pyxllib 0.3.197__py3-none-any.whl → 0.3.200__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.
- pyxllib/__init__.py +21 -21
- pyxllib/algo/__init__.py +8 -8
- pyxllib/algo/disjoint.py +54 -54
- pyxllib/algo/geo.py +541 -541
- pyxllib/algo/intervals.py +964 -964
- pyxllib/algo/matcher.py +389 -389
- pyxllib/algo/newbie.py +166 -166
- pyxllib/algo/pupil.py +629 -629
- pyxllib/algo/shapelylib.py +67 -67
- pyxllib/algo/specialist.py +241 -241
- pyxllib/algo/stat.py +494 -494
- pyxllib/algo/treelib.py +149 -149
- pyxllib/algo/unitlib.py +66 -66
- pyxllib/autogui/__init__.py +5 -5
- pyxllib/autogui/activewin.py +246 -246
- pyxllib/autogui/all.py +9 -9
- pyxllib/autogui/autogui.py +852 -852
- pyxllib/autogui/uiautolib.py +362 -362
- pyxllib/autogui/virtualkey.py +102 -102
- pyxllib/autogui/wechat.py +827 -827
- pyxllib/autogui/wechat_msg.py +421 -421
- pyxllib/autogui/wxautolib.py +84 -84
- pyxllib/cv/__init__.py +5 -5
- pyxllib/cv/expert.py +267 -267
- pyxllib/cv/imfile.py +159 -159
- pyxllib/cv/imhash.py +39 -39
- pyxllib/cv/pupil.py +9 -9
- pyxllib/cv/rgbfmt.py +1525 -1525
- pyxllib/cv/slidercaptcha.py +137 -137
- pyxllib/cv/trackbartools.py +251 -251
- pyxllib/cv/xlcvlib.py +1040 -1040
- pyxllib/cv/xlpillib.py +423 -423
- pyxllib/data/echarts.py +240 -240
- pyxllib/data/jsonlib.py +89 -89
- pyxllib/data/oss.py +72 -72
- pyxllib/data/pglib.py +1127 -1127
- pyxllib/data/sqlite.py +568 -568
- pyxllib/data/sqllib.py +297 -297
- pyxllib/ext/JLineViewer.py +505 -505
- pyxllib/ext/__init__.py +6 -6
- pyxllib/ext/demolib.py +246 -246
- pyxllib/ext/drissionlib.py +277 -277
- pyxllib/ext/kq5034lib.py +12 -12
- pyxllib/ext/old.py +663 -663
- pyxllib/ext/qt.py +449 -449
- pyxllib/ext/robustprocfile.py +497 -497
- pyxllib/ext/seleniumlib.py +76 -76
- pyxllib/ext/tk.py +173 -173
- pyxllib/ext/unixlib.py +827 -827
- pyxllib/ext/utools.py +351 -351
- pyxllib/ext/webhook.py +124 -119
- pyxllib/ext/win32lib.py +40 -40
- pyxllib/ext/wjxlib.py +88 -88
- pyxllib/ext/wpsapi.py +124 -124
- pyxllib/ext/xlwork.py +9 -9
- pyxllib/ext/yuquelib.py +1105 -1105
- pyxllib/file/__init__.py +17 -17
- pyxllib/file/docxlib.py +761 -761
- pyxllib/file/gitlib.py +309 -309
- pyxllib/file/libreoffice.py +165 -165
- pyxllib/file/movielib.py +148 -148
- pyxllib/file/newbie.py +10 -10
- pyxllib/file/onenotelib.py +1469 -1469
- pyxllib/file/packlib/__init__.py +330 -330
- pyxllib/file/packlib/zipfile.py +2441 -2441
- pyxllib/file/pdflib.py +426 -426
- pyxllib/file/pupil.py +185 -185
- pyxllib/file/specialist/__init__.py +685 -685
- pyxllib/file/specialist/dirlib.py +799 -799
