forgex_segment_m Module

Note

Support for handling many Unicode whitespace characters is currently not available, but will be added in the future.

Note

We would like to add a procedure to merge adjacent segments with the same transition destination into a single segment.


Uses


Variables

Type Visibility Attributes Name Initial
type(segment_t), public, parameter :: SEG_ANY = segment_t(UTF8_CODE_MIN, UTF8_CODE_MAX)
type(segment_t), public, parameter :: SEG_CR = segment_t(13, 13)
type(segment_t), public, parameter :: SEG_DIGIT = segment_t(48, 57)
type(segment_t), public, parameter :: SEG_EMPTY = segment_t(UTF8_CODE_EMPTY, UTF8_CODE_EMPTY)
type(segment_t), public, parameter :: SEG_EPSILON = segment_t(UTF8_CODE_MAX+3, UTF8_CODE_MAX+3)
type(segment_t), public, parameter :: SEG_ERROR = segment_t(-2, -2)
type(segment_t), public, parameter :: SEG_FF = segment_t(12, 12)
type(segment_t), public, parameter, dimension(3) :: SEG_HEX = [SEG_DIGIT, segment_t(65, 70), segment_t(97, 102)]
type(segment_t), public, parameter :: SEG_INIT = segment_t(UTF8_CODE_MAX+2, UTF8_CODE_MAX+2)
type(segment_t), public, parameter :: SEG_LF = segment_t(10, 10)
type(segment_t), public, parameter :: SEG_LOWERCASE = segment_t(97, 122)
type(segment_t), public, parameter :: SEG_NULL = segment_t(0, 0)
type(segment_t), public, parameter :: SEG_SPACE = segment_t(32, 32)
type(segment_t), public, parameter :: SEG_TAB = segment_t(9, 9)
type(segment_t), public, parameter :: SEG_UNDERSCORE = segment_t(95, 95)
type(segment_t), public, parameter :: SEG_UPPER = segment_t(UTF8_CODE_MAX+1, UTF8_CODE_MAX+1)
type(segment_t), public, parameter :: SEG_UPPERCASE = segment_t(65, 90)
type(segment_t), public, parameter :: SEG_WHOLE = segment_t(0, UTF8_CODE_MAX)
type(segment_t), public, parameter :: SEG_ZENKAKU_SPACE = segment_t(12288, 12288)

Interfaces

public interface operator(.in.)

This interface block provides the .in. operator, which checks whether an integer and a segment, an integer and a list of segments, or a segment and a segment, is contained in the latter, respectively.

  • private pure elemental function arg_in_segment(a, seg) result(res)

    Checks if the given integer is within the specified segment.

    This function determines whether the integer a falls within the range defined by the min and max values of the segment_t type.

    Arguments

    Type IntentOptional Attributes Name
    integer(kind=int32), intent(in) :: a
    type(segment_t), intent(in) :: seg

    Return Value logical

  • private pure function arg_in_segment_list(a, seg_list) result(res)

    Check if the ginve integer is within any of specified segments in a list.

    This function determins whether the integer a falls within any of the ranges defined by the min and max value of the segment_t type in the provided list of segments.

    Arguments

    Type IntentOptional Attributes Name
    integer(kind=int32), intent(in) :: a
    type(segment_t), intent(in) :: seg_list(:)

    Return Value logical

  • private pure elemental function seg_in_segment(a, b) result(res)

    Check if the one segment is completely within another segment.

    This function determines whether the segment a is entirely within the range specified by the segment b.

    Arguments

    Type IntentOptional Attributes Name
    type(segment_t), intent(in) :: a
    type(segment_t), intent(in) :: b

    Return Value logical

  • private pure function seg_in_segment_list(seg, list) result(res)

    Arguments

    Type IntentOptional Attributes Name
    type(segment_t), intent(in) :: seg
    type(segment_t), intent(in) :: list(:)

    Return Value logical

public interface operator(/=)

This interface block provides a not equal operator for comparing segments.

  • private pure elemental function segment_not_equiv(a, b) result(res)

    Check if two segments are not equivalent.

    This function determines whether the segment a is not equivalent to the segment b, meaning their min or max values are different.

    Arguments

    Type IntentOptional Attributes Name
    type(segment_t), intent(in) :: a
    type(segment_t), intent(in) :: b

    Return Value logical

public interface operator(==)

This interface block provides a equal operator for comparing segments.

  • private pure elemental function segment_equivalent(a, b) result(res)

    Check if the one segment is exactly equal to another segment.

    This function determines wheter the segment a is equivalent to the segment b, meaning both their min and max values are identical.

    Arguments

    Type IntentOptional Attributes Name
    type(segment_t), intent(in) :: a
    type(segment_t), intent(in) :: b

    Return Value logical


Derived Types

type, public ::  segment_t

This derived-type represents a contiguous range of the Unicode character set as a min and max value, providing an effective way to represent ranges of characters when building automata where a range characters share the same transition destination.

