadata_file_fullname,))
# p_one.start()
# p_one.join()
return CResult.merge_result_info(result, self.Name_Format,
self.MetaDataFormat_Json)
def get_sync_xml_dict_list(self, insert_or_updata) -> list:
"""
insert_or_updata 中 self.DB_True为insert，DB_False为updata
本方法的写法为强规则，调用add_value_to_sync_dict_list配置
第一个参数为list，第二个参数为字段名，第三个参数为字段值，第四个参数为特殊配置
"""
object_id = self._obj_id
object_name = self._obj_name
dsometadataxml_bus = self._dataset.value_by_name(
0, 'dsometadataxml_bus', '')
dso_time = self._dataset.value_by_name(0, 'dso_time', '')
dso_time_json = CJson() # 时间数据json
dso_time_json.load_obj(dso_time)
metadataxml_bus_xml = CXml() # 业务元数据xml
metadataxml_bus_xml.load_xml(dsometadataxml_bus)
sync_dict_list = self.get_sync_predefined_dict_list(insert_or_updata)
self.add_value_to_sync_dict_list(sync_dict_list, 'aprndid', object_id)
self.add_value_to_sync_dict_list(
sync_dict_list, 'aprnwid',
self._dataset.value_by_name(0, 'dsoparentobjid', ''))
self.add_value_to_sync_dict_list(
sync_dict_list, 'dataformat',
self._dataset.value_by_name(0, 'dsodatatype', ''))
self.add_value_to_sync_dict_list(
sync_dict_list, 'projinfo',
self._dataset.value_by_name(0, 'dso_prj_project', ''))
# sync_dict_list, 'createrorganize' # 为空
# sync_dict_list, 'submitorganize' # 为空
# sync_dict_list, 'copyrightorgnize' # 为空
# sync_dict_list, 'supplyorganize' # 为空
self.add_value_to_sync_dict_list(sync_dict_list, 'metafilename',
'{0}_21at.xml'.format(object_name))
# sync_dict_list, 'networksize' # 为空
# sync_dict_list, 'zonetype' # 为空
# sync_dict_list, 'centerline' # 为空
# sync_dict_list, 'zoneno' # 为空
# sync_dict_list, 'coordinateunit' # 为空
# sync_dict_list, 'demname' # 为空
# sync_dict_list, 'demstandard' # 为空
self.add_value_to_sync_dict_list(
sync_dict_list, 'dsometadatajson',
self._dataset.value_by_name(0, 'dsometadataxml_bus', ''))
# 插件处理字段
self.add_value_to_sync_dict_list(sync_dict_list, 'datacount', 1)
# sync_dict_list, 'secrecylevel' # 为空
# sync_dict['regioncode'] # 为空
# sync_dict['regionname'] # 为空
# sync_dict_list, 'resolution' # 为空
self.add_value_to_sync_dict_list(
sync_dict_list, 'imagedate',
CUtils.to_day_format(dso_time_json.xpath_one('time', ''),
dso_time_json.xpath_one('time', '')))
self.add_value_to_sync_dict_list(
sync_dict_list, 'begdate',
CUtils.to_day_format(dso_time_json.xpath_one('start_time', ''),
dso_time_json.xpath_one('start_time', '')))
self.add_value_to_sync_dict_list(
sync_dict_list, 'enddate',
CUtils.to_day_format(dso_time_json.xpath_one('end_time', ''),
dso_time_json.xpath_one('end_time', '')))
return sync_dict_list
def get_sync_mdb_dict_list(self, insert_or_updata) -> list:
"""
insert_or_updata 中 self.DB_True为insert，DB_False为updata
本方法的写法为强规则，调用add_value_to_sync_dict_list配置
第一个参数为list，第二个参数为字段名，第三个参数为字段值，第四个参数为特殊配置
"""
object_id = self._obj_id
object_name = self._obj_name
dsometadataxml_bus = self._dataset.value_by_name(
0, 'dsometadataxml_bus', '')
dso_time = self._dataset.value_by_name(0, 'dso_time', '')
dso_time_json = CJson() # 时间数据json
dso_time_json.load_obj(dso_time)
metadataxml_bus_xml = CXml() # 业务元数据xml
metadataxml_bus_xml.load_xml(dsometadataxml_bus)
sync_dict_list = self.get_sync_predefined_dict_list(insert_or_updata)