- pyxllib/file/specialist/download.py +193 -193
- pyxllib/file/specialist/filelib.py +2829 -2829
- pyxllib/file/xlsxlib.py +3131 -3131
- pyxllib/file/xlsyncfile.py +341 -341
- pyxllib/prog/__init__.py +5 -5
- pyxllib/prog/cachetools.py +64 -64
- pyxllib/prog/deprecatedlib.py +233 -233
- pyxllib/prog/filelock.py +42 -42
- pyxllib/prog/ipyexec.py +253 -253
- pyxllib/prog/multiprogs.py +940 -940
- pyxllib/prog/newbie.py +451 -451
- pyxllib/prog/pupil.py +1197 -1197
- pyxllib/prog/sitepackages.py +33 -33
- pyxllib/prog/specialist/__init__.py +391 -391
- pyxllib/prog/specialist/bc.py +203 -203
- pyxllib/prog/specialist/browser.py +497 -497
- pyxllib/prog/specialist/common.py +347 -347
- pyxllib/prog/specialist/datetime.py +198 -198
- pyxllib/prog/specialist/tictoc.py +240 -240
- pyxllib/prog/specialist/xllog.py +180 -180
- pyxllib/prog/xlosenv.py +108 -108
- pyxllib/stdlib/__init__.py +17 -17
- pyxllib/stdlib/tablepyxl/__init__.py +10 -10
- pyxllib/stdlib/tablepyxl/style.py +303 -303
- pyxllib/stdlib/tablepyxl/tablepyxl.py +130 -130
- pyxllib/text/__init__.py +8 -8
- pyxllib/text/ahocorasick.py +39 -39
- pyxllib/text/airscript.js +744 -744
- pyxllib/text/charclasslib.py +121 -121
- pyxllib/text/jiebalib.py +267 -267
- pyxllib/text/jinjalib.py +32 -32
- pyxllib/text/jsa_ai_prompt.md +271 -271
- pyxllib/text/jscode.py +922 -922
- pyxllib/text/latex/__init__.py +158 -158
- pyxllib/text/levenshtein.py +303 -303
- pyxllib/text/nestenv.py +1215 -1215
- pyxllib/text/newbie.py +300 -300
- pyxllib/text/pupil/__init__.py +8 -8
- pyxllib/text/pupil/common.py +1121 -1121
- pyxllib/text/pupil/xlalign.py +326 -326
- pyxllib/text/pycode.py +47 -47
- pyxllib/text/specialist/__init__.py +8 -8
- pyxllib/text/specialist/common.py +112 -112
- pyxllib/text/specialist/ptag.py +186 -186
- pyxllib/text/spellchecker.py +172 -172
- pyxllib/text/templates/echart_base.html +10 -10
- pyxllib/text/templates/highlight_code.html +16 -16
- pyxllib/text/templates/latex_editor.html +102 -102
- pyxllib/text/vbacode.py +17 -17
- pyxllib/text/xmllib.py +747 -747
- pyxllib/xl.py +42 -39
- pyxllib/xlcv.py +17 -17
- {pyxllib-0.3.197.dist-info → pyxllib-0.3.200.dist-info}/METADATA +1 -1
- pyxllib-0.3.200.dist-info/RECORD +126 -0
- {pyxllib-0.3.197.dist-info → pyxllib-0.3.200.dist-info}/licenses/LICENSE +190 -190
- pyxllib-0.3.197.dist-info/RECORD +0 -126
- {pyxllib-0.3.197.dist-info → pyxllib-0.3.200.dist-info}/WHEEL +0 -0
pyxllib/text/specialist/ptag.py
CHANGED
@@ -1,186 +1,186 @@
|
|
1
|
-
#!/usr/bin/env python3
|
2
|
-
# -*- coding: utf-8 -*-
|
3
|
-
# @Author : 陈坤泽
|
