#  ---------------------------------------------------------------------
#  Frogans Address Composition Rules - FACR 1.0
#  FACR Lookup Table
#  ---------------------------------------------------------------------
#
#  Reference: FLT05_LC_Arabic_Employable
#
#  Description: This FACR lookup table contains the list of code points
#  that are employable characters of LC-Arabic with, for each code
#  point, the value of its Script property.  This lookup table is used
#  in the |c1_verify_employable_characters| function defined in Appendix
#  C.1 of the FACR specification document.
#
#  File name:     facr10-adopted.spec.flt05-lc-arabic-employable.txt
#  File created:  2014-12-04T15:55:37Z
#
#  For additional information on the format of FACR lookup tables, see
#  Appendix A in the FACR specification document.
#
#  For additional information on the use of FACR lookup tables, see
#  Appendix C in the FACR specification document.
#
#  Properties mentioned in this document are those defined in the
#  Unicode Standard.
#
#  This document is accessible at the following permanent URL:
#  https://www.frogans.org/en/resources/facr/access.html.
#
#  This document must be used in compliance with the Frogans Technology
#  User Policy, accessible at the following permanent URL:
#  https://www.frogans.org/en/resources/ftup/access.html.
#
#  Copyright (C) 2014 OP3FT.  All rights reserved.
#
#
#  ---------------------------------------------------------------------
#  Third-party source materials used to create this lookup table
#  ---------------------------------------------------------------------
#
#  File: core.zip
#
#  - Location:
#    http://unicode.org/Public/cldr/26/core.zip
#
#  - Description:
#    core.zip is a file in release 26 of the Unicode Common Locale Data
#    Repository (CLDR).  It contains Unicode CLDR directories and files.
#    For details on the format and contents of this file, see
#    http://cldr.unicode.org/.
#
#  - Copyright and Permission Notice:
#    Copyright (C) 1991-2014 Unicode, Inc.  All rights reserved.
#    Distributed under the Terms of Use in
#    http://www.unicode.org/copyright.html.
#
#    Permission is hereby granted, free of charge, to any person
#    obtaining a copy of the Unicode data files and any associated
#    documentation (the "Data Files") or Unicode software and any
#    associated documentation (the "Software") to deal in the Data Files
#    or Software without restriction, including without limitation the
#    rights to use, copy, modify, merge, publish, distribute, and/or
#    sell copies of the Data Files or Software, and to permit persons to
#    whom the Data Files or Software are furnished to do so, provided
#    that (a) the above copyright notice(s) and this permission notice
#    appear with all copies of the Data Files or Software, (b) both the
#    above copyright notice(s) and this permission notice appear in
#    associated documentation, and (c) there is clear notice in each
#    modified Data File or in the Software as well as in the
#    documentation associated with the Data File(s) or Software that the
#    data or software has been modified.
#
#
#  File: UnicodeData.txt
#
#  - Location:
#    http://www.unicode.org/Public/7.0.0/ucd/UnicodeData.txt
#
#  - Description:
#    UnicodeData.txt is a file in the Unicode Character Database of
#    version 7.0.0 of the Unicode Standard.  It lists all Unicode
#    characters and their properties.  For details on the format and
#    contents of this file, see revision 14 of the Unicode Standard
#    Annex #44 at
#    http://www.unicode.org/reports/tr44/tr44-14.html.
#
#  - Copyright and Permission Notice:
#    Copyright (C) 1991-2014 Unicode, Inc.  All rights reserved.
#    Distributed under the Terms of Use in
#    http://www.unicode.org/copyright.html.
#
#    See the Copyright and Permission Notice for the core.zip file
#    above.
#
#
#  File: SpecialCasing.txt
#
#  - Location:
#    http://www.unicode.org/Public/7.0.0/ucd/SpecialCasing.txt
#
#  - Description:
#    SpecialCasing.txt is a file in the Unicode Character Database of
#    version 7.0.0 of the Unicode Standard.  