nlpertools 1.0.6.dev0__tar.gz → 1.0.8__tar.gz

{nlpertools-1.0.6.dev0/src/nlpertools.egg-info → nlpertools-1.0.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nlpertools
-Version: 1.0.6.dev0
+Version: 1.0.8
 Summary: A small package about small basic IO operation when coding
 Home-page: https://github.com/lvzii/nlpertools
 Author: youshuJi
@@ -12,6 +12,11 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: psutil
+Provides-Extra: torch
+Requires-Dist: torch; extra == "torch"
 
 <div align="center">
   <h4 align="center">
@@ -23,9 +28,6 @@ License-File: LICENSE
 </div>
 
 
-# 当前版本
-
-1.0.5
 
 # 说明
 
@@ -75,9 +77,9 @@ https://nlpertools.readthedocs.io/en/latest/
       def __init__(self, IPT_MODEL_PATH):
           self.ltp = LTP(IPT_MODEL_PATH)
   ```
-  通过pyinstrument判断，超过1s的包即采用这种方式
+  通过`pyinstrument`判断，超过1s的包即采用这种方式
   - 2s+ happybase、seaborn、torch、jieba
-  - 1s+
+  - 1s+ /
   - 0.5s+ pandas elasticsearch transformers xgboost nltk mongo
 
 
@@ -85,6 +87,8 @@ https://nlpertools.readthedocs.io/en/latest/
 
 - [readthedoc 检查文档构建状况](https://readthedocs.org/projects/nlpertools/builds)
 
+- [打包发布指南](https://juejin.cn/post/7369413136224878644)
+
 - 发布版本需要加tag
 
 ## 开发哲学
@@ -106,6 +110,23 @@ b = nlpertools.io.file.readtxt_list_all_strip('res.txt')
 ```
 
 ```bash
-# 监控gpu显存
-python -m nlpertools
+# 生成pypi双因素认证的实时密钥(需要提供key)
+python -m nlpertools.get_2fa your_key
+
+## git
+python nlpertools.cli --git_push
+python nlpertools.cli --git_pull
+
+# 以下功能被nvitop替代，不推荐使用
+## 监控gpu显存
+python -m nlpertools.monitor.gpu
+## 监控cpu
+python -m  nlpertools.monitor.memory
 ```
+
+## 一些常用项目
+
+nvitop
+
+ydata-profiling
+

{nlpertools-1.0.6.dev0 → nlpertools-1.0.8}/README.md

@@ -8,9 +8,6 @@
 </div>
 
 
-# 当前版本
-
-1.0.5
 
 # 说明
 
@@ -60,9 +57,9 @@ https://nlpertools.readthedocs.io/en/latest/
       def __init__(self, IPT_MODEL_PATH):
           self.ltp = LTP(IPT_MODEL_PATH)
   ```
-  通过pyinstrument判断，超过1s的包即采用这种方式
+  通过`pyinstrument`判断，超过1s的包即采用这种方式
   - 2s+ happybase、seaborn、torch、jieba
-  - 1s+
+  - 1s+ /
   - 0.5s+ pandas elasticsearch transformers xgboost nltk mongo
 
 
@@ -70,6 +67,8 @@ https://nlpertools.readthedocs.io/en/latest/
 
 - [readthedoc 检查文档构建状况](https://readthedocs.org/projects/nlpertools/builds)
 
+- [打包发布指南](https://juejin.cn/post/7369413136224878644)
+
 - 发布版本需要加tag
 
 ## 开发哲学
@@ -91,6 +90,23 @@ b = nlpertools.io.file.readtxt_list_all_strip('res.txt')
 ```
 
 ```bash
-# 监控gpu显存
-python -m nlpertools
+# 生成pypi双因素认证的实时密钥(需要提供key)
+python -m nlpertools.get_2fa your_key
+
+## git
+python nlpertools.cli --git_push
+python nlpertools.cli --git_pull
+
+# 以下功能被nvitop替代，不推荐使用
+## 监控gpu显存
+python -m nlpertools.monitor.gpu
+## 监控cpu
+python -m  nlpertools.monitor.memory
 ```
+
+## 一些常用项目
+
+nvitop
+
+ydata-profiling
+

