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
@@ -1,158 +1,158 @@
1
- #!/usr/bin/env python3
2
- # -*- coding: utf-8 -*-
3
- # @Author : 陈坤泽
4
- # @Email : 877362867@qq.com
5
- # @Date : 2021/10/08 22:26
6
-
7
- import re
8
-
9
- from pyxllib.prog.specialist import browser
10
- from pyxllib.text.pupil import grp_bracket, continuous_zero
11
-
12
-
13
- class TexTabular:
14
- @classmethod
15
- def parse_multirow(cls, s, brace_text_only=True):
16
- r"""
17
-
18
- :param brace_text_only: 只取花括号里面的内容
19
- 如果为False,会把multirow外部的内容做拼接
20
-
21
- multirow 和 multicolumn 的不同是,第1、2个花括号后面可以有可选参数。
22
- 第2个花括号如果内容是*,可以省略。
23
- 两个[]的内容先省略,不做分析处理
24
-
25
- 注意:这里会取出前后缀内容!业务需要,防止bug,不过这种概率很小
26
-
27
- >>> TexTabular.parse_multirow(r'\multirow{2}*{特点}')
28
- (2, None, '*', None, '特点')
29
- >>> TexTabular.parse_multirow(r'\multirow{2}{*}{特点}')
30
- (2, None, '*', None, '特点')
31
- >>> TexTabular.parse_multirow(r'aa\multirow{2}[bla1]{*}[bla2]{特点}bb', brace_text_only=False)
32
- (2, 'bla1', '*', 'bla2', 'aa特点bb')
33
-
34
- TODO multirow第一个数字是可以负值的,代表向上合并单元格数,
35
- """
36
- square = r'(?:\[(.*?)\])?' # 可选参数
37
- m = re.search(r'\\multirow' + grp_bracket(3, inner=True) + square +
38
- r'(?:{(.*?)}|(\*))' + square + grp_bracket(5, inner=True), s)
39
- if not m: return None
40
- n, bigstructs, width1, width2, fixup, text = m.groups()
41
- width = width1 or width2
42
- if not brace_text_only: text = s[:m.start()] + text + s[m.end():]
43
- # if re.match(r'\d+$', text): text = int(text) # 如果可以,直接识别为数字
44
-
45
- n = int(n)
46
- if -1 <= n <= 1:
47
- n = 1
48
- elif n > 1:
49
- pass
50
- else:
51
- raise ValueError(f'{s} 不支持解析multirow第一个值为负数,向上合并单元格的情况')
52
-
53
- return n, bigstructs, width, fixup, text
54
-
55
- @classmethod
56
- def parse_multicolumn(cls, s):
57
- r"""找出s中第一次出现的满足模式的multicolumn,返回3个关键值
58
-
59
- :returns:
60
- 第1个参数是该合并单元格的尺寸,固定格式: (行数, 列数),只有一行是也会写'1'
61
-
62
- >>> TexTabular.parse_multicolumn(r'\multicolumn{2}{|c|}{aa\multirow{3}*{特点}bb}')
63
- ((3, 2), '|c|', 'aa特点bb')
64
- """
65
- # 1 基本的模式匹配抓取
66
- m = re.search(r'\\multicolumn' + grp_bracket(3, inner=True) * 2
67
- + grp_bracket(5, inner=True), s) # 最后层多套下,我怕不够用
68
- if not m: return None
69
-
70
- # 2 取出参数值
71
- m, col_align, text = m.groups()
72
- m = int(m)
73
-
74
- # 3 如果有 multirow
75
- if 'multirow' in text:
76
- n, bigstructs, width, fixup, text = cls.parse_multirow(text, brace_text_only=False)
77
- else:
78
- n = 1
79
