administration/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-10 03:10:38 +00:00
Code Issues Projects Releases Wiki Activity

[outtmpl] Add alternate forms for q and j

Browse Source
This commit is contained in:
pukkandan 2021-11-08 21:17:57 +05:30
parent aa9369a2d8
commit 4476d2c764
No known key found for this signature in database
GPG Key ID: 0F00D95A001F4698
3 changed files with 17 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -1049,7 +1049,7 @@ The field names themselves (the part inside the parenthesis) can also have some
1. **Date/time Formatting**: Date/time fields can be formatted according to [strftime formatting](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes) by specifying it separated from the field name using a `>`. Eg: `%(duration>%H-%M-%S)s`, `%(upload_date>%Y-%m-%d)s`, `%(epoch-3600>%H-%M-%S)s`
1. **Alternatives**: Alternate fields can be specified seperated with a `,`. Eg: `%(release_date>%Y,upload_date>%Y|Unknown)s`
1. **Default**: A literal default value can be specified for when the field is empty using a `|` seperator. This overrides `--output-na-template`. Eg: `%(uploader|Unknown)s`
1. **More Conversions**: In addition to the normal format types `diouxXeEfFgGcrs`, `B`, `j`, `l`, `q` can be used for converting to **B**ytes, **j**son, a comma seperated **l**ist (alternate form flag `#` makes it new line `\n` seperated) and a string **q**uoted for the terminal, respectively
1. **More Conversions**: In addition to the normal format types `diouxXeEfFgGcrs`, `B`, `j`, `l`, `q` can be used for converting to **B**ytes, **j**son (flag `#` for pretty-printing), a comma seperated **l**ist (flag `#` for `\n` newline-seperated) and a string **q**uoted for the terminal (flag `#` to split a list into different arguments), respectively
1. **Unicode normalization**: The format type `U` can be used for NFC [unicode normalization](https://docs.python.org/3/library/unicodedata.html#unicodedata.normalize). The alternate form flag (`#`) changes the normalization to NFD and the conversion flag `+` can be used for NFKC/NFKD compatibility equivalence normalization. Eg: `%(title)+.100U` is NFKC
To summarize, the general syntax for a field is:

9
test/test_YoutubeDL.py
View File

@ -763,14 +763,15 @@ class TestYoutubeDL(unittest.TestCase):
test('a%(width|)d', 'a', outtmpl_na_placeholder='none')
FORMATS = self.outtmpl_info['formats']
sanitize = lambda x: x.replace(':', ' -').replace('"', "'")
sanitize = lambda x: x.replace(':', ' -').replace('"', "'").replace('\n', ' ')
# Custom type casting
test('%(formats.:.id)l', 'id 1, id 2, id 3')
test('%(formats.:.id)#l', ('id 1\nid 2\nid 3', 'id 1 id 2 id 3'))
test('%(ext)l', 'mp4')
test('%(formats.:.id) 15l', ' id1, id2, id3')
test('%(formats.:.id) 18l', ' id 1, id 2, id 3')
test('%(formats)j', (json.dumps(FORMATS), sanitize(json.dumps(FORMATS))))
test('%(formats)#j', (json.dumps(FORMATS, indent=4), sanitize(json.dumps(FORMATS, indent=4))))
test('%(title5).3B', 'á')
test('%(title5)U', 'áéí 𝐀')
test('%(title5)#U', 'a\u0301e\u0301i\u0301 𝐀')
@ -778,8 +779,12 @@ class TestYoutubeDL(unittest.TestCase):
test('%(title5)+#U', 'a\u0301e\u0301i\u0301 A')
if compat_os_name == 'nt':
test('%(title4)q', ('"foo \\"bar\\" test"', "'foo _'bar_' test'"))
test('%(formats.:.id)#q', ('"id 1" "id 2" "id 3"', "'id 1' 'id 2' 'id 3'"))
test('%(formats.0.id)#q', ('"id 1"', "'id 1'"))
else:
test('%(title4)q', ('\'foo "bar" test\'', "'foo 'bar' test'"))
test('%(formats.:.id)#q', "'id 1' 'id 2' 'id 3'")
test('%(formats.0.id)#q', "'id 1'")
# Internal formatting
test('%(timestamp-1000>%H-%M-%S)s', '11-43-20')

11
yt_dlp/YoutubeDL.py
View File

@ -1104,22 +1104,23 @@ class YoutubeDL(object):
value = default if value is None else value
flags = outer_mobj.group('conversion') or ''
str_fmt = f'{fmt[:-1]}s'
if fmt[-1] == 'l': # list
delim = '\n' if '#' in (outer_mobj.group('conversion') or '') else ', '
delim = '\n' if '#' in flags else ', '
value, fmt = delim.join(variadic(value)), str_fmt
elif fmt[-1] == 'j': # json
value, fmt = json.dumps(value, default=_dumpjson_default), str_fmt
value, fmt = json.dumps(value, default=_dumpjson_default, indent=4 if '#' in flags else None), str_fmt
elif fmt[-1] == 'q': # quoted
value, fmt = compat_shlex_quote(str(value)), str_fmt
value = map(str, variadic(value) if '#' in flags else [value])
value, fmt = ' '.join(map(compat_shlex_quote, value)), str_fmt
elif fmt[-1] == 'B': # bytes
value = f'%{str_fmt}'.encode('utf-8') % str(value).encode('utf-8')
value, fmt = value.decode('utf-8', 'ignore'), 's'
elif fmt[-1] == 'U': # unicode normalized
opts = outer_mobj.group('conversion') or ''
value, fmt = unicodedata.normalize(
# "+" = compatibility equivalence, "#" = NFD
'NF%s%s' % ('K' if '+' in opts else '', 'D' if '#' in opts else 'C'),
'NF%s%s' % ('K' if '+' in flags else '', 'D' if '#' in flags else 'C'),
value), str_fmt
elif fmt[-1] == 'c':
if value: