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
|
# -*-coding: utf8 -*
#Python 3 only
"""
################## Algorithm #########################
# Original | Count | ID | len(ID) #
#Project | 0 | 1 | 1 #
# HW | 1 | 1.1 | 3 #
# Specification | 2 | 1.1.1 | 5 #
# SW | 1 | 1.2 | 3 #
# Specification | 2 | 1.2.1 | 5 #
# Code | 2 | 1.2.2 | 5 #
# Validation | 3 | 1.2.2.1 | 7 #
# Qualification | 1 | 1.3 | 3 #
####################################################################
"""
import os
import re
import sys
def tabCreator(nb_tab, sentence):
"""
Function that returns a sentence with the number of tab on front
"""
temp_sentence = sentence
for tab in range(nb_tab):
temp_sentence = "\t" + temp_sentence
return temp_sentence
def calculID(count_tab, ID):
"""
Function that gives an ID to each title depending on its level of hierarchy
"""
#if the level hierarchy is inferior to the previous ID then add ".1"
if 2*count_tab+1 > len(str(ID)):
ID = ID + ".1"
#otherwise if level hierarchy is equal to the previous ID then increase last numbe
elif 2*count_tab +1 == len(str(ID)):
ID = ID[:-1] + str(int(ID[-1])+1)
#in other cases, increase the level ID
else:
ID = ID[0:count_tab*2] + str(int(ID[count_tab*2])+1)
return ID
class WBS:
"""
Class defining an object for manipulating a WBS document
"""
def __init__(self, origin_file='WBS.txt'):
self.original_content = open(origin_file,'r', encoding="utf8")
self.final_file = open('GENERATED_WBS.txt','w', encoding="utf8")
self.l_final = []
self.count_tab = 0
self.ID = "0"
def parseOrigin(self):
"""
Function for parsing the original content
remove \n character
Allocate tab space to hierarchy number
"""
for each_line in self.original_content:
#counts how many tab are included in the sentence
self.count_tab = each_line.count("\t")
#calculate the level of hierarchy of the title
self.ID = calculID(self.count_tab, self.ID)
#removes the \n character from the line
temp_buffer = each_line.replace('\n','')
#split each line from original list into two different lists
temp_buffer = re.compile("\t+").split(temp_buffer)
#then concatenate ID and the content of the line
temp_buffer[-1] = self.ID + " " + temp_buffer[-1]
#creates a tabulation before ID
final_sentence = tabCreator(self.count_tab, temp_buffer[-1])
#include it into final list
self.l_final.append(final_sentence)
def writeFinalFile(self):
"""
Function to write l_final into final file
"""
for each_line in self.l_final:
print(each_line,file=self.final_file)
def closeFiles(self):
"""
Function to close all files
"""
self.original_content.close()
self.final_file.close()
if __name__ == '__main__':
"""Main function to call python patch_anki.py"""
os.chdir('.')
try:
#sys.argv[1] allows to inclue a file as argument
wbs = WBS(sys.argv[1])
except IndexError :
wbs = WBS()
except FileNotFoundError:
print("file not found")
sys.exit(1)
wbs.parseOrigin()
wbs.writeFinalFile()
wbs.closeFiles() |
parser de texte - amélioration du code
Répondre avec citation
Partager