re-common 10.0.22__py3-none-any.whl → 10.0.24__py3-none-any.whl

re_common/studio/assignment_expressions.py

@@ -1,37 +1,37 @@
-"""
-来自于 PEP572
-
-在 python 3.8 中获取正式支持
-
-https://docs.python.org/3/whatsnew/3.8.html
-
-:= (由于它与海象的眼睛和象牙很像，因此被亲切地称为“海象操作员” )
-
-"""
-
-# 在此示例中，赋值表达式有助于避免调用 len()两次：
-import re
-import string
-
-a = "adahfhoifoigoiwfhoiwg"
-if (n := len(a)) > 10:
-    print(f"List is too long ({n} elements, expected <= 10)")
-
-# 在正则表达式匹配期间会产生类似的好处，其中需要两次匹配对象，一次是测试是否发生匹配，另一次是提取子组：
-discount = 0.0
-advertisement = "a 50% discount"
-if mo := re.search(r'(\d+)% discount', advertisement):
-    discount = float(mo.group(1)) / 100.0
-    print(discount)
-
-
-# 该运算符还对while循环有用，该循环计算一个值来测试循环终止，然后在循环主体中再次需要相同的值：
-# Loop over fixed length blocks
-f = open("./__init__.py", 'rb')
-while len(block := f.read(256)) != 0:
-    print(len(block))
-
-# 另一个具有启发性的用例出现在列表理解中，其中表达式主体中还需要在过滤条件下计算出的值：
-allowed_names = list(string.ascii_letters)
-names = list(string.ascii_letters)
+"""
+来自于 PEP572
+
+在 python 3.8 中获取正式支持
+
+https://docs.python.org/3/whatsnew/3.8.html
+
+:= (由于它与海象的眼睛和象牙很像，因此被亲切地称为“海象操作员” )
+
+"""
+
+# 在此示例中，赋值表达式有助于避免调用 len()两次：
+import re
+import string
+
+a = "adahfhoifoigoiwfhoiwg"
+if (n := len(a)) > 10:
+    print(f"List is too long ({n} elements, expected <= 10)")
+
+# 在正则表达式匹配期间会产生类似的好处，其中需要两次匹配对象，一次是测试是否发生匹配，另一次是提取子组：
+discount = 0.0
+advertisement = "a 50% discount"
+if mo := re.search(r'(\d+)% discount', advertisement):
+    discount = float(mo.group(1)) / 100.0
+    print(discount)
+
+
+# 该运算符还对while循环有用，该循环计算一个值来测试循环终止，然后在循环主体中再次需要相同的值：
+# Loop over fixed length blocks
+f = open("./__init__.py", 'rb')
+while len(block := f.read(256)) != 0:
+    print(len(block))
+
+# 另一个具有启发性的用例出现在列表理解中，其中表达式主体中还需要在过滤条件下计算出的值：
+allowed_names = list(string.ascii_letters)
+names = list(string.ascii_letters)
 print([clean_name for name in names if (clean_name := name) in allowed_names])

re_common/studio/mydash/test1.py

@@ -1,19 +1,19 @@
-import dash
-import dash_table
-import pandas as pd
-import dash_design_kit as ddk
-
-df = pd.read_csv("test.csv")
-app = dash.Dash(__name__)
-
-app.layout = ddk.App(show_editor=True, children=[
-    ddk.DataTable(
-       id='table',
-       columns=[{"name": i, "id": i} for i in df.columns],
-       data=df.to_dict('records'),
-       editable=True
-   )
-])
-
-if __name__ == '__main__':
+import dash
+import dash_table
+import pandas as pd
+import dash_design_kit as ddk
+
+df = pd.read_csv("test.csv")
+app = dash.Dash(__name__)
+
+app.layout = ddk.App(show_editor=True, children=[
+    ddk.DataTable(
+       id='table',
+       columns=[{"name": i, "id": i} for i in df.columns],
+       data=df.to_dict('records'),
+       editable=True
+   )
+])
+
+if __name__ == '__main__':
     app.run_server(debug=True)

