pyxllib 0.3.197__py3-none-any.whl → 3.201.1__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.
Files changed (127) hide show
  1. pyxllib/__init__.py +14 -21
  2. pyxllib/algo/__init__.py +8 -8
  3. pyxllib/algo/disjoint.py +54 -54
  4. pyxllib/algo/geo.py +537 -541
  5. pyxllib/algo/intervals.py +964 -964
  6. pyxllib/algo/matcher.py +389 -389
  7. pyxllib/algo/newbie.py +166 -166
  8. pyxllib/algo/pupil.py +629 -629
  9. pyxllib/algo/shapelylib.py +67 -67
  10. pyxllib/algo/specialist.py +241 -241
  11. pyxllib/algo/stat.py +494 -494
  12. pyxllib/algo/treelib.py +145 -149
  13. pyxllib/algo/unitlib.py +62 -66
  14. pyxllib/autogui/__init__.py +5 -5
  15. pyxllib/autogui/activewin.py +246 -246
  16. pyxllib/autogui/all.py +9 -9
  17. pyxllib/autogui/autogui.py +846 -852
  18. pyxllib/autogui/uiautolib.py +362 -362
  19. pyxllib/autogui/virtualkey.py +102 -102
  20. pyxllib/autogui/wechat.py +827 -827
  21. pyxllib/autogui/wechat_msg.py +421 -421
  22. pyxllib/autogui/wxautolib.py +84 -84
  23. pyxllib/cv/__init__.py +5 -5
  24. pyxllib/cv/expert.py +267 -267
  25. pyxllib/cv/imfile.py +159 -159
  26. pyxllib/cv/imhash.py +39 -39
  27. pyxllib/cv/pupil.py +9 -9
  28. pyxllib/cv/rgbfmt.py +1525 -1525
  29. pyxllib/cv/slidercaptcha.py +137 -137
  30. pyxllib/cv/trackbartools.py +251 -251
  31. pyxllib/cv/xlcvlib.py +1040 -1040
  32. pyxllib/cv/xlpillib.py +423 -423
  33. pyxllib/data/echarts.py +236 -240
  34. pyxllib/data/jsonlib.py +85 -89
  35. pyxllib/data/oss.py +72 -72
  36. pyxllib/data/pglib.py +1111 -1127
  37. pyxllib/data/sqlite.py +568 -568
  38. pyxllib/data/sqllib.py +297 -297
  39. pyxllib/ext/JLineViewer.py +505 -505
  40. pyxllib/ext/__init__.py +6 -6
  41. pyxllib/ext/demolib.py +251 -246
  42. pyxllib/ext/drissionlib.py +277 -277
  43. pyxllib/ext/kq5034lib.py +12 -12
  44. pyxllib/ext/qt.py +449 -449
  45. pyxllib/ext/robustprocfile.py +493 -497
  46. pyxllib/ext/seleniumlib.py +76 -76
  47. pyxllib/ext/tk.py +173 -173
  48. pyxllib/ext/unixlib.py +821 -827
  49. pyxllib/ext/utools.py +345 -351
  50. pyxllib/ext/webhook.py +124 -119
  51. pyxllib/ext/win32lib.py +40 -40
  52. pyxllib/ext/wjxlib.py +91 -88
  53. pyxllib/ext/wpsapi.py +124 -124
  54. pyxllib/ext/xlwork.py +9 -9
  55. pyxllib/ext/yuquelib.py +1110 -1105
  56. pyxllib/file/__init__.py +17 -17
  57. pyxllib/file/docxlib.py +757 -761
  58. pyxllib/file/gitlib.py +309 -309
  59. pyxllib/file/libreoffice.py +165 -165
  60. pyxllib/file/movielib.py +144 -148
  61. pyxllib/file/newbie.py +10 -10
  62. pyxllib/file/onenotelib.py +1469 -1469
  63. pyxllib/file/packlib/__init__.py +330 -330
  64. pyxllib/file/packlib/zipfile.py +2441 -2441
  65. pyxllib/file/pdflib.py +422 -426
  66. pyxllib/file/pupil.py +185 -185
  67. pyxllib/file/specialist/__init__.py +681 -685
  68. pyxllib/file/specialist/dirlib.py +799 -799
  69. pyxllib/file/specialist/download.py +193 -193
