PureBasic Forums - English

Code: Select all

Procedure.i CountWords(a$) ;-Count Words
  
  ReplaceString(a$,Chr(10)," ", #PB_String_InPlace)
  ReplaceString(a$,Chr(13)," ", #PB_String_InPlace)
  
  While FindString(a$,"  ",0)
    a$=ReplaceString(a$,"  "," ")
  Wend 
  
  Trim(a$)
  If (Len(a$)>0)
    numwords=CountString(a$," ")+1
  Else
    numwords=0
  EndIf
  
  ProcedureReturn numwords 
EndProcedure

Code: Select all

Procedure.i CountWords(a$) ;-Count Words
  
  ReplaceString(a$,Chr(10)," ", #PB_String_InPlace)
  ReplaceString(a$,Chr(13)," ", #PB_String_InPlace)
  
  While FindString(a$,"  ",0)
    a$=ReplaceString(a$,"  "," ")
  Wend 
  
  Trim(a$)
  If (Len(a$)>0)
    numwords=CountString(a$," ")+1
  Else
    numwords=0
  EndIf
  
  ProcedureReturn numwords 
EndProcedure

filename$ = OpenFileRequester("", "", "Text (*.txt)|*.txt;", 1)
If filename$
  ReadFile(1, filename$)
  a$ = ReadString(1, #PB_File_IgnoreEOL)
  CloseFile(1)
EndIf

If a$
  t1 = ElapsedMilliseconds()
  c = CountWords(a$)
  t2 = ElapsedMilliseconds() - t1
  
  MessageRequester("Results", "For file: '" + GetFilePart(f$) +"', found " + c + " words in " + t2 + " ms.")
EndIf

Code: Select all

Procedure.l CountWords(*Text.Character); Requires SSE
  
  ; init some mmx registers
  !mov eax, 1
  !movd mm4, eax        ; mm4 = previous comparison result
  !pxor mm3, mm3        ; mm3 = 0
  !movq mm2, mm4        ; mm2 = counter
  !mov eax, 0x200d0a09
  !movd mm1, eax
  !punpcklbw mm1, mm3   ; mm1 = separation characters (tab, lf, cr, space)
  !movq mm0, mm4        ; mm0 = working register
  
  CompilerIf #PB_Compiler_Processor = #PB_Processor_x64
    !mov rdx, [p.p_Text]
  CompilerElse
    !mov edx, [p.p_Text]
  CompilerEndIf
  !jmp countwords_entry
  
  ; main loop
  !countwords_loop:
  ; compare character with separation chars
  !pshufw mm0, mm5, 0
  !pcmpeqw mm0, mm1
  !psrlw mm0, 15
  !psadbw mm0, mm3
  ; at this time mm0 = 1 if a separation char is found otherwise 0
  !pandn mm4, mm0
  !paddd mm2, mm4
  ; make a copy of the comparison result
  !movq mm4, mm0
  
  ; entry point for first character
  !countwords_entry:
  CompilerIf #PB_Compiler_Unicode
    CompilerIf #PB_Compiler_Processor = #PB_Processor_x64
      !movzx eax, word [rdx]
      !add rdx, 2
    CompilerElse
      !movzx eax, word [edx]
      !add edx, 2
    CompilerEndIf
  CompilerElse
    CompilerIf #PB_Compiler_Processor = #PB_Processor_x64
      !movzx eax, byte [rdx]
      !add rdx, 1
    CompilerElse
      !movzx eax, byte [edx]
      !add edx, 1
    CompilerEndIf
  CompilerEndIf
  !movd mm5, eax
  
  ; loop if not end of string
  !and ax, ax
  !jnz countwords_loop
  
  ; correct counter if last character was a separation character
  !psubd mm2, mm0
  ; set result and empty mmx state
  !movd eax, mm2
  !emms
  ProcedureReturn
  
EndProcedure

Code: Select all

S.s = "This is a test string"
Debug CountWords(@S)

Code: Select all

Procedure.l CountWords(*Text.Character)
    Protected wordCount
    If *Text
        While *text\c
            c.c = *text\c                                                    ; get current character
            If c = #TAB Or c = 32 Or c = #CR Or c = #LF                      ; If current char is TAB, SPACE, CR, LF
                *text + SizeOf(Character)                                    ;     ignore it
                Continue                                                     ;     Continue
            Else                                                             ; Else
                wordCount + 1                                                ;     wordCount + 1
                While c And c <> #TAB And c <> 32 And c <> #CR And c <> #LF  ;     take all characters, except: TAB, SPACE, CR, LF, 0
                    *text + SizeOf(Character)                                ;
                    c.c = *text\c                                            ;
                Wend                                                         ;
            EndIf                                                            ; EndIf
        Wend
    EndIf
    ProcedureReturn wordCount
EndProcedure

S.s = "This is a test string"
S.s + #TAB$+Space(10)+#TAB$+#CRLF$+#TAB$+"a bcd"+#LF$+#LFCR$+#CRLF$+Space(10)
Debug CountWords(@S)