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
|
import os
import re
import glob
import app.settings.app_cfg as cfg
from app.utils.file_utils import load_json
import app.utils.sheet_utils as sheet
sidebar = sheet.fetch_google_lookup("sidebar", item_key="key")
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)
def domainFromUrl(url):
domain = url.split('/')[2].split('.')
if len(domain) > 2 and len(domain[-2]) == 2:
return ".".join(domain[-3:])
return ".".join(domain[-2:])
default_metadata = {
'status': 'published',
'title': 'Untitled Page',
'desc': '',
'slug': '',
'published': '2018-12-31',
'updated': '2018-12-31',
'authors': 'Adam Harvey',
'sync': 'true',
'tagline': '',
}
sidebar_order = [
{ 'key': 'published', 'title': 'Published' },
{ 'key': 'images', 'title': 'Images' },
{ 'key': 'videos', 'title': 'Videos' },
{ 'key': 'identities', 'title': 'Identities' },
{ 'key': 'purpose', 'title': 'Purpose' },
{ 'key': 'created_by', 'title': 'Created by' },
{ 'key': 'funded_by_short', 'title': 'Funded by' },
{ 'key': 'size_gb', 'title': 'Download Size' },
{ 'key': 'website', 'title': 'Website' },
]
def parse_metadata(fn, sections):
"""
parse the metadata headers in a markdown file
(everything before the second ---------)
- determines appropriate urls for this page
- loads paper if any
"""
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['og_desc'] = re.sub('<[^<]+?>', '', metadata['desc'])
metadata['sync'] = metadata['sync'] != 'false'
metadata['author_html'] = '<br>'.join(metadata['authors'].split(','))
dataset_path = os.path.join(cfg.DIR_SITE_FINAL_CITATIONS, metadata['slug'] + '.json')
if os.path.exists(dataset_path):
metadata['meta'] = load_json(dataset_path)
if not metadata['meta']:
print("Bad metadata? {}".format(dataset_path))
elif 'datasets' in fn:
print("/!\\ {} does not exist!".format(dataset_path))
if metadata['slug'] in sidebar:
sidebar_row = sidebar[metadata['slug']]
if sidebar_row:
metadata['sidebar'] = []
for item in sidebar_order:
key = item['key']
value = sidebar_row[key]
if value:
value = value.replace(' - ', ' – ')
if key == 'size_gb':
value += ' GB'
if key == 'website':
value = "<a href='" + value + "' target='_blank' rel='nofollow noopener'>" + domainFromUrl(value) + "</a>"
metadata['sidebar'].append({ 'value': value, 'title': item['title'], })
if 'meta' not in metadata or not metadata['meta']: # dude
metadata['meta'] = {}
metadata['sidebar'] = []
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
|