{nlpertools-1.0.6.dev0 → nlpertools-1.0.8}/setup.cfg

@@ -1,6 +1,5 @@
 [metadata]
 name = nlpertools
-version = 1.0.6dev
 author = youshuJi
 author_email = zjs20001205@gmail.com
 description = A small package about small basic IO operation when coding

nlpertools-1.0.8/setup.py

@@ -0,0 +1,36 @@
+import os
+import re
+
+from setuptools import setup
+
+
+def get_version():
+    with open(os.path.join("src", "nlpertools", "__init__.py"), "r", encoding="utf-8") as f:
+        file_content = f.read()
+        pattern = r"{}\W*=\W*\'([^\"]+)\'".format("__version__")
+        (version,) = re.findall(pattern, file_content)
+        return version
+
+
+def main():
+    setup(
+        # https://juejin.cn/post/7369349560421040128
+        install_requires=[
+            "numpy",
+            "pandas",
+            "psutil"
+        ],
+        extras_require={
+            "torch": ["torch"],
+        },
+        version=get_version(),
+        entry_points={
+            "console_scripts": [
+                "ncli=nlpertools.cli:main",
+            ]
+        }
+    )
+
+
+if __name__ == '__main__':
+    main()

{nlpertools-1.0.6.dev0 → nlpertools-1.0.8}/src/nlpertools/__init__.py

@@ -3,6 +3,7 @@
 # @Author  : youshu.Ji
 from .algo.kmp import *
 from .data_structure.base_structure import *
+from .draw import *
 from .dataprocess import *
 from .io.dir import *
 from .io.file import *
@@ -15,10 +16,8 @@ from .reminder import *
 from .utils_for_nlpertools import *
 from .wrapper import *
 from .monitor import *
+from .cli import *
 
-import os
 
 
-DB_CONFIG_FILE = os.path.join(os.path.dirname(__file__),"default_db_config.yml")
-
-__version__ = '1.0.5'
+__version__ = '1.0.8'

nlpertools-1.0.8/src/nlpertools/cli.py

@@ -0,0 +1,87 @@
+import argparse
+import os
+import uuid
+import sys
+
+import pyotp
+
+"""
+如何Debug cli.py
+"""
+
+
+def git_push():
+    """
+    针对国内提交github经常失败，自动提交
+    """
+    num = -1
+    while 1:
+        num += 1
+        print("retry num: {}".format(num))
+        info = os.system("git push --set-upstream origin main")
+        print(str(info))
+        if not str(info).startswith("fatal"):
+            print("scucess")
+            break
+
+
+def git_pull():
+    """
+    针对国内提交github经常失败，自动提交
+    """
+    num = -1
+    while 1:
+        num += 1
+        print("retry num: {}".format(num))
+        info = os.system("git pull")
+        print(str(info))
+        if not str(info).startswith("fatal") and not str(info).startswith("error"):
+            print("scucess")
+            break
+
+
+def get_mac_address():
+    mac = uuid.UUID(int=uuid.getnode()).hex[-12:]
+    mac_address = ":".join([mac[e:e + 2] for e in range(0, 11, 2)])
+    print("mac address 不一定准确")
+    print(mac_address)
+    return mac_address
+
+
+def get_2af_value(key):
+    """
+    key应该是7位的
+    """
+    print(key)
+    totp = pyotp.TOTP(key)
+    print(totp.now())
+
+
+def main():
+    parser = argparse.ArgumentParser(description="CLI tool for git operations and getting MAC address.")
+    parser.add_argument('--gitpush', action='store_true', help='Perform git push operation.')
+    parser.add_argument('--gitpull', action='store_true', help='Perform git push operation.')
+    parser.add_argument('--mac_address', action='store_true', help='Get the MAC address.')
+
+    parser.add_argument('--get_2fa', action='store_true', help='Get the 2fa value.')
+    parser.add_argument('--get_2fa_key', type=str, help='Get the 2fa value.')
+
+    args = parser.parse_args()
+
+    if args.gitpush:
+        git_push()
+    elif args.gitpull:
+        git_pull()
+    elif args.mac_address:
+        get_mac_address()
+    elif args.get_2fa:
+        if args.get_2fa_key:
+            get_2af_value(args.get_2fa_key)
+        else:
+            print("Please provide a key as an argument.")
+    else:
+        print("No operation specified. Use --gitpush or --get_mac_address.")
+
+
+if __name__ == '__main__':
+    main()

