Improve output template internal formatting

* Allow slicing lists/strings using `field.start🔚step`
* A field can also be used as offset like `field1+num+field2`
* A default value can be given using `field|default`
* Capture all format strings and set it to `None` if invalid. This prevents invalid fields from causing errors
This commit is contained in:
pukkandan 2021-05-03 22:36:03 +05:30
parent 12e73423f1
commit e625be0d10
No known key found for this signature in database
GPG key ID: 0F00D95A001F4698
4 changed files with 71 additions and 32 deletions

View file

@ -842,13 +842,14 @@ # OUTPUT TEMPLATE
It may however also contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by formatting operations.
The field names themselves (the part inside the parenthesis) can also have some special formatting:
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` or `%(upload_date>%Y-%m-%d)s`
2. **Offset numbers**: Numeric fields can have an initial offset specified by using a `+` separator. Eg: `%(playlist_index+10)03d`. This can also be used in conjunction with the date-time formatting. Eg: `%(epoch+-3600>%H-%M-%S)s`
3. **Object traversal**: The dictionaries and lists available in metadata can be traversed by using a `.` (dot) separator. Eg: `%(tags.0)s` or `%(subtitles.en.-1.ext)`. Note that the fields that become available using this method are not listed below. Use `-j` to see such fields
1. **Object traversal**: The dictionaries and lists available in metadata can be traversed by using a `.` (dot) separator. You can also do python slicing using `:`. Eg: `%(tags.0)s`, `%(subtitles.en.-1.ext)`, `%(id.3:7:-1)s`. Note that the fields that become available using this method are not listed below. Use `-j` to see such fields
1. **Addition**: Addition and subtraction of numeric fields can be done using `+` and `-` respectively. Eg: `%(playlist_index+10)03d`, `%(n_entries+1-playlist_index)d`
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. **Default**: A default value can be specified for when the field is empty using a `|` seperator. This overrides `--output-na-template`. Eg: `%(uploader|Unknown)s`
To summarize, the general syntax for a field is:
```
%(name[.keys][+offset][>strf])[flags][width][.precision][length]type
%(name[.keys][addition][>strf][|default])[flags][width][.precision][length]type
```
Additionally, you can set different output templates for the various metadata files separately from the general output template by specifying the type of file followed by the template separated by a colon `:`. The different file types supported are `subtitle`, `thumbnail`, `description`, `annotation`, `infojson`, `pl_description`, `pl_infojson`, `chapter`. For example, `-o '%(title)s.%(ext)s' -o 'thumbnail:%(title)s\%(title)s.%(ext)s'` will put the thumbnails in a folder with the same name as the video.

View file

@ -843,29 +843,67 @@ def prepare_outtmpl(self, outtmpl, info_dict, sanitize=None):
if sanitize is None:
sanitize = lambda k, v: v
# Internal Formatting = name.key1.key2+number>strf
INTERNAL_FORMAT_RE = FORMAT_RE.format(
r'''(?P<final_key>
(?P<fields>\w+(?:\.[-\w]+)*)
(?:\+(?P<add>-?\d+(?:\.\d+)?))?
(?:>(?P<strf_format>.+?))?
)''')
for mobj in re.finditer(INTERNAL_FORMAT_RE, outtmpl):
mobj = mobj.groupdict()
# Object traversal
fields = mobj['fields'].split('.')
final_key = mobj['final_key']
value = traverse_dict(template_dict, fields)
# Offset the value
if mobj['add']:
value = float_or_none(value)
if value is not None:
value = value + float(mobj['add'])
# Datetime formatting
if mobj['strf_format']:
value = strftime_or_none(value, mobj['strf_format'])
if mobj['type'] in 'crs' and value is not None: # string
value = sanitize('%{}'.format(mobj['type']) % fields[-1], value)
EXTERNAL_FORMAT_RE = FORMAT_RE.format('(?P<key>[^)]*)')
# Field is of the form key1.key2...
# where keys (except first) can be string, int or slice
FIELD_RE = r'\w+(?:\.(?:\w+|[-\d]*(?::[-\d]*){0,2}))*'
INTERNAL_FORMAT_RE = re.compile(r'''(?x)
(?P<negate>-)?
(?P<fields>{0})
(?P<maths>(?:[-+]-?(?:\d+(?:\.\d+)?|{0}))*)
(?:>(?P<strf_format>.+?))?
(?:\|(?P<default>.*?))?
$'''.format(FIELD_RE))
MATH_OPERATORS_RE = re.compile(r'(?<![-+])([-+])')
MATH_FUNCTIONS = {
'+': float.__add__,
'-': float.__sub__,
}
for outer_mobj in re.finditer(EXTERNAL_FORMAT_RE, outtmpl):
final_key = outer_mobj.group('key')
str_type = outer_mobj.group('type')
value = None
mobj = re.match(INTERNAL_FORMAT_RE, final_key)
if mobj is not None:
mobj = mobj.groupdict()
# Object traversal
fields = mobj['fields'].split('.')
value = traverse_dict(template_dict, fields)
# Negative
if mobj['negate']:
value = float_or_none(value)
if value is not None:
value *= -1
# Do maths
if mobj['maths']:
value = float_or_none(value)
operator = None
for item in MATH_OPERATORS_RE.split(mobj['maths'])[1:]:
if item == '':
value = None
if value is None:
break
if operator:
item, multiplier = (item[1:], -1) if item[0] == '-' else (item, 1)
offset = float_or_none(item)
if offset is None:
offset = float_or_none(traverse_dict(template_dict, item.split('.')))
try:
value = operator(value, multiplier * offset)
except (TypeError, ZeroDivisionError):
value = None
operator = None
else:
operator = MATH_FUNCTIONS[item]
# Datetime formatting
if mobj['strf_format']:
value = strftime_or_none(value, mobj['strf_format'])
# Set default
if value is None and mobj['default'] is not None:
value = mobj['default']
# Sanitize
if str_type in 'crs' and value is not None: # string
value = sanitize('%{}'.format(str_type) % fields[-1], value)
else: # numeric
numeric_fields.append(final_key)
value = float_or_none(value)

View file

@ -24,7 +24,7 @@ def pp_key(cls):
def parse_cmd(self, cmd, info):
# If no %(key)s is found, replace {} for backard compatibility
if not re.search(FORMAT_RE.format(r'[-\w>.+]+'), cmd):
if not re.search(FORMAT_RE.format(r'[^)]*'), cmd):
if '{}' not in cmd:
cmd += ' {}'
return cmd.replace('{}', compat_shlex_quote(info['filepath']))

View file

@ -6112,11 +6112,11 @@ def traverse_dict(dictn, keys, casesense=True):
key = key.lower()
dictn = dictn.get(key)
elif isinstance(dictn, (list, tuple, compat_str)):
key, n = int_or_none(key), len(dictn)
if key is not None and -n <= key < n:
dictn = dictn[key]
if ':' in key:
key = slice(*map(int_or_none, key.split(':')))
else:
dictn = None
key = int_or_none(key)
dictn = try_get(dictn, lambda x: x[key])
else:
return None
return dictn