-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathpsub
297 lines (254 loc) · 12.9 KB
/
psub
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
#!/usr/bin/env python3
# -*- coding:utf-8 -*-
# @Time : 2018-02-10 10:17
# @Author : PengZhw
h = """
-add FILENAME NAAA MBBB X OUTNAME
将FILENAME里面从第一个字符串是NAAA的第一行，到第一个字符串是MBBB的最后一行，
这些行的N、M加上一个数X，且保证修改之后依旧占位8格。
如：-add complex.gro 1DDR 28DDT 1 complex-ordered.gro
将把complex.gro中从1DDR 到 28DDT 改成 2DDR 到 29DDT。
-a
-if
"""
# 这个文件来用迭代器、List实现文件修改，实现备份文件
import re
import os.path
import shutil
from sys import argv
def preprocess(filename_f):
"""
:param filename_f: 传递接受自外界的文件路径。
:return: 如果路径正确则返回一个列表，每个标签是一项，每项也是一个子列表，
子列表包含：1 起始行行号 2 标签名 3 该标签下的列头
"""
# 判断路径有效与否
if not os.path.isfile(filename_f):
print("%s并非指向一个文件的正确路径，请检查路径正确性，区分大小写、区分'\\'与'/'。" % filename_f)
return
with open(filename_f, 'r')as f:
# 预处理：寻找结构头（标签）并写入一个二维数组↓
line_list = f.readlines()
line_number = 0
structure_head = [] # 用二维数组来表示结构头及其行号，0：结构头名称；1：行号；2：列头
for lineText in line_list:
line_number += 1
pattern = r'^[\s{0,4}[a-z_A-Z]+\s{0,4}]'
match_result = re.match(pattern, lineText)
if str(match_result) != 'None':
print(line_number, '\t\t' + match_result.group())
structure_head.append([line_number, match_result.group()])
# 寻找每一标签的列头（列名）并写入二维数组↓
for headIndex in range(1, len(structure_head) + 1): # 第 i 个标签下，headIndex = [第几个标签]
head_begin_line = structure_head[headIndex - 1][0] # 设置行起点
if headIndex < len(structure_head) - 1: # 设置列起点
head_end_line = structure_head[headIndex][0] - 1
else:
head_end_line = len(line_list)
pattern = '.*[a-zA-Z].*' # 设置匹配模式：只要这一行有至少一个字母就匹配
# 编译正则匹配的模式
recompile = re.compile(pattern)
for line_number in range(head_begin_line, head_end_line): # 第 i 个标签下的5行内，匹配第一个非空行
# 重复使用编译过的模式来匹配
match_result = recompile.match(line_list[line_number])
if str(match_result) != 'None':
print(headIndex, structure_head[headIndex - 1][1], '是第' + str(headIndex) + '个非空标签，', end='')
print('它在整个文件文第' + str(line_number) + '行：')
colume_head_match_list = re.split(r'\s+', match_result.group().strip())
structure_head[headIndex - 1].append(colume_head_match_list)
for i in range(1, len(structure_head[headIndex - 1][2])):
print('\t', i, structure_head[headIndex - 1][2][i - 1], end='')
print()
break
else:
print(match_result)
print('\n用subxc函数修改文件：subxc(<标签序号（1-n）>, <列号（1-m）>, <将被替换的数据>, <用此数据去替换>)；'
'\n<标签序号（1-n）>、 <列号（1-m）>均用上面的序号表示；'
'\n如将第2个标签的第4列中所有的111改为222，则输入subxc(2, 4, 111, 222)<Enter>。'
'\n有些标签下第一个行头对应多个数据，程序待改进。')
print(structure_head)
return structure_head
def subxc(n_tag_will_sub, n_colume_will_sub, old_data, new_data, n_colume_charge=None, charge_value=None):
"""
:param n_tag_will_sub: 这是一个序号，表示文件中第几个标签下的内容将会被修改，其值从1开始而不是从0开始，用在List上时要先减1
:param n_colume_will_sub: 类似地，是序号，表示该标签下第几列的内容会被修改，其值从1开始而不是从0开始，用在List上时要先减1
:param old_data: 将要被修改的数据
:param new_data: 想要修改成的数据
:param n_colume_charge: 第多少列需要判断，其值从1开始而不是从0开始，用在List上时要先减1
:param charge_value: 判断是不是何值，其值从1开始而不是从0开始，用在List上时要先减1
:return:
"""
# 生成一个备份文件，备份文件文件名是<源文件名>.bak
shutil.copyfile(FILENAME, BAKFILENAME)
# 对源文件进行修改
print(type(STRUCTURE_HEAD[n_tag_will_sub - 1][0]))
b_line = STRUCTURE_HEAD[n_tag_will_sub - 1][0] # 取出要改动的起始行数
