git ssb

1
import datetime
2
import frontmatter
3
import os
4
import re
5
import unicodedata
6
7
8
input_dir = "content"
9
10
11
def slugify(string):
12
    return re.sub(
13
        r"\W+",
14
        "",
15
        unicodedata.normalize("NFKD", string)
16
        .encode("ascii", "ignore")
17
        .decode("ascii")
18
        .lower(),
19
    )
20
21
22
def sortable_title(string):
23
    return re.sub(r"^the ", "", string, flags=re.IGNORECASE).lower()
24
25
26
def parse_entry_data(entry_data):
27
    entry_data["date"] = datetime.datetime.fromisoformat(entry_data["date"] + "+00:00")
28
    if "description" in entry_data:
29
        entry_data["description"] = entry_data["description"].strip()
30
    if "links" in entry_data:
31
        for link in entry_data["links"]:
32
            link["title"] = link["title"].strip()
33
            if "description" in link:
34
                if link["description"].strip() != "":
35
                    link["description"] = link["description"].strip()
36
                else:
37
                    del link["description"]
38
            clean_link = dict((k, link[k]) for k in link)
39
    if "modified" in entry_data:
40
        entry_data["modified"] = datetime.datetime.fromisoformat(
41
            entry_data["modified"] + "+00:00"
42
        )
43
    if "tags" in entry_data:
44
        entry_data["tags"] = [tag.strip() for tag in entry_data["tags"].split(",")]
45
    if "series" in entry_data:
46
        entry_data["series"] = entry_data["series"].strip()
47
    entry_data["title"] = entry_data["title"].strip()
48
    if os.path.isdir(f"{input_dir}/{entry_data['id']}"):
49
        entry_data["dir"] = f"{input_dir}/{entry_data['id']}"
50
51
52
def _entries():
53
    entries = {}
54
55
    for filename in os.listdir(input_dir):
56
        if filename.endswith(".md") or filename.endswith(".gmi"):
57
            entry_data = frontmatter.load(f"{input_dir}/{filename}")
58
            entry_data["id"], _ = map(slugify, os.path.splitext(filename))
59
            if "date" in entry_data:
60
                parse_entry_data(entry_data)
61
                entries[entry_data["id"]] = entry_data
62
    entries = {
63
        id: entries[id]
64
        for id in sorted(entries.keys(), key=lambda entry: (entries[entry]["date"]))
65
    }
66
    return entries
67
68
69
entries = _entries()
70
71
72
def _series():
73
    series = []
74
    for entry_data in reversed(entries.values()):
75
        if "series" in entry_data and slugify(entry_data["series"]) not in map(
76
            slugify, series
77
        ):
78
            series += [entry_data["series"].strip()]
79
    return sorted(series, key=sortable_title)
80
81
82
series = _series()
83
84
85
def _tags():
86
    tags = []
87
    for entry_data in entries.values():
88
        if "tags" in entry_data:
89
            tags += [
90
                tag.strip()
91
                for tag in entry_data["tags"]
92
                if slugify(tag) not in map(slugify, tags)
93
            ]
94
    return sorted(tags, key=sortable_title)
95
96
97
tags = _tags()
98
99
years = sorted(
100
    set([datetime.datetime(entry["date"].year, 1, 1) for entry in entries.values()])
101
)
102
103
months = sorted(
104
    set(
105
        [
106
            datetime.datetime(entry["date"].year, entry["date"].month, 1)
107
            for entry in entries.values()
108
        ]
109
    )
110
)
111
112
days = sorted(
113
    set(
114
        [
115
            datetime.datetime(
116
                entry["date"].year, entry["date"].month, entry["date"].day
117
            )
118
            for entry in entries.values()
119
        ]
120
    )
121
)
122
123
updated = sorted(
124
    [entry["date"] for entry in entries.values()]
125
    + [entry["modified"] for entry in entries.values() if "modified" in entry]
126
)[-1]
127