re_common/studio/pydashstudio/first.py

@@ -1,9 +1,9 @@
-import pydash
-
-users = [
-    {'name': 'Michelangelo', 'active': False},
-    {'name': 'Donatello', 'active': False},
-    {'name': 'Leonardo', 'active': True}
-]
-callback = lambda item: item["name"] == "Donatello"
-pydash.find_index(users, callback)
+import pydash
+
+users = [
+    {'name': 'Michelangelo', 'active': False},
+    {'name': 'Donatello', 'active': False},
+    {'name': 'Leonardo', 'active': True}
+]
+callback = lambda item: item["name"] == "Donatello"
+pydash.find_index(users, callback)

re_common/studio/streamlitstudio/first_app.py

@@ -1,66 +1,66 @@
-import time
-
-import streamlit as st
-# To make things easier later, we're also importing numpy and pandas for
-# working with sample data.
-import numpy as np
-import pandas as pd
-
-st.title('My first app')
-st.write("Here's our first attempt at using data to create a table:")
-st.write(pd.DataFrame({
-    'first column': [1, 2, 3, 4],
-    'second column': [10, 20, 30, 40]
-}))
-
-
-chart_data = pd.DataFrame(
-     np.random.randn(20, 3),
-     columns=['a', 'b', 'c'])
-
-st.line_chart(chart_data)
-
-# map_data = pd.DataFrame(
-#     np.random.randn(1000, 2) / [50, 50] + [37.76, -122.4],
-#     columns=['lat', 'lon'])
-#
-# st.map(map_data)
-
-if st.checkbox('Show dataframe'):
-    chart_data = pd.DataFrame(
-       np.random.randn(20, 3),
-       columns=['a', 'b', 'c'])
-    chart_data
-
-df = pd.DataFrame({
-  'first column': [1, 2, 3, 4],
-  'second column': [10, 20, 30, 40]
-})
-
-df
-
-option = st.selectbox(
-    'Which number do you like best?',
-     df['first column'])
-
-'You selected: ', option
-
-option2 = st.sidebar.selectbox(
-    'Which number do you like best??',
-     df['first column'])
-
-'You selected:', option2
-
-'Starting a long computation...'
-
-# Add a placeholder
-latest_iteration = st.empty()
-bar = st.progress(0)
-
-for i in range(100):
-  # Update the progress bar with each iteration.
-  latest_iteration.text(f'Iteration {i+1}')
-  bar.progress(i + 1)
-  time.sleep(0.1)
-
+import time
+
+import streamlit as st
+# To make things easier later, we're also importing numpy and pandas for
+# working with sample data.
+import numpy as np
+import pandas as pd
+
+st.title('My first app')
+st.write("Here's our first attempt at using data to create a table:")
+st.write(pd.DataFrame({
+    'first column': [1, 2, 3, 4],
+    'second column': [10, 20, 30, 40]
+}))
+
+
+chart_data = pd.DataFrame(
+     np.random.randn(20, 3),
+     columns=['a', 'b', 'c'])
+
+st.line_chart(chart_data)
+
+# map_data = pd.DataFrame(
+#     np.random.randn(1000, 2) / [50, 50] + [37.76, -122.4],
+#     columns=['lat', 'lon'])
+#
+# st.map(map_data)
+
+if st.checkbox('Show dataframe'):
+    chart_data = pd.DataFrame(
+       np.random.randn(20, 3),
+       columns=['a', 'b', 'c'])
+    chart_data
+
+df = pd.DataFrame({
+  'first column': [1, 2, 3, 4],
+  'second column': [10, 20, 30, 40]
+})
+
+df
+
+option = st.selectbox(
+    'Which number do you like best?',
+     df['first column'])
+
+'You selected: ', option
+
+option2 = st.sidebar.selectbox(
+    'Which number do you like best??',
+     df['first column'])
+
+'You selected:', option2
+
+'Starting a long computation...'
+
+# Add a placeholder
+latest_iteration = st.empty()
+bar = st.progress(0)
+
+for i in range(100):
+  # Update the progress bar with each iteration.
+  latest_iteration.text(f'Iteration {i+1}')
+  bar.progress(i + 1)
+  time.sleep(0.1)
+
 '...and now we\'re done!'