{nlpertools-1.0.6.dev0 → nlpertools-1.0.8}/src/nlpertools/data_client.py

@@ -1,3 +1,4 @@
+#encoding=utf-8
 # !/usr/bin/python3.8
 # -*- coding: utf-8 -*-
 # @Author  : youshu.Ji
@@ -5,9 +6,11 @@ import datetime
 import json
 import logging
 
-from . import DB_CONFIG_FILE
 from .io.file import read_yaml
 from .utils.package import *
+import os
+
+DB_CONFIG_FILE = os.path.join(os.path.dirname(__file__), "default_db_config.yml")
 
 # import aioredis
 # import happybase
@@ -28,21 +31,24 @@ class Neo4jOps(object):
     NEO4J_TIMEOUT = 0.3
     pass
 
+
 class SqliteOps(object):
-    import sqlite3
-    database_path = r'xx.db'
-    conn = sqlite3.connect(database_path)
-    c = conn.cursor()
-    sql = "select name from sqlite_master where type='table' order by name"
-    c.execute(sql)
-    print(c.fetchall())
-    sql = "select * from typecho_contents"
-    c.execute(sql)
-    res = c.fetchall()
-    print(res[3])
-
-    conn.commit()
-    conn.close()
+    pass
+    # import sqlite3
+    # database_path = r'xx.db'
+    # conn = sqlite3.connect(database_path)
+    # c = conn.cursor()
+    # sql = "select name from sqlite_master where type='table' order by name"
+    # c.execute(sql)
+    # print(c.fetchall())
+    # sql = "select * from typecho_contents"
+    # c.execute(sql)
+    # res = c.fetchall()
+    # print(res[3])
+    #
+    # conn.commit()
+    # conn.close()
+
 
 class MysqlOps(object):
     import pandas as pd
@@ -116,6 +122,41 @@ class EsOps(object):
         print(f"批量保存数据： {_res}")
 
 
+class MongoDB_BETA:
+    def __init__(self, host='localhost', port=27017, db_name=None, collection_name=None):
+        self.host = host
+        self.port = port
+        self.db_name = db_name
+        self.collection_name = collection_name
+        self.client = None
+        self.db = None
+        self.collection = None
+
+    def connect(self):
+        self.client = MongoClient(self.host, self.port)
+        self.db = self.client[self.db_name]
+        self.collection = self.db[self.collection_name]
+
+    def close(self):
+        if self.client:
+            self.client.close()
+
+    def insert_data(self, data):
+        if isinstance(data, list):
+            self.collection.insert_many(data)
+        else:
+            self.collection.insert_one(data)
+
+    def check_data_exists(self, query):
+        """
+        检查某个数据是否存在于数据库中
+        :param query: 查询条件
+        :return: 布尔值，表示数据是否存在
+        """
+        return self.collection.count_documents(query) > 0
+
+
+
 class MongoOps(object):
     from pymongo import MongoClient
     def __init__(self, config=global_db_config["mongo"]):
@@ -348,8 +389,6 @@ class KafkaOps(object):
             print(recv)
 
 
-
-
 class MilvusOps(object):
     def __init__(self, config=global_db_config.milvus):
         from pymilvus import connections, Collection

{nlpertools-1.0.6.dev0 → nlpertools-1.0.8}/src/nlpertools/dataprocess.py

@@ -55,9 +55,9 @@ class Pattern:
     # 中文人名
     chinese_name_pattern = "(?:[\u4e00-\u9fa5·]{2,3})"
     # 英文人名
-    english_name_pattern = "(^[a-zA-Z][a-zA-Z\s]{0,20}[a-zA-Z]$)"
+    english_name_pattern = r"(^[a-zA-Z][a-zA-Z\s]{0,20}[a-zA-Z]$)"
     # 纯数字
-    pure_num_pattern = "\d+"
+    pure_num_pattern = r"\d+"
     # xxxx图/表 之类的表述
     pic_table_descript_pattern = ".{1,15}图"
 
