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
|
import html
def parse_line(line):
"""
Parse a line of texte to replace HTML specialchars, link, and strong
/ emphased of markdown for HTML
return: the line ready for HTML
"""
# Change &, <, > for HTML support
html.escape(line)
# Checking if there is strong or emphasized
while "**" in line:
line = line.replace("**", "<strong>", 1)
line = line.replace("**", "</strong>", 1)
while "*" in line:
line = line.replace("*", "<em>", 1)
line = line.replace("*", "</em>", 1)
# Checking if there is image
while "![" in line and "]" in line:
title = line.split("]")[0].split("[")[1]
link = line.split("]")[1].split("(")[1].split(")")[0]
line = line.replace(
"![" + title + "](" + link + ")",
'<img src="' + link + '" alt="' + title + '"/>',
)
# Checking if there is link
while "[" in line and "]" in line:
title = line.split("]")[0].split("[")[1]
link = line.split("]")[1].split("(")[1].split(")")[0]
line = line.replace(
"[" + title + "](" + link + ")", '<a href="' + link + '">' + title + "</a>"
)
return line
def parse_md(filepath, env_vars):
"""
Parse a markdown file and return the content to put into the template page
env_vars: dictionnary of environment variable
filepath: Filepath of the markdown file
return: a dictionnary containing title, metadata, local path, content
"""
content = {
"content": "",
"title": "",
"date": "01-01-0001",
"description": "",
"tags": [],
"filepath": env_vars["pages_path"].replace(env_vars["parent_path"] + "/", "")
+ "/"
+ env_vars["lang"] + "/"
+ filepath.split(".")[0]
+ ".html",
}
inmeta, inquote, inpre, inul = False, False, False, False
# Reading the content of the file and transform into html
for line in open(env_vars["markdown_path"] + "/" + env_vars["lang"] + "/" + filepath, "r"):
line = line.strip()
# Open the metadata
if line.startswith("---"):
if inmeta:
inmeta = False
else:
inmeta = True
# Getting the date metadata
if inmeta and line.startswith("date:"):
content["date"] = line.split(":")[1].strip()
# Getting the description metadata
if inmeta and line.startswith("description:"):
content["description"] = line.split(":")[1].strip()
# Getting the tags metadata
if inmeta and line.startswith("tags:"):
tags = line.split(":")[1].split(",")
# Removing leading and ending white spaces
for i in range(0, len(tags)):
tags[i] = tags[i].strip()
content["tags"] = tags
# Close quote if not quoting
if inquote and not line.startswith(">"):
content["content"] += "</blockquote>\n"
inquote = False
# Close list if not listing
if inul and not line.startswith("-"):
content["content"] += "</li>\n</ul>\n"
inul = False
# Checking if it's a code block
if line.startswith("```"):
if inpre:
content["content"] += "</code></pre>\n"
content["content"] += "<pre><code>" + line.lstrip("```")
inpre = True
# Checking if it's a quote
elif line.startswith(">"):
if inquote:
content["content"] += parse_line(line.lstrip("> "))
else:
content["content"] += "<blockquote>" + parse_line(line.lstrip("> "))
inquote = True
# Checking if it's a list
elif line.startswith("-") and not line.startswith("---"):
if inul:
content["content"] += "</li>\n"
content["content"] += "\t<li>" + parse_line(line.lstrip("- "))
else:
content["content"] += "<ul>\n\t<li>" + parse_line(line.lstrip("- "))
inul = True
# Checking if it's a title
elif line.startswith("###"):
content["content"] += "<h3>" + parse_line(line.lstrip("# ")) + "</h3>\n"
elif line.startswith("##"):
content["content"] += "<h2>" + parse_line(line.lstrip("# ")) + "</h2>\n"
elif line.startswith("#"):
content["title"] += parse_line(line.lstrip("# "))
# else it's a paragraph
elif line != " " and line != "" and not inmeta and not line.startswith("---"):
content["content"] += "<p>" + parse_line(line) + "</p>\n"
# Checking all balise are closed
if inquote:
content["content"] += "</blockquote>\n"
inquote = False
if inul:
content["content"] += "</li>\n</ul>\n"
inul = False
if inpre:
content["content"] += "</code></pre>\n"
inpre = False
return content
|