e_line = STRUCTURE_HEAD[n_tag_will_sub][0] # 取出要改动的末端行数
# 根据要改的列数选择匹配规则
def write_pattern(datum):
pattern_1 = r'^(?P<pre>\s*)(?P<aim>' + str(datum) + r')(?P<pos>.*)$'
pattern_2 = r'^(?P<pre>(?:\s+|[0-9a-zA-Z])[0-9a-zA-Z]+\s+)(?P<aim>' + str(datum) + r')(?P<pos>.*)$'
pattern_3 = r'^(?P<pre>(?:\s+|[0-9a-zA-Z])[0-9a-zA-Z]+\s+[0-9a-zA-Z]+\s+)(?P<aim>' + str(
datum) + r')(?P<pos>.*)$'
pattern_4 = r'^(?P<pre>(?:\s+|[0-9a-zA-Z])[0-9a-zA-Z]+\s+[0-9a-zA-Z]+\s+[0-9a-zA-Z]+\s+' \
r')(?P<aim>' + str(datum) + r')(?P<pos>.*)$'
pattern_5 = r'^(?P<pre>(?:\s+|[0-9a-zA-Z])[0-9a-zA-Z]+\s+[0-9a-zA-Z]+\s+[0-9a-zA-Z]+\s+' \
r'[0-9a-zA-Z]+\s+)(?P<aim>' + str(datum) + r')(?P<pos>.*)$'
pattern_6 = r'^(?P<pre>(?:\s+|[0-9a-zA-Z])[0-9a-zA-Z]+\s+[0-9a-zA-Z]+\s+[0-9a-zA-Z]+\s+' \
r'[0-9a-zA-Z]+\s+[0-9a-zA-Z]+\s+)(?P<aim>' + str(datum) + r')(?P<pos>.*)$'
pattern_7 = r'^(?P<pre>(?:\s+|[0-9a-zA-Z])[0-9a-zA-Z]+\s+[0-9a-zA-Z]+\s+[0-9a-zA-Z]+\s+' \
r'[0-9a-zA-Z]+\s+[0-9a-zA-Z]+\s+[0-9a-zA-Z]+\s+)(?P<aim>' + str(datum) + r')(?P<pos>.*)$'
return [pattern_1, pattern_2, pattern_3, pattern_4, pattern_5, pattern_6, pattern_7]
"""
# 选择模式
if n_colume_will_sub == 1:
pattern = pattern_1
elif n_colume_will_sub == 2:
pattern = pattern_2
elif n_colume_will_sub == 3:
pattern = pattern_3
elif n_colume_will_sub == 4:
pattern = pattern_4
elif n_colume_will_sub == 5:
pattern = pattern_5
elif n_colume_will_sub == 6:
pattern = pattern_6
elif n_colume_will_sub == 7:
pattern = pattern_7
"""
sub_pattern_list = write_pattern(old_data)
charge_pattern_list = write_pattern(charge_value)
if MODE == '-a':
# 编译
print(sub_pattern_list[n_colume_will_sub - 1])
re_compile = re.compile(sub_pattern_list[n_colume_will_sub - 1])
# 读文件
with open(FILENAME, 'r') as fr:
file_lines = fr.readlines()
for line in range(b_line, e_line):
print(file_lines[line - 1])
match_result = re_compile.match(file_lines[line - 1])
print(match_result)
if str(match_result) != 'None':
file_lines[line - 1] = '%s%s%s\n' % (match_result.group('pre'), # 不知道会不会出问题
new_data,
match_result.group('pos'))
with open(r'./new_file.gro', 'w+') as fw:
fw.writelines(file_lines)
if MODE == '-if':
# 编译
sub_compile = re.compile(sub_pattern_list[n_colume_will_sub - 1])
charge_compile = re.compile(charge_pattern_list[n_colume_charge - 1])
# 读文件
with open(FILENAME, 'r') as fr:
file_lines = fr.readlines()
for line in range(b_line, e_line):
charge_match = charge_compile.match(file_lines[line - 1])
aim_match = sub_compile.match(file_lines[line - 1])
if str(charge_match) != 'None' and aim_match.group('aim') == str(old_data):
file_lines[line - 1] = '%s%s%s\n' % (aim_match.group('pre'),
new_data,
aim_match.group('pos'))
with open(r'./new_file.gro', 'w+') as fw:
fw.writelines(file_lines)
def packed_gro_sub(filename, charge_str, end_str, add_number, outname):
# 编译
pattern = r'^(?P<num>\s*\d+' + r')(?P<str>[a-zA-Z]*)(?P<pos>.*)$'
re_compile = re.compile(pattern)
# 读文件
with open(filename, 'r') as fr:
file_lines = fr.readlines()
startline = 0
endline = 0
# 计算起始行
for line in range(len(file_lines)):
match_result = re_compile.match(file_lines[line - 1])