4
|
-
# @Email : 877362867@qq.com
|
5
|
-
# @Date : 2021/06/06 17:22
|
6
|
-
|
7
|
-
""" 百分注格式处理 """
|
8
|
-
|
9
|
-
import re
|
10
|
-
|
11
|
-
import bs4
|
12
|
-
from bs4 import BeautifulSoup
|
13
|
-
|
14
|
-
from pyxllib.prog.pupil import dprint
|
15
|
-
from pyxllib.text.pupil import grp_bracket
|
16
|
-
|
17
|
-
|
18
|
-
def gettag_name(tagstr):
|
19
|
-
"""
|
20
|
-
>>> gettag_name('%<topic type=danxuan description=单选题>')
|
21
|
-
'topic'
|
22
|
-
>>> gettag_name('</topic>')
|
23
|
-
'topic'
|
24
|
-
"""
|
25
|
-
m = re.search(r'</?([a-zA-Z_]+)', tagstr)
|
26
|
-
if m:
|
27
|
-
return m.group(1)
|
28
|
-
else:
|
29
|
-
return None
|
30
|
-
|
31
|
-
|
32
|
-
def settag_name(tagstr, *, new_name=None, switch=None):
|
33
|
-
"""设置标签名称,或者将标签类型设为close类型
|
34
|
-
|
35
|
-
>>> settag_name('%<topic type=danxuan description=单选题>', new_name='mdzz')
|
36
|
-
'%<mdzz type=danxuan description=单选题>'
|
37
|
-
>>> settag_name('<topic type=danxuan description=单选题>', switch=False)
|
38
|
-
'</topic>'
|
39
|
-
"""
|
40
|
-
if new_name: # 是否设置新名称
|
41
|
-
tagstr = re.sub(r'(</?)([a-zA-Z_]+)', lambda m: m.group(1) + new_name, tagstr)
|
42
|
-
|
43
|
-
if switch is not None: # 是否设置标签开关
|
44
|
-
if switch: # 将标签改为开
|
45
|
-
tagstr = tagstr.replace('</', '<')
|
46
|
-
else: # 将标签改为关
|
47
|
-
name = gettag_name(tagstr)
|
48
|
-
res = f'</{name}>' # 会删除所有attr属性
|
49
|
-
tagstr = '%' + res if '%<' in tagstr else res
|
50
|
-
|
51
|
-
return tagstr
|
52
|
-
|
53
|
-
|
54
|
-
def gettag_attr(tagstr, attrname):
|
55
|
-
r"""tagstr是一个标签字符串,attrname是要索引的名字
|
56
|
-
返回属性值,如果不存在该属性则返回None
|
57
|
-
|
58
|
-
>>> gettag_attr('%<topic type=danxuan description=单选题> 123\n<a b=c></a>', 'type')
|
59
|
-
'danxuan'
|
60
|
-
>>> gettag_attr('%<topic type="dan xu an" description=单选题>', 'type')
|
61
|
-
'dan xu an'
|
62
|
-
>>> gettag_attr("%<topic type='dan xu an' description=单选题>", 'type')
|
63
|
-
'dan xu an'
|
64
|
-
>>> gettag_attr('%<topic type=dan xu an description=单选题>', 'description')
|
65
|
-
'单选题'
|
66
|
-
>>> gettag_attr('%<topic type=dan xu an description=单选题>', 'type')
|
67
|
-
'dan'
|
68
|
-
>>> gettag_attr('%<topic type=danxuan description=单选题 >', 'description')
|
69
|
-
'单选题'
|
70
|
-
>>> gettag_attr('%<topic type=danxuan description=单选题 >', 'description123') is None
|
71
|
-
True
|
72
|
-
"""
|
73
|
-
soup = BeautifulSoup(tagstr, 'lxml')
|
74
|
-
try:
|
75
|
-
for tag in soup.p.contents:
|
76
|
-
if isinstance(tag, bs4.Tag):
|
77
|
-
return tag.get(attrname, None)
|
78
|
-
except AttributeError:
|
79
|
-
dprint(tagstr)
|
80
|
-
return None