@@ -66,20 +66,20 @@ class Pattern:
     hlink_pattern = (
         r"(https?|ftp|file)://[-A-Za-z0-9+&@#/%?=~_|!:,.;]+[-A-Za-z0-9+&@#/%=~_|]"
     )
-    http_pattern = "(http|https):\/\/([\w.]+\/?)\S*/\S*"
+    http_pattern = r"(http|https):\/\/([\w.]+\/?)\S*/\S*"
     # 邮箱
-    email_pattern = "[A-Za-z0-9\u4e00-\u9fa5]+@[a-zA-Z0-9_-]+(\.[a-zA-Z0-9_-]+)+"
+    email_pattern = r"[A-Za-z0-9\u4e00-\u9fa5]+@[a-zA-Z0-9_-]+(\.[a-zA-Z0-9_-]+)+"
     # html 可能过于严格了
-    html_pattern = "<[\s\S]*?>"
+    html_pattern = r"<[\s\S]*?>"
     # 重复 “asdasdasdasd”
     repeat_pattern = "(.)\1+"
     # 日期
-    day_time_pattern = "\d{1,4}(-)(1[0-2]|0?[1-9])\1(0?[1-9]|[1-2]\d|30|31)"
+    day_time_pattern = r"\d{1,4}(-)(1[0-2]|0?[1-9])\1(0?[1-9]|[1-2]\d|30|31)"
     # 小时
-    hour_time_pattern = "(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d"
+    hour_time_pattern = r"(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d"
     # 股票
     stock_pattern = (
-        "(s[hz]|S[HZ])(000[\d]{3}|002[\d]{3}|300[\d]{3}|600[\d]{3}|60[\d]{4})"
+        r"(s[hz]|S[HZ])(000[\d]{3}|002[\d]{3}|300[\d]{3}|600[\d]{3}|60[\d]{4})"
     )
 
     # 一般是需要替换的
@@ -91,7 +91,7 @@ class Pattern:
     # 微博视频等
     weibo_pattern = r"([\s]\w+(的微博视频)|#|【|】|转发微博)"
     # @
-    at_pattern = "@\w+"
+    at_pattern = r"@\w+"
 
     # from https://github.com/bigscience-workshop/data-preparation pii
     year_patterns = [
@@ -116,7 +116,7 @@ class Pattern:
     ipv4_pattern = r'(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)(?:\.(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)){3}'
     ipv6_pattern = r'(?:[0-9a-fA-F]{1,4}:){7,7}[0-9a-fA-F]{1,4}|(?:[0-9a-fA-F]{1,4}:){1,7}:|(?:[0-9a-fA-F]{1,4}:){1,6}:[0-9a-fA-F]{1,4}|(?:[0-9a-fA-F]{1,4}:){1,5}(?::[0-9a-fA-F]{1,4}){1,2}|(?:[0-9a-fA-F]{1,4}:){1,4}(?::[0-9a-fA-F]{1,4}){1,3}|(?:[0-9a-fA-F]{1,4}:){1,3}(?::[0-9a-fA-F]{1,4}){1,4}|(?:[0-9a-fA-F]{1,4}:){1,2}(?::[0-9a-fA-F]{1,4}){1,5}|[0-9a-fA-F]{1,4}:(?:(?::[0-9a-fA-F]{1,4}){1,6})|:(?:(?::[0-9a-fA-F]{1,4}){1,7}|:)|fe80:(?::[0-9a-fA-F]{0,4}){0,4}%[0-9a-zA-Z]{1,}|::(?:ffff(?::0{1,4}){0,1}:){0,1}(?:(?:25[0-5]|(?:2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(?:25[0-5]|(?:2[0-4]|1{0,1}[0-9]){0,1}[0-9])|(?:[0-9a-fA-F]{1,4}:){1,4}:(?:(?:25[0-5]|(?:2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(?:2[0-4]|1{0,1}[0-9]){0,1}[0-9])'
     ip_pattern = r"(?:^|[\b\s@?,!;:\'\")(.\p{Han}])(" + r"|".join(
-        [ipv4_pattern, ipv6_pattern]) + ")(?:$|[\s@,?!;:\'\"(.\p{Han}])"
+        [ipv4_pattern, ipv6_pattern]) + r")(?:$|[\s@,?!;:\'\"(.\p{Han}])"
 