re_common/studio/streamlitstudio/uber_pickups.py

@@ -1,24 +1,24 @@
-import streamlit as st
-import pandas as pd
-import numpy as np
-
-st.title('Uber pickups in NYC')
-
-DATE_COLUMN = 'date/time'
-DATA_URL = ('https://s3-us-west-2.amazonaws.com/streamlit-demo-data/uber-raw-data-sep14.csv.gz')
-
-@st.cache
-def load_data(nrows):
-    data = pd.read_csv(DATA_URL, nrows=nrows)
-    lowercase = lambda x: str(x).lower()
-    data.rename(lowercase, axis='columns', inplace=True)
-    data[DATE_COLUMN] = pd.to_datetime(data[DATE_COLUMN])
-    return data
-
-# Create a text element and let the reader know the data is loading.
-data_load_state.text("Done! (using st.cache)")
-
-# Load 10,000 rows of data into the dataframe.
-data = load_data(10000)
-# Notify the reader that the data was successfully loaded.
+import streamlit as st
+import pandas as pd
+import numpy as np
+
+st.title('Uber pickups in NYC')
+
+DATE_COLUMN = 'date/time'
+DATA_URL = ('https://s3-us-west-2.amazonaws.com/streamlit-demo-data/uber-raw-data-sep14.csv.gz')
+
+@st.cache
+def load_data(nrows):
+    data = pd.read_csv(DATA_URL, nrows=nrows)
+    lowercase = lambda x: str(x).lower()
+    data.rename(lowercase, axis='columns', inplace=True)
+    data[DATE_COLUMN] = pd.to_datetime(data[DATE_COLUMN])
+    return data
+
+# Create a text element and let the reader know the data is loading.
+data_load_state.text("Done! (using st.cache)")
+
+# Load 10,000 rows of data into the dataframe.
+data = load_data(10000)
+# Notify the reader that the data was successfully loaded.
 data_load_state.text('Loading data...done!')

re_common/studio/test.py

@@ -1,19 +1,19 @@
-def test_sq():
-    from re_common.baselibrary.utils.basepymongo import BasePyMongo
-    # basemongo = BasePyMongo("mongodb://sdbadmin:sdbadmin@192.168.72.86:11817/test2?authMechanism=SCRAM-SHA-1")
-    # basemongo = BasePyMongo(
-    #     "mongodb://sdbadmin:sdbadmin@192.168.72.86:11817/dataware_house.base_obj_meta_a")
-    basemongo = BasePyMongo(
-        "mongodb://sdbadmin:sdbadmin@192.168.72.86:11817/test2.test?authMechanism=SCRAM-SHA-1")
-
-    basemongo.use_db("test2")
-    # basemongo.auth("sdbadmin", "sdbadmin", "SCRAM-SHA-1")
-    basemongo.create_col("test")
-    # for items in basemongo.find({}):
-    #     print(items["user"])
-    items = basemongo.find()
-    for item in items:
-        ids = item["id"]
-        print(ids)
-
+def test_sq():
+    from re_common.baselibrary.utils.basepymongo import BasePyMongo
+    # basemongo = BasePyMongo("mongodb://sdbadmin:sdbadmin@192.168.72.86:11817/test2?authMechanism=SCRAM-SHA-1")
+    # basemongo = BasePyMongo(
+    #     "mongodb://sdbadmin:sdbadmin@192.168.72.86:11817/dataware_house.base_obj_meta_a")
+    basemongo = BasePyMongo(
+        "mongodb://sdbadmin:sdbadmin@192.168.72.86:11817/test2.test?authMechanism=SCRAM-SHA-1")
+
+    basemongo.use_db("test2")
+    # basemongo.auth("sdbadmin", "sdbadmin", "SCRAM-SHA-1")
+    basemongo.create_col("test")
+    # for items in basemongo.find({}):
+    #     print(items["user"])
+    items = basemongo.find()
+    for item in items:
+        ids = item["id"]
+        print(ids)
+
 test_sq()

