Encode-Guess-Educated

 view release on metacpan or  search on metacpan

lib/Encode/Guess/Educated.pm  view on Meta::CPAN

    0x0005D7 =>       6,   #  ×—  gc=Lo   sc=Hebrew     HEBREW LETTER HET
    0x010907 =>       1,   #  𐤇  gc=Lo   sc=Phoenician PHOENICIAN LETTER HET
    0x01090B =>       1,   #  𐤋  gc=Lo   sc=Phoenician PHOENICIAN LETTER LAMD
    0x010913 =>       1,   #  𐤓  gc=Lo   sc=Phoenician PHOENICIAN LETTER ROSH
    0x00FEE9 =>       1,   #  ﻩ  gc=Lo   sc=Arabic     ARABIC LETTER HEH ISOLATED FORM
    0x0016B9 =>       1,   #  áš¹  gc=Lo   sc=Runic      RUNIC LETTER WUNJO WYNN W
    0x00209F =>      32,   # <unnamed codepoint>
);

my %elsevier_training = (
    0x00202A =>      21,   # <-> gc=Cf   sc=Common     LEFT-TO-RIGHT EMBEDDING
    0x002061 =>     154,   # <-> gc=Cf   sc=Common     FUNCTION APPLICATION
    0x00202B =>       1,   # <-> gc=Cf   sc=Common     RIGHT-TO-LEFT EMBEDDING
    0x002062 =>     143,   # <-> gc=Cf   sc=Common     INVISIBLE TIMES
    0x000092 =>      16,   # <-> gc=Cc   sc=Common     <control>
    0x000341 =>       6,   # ◌ ́  gc=Mn   sc=Inherited  COMBINING ACUTE TONE MARK
    0x000301 =>   57910,   # ◌ ́  gc=Mn   sc=Inherited  COMBINING ACUTE ACCENT
    0x000340 =>       4,   # ◌ ̀  gc=Mn   sc=Inherited  COMBINING GRAVE TONE MARK
    0x000300 =>    1230,   # ◌ ̀  gc=Mn   sc=Inherited  COMBINING GRAVE ACCENT
    0x000306 =>    1526,   # ◌ ̆  gc=Mn   sc=Inherited  COMBINING BREVE
    0x000302 =>    7848,   # ◌ ̂  gc=Mn   sc=Inherited  COMBINING CIRCUMFLEX ACCENT
    0x00030C =>    1919,   # ◌ ̌  gc=Mn   sc=Inherited  COMBINING CARON
    0x00030A =>     724,   # ◌ ̊  gc=Mn   sc=Inherited  COMBINING RING ABOVE

lib/Encode/Guess/Educated.pm  view on Meta::CPAN

    0x0036EE =>       1,  #  ã›® gc=Lo   sc=Han        CJK UNIFIED IDEOGRAPH-36EE
    0x0036EF =>       1,  #  㛯 gc=Lo   sc=Han        CJK UNIFIED IDEOGRAPH-36EF
    0x003B12 =>       1,  #  㬒 gc=Lo   sc=Han        CJK UNIFIED IDEOGRAPH-3B12
    0x003B21 =>       1,  #  㬡 gc=Lo   sc=Han        CJK UNIFIED IDEOGRAPH-3B21
    0x000085 =>     264,  # <--->gc=Cc   sc=Common     <control>
    0x000086 =>      14,  # <--->gc=Cc   sc=Common     <control>
    0x002061 =>   10097,  # <--->gc=Cf   sc=Common     FUNCTION APPLICATION
    0x00206C =>      17,  # <--->gc=Cf   sc=Common     INHIBIT ARABIC FORM SHAPING
    0x00206A =>       1,  # <--->gc=Cf   sc=Common     INHIBIT SYMMETRIC SWAPPING
    0x002062 =>     204,  # <--->gc=Cf   sc=Common     INVISIBLE TIMES
    0x00202A =>       1,  # <--->gc=Cf   sc=Common     LEFT-TO-RIGHT EMBEDDING
    0x00200E =>       5,  # <--->gc=Cf   sc=Common     LEFT-TO-RIGHT MARK
    0x0000AD =>    3587,  # <--->gc=Cf   sc=Common     SOFT HYPHEN
    0x00FEFF =>       9,  # <--->gc=Cf   sc=Common     ZERO WIDTH NO-BREAK SPACE
    0x00200B =>     128,  # <--->gc=Cf   sc=Common     ZERO WIDTH SPACE
    0x00200D =>      59,  # <--->gc=Cf   sc=Inherited  ZERO WIDTH JOINER
    0x100002 =>       2,  # <--->gc=Co   sc=Unknown    <unnamed code point in block=Supplementary Private Use Area-B>
    0x002028 =>   10940,  # <--->gc=Zl   sc=Common     LINE SEPARATOR
    0x002003 =>  602377,  # <--->gc=Zs   sc=Common     EM SPACE
    0x002000 =>       1,  # <--->gc=Zs   sc=Common     EN QUAD
    0x002002 =>    8517,  # <--->gc=Zs   sc=Common     EN SPACE

t/data/cp1252/10329150.cp1252  view on Meta::CPAN

   [EMBED]

   [1]SciVerse Home
   [2]ScienceDirect® Home
     * [3]Hub
     * [4]ScienceDirect
     * [5]Scopus

     * [6]Register
     * [7]Login[8]Login
     * [9]Go to SciVal Suite

t/data/good/10398587.utf8  view on Meta::CPAN

   [EMBED]

   [1]SciVerse Home
   [2]ScienceDirect® Home
     * [3]Hub
     * [4]ScienceDirect
     * [5]Scopus

     * [6]Register
     * [7]Login[8]Login
     * [9]Go to SciVal Suite



( run in 1.584 second using v1.01-cache-2.11-cpan-71847e10f99 )