  70. pyxllib/file/specialist/filelib.py +2825 -2829
  71. pyxllib/file/xlsxlib.py +3122 -3131
  72. pyxllib/file/xlsyncfile.py +341 -341
  73. pyxllib/prog/__init__.py +5 -5
  74. pyxllib/prog/cachetools.py +58 -64
  75. pyxllib/prog/deprecatedlib.py +233 -233
  76. pyxllib/prog/filelock.py +42 -42
  77. pyxllib/prog/ipyexec.py +253 -253
  78. pyxllib/prog/multiprogs.py +940 -940
  79. pyxllib/prog/newbie.py +451 -451
  80. pyxllib/prog/pupil.py +1208 -1197
  81. pyxllib/prog/sitepackages.py +33 -33
  82. pyxllib/prog/specialist/__init__.py +348 -391
  83. pyxllib/prog/specialist/bc.py +203 -203
  84. pyxllib/prog/specialist/browser.py +497 -497
  85. pyxllib/prog/specialist/common.py +347 -347
  86. pyxllib/prog/specialist/datetime.py +198 -198
  87. pyxllib/prog/specialist/tictoc.py +240 -240
  88. pyxllib/prog/specialist/xllog.py +180 -180
  89. pyxllib/prog/xlosenv.py +110 -108
  90. pyxllib/stdlib/__init__.py +17 -17
  91. pyxllib/stdlib/tablepyxl/__init__.py +10 -10
  92. pyxllib/stdlib/tablepyxl/style.py +303 -303
  93. pyxllib/stdlib/tablepyxl/tablepyxl.py +130 -130
  94. pyxllib/text/__init__.py +8 -8
  95. pyxllib/text/ahocorasick.py +36 -39
  96. pyxllib/text/airscript.js +754 -744
  97. pyxllib/text/charclasslib.py +121 -121
  98. pyxllib/text/jiebalib.py +267 -267
  99. pyxllib/text/jinjalib.py +27 -32
  100. pyxllib/text/jsa_ai_prompt.md +271 -271
  101. pyxllib/text/jscode.py +922 -922
  102. pyxllib/text/latex/__init__.py +158 -158
  103. pyxllib/text/levenshtein.py +303 -303
  104. pyxllib/text/nestenv.py +1215 -1215
  105. pyxllib/text/newbie.py +300 -300
  106. pyxllib/text/pupil/__init__.py +8 -8
  107. pyxllib/text/pupil/common.py +1121 -1121
  108. pyxllib/text/pupil/xlalign.py +326 -326
  109. pyxllib/text/pycode.py +47 -47
  110. pyxllib/text/specialist/__init__.py +8 -8
  111. pyxllib/text/specialist/common.py +112 -112
  112. pyxllib/text/specialist/ptag.py +186 -186
  113. pyxllib/text/spellchecker.py +172 -172
  114. pyxllib/text/templates/echart_base.html +10 -10
  115. pyxllib/text/templates/highlight_code.html +16 -16
  116. pyxllib/text/templates/latex_editor.html +102 -102
  117. pyxllib/text/vbacode.py +17 -17
  118. pyxllib/text/xmllib.py +741 -747
  119. pyxllib/xl.py +42 -39
  120. pyxllib/xlcv.py +17 -17
  121. pyxllib-3.201.1.dist-info/METADATA +296 -0
  122. pyxllib-3.201.1.dist-info/RECORD +125 -0
  123. {pyxllib-0.3.197.dist-info → pyxllib-3.201.1.dist-info}/licenses/LICENSE +190 -190
  124. pyxllib/ext/old.py +0 -663
  125. pyxllib-0.3.197.dist-info/METADATA +0 -48
  126. pyxllib-0.3.197.dist-info/RECORD +0 -126
  127. {pyxllib-0.3.197.dist-info → pyxllib-3.201.1.dist-info}/WHEEL +0 -0
pyxllib/text/pycode.py CHANGED
@@ -1,47 +1,47 @@
1
- #!/usr/bin/env python3
2
- # -*- coding: utf-8 -*-
3
- # @Author : 陈坤泽
4
- # @Email : 877362867@qq.com
5
- # @Date : 2021/08/20 11:46
6
-
7
-
8
- import re
9
-
10
-
11
- def py_remove_interaction_chars(s):