|
81
|
-
|
82
|
-
|
83
|
-
def settag_attr(tagstr, attrname, target_value):
|
84
|
-
r"""tagstr是一个标签字符串,attrname是要索引的名字
|
85
|
-
重设该属性的值,设置成功则返回新的tagstr;否则返回原始值
|
86
|
-
|
87
|
-
close类型不能用这个命令,用了的话不进行任何处理,直接返回
|
88
|
-
|
89
|
-
>>> settag_attr('%<topic type=danxuan> 123\n<a></a>', 'type', 'tiankong')
|
90
|
-
'%<topic type="tiankong"> 123\n<a></a>'
|
91
|
-
>>> settag_attr('%<topic>', 'type', 'tiankong')
|
92
|
-
'%<topic type="tiankong">'
|
93
|
-
>>> settag_attr('</topic>', 'type', 'tiankong')
|
94
|
-
'</topic>'
|
95
|
-
>>> settag_attr('<seq value="1">', 'value', '练习1.2')
|
96
|
-
'<seq value="练习1.2">'
|
97
|
-
>>> settag_attr('<seq type=123 value=1>', 'type', '') # 删除attr操作
|
98
|
-
'<seq value=1>'
|
99
|
-
>>> settag_attr('<seq type=123 value=1>', 'value', '') # 删除attr操作
|
100
|
-
'<seq type=123>'
|
101
|
-
>>> settag_attr('<seq type=123 value=1>', 'haha', '') # 删除attr操作
|
102
|
-
'<seq type=123 value=1>'
|
103
|
-
"""
|
104
|
-
# 如果是close类型是不处理的
|
105
|
-
if tagstr.startswith('</'): return tagstr
|
106
|
-
|
107
|
-
# 预处理targetValue的值,删除空白
|
108
|
-
target_value = re.sub(r'\s', '', target_value)
|
109
|
-
r = re.compile(r'(<|\s)(' + attrname + r'=)(.+?)(\s+\w+=|\s*>)')
|
110
|
-
gs = r.search(tagstr)
|
111
|
-
if target_value:
|
112
|
-
if not gs: # 如果未找到则添加attr与value
|
113
|
-
n = tagstr.find('>')
|
114
|
-
return tagstr[:n] + ' ' + attrname + '="' + target_value + '"' + tagstr[n:]
|
115
|
-
else: # 如果找到则更改value
|
116
|
-
# TODO: 目前的替换值是直接放到正则式里了,这样会有很大的风险,后续看看能不能优化这个处理算法
|
117
|
-
return r.sub(r'\1\g<2>"' + target_value + r'"\4', tagstr)
|
118
|
-
else:
|
119
|
-
if gs:
|
120
|
-
return r.sub(r'\4', tagstr)
|
121
|
-
else:
|
122
|
-
return tagstr
|
123
|
-
|
124
|
-
|
125
|
-
def brieftexstr(s):
|
126
|
-
"""对比两段tex文本
|
127
|
-
"""
|
128
|
-
# 1 删除百分注
|
129
|
-
s = re.sub(r'%' + grp_bracket(2, '<', '>'), r'', s)
|
130
|
-
# 2 删除所有空白字符
|
131
|
-
# debuglib.dprint(debuglib.typename(s))
|
132
|
-
s = re.sub(r'\s+', '', s)
|
133
|
-
# 3 转小写字符
|
134
|
-
s = s.casefold()
|
135
|
-
return s
|
136
|
-
|
137
|
-
|
138
|
-
# 默认不建议开,编校如果用的多,可以在那边定义
|
139
|
-
# 定义常用的几种格式,并且只匹配抓取花括号里面的值,不要花括号本身
|
140
|
-
# SQUARE3 = r'\\[(' + grp_bracket(3, '[')[3:-3] + r')\\]'
|
141
|
-
# BRACE1 = '{(' + grp_bracket(1)[1:-1] + ')}'
|
142
|
-
# BRACE2 = '{(' + grp_bracket(2)[1:-1] + ')}'
|
143
|
-
# BRACE3 = '{(' + grp_bracket(3)[1:-1] + ')}'
|
144
|
-
# BRACE4 = '{(' + grp_bracket(4)[1:-1] + ')}'
|
145
|
-
# BRACE5 = '{(' + grp_bracket(5)[1:-1] + ')}'
|
146
|
-
r""" 使用示例
|
147
|
-
>> m = re.search(r'\\multicolumn' + BRACE3*3, r'\multicolumn{2}{|c|}{$2^{12}$个数}')