re_common/v2/baselibrary/business_utils/BusinessStringUtil.py

@@ -0,0 +1,195 @@
+# 某些业务中的字符串处理 算是特定场景的工具 不算通用工具
+import re
+
+from re_common.v2.baselibrary.utils.string_bool import is_all_symbols
+
+
+def clean_organ_postcode(organ):
+    """
+    格式化组织名称字符串，移除括号内容并删除独立的6位数字（邮政编码），然后清理标点。
+
+    备注: 该方法替换java 里面的 formatOrgan
+
+    参数:
+        organ (str): 输入的组织名称字符串，可能包含括号、分号和邮政编码。
+
+    返回:
+        str: 格式化并清理后的组织名称字符串（无独立6位数字）。
+    """
+    # 如果输入为空，设为空字符串以避免后续操作报错
+    if not organ:
+        organ = ""
+
+    # 删除方括号和圆括号中的内容（包括括号本身）
+    organ = re.sub(r"\[.*?\]", "", organ)  # 非贪婪匹配方括号内容
+    organ = re.sub(r"\(.*?\)", "", organ)  # 非贪婪匹配圆括号内容
+
+    # 定义正则表达式，匹配独立的6位数字
+    # \b 表示单词边界，确保6位数字是独立的（前后不是字母、数字或下划线）
+    organ = re.sub(r"\b[0-9]{6}\b", "", organ)
+
+    # 初始化结果列表，用于存储处理后的组织名称部分
+    format_organ = []
+    # 按分号分割字符串，生成组织名称的各个部分
+    organ_parts = organ.split(";")
+
+    # 遍历每个部分，追加到结果列表
+    for temp_organ in organ_parts:
+        # 去除首尾多余空格后追加（避免因移除邮编导致的空字符串）
+        cleaned_part = temp_organ.strip()
+        # 如果首尾是标点符号，则移除
+        # 定义标点符号的正则表达式（这里包括常见标点）
+        punctuation = r"^[!,.?;:#$%^&*+-]+|[!,.?;:#$%^&*+-]+$"
+        cleaned_part = re.sub(punctuation, "", cleaned_part)
+        if cleaned_part:  # 只追加非空部分
+            format_organ.append(cleaned_part)
+
+    # 用分号连接结果，转换为大写并清理标点
+    format_organ = ";".join(format_organ)
+
+    # 返回最终结果并去除首尾空格
+    return format_organ.strip()
+
+
+def get_first_organ(organ):
+    if not organ:
+        return ""
+    organ_list = organ.strip().split(";")
+    for organ_one in organ_list:
+        # 清理邮政编码
+        organ_one = clean_organ_postcode(organ_one)
+        if organ_one.strip():
+            return organ_one
+
+    return ""
+
+
+def get_first_author(author: str) -> str:
+    if not author:
+        return ""
+    au_list = author.strip().split(";")
+    for au in au_list:
+        au = re.sub("\\[.*?]", "", au)
+        au = re.sub("\\(.*?\\)", "", au)
+        if au.strip():
+            return au
+    return ""
+
+def get_author_list(author: str):
+    lists = []
+    if not author:
+        return []
+    au_list = author.strip().split(";")
+    for au in au_list:
+        au = re.sub("\\[.*?]", "", au)
+        au = re.sub("\\(.*?\\)", "", au)
+        if au.strip():
+            lists.append(au.strip())
+    return lists
+
+
+def get_scopus_author_abbr(author_row: str):
+    if not author_row:
+        return ""
+    author_list = author_row.split("&&")
+    if len(author_list) != 3:
+        raise Exception("错误的数据个数 可能来自其他数据源")
+
+    abbr_list = author_list[0].strip().split(";")
+    abbr_list = [author.strip() for author in abbr_list if
+                 author.strip() and author.strip().lower() not in ("*", "and")]
+    return ";".join(abbr_list)
+
+
+def get_wos_author_abbr(author_row: str):
+    if not author_row:
+        return ""
+    author_list = author_row.split("&&")
+    if len(author_list) != 4:
+        raise Exception("错误的数据个数 可能来自其他数据源")
+    abbr_list = []
+    abbr_list_au = author_list[0].strip().split(";")
