RegularExpression#

Module providing routines to check and convert between regular and file expressions.

Utility module fused by ClearMap.Utils.TagExpression.

class PatternInverter(groups=None)[source]#

Bases: object

generate_any(pattern)[source]#

generate_assert(pattern)[source]#

generate_assert_not(pattern)[source]#

generate_at(pattern)[source]#

generate_branch(pattern)[source]#

generate_group(pattern, group_name)[source]#

generate_group_ref(pattern)[source]#

generate_in(pattern)[source]#

generate_literal(pattern)[source]#

generate_max_repeat(pattern)[source]#

generate_min_repeat(pattern)[source]#

generate_negate(pattern)[source]#

generate_not_literal(pattern)[source]#

generate_range(pattern)[source]#

generate_re(pattern)[source]#

generate_re_type(pattern)[source]#

generate_subpattern(pattern)[source]#

at_categories = {AT_BEGINNING: '^', AT_BEGINNING_STRING: '\\A', AT_BOUNDARY: '\\b', AT_NON_BOUNDARY: '\\B', AT_END: '$', AT_END_STRING: '\\Z'}#

escapes = {7: '\\a', 8: '\\b', 9: '\\t', 10: '\\n', 11: '\\v', 12: '\\f', 13: '\\r', 92: '\\'}#

in_categories = {CATEGORY_DIGIT: '\\d', CATEGORY_NOT_DIGIT: '\\D', CATEGORY_SPACE: '\\s', CATEGORY_NOT_SPACE: '\\S', CATEGORY_WORD: '\\w', CATEGORY_NOT_WORD: '\\W'}#

expression_to_glob(expression, replace=None, default='*', ignore='.[]')[source]#

Converts a regular expression to a glob expression, e.g. to search for files

Arguments

expressionstr: The regular expression.
replacedict, all or None: A dictionary specifying how to replace specific groups. If all or None, all groups are replaced with the default.
ignorelist of chars: Ignore these special chars in the regular expression.

Returns

expressionstr: The regular expression in glob form.

expression_to_pattern(expression, ignore=None)[source]#

Convert a regular expression to a parsed pattern for manipulation

Arguments

expressionstr: The regular expression to convert.

Returns

patternlist: The parsed pattern of the regular expression.

format_expression(expression, ignore=None)[source]#

Inserts escapes infront of certain regular expression symbols.

Arguments

expressionstr: The regulsr expresion.
ignorelist of chars: A list of characters to ignore as regular expressions commands.

Returns

expressionstr: The regular expression with escaped characters that are ignored.

glob_to_expression(expression, groups=None, to_group='*')[source]#

Converts a glob expression to a regular expression

Arguments

expressionstr: A glob expression.
groupsdict or None: A dicitonary specifying how to name groups in the form {id : name}
to_grouplist of chars or None: Glob placeholders to convert to a group.

Returns

expressionstr: The regular expression.

group_dict(expression, value, as_types=[<class 'int'>, <class 'float'>])[source]#

Returns a dictionary with the values of the groups in the regular expression that match the value string.

Arguments

expressionstring: The regular expression.
valuestring: The text to match and extract group values from.
as_typeslist of types: List of types to try to convert the extracted group value to.

Returns

valuesdict: The values for each group item.

group_names(expression)[source]#

Returns the names of groups in the regular expression

Arguments

expressionstr: The regular expression.

Returns

nameslist of str: The group names in the regular expression sorted according to appearance.

insert_group_names(expression, groups=None, ignore=None)[source]#

Inserts group names into a regular expression for spcified groups.

Arguments

expressionstr: The regular expression.
groupsdict or None: A dictionary specifying the group names as {groupid : groupname}.

Returns

expressionstr: The regular expression with named groups.

is_expression(expression, group_names=None, n_patterns=None, ignore=None, exclude=None, verbose=False)[source]#

Checks if the regular expression fullfills certain criteria

Arguments

expressionstr: The regular expression to check.
group_nameslist of str or None: List of group names expected to be present in the expression.
n_patternsint or None: Number of group patterns to expect. If negative, the expression is expted to have at least this number of groups.
ignorelist of chars or None: Optional list of chars that should not be regarded as a regular expression command. Useful for filenames setting ignore = [‘.’].
excludelist of str or None: Exculde these tokens when counting groups.
verbosebool: If True, print reason for expression to not fullfil desired criteria.

Returns

is_expressionbool: Returns True if the expression fullfills the desired criteria.

n_groups(expression)[source]#

Returns the number of groups in the expression.

Arguments

expressionstr: The regular expression.

Returns

nint: The number of groups in the epxression.

pattern_to_expression(pattern)[source]#

Convert a pattern to regular expression

Arguments

patternlist: The regular expression in pattern form.

Returns

expressionstr: The regular expression.

replace(expression, replace=None, ignore=None)[source]#

Replaces patterns in a regular expression with given strings

Arguments

expressionstr: The regular expression.
replacedict: The replacements to do in the regular expression given as {pos : str} or {groupname : str}.
ignorelist or chars: Ignore certain regular expression commands.

Returns

replacedstr: The regular expression with replacements.

subpatterns_to_groups(expression, ignore=None, exclude=None, group_names=None)[source]#

Replaces subpatterns with groups in a regular expression.

Arguments

expressionstr: The regular expression to check.
ignorelist of chars or None: Optional list of chars that should not be regarded as a regular expression command. Useful for filenames setting ignore = [‘.’].
excludelist of str or None: Exculde these tokens when counting groups.
group_nameslist of str: The group names to use for the new groups.

Returns

expressionstr: The regular expression with subpatterns replaced as groups.