|
148
|
-
>> m.groups()
|
149
|
-
('2', '|c|', '$2^{12}$个数')
|
150
|
-
"""
|
151
|
-
|
152
|
-
|
153
|
-
def grp_topic(*, type_value=None):
|
154
|
-
"""定位topic
|
155
|
-
|
156
|
-
:param type_value: 设置题目类型(TODO: 功能尚未开发)
|
157
|
-
"""
|
158
|
-
s = r'%<topic.*?%</topic>' # 注意外部使用的re要开flags=re.DOTALL
|
159
|
-
return s
|
160
|
-
|
161
|
-
|
162
|
-
def grp_figure(cnt_groups=0, parpic=False):
|
163
|
-
r""" 生成跟图片匹配相关的表达式
|
164
|
-
|
165
|
-
D:\2017LaTeX\D招培试卷\高中地理,用过 \captionfig{3-3.eps}{图~3}
|
166
|
-
奕本从2018秋季教材开始使用多种图片格式
|
167
|
-
|
168
|
-
191224周二18:20 更新:匹配到的图片名不带花括号
|
169
|
-
"""
|
170
|
-
ibrace3 = grp_bracket(3, inner=True)
|
171
|
-
|
172
|
-
if cnt_groups == 0: # 不分组
|
173
|
-
s = r'\\(?:includegraphics|figt|figc|figr|fig).*?' + grp_bracket(3) # 注意第1组fig要放最后面
|
174
|
-
elif cnt_groups == 1: # 只分1组,那么只对图片括号内的内容分组
|
175
|
-
s = r'\\(?:includegraphics|figt|figc|figr|fig).*?' + ibrace3
|
176
|
-
elif cnt_groups == 2: # 只分2组,那么只对插图命令和图片分组
|
177
|
-
s = r'\\(includegraphics|figt|figc|figr|fig).*?' + ibrace3
|
178
|
-
elif cnt_groups == 3:
|
179
|
-
s = r'\\(includegraphics|figt|figc|figr|fig)(.*?)' + ibrace3
|
180
|
-
else:
|
181
|
-
s = None
|
182
|
-
|
183
|
-
if s and parpic:
|
184
|
-
s = r'{?\\parpic(?:\[.\])?{' + s + r'}*'
|
185
|
-
|
186
|
-
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 17:22
|
6
|
+
|
7
|
+
""" 百分注格式处理 """
|
8
|
+
|
9
|
+
import re
|
10
|
+
|
11
|
+
import bs4
|
12
|
+
from bs4 import BeautifulSoup
|
13
|
+
|
14
|
+
from pyxllib.prog.pupil import dprint
|
15
|
+
from pyxllib.text.pupil import grp_bracket
|
16
|
+
|
17
|
+
|
18
|
+
def gettag_name(tagstr):
|
19
|
+
"""
|
20
|
+
>>> gettag_name('%<topic type=danxuan description=单选题>')
|
21
|
+
'topic'
|
22
|
+
>>> gettag_name('</topic>')
|
23
|
+
'topic'
|
24
|
+
"""
|
25
|
+
m = re.search(r'</?([a-zA-Z_]+)', tagstr)
|
26
|
+
if m:
|
27
|
+
return m.group(1)
|
28
|
+
else:
|
29
|
+
return None
|
30
|
+
|
31
|
+
|
32
|
+
def settag_name(tagstr, *, new_name=None, switch=None):
|
33
|
+
"""设置标签名称,或者将标签类型设为close类型
|
34
|
+
|
35
|
+
>>> settag_name('%<topic type=danxuan description=单选题>', new_name='mdzz')
|
36
|
+
'%<mdzz type=danxuan description=单选题>'
|
37
|
+
>>> settag_name('<topic type=danxuan description=单选题>', switch=False)
|
38
|
+
'</topic>'
|
39
|
+
"""
|
40
|
+
if new_name: # 是否设置新名称
|
41
|
+
tagstr = re.sub(r'(</?)([a-zA-Z_]+)', lambda m: m.group(1) + new_name, tagstr)
|
42
|
+
|
43
|
+
if switch is not None: # 是否设置标签开关
|
44
|
+
if switch: # 将标签改为开
|
45
|
+
tagstr = tagstr.replace('</', '<')
|
46
|
+
else: # 将标签改为关
|
47