+    abbr_list_ba = author_list[2].strip().split(";")
+    abbr_list.extend(abbr_list_au)
+    abbr_list.extend(abbr_list_ba)
+    abbr_list = [author.strip() for author in abbr_list if
+                 author.strip() and author.strip().lower() not in ("*", "and")]
+    return ";".join(abbr_list)
+
+
+def deal_rel_vol(vol_str: str):
+    """
+    处理 期刊融合时的卷处理逻辑
+    """
+
+    # 如果卷是全符号 清理掉
+    if is_all_symbols(vol_str):
+        vol_str = ""
+
+    if vol_str.replace(".", "").isdigit():
+        try:
+            float_num = float(vol_str)
+            if int(float_num) == float_num:
+                return str(int(float_num))
+        except:
+            pass
+
+    if vol_str.lower().startswith("v "):
+        vol_str = vol_str.lower().replace("v ", "").strip()
+        return vol_str
+    if vol_str.lower().startswith("volume "):
+        vol_str = vol_str.lower().replace("volume ", "").strip()
+        return vol_str
+    if vol_str.lower().startswith("vol. "):
+        vol_str = vol_str.lower().replace("vol. ", "").strip()
+        return vol_str
+    if vol_str.lower().startswith("vol "):
+        vol_str = vol_str.lower().replace("vol ", "").strip()
+        return vol_str
+    return vol_str
+
+
+def deal_num_strs(input_str):
+    """
+    int后在str 防止有浮点型的表达方式
+    """
+    number_list = re.findall(r'\d+', input_str)
+    transformed_numbers = [str(int(num)) for num in number_list]
+
+    # 替换原字符串中的数字为转换后的数字
+    for num, transformed_num in zip(number_list, transformed_numbers):
+        input_str = input_str.replace(num, transformed_num)
+    return input_str
+
+
+def deal_num(num_str):
+    """
+    将 期格式化 方便 group尤其是有横杆的数据
+    该方法 为融合二次分割时使用，如果场景合适也可以用于其他地方
+    :param strs:
+    :return:
+    """
+    # 如果期是全符号清理掉
+    if is_all_symbols(num_str):
+        num_str = ""
+
+    if num_str.lower().startswith("n "):
+        num_str = num_str.lower().replace("n ", "").strip()
+
+    num_str = num_str.lower().replace("special_issue_", '').replace("_special_issue", '').replace("issue", "")
+    num_str = num_str.replace("spec.", "").replace("iss.", "").replace("spl.", "").replace("special.", "").replace(
+        "specialissue.", "")
+    num_str = num_str.replace("spec", "").replace("iss", "").replace("spl", "").replace("special", "").replace(
+        "specialissue", '')
+
+    num_str = num_str.replace("-", "_").replace(".", "_").upper()
+    num_str = num_str.lstrip("_").rstrip("_")
+    if num_str.find("_") > -1:
+        start, end = num_str.split("_")
+        start = deal_num_strs(start)
+        end = deal_num_strs(end)
+        num_str = start + "_" + end
+    else:
+        num_str = deal_num_strs(num_str)
+
+    return num_str.lower().strip()

re_common/v2/baselibrary/business_utils/rel_tools.py

@@ -0,0 +1,6 @@
+def assign_group_id(rows: list, sub_db_order: list):
+    subdb_keyid_map = {row.sub_db_id: row.keyid for row in rows}
+    for sub_db_id in sub_db_order:
+        if keyid := subdb_keyid_map.get(sub_db_id):
+            return keyid, len(rows), rows
+    return rows[0].keyid, len(rows), rows