- # if isinstance(text, str) and re.match(r'\d+$', text): text = int(text) # 如果可以,直接识别为数字
80
- return (n, m), col_align, text
81
-
82
- @classmethod
83
- def parse_align(cls, s):
84
- r"""解析latex表头的列对齐格式
85
-
86
- latex表头的规则很复杂,这里目前只处理一些较常用的功能点
87
-
88
- :param s: 内容文本
89
- :return: 不考虑竖线和一些高级对齐格式,暂时返回一个str
90
- 长度是表格列数,每个元素是一个字母存储对齐信息(后续可以扩展更细致的对齐格式信息)
91
-
92
- >>> TexTabular.parse_align('{|c|c|c|c|c|c|c|c|c<{}|c|}')
93
- 'cccccccccc'
94
- >>> TexTabular.parse_align('{|c|w{6em}|w{23mm}|w{47mm}|w{22mm}|}')
95
- 'cwwww'
96
- >>> TexTabular.parse_align('cc*{8}{l}')
97
- 'ccllllllll'
98
- >>> TexTabular.parse_align('|c|')
99
- 'c'
100
- >>> TexTabular.parse_align('|c|*{2}{m{38mm}<{\\centering}|}')
101
- 'cmm'
102
- """
103
- # 展开 *{n}{列格式} 模式
104
- s = re.sub(r'\*(\d+)', r'*{\1}', s) # 给*数字加上花括号,不然我的匹配会错
105
- s = re.sub(r'\*{(\d+)}' + grp_bracket(3, inner=True), lambda m: m.group(2) * int(m.group(1)), s)
106
- # 删除其他干扰字符
107
- if s[0] == '{' and s[-1] == '}': s = s[1:-1] # 去掉头尾 { }
108
- s = re.sub(r'{.*?}', '', s)
109
- for char in '|<>!':
110
- s = s.replace(char, '')
111
- return s
112
-
113
- @classmethod
114
- def create_cline(cls, merge_count):
115
- r"""
116
- :param merge_count: 一个长度等于表格列数的list,第i位的值存储了第i列累计到当前被合并的格子数
117
- 假设一个3*4的表格,第1、3、4列正常,第2列被合并了
118
- 那么遍历到第二行时,merge_count为 [0, 2, 0, 0]
119
- 遍历到第三行时,merge_count 为 [0, 1, 0, 0]
120
- :return:
121
-
122
- >>> TexTabular.create_cline([0, 1, 0, 0])
123
- '\\cline{1-1} \\cline{3-4}'
124
- """
125
-
126
- s = ''.join([('1' if v else '0') for v in merge_count])
127
- if s.count('1') == 0: return '\\hline' # 没有间断,直接用hline命令
128
-
129
- spans = continuous_zero(s) # 注意返回的区间是从0开始编号,左闭右开的
130
- li = [f'\\cline{{{span[0] + 1}-{span[1]}}}' for span in spans]
131
- return ' '.join(li)
132
-
133
- @classmethod
134
- def create_formats(cls, format_count):
135
- """ 获得latex表头格式 """
136
-
137
- def count(s):
138
- """列对齐格式统计,返回最终去用的对齐格式"""
139
- if not s: return 'l' # 默认左对齐
140
- l, c, r = s.count('l'), s.count('c'), s.count('r')
141
- if l >= c and l >= r:
142
- return 'l'
143
- elif c >= l and c >= r:
144
- return 'c'
145
- else:
146
- return 'r'
147
-
148
- formats = [count(x) for x in format_count]
149
- return '{|' + '|'.join(formats) + '|}'
150
-
151
-
152
- def browser_latex(text='请输入...'):
153
- from html import escape
154
- from pyxllib.text.xmllib import get_jinja_template
155
-
156
- # 致谢:感谢奕本在晓波做的工具基础上,做出的这个简洁版的latex渲染器
157
- content = get_jinja_template('latex_editor.html').render(text=escape(text))