|
+
name = gettag_name(tagstr)
|
48
|
+
res = f'</{name}>' # 会删除所有attr属性
|
49
|
+
tagstr = '%' + res if '%<' in tagstr else res
|
50
|
+
|
51
|
+
return tagstr
|
52
|
+
|
53
|
+
|
54
|
+
def gettag_attr(tagstr, attrname):
|
55
|
+
r"""tagstr是一个标签字符串,attrname是要索引的名字
|
56
|
+
返回属性值,如果不存在该属性则返回None
|
57
|
+
|
58
|
+
>>> gettag_attr('%<topic type=danxuan description=单选题> 123\n<a b=c></a>', 'type')
|
59
|
+
'danxuan'
|
60
|
+
>>> gettag_attr('%<topic type="dan xu an" description=单选题>', 'type')
|
61
|
+
'dan xu an'
|
62
|
+
>>> gettag_attr("%<topic type='dan xu an' description=单选题>", 'type')
|
63
|
+
'dan xu an'
|
64
|
+
>>> gettag_attr('%<topic type=dan xu an description=单选题>', 'description')
|
65
|
+
'单选题'
|
66
|
+
>>> gettag_attr('%<topic type=dan xu an description=单选题>', 'type')
|
67
|
+
'dan'
|
68
|
+
>>> gettag_attr('%<topic type=danxuan description=单选题 >', 'description')
|
69
|
+
'单选题'
|
70
|
+
>>> gettag_attr('%<topic type=danxuan description=单选题 >', 'description123') is None
|
71
|
+
True
|
72
|
+
"""
|
73
|
+
soup = BeautifulSoup(tagstr, 'lxml')
|
74
|
+
try:
|
75
|
+
for tag in soup.p.contents:
|
76
|
+
if isinstance(tag, bs4.Tag):
|
77
|
+
return tag.get(attrname, None)
|
78
|
+
except AttributeError:
|
79
|
+
dprint(tagstr)
|
80
|
+
return None
|
81
|
+
|
82
|
+
|
83
|
+
def settag_attr(tagstr, attrname, target_value):
|
84
|
+
r"""tagstr是一个标签字符串,attrname是要索引的名字
|
85
|
+
重设该属性的值,设置成功则返回新的tagstr;否则返回原始值
|
86
|
+
|
87
|
+
close类型不能用这个命令,用了的话不进行任何处理,直接返回
|
88
|
+
|
89
|
+
>>> settag_attr('%<topic type=danxuan> 123\n<a></a>', 'type', 'tiankong')
|
90
|
+
'%<topic type="tiankong"> 123\n<a></a>'
|
91
|
+
>>> settag_attr('%<topic>', 'type', 'tiankong')
|
92
|
+
'%<topic type="tiankong">'
|
93
|
+
>>> settag_attr('</topic>', 'type', 'tiankong')
|
94
|
+
'</topic>'
|
95
|
+
>>> settag_attr('<seq value="1">', 'value', '练习1.2')
|
96
|
+
'<seq value="练习1.2">'
|
97
|
+
>>> settag_attr('<seq type=123 value=1>', 'type', '') # 删除attr操作
|
98
|
+
'<seq value=1>'
|
99
|
+
>>> settag_attr('<seq type=123 value=1>', 'value', '') # 删除attr操作
|
100
|
+
'<seq type=123>'
|
101
|
+
>>> settag_attr('<seq type=123 value=1>', 'haha', '') # 删除attr操作
|
102
|
+
'<seq type=123 value=1>'
|
103
|
+
"""
|
104
|
+
# 如果是close类型是不处理的
|
105
|
+
if tagstr.startswith('</'): return tagstr
|
106
|
+
|
107
|
+
# 预处理targetValue的值,删除空白
|
108
|
+
target_value = re.sub(r'\s', '', target_value)
|
109
|
+
r = re.compile(r'(<|\s)(' + attrname + r'=)(.+?)(\s+\w+=|\s*>)')
|
110
|
+
gs = r.search(tagstr)
|
111
|
+
if target_value:
|
112
|
+
if not gs: # 如果未找到则添加attr与value
|