     # https://regex101.com/r/EpA5B7/1
     email_line_pattern = r'''
@@ -466,7 +466,7 @@ class TextProcess(object):
         p = re.compile(pattern, re.S)
         text = p.sub("", text)
 
-        dr = re.compile("@\w+", re.S)
+        dr = re.compile(r"@\w+", re.S)
         text = dr.sub("", text)
 
         return text
@@ -527,7 +527,7 @@ class TextProcess(object):
             text = re.sub(pattern, replace, text)
         return text
 
-    def calc_proportion_zh(self,text):
+    def calc_proportion_zh(self, text):
         text = text.strip()
         # 如果是中国英文的情况，并且英文有空格分开
         if " " in text:
@@ -538,6 +538,8 @@ class TextProcess(object):
                 chinese_count += 1
             else:
                 pass
+
+
 class CopyFunc():
     # from https://github.com/lemon234071/clean-dialog
     def is_chinese_char(cp):
@@ -597,6 +599,20 @@ def convert_basic2fullwidth(sentence):
         new_sentence += char
     return new_sentence
 
+
+def clean_illegal_chars_for_excel(df):
+    # openpyxl 库写入 Excel 文件时，有一些非法字符，需要删除
+    # 定义一个函数来移除字符串中的非法字符
+    def remove_illegal_chars(s):
+        if isinstance(s, str):
+            # 移除 ASCII 码在非法范围内的字符
+            return re.sub(r'[\x00-\x08\x0B\x0C\x0E-\x1F]', '', s)
+        return s
+
+    # 应用清理函数到数据框的每个元素
+    return df.map(remove_illegal_chars)
+
+
 if __name__ == "__main__":
     pattern_for_filter = [
         Pattern.redundancy_space_pattern,

nlpertools-1.0.8/src/nlpertools/draw/draw.py

@@ -0,0 +1,83 @@
+#!/usr/bin/python3.8
+# -*- coding: utf-8 -*-
+# @Author  : youshu.Ji
+from ..utils.package import plt
+
+
+def confused_matrix(confuse_matrix):
+    import seaborn as sns
+    sns.set()
+    f, ax = plt.subplots()
+    ticklabels = ["l1", "l2", "l31"]
+    sns.heatmap(confuse_matrix, annot=True, fmt=".3g", ax=ax, cmap='rainbow',
+                xticklabels=ticklabels, yticklabels=ticklabels)  # 画热力图
+
+    ax.set_title('confusion matrix')  # 标题
+    ax.set_xlabel('predict')  # x轴
+    ax.set_ylabel('true')  # y轴
+    plt.show()
+
+    f.savefig('tmp.jpg', bbox_inches='tight')
+
+
+def plot_histogram(data, bin_size):
+    """
+    画直方图，超过1000的统一按1000算
+    :param data:
+    :param bin_size:
+    :return:
+    """
+    import matplotlib.pyplot as plt
+    import numpy as np
+    import pandas as pd
+    from matplotlib.ticker import MaxNLocator
+    # 将超过1000的值改为1000
+    def process_lengths(data):
+        return [length if length <= 1000 else 1003 for length in data]
+
+    # 前闭后开
+    min_num, max_num = 0, 1000
+    # min_num, max_num = min(data), max(data)
+
+    plt.figure(figsize=(12, 8))
+    processed_data = process_lengths(data)
+    bins = np.arange(0, 1000 + 2 * bin_size, bin_size)
+    # 绘制直方图
+    n, new_bins, patches = plt.hist(processed_data, bins=bins, edgecolor='black', color='skyblue', alpha=0.7,
+                                    linewidth=0)
+
+    # 添加"∞"的标签
+    # bins会改变
+    plt.gca().set_xticks(bins)
+    plt.gca().set_xticklabels([str(i) for i in plt.xticks()[0][:-1]] + ["∞"])
+
+    mean_val = np.mean(data)
+    plt.axvline(mean_val, color='red', linestyle='dashed', linewidth=1)
+    plt.text(mean_val + bin_size / 10, max(n) * 0.9, f'Mean: {mean_val:.2f}', color='red')
+
+    # 添加标题和标签
+    plt.title('Module Line Number Distribution', fontsize=16, fontweight='bold')
+    plt.xlabel('module line number', fontsize=14)
+    plt.ylabel('frequency', fontsize=14)
+
+    # 添加网格
+    plt.grid(True, linestyle='--', alpha=0.6)
+
+    # 美化x轴和y轴的刻度
+    plt.xticks(fontsize=12)
+    plt.yticks(fontsize=12)
+
+    # 在每个柱状图上显示数值
+    for i in range(len(patches)):
+        plt.text(patches[i].get_x() + patches[i].get_width() / 2, patches[i].get_height(),
+                 str(int(n[i])), ha='center', va='bottom', fontsize=12)
+    plt.gca().yaxis.set_major_locator(MaxNLocator(integer=True))
+    # 显示图表
+    plt.show()
+
+
+if __name__ == '__main__':
+    # 调整区间大小
+    bin_size = 50
+    # 示例模块长度数据
+    plot_histogram([1, 100, 999, 1000, 1002, 1100, 1150], bin_size)

