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
|
import os
import re
import glob
import simplejson as json
import app.settings.app_cfg as cfg
def read_metadata(fn):
"""
Read in read a markdown file and extract the metadata
"""
with open(fn, "r") as file:
data = file.read()
data = data.replace("\n ", "\n")
if "\n" in data:
data = data.replace("\r", "")
else:
data = data.replace("\r", "\n")
sections = data.split("\n\n")
return parse_metadata(fn, sections)
default_metadata = {
'status': 'published',
'title': 'Untitled Page',
'desc': '',
'slug': '',
'published': '2018-12-31',
'updated': '2018-12-31',
'authors': 'Adam Harvey',
'sync': 'true',
'tagline': '',
}
def parse_metadata(fn, sections):
"""
parse the metadata headers in a markdown file
(everything before the second ---------)
also generates appropriate urls for this page :)
"""
found_meta = False
metadata = {}
valid_sections = []
for section in sections:
if not found_meta and ': ' in section:
found_meta = True
parse_metadata_section(metadata, section)
continue
if '-----' in section:
continue
if found_meta:
valid_sections.append(section)
if 'title' not in metadata:
print('warning: {} has no title'.format(fn))
for key in default_metadata:
if key not in metadata:
metadata[key] = default_metadata[key]
basedir = os.path.dirname(fn.replace(cfg.DIR_SITE_CONTENT, ''))
basename = os.path.basename(fn)
if basedir == '/':
metadata['path'] = '/'
metadata['url'] = '/'
elif basename == 'index.md':
metadata['path'] = basedir + '/'
metadata['url'] = metadata['path']
else:
metadata['path'] = basedir + '/'
metadata['url'] = metadata['path'] + basename.replace('.md', '') + '/'
if metadata['status'] == 'published|draft|private':
metadata['status'] = 'published'
metadata['sync'] = metadata['sync'] != 'false'
metadata['author_html'] = '<br>'.join(metadata['authors'].split(','))
return metadata, valid_sections
def parse_metadata_section(metadata, section):
"""
parse a metadata key: value pair
"""
for line in section.split("\n"):
if ': ' not in line:
continue
key, value = line.split(': ', 1)
metadata[key.lower()] = value
def read_research_post_index():
"""
Generate an index of the research (blog) posts
"""
return read_post_index('research')
def read_datasets_index():
"""
Generate an index of the datasets
"""
return read_post_index('datasets')
def read_post_index(basedir):
"""
Generate an index of posts
"""
posts = []
for fn in sorted(glob.glob(os.path.join(cfg.DIR_SITE_CONTENT, basedir, '*/index.md'))):
metadata, valid_sections = read_metadata(fn)
if metadata is None or metadata['status'] == 'private' or metadata['status'] == 'draft':
continue
posts.append(metadata)
if not len(posts):
posts.append({
'title': 'Placeholder',
'slug': 'placeholder',
'date': 'Placeholder',
'url': '/',
})
return posts
|
