aboutsummaryrefslogtreecommitdiff
path: root/rebuild.py
blob: 3c0ebd92f279c8d9392989fe7adbdfa53832f501 (plain)
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
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
#!/usr/bin/env python3

import hashlib
import json
import math
import os
from datetime import timedelta
from flask import Flask
from lib.tinytag import TinyTag

def get_books(root_path, cache=dict()):
    '''
    Discover audiobooks under :root_path: and populate books object

    :cache: existing JSON cache, used to determine which content is new
            (existing content is not re-hashed)
    '''
    if not os.path.exists(root_path):
        raise ValueError('root path does not exist: %s' % root_path)

    # '/home/user/audiobooks/book': d815c7a3cc11f08558b4d91ca93de023
    existing_books = {}
    for k, _ in cache.items():
        path = cache[k]['path']
        if os.path.exists(path):
            existing_books[path] = k

    book_dirs = list()
    for root, dirs, _ in os.walk(root_path):
        for d in dirs:
            book_dirs.append(os.path.join(root, d))

    books = dict()
    for book_path in book_dirs:
        # if already cached, populate books with existing k/v
        if book_path in existing_books:
            _hash = existing_books[book_path]
            books[_hash] = cache[_hash]
            continue
        book = is_book(book_path)
        if book:
            books[book[0]] = book[1]

    return books

def is_book(book_path):
    '''
    Determine if :book_path: contains (supported) audio files

    Returns False (not a book) or populated book dict
    '''
    ext = ['mp3'] # m4b seems to be unsupported by Apple

    # book attributes to be populated
    book = {
        'author':       None,
        'duration':     0,
        'duration_str': None,
        'files':        dict(),
        'path':         book_path,
        'size_bytes':   0,
        'size_str':     None,
        'title':        None
    }

    # hash of each file in directory w/ track extension
    folder_hash = hashlib.md5()

    # a book_path is only a book if it contains at least one track
    is_book = False

    for f in os.listdir(book_path):
        file_path = os.path.join(book_path, f)

        # is a file and has a supported extension
        if not os.path.isfile(file_path) or not f.split('.')[-1] in ext:
            continue

        # track duration is required
        tag = TinyTag.get(file_path)
        if not tag.duration:
            continue

        # previous conditions met, we're a book! :D
        is_book = True
        print('[+] processing: %s' % f)

        # update collective hash of folder with MD5 of current file
        BLOCK = 1024
        file_hash = hashlib.md5()
        with open(file_path, 'rb') as f:
            while True:
                data = f.read(BLOCK)
                if not data:
                    break
                folder_hash.update(data)
                file_hash.update(data)

        # 1 day, 10:59:58
        duration_str = str(timedelta(seconds=tag.duration))

        # per-file atributes, some values are populated conditionally
        track = {
            'album':        validate(tag.album, os.path.split(book_path)[1]),
            'author':       validate(tag.artist, 'Unknown'),
            'duration':     tag.duration,
            'duration_str': duration_str.split('.')[0],
            'filename':     os.path.split(file_path)[1],
            'path':         file_path,
            'size_bytes':   tag.filesize,
            'title':        validate(tag.title, os.path.split(file_path)[1]),
            'track':        tag.track
        }

        # we assume author and album attributes are unchanged between tracks
        book['author'] = track['author']
        book['title'] = track['album']

        # increment book total size/duration
        book['duration'] += tag.duration
        book['size_bytes'] += tag.filesize

        # hexdigest: track dict
        book['files'][file_hash.hexdigest()] = track

    # if we're a book, store formatted book size and duration
    if is_book:
        folder_hash = folder_hash.hexdigest()
        total_size = book['size_bytes']
        try:
            _i = int(math.floor(math.log(total_size, 1024)))
            _p = math.pow(1024, _i)
            _s = round(total_size / _p, 2)
        except:
            _i = 1
            _s = 0

        # e.g. 1.48 GB
        SIZES = ('B', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB', 'ZB', 'YB')
        book['size_str'] = '%s %s' % (str(_s), SIZES[_i])

        # e.g. 2 days, 5:47:47
        duration_str = str(timedelta(seconds=book['duration']))
        book['duration_str'] = duration_str.split('.')[0]
        return (folder_hash, book)

    return False

def write_cache(books, json_path):
    '''
    Dump contents of :books: to :json_path:
    '''
    cache_path = os.path.dirname(json_path)
    if not os.path.exists(cache_path):
        os.mkdir(cache_path)
    with open(json_path, 'w') as f:
        json.dump(books, f, indent=4)

def read_cache(json_path):
    '''
    Return dict of existing cache
    '''
    with open(json_path, 'r') as cache:
        books = json.load(cache)

    return books

def validate(v, b):
    '''
    Returns :v: if :v: and v.isspace(), otherwise :b:
    '''
    if v and not v.isspace():
        return v
    else:
        return b

if __name__ == '__main__':
    ABS_PATH = os.path.dirname(os.path.abspath(__file__))
    CACHE_PATH = os.path.join(ABS_PATH, 'cache')
    JSON_PATH = os.path.join(CACHE_PATH, 'audiobooks.json')

    # use Flask's config parser, configparser would be hacky
    APP = Flask(__name__)
    APP.config.from_pyfile(os.path.join(ABS_PATH, 'app.cfg'))

    if os.path.exists(JSON_PATH):
        cache = read_cache(JSON_PATH)
        BOOKS = get_books(APP.config['ROOT_PATH'], cache)
    else:
        BOOKS = get_books(APP.config['ROOT_PATH'])

    write_cache(BOOKS, JSON_PATH)