Components

Type Visibility Attributes Name Initial
integer(kind=int32), public :: max = UTF8_CODE_MAX+2
integer(kind=int32), public :: min = UTF8_CODE_MAX+2

Type-Bound Procedures

procedure, public :: print => segment_for_print
procedure, public :: validate => segment_is_valid

Functions

public pure function join_two_segments(segA, segB) result(res)

This function converts two isolated segments into single fused segment and returns it.

Arguments

Type IntentOptional Attributes Name
type(segment_t), intent(in) :: segA
type(segment_t), intent(in) :: segB

Return Value type(segment_t)

public pure elemental function segment_is_valid(self) result(res)

Checks if a segment is valid.

Read more…

Arguments

Type IntentOptional Attributes Name
class(segment_t), intent(in) :: self

Return Value logical

public pure function symbol_to_segment(symbol) result(res)

This function convert an input symbol into the segment corresponding it.

Arguments

Type IntentOptional Attributes Name
character(len=*), intent(in) :: symbol

Return Value type(segment_t)

public pure function total_width_of_segment(seg_list) result(res)

Arguments

Type IntentOptional Attributes Name
type(segment_t), intent(in) :: seg_list(:)

Return Value integer

public pure function which_segment_symbol_belong(segments, symbol) result(res)

This function takes an array of segments and a character as arguments, and returns the segment as rank=1 array to which symbol belongs (included in the segment interval).

Arguments

Type IntentOptional Attributes Name
type(segment_t), intent(in) :: segments(:)
character(len=*), intent(in) :: symbol

Return Value type(segment_t)

public pure elemental function width_of_segment(seg) result(res)

Arguments

Type IntentOptional Attributes Name
type(segment_t), intent(in) :: seg

Return Value integer

private pure elemental function arg_in_segment(a, seg) result(res)

Checks if the given integer is within the specified segment.

Read more…

Arguments

Type IntentOptional Attributes Name
integer(kind=int32), intent(in) :: a
type(segment_t), intent(in) :: seg

Return Value logical

private pure function arg_in_segment_list(a, seg_list) result(res)

Check if the ginve integer is within any of specified segments in a list.

Read more…

Arguments

Type IntentOptional Attributes Name
integer(kind=int32), intent(in) :: a
type(segment_t), intent(in) :: seg_list(:)

Return Value logical

private pure elemental function seg_in_segment(a, b) result(res)

Check if the one segment is completely within another segment.

Read more…

Arguments

Type IntentOptional Attributes Name
type(segment_t), intent(in) :: a
type(segment_t), intent(in) :: b

Return Value logical

private pure function seg_in_segment_list(seg, list) result(res)

Arguments

Type IntentOptional Attributes Name
type(segment_t), intent(in) :: seg
type(segment_t), intent(in) :: list(:)

Return Value logical

private pure elemental function segment_equivalent(a, b) result(res)

Check if the one segment is exactly equal to another segment.

Read more…

Arguments

Type IntentOptional Attributes Name
type(segment_t), intent(in) :: a
type(segment_t), intent(in) :: b

Return Value logical

private function segment_for_print(seg) result(res)

Converts a segment to a printable string representation.

Read more…

Arguments

Type IntentOptional Attributes Name
class(segment_t), intent(in) :: seg

Return Value character(len=:), allocatable

private pure elemental function segment_not_equiv(a, b) result(res)

Check if two segments are not equivalent.

Read more…

Arguments

Type IntentOptional Attributes Name
type(segment_t), intent(in) :: a
type(segment_t), intent(in) :: b

Return Value logical


Subroutines

public pure subroutine hex2seg(str, seg, ierr)

This subroutine converts character string that represents hexadecimal value to the segment corresponding its integer type.

Arguments

Type IntentOptional Attributes Name
character(len=*), intent(in) :: str
type(segment_t), intent(inout) :: seg
integer, intent(inout) :: ierr

public pure subroutine invert_segment_list(list)

This subroutine inverts a list of segment ranges representing Unicode characters. It compute the complement of the given ranges and modifies the list accordingly.

Arguments

Type IntentOptional Attributes Name
type(segment_t), intent(inout), allocatable :: list(:)

public pure subroutine merge_segments(segments)

Arguments

Type IntentOptional Attributes Name
type(segment_t), intent(inout), allocatable :: segments(:)

public pure subroutine prop2seg(property, seglist, ierr)

Arguments

Type IntentOptional Attributes Name
character(len=*), intent(in) :: property
type(segment_t), intent(inout), allocatable :: seglist(:)
integer, intent(inout) :: ierr

public pure subroutine register_segment_to_list(segment_list, segment, k, ierr)

This procedure registers given segment_t value to segment_t type array, increments counter of the actual size of the array, and initializes temporary variable.

Arguments

Type IntentOptional Attributes Name
type(segment_t), intent(inout) :: segment_list(:)
type(segment_t), intent(inout) :: segment
integer, intent(inout) :: k
integer, intent(inout) :: ierr

public pure subroutine sort_segment_by_min(segments)

Arguments

Type IntentOptional Attributes Name
type(segment_t), intent(inout), allocatable :: segments(:)