self.add_value_to_sync_dict_list(sync_dict_list, 'aprsdid', object_id)
self.add_value_to_sync_dict_list(
sync_dict_list, 'aprswid',
self._dataset.value_by_name(0, 'dsoparentobjid', ''))
# sync_dict['fname'] #为空
self.add_value_to_sync_dict_list(
sync_dict_list, 'fno',
metadataxml_bus_xml.get_element_text_by_xpath_one(
"//item[@name='th']"))
'''
object_name[0:1] 100万图幅行号为字母
object_name[1:3] 100万图幅列号为数字
object_name[3:4] 比例尺代码为字母
object_name[4:7] 图幅行号为数字
object_name[7:10] 图幅列号为数字
'''
if CUtils.text_is_alpha(object_name[0:1]):
self.add_value_to_sync_dict_list(sync_dict_list, 'hrowno',
object_name[0:1])
self.add_value_to_sync_dict_list(sync_dict_list, 'hcolno',
object_name[1:3])
self.add_value_to_sync_dict_list(sync_dict_list, 'scalecode',
object_name[3:4])
self.add_value_to_sync_dict_list(sync_dict_list, 'rowno',
object_name[4:7])
self.add_value_to_sync_dict_list(sync_dict_list, 'colno',
object_name[7:10])
# sync_dict['expandextent'] # 为空
# sync_dict['pupdatedate'] # 为空
# sync_dict['pversion'] # 为空
# sync_dict['publishdate'] # 为空
self.add_value_to_sync_dict_list(
sync_dict_list, 'dataformat',
metadataxml_bus_xml.get_element_text_by_xpath_one(
"//item[@name='sjgs']"))
# sync_dict['maindatasource'] # 为空
self.add_value_to_sync_dict_list(
sync_dict_list, 'dsometadatajson',
self._dataset.value_by_name(0, 'dsometadataxml_bus', ''))
self.add_value_to_sync_dict_list(
sync_dict_list, 'createrorganize',
metadataxml_bus_xml.get_element_text_by_xpath_one(
"//item[@name='sjscdwm']"))
self.add_value_to_sync_dict_list(
sync_dict_list, 'submitorganize',
metadataxml_bus_xml.get_element_text_by_xpath_one(
"//item[@name='sjbqdwm']"))
self.add_value_to_sync_dict_list(
sync_dict_list, 'copyrightorgnize',
metadataxml_bus_xml.get_element_text_by_xpath_one(
"//item[@name='sjcbdwm']"))
# sync_dict['supplyorganize'] # 为空
self.add_value_to_sync_dict_list(
sync_dict_list, 'colormodel',
metadataxml_bus_xml.get_element_text_by_xpath_one(
"//item[@name='yxscms']"))
self.add_value_to_sync_dict_list(
sync_dict_list, 'piexldepth',
metadataxml_bus_xml.get_element_text_by_xpath_one(
"//item[@name='xsws']"))
# sync_dict['scale'] # 为空
self.add_value_to_sync_dict_list(
sync_dict_list, 'mainrssource',
metadataxml_bus_xml.get_element_text_by_xpath_one(
"//item[@name='wxmc']"))
# 插件处理字段
self.add_value_to_sync_dict_list(sync_dict_list, 'datacount', 1)
self.add_value_to_sync_dict_list(
sync_dict_list, 'secrecylevel',
metadataxml_bus_xml.get_element_text_by_xpath_one(
"//item[@name='mj']"))
# sync_dict['regioncode'] # 为空
# sync_dict['regionname'] # 为空
self.add_value_to_sync_dict_list(
sync_dict_list, 'resolution',
metadataxml_bus_xml.get_element_text_by_xpath_one(
"//item[@name='dmfbl']"))
self.add_value_to_sync_dict_list(
sync_dict_list, 'imagedate',
CUtils.to_day_format(dso_time_json.xpath_one('time', ''),
dso_time_json.xpath_one('time', '')))
self.add_value_to_sync_dict_list(
sync_dict_list, 'begdate',
CUtils.to_day_format(dso_time_json.xpath_one('start_time', ''),
dso_time_json.xpath_one('start_time', '')))
self.add_value_to_sync_dict_list(
sync_dict_list, 'enddate',
CUtils.to_day_format(dso_time_json.xpath_one('end_time', ''),
dso_time_json.xpath_one('end_time', '')))
return sync_dict_list