158
- browser.html(content)
1
+ #!/usr/bin/env python3
2
+ # -*- coding: utf-8 -*-
3
+ # @Author : 陈坤泽
4
+ # @Email : 877362867@qq.com
5
+ # @Date : 2021/10/08 22:26
6
+
7
+ import re
8
+
9
+ from pyxllib.prog.specialist import browser
10
+ from pyxllib.text.pupil import grp_bracket, continuous_zero
11
+
12
+
13
+ class TexTabular:
14
+ @classmethod
15
+ def parse_multirow(cls, s, brace_text_only=True):
16
+ r"""
17
+
18
+ :param brace_text_only: 只取花括号里面的内容
19
+ 如果为False,会把multirow外部的内容做拼接
20
+
21
+ multirow 和 multicolumn 的不同是,第1、2个花括号后面可以有可选参数。
22
+ 第2个花括号如果内容是*,可以省略。
23
+ 两个[]的内容先省略,不做分析处理
24
+
25
+ 注意:这里会取出前后缀内容!业务需要,防止bug,不过这种概率很小
26
+
27
+ >>> TexTabular.parse_multirow(r'\multirow{2}*{特点}')
28
+ (2, None, '*', None, '特点')
29
+ >>> TexTabular.parse_multirow(r'\multirow{2}{*}{特点}')
30
+ (2, None, '*', None, '特点')
31
+ >>> TexTabular.parse_multirow(r'aa\multirow{2}[bla1]{*}[bla2]{特点}bb', brace_text_only=False)
32
+ (2, 'bla1', '*', 'bla2', 'aa特点bb')
33
+
34
+ TODO multirow第一个数字是可以负值的,代表向上合并单元格数,
35
+ """
36
+ square = r'(?:\[(.*?)\])?' # 可选参数
37
+ m = re.search(r'\\multirow' + grp_bracket(3, inner=True) + square +
38
+ r'(?:{(.*?)}|(\*))' + square + grp_bracket(5, inner=True), s)
39
+ if not m: return None
40
+ n, bigstructs, width1, width2, fixup, text = m.groups()
41
+ width = width1 or width2
42
+ if not brace_text_only: text = s[:m.start()] + text + s[m.end():]
43
+ # if re.match(r'\d+$', text): text = int(text) # 如果可以,直接识别为数字
44
+
45
+ n = int(n)
46
+ if -1 <= n <= 1:
47
+ n = 1
48
+ elif n > 1:
49
+ pass
50
+ else:
51
+ raise ValueError(f'{s} 不支持解析multirow第一个值为负数,向上合并单元格的情况')
52
+
53
+ return n, bigstructs, width, fixup, text
54
+
55
+ @classmethod
56
+ def parse_multicolumn(cls, s):
57
+ r"""找出s中第一次出现的满足模式的multicolumn,返回3个关键值
58
+
59
+ :returns:
60
+ 第1个参数是该合并单元格的尺寸,固定格式: (行数, 列数),只有一行是也会写'1'
61
+
62
+ >>> TexTabular.parse_multicolumn(r'\multicolumn{2}{|c|}{aa\multirow{3}*{特点}bb}')
63
+ ((3, 2), '|c|', 'aa特点bb')
64
+ """
65
+ # 1 基本的模式匹配抓取
66
+ m = re.search(r'\\multicolumn' + grp_bracket(3, inner=True) * 2
67
+ + grp_bracket(5, inner=True), s) # 最后层多套下,我怕不够用
68
+ if not m: return None
69
+
70
+ # 2 取出参数值
71
+ m, col_align, text = m.groups()
72
+ m = int(m)
73
+
74
+ # 3 如果有 multirow
75
+ if 'multirow' in text:
76
+ n, bigstructs, width, fixup, text = cls.parse_multirow(text, brace_text_only=False)
77
+ else:
78
+ n = 1
79
+ # if isinstance(text, str) and re.match(r'\d+$', text): text = int(text) # 如果可以,直接识别为数字