re_common/v2/baselibrary/decorators/utils.py

@@ -1,59 +1,59 @@
-import warnings
-import functools
-
-# 全局集合，用于记录已警告的函数或类
-_warned_once = set()
-
-
-def deprecated(message=None):
-    """
-    装饰器：标记函数或类为已废弃，整个进程只发出一次警告。
-
-    Args:
-        message (str): 自定义警告信息，默认为 None。
-    """
-
-    def decorator(obj):
-        # 如果是函数
-        if isinstance(obj, type(lambda: None)):
-            @functools.wraps(obj)
-            def wrapper(*args, **kwargs):
-                obj_id = id(obj)  # 使用对象的内存地址作为唯一标识
-                if obj_id not in _warned_once:
-                    default_msg = f"函数 {obj.__name__} 已不建议使用。"
-                    warn_msg = f"{default_msg} {message}" if message else default_msg
-                    warnings.warn(
-                        warn_msg,
-                        category=DeprecationWarning,
-                        stacklevel=2
-                    )
-                    _warned_once.add(obj_id)  # 记录已警告
-                return obj(*args, **kwargs)
-
-            return wrapper
-
-        # 如果是类
-        elif isinstance(obj, type):
-            orig_init = obj.__init__
-
-            @functools.wraps(orig_init)
-            def new_init(self, *args, **kwargs):
-                obj_id = id(obj)
-                if obj_id not in _warned_once:
-                    default_msg = f"类 {obj.__name__} 已不建议使用。"
-                    warn_msg = f"{default_msg} {message}" if message else default_msg
-                    warnings.warn(
-                        warn_msg,
-                        category=DeprecationWarning,
-                        stacklevel=2
-                    )
-                    _warned_once.add(obj_id)  # 记录已警告
-                orig_init(self, *args, **kwargs)
-
-            obj.__init__ = new_init
-            return obj
-
-        else:
-            raise TypeError("此装饰器仅适用于函数和类")
-
-    return decorator
+import warnings
+import functools
+
+# 全局集合，用于记录已警告的函数或类
+_warned_once = set()
+
+
+def deprecated(message=None):
+    """
+    装饰器：标记函数或类为已废弃，整个进程只发出一次警告。
+
+    Args:
+        message (str): 自定义警告信息，默认为 None。
+    """
+
+    def decorator(obj):
+        # 如果是函数
+        if isinstance(obj, type(lambda: None)):
+            @functools.wraps(obj)
+            def wrapper(*args, **kwargs):
+                obj_id = id(obj)  # 使用对象的内存地址作为唯一标识
+                if obj_id not in _warned_once:
+                    default_msg = f"函数 {obj.__name__} 已不建议使用。"
+                    warn_msg = f"{default_msg} {message}" if message else default_msg
+                    warnings.warn(
+                        warn_msg,
+                        category=DeprecationWarning,
+                        stacklevel=2
+                    )
+                    _warned_once.add(obj_id)  # 记录已警告
+                return obj(*args, **kwargs)
+
+            return wrapper
+
+        # 如果是类
+        elif isinstance(obj, type):
+            orig_init = obj.__init__
+
+            @functools.wraps(orig_init)
+            def new_init(self, *args, **kwargs):
+                obj_id = id(obj)
+                if obj_id not in _warned_once:
+                    default_msg = f"类 {obj.__name__} 已不建议使用。"
+                    warn_msg = f"{default_msg} {message}" if message else default_msg
+                    warnings.warn(
+                        warn_msg,
+                        category=DeprecationWarning,
+                        stacklevel=2
+                    )
+                    _warned_once.add(obj_id)  # 记录已警告
+                orig_init(self, *args, **kwargs)
+
+            obj.__init__ = new_init
+            return obj
+
+        else:
+            raise TypeError("此装饰器仅适用于函数和类")
+
+    return decorator