当前页面位置: » 丰搜网 » 文档中心 » 详细内容
在delphi中实现stringtokenizer功能模块
unit skystringtokenizer;
{字符串分析处理类
}
interface
uses
sysutils, classes;
type
iiterator = interface
function hasnext(): boolean;
function next(): string;
end;
type
tskystringtokenizer = class(tcomponent, iiterator)
private
tokens: tstringlist;
index: integer;
data: string;
delimiter: string;
procedure init(dataline: string; delim: string);
function characterintokens(ch: string; const sl: tstringlist): boolean;
function stringtochararray(delim: string): tstringlist;
function splitstring(source, ch: string): tstringlist;
protected
{ protected declarations }
public
{ public declarations }
constructor create(dataline: string); overload;
constructor create(dataline: string; delim: string); overload;
destructor destroy();override;
function hasnext(): boolean;
function next(): string;
published
{ published declarations }
end;
procedure register;
implementation
procedure register;
begin
registercomponents('skydevkit', [tskystringtokenizer]);
end;
{ tstringtokenizer }
function tskystringtokenizer.hasnext: boolean;
begin
result := (index < tokens.count - 1);
end;
procedure tskystringtokenizer.init(dataline, delim: string);
begin
tokens := tstringlist.create();
delimiter := delim;
data := dataline;
tokens := splitstring(data, delimiter);
//tokens := data.split(delimiter.tochararray());
index := -1;
end;
function tskystringtokenizer.next: string;
var
s: string;
begin
inc(index);
s := tokens[index];
while ((length(s) <= 0) and (index < tokens.count)) do
begin
inc(index);
s := tokens[index];
end;
result := s;
end;
function tskystringtokenizer.stringtochararray(delim: string): tstringlist;
var
sl: tstringlist;
i: integer;
begin
sl := tstringlist.create();
for i := 1 to length(delim) do // iterate
begin
sl.append(copy(delim, i, 1));
end; // for
result := sl;
end;
constructor tskystringtokenizer.create(dataline, delim: string);
begin
inherited create(nil);
self.init(dataline, delim);
end;
constructor tskystringtokenizer.create(dataline: string);
begin
inherited create(nil);
self.init(dataline, ' ');
end;
function tskystringtokenizer.splitstring(source, ch: string): tstringlist;
var
temp: string;
//i: integer;
sl: tstringlist;
index: integer;
begin
if ch = '' then
ch := ' ';
sl := tstringlist.create();
result := tstringlist.create();
sl := self.stringtochararray(ch);
temp := '';
for index := 1 to length(source) do // iterate
begin
if not characterintokens(source[index], sl) then
begin
temp := temp + source[index];
end
else
begin
result.add(temp);
temp := '';
end; //if
end; // for
if (temp <> '') then
result.add(temp);
sl.free;
end;
function tskystringtokenizer.characterintokens(ch: string;
const sl: tstringlist): boolean;
var
index: integer;
// i: integer;
begin
result := false;
for index := 0 to sl.count - 1 do // iterate
begin
result := result or (ch = sl[index]);
{if ch = sl[index] then
begin
result := true;
break;
end;
}
end; // for
end;
destructor tskystringtokenizer.destroy;
begin
tokens.free ;
inherited;
end;
end.
//下面是c#版本，最初版本不是我写的
using system;
namespace csharppats
{
//string tokenizer class
public class stringtokenizer {
private string data, delimiter;
private string[] tokens;
private int index;
public stringtokenizer(string dataline) {
init(dataline, " ");
}
private void init(string dataline, string delim) {
delimiter = delim;
data = dataline;
tokens = data.split (delimiter.tochararray() );
index = 0;
}
public stringtokenizer(string dataline, string delim) {
init(dataline, delim);
}
public bool hasmoreelements() {
return (index < (tokens.length));
}
public string nextelement() {
string s = tokens[index++];
while((s.length <=0) && (index<tokens.length ))
s = tokens[index++];
return s;
}
}
}