# print(file_lines[line - 1].split()[0])
# print(charge_str)
if str(match_result) != 'None' and file_lines[line - 1].split()[0] == charge_str:
startline = line
break
# 计算结束行
if end_str == 'no':
endline = 99999999
else:
for line in range(len(file_lines)):
match_result = re_compile.match(file_lines[line - 1])
# print(file_lines[line - 1].split()[0])
if str(match_result) != 'None' and file_lines[line - 1].split()[0] == end_str:
endline = line
# 结束行用要被改动的最后一行行号，所以不break
print(startline)
print(endline)
for line in range(len(file_lines)):
match_result = re_compile.match(file_lines[line - 1])
# print(match_result)
if str(match_result) != 'None' and endline-1 >= line-1 >= startline-1:
file_lines[line - 1] = '%8s%s\n' % (str(int(add_number)+int(match_result.group('num'))).strip()
+match_result.group('str'),
match_result.group('pos'))
if line-1 == 15953:
print(match_result, startline)
with open(outname, 'w+', newline='\n') as fw:
fw.writelines(file_lines)
def packed_gro_sub_by_line(filename, strat_line, end_line, add_number, outname):
# 编译
pattern = r'^(?P<num>\s*\d+' + r')(?P<str>[a-zA-Z]*)(?P<pos>.*)$'
re_compile = re.compile(pattern)
# 读文件
with open(filename, 'r') as fr:
file_lines = fr.readlines()
startline = int(strat_line)
endline = int(end_line)
print(startline)
print(endline)
for line in range(len(file_lines)):
match_result = re_compile.match(file_lines[line - 1])
# print(match_result)
if str(match_result) != 'None' and endline-1 >= line-1 >= startline-1:
file_lines[line - 1] = '%8s%s\n' % (str(int(add_number)+int(match_result.group('num'))).strip()
+match_result.group('str'),
match_result.group('pos'))
if line-1 == 15953:
print(match_result, startline)
with open(outname, 'w+', newline='\n') as fw:
fw.writelines(file_lines)
if '-a' in argv:
"""
argv 接收7个参数:
1. 本Python模组的文件名
2. '-a'
3. FILENAME： 含路径的文件名
4. N_TAG： 第几个标签
5. N_COLUME： 第几列的数据
6. OLD_DATA: 旧数据
7. NEW_DATA: 新数据
"""
self, MODE, FILENAME, N_TAG, N_COLUME, OLD_DATA, NEW_DATA = argv
# FILENAME = r'd:/test.gro' # 暂时先用固定的路径，以后改为用参数接收输入
BAKFILENAME = FILENAME + '.bak'
print('第一步，用preprocess(<文件路径>)来对想要操作的文件进行预处理：')
STRUCTURE_HEAD = preprocess(filename_f=FILENAME)
# shutil.copyfile(FILENAME, BAKFILENAME) # 测试备份是否可用
# input("依次输入标签序号 列序号 原始数据 需要改成的数据", )
subxc(int(N_TAG), int(N_COLUME), str(OLD_DATA), str(NEW_DATA)) # 把第*个标签下的第*列的所有***改成***
if '-if' in argv:
"""
argv
"""
self, MODE, FILENAME, N_TAG, N_COLUME, OLD_DATA, NEW_DATA, N_COLUME_CHARGE, CHARGE_VALUE = argv
BAKFILENAME = FILENAME + '.bak'
STRUCTURE_HEAD = preprocess(filename_f=FILENAME)
subxc(int(N_TAG), int(N_COLUME), str(OLD_DATA), str(NEW_DATA), int(N_COLUME_CHARGE), str(CHARGE_VALUE))
if '-add' in argv:
# $ psub -add FILENAME CHARGE_VALUE ADD_NUMBER
self, MODE, FILENAME, CHARGE_STR, END_STR, ADD_NUMBER, OUTNAME = argv
packed_gro_sub(FILENAME, CHARGE_STR, END_STR, ADD_NUMBER, OUTNAME)
if '-adl' in argv:
# $ psub -add FILENAME CHARGE_VALUE ADD_NUMBER
self, MODE, FILENAME, START_LINE, END_LINE, ADD_NUMBER, OUTNAME = argv
packed_gro_sub_by_line(FILENAME, START_LINE, END_LINE, ADD_NUMBER, OUTNAME)
else:
print("请在第一个参数位选择模式，如'-a''-if'等")
if len(argv) <= 1:
print("无参数接收")