It is a supplement to the
#    UnicodeData.txt file and provides additional information about the
#    casing of Unicode characters.  For details on the format and
#    contents of this file, see revision 14 of the Unicode Standard
#    Annex #44 at http://www.unicode.org/reports/tr44/tr44-14.html.
#
#  - Copyright and Permission Notice:
#    Copyright (C) 1991-2014 Unicode, Inc.  All rights reserved.
#    Distributed under the Terms of Use in
#    http://www.unicode.org/copyright.html.
#
#    See the Copyright and Permission Notice for the core.zip file
#    above.
#
#
#  File: Scripts.txt
#
#  - Location:
#    http://www.unicode.org/Public/7.0.0/ucd/Scripts.txt
#
#  - Description:
#    Scripts.txt is a file in the Unicode Character Database of version
#    7.0.0 of the Unicode Standard.  It lists code points and their
#    associated scripts.  For details on the format and contents of this
#    file, see revision 14 of the Unicode Standard Annex #44 at
#    http://www.unicode.org/reports/tr44/tr44-14.html.
#
#  - Copyright and Permission Notice:
#    Copyright (C) 1991-2014 Unicode, Inc.  All rights reserved.
#    Distributed under the Terms of Use in
#    http://www.unicode.org/copyright.html.
#
#    See the Copyright and Permission Notice for the core.zip file
#    above.
#
#
#  ---------------------------------------------------------------------
#  IFAP lookup tables used to create this lookup table
#  ---------------------------------------------------------------------
#
#  ILT08_Eligible_Characters
#
#  This IFAP lookup table is part of version 1.1 of the International
#  Frogans Address Pattern (IFAP) specification published by the OP3FT.
#
#  The IFAP specification, including its lookup tables, is accessible at
#  the following permanent URL:
#  https://www.frogans.org/en/resources/ifap/access.html
#
#
#  ---------------------------------------------------------------------
#  Other FACR lookup tables used to create this lookup table
#  ---------------------------------------------------------------------
#
#  None
#
#
#  ---------------------------------------------------------------------
#  Description of the fields in this lookup table
#  ---------------------------------------------------------------------
#
#  Field count: 2
#
#
#  Field 1: CODE_POINT
#
#  - Description:
#    A code point or a range of code points
#
#  Field 2: SCRIPT
#
#  - Description:
#    A text value representing the Script property of the code point or
#    the range of code points
#
#
#  ---------------------------------------------------------------------
#  Method used to compute the field values in this lookup table
#  ---------------------------------------------------------------------
#
#  The data lines following these comments are created by the six-step
#  process described below.
#
#  During the execution of this process, four temporary tables TT1, TT2,
#  TT3, and TT4 are created and used for storage of values.  These
#  temporary tables are discarded at the end of the process.
#
#
#  Step 1
#
#  The purpose of this step is to produce a list of Unicode language
#  identifiers.  The text values resulting from this step are stored in
#  TT1.
#
#  The process which follows uses the XML data file supplementalData.xml
#  located in the common/supplemental/ directory of core.zip.
#
#  After parsing this XML data file, each <language> element contained
#  in the <languageData> element is analyzed.  If a <language> element
#  is skipped in the process below, then the process continues with the
#  next <language> element.
#
#  If the value of the "scripts" attribute does not contain 'Arab', then
#  the <language> element is skipped.  The value of the "scripts"
#  attribute contains one or more script subtags, separated by spaces.
#
#  Otherwise, if the value of the "alt" attribute is equal to
#  'secondary', then the <language> element is skipped.  According to
#  the specification of this XML data file, the "alt" attribute is not
#  required and it is only included, with a value equal to 'secondary',
#  if the language identifier does not correspond with a modern
#  language, or the script is not a modern script, or the language is
#  not a major language of the territory.
