bgc_data_processing.utils.patterns

Filenames Patterns building.

FileNamePattern(str_pattern, year_field='years', month_field='months', day_field='days')

Create the pattern to use to select filenames.

Parameters:

Name	Type	Description	Default
str_pattern	str	Raw string pattern, with field to infer written in brackets ('{'&'}').	required
year_field	str	Name of the field supposed to contain the year informations. , by default "years"	'years'
month_field	str	Name of the field supposed to contain the month informations. , by default "months"	'months'
day_field	str	Name of the field supposed to contain the day informations. , by default "days"	'days'

Source code in src/bgc_data_processing/utils/patterns.py

def __init__(
    self,
    str_pattern: str,
    year_field: str = "years",
    month_field: str = "months",
    day_field: str = "days",
) -> None:
    self._base = str_pattern
    self._year = year_field
    self._month = month_field
    self._day = day_field

build_from_constraint(date_constraint)

Build the pattern from date constraints.

Parameters:

Name	Type	Description	Default
date_constraint	dict	Date constraint.	required

Returns:

Type	Description
str	Final pattern.

Source code in src/bgc_data_processing/utils/patterns.py

def build_from_constraint(self, date_constraint: dict) -> "PatternMatcher":
    """Build the pattern from date constraints.

    Parameters
    ----------
    date_constraint : dict
        Date constraint.

    Returns
    -------
    str
        Final pattern.
    """
    date_min, date_max = self._parse_dates_from_constraints(date_constraint)
    return self.build(date_min=date_min, date_max=date_max)

build(date_min, date_max)

Build the pattern from the starting and ending dates.

Parameters:

Name	Type	Description	Default
date_min	date | None	Starting date.	required
date_max	date | None	Ending date.	required

Returns:

Type	Description
str	Final pattern.

Source code in src/bgc_data_processing/utils/patterns.py

def build(
    self,
    date_min: dt.date | None,
    date_max: dt.date | None,
) -> "PatternMatcher":
    """Build the pattern from the starting and ending dates.

    Parameters
    ----------
    date_min : dt.date | None
        Starting date.
    date_max : dt.date | None
        Ending date.

    Returns
    -------
    str
        Final pattern.
    """
    interval_patterns = self._slice(date_min=date_min, date_max=date_max)
    pattern = "|".join(map(self._create_pattern, interval_patterns))
    return PatternMatcher(pattern=pattern)

DateIntervalPattern(date_min, date_max, precision='day')

Create the patterns values for a given date interval.

Parameters:

Name	Type	Description	Default
date_min	date | None	Starting date of the interval.	required
date_max	date | None	Ending date of the interval.	required
precision	str	Precision of the interval. A "day" precision means that year and month are constant, therefore the required days are contained between the minimum day number and the maximum day number. A "month" precision means that year is constant but months are different but totally included (from first day to last day.) in the interval., therefore the required months are contained between the minimum months number and the maximum months number. A "year" precision means the years to include are different but totally included (from first day to last day.) in the interval, therefore the required years are contained between the minimum year number and the maximum year number., by default "day"	'day'

Source code in src/bgc_data_processing/utils/patterns.py

def __init__(
    self,
    date_min: dt.date | None,
    date_max: dt.date | None,
    precision: str = "day",
) -> None:
    if not (date_min is None and date_max is None):
        self._validate_inputs(
            date_min=date_min,
            date_max=date_max,
            precision=precision,
        )

    self._precision = precision
    self._min = date_min
    self._max = date_max

years: str property

'year' part of the pattern.

months: str property

'month' part of the pattern.

days: str property

'day' part of the pattern.

__repr__()

Object representation string.

Returns:

Type	Description
str	Starting date - Ending date ; precision: interval precision.

Source code in src/bgc_data_processing/utils/patterns.py

def __repr__(self) -> str:
    """Object representation string.