12
- """ 去掉复制的一段代码中,前导的“>>>”标记 """
13
- # 这个算法可能还不够严谨,实际应用中再逐步写鲁棒
14
- # ">>> "、"... "
15
- lines = [line[4:] for line in s.splitlines()]
16
- return '\n'.join(lines)
17
-
18
-
19
- def pycode_sort_import(s):
20
- from pyxllib.text.nestenv import PyNestEnv
21
-
22
- def cmp(line):
23
- """ 将任意一句import映射为一个可比较的list对象
24
-
25
- :return: 2个数值
26
- 1、模块优先级
27
- 2、import在前,from在后
28
- """
29
- name = re.search(r'(?:import|from)\s+(\S+)', line).group(1)
30
- for i, x in enumerate('stdlib prog algo text file cv data extend'.split()):
31
- name = name.replace('pyxllib.' + x, f'{i:02}')
32
- for i, x in enumerate('pyxllib pyxlpr xlproject'.split()):
33
- name = name.replace(x, f'~{i:02}')
34
- for i, x in enumerate('newbie pupil specialist expert'.split()):
35
- name = name.replace('.' + x, f'{i:02}')
36
-
37
- # 忽略大小写
38
- return [name.lower(), line.startswith('import')]
39
-
40
- def sort_part(m):
41
- parts = PyNestEnv(m.group()).imports().strings()
42
- parts = [p.rstrip() + '\n' for p in parts]
43
- parts.sort(key=cmp)
44
- return ''.join(parts)
45
-
46
- res = PyNestEnv(s).imports().sub(sort_part, adjacent=True) # 需要邻接,分块处理
47
- return res
1
+ #!/usr/bin/env python3
2
+ # -*- coding: utf-8 -*-
3
+ # @Author : 陈坤泽
4
+ # @Email : 877362867@qq.com
5
+ # @Date : 2021/08/20 11:46
6
+
7
+
8
+ import re
9
+
10
+
11
+ def py_remove_interaction_chars(s):
12
+ """ 去掉复制的一段代码中,前导的“>>>”标记 """
13
+ # 这个算法可能还不够严谨,实际应用中再逐步写鲁棒
14
+ # ">>> "、"... "
15
+ lines = [line[4:] for line in s.splitlines()]
16
+ return '\n'.join(lines)
17
+
18
+
19
+ def pycode_sort_import(s):
20
+ from pyxllib.text.nestenv import PyNestEnv
21
+
22
+ def cmp(line):
23
+ """ 将任意一句import映射为一个可比较的list对象
24
+
25
+ :return: 2个数值
26
+ 1、模块优先级
27
+ 2、import在前,from在后
28
+ """
29
+ name = re.search(r'(?:import|from)\s+(\S+)', line).group(1)
30
+ for i, x in enumerate('stdlib prog algo text file cv data extend'.split()):
31
+ name = name.replace('pyxllib.' + x, f'{i:02}')
32
+ for i, x in enumerate('pyxllib pyxlpr xlproject'.split()):
33
+ name = name.replace(x, f'~{i:02}')
34
+ for i, x in enumerate('newbie pupil specialist expert'.split()):
35
+ name = name.replace('.' + x, f'{i:02}')
36
+
37
+ # 忽略大小写
38
+ return [name.lower(), line.startswith('import')]
39
+
40
+ def sort_part(m):
41
+ parts = PyNestEnv(m.group()).imports().strings()
42
+ parts = [p.rstrip() + '\n' for p in parts]
43
+ parts.sort(key=cmp)
44
+ return ''.join(parts)
45
+
46
+ res = PyNestEnv(s).imports().sub(sort_part, adjacent=True) # 需要邻接,分块处理
47
+ return res
@@ -1,8 +1,8 @@
1
- #!/usr/bin/env python3
2
- # -*- coding: utf-8 -*-
3
- # @Author : 陈坤泽
4
- # @Email : 877362867@qq.com
5
- # @Date : 2021/06/06 17:56
6
-
7
- from pyxllib.text.specialist.common import *
8
- from pyxllib.text.specialist.ptag import *
1
+ #!/usr/bin/env python3
2
+ # -*- coding: utf-8 -*-
3
+ # @Author : 陈坤泽
4
+ # @Email : 877362867@qq.com
5
+ # @Date : 2021/06/06 17:56
6
+
7
+ from pyxllib.text.specialist.common import *
8
+ from pyxllib.text.specialist.ptag import *
@@ -1,112 +1,112 @@
1
- #!/usr/bin/env python3
2
- # -*- coding: utf-8 -*-
3
- # @Author : 陈坤泽
4
- # @Email : 877362867@qq.com
5
- # @Date : 2021/06/06 17:34
6
-
7
- import re
8
- import sys
9
- import textwrap
10
-
11
- from bs4 import BeautifulSoup
12
- import pandas as pd
13
- import requests
14
-
15
- from pyxllib.prog.newbie import len_in_dim2
16
- from pyxllib.prog.pupil import check_install_package
17
- from pyxllib.prog.specialist import dataframe_str
18
- from pyxllib.text.pupil import ContentLine
19
- from pyxllib.file.specialist import get_encoding, File
20
-
21
-
22
- def regularcheck(pattern, string, flags=0):
23
- arr = []
24
- cl = ContentLine(string)
25
- for i, m in enumerate(re.finditer(pattern, string, flags)):
26
- ss = map(lambda x: textwrap.shorten(x, 200), m.groups())
27
- arr.append([i + 1, cl.in_line(m.start(0)), *ss])
28
- tablehead = ['行号'] + list(map(lambda x: f'第{x}组', range(len_in_dim2(arr) - 2)))
29
- df = pd.DataFrame.from_records(arr, columns=tablehead)
30
- res = f'正则模式:{pattern},匹配结果:\n' + dataframe_str(df)
31
- return res
32
-
33
-
34
- def readtext(filename, encoding=None):
35
- """读取普通的文本文件
36
- 会根据tex、py文件情况指定默认编码
37
- """
38
- try:
39
- with open(filename, 'rb') as f: # 以二进制读取文件,注意二进制没有\r\n参数
40
- bstr = f.read()
41
- except FileNotFoundError:
42
- return None
43
-
44
- if not encoding:
45
- encoding = get_encoding(bstr)
46
- s = bstr.decode(encoding=encoding, errors='ignore')
47
- if '\r' in s: # 注意这个问题跟gb2312和gbk是独立的,用gbk编码也要做这个处理
48
- s = s.replace('\r\n', '\n') # 如果用\r\n作为换行符会有一些意外不好处理
49
- return s
50
-
51
-
52
- def ensure_content(ob=None, encoding=None):
53
- """
54
- :param ob:
55
- 未输入:从控制台获取文本
56
- 存在的文件名:读取文件的内容返回
57
- tex、py、
58
- docx、doc
59
- pdf
60
- 有read可调用成员方法:返回f.read()
61
- 其他字符串:返回原值
62
- :param encoding: 强制指定编码
63
- """
64
- # TODO: 如果输入的是一个文件指针,也能调用f.read()返回所有内容
65
- # TODO: 增加鲁棒性判断,如果输入的不是字符串类型也要有出错判断
66
- if ob is None:
67
- return sys.stdin.read() # 注意输入是按 Ctrl + D 结束
68
- elif File(ob): # 如果存在这样的文件,那就读取文件内容(bug点:如果输入是目录名会PermissionError)
69
- if ob.endswith('.docx'): # 这里还要再扩展pdf、doc文件的读取
70
- # 安装详见: https://blog.csdn.net/code4101/article/details/79328636
71
- check_install_package('textract')
72
- text = textract.process(ob)
73
- return text.decode('utf8', errors='ignore')
74
- elif ob.endswith('.doc'):
75
- raise NotImplementedError
76
- elif ob.endswith('.pdf'):
77
- raise NotImplementedError
78
- else: # 按照普通的文本文件读取内容
79
- return readtext(ob, encoding)
80
- else: # 判断不了的情况,也认为是字符串
81
- return ob
82
-
83
-
84
- def file_lastlines(fn, n):
85
- """获得一个文件最后的几行内容
86
- 参考资料: https://stackoverflow.com/questions/136168/get-last-n-lines-of-a-file-with-python-similar-to-tail
87
-
88
- >> s = FileLastLine('book.log', 1)
89
- 'Output written on book.dvi (2 pages, 7812 bytes).'
90
- """
91
- f = ensure_content(fn)
92
- assert n >= 0
93
- pos, lines = n + 1, []
94
- while len(lines) <= n:
95
- try:
96
- f.seek(-pos, 2)
97
- except IOError:
98
- f.seek(0)
99
- break
100
- finally:
101
- lines = list(f)
102
- pos *= 2
103
- f.close()
104
- return ''.join(lines[-n:])
105
-
106
-
107
- def readurl(url):
108
- """从url读取文本"""
109
- r = requests.get(url)
110
- soup = BeautifulSoup(r.text, 'lxml')
111
- s = soup.get_text()
112
- return s
1
+ #!/usr/bin/env python3
2
+ # -*- coding: utf-8 -*-
3
+ # @Author : 陈坤泽
4
+ # @Email : 877362867@qq.com
5
+ # @Date : 2021/06/06 17:34
6
+
7
+ import re
8
+ import sys
9
+ import textwrap
10
+
11
+ from bs4 import BeautifulSoup
12
+ import pandas as pd
13
+ import requests
14
+
15
+ from pyxllib.prog.newbie import len_in_dim2
16
+ from pyxllib.prog.pupil import check_install_package
17
+ from pyxllib.prog.specialist import dataframe_str
18
+ from pyxllib.text.pupil import ContentLine
19
+ from pyxllib.file.specialist import get_encoding, File
20
+
21
+
22
+ def regularcheck(pattern, string, flags=0):
23
+ arr = []
24
+ cl = ContentLine(string)
25
+ for i, m in enumerate(re.finditer(pattern, string, flags)):
26
+ ss = map(lambda x: textwrap.shorten(x, 200), m.groups())
27
+ arr.append([i + 1, cl.in_line(m.start(0)), *ss])
28
+ tablehead = ['行号'] + list(map(lambda x: f'第{x}组', range(len_in_dim2(arr) - 2)))
29
+ df = pd.DataFrame.from_records(arr, columns=tablehead)
30
+ res = f'正则模式:{pattern},匹配结果:\n' + dataframe_str(df)
31
+ return res
32
+
33
+
34
+ def readtext(filename, encoding=None):
35
+ """读取普通的文本文件
36
+ 会根据tex、py文件情况指定默认编码
37
+ """
38
+ try:
39
+ with open(filename, 'rb') as f: # 以二进制读取文件,注意二进制没有\r\n参数
40
+ bstr = f.read()
41
+ except FileNotFoundError:
42
+ return None
43
+
44
+ if not encoding:
45
+ encoding = get_encoding(bstr)
46
+ s = bstr.decode(encoding=encoding, errors='ignore')
47
+ if '\r' in s: # 注意这个问题跟gb2312和gbk是独立的,用gbk编码也要做这个处理
48
+ s = s.replace('\r\n', '\n') # 如果用\r\n作为换行符会有一些意外不好处理
49
+ return s
50
+
51
+
52
+ def ensure_content(ob=None, encoding=None):
53
+ """
54
+ :param ob:
55
+ 未输入:从控制台获取文本
56
+ 存在的文件名:读取文件的内容返回
57
+ tex、py、
58
+ docx、doc
59
+ pdf
60
+ 有read可调用成员方法:返回f.read()
61
+ 其他字符串:返回原值
62
+ :param encoding: 强制指定编码
63
+ """
64
+ # TODO: 如果输入的是一个文件指针,也能调用f.read()返回所有内容
65
+ # TODO: 增加鲁棒性判断,如果输入的不是字符串类型也要有出错判断
66
+ if ob is None:
67
+ return sys.stdin.read() # 注意输入是按 Ctrl + D 结束
68
+ elif File(ob): # 如果存在这样的文件,那就读取文件内容(bug点:如果输入是目录名会PermissionError)
69
+ if ob.endswith('.docx'): # 这里还要再扩展pdf、doc文件的读取
70
+ # 安装详见: https://blog.csdn.net/code4101/article/details/79328636
71
+ check_install_package('textract')
72
+ text = textract.process(ob)
73
+ return text.decode('utf8', errors='ignore')
74
+ elif ob.endswith('.doc'):
75
+ raise NotImplementedError
76
+ elif ob.endswith('.pdf'):
77
+ raise NotImplementedError
78
+ else: # 按照普通的文本文件读取内容
79
+ return readtext(ob, encoding)
80
+ else: # 判断不了的情况,也认为是字符串
81
+ return ob
82
+
83
+
84
+ def file_lastlines(fn, n):
85
+ """获得一个文件最后的几行内容
86
+ 参考资料: https://stackoverflow.com/questions/136168/get-last-n-lines-of-a-file-with-python-similar-to-tail
87
+
88
+ >> s = FileLastLine('book.log', 1)
89
+ 'Output written on book.dvi (2 pages, 7812 bytes).'
90
+ """
91
+ f = ensure_content(fn)
92
+ assert n >= 0
93
+ pos, lines = n + 1, []
94
+ while len(lines) <= n:
95
+ try:
96
+ f.seek(-pos, 2)
97
+ except IOError:
98
+ f.seek(0)
99
+ break
100
+ finally:
101
+ lines = list(f)
102
+ pos *= 2
103
+ f.close()
104
+ return ''.join(lines[-n:])
105
+
106
+
107
+ def readurl(url):
108
+ """从url读取文本"""
109
+ r = requests.get(url)
110
+ soup = BeautifulSoup(r.text, 'lxml')
111
+ s = soup.get_text()
112
+ return s