113
|
+
n = tagstr.find('>')
|
114
|
+
return tagstr[:n] + ' ' + attrname + '="' + target_value + '"' + tagstr[n:]
|
115
|
+
else: # 如果找到则更改value
|
116
|
+
# TODO: 目前的替换值是直接放到正则式里了,这样会有很大的风险,后续看看能不能优化这个处理算法
|
117
|
+
return r.sub(r'\1\g<2>"' + target_value + r'"\4', tagstr)
|
118
|
+
else:
|
119
|
+
if gs:
|
120
|
+
return r.sub(r'\4', tagstr)
|
121
|
+
else:
|
122
|
+
return tagstr
|
123
|
+
|
124
|
+
|
125
|
+
def brieftexstr(s):
|
126
|
+
"""对比两段tex文本
|
127
|
+
"""
|
128
|
+
# 1 删除百分注
|
129
|
+
s = re.sub(r'%' + grp_bracket(2, '<', '>'), r'', s)
|
130
|
+
# 2 删除所有空白字符
|
131
|
+
# debuglib.dprint(debuglib.typename(s))
|
132
|
+
s = re.sub(r'\s+', '', s)
|
133
|
+
# 3 转小写字符
|
134
|
+
s = s.casefold()
|
135
|
+
return s
|
136
|
+
|
137
|
+
|
138
|
+
# 默认不建议开,编校如果用的多,可以在那边定义
|
139
|
+
# 定义常用的几种格式,并且只匹配抓取花括号里面的值,不要花括号本身
|
140
|
+
# SQUARE3 = r'\\[(' + grp_bracket(3, '[')[3:-3] + r')\\]'
|
141
|
+
# BRACE1 = '{(' + grp_bracket(1)[1:-1] + ')}'
|
142
|
+
# BRACE2 = '{(' + grp_bracket(2)[1:-1] + ')}'
|
143
|
+
# BRACE3 = '{(' + grp_bracket(3)[1:-1] + ')}'
|
144
|
+
# BRACE4 = '{(' + grp_bracket(4)[1:-1] + ')}'
|
145
|
+
# BRACE5 = '{(' + grp_bracket(5)[1:-1] + ')}'
|
146
|
+
r""" 使用示例
|
147
|
+
>> m = re.search(r'\\multicolumn' + BRACE3*3, r'\multicolumn{2}{|c|}{$2^{12}$个数}')
|
148
|
+
>> m.groups()
|
149
|
+
('2', '|c|', '$2^{12}$个数')
|
150
|
+
"""
|
151
|
+
|
152
|
+
|
153
|
+
def grp_topic(*, type_value=None):
|
154
|
+
"""定位topic
|
155
|
+
|
156
|
+
:param type_value: 设置题目类型(TODO: 功能尚未开发)
|
157
|
+
"""
|
158
|
+
s = r'%<topic.*?%</topic>' # 注意外部使用的re要开flags=re.DOTALL
|
159
|
+
return s
|
160
|
+
|
161
|
+
|
162
|
+
def grp_figure(cnt_groups=0, parpic=False):
|
163
|
+
r""" 生成跟图片匹配相关的表达式
|
164
|
+
|
165
|
+
D:\2017LaTeX\D招培试卷\高中地理,用过 \captionfig{3-3.eps}{图~3}
|
166
|
+
奕本从2018秋季教材开始使用多种图片格式
|
167
|
+
|
168
|
+
191224周二18:20 更新:匹配到的图片名不带花括号
|
169
|
+
"""
|
170
|
+
ibrace3 = grp_bracket(3, inner=True)
|
171
|
+
|
172
|
+
if cnt_groups == 0: # 不分组
|
173
|
+
s = r'\\(?:includegraphics|figt|figc|figr|fig).*?' + grp_bracket(3) # 注意第1组fig要放最后面
|
174
|
+
elif cnt_groups == 1: # 只分1组,那么只对图片括号内的内容分组
|
175
|
+
s = r'\\(?:includegraphics|figt|figc|figr|fig).*?' + ibrace3
|
176
|
+
elif cnt_groups == 2: # 只分2组,那么只对插图命令和图片分组
|
177
|
+
s = r'\\(includegraphics|figt|figc|figr|fig).*?' + ibrace3
|
178
|
+
elif cnt_groups == 3:
|
179
|
+
s = r'\\(includegraphics|figt|figc|figr|fig)(.*?)' + ibrace3
|
180
|
+
else:
|
181
|
+
s = None
|
182
|
+
|
183
|
+
if s and parpic:
|
184
|
+
s = r'{?\\parpic(?:\[.\])?{' + s + r'}*'
|
185
|
+
|
186
|
+
return s
|