80
+ return (n, m), col_align, text
81
+
82
+ @classmethod
83
+ def parse_align(cls, s):
84
+ r"""解析latex表头的列对齐格式
85
+
86
+ latex表头的规则很复杂,这里目前只处理一些较常用的功能点
87
+
88
+ :param s: 内容文本
89
+ :return: 不考虑竖线和一些高级对齐格式,暂时返回一个str
90
+ 长度是表格列数,每个元素是一个字母存储对齐信息(后续可以扩展更细致的对齐格式信息)
91
+
92
+ >>> TexTabular.parse_align('{|c|c|c|c|c|c|c|c|c<{}|c|}')
93
+ 'cccccccccc'
94
+ >>> TexTabular.parse_align('{|c|w{6em}|w{23mm}|w{47mm}|w{22mm}|}')
95
+ 'cwwww'
96
+ >>> TexTabular.parse_align('cc*{8}{l}')
97
+ 'ccllllllll'
98
+ >>> TexTabular.parse_align('|c|')
99
+ 'c'
100
+ >>> TexTabular.parse_align('|c|*{2}{m{38mm}<{\\centering}|}')
101
+ 'cmm'
102
+ """
103
+ # 展开 *{n}{列格式} 模式
104
+ s = re.sub(r'\*(\d+)', r'*{\1}', s) # 给*数字加上花括号,不然我的匹配会错
105
+ s = re.sub(r'\*{(\d+)}' + grp_bracket(3, inner=True), lambda m: m.group(2) * int(m.group(1)), s)
106
+ # 删除其他干扰字符
107
+ if s[0] == '{' and s[-1] == '}': s = s[1:-1] # 去掉头尾 { }
108
+ s = re.sub(r'{.*?}', '', s)
109
+ for char in '|<>!':
110
+ s = s.replace(char, '')
111
+ return s
112
+
113
+ @classmethod
114
+ def create_cline(cls, merge_count):
115
+ r"""
116
+ :param merge_count: 一个长度等于表格列数的list,第i位的值存储了第i列累计到当前被合并的格子数
117
+ 假设一个3*4的表格,第1、3、4列正常,第2列被合并了
118
+ 那么遍历到第二行时,merge_count为 [0, 2, 0, 0]
119
+ 遍历到第三行时,merge_count 为 [0, 1, 0, 0]
120
+ :return:
121
+
122
+ >>> TexTabular.create_cline([0, 1, 0, 0])
123
+ '\\cline{1-1} \\cline{3-4}'
124
+ """
125
+
126
+ s = ''.join([('1' if v else '0') for v in merge_count])
127
+ if s.count('1') == 0: return '\\hline' # 没有间断,直接用hline命令
128
+
129
+ spans = continuous_zero(s) # 注意返回的区间是从0开始编号,左闭右开的
130
+ li = [f'\\cline{{{span[0] + 1}-{span[1]}}}' for span in spans]
131
+ return ' '.join(li)
132
+
133
+ @classmethod
134
+ def create_formats(cls, format_count):
135
+ """ 获得latex表头格式 """
136
+
137
+ def count(s):
138
+ """列对齐格式统计,返回最终去用的对齐格式"""
139
+ if not s: return 'l' # 默认左对齐
140
+ l, c, r = s.count('l'), s.count('c'), s.count('r')
141
+ if l >= c and l >= r:
142
+ return 'l'
143
+ elif c >= l and c >= r:
144
+ return 'c'
145
+ else:
146
+ return 'r'
147
+
148
+ formats = [count(x) for x in format_count]
149
+ return '{|' + '|'.join(formats) + '|}'
150
+
151
+
152
+ def browser_latex(text='请输入...'):
153
+ from html import escape
154
+ from pyxllib.text.xmllib import get_jinja_template
155
+
156
+ # 致谢:感谢奕本在晓波做的工具基础上,做出的这个简洁版的latex渲染器
157
+ content = get_jinja_template('latex_editor.html').render(text=escape(text))
158
+ browser.html(content)