nlpertools-1.0.8/src/nlpertools/draw/math_func.py

@@ -0,0 +1,33 @@
+# 数学函数
+def draw_log():
+    import matplotlib.pyplot as plt
+    import numpy as np
+    from matplotlib.ticker import MultipleLocator, FormatStrFormatter
+
+    # 生成一些数据
+    x = np.linspace(0.1, 10, 100)
+    # 默认log指的时loge
+    y = np.log(x)
+
+    # 创建一个新的图形和轴
+    fig, ax = plt.subplots()
+
+    # 绘制log图像
+    ax.plot(x, y)
+
+    # 设置图像标题和轴标签
+    ax.set_title("Logarithmic Function")
+    ax.set_xlabel("x")
+    ax.set_ylabel("log(x)")
+    # 设置横坐标的刻度间隔为1
+    ax.xaxis.set_major_locator(MultipleLocator(1))
+
+    # 设置横坐标的刻度格式
+    ax.xaxis.set_major_formatter(FormatStrFormatter("%.1f"))
+    # 添加x=1的虚线
+    ax.axvline(x=1, linestyle="--", color="gray")
+    # 添加y=1的虚线
+    ax.axhline(y=0, linestyle="--", color="gray")
+
+    # 显示图像
+    plt.show()

{nlpertools-1.0.6.dev0 → nlpertools-1.0.8}/src/nlpertools/io/dir.py

@@ -10,7 +10,30 @@ def j_mkdir(name):
     os.makedirs(name, exist_ok=True)
 
 
-def get_filename(path) -> str:
+def j_walk(name, suffix=None):
+    paths = []
+    for root, dirs, files in os.walk(name):
+        for file in files:
+            path = os.path.join(root, file)
+            if not (suffix and not path.endswith(suffix)):
+                paths.append(path)
+    return paths
+
+
+def windows_to_wsl_path(windows_path):
+    # 转换驱动器号
+    if windows_path[1:3] == ':\\':
+        drive_letter = windows_path[0].lower()
+        path = windows_path[2:].replace('\\', '/')
+        wsl_path = f'/mnt/{drive_letter}{path}'
+    else:
+        # 如果路径不是以驱动器号开头，则直接替换路径分隔符
+        wsl_path = windows_path.replace('\\', '/').replace("'", "\'")
+
+    return wsl_path
+
+
+def get_filename(path, suffix=True) -> str:
     """
     返回路径最后的文件名
     :param path:
@@ -18,11 +41,20 @@ def get_filename(path) -> str:
     """
     # path = r'***/**/***.txt'
     filename = os.path.split(path)[-1]
+    if not suffix:
+        filename = filename.split('.')[0]
     return filename
 
 
 def j_listdir(dir_name, including_dir=True):
-    #  yield
+    filenames = os.listdir(dir_name)
+    if including_dir:
+        return [os.path.join(dir_name, filename) for filename in filenames]
+    else:
+        return list(filenames)
+
+
+def j_listdir_yield(dir_name, including_dir=True):
     filenames = os.listdir(dir_name)
     for filename in filenames:
         if including_dir: