re-common 10.0.18__py3-none-any.whl → 10.0.19__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- re_common/v2/baselibrary/tools/hdfs_data_processer.py +4 -4
- {re_common-10.0.18.dist-info → re_common-10.0.19.dist-info}/METADATA +1 -1
- {re_common-10.0.18.dist-info → re_common-10.0.19.dist-info}/RECORD +6 -6
- {re_common-10.0.18.dist-info → re_common-10.0.19.dist-info}/LICENSE +0 -0
- {re_common-10.0.18.dist-info → re_common-10.0.19.dist-info}/WHEEL +0 -0
- {re_common-10.0.18.dist-info → re_common-10.0.19.dist-info}/top_level.txt +0 -0
|
@@ -109,12 +109,12 @@ class HDFSDataProcessor:
|
|
|
109
109
|
retry_count = 0
|
|
110
110
|
while retry_count < self.retry_limit:
|
|
111
111
|
try:
|
|
112
|
-
return await process_func(data)
|
|
112
|
+
return await process_func(data) # 成功处理后退出
|
|
113
113
|
except Exception as e:
|
|
114
114
|
retry_count += 1
|
|
115
115
|
print(f"处理数据时发生错误: {e}, 正在重试 {retry_count}/{self.retry_limit}, data: {data}")
|
|
116
116
|
await asyncio.sleep(2**retry_count)
|
|
117
|
-
|
|
117
|
+
raise Exception(f"处理数据失败, 达到重试上限, data: {data}")
|
|
118
118
|
|
|
119
119
|
async def process_file(self, hdfs_file_path, process_func, write_dir: str):
|
|
120
120
|
"""处理单个 gz 文件"""
|
|
@@ -132,7 +132,7 @@ class HDFSDataProcessor:
|
|
|
132
132
|
data = json.loads(line)
|
|
133
133
|
tasks.append(self.process_data(data, process_func))
|
|
134
134
|
except json.JSONDecodeError as e:
|
|
135
|
-
|
|
135
|
+
raise Exception(f"解析JSON失败: {e}, 行内容: {line.strip()}")
|
|
136
136
|
|
|
137
137
|
# await AsyncTaskPool(self.batch_size).run(tasks) # AsyncTaskPool 适用于一次提交所有任务, 限制并发数执行
|
|
138
138
|
results.extend(await asyncio.gather(*tasks))
|
|
@@ -236,7 +236,7 @@ class HDFSDataProcessor:
|
|
|
236
236
|
data = json.loads(line)
|
|
237
237
|
batch_data.append(data)
|
|
238
238
|
except json.JSONDecodeError as e:
|
|
239
|
-
|
|
239
|
+
raise Exception(f"解析JSON失败: {e}, 行内容: {line.strip()}")
|
|
240
240
|
|
|
241
241
|
# 处理读取到的批次数据
|
|
242
242
|
if batch_data:
|
|
@@ -173,7 +173,7 @@ re_common/v2/baselibrary/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5
|
|
|
173
173
|
re_common/v2/baselibrary/tools/ac_ahocorasick.py,sha256=c63y5RtKVLD37nyPCnBqfNygwRj4gTQqyIdDOrC65G0,2847
|
|
174
174
|
re_common/v2/baselibrary/tools/dict_tools.py,sha256=BTh7oJuJ619IZgxiYlim0ltrXBclDtb7WzyFGr7wVf0,1246
|
|
175
175
|
re_common/v2/baselibrary/tools/dolphinscheduler.py,sha256=1m7UGYDiuvJUCI6ik6CGM2fO8U5XteJzn55VRbwB9ts,7978
|
|
176
|
-
re_common/v2/baselibrary/tools/hdfs_data_processer.py,sha256=
|
|
176
|
+
re_common/v2/baselibrary/tools/hdfs_data_processer.py,sha256=g0DaNjXM1hIUblFQ6YBwnwEBKIXn48X8Y9Eiok4dVlQ,14824
|
|
177
177
|
re_common/v2/baselibrary/tools/list_tools.py,sha256=mZyrOGdW6tuany0lKQOD4P739xikvmeKm1VSzo37Byc,1973
|
|
178
178
|
re_common/v2/baselibrary/tools/search_hash_tools.py,sha256=2ENLtZE8opRsfkwRtTNMzITmpTsjO7wZ1ZkfkqpOH9U,1937
|
|
179
179
|
re_common/v2/baselibrary/tools/text_matcher.py,sha256=cPMoFxaA0-ce3tLRxVSs8_3pTYS1oVIHDnNy_AlPU-4,10756
|
|
@@ -219,8 +219,8 @@ re_common/vip/title/transform/TransformRegulationTitleToZt.py,sha256=LKRdIsWKues
|
|
|
219
219
|
re_common/vip/title/transform/TransformStandardTitleToZt.py,sha256=-fCKAbSBzXVyQDCE61CalvR9E_QzQMA08QOO_NePFNI,5563
|
|
220
220
|
re_common/vip/title/transform/TransformThesisTitleToZt.py,sha256=QS-uV0cQrpUFAcKucuJQ9Ue2VRQH-inmfn_X3IplfRo,5488
|
|
221
221
|
re_common/vip/title/transform/__init__.py,sha256=m83-CWyRq_VHPYHaALEQlmXrkTdrZ3e4B_kCfBYE-uc,239
|
|
222
|
-
re_common-10.0.
|
|
223
|
-
re_common-10.0.
|
|
224
|
-
re_common-10.0.
|
|
225
|
-
re_common-10.0.
|
|
226
|
-
re_common-10.0.
|
|
222
|
+
re_common-10.0.19.dist-info/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
|
|
223
|
+
re_common-10.0.19.dist-info/METADATA,sha256=HmlwedZs6uIg94rFxGDllhiPs6eRSk_NtjdcHmbZ3Sg,764
|
|
224
|
+
re_common-10.0.19.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
|
|
225
|
+
re_common-10.0.19.dist-info/top_level.txt,sha256=_H9H23zoLIalm1AIY_KYTVh_H0ZnmjxQIxsvXtLv45o,10
|
|
226
|
+
re_common-10.0.19.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
|
File without changes
|