re-common 10.0.0__tar.gz → 10.0.1__tar.gz

{re_common-10.0.0 → re_common-10.0.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: re_common
-Version: 10.0.0
+Version: 10.0.1
 Summary: a library about all python projects
 Home-page: https://gitee.com/xujiangios/re-common
 Author: vic

{re_common-10.0.0 → re_common-10.0.1}/re_common/v2/baselibrary/utils/author_smi.py

@@ -1,3 +1,4 @@
+import copy
 import re
 import string
 
@@ -248,6 +249,16 @@ def AuthorRatio(
     if len(l1) == len(l2) and (is_same_or_initials_match(l1, l2) or set(l1) == set(l2)):
         return 1
 
+    # 在这里针对上面一条算法再增加一条算法，先对list 排序在对他进行上面的对比
+    # 如果长度相等 简写也是单词的首字母 那么两个名字一致 举例:Guo, Qiang @@ Q. Guo
+    sort_l1 = copy.deepcopy(l1)
+    sort_l2 = copy.deepcopy(l2)
+    sort_l1.sort()
+    sort_l2.sort()
+    if len(sort_l1) == len(sort_l2) and (is_same_or_initials_match(sort_l1, sort_l2) or set(sort_l1) == set(sort_l2)):
+        return 0.99
+
+
     ##############################################################
     # 以上为情况穷举情况，以下为其他情况的相似率计算
     ##############################################################
@@ -262,7 +273,7 @@ def AuthorRatio(
     len_ratio = len1 / len2 if len1 > len2 else len2 / len1
 
     # 计算归一化的 Indel 相似度。 对于比率<score_cutoff，返回0。
-    end_ratio = normal_end_ratio = Jaro.normalized_similarity(s1, s2)
+    end_ratio = normal_end_ratio = Jaro.normalized_similarity(s1.lower(), s2.lower())
 
     # 需要对作者的比率分布进行调研决定哪些是小比率哪些是大比率
     if len_ratio > 1.5 and len_ratio < 3:
@@ -287,7 +298,7 @@ def AuthorRatio(
 
     # 首字母相同提分
     # if is_contained(extract_initials(s1), extract_initials(s2)):
-    if is_contained_list([i[:1] for i in l1], [i[:1] for i in l2]):
+    if is_contained_list([i[:1].lower() for i in l1], [i[:1].lower() for i in l2]):
         # 应该提分
         end_ratio = end_ratio * 1.05
     else:
@@ -302,7 +313,7 @@ def AuthorRatio(
         end_ratio = end_ratio * 1.1
 
     if l1[0] != l2[0]:
-        end_ratio = end_ratio * Jaro.normalized_similarity(l1[0], l2[0])
+        end_ratio = end_ratio * Jaro.normalized_similarity(l1[0].lower(), l2[0].lower())
 
     # 如果字符串本身的相似度高 应该拉上去 否者应该拉下来
     return min(end_ratio, 1) * 0.5 + normal_end_ratio * 0.5

{re_common-10.0.0 → re_common-10.0.1}/re_common/v2/baselibrary/utils/stringutils.py

@@ -63,6 +63,7 @@ def get_diacritic_variant(char1):
     return base_char1
 
 def get_alphabetic_ratio(text: str) -> float:
+    # 返回字母型字符所占比例
     if not text:
         return 0
 

{re_common-10.0.0 → re_common-10.0.1}/re_common.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: re_common
-Version: 10.0.0
+Version: 10.0.1
 Summary: a library about all python projects
 Home-page: https://gitee.com/xujiangios/re-common
 Author: vic

{re_common-10.0.0 → re_common-10.0.1}/setup.py

@@ -35,7 +35,7 @@ long_description = """
 """
 setuptools.setup(
     name="re_common",
-    version="10.0.0",
+    version="10.0.1",
     author="vic",
     author_email="xujiang5@163.com",
     description="a library about all python projects",