#
#  Otherwise, if the value of the "scripts" attribute contains 'Arab'
#  only:
#
#  - If the "territories" attribute is included, then for each region
#    subtag within the value of the "territories" attribute, a line is
#    added to TT1 containing a concatenation of the value of the "type"
#    attribute and '_' and the region subtag.
#
#  - Otherwise, if the "territories" attribute is not included, then a
#    line is added to TT1 containing the value of the "type" attribute.
#
#  Otherwise, if the value of the "scripts" attribute contains 'Arab'
#  amongst other script subtags:
#
#  - If the "territories" attribute is included, then for each region
#    subtag within the value of the "territories" attribute, a line is
#    added to TT1 containing a concatenation of the value of the "type"
#    attribute and '_Arab_' and the region subtag.
#
#  - Otherwise, if the "territories" attribute is not included, then a
#    line is added to TT1 containing a concatenation of the value of the
#    "type" attribute and '_Arab'.
#
#
#  Step 2
#
#  The purpose of this step is to produce a list of exemplar characters.
#  The code points resulting from this step are stored in TT2.
#
#  For each language identifier in TT1, the fully-resolved XML data file
#  associated with that language identifier is produced from the XML
#  data files within the common/main/ directory of core.zip and the
#  process described in revision 35 of the Unicode Technical Standard
#  #35, Unicode Locale Data Markup Language (LDML), Part 1, Core, 4.2.2
#  Resolved Data File.
#  See http://www.unicode.org/reports/tr35/tr35-35/tr35.html.
#
#  The exemplar characters are retrieved from the <exemplarCharacters>
#  elements contained in the <characters> element of the fully-resolved
#  XML data file if either of the following conditions is met: the
#  "type" attribute of the <exemplarCharacters> element is not included,
#  or the value of the "type" attribute is equal to 'punctuation'.  Note
#  that exemplar characters are not retrieved from <exemplarCharacters>
#  elements which have "type" attribute values equal to either
#  'auxiliary' or 'index'.
#
#  The text content of the <exemplarCharacters> element is converted to
#  a list of code points using a process based upon the syntax of
#  exemplar characters described in revision 35 of the Unicode Technical
#  Standard #35, Unicode Locale Data Markup Language (LDML), Part 2,
#  General, 3.1 Exemplar Syntax.
#
#  For each code point in this list that has not already been added to
#  TT2, a line is added to TT2 containing the code point.
#
#  The text content of the <defaultNumberingSystem> element contained in
#  the <numbers> element of the fully-resolved XML data file is looked
#  up in the XML data file numberingSystems.xml located in the
#  common/supplemental/ directory of core.zip.  This lookup is performed
#  on the value of the "id" attribute of the <numberingSystem> element
#  contained in the <numberingSystems> element.  If the value of the
#  "type" attribute of the matching <numberingSystem> element is equal
#  to 'numeric', then the value of the "digits" attribute of that
#  element is retrieved and converted to ten individual code points.
#
#  For each of these ten code points that has not already been added to
#  TT2, a line is added to TT2 containing the code point.
#
#  Then the process continues with the next language identifier in TT1.
#
#
#  Step 3
#
#  The purpose of this step is to include code points corresponding to
#  uppercase and titlecase characters.  The code points resulting from
#  this step are stored in TT3.
#
#  Each line of TT2, corresponding to a code point, is read.
#
#  First, a line is added to TT3 containing the code point.
#
#  Second, the code point is looked up in UnicodeData.txt and the
#  thirteenth and the fifteenth fields in the semi-colon separated list
#  in matching lines of UnicodeData.txt are analyzed.  These fields
#  correspond to the Simple_Uppercase_Mapping and the
#  Simple_Titlecase_Mapping properties respectively.  If these fields
#  are not empty, then the value of each field is a code point.
#
#  If the thirteenth field is not empty, and its value has not already
#  been added to TT3, a line is added to TT3 containing its value.
