Parsing Text – Tokens

/*
From Harbour changelog (at 2007-04-04 10:35 UTC+0200 By Przemyslaw Czerpak )
Added set of functions to manipulate string tokens:
HB_TOKENCOUNT( <cString>, [ <cDelim> ], [ <lSkipStrings> ],
 [ <lDoubleQuoteOnly> ] ) -> <nTokens>

 HB_TOKENGET( <cString>, <nToken>, [ <cDelim> ], [ <lSkipStrings> ],
 [ <lDoubleQuoteOnly> ] ) -> <cToken>

 HB_TOKENPTR( <cString>, @<nSkip>, [ <cDelim> ], [ <lSkipStrings> ],
 [ <lDoubleQuoteOnly> ] ) -> <cToken>

 HB_ATOKENS( <cString>, [ <cDelim> ], [ <lSkipStrings> ],
 [ <lDoubleQuoteOnly> ] ) -> <aTokens>

 All these functions use the same method of tokenization. They can
 accept as delimiters string longer then one character. By default
 they are using " " as delimiter. " " delimiter has special mening

 Unlike other delimiters repeted ' ' characters does not create empty
 tokens, f.e.: 

 HB_ATOKENS( " 1 2 3 " ) returns array:
 { "1", "2", "3" }

 Any other delimiters are restrictly counted, f.e.:

 HB_ATOKENS( ",,1,,2,") returns array:
 { "", "", "1", "", "2", "" }
And a strong suggession made at 2009-12-09 21:25 UTC+0100 ( By Przemyslaw Czerpak )
I strongly suggest to use hb_aTokens() and hb_token*() functions.
 They have more options and for really large data many times
 (even hundreds times) faster.

*/
#define CRLF HB_OsNewLine()
PROCEDURE Main()
LOCAL cTextFName := "Shakespeare.txt",;
 c1Line 

 SET COLO TO "W/B"
 SetMode( 40, 120 )

 CLS

 HB_MEMOWRIT( cTextFName,;
 "When in eternal lines to time thou grow'st," + CRLF + ;
 "So long as men can breathe, or eyes can see," + CRLF + ;
 "So long lives this, and this gives life to thee." )

 aLines := HB_ATOKENS( MEMOREAD( cTextFName ), CRLF )

 ?
 ? "Text file line by line :"
 ?
 AEVAL( aLines, { | c1Line | QOUT( c1Line ) } )
 ?
 WAIT "Press a key for parsing as words"
 CLS
 ?
 ? "Text file word by word :"
 ?
 FOR EACH c1Line IN aLines
 a1Line := HB_ATOKENS( c1Line ) 
 AEVAL( a1Line, { | c1Word | QOUT( c1Word ) } )
 NEXT 
 ?
 WAIT "Press a key for parsing directly as words"
 CLS
 ?
 ? "Text file directly word by word :"
 ?
 aWords := HB_ATOKENS( MEMOREAD( cTextFName ) )
 AEVAL( aWords, { | c1Word | QOUT( c1Word ) } ) 

 ?
 @ MAXROW(), 0
 WAIT "EOF TP_Token.prg" 

RETURN // TP_Token.Main()
 TP_Token
Advertisements