Delphi stringlist finding negative keyword in list

I have two string lists that I'm working with. One that has a list of keywords, and then another that has a list of negative keywords. I want to be able to search through the list and pick out the list items that do not contain the negative keyword and output to a third keyword list. I was using the AnsiPos function but that found the negative keywords if they were part of a word, vs full word.

Any suggestions on a relatively easy way to do this? Speed is not that important, but would be nice.

Example of what I'm looking to do:

Keyword List:

Cat 
Catfish
Fish Sticks
Dog Food

Negative Keyword List:

Fish

Returned Values Wanted:

Cat 
Catfish
Dog Food

This is what I've got开发者_运维技巧 so far.. which does not work. I used information from: Is There An Efficient Whole Word Search Function in Delphi?

function ExistWordInString(aString: PAnsichar; aSearchString: string;
  aSearchOptions: TStringSearchOptions): Boolean;
var
  Size : Integer;
begin
  Size := StrLen(aString);
  result := SearchBuf(aString, Size, 0, 0, aSearchString, aSearchOptions) <> nil;
end;

procedure TForm2.Button1Click(Sender: TObject);
var
  i, j, index: integer;
  s: string;
  stl: tstringlist;
begin
  stl := TStringList.Create;
  stl.Text := listbox1.Items.Text;
  for I := 0 to stl.Count - 1 do
  begin
    for j := 0 to listbox2.Count - 1 do
    begin
      if not ExistWordInString(PAnsiChar(listbox2.Items.Strings[j]),
        listbox1.Items.Strings[i], [soWholeWord, soDown])
      then
        listbox3.Items.Append(stl.Strings[i]);
    end;
  end;
end;

---

If spaces are the only word delimiter you need to worry about, then you can do a whole word match using AnsiPos by adding a space before and after both the keyword and the negative keyword, ie

AnsiPos(' '+SubStr+' ', ' '+Str+' ')

You'd need a loop to check every entry from the negative keyword list.

---

this sample code works like a charm (using Delphi 7):

unit Unit1;

interface

uses
  Windows, Messages, SysUtils, Classes, Graphics, Controls, Forms, Dialogs,
  StdCtrls, StrUtils;

type
  TForm1 = class(TForm)
  Button1: TButton;
  ListBox1: TListBox;
  ListBox2: TListBox;
  ListBox3: TListBox;
  procedure Button1Click(Sender: TObject);

  private
     function ExistWordInString(aString, aSearchString:string;aSearchOptions: TStringSearchOptions): Boolean;

  public
  end;

var
  Form1: TForm1;

implementation

{$R *.DFM}

procedure TForm1.Button1Click(Sender: TObject);
var
    i,k: integer;

begin

    for k:= 0 to ListBox2.Count -1 do
        for i:= 0 to ListBox1.Count - 1 do
        begin
            if not ExistWordInString(ListBox1.Items[i], ListBox2.Items[k],[soWholeWord,soDown]) then
                ListBox3.Items.Append(ListBox1.Items[i]);
        end;

end;

function TForm1.ExistWordInString(aString, aSearchString: string; aSearchOptions: TStringSearchOptions): Boolean;
var
  Size : Integer;

begin
        Size:=Length(aString);
        Result := SearchBuf(PChar(aString), Size, 0, 0, aSearchString, aSearchOptions)<>nil;

end;
end.    

and here's the form:

object Form1: TForm1
  Left = 1008
  Top = 398
  Width = 411
  Height = 294
  Caption = 'Form1'
  Color = clBtnFace
  Font.Charset = DEFAULT_CHARSET
  Font.Color = clWindowText
  Font.Height = -11
  Font.Name = 'Tahoma'
  Font.Style = []
  OldCreateOrder = False
  PixelsPerInch = 96
  TextHeight = 13
  object Button1: TButton
    Left = 320
    Top = 8
    Width = 75
    Height = 25
    Caption = 'Button1'
    TabOrder = 0
    OnClick = Button1Click
  end
  object ListBox1: TListBox
    Left = 8
    Top = 8
    Width = 177
    Height = 97
    ItemHeight = 13
    Items.Strings = (
      'Cat '
      'Catfish'
      'Fish Sticks'
      'Dog Food')
    TabOrder = 1
  end
  object ListBox2: TListBox
    Left = 192
    Top = 8
    Width = 121
    Height = 97
    ItemHeight = 13
    Items.Strings = (
      'Fish')
    TabOrder = 2
  end
  object ListBox3: TListBox
    Left = 8
    Top = 112
    Width = 305
    Height = 137
    ItemHeight = 13
    TabOrder = 3
  end
end

hope this helps.

Reinhard :-)

---

I think I figured it out. Use stringlist.find('fish',index);

I didn't figure it out. .find did not work.

-Brad

---

You can use the SearchBuf function (see the pastacool's answer) IF you are not interested in other characters except A..Z / Unicode.

If you have an Unicode Delphi (D2009 or D2010) then you must use TCharacter.IsLetterOrDigit(aString: string; aIndex: integer): boolean; from the Character unit. A simple example for you to get the idea:

procedure TForm7.btn1Click(Sender: TObject);
var
  bMatches: boolean;

begin
  with rgx1 do //custom component - disregard it
  begin
    RegEx:=edtTextToFind.Text; //text to find
    Subject:=mmoResult.Text; //text in which to search
    if Match then //aha! found it!
    begin
      bMatches:=True;
      if chkWholeWord.Checked then //be attentive from here!! - I think that's self explaining...
      begin
        if MatchedExpressionOffset>1 then
          bMatches:=not TCharacter.IsLetterOrDigit(Subject, MatchedExpressionOffset-1);
        if bMatches and (MatchedExpressionOffset+MatchedExpressionLength<=Length(Subject)) then
          bMatches:=not TCharacter.IsLetterOrDigit(Subject, MatchedExpressionOffset+MatchedExpressionLength);
      end;
      if bMatches then //select it in the memo
      begin
        mmoResult.SelStart:=MatchedExpressionOffset-1;
        mmoResult.SelLength:=MatchedExpressionLength;
        mmoResult.SetFocus;
      end
      else
        ShowMessage('Text not found!');
    end
    else
      ShowMessage('Text not found!');
  end;
end;

---

Change your function to read:

function ExistWordInString(aString:PAnsichar;
   aSearchString:string;
   aSearchOptions: TStringSearchOptions): Boolean;
var 
  b : boolean;
begin
  if soWholeWord in aSearchOptions then
    b := Pos(' '+Uppercase(aSearchString)+' ',' '+UpperCase(aString)+' ') > 0;
  else
    b := Pos(UpperCase(aSearchString),UpperCase(aString)) > 0;
  Result := b;
end;

If your using Delphi 2009/2010 then change it from Pos to AnsiPos. My assumption here is that soWholeWord means that the match "Fish" would match "Fish Sticks" but not "catfish".