#
#  If the fifteenth field is not empty, and its value has not already
#  been added to TT3, a line is added to TT3 containing its value.
#
#  Finally, the code point is looked up in the lines of
#  SpecialCasing.txt and the third and the fourth fields in the
#  semi-colon separated list in matching lines of SpecialCasing.txt are
#  analyzed.  These fields correspond to the Titlecase_Mapping and the
#  Uppercase_Mapping properties respectively.  If these fields are not
#  empty, then the value of each field is one or more code points.
#
#  If the third field is not empty, then it is analyzed.  For each
#  code point in the field, a line is added to TT3 containing the code
#  point, if the code point has not already been added to TT3.
#
#  If the fourth field is not empty, then its value is analyzed.  For
#  each code point contained in the value of the field, a line is added
#  to TT3 containing the code point, if the code point has not already
#  been added to TT3.
#
#
#  Step 4
#
#  The purpose of this step is to exclude code points in accordance with
#  section 10.5.2 of version 1.0 of the FACR specification.  No code
#  points are generated in this step.
#
#  The U+002A ASTERISK character is removed from TT3.
#
#  The following code points and range of code points are removed from
#  TT3:  U+064B .. U+0652, U+0654, U+0655, U+0656, U+0657, U+065A,
#  U+065B, U+0670, U+06EA, U+06ED.
#
#
#  Step 5
#
#  The purpose of this step is to exclude code points that are not
#  eligible characters according to version 1.1 of the IFAP
#  specification.  The code points resulting from this step are stored
#  in TT4.
#
#  Each line of TT3, corresponding to one or more code points, is read.
#  If a code point is skipped in the process below, then the process
#  continues with the next code point in the line or in the next line.
#
#  The code point is looked up in ILT08_Eligible_Characters.
#
#  If the code point is not found, then the code point is skipped.
#
#  Otherwise, in the data line of ILT08_Eligible_Characters that
#  contains the code point, if the second field (IS_ELIGIBLE) equals 0,
#  then the code point is skipped.
#
#  Otherwise, the code point is looked up in Scripts.txt to retrieve the
#  value of the Script property, which is the second field in the
#  semi-colon separated list in each line of Scripts.txt.
#
#  A line consisting of two fields is added to TT4:
#
#  - The value of the first field contains the code point.
#
#  - The value of the second field contains the value of the Script
#    property for the code point.
#
#
#  Step 6
#
#  The purpose of this step is to generate the data lines in
#  FLT05_LC_Arabic_Employable.
#
#  The lines in TT4 are sorted by the value of the first field.  Then
#  any lines in TT4 with consecutive values in the first field and
#  identical values in the second field are merged into a single line in
#  TT4 having the following values:
#
#  - The first field contains the code point range.
#
#  - The second field contains the value of the Script property for the
#    code point range.
#
#  When the above process is complete, for each line of TT4, a data line
#  is added to FLT05_LC_Arabic_Employable with the value of the two
#  fields CODE_POINT and SCRIPT:
#
#  - The first value contains the code point or code point range.
#
#  - The second value contains the value of the Script property for the
#    code point or code point range.  The value of this field can be
#    'Common' and 'Arabic'.
#
#
#  ---------------------------------------------------------------------
#  Generated data lines
#  ---------------------------------------------------------------------
#
CODE_POINT,SCRIPT
002D,Common
0030..0039,Common
0621..063A,Arabic
0641..064A,Arabic
0660..0669,Common
066E,Arabic
0672,Arabic
0679,Arabic
067C,Arabic
067E,Arabic
0681,Arabic
0685..0686,Arabic
0688..0689,Arabic
0691,Arabic
0693,Arabic
0696,Arabic
0698,Arabic
069A,Arabic
06A9,Arabic
06AB,Arabic
06AD,Arabic
06AF,Arabic
06BA,Arabic
06BC,Arabic
06BE,Arabic
06C1..06C2,Arabic
06C4,Arabic
06C6..06C9,Arabic
06CB..06CD,Arabic
06D0,Arabic
06D2,Arabic
06D5,Arabic
06F0..06F9,Arabic