re-common 10.0.12__py3-none-any.whl → 10.0.13__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/utils/stringutils.py +2 -1
- {re_common-10.0.12.dist-info → re_common-10.0.13.dist-info}/METADATA +1 -1
- {re_common-10.0.12.dist-info → re_common-10.0.13.dist-info}/RECORD +6 -6
- {re_common-10.0.12.dist-info → re_common-10.0.13.dist-info}/LICENSE +0 -0
- {re_common-10.0.12.dist-info → re_common-10.0.13.dist-info}/WHEEL +0 -0
- {re_common-10.0.12.dist-info → re_common-10.0.13.dist-info}/top_level.txt +0 -0
|
@@ -6,7 +6,7 @@ import regex
|
|
|
6
6
|
import unicodedata
|
|
7
7
|
from html.parser import HTMLParser
|
|
8
8
|
|
|
9
|
-
|
|
9
|
+
|
|
10
10
|
from re_common.v2.baselibrary.utils.string_smi import JaroDamerauLevenshteinMaxSim
|
|
11
11
|
|
|
12
12
|
|
|
@@ -163,6 +163,7 @@ sim_utils = JaroDamerauLevenshteinMaxSim()
|
|
|
163
163
|
|
|
164
164
|
def group_similar_texts(texts, threshold=0.9):
|
|
165
165
|
"""根据相似度对文本进行分组"""
|
|
166
|
+
from re_common.v2.baselibrary.utils.string_clear import rel_clear
|
|
166
167
|
n = len(texts)
|
|
167
168
|
# 创建邻接表表示图
|
|
168
169
|
graph = [[] for _ in range(n)]
|
|
@@ -184,7 +184,7 @@ re_common/v2/baselibrary/utils/n_ary_expression_tree.py,sha256=-05kO6G2Rth7CEK-5
|
|
|
184
184
|
re_common/v2/baselibrary/utils/string_bool.py,sha256=EJnkSck4ofcIeJ6nLzAOVtlt6o1WBgvgVwIqJKj5Suc,2993
|
|
185
185
|
re_common/v2/baselibrary/utils/string_clear.py,sha256=pGxL9PlzQDM06sC0j6U0zYRemvsJ7-OOpfzS5ETCxAs,6258
|
|
186
186
|
re_common/v2/baselibrary/utils/string_smi.py,sha256=cU0WAWHRGnGoVQx3eCEKeM_q_olFNzRTJe7rSe586SY,741
|
|
187
|
-
re_common/v2/baselibrary/utils/stringutils.py,sha256=
|
|
187
|
+
re_common/v2/baselibrary/utils/stringutils.py,sha256=WuxhXJVU6xuGfgHiSjxrn7Go1eobpa8DMR3Icoey4vo,6039
|
|
188
188
|
re_common/vip/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
189
189
|
re_common/vip/base_step_process.py,sha256=VXXiNj0I5CpzXIMCgOPU86bzDJkSBkUS-9CpZIl_GOk,205
|
|
190
190
|
re_common/vip/baseencodeid.py,sha256=nERoe89ueFM52bG7xwJdflcZHk6T2RQQKbc5uUZc3RM,3272
|
|
@@ -211,8 +211,8 @@ re_common/vip/title/transform/TransformRegulationTitleToZt.py,sha256=LKRdIsWKues
|
|
|
211
211
|
re_common/vip/title/transform/TransformStandardTitleToZt.py,sha256=-fCKAbSBzXVyQDCE61CalvR9E_QzQMA08QOO_NePFNI,5563
|
|
212
212
|
re_common/vip/title/transform/TransformThesisTitleToZt.py,sha256=QS-uV0cQrpUFAcKucuJQ9Ue2VRQH-inmfn_X3IplfRo,5488
|
|
213
213
|
re_common/vip/title/transform/__init__.py,sha256=m83-CWyRq_VHPYHaALEQlmXrkTdrZ3e4B_kCfBYE-uc,239
|
|
214
|
-
re_common-10.0.
|
|
215
|
-
re_common-10.0.
|
|
216
|
-
re_common-10.0.
|
|
217
|
-
re_common-10.0.
|
|
218
|
-
re_common-10.0.
|
|
214
|
+
re_common-10.0.13.dist-info/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
|
|
215
|
+
re_common-10.0.13.dist-info/METADATA,sha256=QdkCM_LoID9na9D2qL4Zamec2QOdKtXgOxCWBSZQO8k,582
|
|
216
|
+
re_common-10.0.13.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
|
|
217
|
+
re_common-10.0.13.dist-info/top_level.txt,sha256=_H9H23zoLIalm1AIY_KYTVh_H0ZnmjxQIxsvXtLv45o,10
|
|
218
|
+
re_common-10.0.13.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
|
File without changes
|