-}
-
- printf("\n\nUnicode Set Patterns:\n"
- " Pattern Description\n"
- " Ranges [a-z] The lower case letters a through z\n"
- " Named Chars [abc123] The six characters a,b,c,1,2 and 3\n"
- " String [abc{def}] chars a, b and c, and string 'def'\n"
- " Categories [\\p{Letter}] Perl General Category 'Letter'.\n"
- " Categories [:Letter:] Posix General Category 'Letter'.\n"
- "\n"
- " Combination Example\n"
- " Union [[:Greek:] [:letter:]]\n"
- " Intersection [[:Greek:] & [:letter:]]\n"
- " Set Complement [[:Greek:] - [:letter:]]\n"
- " Complement [^[:Greek:] [:letter:]]\n"
- "\n"
- "see: http://icu.sourceforge.net/userguide/unicodeSet.html\n"
- "\n"
- "Examples:\n"
- " [:Punctuation:] Any-Remove\n"
- " [:Cased-Letter:] Any-Upper\n"
- " [:Control:] Any-Remove\n"
- " [:Decimal_Number:] Any-Remove\n"
- " [:Final_Punctuation:] Any-Remove\n"
- " [:Georgian:] Any-Upper\n"
- " [:Katakana:] Any-Remove\n"
- " [:Arabic:] Any-Remove\n"
- " [:Punctuation:] Remove\n"
- " [[:Punctuation:]-[.,]] Remove\n"
- " [:Line_Separator:] Any-Remove\n"
- " [:Math_Symbol:] Any-Remove\n"
- " Lower; [:^Letter:] Remove (word tokenization)\n"
- " [:^Number:] Remove (numeric tokenization)\n"
- " [:^Katagana:] Remove (remove everything except Katagana)\n"
- " Lower;[[:WhiteSpace:][:Punctuation:]] Remove (word tokenization)\n"
- " NFD; [:Nonspacing Mark:] Remove; NFC (removes accents from characters)\n"
- " [A-Za-z]; Lower(); Latin-Katakana; Katakana-Hiragana (transforms latin and katagana to hiragana)\n"
- " [[:separator:][:start punctuation:][:initial punctuation:]] Remove \n"
- "\n"
- "see http://icu.sourceforge.net/userguide/Transform.html\n"
- " http://www.unicode.org/Public/UNIDATA/UCD.html\n"
- " http://icu.sourceforge.net/userguide/Transform.html\n"
- " http://icu.sourceforge.net/userguide/TransformRule.html\n"
- );
-#endif