    Returns
    -------
    str
        Starting date - Ending date ; precision: interval precision.
    """
    return f"{self._min} - {self._max} ; precision: {self._precision}"

with_day_precision(date_min, date_max) classmethod

Create a DateIntervalPattern with day precision.

Parameters:

Name	Type	Description	Default
date_min	date	Starting date.	required
date_max	date	Ending date.	required

Returns:

Type	Description
DateIntervalPattern	Date interval pattern.

Source code in src/bgc_data_processing/utils/patterns.py

@classmethod
def with_day_precision(
    cls,
    date_min: dt.date,
    date_max: dt.date,
) -> "DateIntervalPattern":
    """Create a DateIntervalPattern with day precision.

    Parameters
    ----------
    date_min : dt.date
        Starting date.
    date_max : dt.date
        Ending date.

    Returns
    -------
    DateIntervalPattern
        Date interval pattern.
    """
    return cls(
        date_min=date_min,
        date_max=date_max,
        precision=cls._day_precision_label,
    )

with_month_precision(date_min, date_max) classmethod

Create a DateIntervalPattern with month precision.

Parameters:

Name	Type	Description	Default
date_min	date	Starting date.	required
date_max	date	Ending date.	required

Returns:

Type	Description
DateIntervalPattern	Date interval pattern.

Source code in src/bgc_data_processing/utils/patterns.py

@classmethod
def with_month_precision(
    cls,
    date_min: dt.date,
    date_max: dt.date,
) -> "DateIntervalPattern":
    """Create a DateIntervalPattern with month precision.

    Parameters
    ----------
    date_min : dt.date
        Starting date.
    date_max : dt.date
        Ending date.

    Returns
    -------
    DateIntervalPattern
        Date interval pattern.
    """
    return cls(
        date_min=date_min,
        date_max=date_max,
        precision=cls._month_precision_label,
    )

with_year_precision(date_min, date_max) classmethod

Create a DateIntervalPattern with year precision.

Parameters:

Name	Type	Description	Default
date_min	date	Starting date.	required
date_max	date	Ending date.	required

Returns:

Type	Description
DateIntervalPattern	Date interval pattern.

Source code in src/bgc_data_processing/utils/patterns.py

@classmethod
def with_year_precision(
    cls,
    date_min: dt.date,
    date_max: dt.date,
) -> "DateIntervalPattern":
    """Create a DateIntervalPattern with year precision.

    Parameters
    ----------
    date_min : dt.date
        Starting date.
    date_max : dt.date
        Ending date.

    Returns
    -------
    DateIntervalPattern
        Date interval pattern.
    """
    return cls(
        date_min=date_min,
        date_max=date_max,
        precision=cls._year_precision_label,
    )

PatternMatcher(pattern, validation_function=lambda : True)

Matcher to find files which match agiven pattern.

Parameters:

Name	Type	Description	Default
pattern	str	Pattern to match.	required
validation_function	Callable	Function to use to validate that files are to be loaded., by default lambdafilepath	lambda : True

Source code in src/bgc_data_processing/utils/patterns.py

def __init__(
    self,
    pattern: str,
    validation_function: Callable = lambda filepath: True,  # noqa: ARG005
) -> None:
    self._pattern = pattern
    self.validate = validation_function

validate: Callable property writable

Validation function.

select_matching_filepath(research_directory)

Select the filepaths matching the pattern.

Parameters:

Name	Type	Description	Default
research_directory	Path | str	Directory to serach for files.	required

Returns:

Type	Description
list[Path]	List of correct paths.

Source code in src/bgc_data_processing/utils/patterns.py

def select_matching_filepath(
    self,
    research_directory: Path | str,
) -> list[Path]:
    """Select the filepaths matching the pattern.

    Parameters
    ----------
    research_directory : Path | str
        Directory to serach for files.

    Returns
    -------
    list[Path]
        List of correct paths.
    """
    return self._recursive_match(
        research_dir=Path(research_directory),
        pattern=self._pattern,
    )